Dissolved oxygen content prediction in crab culture using a hybrid intelligent method.

PubMed

Yu, Huihui; Chen, Yingyi; Hassan, ShahbazGul; Li, Daoliang

2016-06-08

A precise predictive model is needed to obtain a clear understanding of the changing dissolved oxygen content in outdoor crab ponds, to assess how to reduce risk and to optimize water quality management. The uncertainties in the data from multiple sensors are a significant factor when building a dissolved oxygen content prediction model. To increase prediction accuracy, a new hybrid dissolved oxygen content forecasting model based on the radial basis function neural networks (RBFNN) data fusion method and a least squares support vector machine (LSSVM) with an optimal improved particle swarm optimization(IPSO) is developed. In the modelling process, the RBFNN data fusion method is used to improve information accuracy and provide more trustworthy training samples for the IPSO-LSSVM prediction model. The LSSVM is a powerful tool for achieving nonlinear dissolved oxygen content forecasting. In addition, an improved particle swarm optimization algorithm is developed to determine the optimal parameters for the LSSVM with high accuracy and generalizability. In this study, the comparison of the prediction results of different traditional models validates the effectiveness and accuracy of the proposed hybrid RBFNN-IPSO-LSSVM model for dissolved oxygen content prediction in outdoor crab ponds.

Life History Traits and Niche Instability Impact Accuracy and Temporal Transferability for Historically Calibrated Distribution Models of North American Birds

PubMed Central

Wogan, Guinevere O. U.

2016-01-01

A primary assumption of environmental niche models (ENMs) is that models are both accurate and transferable across geography or time; however, recent work has shown that models may be accurate but not highly transferable. While some of this is due to modeling technique, individual species ecologies may also underlie this phenomenon. Life history traits certainly influence the accuracy of predictive ENMs, but their impact on model transferability is less understood. This study investigated how life history traits influence the predictive accuracy and transferability of ENMs using historically calibrated models for birds. In this study I used historical occurrence and climate data (1950-1990s) to build models for a sample of birds, and then projected them forward to the ‘future’ (1960-1990s). The models were then validated against models generated from occurrence data at that ‘future’ time. Internal and external validation metrics, as well as metrics assessing transferability, and Generalized Linear Models were used to identify life history traits that were significant predictors of accuracy and transferability. This study found that the predictive ability of ENMs differs with regard to life history characteristics such as range, migration, and habitat, and that the rarity versus commonness of a species affects the predicted stability and overlap and hence the transferability of projected models. Projected ENMs with both high accuracy and transferability scores, still sometimes suffered from over- or under- predicted species ranges. Life history traits certainly influenced the accuracy of predictive ENMs for birds, but while aspects of geographic range impact model transferability, the mechanisms underlying this are less understood. PMID:26959979

Selecting Optimal Random Forest Predictive Models: A Case Study on Predicting the Spatial Distribution of Seabed Hardness

PubMed Central

Li, Jin; Tran, Maggie; Siwabessy, Justy

2016-01-01

Spatially continuous predictions of seabed hardness are important baseline environmental information for sustainable management of Australia’s marine jurisdiction. Seabed hardness is often inferred from multibeam backscatter data with unknown accuracy and can be inferred from underwater video footage at limited locations. In this study, we classified the seabed into four classes based on two new seabed hardness classification schemes (i.e., hard90 and hard70). We developed optimal predictive models to predict seabed hardness using random forest (RF) based on the point data of hardness classes and spatially continuous multibeam data. Five feature selection (FS) methods that are variable importance (VI), averaged variable importance (AVI), knowledge informed AVI (KIAVI), Boruta and regularized RF (RRF) were tested based on predictive accuracy. Effects of highly correlated, important and unimportant predictors on the accuracy of RF predictive models were examined. Finally, spatial predictions generated using the most accurate models were visually examined and analysed. This study confirmed that: 1) hard90 and hard70 are effective seabed hardness classification schemes; 2) seabed hardness of four classes can be predicted with a high degree of accuracy; 3) the typical approach used to pre-select predictive variables by excluding highly correlated variables needs to be re-examined; 4) the identification of the important and unimportant predictors provides useful guidelines for further improving predictive models; 5) FS methods select the most accurate predictive model(s) instead of the most parsimonious ones, and AVI and Boruta are recommended for future studies; and 6) RF is an effective modelling method with high predictive accuracy for multi-level categorical data and can be applied to ‘small p and large n’ problems in environmental sciences. Additionally, automated computational programs for AVI need to be developed to increase its computational efficiency and caution should be taken when applying filter FS methods in selecting predictive models. PMID:26890307

Selecting Optimal Random Forest Predictive Models: A Case Study on Predicting the Spatial Distribution of Seabed Hardness.

PubMed

Li, Jin; Tran, Maggie; Siwabessy, Justy

2016-01-01

Spatially continuous predictions of seabed hardness are important baseline environmental information for sustainable management of Australia's marine jurisdiction. Seabed hardness is often inferred from multibeam backscatter data with unknown accuracy and can be inferred from underwater video footage at limited locations. In this study, we classified the seabed into four classes based on two new seabed hardness classification schemes (i.e., hard90 and hard70). We developed optimal predictive models to predict seabed hardness using random forest (RF) based on the point data of hardness classes and spatially continuous multibeam data. Five feature selection (FS) methods that are variable importance (VI), averaged variable importance (AVI), knowledge informed AVI (KIAVI), Boruta and regularized RF (RRF) were tested based on predictive accuracy. Effects of highly correlated, important and unimportant predictors on the accuracy of RF predictive models were examined. Finally, spatial predictions generated using the most accurate models were visually examined and analysed. This study confirmed that: 1) hard90 and hard70 are effective seabed hardness classification schemes; 2) seabed hardness of four classes can be predicted with a high degree of accuracy; 3) the typical approach used to pre-select predictive variables by excluding highly correlated variables needs to be re-examined; 4) the identification of the important and unimportant predictors provides useful guidelines for further improving predictive models; 5) FS methods select the most accurate predictive model(s) instead of the most parsimonious ones, and AVI and Boruta are recommended for future studies; and 6) RF is an effective modelling method with high predictive accuracy for multi-level categorical data and can be applied to 'small p and large n' problems in environmental sciences. Additionally, automated computational programs for AVI need to be developed to increase its computational efficiency and caution should be taken when applying filter FS methods in selecting predictive models.

Development of machine learning models for diagnosis of glaucoma.

PubMed

Kim, Seong Jae; Cho, Kyong Jin; Oh, Sejong

2017-01-01

The study aimed to develop machine learning models that have strong prediction power and interpretability for diagnosis of glaucoma based on retinal nerve fiber layer (RNFL) thickness and visual field (VF). We collected various candidate features from the examination of retinal nerve fiber layer (RNFL) thickness and visual field (VF). We also developed synthesized features from original features. We then selected the best features proper for classification (diagnosis) through feature evaluation. We used 100 cases of data as a test dataset and 399 cases of data as a training and validation dataset. To develop the glaucoma prediction model, we considered four machine learning algorithms: C5.0, random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). We repeatedly composed a learning model using the training dataset and evaluated it by using the validation dataset. Finally, we got the best learning model that produces the highest validation accuracy. We analyzed quality of the models using several measures. The random forest model shows best performance and C5.0, SVM, and KNN models show similar accuracy. In the random forest model, the classification accuracy is 0.98, sensitivity is 0.983, specificity is 0.975, and AUC is 0.979. The developed prediction models show high accuracy, sensitivity, specificity, and AUC in classifying among glaucoma and healthy eyes. It will be used for predicting glaucoma against unknown examination records. Clinicians may reference the prediction results and be able to make better decisions. We may combine multiple learning models to increase prediction accuracy. The C5.0 model includes decision rules for prediction. It can be used to explain the reasons for specific predictions.

Final Technical Report: Increasing Prediction Accuracy.

DOE Office of Scientific and Technical Information (OSTI.GOV)

King, Bruce Hardison; Hansen, Clifford; Stein, Joshua

2015-12-01

PV performance models are used to quantify the value of PV plants in a given location. They combine the performance characteristics of the system, the measured or predicted irradiance and weather at a site, and the system configuration and design into a prediction of the amount of energy that will be produced by a PV system. These predictions must be as accurate as possible in order for finance charges to be minimized. Higher accuracy equals lower project risk. The Increasing Prediction Accuracy project at Sandia focuses on quantifying and reducing uncertainties in PV system performance models.

Application of GA-SVM method with parameter optimization for landslide development prediction

NASA Astrophysics Data System (ADS)

Li, X. Z.; Kong, J. M.

2013-10-01

Prediction of landslide development process is always a hot issue in landslide research. So far, many methods for landslide displacement series prediction have been proposed. Support vector machine (SVM) has been proved to be a novel algorithm with good performance. However, the performance strongly depends on the right selection of the parameters (C and γ) of SVM model. In this study, we presented an application of GA-SVM method with parameter optimization in landslide displacement rate prediction. We selected a typical large-scale landslide in some hydro - electrical engineering area of Southwest China as a case. On the basis of analyzing the basic characteristics and monitoring data of the landslide, a single-factor GA-SVM model and a multi-factor GA-SVM model of the landslide were built. Moreover, the models were compared with single-factor and multi-factor SVM models of the landslide. The results show that, the four models have high prediction accuracies, but the accuracies of GA-SVM models are slightly higher than those of SVM models and the accuracies of multi-factor models are slightly higher than those of single-factor models for the landslide prediction. The accuracy of the multi-factor GA-SVM models is the highest, with the smallest RSME of 0.0009 and the biggest RI of 0.9992.

A Final Approach Trajectory Model for Current Operations

NASA Technical Reports Server (NTRS)

Gong, Chester; Sadovsky, Alexander

2010-01-01

Predicting accurate trajectories with limited intent information is a challenge faced by air traffic management decision support tools in operation today. One such tool is the FAA's Terminal Proximity Alert system which is intended to assist controllers in maintaining safe separation of arrival aircraft during final approach. In an effort to improve the performance of such tools, two final approach trajectory models are proposed; one based on polynomial interpolation, the other on the Fourier transform. These models were tested against actual traffic data and used to study effects of the key final approach trajectory modeling parameters of wind, aircraft type, and weight class, on trajectory prediction accuracy. Using only the limited intent data available to today's ATM system, both the polynomial interpolation and Fourier transform models showed improved trajectory prediction accuracy over a baseline dead reckoning model. Analysis of actual arrival traffic showed that this improved trajectory prediction accuracy leads to improved inter-arrival separation prediction accuracy for longer look ahead times. The difference in mean inter-arrival separation prediction error between the Fourier transform and dead reckoning models was 0.2 nmi for a look ahead time of 120 sec, a 33 percent improvement, with a corresponding 32 percent improvement in standard deviation.

Methods for evaluating the predictive accuracy of structural dynamic models

NASA Technical Reports Server (NTRS)

Hasselman, Timothy K.; Chrostowski, Jon D.

1991-01-01

Modeling uncertainty is defined in terms of the difference between predicted and measured eigenvalues and eigenvectors. Data compiled from 22 sets of analysis/test results was used to create statistical databases for large truss-type space structures and both pretest and posttest models of conventional satellite-type space structures. Modeling uncertainty is propagated through the model to produce intervals of uncertainty on frequency response functions, both amplitude and phase. This methodology was used successfully to evaluate the predictive accuracy of several structures, including the NASA CSI Evolutionary Structure tested at Langley Research Center. Test measurements for this structure were within + one-sigma intervals of predicted accuracy for the most part, demonstrating the validity of the methodology and computer code.

Prediction of Industrial Electric Energy Consumption in Anhui Province Based on GA-BP Neural Network

NASA Astrophysics Data System (ADS)

Zhang, Jiajing; Yin, Guodong; Ni, Youcong; Chen, Jinlan

2018-01-01

In order to improve the prediction accuracy of industrial electrical energy consumption, a prediction model of industrial electrical energy consumption was proposed based on genetic algorithm and neural network. The model use genetic algorithm to optimize the weights and thresholds of BP neural network, and the model is used to predict the energy consumption of industrial power in Anhui Province, to improve the prediction accuracy of industrial electric energy consumption in Anhui province. By comparing experiment of GA-BP prediction model and BP neural network model, the GA-BP model is more accurate with smaller number of neurons in the hidden layer.

A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM2.5 concentration forecasting

NASA Astrophysics Data System (ADS)

Niu, Mingfei; Wang, Yufang; Sun, Shaolong; Li, Yongwu

2016-06-01

To enhance prediction reliability and accuracy, a hybrid model based on the promising principle of "decomposition and ensemble" and a recently proposed meta-heuristic called grey wolf optimizer (GWO) is introduced for daily PM2.5 concentration forecasting. Compared with existing PM2.5 forecasting methods, this proposed model has improved the prediction accuracy and hit rates of directional prediction. The proposed model involves three main steps, i.e., decomposing the original PM2.5 series into several intrinsic mode functions (IMFs) via complementary ensemble empirical mode decomposition (CEEMD) for simplifying the complex data; individually predicting each IMF with support vector regression (SVR) optimized by GWO; integrating all predicted IMFs for the ensemble result as the final prediction by another SVR optimized by GWO. Seven benchmark models, including single artificial intelligence (AI) models, other decomposition-ensemble models with different decomposition methods and models with the same decomposition-ensemble method but optimized by different algorithms, are considered to verify the superiority of the proposed hybrid model. The empirical study indicates that the proposed hybrid decomposition-ensemble model is remarkably superior to all considered benchmark models for its higher prediction accuracy and hit rates of directional prediction.

Improving the prediction of going concern of Taiwanese listed companies using a hybrid of LASSO with data mining techniques.

PubMed

Goo, Yeung-Ja James; Chi, Der-Jang; Shen, Zong-De

2016-01-01

The purpose of this study is to establish rigorous and reliable going concern doubt (GCD) prediction models. This study first uses the least absolute shrinkage and selection operator (LASSO) to select variables and then applies data mining techniques to establish prediction models, such as neural network (NN), classification and regression tree (CART), and support vector machine (SVM). The samples of this study include 48 GCD listed companies and 124 NGCD (non-GCD) listed companies from 2002 to 2013 in the TEJ database. We conduct fivefold cross validation in order to identify the prediction accuracy. According to the empirical results, the prediction accuracy of the LASSO-NN model is 88.96 % (Type I error rate is 12.22 %; Type II error rate is 7.50 %), the prediction accuracy of the LASSO-CART model is 88.75 % (Type I error rate is 13.61 %; Type II error rate is 14.17 %), and the prediction accuracy of the LASSO-SVM model is 89.79 % (Type I error rate is 10.00 %; Type II error rate is 15.83 %).

Genomic Prediction Accounting for Residual Heteroskedasticity

PubMed Central

Ou, Zhining; Tempelman, Robert J.; Steibel, Juan P.; Ernst, Catherine W.; Bates, Ronald O.; Bello, Nora M.

2015-01-01

Whole-genome prediction (WGP) models that use single-nucleotide polymorphism marker information to predict genetic merit of animals and plants typically assume homogeneous residual variance. However, variability is often heterogeneous across agricultural production systems and may subsequently bias WGP-based inferences. This study extends classical WGP models based on normality, heavy-tailed specifications and variable selection to explicitly account for environmentally-driven residual heteroskedasticity under a hierarchical Bayesian mixed-models framework. WGP models assuming homogeneous or heterogeneous residual variances were fitted to training data generated under simulation scenarios reflecting a gradient of increasing heteroskedasticity. Model fit was based on pseudo-Bayes factors and also on prediction accuracy of genomic breeding values computed on a validation data subset one generation removed from the simulated training dataset. Homogeneous vs. heterogeneous residual variance WGP models were also fitted to two quantitative traits, namely 45-min postmortem carcass temperature and loin muscle pH, recorded in a swine resource population dataset prescreened for high and mild residual heteroskedasticity, respectively. Fit of competing WGP models was compared using pseudo-Bayes factors. Predictive ability, defined as the correlation between predicted and observed phenotypes in validation sets of a five-fold cross-validation was also computed. Heteroskedastic error WGP models showed improved model fit and enhanced prediction accuracy compared to homoskedastic error WGP models although the magnitude of the improvement was small (less than two percentage points net gain in prediction accuracy). Nevertheless, accounting for residual heteroskedasticity did improve accuracy of selection, especially on individuals of extreme genetic merit. PMID:26564950

A Real-time Breakdown Prediction Method for Urban Expressway On-ramp Bottlenecks

NASA Astrophysics Data System (ADS)

Ye, Yingjun; Qin, Guoyang; Sun, Jian; Liu, Qiyuan

2018-01-01

Breakdown occurrence on expressway is considered to relate with various factors. Therefore, to investigate the association between breakdowns and these factors, a Bayesian network (BN) model is adopted in this paper. Based on the breakdown events identified at 10 urban expressways on-ramp in Shanghai, China, 23 parameters before breakdowns are extracted, including dynamic environment conditions aggregated with 5-minutes and static geometry features. Different time periods data are used to predict breakdown. Results indicate that the models using 5-10 min data prior to breakdown performs the best prediction, with the prediction accuracies higher than 73%. Moreover, one unified model for all bottlenecks is also built and shows reasonably good prediction performance with the classification accuracy of breakdowns about 75%, at best. Additionally, to simplify the model parameter input, the random forests (RF) model is adopted to identify the key variables. Modeling with the selected 7 parameters, the refined BN model can predict breakdown with adequate accuracy.

Genomic-Enabled Prediction Kernel Models with Random Intercepts for Multi-environment Trials.

PubMed

Cuevas, Jaime; Granato, Italo; Fritsche-Neto, Roberto; Montesinos-Lopez, Osval A; Burgueño, Juan; Bandeira E Sousa, Massaine; Crossa, José

2018-03-28

In this study, we compared the prediction accuracy of the main genotypic effect model (MM) without G×E interactions, the multi-environment single variance G×E deviation model (MDs), and the multi-environment environment-specific variance G×E deviation model (MDe) where the random genetic effects of the lines are modeled with the markers (or pedigree). With the objective of further modeling the genetic residual of the lines, we incorporated the random intercepts of the lines ([Formula: see text]) and generated another three models. Each of these 6 models were fitted with a linear kernel method (Genomic Best Linear Unbiased Predictor, GB) and a Gaussian Kernel (GK) method. We compared these 12 model-method combinations with another two multi-environment G×E interactions models with unstructured variance-covariances (MUC) using GB and GK kernels (4 model-method). Thus, we compared the genomic-enabled prediction accuracy of a total of 16 model-method combinations on two maize data sets with positive phenotypic correlations among environments, and on two wheat data sets with complex G×E that includes some negative and close to zero phenotypic correlations among environments. The two models (MDs and MDE with the random intercept of the lines and the GK method) were computationally efficient and gave high prediction accuracy in the two maize data sets. Regarding the more complex G×E wheat data sets, the prediction accuracy of the model-method combination with G×E, MDs and MDe, including the random intercepts of the lines with GK method had important savings in computing time as compared with the G×E interaction multi-environment models with unstructured variance-covariances but with lower genomic prediction accuracy. Copyright © 2018 Cuevas et al.

Genomic-Enabled Prediction Kernel Models with Random Intercepts for Multi-environment Trials

PubMed Central

Cuevas, Jaime; Granato, Italo; Fritsche-Neto, Roberto; Montesinos-Lopez, Osval A.; Burgueño, Juan; Bandeira e Sousa, Massaine; Crossa, José

2018-01-01

In this study, we compared the prediction accuracy of the main genotypic effect model (MM) without G×E interactions, the multi-environment single variance G×E deviation model (MDs), and the multi-environment environment-specific variance G×E deviation model (MDe) where the random genetic effects of the lines are modeled with the markers (or pedigree). With the objective of further modeling the genetic residual of the lines, we incorporated the random intercepts of the lines (l) and generated another three models. Each of these 6 models were fitted with a linear kernel method (Genomic Best Linear Unbiased Predictor, GB) and a Gaussian Kernel (GK) method. We compared these 12 model-method combinations with another two multi-environment G×E interactions models with unstructured variance-covariances (MUC) using GB and GK kernels (4 model-method). Thus, we compared the genomic-enabled prediction accuracy of a total of 16 model-method combinations on two maize data sets with positive phenotypic correlations among environments, and on two wheat data sets with complex G×E that includes some negative and close to zero phenotypic correlations among environments. The two models (MDs and MDE with the random intercept of the lines and the GK method) were computationally efficient and gave high prediction accuracy in the two maize data sets. Regarding the more complex G×E wheat data sets, the prediction accuracy of the model-method combination with G×E, MDs and MDe, including the random intercepts of the lines with GK method had important savings in computing time as compared with the G×E interaction multi-environment models with unstructured variance-covariances but with lower genomic prediction accuracy. PMID:29476023

Improving Fermi Orbit Determination and Prediction in an Uncertain Atmospheric Drag Environment

NASA Technical Reports Server (NTRS)

Vavrina, Matthew A.; Newman, Clark P.; Slojkowski, Steven E.; Carpenter, J. Russell

2014-01-01

Orbit determination and prediction of the Fermi Gamma-ray Space Telescope trajectory is strongly impacted by the unpredictability and variability of atmospheric density and the spacecraft's ballistic coefficient. Operationally, Global Positioning System point solutions are processed with an extended Kalman filter for orbit determination, and predictions are generated for conjunction assessment with secondary objects. When these predictions are compared to Joint Space Operations Center radar-based solutions, the close approach distance between the two predictions can greatly differ ahead of the conjunction. This work explores strategies for improving prediction accuracy and helps to explain the prediction disparities. Namely, a tuning analysis is performed to determine atmospheric drag modeling and filter parameters that can improve orbit determination as well as prediction accuracy. A 45% improvement in three-day prediction accuracy is realized by tuning the ballistic coefficient and atmospheric density stochastic models, measurement frequency, and other modeling and filter parameters.

Model training across multiple breeding cycles significantly improves genomic prediction accuracy in rye (Secale cereale L.).

PubMed

Auinger, Hans-Jürgen; Schönleben, Manfred; Lehermeier, Christina; Schmidt, Malthe; Korzun, Viktor; Geiger, Hartwig H; Piepho, Hans-Peter; Gordillo, Andres; Wilde, Peer; Bauer, Eva; Schön, Chris-Carolin

2016-11-01

Genomic prediction accuracy can be significantly increased by model calibration across multiple breeding cycles as long as selection cycles are connected by common ancestors. In hybrid rye breeding, application of genome-based prediction is expected to increase selection gain because of long selection cycles in population improvement and development of hybrid components. Essentially two prediction scenarios arise: (1) prediction of the genetic value of lines from the same breeding cycle in which model training is performed and (2) prediction of lines from subsequent cycles. It is the latter from which a reduction in cycle length and consequently the strongest impact on selection gain is expected. We empirically investigated genome-based prediction of grain yield, plant height and thousand kernel weight within and across four selection cycles of a hybrid rye breeding program. Prediction performance was assessed using genomic and pedigree-based best linear unbiased prediction (GBLUP and PBLUP). A total of 1040 S 2 lines were genotyped with 16 k SNPs and each year testcrosses of 260 S 2 lines were phenotyped in seven or eight locations. The performance gap between GBLUP and PBLUP increased significantly for all traits when model calibration was performed on aggregated data from several cycles. Prediction accuracies obtained from cross-validation were in the order of 0.70 for all traits when data from all cycles (N CS  = 832) were used for model training and exceeded within-cycle accuracies in all cases. As long as selection cycles are connected by a sufficient number of common ancestors and prediction accuracy has not reached a plateau when increasing sample size, aggregating data from several preceding cycles is recommended for predicting genetic values in subsequent cycles despite decreasing relatedness over time.

Accuracy Analysis of a Box-wing Theoretical SRP Model

NASA Astrophysics Data System (ADS)

Wang, Xiaoya; Hu, Xiaogong; Zhao, Qunhe; Guo, Rui

2016-07-01

For Beidou satellite navigation system (BDS) a high accuracy SRP model is necessary for high precise applications especially with Global BDS establishment in future. The BDS accuracy for broadcast ephemeris need be improved. So, a box-wing theoretical SRP model with fine structure and adding conical shadow factor of earth and moon were established. We verified this SRP model by the GPS Block IIF satellites. The calculation was done with the data of PRN 1, 24, 25, 27 satellites. The results show that the physical SRP model for POD and forecast for GPS IIF satellite has higher accuracy with respect to Bern empirical model. The 3D-RMS of orbit is about 20 centimeters. The POD accuracy for both models is similar but the prediction accuracy with the physical SRP model is more than doubled. We tested 1-day 3-day and 7-day orbit prediction. The longer is the prediction arc length, the more significant is the improvement. The orbit prediction accuracy with the physical SRP model for 1-day, 3-day and 7-day arc length are 0.4m, 2.0m, 10.0m respectively. But they are 0.9m, 5.5m and 30m with Bern empirical model respectively. We apply this means to the BDS and give out a SRP model for Beidou satellites. Then we test and verify the model with Beidou data of one month only for test. Initial results show the model is good but needs more data for verification and improvement. The orbit residual RMS is similar to that with our empirical force model which only estimate the force for along track, across track direction and y-bias. But the orbit overlap and SLR observation evaluation show some improvement. The remaining empirical force is reduced significantly for present Beidou constellation.

Canopy Temperature and Vegetation Indices from High-Throughput Phenotyping Improve Accuracy of Pedigree and Genomic Selection for Grain Yield in Wheat

PubMed Central

Rutkoski, Jessica; Poland, Jesse; Mondal, Suchismita; Autrique, Enrique; Pérez, Lorena González; Crossa, José; Reynolds, Matthew; Singh, Ravi

2016-01-01

Genomic selection can be applied prior to phenotyping, enabling shorter breeding cycles and greater rates of genetic gain relative to phenotypic selection. Traits measured using high-throughput phenotyping based on proximal or remote sensing could be useful for improving pedigree and genomic prediction model accuracies for traits not yet possible to phenotype directly. We tested if using aerial measurements of canopy temperature, and green and red normalized difference vegetation index as secondary traits in pedigree and genomic best linear unbiased prediction models could increase accuracy for grain yield in wheat, Triticum aestivum L., using 557 lines in five environments. Secondary traits on training and test sets, and grain yield on the training set were modeled as multivariate, and compared to univariate models with grain yield on the training set only. Cross validation accuracies were estimated within and across-environment, with and without replication, and with and without correcting for days to heading. We observed that, within environment, with unreplicated secondary trait data, and without correcting for days to heading, secondary traits increased accuracies for grain yield by 56% in pedigree, and 70% in genomic prediction models, on average. Secondary traits increased accuracy slightly more when replicated, and considerably less when models corrected for days to heading. In across-environment prediction, trends were similar but less consistent. These results show that secondary traits measured in high-throughput could be used in pedigree and genomic prediction to improve accuracy. This approach could improve selection in wheat during early stages if validated in early-generation breeding plots. PMID:27402362

Comparison of Models and Whole-Genome Profiling Approaches for Genomic-Enabled Prediction of Septoria Tritici Blotch, Stagonospora Nodorum Blotch, and Tan Spot Resistance in Wheat.

PubMed

Juliana, Philomin; Singh, Ravi P; Singh, Pawan K; Crossa, Jose; Rutkoski, Jessica E; Poland, Jesse A; Bergstrom, Gary C; Sorrells, Mark E

2017-07-01

The leaf spotting diseases in wheat that include Septoria tritici blotch (STB) caused by , Stagonospora nodorum blotch (SNB) caused by , and tan spot (TS) caused by pose challenges to breeding programs in selecting for resistance. A promising approach that could enable selection prior to phenotyping is genomic selection that uses genome-wide markers to estimate breeding values (BVs) for quantitative traits. To evaluate this approach for seedling and/or adult plant resistance (APR) to STB, SNB, and TS, we compared the predictive ability of least-squares (LS) approach with genomic-enabled prediction models including genomic best linear unbiased predictor (GBLUP), Bayesian ridge regression (BRR), Bayes A (BA), Bayes B (BB), Bayes Cπ (BC), Bayesian least absolute shrinkage and selection operator (BL), and reproducing kernel Hilbert spaces markers (RKHS-M), a pedigree-based model (RKHS-P) and RKHS markers and pedigree (RKHS-MP). We observed that LS gave the lowest prediction accuracies and RKHS-MP, the highest. The genomic-enabled prediction models and RKHS-P gave similar accuracies. The increase in accuracy using genomic prediction models over LS was 48%. The mean genomic prediction accuracies were 0.45 for STB (APR), 0.55 for SNB (seedling), 0.66 for TS (seedling) and 0.48 for TS (APR). We also compared markers from two whole-genome profiling approaches: genotyping by sequencing (GBS) and diversity arrays technology sequencing (DArTseq) for prediction. While, GBS markers performed slightly better than DArTseq, combining markers from the two approaches did not improve accuracies. We conclude that implementing GS in breeding for these diseases would help to achieve higher accuracies and rapid gains from selection. Copyright © 2017 Crop Science Society of America.

Parameter prediction based on Improved Process neural network and ARMA error compensation in Evaporation Process

NASA Astrophysics Data System (ADS)

Qian, Xiaoshan

2018-01-01

The traditional model of evaporation process parameters have continuity and cumulative characteristics of the prediction error larger issues, based on the basis of the process proposed an adaptive particle swarm neural network forecasting method parameters established on the autoregressive moving average (ARMA) error correction procedure compensated prediction model to predict the results of the neural network to improve prediction accuracy. Taking a alumina plant evaporation process to analyze production data validation, and compared with the traditional model, the new model prediction accuracy greatly improved, can be used to predict the dynamic process of evaporation of sodium aluminate solution components.

What is the Best Model Specification and Earth Observation Product for Predicting Regional Grain Yields in Food Insecure Countries?

NASA Astrophysics Data System (ADS)

Davenport, F., IV; Harrison, L.; Shukla, S.; Husak, G. J.; Funk, C. C.

2017-12-01

We evaluate the predictive accuracy of an ensemble of empirical model specifications that use earth observation data to predict sub-national grain yields in Mexico and East Africa. Products that are actively used for seasonal drought monitoring are tested as yield predictors. Our research is driven by the fact that East Africa is a region where decisions regarding agricultural production are critical to preventing the loss of economic livelihoods and human life. Regional grain yield forecasts can be used to anticipate availability and prices of key staples, which can turn can inform decisions about targeting humanitarian response such as food aid. Our objective is to identify-for a given region, grain, and time year- what type of model and/or earth observation can most accurately predict end of season yields. We fit a set of models to county level panel data from Mexico, Kenya, Sudan, South Sudan, and Somalia. We then examine out of sample predicative accuracy using various linear and non-linear models that incorporate spatial and time varying coefficients. We compare accuracy within and across models that use predictor variables from remotely sensed measures of precipitation, temperature, soil moisture, and other land surface processes. We also examine at what point in the season a given model or product is most useful for determining predictive accuracy. Finally we compare predictive accuracy across a variety of agricultural regimes including high intensity irrigated commercial agricultural and rain fed subsistence level farms.

Proposal for a New Predictive Model of Short-Term Mortality After Living Donor Liver Transplantation due to Acute Liver Failure.

PubMed

Chung, Hyun Sik; Lee, Yu Jung; Jo, Yun Sung

2017-02-21

BACKGROUND Acute liver failure (ALF) is known to be a rapidly progressive and fatal disease. Various models which could help to estimate the post-transplant outcome for ALF have been developed; however, none of them have been proved to be the definitive predictive model of accuracy. We suggest a new predictive model, and investigated which model has the highest predictive accuracy for the short-term outcome in patients who underwent living donor liver transplantation (LDLT) due to ALF. MATERIAL AND METHODS Data from a total 88 patients were collected retrospectively. King's College Hospital criteria (KCH), Child-Turcotte-Pugh (CTP) classification, and model for end-stage liver disease (MELD) score were calculated. Univariate analysis was performed, and then multivariate statistical adjustment for preoperative variables of ALF prognosis was performed. A new predictive model was developed, called the MELD conjugated serum phosphorus model (MELD-p). The individual diagnostic accuracy and cut-off value of models in predicting 3-month post-transplant mortality were evaluated using the area under the receiver operating characteristic curve (AUC). The difference in AUC between MELD-p and the other models was analyzed. The diagnostic improvement in MELD-p was assessed using the net reclassification improvement (NRI) and integrated discrimination improvement (IDI). RESULTS The MELD-p and MELD scores had high predictive accuracy (AUC >0.9). KCH and serum phosphorus had an acceptable predictive ability (AUC >0.7). The CTP classification failed to show discriminative accuracy in predicting 3-month post-transplant mortality. The difference in AUC between MELD-p and the other models had statistically significant associations with CTP and KCH. The cut-off value of MELD-p was 3.98 for predicting 3-month post-transplant mortality. The NRI was 9.9% and the IDI was 2.9%. CONCLUSIONS MELD-p score can predict 3-month post-transplant mortality better than other scoring systems after LDLT due to ALF. The recommended cut-off value of MELD-p is 3.98.

The Use of Linear Programming for Prediction.

ERIC Educational Resources Information Center

Schnittjer, Carl J.

The purpose of the study was to develop a linear programming model to be used for prediction, test the accuracy of the predictions, and compare the accuracy with that produced by curvilinear multiple regression analysis. (Author)

Genomic selection models double the accuracy of predicted breeding values for bacterial cold water disease resistance compared to a traditional pedigree-based model in rainbow trout aquaculture.

PubMed

Vallejo, Roger L; Leeds, Timothy D; Gao, Guangtu; Parsons, James E; Martin, Kyle E; Evenhuis, Jason P; Fragomeni, Breno O; Wiens, Gregory D; Palti, Yniv

2017-02-01

Previously, we have shown that bacterial cold water disease (BCWD) resistance in rainbow trout can be improved using traditional family-based selection, but progress has been limited to exploiting only between-family genetic variation. Genomic selection (GS) is a new alternative that enables exploitation of within-family genetic variation. We compared three GS models [single-step genomic best linear unbiased prediction (ssGBLUP), weighted ssGBLUP (wssGBLUP), and BayesB] to predict genomic-enabled breeding values (GEBV) for BCWD resistance in a commercial rainbow trout population, and compared the accuracy of GEBV to traditional estimates of breeding values (EBV) from a pedigree-based BLUP (P-BLUP) model. We also assessed the impact of sampling design on the accuracy of GEBV predictions. For these comparisons, we used BCWD survival phenotypes recorded on 7893 fish from 102 families, of which 1473 fish from 50 families had genotypes [57 K single nucleotide polymorphism (SNP) array]. Naïve siblings of the training fish (n = 930 testing fish) were genotyped to predict their GEBV and mated to produce 138 progeny testing families. In the following generation, 9968 progeny were phenotyped to empirically assess the accuracy of GEBV predictions made on their non-phenotyped parents. The accuracy of GEBV from all tested GS models were substantially higher than the P-BLUP model EBV. The highest increase in accuracy relative to the P-BLUP model was achieved with BayesB (97.2 to 108.8%), followed by wssGBLUP at iteration 2 (94.4 to 97.1%) and 3 (88.9 to 91.2%) and ssGBLUP (83.3 to 85.3%). Reducing the training sample size to n = ~1000 had no negative impact on the accuracy (0.67 to 0.72), but with n = ~500 the accuracy dropped to 0.53 to 0.61 if the training and testing fish were full-sibs, and even substantially lower, to 0.22 to 0.25, when they were not full-sibs. Using progeny performance data, we showed that the accuracy of genomic predictions is substantially higher than estimates obtained from the traditional pedigree-based BLUP model for BCWD resistance. Overall, we found that using a much smaller training sample size compared to similar studies in livestock, GS can substantially improve the selection accuracy and genetic gains for this trait in a commercial rainbow trout breeding population.

Genomic Prediction Accounting for Residual Heteroskedasticity.

PubMed

Ou, Zhining; Tempelman, Robert J; Steibel, Juan P; Ernst, Catherine W; Bates, Ronald O; Bello, Nora M

2015-11-12

Whole-genome prediction (WGP) models that use single-nucleotide polymorphism marker information to predict genetic merit of animals and plants typically assume homogeneous residual variance. However, variability is often heterogeneous across agricultural production systems and may subsequently bias WGP-based inferences. This study extends classical WGP models based on normality, heavy-tailed specifications and variable selection to explicitly account for environmentally-driven residual heteroskedasticity under a hierarchical Bayesian mixed-models framework. WGP models assuming homogeneous or heterogeneous residual variances were fitted to training data generated under simulation scenarios reflecting a gradient of increasing heteroskedasticity. Model fit was based on pseudo-Bayes factors and also on prediction accuracy of genomic breeding values computed on a validation data subset one generation removed from the simulated training dataset. Homogeneous vs. heterogeneous residual variance WGP models were also fitted to two quantitative traits, namely 45-min postmortem carcass temperature and loin muscle pH, recorded in a swine resource population dataset prescreened for high and mild residual heteroskedasticity, respectively. Fit of competing WGP models was compared using pseudo-Bayes factors. Predictive ability, defined as the correlation between predicted and observed phenotypes in validation sets of a five-fold cross-validation was also computed. Heteroskedastic error WGP models showed improved model fit and enhanced prediction accuracy compared to homoskedastic error WGP models although the magnitude of the improvement was small (less than two percentage points net gain in prediction accuracy). Nevertheless, accounting for residual heteroskedasticity did improve accuracy of selection, especially on individuals of extreme genetic merit. Copyright © 2016 Ou et al.

Validation of Models Used to Inform Colorectal Cancer Screening Guidelines: Accuracy and Implications.

PubMed

Rutter, Carolyn M; Knudsen, Amy B; Marsh, Tracey L; Doria-Rose, V Paul; Johnson, Eric; Pabiniak, Chester; Kuntz, Karen M; van Ballegooijen, Marjolein; Zauber, Ann G; Lansdorp-Vogelaar, Iris

2016-07-01

Microsimulation models synthesize evidence about disease processes and interventions, providing a method for predicting long-term benefits and harms of prevention, screening, and treatment strategies. Because models often require assumptions about unobservable processes, assessing a model's predictive accuracy is important. We validated 3 colorectal cancer (CRC) microsimulation models against outcomes from the United Kingdom Flexible Sigmoidoscopy Screening (UKFSS) Trial, a randomized controlled trial that examined the effectiveness of one-time flexible sigmoidoscopy screening to reduce CRC mortality. The models incorporate different assumptions about the time from adenoma initiation to development of preclinical and symptomatic CRC. Analyses compare model predictions to study estimates across a range of outcomes to provide insight into the accuracy of model assumptions. All 3 models accurately predicted the relative reduction in CRC mortality 10 years after screening (predicted hazard ratios, with 95% percentile intervals: 0.56 [0.44, 0.71], 0.63 [0.51, 0.75], 0.68 [0.53, 0.83]; estimated with 95% confidence interval: 0.56 [0.45, 0.69]). Two models with longer average preclinical duration accurately predicted the relative reduction in 10-year CRC incidence. Two models with longer mean sojourn time accurately predicted the number of screen-detected cancers. All 3 models predicted too many proximal adenomas among patients referred to colonoscopy. Model accuracy can only be established through external validation. Analyses such as these are therefore essential for any decision model. Results supported the assumptions that the average time from adenoma initiation to development of preclinical cancer is long (up to 25 years), and mean sojourn time is close to 4 years, suggesting the window for early detection and intervention by screening is relatively long. Variation in dwell time remains uncertain and could have important clinical and policy implications. © The Author(s) 2016.

Evaluation of Data-Driven Models for Predicting Solar Photovoltaics Power Output

DOE PAGES

Moslehi, Salim; Reddy, T. Agami; Katipamula, Srinivas

2017-09-10

This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature.more » The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2% and 8.6% when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the corresponding appropriate modeling pathways have been proposed. The corresponding models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.« less

Artificial neural network modeling using clinical and knowledge independent variables predicts salt intake reduction behavior

PubMed Central

Isma’eel, Hussain A.; Sakr, George E.; Almedawar, Mohamad M.; Fathallah, Jihan; Garabedian, Torkom; Eddine, Savo Bou Zein

2015-01-01

Background High dietary salt intake is directly linked to hypertension and cardiovascular diseases (CVDs). Predicting behaviors regarding salt intake habits is vital to guide interventions and increase their effectiveness. We aim to compare the accuracy of an artificial neural network (ANN) based tool that predicts behavior from key knowledge questions along with clinical data in a high cardiovascular risk cohort relative to the least square models (LSM) method. Methods We collected knowledge, attitude and behavior data on 115 patients. A behavior score was calculated to classify patients’ behavior towards reducing salt intake. Accuracy comparison between ANN and regression analysis was calculated using the bootstrap technique with 200 iterations. Results Starting from a 69-item questionnaire, a reduced model was developed and included eight knowledge items found to result in the highest accuracy of 62% CI (58-67%). The best prediction accuracy in the full and reduced models was attained by ANN at 66% and 62%, respectively, compared to full and reduced LSM at 40% and 34%, respectively. The average relative increase in accuracy over all in the full and reduced models is 82% and 102%, respectively. Conclusions Using ANN modeling, we can predict salt reduction behaviors with 66% accuracy. The statistical model has been implemented in an online calculator and can be used in clinics to estimate the patient’s behavior. This will help implementation in future research to further prove clinical utility of this tool to guide therapeutic salt reduction interventions in high cardiovascular risk individuals. PMID:26090333

Evaluating the accuracy of SHAPE-directed RNA secondary structure predictions

PubMed Central

Sükösd, Zsuzsanna; Swenson, M. Shel; Kjems, Jørgen; Heitsch, Christine E.

2013-01-01

Recent advances in RNA structure determination include using data from high-throughput probing experiments to improve thermodynamic prediction accuracy. We evaluate the extent and nature of improvements in data-directed predictions for a diverse set of 16S/18S ribosomal sequences using a stochastic model of experimental SHAPE data. The average accuracy for 1000 data-directed predictions always improves over the original minimum free energy (MFE) structure. However, the amount of improvement varies with the sequence, exhibiting a correlation with MFE accuracy. Further analysis of this correlation shows that accurate MFE base pairs are typically preserved in a data-directed prediction, whereas inaccurate ones are not. Thus, the positive predictive value of common base pairs is consistently higher than the directed prediction accuracy. Finally, we confirm sequence dependencies in the directability of thermodynamic predictions and investigate the potential for greater accuracy improvements in the worst performing test sequence. PMID:23325843

Analysis of model development strategies: predicting ventral hernia recurrence.

PubMed

Holihan, Julie L; Li, Linda T; Askenasy, Erik P; Greenberg, Jacob A; Keith, Jerrod N; Martindale, Robert G; Roth, J Scott; Liang, Mike K

2016-11-01

There have been many attempts to identify variables associated with ventral hernia recurrence; however, it is unclear which statistical modeling approach results in models with greatest internal and external validity. We aim to assess the predictive accuracy of models developed using five common variable selection strategies to determine variables associated with hernia recurrence. Two multicenter ventral hernia databases were used. Database 1 was randomly split into "development" and "internal validation" cohorts. Database 2 was designated "external validation". The dependent variable for model development was hernia recurrence. Five variable selection strategies were used: (1) "clinical"-variables considered clinically relevant, (2) "selective stepwise"-all variables with a P value <0.20 were assessed in a step-backward model, (3) "liberal stepwise"-all variables were included and step-backward regression was performed, (4) "restrictive internal resampling," and (5) "liberal internal resampling." Variables were included with P < 0.05 for the Restrictive model and P < 0.10 for the Liberal model. A time-to-event analysis using Cox regression was performed using these strategies. The predictive accuracy of the developed models was tested on the internal and external validation cohorts using Harrell's C-statistic where C > 0.70 was considered "reasonable". The recurrence rate was 32.9% (n = 173/526; median/range follow-up, 20/1-58 mo) for the development cohort, 36.0% (n = 95/264, median/range follow-up 20/1-61 mo) for the internal validation cohort, and 12.7% (n = 155/1224, median/range follow-up 9/1-50 mo) for the external validation cohort. Internal validation demonstrated reasonable predictive accuracy (C-statistics = 0.772, 0.760, 0.767, 0.757, 0.763), while on external validation, predictive accuracy dipped precipitously (C-statistic = 0.561, 0.557, 0.562, 0.553, 0.560). Predictive accuracy was equally adequate on internal validation among models; however, on external validation, all five models failed to demonstrate utility. Future studies should report multiple variable selection techniques and demonstrate predictive accuracy on external data sets for model validation. Copyright © 2016 Elsevier Inc. All rights reserved.

Assessing Predictive Properties of Genome-Wide Selection in Soybeans

PubMed Central

Xavier, Alencar; Muir, William M.; Rainey, Katy Martin

2016-01-01

Many economically important traits in plant breeding have low heritability or are difficult to measure. For these traits, genomic selection has attractive features and may boost genetic gains. Our goal was to evaluate alternative scenarios to implement genomic selection for yield components in soybean (Glycine max L. merr). We used a nested association panel with cross validation to evaluate the impacts of training population size, genotyping density, and prediction model on the accuracy of genomic prediction. Our results indicate that training population size was the factor most relevant to improvement in genome-wide prediction, with greatest improvement observed in training sets up to 2000 individuals. We discuss assumptions that influence the choice of the prediction model. Although alternative models had minor impacts on prediction accuracy, the most robust prediction model was the combination of reproducing kernel Hilbert space regression and BayesB. Higher genotyping density marginally improved accuracy. Our study finds that breeding programs seeking efficient genomic selection in soybeans would best allocate resources by investing in a representative training set. PMID:27317786

Bayesian decision support for coding occupational injury data.

PubMed

Nanda, Gaurav; Grattan, Kathleen M; Chu, MyDzung T; Davis, Letitia K; Lehto, Mark R

2016-06-01

Studies on autocoding injury data have found that machine learning algorithms perform well for categories that occur frequently but often struggle with rare categories. Therefore, manual coding, although resource-intensive, cannot be eliminated. We propose a Bayesian decision support system to autocode a large portion of the data, filter cases for manual review, and assist human coders by presenting them top k prediction choices and a confusion matrix of predictions from Bayesian models. We studied the prediction performance of Single-Word (SW) and Two-Word-Sequence (TW) Naïve Bayes models on a sample of data from the 2011 Survey of Occupational Injury and Illness (SOII). We used the agreement in prediction results of SW and TW models, and various prediction strength thresholds for autocoding and filtering cases for manual review. We also studied the sensitivity of the top k predictions of the SW model, TW model, and SW-TW combination, and then compared the accuracy of the manually assigned codes to SOII data with that of the proposed system. The accuracy of the proposed system, assuming well-trained coders reviewing a subset of only 26% of cases flagged for review, was estimated to be comparable (86.5%) to the accuracy of the original coding of the data set (range: 73%-86.8%). Overall, the TW model had higher sensitivity than the SW model, and the accuracy of the prediction results increased when the two models agreed, and for higher prediction strength thresholds. The sensitivity of the top five predictions was 93%. The proposed system seems promising for coding injury data as it offers comparable accuracy and less manual coding. Accurate and timely coded occupational injury data is useful for surveillance as well as prevention activities that aim to make workplaces safer. Copyright © 2016 Elsevier Ltd and National Safety Council. All rights reserved.

Bridge Structure Deformation Prediction Based on GNSS Data Using Kalman-ARIMA-GARCH Model

PubMed Central

Li, Xiaoqing; Wang, Yu

2018-01-01

Bridges are an essential part of the ground transportation system. Health monitoring is fundamentally important for the safety and service life of bridges. A large amount of structural information is obtained from various sensors using sensing technology, and the data processing has become a challenging issue. To improve the prediction accuracy of bridge structure deformation based on data mining and to accurately evaluate the time-varying characteristics of bridge structure performance evolution, this paper proposes a new method for bridge structure deformation prediction, which integrates the Kalman filter, autoregressive integrated moving average model (ARIMA), and generalized autoregressive conditional heteroskedasticity (GARCH). Firstly, the raw deformation data is directly pre-processed using the Kalman filter to reduce the noise. After that, the linear recursive ARIMA model is established to analyze and predict the structure deformation. Finally, the nonlinear recursive GARCH model is introduced to further improve the accuracy of the prediction. Simulation results based on measured sensor data from the Global Navigation Satellite System (GNSS) deformation monitoring system demonstrated that: (1) the Kalman filter is capable of denoising the bridge deformation monitoring data; (2) the prediction accuracy of the proposed Kalman-ARIMA-GARCH model is satisfactory, where the mean absolute error increases only from 3.402 mm to 5.847 mm with the increment of the prediction step; and (3) in comparision to the Kalman-ARIMA model, the Kalman-ARIMA-GARCH model results in superior prediction accuracy as it includes partial nonlinear characteristics (heteroscedasticity); the mean absolute error of five-step prediction using the proposed model is improved by 10.12%. This paper provides a new way for structural behavior prediction based on data processing, which can lay a foundation for the early warning of bridge health monitoring system based on sensor data using sensing technology. PMID:29351254

Bridge Structure Deformation Prediction Based on GNSS Data Using Kalman-ARIMA-GARCH Model.

PubMed

Xin, Jingzhou; Zhou, Jianting; Yang, Simon X; Li, Xiaoqing; Wang, Yu

2018-01-19

Bridges are an essential part of the ground transportation system. Health monitoring is fundamentally important for the safety and service life of bridges. A large amount of structural information is obtained from various sensors using sensing technology, and the data processing has become a challenging issue. To improve the prediction accuracy of bridge structure deformation based on data mining and to accurately evaluate the time-varying characteristics of bridge structure performance evolution, this paper proposes a new method for bridge structure deformation prediction, which integrates the Kalman filter, autoregressive integrated moving average model (ARIMA), and generalized autoregressive conditional heteroskedasticity (GARCH). Firstly, the raw deformation data is directly pre-processed using the Kalman filter to reduce the noise. After that, the linear recursive ARIMA model is established to analyze and predict the structure deformation. Finally, the nonlinear recursive GARCH model is introduced to further improve the accuracy of the prediction. Simulation results based on measured sensor data from the Global Navigation Satellite System (GNSS) deformation monitoring system demonstrated that: (1) the Kalman filter is capable of denoising the bridge deformation monitoring data; (2) the prediction accuracy of the proposed Kalman-ARIMA-GARCH model is satisfactory, where the mean absolute error increases only from 3.402 mm to 5.847 mm with the increment of the prediction step; and (3) in comparision to the Kalman-ARIMA model, the Kalman-ARIMA-GARCH model results in superior prediction accuracy as it includes partial nonlinear characteristics (heteroscedasticity); the mean absolute error of five-step prediction using the proposed model is improved by 10.12%. This paper provides a new way for structural behavior prediction based on data processing, which can lay a foundation for the early warning of bridge health monitoring system based on sensor data using sensing technology.

Genotyping by sequencing for genomic prediction in a soybean breeding population.

PubMed

Jarquín, Diego; Kocak, Kyle; Posadas, Luis; Hyma, Katie; Jedlicka, Joseph; Graef, George; Lorenz, Aaron

2014-08-29

Advances in genotyping technology, such as genotyping by sequencing (GBS), are making genomic prediction more attractive to reduce breeding cycle times and costs associated with phenotyping. Genomic prediction and selection has been studied in several crop species, but no reports exist in soybean. The objectives of this study were (i) evaluate prospects for genomic selection using GBS in a typical soybean breeding program and (ii) evaluate the effect of GBS marker selection and imputation on genomic prediction accuracy. To achieve these objectives, a set of soybean lines sampled from the University of Nebraska Soybean Breeding Program were genotyped using GBS and evaluated for yield and other agronomic traits at multiple Nebraska locations. Genotyping by sequencing scored 16,502 single nucleotide polymorphisms (SNPs) with minor-allele frequency (MAF) > 0.05 and percentage of missing values ≤ 5% on 301 elite soybean breeding lines. When SNPs with up to 80% missing values were included, 52,349 SNPs were scored. Prediction accuracy for grain yield, assessed using cross validation, was estimated to be 0.64, indicating good potential for using genomic selection for grain yield in soybean. Filtering SNPs based on missing data percentage had little to no effect on prediction accuracy, especially when random forest imputation was used to impute missing values. The highest accuracies were observed when random forest imputation was used on all SNPs, but differences were not significant. A standard additive G-BLUP model was robust; modeling additive-by-additive epistasis did not provide any improvement in prediction accuracy. The effect of training population size on accuracy began to plateau around 100, but accuracy steadily climbed until the largest possible size was used in this analysis. Including only SNPs with MAF > 0.30 provided higher accuracies when training populations were smaller. Using GBS for genomic prediction in soybean holds good potential to expedite genetic gain. Our results suggest that standard additive G-BLUP models can be used on unfiltered, imputed GBS data without loss in accuracy.

Impact of fitting dominance and additive effects on accuracy of genomic prediction of breeding values in layers.

PubMed

Heidaritabar, M; Wolc, A; Arango, J; Zeng, J; Settar, P; Fulton, J E; O'Sullivan, N P; Bastiaansen, J W M; Fernando, R L; Garrick, D J; Dekkers, J C M

2016-10-01

Most genomic prediction studies fit only additive effects in models to estimate genomic breeding values (GEBV). However, if dominance genetic effects are an important source of variation for complex traits, accounting for them may improve the accuracy of GEBV. We investigated the effect of fitting dominance and additive effects on the accuracy of GEBV for eight egg production and quality traits in a purebred line of brown layers using pedigree or genomic information (42K single-nucleotide polymorphism (SNP) panel). Phenotypes were corrected for the effect of hatch date. Additive and dominance genetic variances were estimated using genomic-based [genomic best linear unbiased prediction (GBLUP)-REML and BayesC] and pedigree-based (PBLUP-REML) methods. Breeding values were predicted using a model that included both additive and dominance effects and a model that included only additive effects. The reference population consisted of approximately 1800 animals hatched between 2004 and 2009, while approximately 300 young animals hatched in 2010 were used for validation. Accuracy of prediction was computed as the correlation between phenotypes and estimated breeding values of the validation animals divided by the square root of the estimate of heritability in the whole population. The proportion of dominance variance to total phenotypic variance ranged from 0.03 to 0.22 with PBLUP-REML across traits, from 0 to 0.03 with GBLUP-REML and from 0.01 to 0.05 with BayesC. Accuracies of GEBV ranged from 0.28 to 0.60 across traits. Inclusion of dominance effects did not improve the accuracy of GEBV, and differences in their accuracies between genomic-based methods were small (0.01-0.05), with GBLUP-REML yielding higher prediction accuracies than BayesC for egg production, egg colour and yolk weight, while BayesC yielded higher accuracies than GBLUP-REML for the other traits. In conclusion, fitting dominance effects did not impact accuracy of genomic prediction of breeding values in this population. © 2016 Blackwell Verlag GmbH.

Genomic Prediction of Gene Bank Wheat Landraces.

PubMed

Crossa, José; Jarquín, Diego; Franco, Jorge; Pérez-Rodríguez, Paulino; Burgueño, Juan; Saint-Pierre, Carolina; Vikram, Prashant; Sansaloni, Carolina; Petroli, Cesar; Akdemir, Deniz; Sneller, Clay; Reynolds, Matthew; Tattaris, Maria; Payne, Thomas; Guzman, Carlos; Peña, Roberto J; Wenzl, Peter; Singh, Sukhwinder

2016-07-07

This study examines genomic prediction within 8416 Mexican landrace accessions and 2403 Iranian landrace accessions stored in gene banks. The Mexican and Iranian collections were evaluated in separate field trials, including an optimum environment for several traits, and in two separate environments (drought, D and heat, H) for the highly heritable traits, days to heading (DTH), and days to maturity (DTM). Analyses accounting and not accounting for population structure were performed. Genomic prediction models include genotype × environment interaction (G × E). Two alternative prediction strategies were studied: (1) random cross-validation of the data in 20% training (TRN) and 80% testing (TST) (TRN20-TST80) sets, and (2) two types of core sets, "diversity" and "prediction", including 10% and 20%, respectively, of the total collections. Accounting for population structure decreased prediction accuracy by 15-20% as compared to prediction accuracy obtained when not accounting for population structure. Accounting for population structure gave prediction accuracies for traits evaluated in one environment for TRN20-TST80 that ranged from 0.407 to 0.677 for Mexican landraces, and from 0.166 to 0.662 for Iranian landraces. Prediction accuracy of the 20% diversity core set was similar to accuracies obtained for TRN20-TST80, ranging from 0.412 to 0.654 for Mexican landraces, and from 0.182 to 0.647 for Iranian landraces. The predictive core set gave similar prediction accuracy as the diversity core set for Mexican collections, but slightly lower for Iranian collections. Prediction accuracy when incorporating G × E for DTH and DTM for Mexican landraces for TRN20-TST80 was around 0.60, which is greater than without the G × E term. For Iranian landraces, accuracies were 0.55 for the G × E model with TRN20-TST80. Results show promising prediction accuracies for potential use in germplasm enhancement and rapid introgression of exotic germplasm into elite materials. Copyright © 2016 Crossa et al.

Adaptive time-variant models for fuzzy-time-series forecasting.

PubMed

Wong, Wai-Keung; Bai, Enjian; Chu, Alice Wai-Ching

2010-12-01

A fuzzy time series has been applied to the prediction of enrollment, temperature, stock indices, and other domains. Related studies mainly focus on three factors, namely, the partition of discourse, the content of forecasting rules, and the methods of defuzzification, all of which greatly influence the prediction accuracy of forecasting models. These studies use fixed analysis window sizes for forecasting. In this paper, an adaptive time-variant fuzzy-time-series forecasting model (ATVF) is proposed to improve forecasting accuracy. The proposed model automatically adapts the analysis window size of fuzzy time series based on the prediction accuracy in the training phase and uses heuristic rules to generate forecasting values in the testing phase. The performance of the ATVF model is tested using both simulated and actual time series including the enrollments at the University of Alabama, Tuscaloosa, and the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX). The experiment results show that the proposed ATVF model achieves a significant improvement in forecasting accuracy as compared to other fuzzy-time-series forecasting models.

Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network

PubMed Central

Chiu, Herng-Chia; Ho, Te-Wei; Lee, King-Teh; Chen, Hong-Yaw; Ho, Wen-Hsien

2013-01-01

The aim of this present study is firstly to compare significant predictors of mortality for hepatocellular carcinoma (HCC) patients undergoing resection between artificial neural network (ANN) and logistic regression (LR) models and secondly to evaluate the predictive accuracy of ANN and LR in different survival year estimation models. We constructed a prognostic model for 434 patients with 21 potential input variables by Cox regression model. Model performance was measured by numbers of significant predictors and predictive accuracy. The results indicated that ANN had double to triple numbers of significant predictors at 1-, 3-, and 5-year survival models as compared with LR models. Scores of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) of 1-, 3-, and 5-year survival estimation models using ANN were superior to those of LR in all the training sets and most of the validation sets. The study demonstrated that ANN not only had a great number of predictors of mortality variables but also provided accurate prediction, as compared with conventional methods. It is suggested that physicians consider using data mining methods as supplemental tools for clinical decision-making and prognostic evaluation. PMID:23737707

Hydrometeorological model for streamflow prediction

USGS Publications Warehouse

Tangborn, Wendell V.

1979-01-01

The hydrometeorological model described in this manual was developed to predict seasonal streamflow from water in storage in a basin using streamflow and precipitation data. The model, as described, applies specifically to the Skokomish, Nisqually, and Cowlitz Rivers, in Washington State, and more generally to streams in other regions that derive seasonal runoff from melting snow. Thus the techniques demonstrated for these three drainage basins can be used as a guide for applying this method to other streams. Input to the computer program consists of daily averages of gaged runoff of these streams, and daily values of precipitation collected at Longmire, Kid Valley, and Cushman Dam. Predictions are based on estimates of the absolute storage of water, predominately as snow: storage is approximately equal to basin precipitation less observed runoff. A pre-forecast test season is used to revise the storage estimate and improve the prediction accuracy. To obtain maximum prediction accuracy for operational applications with this model , a systematic evaluation of several hydrologic and meteorologic variables is first necessary. Six input options to the computer program that control prediction accuracy are developed and demonstrated. Predictions of streamflow can be made at any time and for any length of season, although accuracy is usually poor for early-season predictions (before December 1) or for short seasons (less than 15 days). The coefficient of prediction (CP), the chief measure of accuracy used in this manual, approaches zero during the late autumn and early winter seasons and reaches a maximum of about 0.85 during the spring snowmelt season. (Kosco-USGS)

DOE Office of Scientific and Technical Information (OSTI.GOV)

Moslehi, Salim; Reddy, T. Agami; Katipamula, Srinivas

This research was undertaken to evaluate different inverse models for predicting power output of solar photovoltaic (PV) systems under different practical scenarios. In particular, we have investigated whether PV power output prediction accuracy can be improved if module/cell temperature was measured in addition to climatic variables, and also the extent to which prediction accuracy degrades if solar irradiation is not measured on the plane of array but only on a horizontal surface. We have also investigated the significance of different independent or regressor variables, such as wind velocity and incident angle modifier in predicting PV power output and cell temperature.more » The inverse regression model forms have been evaluated both in terms of their goodness-of-fit, and their accuracy and robustness in terms of their predictive performance. Given the accuracy of the measurements, expected CV-RMSE of hourly power output prediction over the year varies between 3.2% and 8.6% when only climatic data are used. Depending on what type of measured climatic and PV performance data is available, different scenarios have been identified and the corresponding appropriate modeling pathways have been proposed. The corresponding models are to be implemented on a controller platform for optimum operational planning of microgrids and integrated energy systems.« less

High accuracy satellite drag model (HASDM)

NASA Astrophysics Data System (ADS)

Storz, M.; Bowman, B.; Branson, J.

The dominant error source in the force models used to predict low perigee satellite trajectories is atmospheric drag. Errors in operational thermospheric density models cause significant errors in predicted satellite positions, since these models do not account for dynamic changes in atmospheric drag for orbit predictions. The Air Force Space Battlelab's High Accuracy Satellite Drag Model (HASDM) estimates and predicts (out three days) a dynamically varying high-resolution density field. HASDM includes the Dynamic Calibration Atmosphere (DCA) algorithm that solves for the phases and amplitudes of the diurnal, semidiurnal and terdiurnal variations of thermospheric density near real-time from the observed drag effects on a set of Low Earth Orbit (LEO) calibration satellites. The density correction is expressed as a function of latitude, local solar time and altitude. In HASDM, a time series prediction filter relates the extreme ultraviolet (EUV) energy index E10.7 and the geomagnetic storm index a p to the DCA density correction parameters. The E10.7 index is generated by the SOLAR2000 model, the first full spectrum model of solar irradiance. The estimated and predicted density fields will be used operationally to significantly improve the accuracy of predicted trajectories for all low perigee satellites.

High accuracy satellite drag model (HASDM)

NASA Astrophysics Data System (ADS)

Storz, Mark F.; Bowman, Bruce R.; Branson, Major James I.; Casali, Stephen J.; Tobiska, W. Kent

The dominant error source in force models used to predict low-perigee satellite trajectories is atmospheric drag. Errors in operational thermospheric density models cause significant errors in predicted satellite positions, since these models do not account for dynamic changes in atmospheric drag for orbit predictions. The Air Force Space Battlelab's High Accuracy Satellite Drag Model (HASDM) estimates and predicts (out three days) a dynamically varying global density field. HASDM includes the Dynamic Calibration Atmosphere (DCA) algorithm that solves for the phases and amplitudes of the diurnal and semidiurnal variations of thermospheric density near real-time from the observed drag effects on a set of Low Earth Orbit (LEO) calibration satellites. The density correction is expressed as a function of latitude, local solar time and altitude. In HASDM, a time series prediction filter relates the extreme ultraviolet (EUV) energy index E10.7 and the geomagnetic storm index ap, to the DCA density correction parameters. The E10.7 index is generated by the SOLAR2000 model, the first full spectrum model of solar irradiance. The estimated and predicted density fields will be used operationally to significantly improve the accuracy of predicted trajectories for all low-perigee satellites.

Orbit Determination for the Lunar Reconnaissance Orbiter Using an Extended Kalman Filter

NASA Technical Reports Server (NTRS)

Slojkowski, Steven; Lowe, Jonathan; Woodburn, James

2015-01-01

Orbit determination (OD) analysis results are presented for the Lunar Reconnaissance Orbiter (LRO) using a commercially available Extended Kalman Filter, Analytical Graphics' Orbit Determination Tool Kit (ODTK). Process noise models for lunar gravity and solar radiation pressure (SRP) are described and OD results employing the models are presented. Definitive accuracy using ODTK meets mission requirements and is better than that achieved using the operational LRO OD tool, the Goddard Trajectory Determination System (GTDS). Results demonstrate that a Vasicek stochastic model produces better estimates of the coefficient of solar radiation pressure than a Gauss-Markov model, and prediction accuracy using a Vasicek model meets mission requirements over the analysis span. Modeling the effect of antenna motion on range-rate tracking considerably improves residuals and filter-smoother consistency. Inclusion of off-axis SRP process noise and generalized process noise improves filter performance for both definitive and predicted accuracy. Definitive accuracy from the smoother is better than achieved using GTDS and is close to that achieved by precision OD methods used to generate definitive science orbits. Use of a multi-plate dynamic spacecraft area model with ODTK's force model plugin capability provides additional improvements in predicted accuracy.

Comparison and validation of statistical methods for predicting power outage durations in the event of hurricanes.

PubMed

Nateghi, Roshanak; Guikema, Seth D; Quiring, Steven M

2011-12-01

This article compares statistical methods for modeling power outage durations during hurricanes and examines the predictive accuracy of these methods. Being able to make accurate predictions of power outage durations is valuable because the information can be used by utility companies to plan their restoration efforts more efficiently. This information can also help inform customers and public agencies of the expected outage times, enabling better collective response planning, and coordination of restoration efforts for other critical infrastructures that depend on electricity. In the long run, outage duration estimates for future storm scenarios may help utilities and public agencies better allocate risk management resources to balance the disruption from hurricanes with the cost of hardening power systems. We compare the out-of-sample predictive accuracy of five distinct statistical models for estimating power outage duration times caused by Hurricane Ivan in 2004. The methods compared include both regression models (accelerated failure time (AFT) and Cox proportional hazard models (Cox PH)) and data mining techniques (regression trees, Bayesian additive regression trees (BART), and multivariate additive regression splines). We then validate our models against two other hurricanes. Our results indicate that BART yields the best prediction accuracy and that it is possible to predict outage durations with reasonable accuracy. © 2011 Society for Risk Analysis.

Semi-supervised learning for genomic prediction of novel traits with small reference populations: an application to residual feed intake in dairy cattle.

PubMed

Yao, Chen; Zhu, Xiaojin; Weigel, Kent A

2016-11-07

Genomic prediction for novel traits, which can be costly and labor-intensive to measure, is often hampered by low accuracy due to the limited size of the reference population. As an option to improve prediction accuracy, we introduced a semi-supervised learning strategy known as the self-training model, and applied this method to genomic prediction of residual feed intake (RFI) in dairy cattle. We describe a self-training model that is wrapped around a support vector machine (SVM) algorithm, which enables it to use data from animals with and without measured phenotypes. Initially, a SVM model was trained using data from 792 animals with measured RFI phenotypes. Then, the resulting SVM was used to generate self-trained phenotypes for 3000 animals for which RFI measurements were not available. Finally, the SVM model was re-trained using data from up to 3792 animals, including those with measured and self-trained RFI phenotypes. Incorporation of additional animals with self-trained phenotypes enhanced the accuracy of genomic predictions compared to that of predictions that were derived from the subset of animals with measured phenotypes. The optimal ratio of animals with self-trained phenotypes to animals with measured phenotypes (2.5, 2.0, and 1.8) and the maximum increase achieved in prediction accuracy measured as the correlation between predicted and actual RFI phenotypes (5.9, 4.1, and 2.4%) decreased as the size of the initial training set (300, 400, and 500 animals with measured phenotypes) increased. The optimal number of animals with self-trained phenotypes may be smaller when prediction accuracy is measured as the mean squared error rather than the correlation between predicted and actual RFI phenotypes. Our results demonstrate that semi-supervised learning models that incorporate self-trained phenotypes can achieve genomic prediction accuracies that are comparable to those obtained with models using larger training sets that include only animals with measured phenotypes. Semi-supervised learning can be helpful for genomic prediction of novel traits, such as RFI, for which the size of reference population is limited, in particular, when the animals to be predicted and the animals in the reference population originate from the same herd-environment.

Analysis of near infrared spectra for age-grading of wild populations of Anopheles gambiae.

PubMed

Krajacich, Benjamin J; Meyers, Jacob I; Alout, Haoues; Dabiré, Roch K; Dowell, Floyd E; Foy, Brian D

2017-11-07

Understanding the age-structure of mosquito populations, especially malaria vectors such as Anopheles gambiae, is important for assessing the risk of infectious mosquitoes, and how vector control interventions may impact this risk. The use of near-infrared spectroscopy (NIRS) for age-grading has been demonstrated previously on laboratory and semi-field mosquitoes, but to date has not been utilized on wild-caught mosquitoes whose age is externally validated via parity status or parasite infection stage. In this study, we developed regression and classification models using NIRS on datasets of wild An. gambiae (s.l.) reared from larvae collected from the field in Burkina Faso, and two laboratory strains. We compared the accuracy of these models for predicting the ages of wild-caught mosquitoes that had been scored for their parity status as well as for positivity for Plasmodium sporozoites. Regression models utilizing variable selection increased predictive accuracy over the more common full-spectrum partial least squares (PLS) approach for cross-validation of the datasets, validation, and independent test sets. Models produced from datasets that included the greatest range of mosquito samples (i.e. different sampling locations and times) had the highest predictive accuracy on independent testing sets, though overall accuracy on these samples was low. For classification, we found that intramodel accuracy ranged between 73.5-97.0% for grouping of mosquitoes into "early" and "late" age classes, with the highest prediction accuracy found in laboratory colonized mosquitoes. However, this accuracy was decreased on test sets, with the highest classification of an independent set of wild-caught larvae reared to set ages being 69.6%. Variation in NIRS data, likely from dietary, genetic, and other factors limits the accuracy of this technique with wild-caught mosquitoes. Alternative algorithms may help improve prediction accuracy, but care should be taken to either maximize variety in models or minimize confounders.

Genomic Prediction of Gene Bank Wheat Landraces

PubMed Central

Crossa, José; Jarquín, Diego; Franco, Jorge; Pérez-Rodríguez, Paulino; Burgueño, Juan; Saint-Pierre, Carolina; Vikram, Prashant; Sansaloni, Carolina; Petroli, Cesar; Akdemir, Deniz; Sneller, Clay; Reynolds, Matthew; Tattaris, Maria; Payne, Thomas; Guzman, Carlos; Peña, Roberto J.; Wenzl, Peter; Singh, Sukhwinder

2016-01-01

This study examines genomic prediction within 8416 Mexican landrace accessions and 2403 Iranian landrace accessions stored in gene banks. The Mexican and Iranian collections were evaluated in separate field trials, including an optimum environment for several traits, and in two separate environments (drought, D and heat, H) for the highly heritable traits, days to heading (DTH), and days to maturity (DTM). Analyses accounting and not accounting for population structure were performed. Genomic prediction models include genotype × environment interaction (G × E). Two alternative prediction strategies were studied: (1) random cross-validation of the data in 20% training (TRN) and 80% testing (TST) (TRN20-TST80) sets, and (2) two types of core sets, “diversity” and “prediction”, including 10% and 20%, respectively, of the total collections. Accounting for population structure decreased prediction accuracy by 15–20% as compared to prediction accuracy obtained when not accounting for population structure. Accounting for population structure gave prediction accuracies for traits evaluated in one environment for TRN20-TST80 that ranged from 0.407 to 0.677 for Mexican landraces, and from 0.166 to 0.662 for Iranian landraces. Prediction accuracy of the 20% diversity core set was similar to accuracies obtained for TRN20-TST80, ranging from 0.412 to 0.654 for Mexican landraces, and from 0.182 to 0.647 for Iranian landraces. The predictive core set gave similar prediction accuracy as the diversity core set for Mexican collections, but slightly lower for Iranian collections. Prediction accuracy when incorporating G × E for DTH and DTM for Mexican landraces for TRN20-TST80 was around 0.60, which is greater than without the G × E term. For Iranian landraces, accuracies were 0.55 for the G × E model with TRN20-TST80. Results show promising prediction accuracies for potential use in germplasm enhancement and rapid introgression of exotic germplasm into elite materials. PMID:27172218

Predicting School Enrollments Using the Modified Regression Technique.

ERIC Educational Resources Information Center

Grip, Richard S.; Young, John W.

This report is based on a study in which a regression model was constructed to increase accuracy in enrollment predictions. A model, known as the Modified Regression Technique (MRT), was used to examine K-12 enrollment over the past 20 years in 2 New Jersey school districts of similar size and ethnicity. To test the model's accuracy, MRT was…

Correlation of ground tests and analyses of a dynamically scaled Space Station model configuration

NASA Technical Reports Server (NTRS)

Javeed, Mehzad; Edighoffer, Harold H.; Mcgowan, Paul E.

1993-01-01

Verification of analytical models through correlation with ground test results of a complex space truss structure is demonstrated. A multi-component, dynamically scaled space station model configuration is the focus structure for this work. Previously established test/analysis correlation procedures are used to develop improved component analytical models. Integrated system analytical models, consisting of updated component analytical models, are compared with modal test results to establish the accuracy of system-level dynamic predictions. Design sensitivity model updating methods are shown to be effective for providing improved component analytical models. Also, the effects of component model accuracy and interface modeling fidelity on the accuracy of integrated model predictions is examined.

Genomic prediction based on data from three layer lines using non-linear regression models.

PubMed

Huang, Heyun; Windig, Jack J; Vereijken, Addie; Calus, Mario P L

2014-11-06

Most studies on genomic prediction with reference populations that include multiple lines or breeds have used linear models. Data heterogeneity due to using multiple populations may conflict with model assumptions used in linear regression methods. In an attempt to alleviate potential discrepancies between assumptions of linear models and multi-population data, two types of alternative models were used: (1) a multi-trait genomic best linear unbiased prediction (GBLUP) model that modelled trait by line combinations as separate but correlated traits and (2) non-linear models based on kernel learning. These models were compared to conventional linear models for genomic prediction for two lines of brown layer hens (B1 and B2) and one line of white hens (W1). The three lines each had 1004 to 1023 training and 238 to 240 validation animals. Prediction accuracy was evaluated by estimating the correlation between observed phenotypes and predicted breeding values. When the training dataset included only data from the evaluated line, non-linear models yielded at best a similar accuracy as linear models. In some cases, when adding a distantly related line, the linear models showed a slight decrease in performance, while non-linear models generally showed no change in accuracy. When only information from a closely related line was used for training, linear models and non-linear radial basis function (RBF) kernel models performed similarly. The multi-trait GBLUP model took advantage of the estimated genetic correlations between the lines. Combining linear and non-linear models improved the accuracy of multi-line genomic prediction. Linear models and non-linear RBF models performed very similarly for genomic prediction, despite the expectation that non-linear models could deal better with the heterogeneous multi-population data. This heterogeneity of the data can be overcome by modelling trait by line combinations as separate but correlated traits, which avoids the occasional occurrence of large negative accuracies when the evaluated line was not included in the training dataset. Furthermore, when using a multi-line training dataset, non-linear models provided information on the genotype data that was complementary to the linear models, which indicates that the underlying data distributions of the three studied lines were indeed heterogeneous.

A Multicriteria Approach to Find Predictive and Sparse Models with Stable Feature Selection for High-Dimensional Data.

PubMed

Bommert, Andrea; Rahnenführer, Jörg; Lang, Michel

2017-01-01

Finding a good predictive model for a high-dimensional data set can be challenging. For genetic data, it is not only important to find a model with high predictive accuracy, but it is also important that this model uses only few features and that the selection of these features is stable. This is because, in bioinformatics, the models are used not only for prediction but also for drawing biological conclusions which makes the interpretability and reliability of the model crucial. We suggest using three target criteria when fitting a predictive model to a high-dimensional data set: the classification accuracy, the stability of the feature selection, and the number of chosen features. As it is unclear which measure is best for evaluating the stability, we first compare a variety of stability measures. We conclude that the Pearson correlation has the best theoretical and empirical properties. Also, we find that for the stability assessment behaviour it is most important that a measure contains a correction for chance or large numbers of chosen features. Then, we analyse Pareto fronts and conclude that it is possible to find models with a stable selection of few features without losing much predictive accuracy.

A signal detection model predicts the effects of set size on visual search accuracy for feature, conjunction, triple conjunction, and disjunction displays

NASA Technical Reports Server (NTRS)

Eckstein, M. P.; Thomas, J. P.; Palmer, J.; Shimozaki, S. S.

2000-01-01

Recently, quantitative models based on signal detection theory have been successfully applied to the prediction of human accuracy in visual search for a target that differs from distractors along a single attribute (feature search). The present paper extends these models for visual search accuracy to multidimensional search displays in which the target differs from the distractors along more than one feature dimension (conjunction, disjunction, and triple conjunction displays). The model assumes that each element in the display elicits a noisy representation for each of the relevant feature dimensions. The observer combines the representations across feature dimensions to obtain a single decision variable, and the stimulus with the maximum value determines the response. The model accurately predicts human experimental data on visual search accuracy in conjunctions and disjunctions of contrast and orientation. The model accounts for performance degradation without resorting to a limited-capacity spatially localized and temporally serial mechanism by which to bind information across feature dimensions.

Prediction of heterosis using genome-wide SNP-marker data: application to egg production traits in white Leghorn crosses.

PubMed

Amuzu-Aweh, E N; Bijma, P; Kinghorn, B P; Vereijken, A; Visscher, J; van Arendonk, J Am; Bovenhuis, H

2013-12-01

Prediction of heterosis has a long history with mixed success, partly due to low numbers of genetic markers and/or small data sets. We investigated the prediction of heterosis for egg number, egg weight and survival days in domestic white Leghorns, using ∼400 000 individuals from 47 crosses and allele frequencies on ∼53 000 genome-wide single nucleotide polymorphisms (SNPs). When heterosis is due to dominance, and dominance effects are independent of allele frequencies, heterosis is proportional to the squared difference in allele frequency (SDAF) between parental pure lines (not necessarily homozygous). Under these assumptions, a linear model including regression on SDAF partitions crossbred phenotypes into pure-line values and heterosis, even without pure-line phenotypes. We therefore used models where phenotypes of crossbreds were regressed on the SDAF between parental lines. Accuracy of prediction was determined using leave-one-out cross-validation. SDAF predicted heterosis for egg number and weight with an accuracy of ∼0.5, but did not predict heterosis for survival days. Heterosis predictions allowed preselection of pure lines before field-testing, saving ∼50% of field-testing cost with only 4% loss in heterosis. Accuracies from cross-validation were lower than from the model-fit, suggesting that accuracies previously reported in literature are overestimated. Cross-validation also indicated that dominance cannot fully explain heterosis. Nevertheless, the dominance model had considerable accuracy, clearly greater than that of a general/specific combining ability model. This work also showed that heterosis can be modelled even when pure-line phenotypes are unavailable. We concluded that SDAF is a useful predictor of heterosis in commercial layer breeding.

Prospects for Genomic Selection in Cassava Breeding.

PubMed

Wolfe, Marnin D; Del Carpio, Dunia Pino; Alabi, Olumide; Ezenwaka, Lydia C; Ikeogu, Ugochukwu N; Kayondo, Ismail S; Lozano, Roberto; Okeke, Uche G; Ozimati, Alfred A; Williams, Esuma; Egesi, Chiedozie; Kawuki, Robert S; Kulakow, Peter; Rabbi, Ismail Y; Jannink, Jean-Luc

2017-11-01

Cassava ( Crantz) is a clonally propagated staple food crop in the tropics. Genomic selection (GS) has been implemented at three breeding institutions in Africa to reduce cycle times. Initial studies provided promising estimates of predictive abilities. Here, we expand on previous analyses by assessing the accuracy of seven prediction models for seven traits in three prediction scenarios: cross-validation within populations, cross-population prediction and cross-generation prediction. We also evaluated the impact of increasing the training population (TP) size by phenotyping progenies selected either at random or with a genetic algorithm. Cross-validation results were mostly consistent across programs, with nonadditive models predicting of 10% better on average. Cross-population accuracy was generally low (mean = 0.18) but prediction of cassava mosaic disease increased up to 57% in one Nigerian population when data from another related population were combined. Accuracy across generations was poorer than within-generation accuracy, as expected, but accuracy for dry matter content and mosaic disease severity should be sufficient for rapid-cycling GS. Selection of a prediction model made some difference across generations, but increasing TP size was more important. With a genetic algorithm, selection of one-third of progeny could achieve an accuracy equivalent to phenotyping all progeny. We are in the early stages of GS for this crop but the results are promising for some traits. General guidelines that are emerging are that TPs need to continue to grow but phenotyping can be done on a cleverly selected subset of individuals, reducing the overall phenotyping burden. Copyright © 2017 Crop Science Society of America.

Feasibility of developing LSI microcircuit reliability prediction models

NASA Technical Reports Server (NTRS)

Ryerson, C. M.

1972-01-01

In the proposed modeling approach, when any of the essential key factors are not known initially, they can be approximated in various ways with a known impact on the accuracy of the final predictions. For example, on any program where reliability predictions are started at interim states of project completion, a-priori approximate estimates of the key factors are established for making preliminary predictions. Later these are refined for greater accuracy as subsequent program information of a more definitive nature becomes available. Specific steps to develop, validate and verify these new models are described.

Evaluation of a habitat capability model for nongame birds in the Black Hills, South Dakota

Treesearch

Todd R. Mills; Mark A. Rumble; Lester D. Flake

1996-01-01

Habitat models, used to predict consequences of land management decisions on wildlife, can have considerable economic effect on management decisions. The Black Hills National Forest uses such a habitat capability model (HABCAP), but its accuracy is largely unknown. We tested this model’s predictive accuracy for nongame birds in 13 vegetative structural stages of...

Improving accuracies of genomic predictions for drought tolerance in maize by joint modeling of additive and dominance effects in multi-environment trials.

PubMed

Dias, Kaio Olímpio Das Graças; Gezan, Salvador Alejandro; Guimarães, Claudia Teixeira; Nazarian, Alireza; da Costa E Silva, Luciano; Parentoni, Sidney Netto; de Oliveira Guimarães, Paulo Evaristo; de Oliveira Anoni, Carina; Pádua, José Maria Villela; de Oliveira Pinto, Marcos; Noda, Roberto Willians; Ribeiro, Carlos Alexandre Gomes; de Magalhães, Jurandir Vieira; Garcia, Antonio Augusto Franco; de Souza, João Cândido; Guimarães, Lauro José Moreira; Pastina, Maria Marta

2018-07-01

Breeding for drought tolerance is a challenging task that requires costly, extensive, and precise phenotyping. Genomic selection (GS) can be used to maximize selection efficiency and the genetic gains in maize (Zea mays L.) breeding programs for drought tolerance. Here, we evaluated the accuracy of genomic selection (GS) using additive (A) and additive + dominance (AD) models to predict the performance of untested maize single-cross hybrids for drought tolerance in multi-environment trials. Phenotypic data of five drought tolerance traits were measured in 308 hybrids along eight trials under water-stressed (WS) and well-watered (WW) conditions over two years and two locations in Brazil. Hybrids' genotypes were inferred based on their parents' genotypes (inbred lines) using single-nucleotide polymorphism markers obtained via genotyping-by-sequencing. GS analyses were performed using genomic best linear unbiased prediction by fitting a factor analytic (FA) multiplicative mixed model. Two cross-validation (CV) schemes were tested: CV1 and CV2. The FA framework allowed for investigating the stability of additive and dominance effects across environments, as well as the additive-by-environment and the dominance-by-environment interactions, with interesting applications for parental and hybrid selection. Results showed differences in the predictive accuracy between A and AD models, using both CV1 and CV2, for the five traits in both water conditions. For grain yield (GY) under WS and using CV1, the AD model doubled the predictive accuracy in comparison to the A model. Through CV2, GS models benefit from borrowing information of correlated trials, resulting in an increase of 40% and 9% in the predictive accuracy of GY under WS for A and AD models, respectively. These results highlight the importance of multi-environment trial analyses using GS models that incorporate additive and dominance effects for genomic predictions of GY under drought in maize single-cross hybrids.

Using Time Series Analysis to Predict Cardiac Arrest in a PICU.

PubMed

Kennedy, Curtis E; Aoki, Noriaki; Mariscalco, Michele; Turley, James P

2015-11-01

To build and test cardiac arrest prediction models in a PICU, using time series analysis as input, and to measure changes in prediction accuracy attributable to different classes of time series data. Retrospective cohort study. Thirty-one bed academic PICU that provides care for medical and general surgical (not congenital heart surgery) patients. Patients experiencing a cardiac arrest in the PICU and requiring external cardiac massage for at least 2 minutes. None. One hundred three cases of cardiac arrest and 109 control cases were used to prepare a baseline dataset that consisted of 1,025 variables in four data classes: multivariate, raw time series, clinical calculations, and time series trend analysis. We trained 20 arrest prediction models using a matrix of five feature sets (combinations of data classes) with four modeling algorithms: linear regression, decision tree, neural network, and support vector machine. The reference model (multivariate data with regression algorithm) had an accuracy of 78% and 87% area under the receiver operating characteristic curve. The best model (multivariate + trend analysis data with support vector machine algorithm) had an accuracy of 94% and 98% area under the receiver operating characteristic curve. Cardiac arrest predictions based on a traditional model built with multivariate data and a regression algorithm misclassified cases 3.7 times more frequently than predictions that included time series trend analysis and built with a support vector machine algorithm. Although the final model lacks the specificity necessary for clinical application, we have demonstrated how information from time series data can be used to increase the accuracy of clinical prediction models.

Increased genomic prediction accuracy in wheat breeding through spatial adjustment of field trial data.

PubMed

Lado, Bettina; Matus, Ivan; Rodríguez, Alejandra; Inostroza, Luis; Poland, Jesse; Belzile, François; del Pozo, Alejandro; Quincke, Martín; Castro, Marina; von Zitzewitz, Jarislav

2013-12-09

In crop breeding, the interest of predicting the performance of candidate cultivars in the field has increased due to recent advances in molecular breeding technologies. However, the complexity of the wheat genome presents some challenges for applying new technologies in molecular marker identification with next-generation sequencing. We applied genotyping-by-sequencing, a recently developed method to identify single-nucleotide polymorphisms, in the genomes of 384 wheat (Triticum aestivum) genotypes that were field tested under three different water regimes in Mediterranean climatic conditions: rain-fed only, mild water stress, and fully irrigated. We identified 102,324 single-nucleotide polymorphisms in these genotypes, and the phenotypic data were used to train and test genomic selection models intended to predict yield, thousand-kernel weight, number of kernels per spike, and heading date. Phenotypic data showed marked spatial variation. Therefore, different models were tested to correct the trends observed in the field. A mixed-model using moving-means as a covariate was found to best fit the data. When we applied the genomic selection models, the accuracy of predicted traits increased with spatial adjustment. Multiple genomic selection models were tested, and a Gaussian kernel model was determined to give the highest accuracy. The best predictions between environments were obtained when data from different years were used to train the model. Our results confirm that genotyping-by-sequencing is an effective tool to obtain genome-wide information for crops with complex genomes, that these data are efficient for predicting traits, and that correction of spatial variation is a crucial ingredient to increase prediction accuracy in genomic selection models.

Predicting Survival From Large Echocardiography and Electronic Health Record Datasets: Optimization With Machine Learning.

PubMed

Samad, Manar D; Ulloa, Alvaro; Wehner, Gregory J; Jing, Linyuan; Hartzel, Dustin; Good, Christopher W; Williams, Brent A; Haggerty, Christopher M; Fornwalt, Brandon K

2018-06-09

The goal of this study was to use machine learning to more accurately predict survival after echocardiography. Predicting patient outcomes (e.g., survival) following echocardiography is primarily based on ejection fraction (EF) and comorbidities. However, there may be significant predictive information within additional echocardiography-derived measurements combined with clinical electronic health record data. Mortality was studied in 171,510 unselected patients who underwent 331,317 echocardiograms in a large regional health system. We investigated the predictive performance of nonlinear machine learning models compared with that of linear logistic regression models using 3 different inputs: 1) clinical variables, including 90 cardiovascular-relevant International Classification of Diseases, Tenth Revision, codes, and age, sex, height, weight, heart rate, blood pressures, low-density lipoprotein, high-density lipoprotein, and smoking; 2) clinical variables plus physician-reported EF; and 3) clinical variables and EF, plus 57 additional echocardiographic measurements. Missing data were imputed with a multivariate imputation by using a chained equations algorithm (MICE). We compared models versus each other and baseline clinical scoring systems by using a mean area under the curve (AUC) over 10 cross-validation folds and across 10 survival durations (6 to 60 months). Machine learning models achieved significantly higher prediction accuracy (all AUC >0.82) over common clinical risk scores (AUC = 0.61 to 0.79), with the nonlinear random forest models outperforming logistic regression (p < 0.01). The random forest model including all echocardiographic measurements yielded the highest prediction accuracy (p < 0.01 across all models and survival durations). Only 10 variables were needed to achieve 96% of the maximum prediction accuracy, with 6 of these variables being derived from echocardiography. Tricuspid regurgitation velocity was more predictive of survival than LVEF. In a subset of studies with complete data for the top 10 variables, multivariate imputation by chained equations yielded slightly reduced predictive accuracies (difference in AUC of 0.003) compared with the original data. Machine learning can fully utilize large combinations of disparate input variables to predict survival after echocardiography with superior accuracy. Copyright © 2018 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

Posterior Predictive Checks for Conditional Independence between Response Time and Accuracy

ERIC Educational Resources Information Center

Bolsinova, Maria; Tijmstra, Jesper

2016-01-01

Conditional independence (CI) between response time and response accuracy is a fundamental assumption of many joint models for time and accuracy used in educational measurement. In this study, posterior predictive checks (PPCs) are proposed for testing this assumption. These PPCs are based on three discrepancy measures reflecting different…

Prediction accuracy of direct and indirect approaches, and their relationships with prediction ability of calibration models.

PubMed

Belay, T K; Dagnachew, B S; Boison, S A; Ådnøy, T

2018-03-28

Milk infrared spectra are routinely used for phenotyping traits of interest through links developed between the traits and spectra. Predicted individual traits are then used in genetic analyses for estimated breeding value (EBV) or for phenotypic predictions using a single-trait mixed model; this approach is referred to as indirect prediction (IP). An alternative approach [direct prediction (DP)] is a direct genetic analysis of (a reduced dimension of) the spectra using a multitrait model to predict multivariate EBV of the spectral components and, ultimately, also to predict the univariate EBV or phenotype for the traits of interest. We simulated 3 traits under different genetic (low: 0.10 to high: 0.90) and residual (zero to high: ±0.90) correlation scenarios between the 3 traits and assumed the first trait is a linear combination of the other 2 traits. The aim was to compare the IP and DP approaches for predictions of EBV and phenotypes under the different correlation scenarios. We also evaluated relationships between performances of the 2 approaches and the accuracy of calibration equations. Moreover, the effect of using different regression coefficients estimated from simulated phenotypes (β p ), true breeding values (β g ), and residuals (β r ) on performance of the 2 approaches were evaluated. The simulated data contained 2,100 parents (100 sires and 2,000 cows) and 8,000 offspring (4 offspring per cow). Of the 8,000 observations, 2,000 were randomly selected and used to develop links between the first and the other 2 traits using partial least square (PLS) regression analysis. The different PLS regression coefficients, such as β p , β g , and β r , were used in subsequent predictions following the IP and DP approaches. We used BLUP analyses for the remaining 6,000 observations using the true (co)variance components that had been used for the simulation. Accuracy of prediction (of EBV and phenotype) was calculated as a correlation between predicted and true values from the simulations. The results showed that accuracies of EBV prediction were higher in the DP than in the IP approach. The reverse was true for accuracy of phenotypic prediction when using β p but not when using β g and β r , where accuracy of phenotypic prediction in the DP was slightly higher than in the IP approach. Within the DP approach, accuracies of EBV when using β g were higher than when using β p only at the low genetic correlation scenario. However, we found no differences in EBV prediction accuracy between the β p and β g in the IP approach. Accuracy of the calibration models increased with an increase in genetic and residual correlations between the traits. Performance of both approaches increased with an increase in accuracy of the calibration models. In conclusion, the DP approach is a good strategy for EBV prediction but not for phenotypic prediction, where the classical PLS regression-based equations or the IP approach provided better results. The Authors. Published by FASS Inc. and Elsevier Inc. on behalf of the American Dairy Science Association®. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/).

Leuconostoc mesenteroides growth in food products: prediction and sensitivity analysis by adaptive-network-based fuzzy inference systems.

PubMed

Wang, Hue-Yu; Wen, Ching-Feng; Chiu, Yu-Hsien; Lee, I-Nong; Kao, Hao-Yun; Lee, I-Chen; Ho, Wen-Hsien

2013-01-01

An adaptive-network-based fuzzy inference system (ANFIS) was compared with an artificial neural network (ANN) in terms of accuracy in predicting the combined effects of temperature (10.5 to 24.5°C), pH level (5.5 to 7.5), sodium chloride level (0.25% to 6.25%) and sodium nitrite level (0 to 200 ppm) on the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. THE ANFIS AND ANN MODELS WERE COMPARED IN TERMS OF SIX STATISTICAL INDICES CALCULATED BY COMPARING THEIR PREDICTION RESULTS WITH ACTUAL DATA: mean absolute percentage error (MAPE), root mean square error (RMSE), standard error of prediction percentage (SEP), bias factor (Bf), accuracy factor (Af), and absolute fraction of variance (R (2)). Graphical plots were also used for model comparison. The learning-based systems obtained encouraging prediction results. Sensitivity analyses of the four environmental factors showed that temperature and, to a lesser extent, NaCl had the most influence on accuracy in predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. The observed effectiveness of ANFIS for modeling microbial kinetic parameters confirms its potential use as a supplemental tool in predictive mycology. Comparisons between growth rates predicted by ANFIS and actual experimental data also confirmed the high accuracy of the Gaussian membership function in ANFIS. Comparisons of the six statistical indices under both aerobic and anaerobic conditions also showed that the ANFIS model was better than all ANN models in predicting the four kinetic parameters. Therefore, the ANFIS model is a valuable tool for quickly predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions.

Leuconostoc Mesenteroides Growth in Food Products: Prediction and Sensitivity Analysis by Adaptive-Network-Based Fuzzy Inference Systems

PubMed Central

Wang, Hue-Yu; Wen, Ching-Feng; Chiu, Yu-Hsien; Lee, I-Nong; Kao, Hao-Yun; Lee, I-Chen; Ho, Wen-Hsien

2013-01-01

Background An adaptive-network-based fuzzy inference system (ANFIS) was compared with an artificial neural network (ANN) in terms of accuracy in predicting the combined effects of temperature (10.5 to 24.5°C), pH level (5.5 to 7.5), sodium chloride level (0.25% to 6.25%) and sodium nitrite level (0 to 200 ppm) on the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. Methods The ANFIS and ANN models were compared in terms of six statistical indices calculated by comparing their prediction results with actual data: mean absolute percentage error (MAPE), root mean square error (RMSE), standard error of prediction percentage (SEP), bias factor (Bf), accuracy factor (Af), and absolute fraction of variance (R 2). Graphical plots were also used for model comparison. Conclusions The learning-based systems obtained encouraging prediction results. Sensitivity analyses of the four environmental factors showed that temperature and, to a lesser extent, NaCl had the most influence on accuracy in predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. The observed effectiveness of ANFIS for modeling microbial kinetic parameters confirms its potential use as a supplemental tool in predictive mycology. Comparisons between growth rates predicted by ANFIS and actual experimental data also confirmed the high accuracy of the Gaussian membership function in ANFIS. Comparisons of the six statistical indices under both aerobic and anaerobic conditions also showed that the ANFIS model was better than all ANN models in predicting the four kinetic parameters. Therefore, the ANFIS model is a valuable tool for quickly predicting the growth rate of Leuconostoc mesenteroides under aerobic and anaerobic conditions. PMID:23705023

Prediction of beef carcass and meat traits from rearing factors in young bulls and cull cows.

PubMed

Soulat, J; Picard, B; Léger, S; Monteils, V

2016-04-01

The aim of this study was to predict the beef carcass and LM (thoracis part) characteristics and the sensory properties of the LM from rearing factors applied during the fattening period. Individual data from 995 animals (688 young bulls and 307 cull cows) in 15 experiments were used to establish prediction models. The data concerned rearing factors (13 variables), carcass characteristics (5 variables), LM characteristics (2 variables), and LM sensory properties (3 variables). In this study, 8 prediction models were established: dressing percentage and the proportions of fat tissue and muscle in the carcass to characterize the beef carcass; cross-sectional area of fibers (mean fiber area) and isocitrate dehydrogenase activity to characterize the LM; and, finally, overall tenderness, juiciness, and flavor intensity scores to characterize the LM sensory properties. A random effect was considered in each model: the breed for the prediction models for the carcass and LM characteristics and the trained taste panel for the prediction of the meat sensory properties. To evaluate the quality of prediction models, 3 criteria were measured: robustness, accuracy, and precision. The model was robust when the root mean square errors of prediction of calibration and validation sub-data sets were near to one another. Except for the mean fiber area model, the obtained predicted models were robust. The prediction models were considered to have a high accuracy when the mean prediction error (MPE) was ≤0.10 and to have a high precision when the was the closest to 1. The prediction of the characteristics of the carcass from the rearing factors had a high precision ( > 0.70) and a high prediction accuracy (MPE < 0.10), except for the fat percentage model ( = 0.67, MPE = 0.16). However, the predictions of the LM characteristics and LM sensory properties from the rearing factors were not sufficiently precise ( < 0.50) and accurate (MPE > 0.10). Only the flavor intensity of the beef score could be satisfactorily predicted from the rearing factors with high precision ( = 0.72) and accuracy (MPE = 0.10). All the prediction models displayed different effects of the rearing factors according to animal categories (young bulls or cull cows). In consequence, these prediction models display the necessary adaption of rearing factors during the fattening period according to animal categories to optimize the carcass traits according to animal categories.

Assessment of Protein Side-Chain Conformation Prediction Methods in Different Residue Environments

PubMed Central

Peterson, Lenna X.; Kang, Xuejiao; Kihara, Daisuke

2016-01-01

Computational prediction of side-chain conformation is an important component of protein structure prediction. Accurate side-chain prediction is crucial for practical applications of protein structure models that need atomic detailed resolution such as protein and ligand design. We evaluated the accuracy of eight side-chain prediction methods in reproducing the side-chain conformations of experimentally solved structures deposited to the Protein Data Bank. Prediction accuracy was evaluated for a total of four different structural environments (buried, surface, interface, and membrane-spanning) in three different protein types (monomeric, multimeric, and membrane). Overall, the highest accuracy was observed for buried residues in monomeric and multimeric proteins. Notably, side-chains at protein interfaces and membrane-spanning regions were better predicted than surface residues even though the methods did not all use multimeric and membrane proteins for training. Thus, we conclude that the current methods are as practically useful for modeling protein docking interfaces and membrane-spanning regions as for modeling monomers. PMID:24619909

The novel application of artificial neural network on bioelectrical impedance analysis to assess the body composition in elderly

PubMed Central

2013-01-01

Background This study aims to improve accuracy of Bioelectrical Impedance Analysis (BIA) prediction equations for estimating fat free mass (FFM) of the elderly by using non-linear Back Propagation Artificial Neural Network (BP-ANN) model and to compare the predictive accuracy with the linear regression model by using energy dual X-ray absorptiometry (DXA) as reference method. Methods A total of 88 Taiwanese elderly adults were recruited in this study as subjects. Linear regression equations and BP-ANN prediction equation were developed using impedances and other anthropometrics for predicting the reference FFM measured by DXA (FFMDXA) in 36 male and 26 female Taiwanese elderly adults. The FFM estimated by BIA prediction equations using traditional linear regression model (FFMLR) and BP-ANN model (FFMANN) were compared to the FFMDXA. The measuring results of an additional 26 elderly adults were used to validate than accuracy of the predictive models. Results The results showed the significant predictors were impedance, gender, age, height and weight in developed FFMLR linear model (LR) for predicting FFM (coefficient of determination, r2 = 0.940; standard error of estimate (SEE) = 2.729 kg; root mean square error (RMSE) = 2.571kg, P < 0.001). The above predictors were set as the variables of the input layer by using five neurons in the BP-ANN model (r2 = 0.987 with a SD = 1.192 kg and relatively lower RMSE = 1.183 kg), which had greater (improved) accuracy for estimating FFM when compared with linear model. The results showed a better agreement existed between FFMANN and FFMDXA than that between FFMLR and FFMDXA. Conclusion When compared the performance of developed prediction equations for estimating reference FFMDXA, the linear model has lower r2 with a larger SD in predictive results than that of BP-ANN model, which indicated ANN model is more suitable for estimating FFM. PMID:23388042

Radiomics-based Prognosis Analysis for Non-Small Cell Lung Cancer

NASA Astrophysics Data System (ADS)

Zhang, Yucheng; Oikonomou, Anastasia; Wong, Alexander; Haider, Masoom A.; Khalvati, Farzad

2017-04-01

Radiomics characterizes tumor phenotypes by extracting large numbers of quantitative features from radiological images. Radiomic features have been shown to provide prognostic value in predicting clinical outcomes in several studies. However, several challenges including feature redundancy, unbalanced data, and small sample sizes have led to relatively low predictive accuracy. In this study, we explore different strategies for overcoming these challenges and improving predictive performance of radiomics-based prognosis for non-small cell lung cancer (NSCLC). CT images of 112 patients (mean age 75 years) with NSCLC who underwent stereotactic body radiotherapy were used to predict recurrence, death, and recurrence-free survival using a comprehensive radiomics analysis. Different feature selection and predictive modeling techniques were used to determine the optimal configuration of prognosis analysis. To address feature redundancy, comprehensive analysis indicated that Random Forest models and Principal Component Analysis were optimum predictive modeling and feature selection methods, respectively, for achieving high prognosis performance. To address unbalanced data, Synthetic Minority Over-sampling technique was found to significantly increase predictive accuracy. A full analysis of variance showed that data endpoints, feature selection techniques, and classifiers were significant factors in affecting predictive accuracy, suggesting that these factors must be investigated when building radiomics-based predictive models for cancer prognosis.

Medium- and Long-term Prediction of LOD Change with the Leap-step Autoregressive Model

NASA Astrophysics Data System (ADS)

Liu, Q. B.; Wang, Q. J.; Lei, M. F.

2015-09-01

It is known that the accuracies of medium- and long-term prediction of changes of length of day (LOD) based on the combined least-square and autoregressive (LS+AR) decrease gradually. The leap-step autoregressive (LSAR) model is more accurate and stable in medium- and long-term prediction, therefore it is used to forecast the LOD changes in this work. Then the LOD series from EOP 08 C04 provided by IERS (International Earth Rotation and Reference Systems Service) is used to compare the effectiveness of the LSAR and traditional AR methods. The predicted series resulted from the two models show that the prediction accuracy with the LSAR model is better than that from AR model in medium- and long-term prediction.

Application of linear regression analysis in accuracy assessment of rolling force calculations

NASA Astrophysics Data System (ADS)

Poliak, E. I.; Shim, M. K.; Kim, G. S.; Choo, W. Y.

1998-10-01

Efficient operation of the computational models employed in process control systems require periodical assessment of the accuracy of their predictions. Linear regression is proposed as a tool which allows separate systematic and random prediction errors from those related to measurements. A quantitative characteristic of the model predictive ability is introduced in addition to standard statistical tests for model adequacy. Rolling force calculations are considered as an example for the application. However, the outlined approach can be used to assess the performance of any computational model.

Threshold models for genome-enabled prediction of ordinal categorical traits in plant breeding.

PubMed

Montesinos-López, Osval A; Montesinos-López, Abelardo; Pérez-Rodríguez, Paulino; de Los Campos, Gustavo; Eskridge, Kent; Crossa, José

2014-12-23

Categorical scores for disease susceptibility or resistance often are recorded in plant breeding. The aim of this study was to introduce genomic models for analyzing ordinal characters and to assess the predictive ability of genomic predictions for ordered categorical phenotypes using a threshold model counterpart of the Genomic Best Linear Unbiased Predictor (i.e., TGBLUP). The threshold model was used to relate a hypothetical underlying scale to the outward categorical response. We present an empirical application where a total of nine models, five without interaction and four with genomic × environment interaction (G×E) and genomic additive × additive × environment interaction (G×G×E), were used. We assessed the proposed models using data consisting of 278 maize lines genotyped with 46,347 single-nucleotide polymorphisms and evaluated for disease resistance [with ordinal scores from 1 (no disease) to 5 (complete infection)] in three environments (Colombia, Zimbabwe, and Mexico). Models with G×E captured a sizeable proportion of the total variability, which indicates the importance of introducing interaction to improve prediction accuracy. Relative to models based on main effects only, the models that included G×E achieved 9-14% gains in prediction accuracy; adding additive × additive interactions did not increase prediction accuracy consistently across locations. Copyright © 2015 Montesinos-López et al.

Prediction of skin sensitization potency using machine learning approaches.

PubMed

Zang, Qingda; Paris, Michael; Lehmann, David M; Bell, Shannon; Kleinstreuer, Nicole; Allen, David; Matheson, Joanna; Jacobs, Abigail; Casey, Warren; Strickland, Judy

2017-07-01

The replacement of animal use in testing for regulatory classification of skin sensitizers is a priority for US federal agencies that use data from such testing. Machine learning models that classify substances as sensitizers or non-sensitizers without using animal data have been developed and evaluated. Because some regulatory agencies require that sensitizers be further classified into potency categories, we developed statistical models to predict skin sensitization potency for murine local lymph node assay (LLNA) and human outcomes. Input variables for our models included six physicochemical properties and data from three non-animal test methods: direct peptide reactivity assay; human cell line activation test; and KeratinoSens™ assay. Models were built to predict three potency categories using four machine learning approaches and were validated using external test sets and leave-one-out cross-validation. A one-tiered strategy modeled all three categories of response together while a two-tiered strategy modeled sensitizer/non-sensitizer responses and then classified the sensitizers as strong or weak sensitizers. The two-tiered model using the support vector machine with all assay and physicochemical data inputs provided the best performance, yielding accuracy of 88% for prediction of LLNA outcomes (120 substances) and 81% for prediction of human test outcomes (87 substances). The best one-tiered model predicted LLNA outcomes with 78% accuracy and human outcomes with 75% accuracy. By comparison, the LLNA predicts human potency categories with 69% accuracy (60 of 87 substances correctly categorized). These results suggest that computational models using non-animal methods may provide valuable information for assessing skin sensitization potency. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Researches on High Accuracy Prediction Methods of Earth Orientation Parameters

NASA Astrophysics Data System (ADS)

Xu, X. Q.

2015-09-01

The Earth rotation reflects the coupling process among the solid Earth, atmosphere, oceans, mantle, and core of the Earth on multiple spatial and temporal scales. The Earth rotation can be described by the Earth's orientation parameters, which are abbreviated as EOP (mainly including two polar motion components PM_X and PM_Y, and variation in the length of day ΔLOD). The EOP is crucial in the transformation between the terrestrial and celestial reference systems, and has important applications in many areas such as the deep space exploration, satellite precise orbit determination, and astrogeodynamics. However, the EOP products obtained by the space geodetic technologies generally delay by several days to two weeks. The growing demands for modern space navigation make high-accuracy EOP prediction be a worthy topic. This thesis is composed of the following three aspects, for the purpose of improving the EOP forecast accuracy. (1) We analyze the relation between the length of the basic data series and the EOP forecast accuracy, and compare the EOP prediction accuracy for the linear autoregressive (AR) model and the nonlinear artificial neural network (ANN) method by performing the least squares (LS) extrapolations. The results show that the high precision forecast of EOP can be realized by appropriate selection of the basic data series length according to the required time span of EOP prediction: for short-term prediction, the basic data series should be shorter, while for the long-term prediction, the series should be longer. The analysis also showed that the LS+AR model is more suitable for the short-term forecasts, while the LS+ANN model shows the advantages in the medium- and long-term forecasts. (2) We develop for the first time a new method which combines the autoregressive model and Kalman filter (AR+Kalman) in short-term EOP prediction. The equations of observation and state are established using the EOP series and the autoregressive coefficients respectively, which are used to improve/re-evaluate the AR model. Comparing to the single AR model, the AR+Kalman method performs better in the prediction of UT1-UTC and ΔLOD, and the improvement in the prediction of the polar motion is significant. (3) Following the successful Earth Orientation Parameter Prediction Comparison Campaign (EOP PCC), the Earth Orientation Parameter Combination of Prediction Pilot Project (EOPC PPP) was sponsored in 2010. As one of the participants from China, we update and submit the short- and medium-term (1 to 90 days) EOP predictions every day. From the current comparative statistics, our prediction accuracy is on the medium international level. We will carry out more innovative researches to improve the EOP forecast accuracy and enhance our level in EOP forecast.

[Comparison of three stand-level biomass estimation methods].

PubMed

Dong, Li Hu; Li, Feng Ri

2016-12-01

At present, the forest biomass methods of regional scale attract most of attention of the researchers, and developing the stand-level biomass model is popular. Based on the forestry inventory data of larch plantation (Larix olgensis) in Jilin Province, we used non-linear seemly unrelated regression (NSUR) to estimate the parameters in two additive system of stand-level biomass equations, i.e., stand-level biomass equations including the stand variables and stand biomass equations including the biomass expansion factor (i.e., Model system 1 and Model system 2), listed the constant biomass expansion factor for larch plantation and compared the prediction accuracy of three stand-level biomass estimation methods. The results indicated that for two additive system of biomass equations, the adjusted coefficient of determination (R a 2 ) of the total and stem equations was more than 0.95, the root mean squared error (RMSE), the mean prediction error (MPE) and the mean absolute error (MAE) were smaller. The branch and foliage biomass equations were worse than total and stem biomass equations, and the adjusted coefficient of determination (R a 2 ) was less than 0.95. The prediction accuracy of a constant biomass expansion factor was relatively lower than the prediction accuracy of Model system 1 and Model system 2. Overall, although stand-level biomass equation including the biomass expansion factor belonged to the volume-derived biomass estimation method, and was different from the stand biomass equations including stand variables in essence, but the obtained prediction accuracy of the two methods was similar. The constant biomass expansion factor had the lower prediction accuracy, and was inappropriate. In addition, in order to make the model parameter estimation more effective, the established stand-level biomass equations should consider the additivity in a system of all tree component biomass and total biomass equations.

Spatiotemporal Bayesian networks for malaria prediction.

PubMed

Haddawy, Peter; Hasan, A H M Imrul; Kasantikul, Rangwan; Lawpoolsri, Saranath; Sa-Angchai, Patiwat; Kaewkungwal, Jaranit; Singhasivanon, Pratap

2018-01-01

Targeted intervention and resource allocation are essential for effective malaria control, particularly in remote areas, with predictive models providing important information for decision making. While a diversity of modeling technique have been used to create predictive models of malaria, no work has made use of Bayesian networks. Bayes nets are attractive due to their ability to represent uncertainty, model time lagged and nonlinear relations, and provide explanations. This paper explores the use of Bayesian networks to model malaria, demonstrating the approach by creating village level models with weekly temporal resolution for Tha Song Yang district in northern Thailand. The networks are learned using data on cases and environmental covariates. Three types of networks are explored: networks for numeric prediction, networks for outbreak prediction, and networks that incorporate spatial autocorrelation. Evaluation of the numeric prediction network shows that the Bayes net has prediction accuracy in terms of mean absolute error of about 1.4 cases for 1 week prediction and 1.7 cases for 6 week prediction. The network for outbreak prediction has an ROC AUC above 0.9 for all prediction horizons. Comparison of prediction accuracy of both Bayes nets against several traditional modeling approaches shows the Bayes nets to outperform the other models for longer time horizon prediction of high incidence transmission. To model spread of malaria over space, we elaborate the models with links between the village networks. This results in some very large models which would be far too laborious to build by hand. So we represent the models as collections of probability logic rules and automatically generate the networks. Evaluation of the models shows that the autocorrelation links significantly improve prediction accuracy for some villages in regions of high incidence. We conclude that spatiotemporal Bayesian networks are a highly promising modeling alternative for prediction of malaria and other vector-borne diseases. Copyright © 2017 Elsevier B.V. All rights reserved.

Genomic selection for crossbred performance accounting for breed-specific effects.

PubMed

Lopes, Marcos S; Bovenhuis, Henk; Hidalgo, André M; van Arendonk, Johan A M; Knol, Egbert F; Bastiaansen, John W M

2017-06-26

Breed-specific effects are observed when the same allele of a given genetic marker has a different effect depending on its breed origin, which results in different allele substitution effects across breeds. In such a case, single-breed breeding values may not be the most accurate predictors of crossbred performance. Our aim was to estimate the contribution of alleles from each parental breed to the genetic variance of traits that are measured in crossbred offspring, and to compare the prediction accuracies of estimated direct genomic values (DGV) from a traditional genomic selection model (GS) that are trained on purebred or crossbred data, with accuracies of DGV from a model that accounts for breed-specific effects (BS), trained on purebred or crossbred data. The final dataset was composed of 924 Large White, 924 Landrace and 924 two-way cross (F1) genotyped and phenotyped animals. The traits evaluated were litter size (LS) and gestation length (GL) in pigs. The genetic correlation between purebred and crossbred performance was higher than 0.88 for both LS and GL. For both traits, the additive genetic variance was larger for alleles inherited from the Large White breed compared to alleles inherited from the Landrace breed (0.74 and 0.56 for LS, and 0.42 and 0.40 for GL, respectively). The highest prediction accuracies of crossbred performance were obtained when training was done on crossbred data. For LS, prediction accuracies were the same for GS and BS DGV (0.23), while for GL, prediction accuracy for BS DGV was similar to the accuracy of GS DGV (0.53 and 0.52, respectively). In this study, training on crossbred data resulted in higher prediction accuracy than training on purebred data and evidence of breed-specific effects for LS and GL was demonstrated. However, when training was done on crossbred data, both GS and BS models resulted in similar prediction accuracies. In future studies, traits with a lower genetic correlation between purebred and crossbred performance should be included to further assess the value of the BS model in genomic predictions.

Development and evaluation of a regression-based model to predict cesium-137 concentration ratios for saltwater fish.

PubMed

Pinder, John E; Rowan, David J; Smith, Jim T

2016-02-01

Data from published studies and World Wide Web sources were combined to develop a regression model to predict (137)Cs concentration ratios for saltwater fish. Predictions were developed from 1) numeric trophic levels computed primarily from random resampling of known food items and 2) K concentrations in the saltwater for 65 samplings from 41 different species from both the Atlantic and Pacific Oceans. A number of different models were initially developed and evaluated for accuracy which was assessed as the ratios of independently measured concentration ratios to those predicted by the model. In contrast to freshwater systems, were K concentrations are highly variable and are an important factor in affecting fish concentration ratios, the less variable K concentrations in saltwater were relatively unimportant in affecting concentration ratios. As a result, the simplest model, which used only trophic level as a predictor, had comparable accuracies to more complex models that also included K concentrations. A test of model accuracy involving comparisons of 56 published concentration ratios from 51 species of marine fish to those predicted by the model indicated that 52 of the predicted concentration ratios were within a factor of 2 of the observed concentration ratios. Copyright © 2015 Elsevier Ltd. All rights reserved.

Improvement of PM concentration predictability using WRF-CMAQ-DLM coupled system and its applications

NASA Astrophysics Data System (ADS)

Lee, Soon Hwan; Kim, Ji Sun; Lee, Kang Yeol; Shon, Keon Tae

2017-04-01

Air quality due to increasing Particulate Matter(PM) in Korea in Asia is getting worse. At present, the PM forecast is announced based on the PM concentration predicted from the air quality prediction numerical model. However, forecast accuracy is not as high as expected due to various uncertainties for PM physical and chemical characteristics. The purpose of this study was to develop a numerical-statistically ensemble models to improve the accuracy of prediction of PM10 concentration. Numerical models used in this study are the three dimensional atmospheric model Weather Research and Forecasting(WRF) and the community multiscale air quality model (CMAQ). The target areas for the PM forecast are Seoul, Busan, Daegu, and Daejeon metropolitan areas in Korea. The data used in the model development are PM concentration and CMAQ predictions and the data period is 3 months (March 1 - May 31, 2014). The dynamic-statistical technics for reducing the systematic error of the CMAQ predictions was applied to the dynamic linear model(DLM) based on the Baysian Kalman filter technic. As a result of applying the metrics generated from the dynamic linear model to the forecasting of PM concentrations accuracy was improved. Especially, at the high PM concentration where the damage is relatively large, excellent improvement results are shown.

Risk-adjusted capitation based on the Diagnostic Cost Group Model: an empirical evaluation with health survey information.

PubMed Central

Lamers, L M

1999-01-01

OBJECTIVE: To evaluate the predictive accuracy of the Diagnostic Cost Group (DCG) model using health survey information. DATA SOURCES/STUDY SETTING: Longitudinal data collected for a sample of members of a Dutch sickness fund. In the Netherlands the sickness funds provide compulsory health insurance coverage for the 60 percent of the population in the lowest income brackets. STUDY DESIGN: A demographic model and DCG capitation models are estimated by means of ordinary least squares, with an individual's annual healthcare expenditures in 1994 as the dependent variable. For subgroups based on health survey information, costs predicted by the models are compared with actual costs. Using stepwise regression procedures a subset of relevant survey variables that could improve the predictive accuracy of the three-year DCG model was identified. Capitation models were extended with these variables. DATA COLLECTION/EXTRACTION METHODS: For the empirical analysis, panel data of sickness fund members were used that contained demographic information, annual healthcare expenditures, and diagnostic information from hospitalizations for each member. In 1993, a mailed health survey was conducted among a random sample of 15,000 persons in the panel data set, with a 70 percent response rate. PRINCIPAL FINDINGS: The predictive accuracy of the demographic model improves when it is extended with diagnostic information from prior hospitalizations (DCGs). A subset of survey variables further improves the predictive accuracy of the DCG capitation models. The predictable profits and losses based on survey information for the DCG models are smaller than for the demographic model. Most persons with predictable losses based on health survey information were not hospitalized in the preceding year. CONCLUSIONS: The use of diagnostic information from prior hospitalizations is a promising option for improving the demographic capitation payment formula. This study suggests that diagnostic information from outpatient utilization is complementary to DCGs in predicting future costs. PMID:10029506

Predicting coronary artery disease using different artificial neural network models.

PubMed

Colak, M Cengiz; Colak, Cemil; Kocatürk, Hasan; Sağiroğlu, Seref; Barutçu, Irfan

2008-08-01

Eight different learning algorithms used for creating artificial neural network (ANN) models and the different ANN models in the prediction of coronary artery disease (CAD) are introduced. This work was carried out as a retrospective case-control study. Overall, 124 consecutive patients who had been diagnosed with CAD by coronary angiography (at least 1 coronary stenosis > 50% in major epicardial arteries) were enrolled in the work. Angiographically, the 113 people (group 2) with normal coronary arteries were taken as control subjects. Multi-layered perceptrons ANN architecture were applied. The ANN models trained with different learning algorithms were performed in 237 records, divided into training (n=171) and testing (n=66) data sets. The performance of prediction was evaluated by sensitivity, specificity and accuracy values based on standard definitions. The results have demonstrated that ANN models trained with eight different learning algorithms are promising because of high (greater than 71%) sensitivity, specificity and accuracy values in the prediction of CAD. Accuracy, sensitivity and specificity values varied between 83.63%-100%, 86.46%-100% and 74.67%-100% for training, respectively. For testing, the values were more than 71% for sensitivity, 76% for specificity and 81% for accuracy. It may be proposed that the use of different learning algorithms other than backpropagation and larger sample sizes can improve the performance of prediction. The proposed ANN models trained with these learning algorithms could be used a promising approach for predicting CAD without the need for invasive diagnostic methods and could help in the prognostic clinical decision.

Mathematical-Artificial Neural Network Hybrid Model to Predict Roll Force during Hot Rolling of Steel

NASA Astrophysics Data System (ADS)

Rath, S.; Sengupta, P. P.; Singh, A. P.; Marik, A. K.; Talukdar, P.

2013-07-01

Accurate prediction of roll force during hot strip rolling is essential for model based operation of hot strip mills. Traditionally, mathematical models based on theory of plastic deformation have been used for prediction of roll force. In the last decade, data driven models like artificial neural network have been tried for prediction of roll force. Pure mathematical models have accuracy limitations whereas data driven models have difficulty in convergence when applied to industrial conditions. Hybrid models by integrating the traditional mathematical formulations and data driven methods are being developed in different parts of world. This paper discusses the methodology of development of an innovative hybrid mathematical-artificial neural network model. In mathematical model, the most important factor influencing accuracy is flow stress of steel. Coefficients of standard flow stress equation, calculated by parameter estimation technique, have been used in the model. The hybrid model has been trained and validated with input and output data collected from finishing stands of Hot Strip Mill, Bokaro Steel Plant, India. It has been found that the model accuracy has been improved with use of hybrid model, over the traditional mathematical model.

Increased Genomic Prediction Accuracy in Wheat Breeding Through Spatial Adjustment of Field Trial Data

PubMed Central

Lado, Bettina; Matus, Ivan; Rodríguez, Alejandra; Inostroza, Luis; Poland, Jesse; Belzile, François; del Pozo, Alejandro; Quincke, Martín; Castro, Marina; von Zitzewitz, Jarislav

2013-01-01

In crop breeding, the interest of predicting the performance of candidate cultivars in the field has increased due to recent advances in molecular breeding technologies. However, the complexity of the wheat genome presents some challenges for applying new technologies in molecular marker identification with next-generation sequencing. We applied genotyping-by-sequencing, a recently developed method to identify single-nucleotide polymorphisms, in the genomes of 384 wheat (Triticum aestivum) genotypes that were field tested under three different water regimes in Mediterranean climatic conditions: rain-fed only, mild water stress, and fully irrigated. We identified 102,324 single-nucleotide polymorphisms in these genotypes, and the phenotypic data were used to train and test genomic selection models intended to predict yield, thousand-kernel weight, number of kernels per spike, and heading date. Phenotypic data showed marked spatial variation. Therefore, different models were tested to correct the trends observed in the field. A mixed-model using moving-means as a covariate was found to best fit the data. When we applied the genomic selection models, the accuracy of predicted traits increased with spatial adjustment. Multiple genomic selection models were tested, and a Gaussian kernel model was determined to give the highest accuracy. The best predictions between environments were obtained when data from different years were used to train the model. Our results confirm that genotyping-by-sequencing is an effective tool to obtain genome-wide information for crops with complex genomes, that these data are efficient for predicting traits, and that correction of spatial variation is a crucial ingredient to increase prediction accuracy in genomic selection models. PMID:24082033

Improving orbit prediction accuracy through supervised machine learning

NASA Astrophysics Data System (ADS)

Peng, Hao; Bai, Xiaoli

2018-05-01

Due to the lack of information such as the space environment condition and resident space objects' (RSOs') body characteristics, current orbit predictions that are solely grounded on physics-based models may fail to achieve required accuracy for collision avoidance and have led to satellite collisions already. This paper presents a methodology to predict RSOs' trajectories with higher accuracy than that of the current methods. Inspired by the machine learning (ML) theory through which the models are learned based on large amounts of observed data and the prediction is conducted without explicitly modeling space objects and space environment, the proposed ML approach integrates physics-based orbit prediction algorithms with a learning-based process that focuses on reducing the prediction errors. Using a simulation-based space catalog environment as the test bed, the paper demonstrates three types of generalization capability for the proposed ML approach: (1) the ML model can be used to improve the same RSO's orbit information that is not available during the learning process but shares the same time interval as the training data; (2) the ML model can be used to improve predictions of the same RSO at future epochs; and (3) the ML model based on a RSO can be applied to other RSOs that share some common features.

Comparison of linear and non-linear models for predicting energy expenditure from raw accelerometer data.

PubMed

Montoye, Alexander H K; Begum, Munni; Henning, Zachary; Pfeiffer, Karin A

2017-02-01

This study had three purposes, all related to evaluating energy expenditure (EE) prediction accuracy from body-worn accelerometers: (1) compare linear regression to linear mixed models, (2) compare linear models to artificial neural network models, and (3) compare accuracy of accelerometers placed on the hip, thigh, and wrists. Forty individuals performed 13 activities in a 90 min semi-structured, laboratory-based protocol. Participants wore accelerometers on the right hip, right thigh, and both wrists and a portable metabolic analyzer (EE criterion). Four EE prediction models were developed for each accelerometer: linear regression, linear mixed, and two ANN models. EE prediction accuracy was assessed using correlations, root mean square error (RMSE), and bias and was compared across models and accelerometers using repeated-measures analysis of variance. For all accelerometer placements, there were no significant differences for correlations or RMSE between linear regression and linear mixed models (correlations: r  =  0.71-0.88, RMSE: 1.11-1.61 METs; p  >  0.05). For the thigh-worn accelerometer, there were no differences in correlations or RMSE between linear and ANN models (ANN-correlations: r  =  0.89, RMSE: 1.07-1.08 METs. Linear models-correlations: r  =  0.88, RMSE: 1.10-1.11 METs; p  >  0.05). Conversely, one ANN had higher correlations and lower RMSE than both linear models for the hip (ANN-correlation: r  =  0.88, RMSE: 1.12 METs. Linear models-correlations: r  =  0.86, RMSE: 1.18-1.19 METs; p  <  0.05), and both ANNs had higher correlations and lower RMSE than both linear models for the wrist-worn accelerometers (ANN-correlations: r  =  0.82-0.84, RMSE: 1.26-1.32 METs. Linear models-correlations: r  =  0.71-0.73, RMSE: 1.55-1.61 METs; p  <  0.01). For studies using wrist-worn accelerometers, machine learning models offer a significant improvement in EE prediction accuracy over linear models. Conversely, linear models showed similar EE prediction accuracy to machine learning models for hip- and thigh-worn accelerometers and may be viable alternative modeling techniques for EE prediction for hip- or thigh-worn accelerometers.

Variable selection models for genomic selection using whole-genome sequence data and singular value decomposition.

PubMed

Meuwissen, Theo H E; Indahl, Ulf G; Ødegård, Jørgen

2017-12-27

Non-linear Bayesian genomic prediction models such as BayesA/B/C/R involve iteration and mostly Markov chain Monte Carlo (MCMC) algorithms, which are computationally expensive, especially when whole-genome sequence (WGS) data are analyzed. Singular value decomposition (SVD) of the genotype matrix can facilitate genomic prediction in large datasets, and can be used to estimate marker effects and their prediction error variances (PEV) in a computationally efficient manner. Here, we developed, implemented, and evaluated a direct, non-iterative method for the estimation of marker effects for the BayesC genomic prediction model. The BayesC model assumes a priori that markers have normally distributed effects with probability [Formula: see text] and no effect with probability (1 - [Formula: see text]). Marker effects and their PEV are estimated by using SVD and the posterior probability of the marker having a non-zero effect is calculated. These posterior probabilities are used to obtain marker-specific effect variances, which are subsequently used to approximate BayesC estimates of marker effects in a linear model. A computer simulation study was conducted to compare alternative genomic prediction methods, where a single reference generation was used to estimate marker effects, which were subsequently used for 10 generations of forward prediction, for which accuracies were evaluated. SVD-based posterior probabilities of markers having non-zero effects were generally lower than MCMC-based posterior probabilities, but for some regions the opposite occurred, resulting in clear signals for QTL-rich regions. The accuracies of breeding values estimated using SVD- and MCMC-based BayesC analyses were similar across the 10 generations of forward prediction. For an intermediate number of generations (2 to 5) of forward prediction, accuracies obtained with the BayesC model tended to be slightly higher than accuracies obtained using the best linear unbiased prediction of SNP effects (SNP-BLUP model). When reducing marker density from WGS data to 30 K, SNP-BLUP tended to yield the highest accuracies, at least in the short term. Based on SVD of the genotype matrix, we developed a direct method for the calculation of BayesC estimates of marker effects. Although SVD- and MCMC-based marker effects differed slightly, their prediction accuracies were similar. Assuming that the SVD of the marker genotype matrix is already performed for other reasons (e.g. for SNP-BLUP), computation times for the BayesC predictions were comparable to those of SNP-BLUP.

Artificial neural network prediction of ischemic tissue fate in acute stroke imaging

PubMed Central

Huang, Shiliang; Shen, Qiang; Duong, Timothy Q

2010-01-01

Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin–spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBF+ADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis. PMID:20424631

Glucose Prediction Algorithms from Continuous Monitoring Data: Assessment of Accuracy via Continuous Glucose Error-Grid Analysis.

PubMed

Zanderigo, Francesca; Sparacino, Giovanni; Kovatchev, Boris; Cobelli, Claudio

2007-09-01

The aim of this article was to use continuous glucose error-grid analysis (CG-EGA) to assess the accuracy of two time-series modeling methodologies recently developed to predict glucose levels ahead of time using continuous glucose monitoring (CGM) data. We considered subcutaneous time series of glucose concentration monitored every 3 minutes for 48 hours by the minimally invasive CGM sensor Glucoday® (Menarini Diagnostics, Florence, Italy) in 28 type 1 diabetic volunteers. Two prediction algorithms, based on first-order polynomial and autoregressive (AR) models, respectively, were considered with prediction horizons of 30 and 45 minutes and forgetting factors (ff) of 0.2, 0.5, and 0.8. CG-EGA was used on the predicted profiles to assess their point and dynamic accuracies using original CGM profiles as reference. Continuous glucose error-grid analysis showed that the accuracy of both prediction algorithms is overall very good and that their performance is similar from a clinical point of view. However, the AR model seems preferable for hypoglycemia prevention. CG-EGA also suggests that, irrespective of the time-series model, the use of ff = 0.8 yields the highest accurate readings in all glucose ranges. For the first time, CG-EGA is proposed as a tool to assess clinically relevant performance of a prediction method separately at hypoglycemia, euglycemia, and hyperglycemia. In particular, we have shown that CG-EGA can be helpful in comparing different prediction algorithms, as well as in optimizing their parameters.

Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology.

PubMed

Fox, Eric W; Hill, Ryan A; Leibowitz, Scott G; Olsen, Anthony R; Thornbrugh, Darren J; Weber, Marc H

2017-07-01

Random forest (RF) modeling has emerged as an important statistical learning method in ecology due to its exceptional predictive performance. However, for large and complex ecological data sets, there is limited guidance on variable selection methods for RF modeling. Typically, either a preselected set of predictor variables are used or stepwise procedures are employed which iteratively remove variables according to their importance measures. This paper investigates the application of variable selection methods to RF models for predicting probable biological stream condition. Our motivating data set consists of the good/poor condition of n = 1365 stream survey sites from the 2008/2009 National Rivers and Stream Assessment, and a large set (p = 212) of landscape features from the StreamCat data set as potential predictors. We compare two types of RF models: a full variable set model with all 212 predictors and a reduced variable set model selected using a backward elimination approach. We assess model accuracy using RF's internal out-of-bag estimate, and a cross-validation procedure with validation folds external to the variable selection process. We also assess the stability of the spatial predictions generated by the RF models to changes in the number of predictors and argue that model selection needs to consider both accuracy and stability. The results suggest that RF modeling is robust to the inclusion of many variables of moderate to low importance. We found no substantial improvement in cross-validated accuracy as a result of variable reduction. Moreover, the backward elimination procedure tended to select too few variables and exhibited numerous issues such as upwardly biased out-of-bag accuracy estimates and instabilities in the spatial predictions. We use simulations to further support and generalize results from the analysis of real data. A main purpose of this work is to elucidate issues of model selection bias and instability to ecologists interested in using RF to develop predictive models with large environmental data sets.

A prediction model of compressor with variable-geometry diffuser based on elliptic equation and partial least squares

PubMed Central

Yang, Chuanlei; Wang, Yinyan; Wang, Hechun

2018-01-01

To achieve a much more extensive intake air flow range of the diesel engine, a variable-geometry compressor (VGC) is introduced into a turbocharged diesel engine. However, due to the variable diffuser vane angle (DVA), the prediction for the performance of the VGC becomes more difficult than for a normal compressor. In the present study, a prediction model comprising an elliptical equation and a PLS (partial least-squares) model was proposed to predict the performance of the VGC. The speed lines of the pressure ratio map and the efficiency map were fitted with the elliptical equation, and the coefficients of the elliptical equation were introduced into the PLS model to build the polynomial relationship between the coefficients and the relative speed, the DVA. Further, the maximal order of the polynomial was investigated in detail to reduce the number of sub-coefficients and achieve acceptable fit accuracy simultaneously. The prediction model was validated with sample data and in order to present the superiority of compressor performance prediction, the prediction results of this model were compared with those of the look-up table and back-propagation neural networks (BPNNs). The validation and comparison results show that the prediction accuracy of the new developed model is acceptable, and this model is much more suitable than the look-up table and the BPNN methods under the same condition in VGC performance prediction. Moreover, the new developed prediction model provides a novel and effective prediction solution for the VGC and can be used to improve the accuracy of the thermodynamic model for turbocharged diesel engines in the future. PMID:29410849

A prediction model of compressor with variable-geometry diffuser based on elliptic equation and partial least squares.

PubMed

Li, Xu; Yang, Chuanlei; Wang, Yinyan; Wang, Hechun

2018-01-01

To achieve a much more extensive intake air flow range of the diesel engine, a variable-geometry compressor (VGC) is introduced into a turbocharged diesel engine. However, due to the variable diffuser vane angle (DVA), the prediction for the performance of the VGC becomes more difficult than for a normal compressor. In the present study, a prediction model comprising an elliptical equation and a PLS (partial least-squares) model was proposed to predict the performance of the VGC. The speed lines of the pressure ratio map and the efficiency map were fitted with the elliptical equation, and the coefficients of the elliptical equation were introduced into the PLS model to build the polynomial relationship between the coefficients and the relative speed, the DVA. Further, the maximal order of the polynomial was investigated in detail to reduce the number of sub-coefficients and achieve acceptable fit accuracy simultaneously. The prediction model was validated with sample data and in order to present the superiority of compressor performance prediction, the prediction results of this model were compared with those of the look-up table and back-propagation neural networks (BPNNs). The validation and comparison results show that the prediction accuracy of the new developed model is acceptable, and this model is much more suitable than the look-up table and the BPNN methods under the same condition in VGC performance prediction. Moreover, the new developed prediction model provides a novel and effective prediction solution for the VGC and can be used to improve the accuracy of the thermodynamic model for turbocharged diesel engines in the future.

A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in Western Australia.

PubMed

Aboagye-Sarfo, Patrick; Mai, Qun; Sanfilippo, Frank M; Preen, David B; Stewart, Louise M; Fatovich, Daniel M

2015-10-01

To develop multivariate vector-ARMA (VARMA) forecast models for predicting emergency department (ED) demand in Western Australia (WA) and compare them to the benchmark univariate autoregressive moving average (ARMA) and Winters' models. Seven-year monthly WA state-wide public hospital ED presentation data from 2006/07 to 2012/13 were modelled. Graphical and VARMA modelling methods were used for descriptive analysis and model fitting. The VARMA models were compared to the benchmark univariate ARMA and Winters' models to determine their accuracy to predict ED demand. The best models were evaluated by using error correction methods for accuracy. Descriptive analysis of all the dependent variables showed an increasing pattern of ED use with seasonal trends over time. The VARMA models provided a more precise and accurate forecast with smaller confidence intervals and better measures of accuracy in predicting ED demand in WA than the ARMA and Winters' method. VARMA models are a reliable forecasting method to predict ED demand for strategic planning and resource allocation. While the ARMA models are a closely competing alternative, they under-estimated future ED demand. Copyright © 2015 Elsevier Inc. All rights reserved.

Evaluating the predictive accuracy and the clinical benefit of a nomogram aimed to predict survival in node-positive prostate cancer patients: External validation on a multi-institutional database.

PubMed

Bianchi, Lorenzo; Schiavina, Riccardo; Borghesi, Marco; Bianchi, Federico Mineo; Briganti, Alberto; Carini, Marco; Terrone, Carlo; Mottrie, Alex; Gacci, Mauro; Gontero, Paolo; Imbimbo, Ciro; Marchioro, Giansilvio; Milanese, Giulio; Mirone, Vincenzo; Montorsi, Francesco; Morgia, Giuseppe; Novara, Giacomo; Porreca, Angelo; Volpe, Alessandro; Brunocilla, Eugenio

2018-04-06

To assess the predictive accuracy and the clinical value of a recent nomogram predicting cancer-specific mortality-free survival after surgery in pN1 prostate cancer patients through an external validation. We evaluated 518 prostate cancer patients treated with radical prostatectomy and pelvic lymph node dissection with evidence of nodal metastases at final pathology, at 10 tertiary centers. External validation was carried out using regression coefficients of the previously published nomogram. The performance characteristics of the model were assessed by quantifying predictive accuracy, according to the area under the curve in the receiver operating characteristic curve and model calibration. Furthermore, we systematically analyzed the specificity, sensitivity, positive predictive value and negative predictive value for each nomogram-derived probability cut-off. Finally, we implemented decision curve analysis, in order to quantify the nomogram's clinical value in routine practice. External validation showed inferior predictive accuracy as referred to in the internal validation (65.8% vs 83.3%, respectively). The discrimination (area under the curve) of the multivariable model was 66.7% (95% CI 60.1-73.0%) by testing with receiver operating characteristic curve analysis. The calibration plot showed an overestimation throughout the range of predicted cancer-specific mortality-free survival rates probabilities. However, in decision curve analysis, the nomogram's use showed a net benefit when compared with the scenarios of treating all patients or none. In an external setting, the nomogram showed inferior predictive accuracy and suboptimal calibration characteristics as compared to that reported in the original population. However, decision curve analysis showed a clinical net benefit, suggesting a clinical implication to correctly manage pN1 prostate cancer patients after surgery. © 2018 The Japanese Urological Association.

Assessment of a remote sensing-based model for predicting malaria transmission risk in villages of Chiapas, Mexico

NASA Technical Reports Server (NTRS)

Beck, L. R.; Rodriguez, M. H.; Dister, S. W.; Rodriguez, A. D.; Washino, R. K.; Roberts, D. R.; Spanner, M. A.

1997-01-01

A blind test of two remote sensing-based models for predicting adult populations of Anopheles albimanus in villages, an indicator of malaria transmission risk, was conducted in southern Chiapas, Mexico. One model was developed using a discriminant analysis approach, while the other was based on regression analysis. The models were developed in 1992 for an area around Tapachula, Chiapas, using Landsat Thematic Mapper (TM) satellite data and geographic information system functions. Using two remotely sensed landscape elements, the discriminant model was able to successfully distinguish between villages with high and low An. albimanus abundance with an overall accuracy of 90%. To test the predictive capability of the models, multitemporal TM data were used to generate a landscape map of the Huixtla area, northwest of Tapachula, where the models were used to predict risk for 40 villages. The resulting predictions were not disclosed until the end of the test. Independently, An. albimanus abundance data were collected in the 40 randomly selected villages for which the predictions had been made. These data were subsequently used to assess the models' accuracies. The discriminant model accurately predicted 79% of the high-abundance villages and 50% of the low-abundance villages, for an overall accuracy of 70%. The regression model correctly identified seven of the 10 villages with the highest mosquito abundance. This test demonstrated that remote sensing-based models generated for one area can be used successfully in another, comparable area.

Including non-additive genetic effects in Bayesian methods for the prediction of genetic values based on genome-wide markers

PubMed Central

2011-01-01

Background Molecular marker information is a common source to draw inferences about the relationship between genetic and phenotypic variation. Genetic effects are often modelled as additively acting marker allele effects. The true mode of biological action can, of course, be different from this plain assumption. One possibility to better understand the genetic architecture of complex traits is to include intra-locus (dominance) and inter-locus (epistasis) interaction of alleles as well as the additive genetic effects when fitting a model to a trait. Several Bayesian MCMC approaches exist for the genome-wide estimation of genetic effects with high accuracy of genetic value prediction. Including pairwise interaction for thousands of loci would probably go beyond the scope of such a sampling algorithm because then millions of effects are to be estimated simultaneously leading to months of computation time. Alternative solving strategies are required when epistasis is studied. Methods We extended a fast Bayesian method (fBayesB), which was previously proposed for a purely additive model, to include non-additive effects. The fBayesB approach was used to estimate genetic effects on the basis of simulated datasets. Different scenarios were simulated to study the loss of accuracy of prediction, if epistatic effects were not simulated but modelled and vice versa. Results If 23 QTL were simulated to cause additive and dominance effects, both fBayesB and a conventional MCMC sampler BayesB yielded similar results in terms of accuracy of genetic value prediction and bias of variance component estimation based on a model including additive and dominance effects. Applying fBayesB to data with epistasis, accuracy could be improved by 5% when all pairwise interactions were modelled as well. The accuracy decreased more than 20% if genetic variation was spread over 230 QTL. In this scenario, accuracy based on modelling only additive and dominance effects was generally superior to that of the complex model including epistatic effects. Conclusions This simulation study showed that the fBayesB approach is convenient for genetic value prediction. Jointly estimating additive and non-additive effects (especially dominance) has reasonable impact on the accuracy of prediction and the proportion of genetic variation assigned to the additive genetic source. PMID:21867519

Numerical simulation of turbulence flow in a Kaplan turbine -Evaluation on turbine performance prediction accuracy-

NASA Astrophysics Data System (ADS)

Ko, P.; Kurosawa, S.

2014-03-01

The understanding and accurate prediction of the flow behaviour related to cavitation and pressure fluctuation in a Kaplan turbine are important to the design work enhancing the turbine performance including the elongation of the operation life span and the improvement of turbine efficiency. In this paper, high accuracy turbine and cavitation performance prediction method based on entire flow passage for a Kaplan turbine is presented and evaluated. Two-phase flow field is predicted by solving Reynolds-Averaged Navier-Stokes equations expressed by volume of fluid method tracking the free surface and combined with Reynolds Stress model. The growth and collapse of cavitation bubbles are modelled by the modified Rayleigh-Plesset equation. The prediction accuracy is evaluated by comparing with the model test results of Ns 400 Kaplan model turbine. As a result that the experimentally measured data including turbine efficiency, cavitation performance, and pressure fluctuation are accurately predicted. Furthermore, the cavitation occurrence on the runner blade surface and the influence to the hydraulic loss of the flow passage are discussed. Evaluated prediction method for the turbine flow and performance is introduced to facilitate the future design and research works on Kaplan type turbine.

SU-E-J-234: Application of a Breathing Motion Model to ViewRay Cine MR Images

DOE Office of Scientific and Technical Information (OSTI.GOV)

O’Connell, D. P.; Thomas, D. H.; Dou, T. H.

2015-06-15

Purpose: A respiratory motion model previously used to generate breathing-gated CT images was used with cine MR images. Accuracy and predictive ability of the in-plane models were evaluated. Methods: Sagittalplane cine MR images of a patient undergoing treatment on a ViewRay MRI/radiotherapy system were acquired before and during treatment. Images were acquired at 4 frames/second with 3.5 × 3.5 mm resolution and a slice thickness of 5 mm. The first cine frame was deformably registered to following frames. Superior/inferior component of the tumor centroid position was used as a breathing surrogate. Deformation vectors and surrogate measurements were used to determinemore » motion model parameters. Model error was evaluated and subsequent treatment cines were predicted from breathing surrogate data. A simulated CT cine was created by generating breathing-gated volumetric images at 0.25 second intervals along the measured breathing trace, selecting a sagittal slice and downsampling to the resolution of the MR cines. A motion model was built using the first half of the simulated cine data. Model accuracy and error in predicting the remaining frames of the cine were evaluated. Results: Mean difference between model predicted and deformably registered lung tissue positions for the 28 second preview MR cine acquired before treatment was 0.81 +/− 0.30 mm. The model was used to predict two minutes of the subsequent treatment cine with a mean accuracy of 1.59 +/− 0.63 mm. Conclusion: Inplane motion models were built using MR cine images and evaluated for accuracy and ability to predict future respiratory motion from breathing surrogate measurements. Examination of long term predictive ability is ongoing. The technique was applied to simulated CT cines for further validation, and the authors are currently investigating use of in-plane models to update pre-existing volumetric motion models used for generation of breathing-gated CT planning images.« less

Evaluation of an ensemble of genetic models for prediction of a quantitative trait.

PubMed

Milton, Jacqueline N; Steinberg, Martin H; Sebastiani, Paola

2014-01-01

Many genetic markers have been shown to be associated with common quantitative traits in genome-wide association studies. Typically these associated genetic markers have small to modest effect sizes and individually they explain only a small amount of the variability of the phenotype. In order to build a genetic prediction model without fitting a multiple linear regression model with possibly hundreds of genetic markers as predictors, researchers often summarize the joint effect of risk alleles into a genetic score that is used as a covariate in the genetic prediction model. However, the prediction accuracy can be highly variable and selecting the optimal number of markers to be included in the genetic score is challenging. In this manuscript we present a strategy to build an ensemble of genetic prediction models from data and we show that the ensemble-based method makes the challenge of choosing the number of genetic markers more amenable. Using simulated data with varying heritability and number of genetic markers, we compare the predictive accuracy and inclusion of true positive and false positive markers of a single genetic prediction model and our proposed ensemble method. The results show that the ensemble of genetic models tends to include a larger number of genetic variants than a single genetic model and it is more likely to include all of the true genetic markers. This increased sensitivity is obtained at the price of a lower specificity that appears to minimally affect the predictive accuracy of the ensemble.

Validation of Groundwater Models: Meaningful or Meaningless?

NASA Astrophysics Data System (ADS)

Konikow, L. F.

2003-12-01

Although numerical simulation models are valuable tools for analyzing groundwater systems, their predictive accuracy is limited. People who apply groundwater flow or solute-transport models, as well as those who make decisions based on model results, naturally want assurance that a model is "valid." To many people, model validation implies some authentication of the truth or accuracy of the model. History matching is often presented as the basis for model validation. Although such model calibration is a necessary modeling step, it is simply insufficient for model validation. Because of parameter uncertainty and solution non-uniqueness, declarations of validation (or verification) of a model are not meaningful. Post-audits represent a useful means to assess the predictive accuracy of a site-specific model, but they require the existence of long-term monitoring data. Model testing may yield invalidation, but that is an opportunity to learn and to improve the conceptual and numerical models. Examples of post-audits and of the application of a solute-transport model to a radioactive waste disposal site illustrate deficiencies in model calibration, prediction, and validation.

Genomic predictions across Nordic Holstein and Nordic Red using the genomic best linear unbiased prediction model with different genomic relationship matrices.

PubMed

Zhou, L; Lund, M S; Wang, Y; Su, G

2014-08-01

This study investigated genomic predictions across Nordic Holstein and Nordic Red using various genomic relationship matrices. Different sources of information, such as consistencies of linkage disequilibrium (LD) phase and marker effects, were used to construct the genomic relationship matrices (G-matrices) across these two breeds. Single-trait genomic best linear unbiased prediction (GBLUP) model and two-trait GBLUP model were used for single-breed and two-breed genomic predictions. The data included 5215 Nordic Holstein bulls and 4361 Nordic Red bulls, which was composed of three populations: Danish Red, Swedish Red and Finnish Ayrshire. The bulls were genotyped with 50 000 SNP chip. Using the two-breed predictions with a joint Nordic Holstein and Nordic Red reference population, accuracies increased slightly for all traits in Nordic Red, but only for some traits in Nordic Holstein. Among the three subpopulations of Nordic Red, accuracies increased more for Danish Red than for Swedish Red and Finnish Ayrshire. This is because closer genetic relationships exist between Danish Red and Nordic Holstein. Among Danish Red, individuals with higher genomic relationship coefficients with Nordic Holstein showed more increased accuracies in the two-breed predictions. Weighting the two-breed G-matrices by LD phase consistencies, marker effects or both did not further improve accuracies of the two-breed predictions. © 2014 Blackwell Verlag GmbH.

Effects of number of training generations on genomic prediction for various traits in a layer chicken population.

PubMed

Weng, Ziqing; Wolc, Anna; Shen, Xia; Fernando, Rohan L; Dekkers, Jack C M; Arango, Jesus; Settar, Petek; Fulton, Janet E; O'Sullivan, Neil P; Garrick, Dorian J

2016-03-19

Genomic estimated breeding values (GEBV) based on single nucleotide polymorphism (SNP) genotypes are widely used in animal improvement programs. It is typically assumed that the larger the number of animals is in the training set, the higher is the prediction accuracy of GEBV. The aim of this study was to quantify genomic prediction accuracy depending on the number of ancestral generations included in the training set, and to determine the optimal number of training generations for different traits in an elite layer breeding line. Phenotypic records for 16 traits on 17,793 birds were used. All parents and some selection candidates from nine non-overlapping generations were genotyped for 23,098 segregating SNPs. An animal model with pedigree relationships (PBLUP) and the BayesB genomic prediction model were applied to predict EBV or GEBV at each validation generation (progeny of the most recent training generation) based on varying numbers of immediately preceding ancestral generations. Prediction accuracy of EBV or GEBV was assessed as the correlation between EBV and phenotypes adjusted for fixed effects, divided by the square root of trait heritability. The optimal number of training generations that resulted in the greatest prediction accuracy of GEBV was determined for each trait. The relationship between optimal number of training generations and heritability was investigated. On average, accuracies were higher with the BayesB model than with PBLUP. Prediction accuracies of GEBV increased as the number of closely-related ancestral generations included in the training set increased, but reached an asymptote or slightly decreased when distant ancestral generations were used in the training set. The optimal number of training generations was 4 or more for high heritability traits but less than that for low heritability traits. For less heritable traits, limiting the training datasets to individuals closely related to the validation population resulted in the best predictions. The effect of adding distant ancestral generations in the training set on prediction accuracy differed between traits and the optimal number of necessary training generations is associated with the heritability of traits.

All-atom 3D structure prediction of transmembrane β-barrel proteins from sequences.

PubMed

Hayat, Sikander; Sander, Chris; Marks, Debora S; Elofsson, Arne

2015-04-28

Transmembrane β-barrels (TMBs) carry out major functions in substrate transport and protein biogenesis but experimental determination of their 3D structure is challenging. Encouraged by successful de novo 3D structure prediction of globular and α-helical membrane proteins from sequence alignments alone, we developed an approach to predict the 3D structure of TMBs. The approach combines the maximum-entropy evolutionary coupling method for predicting residue contacts (EVfold) with a machine-learning approach (boctopus2) for predicting β-strands in the barrel. In a blinded test for 19 TMB proteins of known structure that have a sufficient number of diverse homologous sequences available, this combined method (EVfold_bb) predicts hydrogen-bonded residue pairs between adjacent β-strands at an accuracy of ∼70%. This accuracy is sufficient for the generation of all-atom 3D models. In the transmembrane barrel region, the average 3D structure accuracy [template-modeling (TM) score] of top-ranked models is 0.54 (ranging from 0.36 to 0.85), with a higher (44%) number of residue pairs in correct strand-strand registration than in earlier methods (18%). Although the nonbarrel regions are predicted less accurately overall, the evolutionary couplings identify some highly constrained loop residues and, for FecA protein, the barrel including the structure of a plug domain can be accurately modeled (TM score = 0.68). Lower prediction accuracy tends to be associated with insufficient sequence information and we therefore expect increasing numbers of β-barrel families to become accessible to accurate 3D structure prediction as the number of available sequences increases.

Comparison of integrated clustering methods for accurate and stable prediction of building energy consumption data

DOE PAGES

Hsu, David

2015-09-27

Clustering methods are often used to model energy consumption for two reasons. First, clustering is often used to process data and to improve the predictive accuracy of subsequent energy models. Second, stable clusters that are reproducible with respect to non-essential changes can be used to group, target, and interpret observed subjects. However, it is well known that clustering methods are highly sensitive to the choice of algorithms and variables. This can lead to misleading assessments of predictive accuracy and mis-interpretation of clusters in policymaking. This paper therefore introduces two methods to the modeling of energy consumption in buildings: clusterwise regression,more » also known as latent class regression, which integrates clustering and regression simultaneously; and cluster validation methods to measure stability. Using a large dataset of multifamily buildings in New York City, clusterwise regression is compared to common two-stage algorithms that use K-means and model-based clustering with linear regression. Predictive accuracy is evaluated using 20-fold cross validation, and the stability of the perturbed clusters is measured using the Jaccard coefficient. These results show that there seems to be an inherent tradeoff between prediction accuracy and cluster stability. This paper concludes by discussing which clustering methods may be appropriate for different analytical purposes.« less

The drivers of wildfire enlargement do not exhibit scale thresholds in southeastern Australian forests.

PubMed

Price, Owen F; Penman, Trent; Bradstock, Ross; Borah, Rittick

2016-10-01

Wildfires are complex adaptive systems, and have been hypothesized to exhibit scale-dependent transitions in the drivers of fire spread. Among other things, this makes the prediction of final fire size from conditions at the ignition difficult. We test this hypothesis by conducting a multi-scale statistical modelling of the factors determining whether fires reached 10 ha, then 100 ha then 1000 ha and the final size of fires >1000 ha. At each stage, the predictors were measures of weather, fuels, topography and fire suppression. The objectives were to identify differences among the models indicative of scale transitions, assess the accuracy of the multi-step method for predicting fire size (compared to predicting final size from initial conditions) and to quantify the importance of the predictors. The data were 1116 fires that occurred in the eucalypt forests of New South Wales between 1985 and 2010. The models were similar at the different scales, though there were subtle differences. For example, the presence of roads affected whether fires reached 10 ha but not larger scales. Weather was the most important predictor overall, though fuel load, topography and ease of suppression all showed effects. Overall, there was no evidence that fires have scale-dependent transitions in behaviour. The models had a predictive accuracy of 73%, 66%, 72% and 53% accuracy at 10 ha, 100 ha, 1000 ha and final size scales. When these steps were combined, the overall accuracy for predicting the size of fires was 62%, while the accuracy of the one step model was only 20%. Thus, the multi-scale approach was an improvement on the single scale approach, even though the predictive accuracy was probably insufficient for use as an operational tool. The analysis has also provided further evidence of the important role of weather, compared to fuel, suppression and topography in driving fire behaviour. Copyright © 2016. Published by Elsevier Ltd.

Potential and limits to unravel the genetic architecture and predict the variation of Fusarium head blight resistance in European winter wheat (Triticum aestivum L.).

PubMed

Jiang, Y; Zhao, Y; Rodemann, B; Plieske, J; Kollers, S; Korzun, V; Ebmeyer, E; Argillier, O; Hinze, M; Ling, J; Röder, M S; Ganal, M W; Mette, M F; Reif, J C

2015-03-01

Genome-wide mapping approaches in diverse populations are powerful tools to unravel the genetic architecture of complex traits. The main goals of our study were to investigate the potential and limits to unravel the genetic architecture and to identify the factors determining the accuracy of prediction of the genotypic variation of Fusarium head blight (FHB) resistance in wheat (Triticum aestivum L.) based on data collected with a diverse panel of 372 European varieties. The wheat lines were phenotyped in multi-location field trials for FHB resistance and genotyped with 782 simple sequence repeat (SSR) markers, and 9k and 90k single-nucleotide polymorphism (SNP) arrays. We applied genome-wide association mapping in combination with fivefold cross-validations and observed surprisingly high accuracies of prediction for marker-assisted selection based on the detected quantitative trait loci (QTLs). Using a random sample of markers not selected for marker-trait associations revealed only a slight decrease in prediction accuracy compared with marker-based selection exploiting the QTL information. The same picture was confirmed in a simulation study, suggesting that relatedness is a main driver of the accuracy of prediction in marker-assisted selection of FHB resistance. When the accuracy of prediction of three genomic selection models was contrasted for the three marker data sets, no significant differences in accuracies among marker platforms and genomic selection models were observed. Marker density impacted the accuracy of prediction only marginally. Consequently, genomic selection of FHB resistance can be implemented most cost-efficiently based on low- to medium-density SNP arrays.

Predicting oropharyngeal tumor volume throughout the course of radiation therapy from pretreatment computed tomography data using general linear models.

PubMed

Yock, Adam D; Rao, Arvind; Dong, Lei; Beadle, Beth M; Garden, Adam S; Kudchadker, Rajat J; Court, Laurence E

2014-05-01

The purpose of this work was to develop and evaluate the accuracy of several predictive models of variation in tumor volume throughout the course of radiation therapy. Nineteen patients with oropharyngeal cancers were imaged daily with CT-on-rails for image-guided alignment per an institutional protocol. The daily volumes of 35 tumors in these 19 patients were determined and used to generate (1) a linear model in which tumor volume changed at a constant rate, (2) a general linear model that utilized the power fit relationship between the daily and initial tumor volumes, and (3) a functional general linear model that identified and exploited the primary modes of variation between time series describing the changing tumor volumes. Primary and nodal tumor volumes were examined separately. The accuracy of these models in predicting daily tumor volumes were compared with those of static and linear reference models using leave-one-out cross-validation. In predicting the daily volume of primary tumors, the general linear model and the functional general linear model were more accurate than the static reference model by 9.9% (range: -11.6%-23.8%) and 14.6% (range: -7.3%-27.5%), respectively, and were more accurate than the linear reference model by 14.2% (range: -6.8%-40.3%) and 13.1% (range: -1.5%-52.5%), respectively. In predicting the daily volume of nodal tumors, only the 14.4% (range: -11.1%-20.5%) improvement in accuracy of the functional general linear model compared to the static reference model was statistically significant. A general linear model and a functional general linear model trained on data from a small population of patients can predict the primary tumor volume throughout the course of radiation therapy with greater accuracy than standard reference models. These more accurate models may increase the prognostic value of information about the tumor garnered from pretreatment computed tomography images and facilitate improved treatment management.

Radiation model predictions and validation using LDEF satellite data

NASA Technical Reports Server (NTRS)

Armstrong, T. W.; Colborn, B. L.

1993-01-01

Predictions and comparisons with the radiation dose measurements on Long Duration Exposure Facility (LDEF) by thermoluminescent dosimeters were made to evaluate the accuracy of models currently used in defining the ionizing radiation environment for low Earth orbit missions. The calculations include a detailed simulation of the radiation exposure (altitude and solar cycle variations, directional dependence) and shielding effects (three-dimensional LDEF geometry model) so that differences in the predicted and observed doses can be attributed to environment model uncertainties. The LDEF dose data are utilized to assess the accuracy of models describing the trapped proton flux, the trapped proton directionality, and the trapped electron flux.

Prediction accuracies for growth and wood attributes of interior spruce in space using genotyping-by-sequencing.

PubMed

Gamal El-Dien, Omnia; Ratcliffe, Blaise; Klápště, Jaroslav; Chen, Charles; Porth, Ilga; El-Kassaby, Yousry A

2015-05-09

Genomic selection (GS) in forestry can substantially reduce the length of breeding cycle and increase gain per unit time through early selection and greater selection intensity, particularly for traits of low heritability and late expression. Affordable next-generation sequencing technologies made it possible to genotype large numbers of trees at a reasonable cost. Genotyping-by-sequencing was used to genotype 1,126 Interior spruce trees representing 25 open-pollinated families planted over three sites in British Columbia, Canada. Four imputation algorithms were compared (mean value (MI), singular value decomposition (SVD), expectation maximization (EM), and a newly derived, family-based k-nearest neighbor (kNN-Fam)). Trees were phenotyped for several yield and wood attributes. Single- and multi-site GS prediction models were developed using the Ridge Regression Best Linear Unbiased Predictor (RR-BLUP) and the Generalized Ridge Regression (GRR) to test different assumption about trait architecture. Finally, using PCA, multi-trait GS prediction models were developed. The EM and kNN-Fam imputation methods were superior for 30 and 60% missing data, respectively. The RR-BLUP GS prediction model produced better accuracies than the GRR indicating that the genetic architecture for these traits is complex. GS prediction accuracies for multi-site were high and better than those of single-sites while multi-site predictability produced the lowest accuracies reflecting type-b genetic correlations and deemed unreliable. The incorporation of genomic information in quantitative genetics analyses produced more realistic heritability estimates as half-sib pedigree tended to inflate the additive genetic variance and subsequently both heritability and gain estimates. Principle component scores as representatives of multi-trait GS prediction models produced surprising results where negatively correlated traits could be concurrently selected for using PCA2 and PCA3. The application of GS to open-pollinated family testing, the simplest form of tree improvement evaluation methods, was proven to be effective. Prediction accuracies obtained for all traits greatly support the integration of GS in tree breeding. While the within-site GS prediction accuracies were high, the results clearly indicate that single-site GS models ability to predict other sites are unreliable supporting the utilization of multi-site approach. Principle component scores provided an opportunity for the concurrent selection of traits with different phenotypic optima.

Development and Validation of Decision Forest Model for Estrogen Receptor Binding Prediction of Chemicals Using Large Data Sets.

PubMed

Ng, Hui Wen; Doughty, Stephen W; Luo, Heng; Ye, Hao; Ge, Weigong; Tong, Weida; Hong, Huixiao

2015-12-21

Some chemicals in the environment possess the potential to interact with the endocrine system in the human body. Multiple receptors are involved in the endocrine system; estrogen receptor α (ERα) plays very important roles in endocrine activity and is the most studied receptor. Understanding and predicting estrogenic activity of chemicals facilitates the evaluation of their endocrine activity. Hence, we have developed a decision forest classification model to predict chemical binding to ERα using a large training data set of 3308 chemicals obtained from the U.S. Food and Drug Administration's Estrogenic Activity Database. We tested the model using cross validations and external data sets of 1641 chemicals obtained from the U.S. Environmental Protection Agency's ToxCast project. The model showed good performance in both internal (92% accuracy) and external validations (∼ 70-89% relative balanced accuracies), where the latter involved the validations of the model across different ER pathway-related assays in ToxCast. The important features that contribute to the prediction ability of the model were identified through informative descriptor analysis and were related to current knowledge of ER binding. Prediction confidence analysis revealed that the model had both high prediction confidence and accuracy for most predicted chemicals. The results demonstrated that the model constructed based on the large training data set is more accurate and robust for predicting ER binding of chemicals than the published models that have been developed using much smaller data sets. The model could be useful for the evaluation of ERα-mediated endocrine activity potential of environmental chemicals.

Predicting the accuracy of ligand overlay methods with Random Forest models.

PubMed

Nandigam, Ravi K; Evans, David A; Erickson, Jon A; Kim, Sangtae; Sutherland, Jeffrey J

2008-12-01

The accuracy of binding mode prediction using standard molecular overlay methods (ROCS, FlexS, Phase, and FieldCompare) is studied. Previous work has shown that simple decision tree modeling can be used to improve accuracy by selection of the best overlay template. This concept is extended to the use of Random Forest (RF) modeling for template and algorithm selection. An extensive data set of 815 ligand-bound X-ray structures representing 5 gene families was used for generating ca. 70,000 overlays using four programs. RF models, trained using standard measures of ligand and protein similarity and Lipinski-related descriptors, are used for automatically selecting the reference ligand and overlay method maximizing the probability of reproducing the overlay deduced from X-ray structures (i.e., using rmsd < or = 2 A as the criteria for success). RF model scores are highly predictive of overlay accuracy, and their use in template and method selection produces correct overlays in 57% of cases for 349 overlay ligands not used for training RF models. The inclusion in the models of protein sequence similarity enables the use of templates bound to related protein structures, yielding useful results even for proteins having no available X-ray structures.

Predicting human olfactory perception from chemical features of odor molecules.

PubMed

Keller, Andreas; Gerkin, Richard C; Guan, Yuanfang; Dhurandhar, Amit; Turu, Gabor; Szalai, Bence; Mainland, Joel D; Ihara, Yusuke; Yu, Chung Wen; Wolfinger, Russ; Vens, Celine; Schietgat, Leander; De Grave, Kurt; Norel, Raquel; Stolovitzky, Gustavo; Cecchi, Guillermo A; Vosshall, Leslie B; Meyer, Pablo

2017-02-24

It is still not possible to predict whether a given molecule will have a perceived odor or what olfactory percept it will produce. We therefore organized the crowd-sourced DREAM Olfaction Prediction Challenge. Using a large olfactory psychophysical data set, teams developed machine-learning algorithms to predict sensory attributes of molecules based on their chemoinformatic features. The resulting models accurately predicted odor intensity and pleasantness and also successfully predicted 8 among 19 rated semantic descriptors ("garlic," "fish," "sweet," "fruit," "burnt," "spices," "flower," and "sour"). Regularized linear models performed nearly as well as random forest-based ones, with a predictive accuracy that closely approaches a key theoretical limit. These models help to predict the perceptual qualities of virtually any molecule with high accuracy and also reverse-engineer the smell of a molecule. Copyright © 2017, American Association for the Advancement of Science.

Evaluating model accuracy for model-based reasoning

NASA Technical Reports Server (NTRS)

Chien, Steve; Roden, Joseph

1992-01-01

Described here is an approach to automatically assessing the accuracy of various components of a model. In this approach, actual data from the operation of a target system is used to drive statistical measures to evaluate the prediction accuracy of various portions of the model. We describe how these statistical measures of model accuracy can be used in model-based reasoning for monitoring and design. We then describe the application of these techniques to the monitoring and design of the water recovery system of the Environmental Control and Life Support System (ECLSS) of Space Station Freedom.

Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks.

PubMed

Catto, James W F; Linkens, Derek A; Abbod, Maysam F; Chen, Minyou; Burton, Julian L; Feeley, Kenneth M; Hamdy, Freddie C

2003-09-15

New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI, have been used successfully, its hidden networks remain an obstacle to its acceptance. Neuro-fuzzy modeling (NFM), another AI method, has a transparent functional layer and is without many of the drawbacks of ANN. We have compared the predictive accuracies of NFM, ANN, and traditional statistical methods, for the behavior of bladder cancer. Experimental molecular biomarkers, including p53 and the mismatch repair proteins, and conventional clinicopathological data were studied in a cohort of 109 patients with bladder cancer. For all three of the methods, models were produced to predict the presence and timing of a tumor relapse. Both methods of AI predicted relapse with an accuracy ranging from 88% to 95%. This was superior to statistical methods (71-77%; P < 0.0006). NFM appeared better than ANN at predicting the timing of relapse (P = 0.073). The use of AI can accurately predict cancer behavior. NFM has a similar or superior predictive accuracy to ANN. However, unlike the impenetrable "black-box" of a neural network, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions. This technique could be used widely in a variety of areas of medicine.

The accuracy of Genomic Selection in Norwegian red cattle assessed by cross-validation.

PubMed

Luan, Tu; Woolliams, John A; Lien, Sigbjørn; Kent, Matthew; Svendsen, Morten; Meuwissen, Theo H E

2009-11-01

Genomic Selection (GS) is a newly developed tool for the estimation of breeding values for quantitative traits through the use of dense markers covering the whole genome. For a successful application of GS, accuracy of the prediction of genomewide breeding value (GW-EBV) is a key issue to consider. Here we investigated the accuracy and possible bias of GW-EBV prediction, using real bovine SNP genotyping (18,991 SNPs) and phenotypic data of 500 Norwegian Red bulls. The study was performed on milk yield, fat yield, protein yield, first lactation mastitis traits, and calving ease. Three methods, best linear unbiased prediction (G-BLUP), Bayesian statistics (BayesB), and a mixture model approach (MIXTURE), were used to estimate marker effects, and their accuracy and bias were estimated by using cross-validation. The accuracies of the GW-EBV prediction were found to vary widely between 0.12 and 0.62. G-BLUP gave overall the highest accuracy. We observed a strong relationship between the accuracy of the prediction and the heritability of the trait. GW-EBV prediction for production traits with high heritability achieved higher accuracy and also lower bias than health traits with low heritability. To achieve a similar accuracy for the health traits probably more records will be needed.

Short-term prediction of solar energy in Saudi Arabia using automated-design fuzzy logic systems

PubMed Central

2017-01-01

Solar energy is considered as one of the main sources for renewable energy in the near future. However, solar energy and other renewable energy sources have a drawback related to the difficulty in predicting their availability in the near future. This problem affects optimal exploitation of solar energy, especially in connection with other resources. Therefore, reliable solar energy prediction models are essential to solar energy management and economics. This paper presents work aimed at designing reliable models to predict the global horizontal irradiance (GHI) for the next day in 8 stations in Saudi Arabia. The designed models are based on computational intelligence methods of automated-design fuzzy logic systems. The fuzzy logic systems are designed and optimized with two models using fuzzy c-means clustering (FCM) and simulated annealing (SA) algorithms. The first model uses FCM based on the subtractive clustering algorithm to automatically design the predictor fuzzy rules from data. The second model is using FCM followed by simulated annealing algorithm to enhance the prediction accuracy of the fuzzy logic system. The objective of the predictor is to accurately predict next-day global horizontal irradiance (GHI) using previous-day meteorological and solar radiation observations. The proposed models use observations of 10 variables of measured meteorological and solar radiation data to build the model. The experimentation and results of the prediction are detailed where the root mean square error of the prediction was approximately 88% for the second model tuned by simulated annealing compared to 79.75% accuracy using the first model. This results demonstrate a good modeling accuracy of the second model despite that the training and testing of the proposed models were carried out using spatially and temporally independent data. PMID:28806754

QSAR Modeling of Rat Acute Toxicity by Oral Exposure

PubMed Central

Zhu, Hao; Martin, Todd M.; Ye, Lin; Sedykh, Alexander; Young, Douglas M.; Tropsha, Alexander

2009-01-01

Few Quantitative Structure-Activity Relationship (QSAR) studies have successfully modeled large, diverse rodent toxicity endpoints. In this study, a comprehensive dataset of 7,385 compounds with their most conservative lethal dose (LD50) values has been compiled. A combinatorial QSAR approach has been employed to develop robust and predictive models of acute toxicity in rats caused by oral exposure to chemicals. To enable fair comparison between the predictive power of models generated in this study versus a commercial toxicity predictor, TOPKAT (Toxicity Prediction by Komputer Assisted Technology), a modeling subset of the entire dataset was selected that included all 3,472 compounds used in the TOPKAT’s training set. The remaining 3,913 compounds, which were not present in the TOPKAT training set, were used as the external validation set. QSAR models of five different types were developed for the modeling set. The prediction accuracy for the external validation set was estimated by determination coefficient R2 of linear regression between actual and predicted LD50 values. The use of the applicability domain threshold implemented in most models generally improved the external prediction accuracy but expectedly led to the decrease in chemical space coverage; depending on the applicability domain threshold, R2 ranged from 0.24 to 0.70. Ultimately, several consensus models were developed by averaging the predicted LD50 for every compound using all 5 models. The consensus models afforded higher prediction accuracy for the external validation dataset with the higher coverage as compared to individual constituent models. The validated consensus LD50 models developed in this study can be used as reliable computational predictors of in vivo acute toxicity. PMID:19845371

Short-term prediction of solar energy in Saudi Arabia using automated-design fuzzy logic systems.

PubMed

Almaraashi, Majid

2017-01-01

Solar energy is considered as one of the main sources for renewable energy in the near future. However, solar energy and other renewable energy sources have a drawback related to the difficulty in predicting their availability in the near future. This problem affects optimal exploitation of solar energy, especially in connection with other resources. Therefore, reliable solar energy prediction models are essential to solar energy management and economics. This paper presents work aimed at designing reliable models to predict the global horizontal irradiance (GHI) for the next day in 8 stations in Saudi Arabia. The designed models are based on computational intelligence methods of automated-design fuzzy logic systems. The fuzzy logic systems are designed and optimized with two models using fuzzy c-means clustering (FCM) and simulated annealing (SA) algorithms. The first model uses FCM based on the subtractive clustering algorithm to automatically design the predictor fuzzy rules from data. The second model is using FCM followed by simulated annealing algorithm to enhance the prediction accuracy of the fuzzy logic system. The objective of the predictor is to accurately predict next-day global horizontal irradiance (GHI) using previous-day meteorological and solar radiation observations. The proposed models use observations of 10 variables of measured meteorological and solar radiation data to build the model. The experimentation and results of the prediction are detailed where the root mean square error of the prediction was approximately 88% for the second model tuned by simulated annealing compared to 79.75% accuracy using the first model. This results demonstrate a good modeling accuracy of the second model despite that the training and testing of the proposed models were carried out using spatially and temporally independent data.

Quantitative structure-activity relationship modeling of rat acute toxicity by oral exposure.

PubMed

Zhu, Hao; Martin, Todd M; Ye, Lin; Sedykh, Alexander; Young, Douglas M; Tropsha, Alexander

2009-12-01

Few quantitative structure-activity relationship (QSAR) studies have successfully modeled large, diverse rodent toxicity end points. In this study, a comprehensive data set of 7385 compounds with their most conservative lethal dose (LD(50)) values has been compiled. A combinatorial QSAR approach has been employed to develop robust and predictive models of acute toxicity in rats caused by oral exposure to chemicals. To enable fair comparison between the predictive power of models generated in this study versus a commercial toxicity predictor, TOPKAT (Toxicity Prediction by Komputer Assisted Technology), a modeling subset of the entire data set was selected that included all 3472 compounds used in TOPKAT's training set. The remaining 3913 compounds, which were not present in the TOPKAT training set, were used as the external validation set. QSAR models of five different types were developed for the modeling set. The prediction accuracy for the external validation set was estimated by determination coefficient R(2) of linear regression between actual and predicted LD(50) values. The use of the applicability domain threshold implemented in most models generally improved the external prediction accuracy but expectedly led to the decrease in chemical space coverage; depending on the applicability domain threshold, R(2) ranged from 0.24 to 0.70. Ultimately, several consensus models were developed by averaging the predicted LD(50) for every compound using all five models. The consensus models afforded higher prediction accuracy for the external validation data set with the higher coverage as compared to individual constituent models. The validated consensus LD(50) models developed in this study can be used as reliable computational predictors of in vivo acute toxicity.

The RAPIDD ebola forecasting challenge: Synthesis and lessons learnt.

PubMed

Viboud, Cécile; Sun, Kaiyuan; Gaffey, Robert; Ajelli, Marco; Fumanelli, Laura; Merler, Stefano; Zhang, Qian; Chowell, Gerardo; Simonsen, Lone; Vespignani, Alessandro

2018-03-01

Infectious disease forecasting is gaining traction in the public health community; however, limited systematic comparisons of model performance exist. Here we present the results of a synthetic forecasting challenge inspired by the West African Ebola crisis in 2014-2015 and involving 16 international academic teams and US government agencies, and compare the predictive performance of 8 independent modeling approaches. Challenge participants were invited to predict 140 epidemiological targets across 5 different time points of 4 synthetic Ebola outbreaks, each involving different levels of interventions and "fog of war" in outbreak data made available for predictions. Prediction targets included 1-4 week-ahead case incidences, outbreak size, peak timing, and several natural history parameters. With respect to weekly case incidence targets, ensemble predictions based on a Bayesian average of the 8 participating models outperformed any individual model and did substantially better than a null auto-regressive model. There was no relationship between model complexity and prediction accuracy; however, the top performing models for short-term weekly incidence were reactive models with few parameters, fitted to a short and recent part of the outbreak. Individual model outputs and ensemble predictions improved with data accuracy and availability; by the second time point, just before the peak of the epidemic, estimates of final size were within 20% of the target. The 4th challenge scenario - mirroring an uncontrolled Ebola outbreak with substantial data reporting noise - was poorly predicted by all modeling teams. Overall, this synthetic forecasting challenge provided a deep understanding of model performance under controlled data and epidemiological conditions. We recommend such "peace time" forecasting challenges as key elements to improve coordination and inspire collaboration between modeling groups ahead of the next pandemic threat, and to assess model forecasting accuracy for a variety of known and hypothetical pathogens. Published by Elsevier B.V.

Predicting the biological condition of streams: Use of geospatial indicators of natural and anthropogenic characteristics of watersheds

USGS Publications Warehouse

Carlisle, D.M.; Falcone, J.; Meador, M.R.

2009-01-01

We developed and evaluated empirical models to predict biological condition of wadeable streams in a large portion of the eastern USA, with the ultimate goal of prediction for unsampled basins. Previous work had classified (i.e., altered vs. unaltered) the biological condition of 920 streams based on a biological assessment of macroinvertebrate assemblages. Predictor variables were limited to widely available geospatial data, which included land cover, topography, climate, soils, societal infrastructure, and potential hydrologic modification. We compared the accuracy of predictions of biological condition class based on models with continuous and binary responses. We also evaluated the relative importance of specific groups and individual predictor variables, as well as the relationships between the most important predictors and biological condition. Prediction accuracy and the relative importance of predictor variables were different for two subregions for which models were created. Predictive accuracy in the highlands region improved by including predictors that represented both natural and human activities. Riparian land cover and road-stream intersections were the most important predictors. In contrast, predictive accuracy in the lowlands region was best for models limited to predictors representing natural factors, including basin topography and soil properties. Partial dependence plots revealed complex and nonlinear relationships between specific predictors and the probability of biological alteration. We demonstrate a potential application of the model by predicting biological condition in 552 unsampled basins across an ecoregion in southeastern Wisconsin (USA). Estimates of the likelihood of biological condition of unsampled streams could be a valuable tool for screening large numbers of basins to focus targeted monitoring of potentially unaltered or altered stream segments. ?? Springer Science+Business Media B.V. 2008.

Improving risk prediction accuracy for new soldiers in the U.S. Army by adding self-report survey data to administrative data.

PubMed

Bernecker, Samantha L; Rosellini, Anthony J; Nock, Matthew K; Chiu, Wai Tat; Gutierrez, Peter M; Hwang, Irving; Joiner, Thomas E; Naifeh, James A; Sampson, Nancy A; Zaslavsky, Alan M; Stein, Murray B; Ursano, Robert J; Kessler, Ronald C

2018-04-03

High rates of mental disorders, suicidality, and interpersonal violence early in the military career have raised interest in implementing preventive interventions with high-risk new enlistees. The Army Study to Assess Risk and Resilience in Servicemembers (STARRS) developed risk-targeting systems for these outcomes based on machine learning methods using administrative data predictors. However, administrative data omit many risk factors, raising the question whether risk targeting could be improved by adding self-report survey data to prediction models. If so, the Army may gain from routinely administering surveys that assess additional risk factors. The STARRS New Soldier Survey was administered to 21,790 Regular Army soldiers who agreed to have survey data linked to administrative records. As reported previously, machine learning models using administrative data as predictors found that small proportions of high-risk soldiers accounted for high proportions of negative outcomes. Other machine learning models using self-report survey data as predictors were developed previously for three of these outcomes: major physical violence and sexual violence perpetration among men and sexual violence victimization among women. Here we examined the extent to which this survey information increases prediction accuracy, over models based solely on administrative data, for those three outcomes. We used discrete-time survival analysis to estimate a series of models predicting first occurrence, assessing how model fit improved and concentration of risk increased when adding the predicted risk score based on survey data to the predicted risk score based on administrative data. The addition of survey data improved prediction significantly for all outcomes. In the most extreme case, the percentage of reported sexual violence victimization among the 5% of female soldiers with highest predicted risk increased from 17.5% using only administrative predictors to 29.4% adding survey predictors, a 67.9% proportional increase in prediction accuracy. Other proportional increases in concentration of risk ranged from 4.8% to 49.5% (median = 26.0%). Data from an ongoing New Soldier Survey could substantially improve accuracy of risk models compared to models based exclusively on administrative predictors. Depending upon the characteristics of interventions used, the increase in targeting accuracy from survey data might offset survey administration costs.

Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran.

PubMed

Azadi, Sama; Karimi-Jashni, Ayoub

2016-02-01

Predicting the mass of solid waste generation plays an important role in integrated solid waste management plans. In this study, the performance of two predictive models, Artificial Neural Network (ANN) and Multiple Linear Regression (MLR) was verified to predict mean Seasonal Municipal Solid Waste Generation (SMSWG) rate. The accuracy of the proposed models is illustrated through a case study of 20 cities located in Fars Province, Iran. Four performance measures, MAE, MAPE, RMSE and R were used to evaluate the performance of these models. The MLR, as a conventional model, showed poor prediction performance. On the other hand, the results indicated that the ANN model, as a non-linear model, has a higher predictive accuracy when it comes to prediction of the mean SMSWG rate. As a result, in order to develop a more cost-effective strategy for waste management in the future, the ANN model could be used to predict the mean SMSWG rate. Copyright © 2015 Elsevier Ltd. All rights reserved.

A genome-scale metabolic flux model of Escherichia coli K–12 derived from the EcoCyc database

PubMed Central

2014-01-01

Background Constraint-based models of Escherichia coli metabolic flux have played a key role in computational studies of cellular metabolism at the genome scale. We sought to develop a next-generation constraint-based E. coli model that achieved improved phenotypic prediction accuracy while being frequently updated and easy to use. We also sought to compare model predictions with experimental data to highlight open questions in E. coli biology. Results We present EcoCyc–18.0–GEM, a genome-scale model of the E. coli K–12 MG1655 metabolic network. The model is automatically generated from the current state of EcoCyc using the MetaFlux software, enabling the release of multiple model updates per year. EcoCyc–18.0–GEM encompasses 1445 genes, 2286 unique metabolic reactions, and 1453 unique metabolites. We demonstrate a three-part validation of the model that breaks new ground in breadth and accuracy: (i) Comparison of simulated growth in aerobic and anaerobic glucose culture with experimental results from chemostat culture and simulation results from the E. coli modeling literature. (ii) Essentiality prediction for the 1445 genes represented in the model, in which EcoCyc–18.0–GEM achieves an improved accuracy of 95.2% in predicting the growth phenotype of experimental gene knockouts. (iii) Nutrient utilization predictions under 431 different media conditions, for which the model achieves an overall accuracy of 80.7%. The model’s derivation from EcoCyc enables query and visualization via the EcoCyc website, facilitating model reuse and validation by inspection. We present an extensive investigation of disagreements between EcoCyc–18.0–GEM predictions and experimental data to highlight areas of interest to E. coli modelers and experimentalists, including 70 incorrect predictions of gene essentiality on glucose, 80 incorrect predictions of gene essentiality on glycerol, and 83 incorrect predictions of nutrient utilization. Conclusion Significant advantages can be derived from the combination of model organism databases and flux balance modeling represented by MetaFlux. Interpretation of the EcoCyc database as a flux balance model results in a highly accurate metabolic model and provides a rigorous consistency check for information stored in the database. PMID:24974895

A Flexible Spatio-Temporal Model for Air Pollution with Spatial and Spatio-Temporal Covariates.

PubMed

Lindström, Johan; Szpiro, Adam A; Sampson, Paul D; Oron, Assaf P; Richards, Mark; Larson, Tim V; Sheppard, Lianne

2014-09-01

The development of models that provide accurate spatio-temporal predictions of ambient air pollution at small spatial scales is of great importance for the assessment of potential health effects of air pollution. Here we present a spatio-temporal framework that predicts ambient air pollution by combining data from several different monitoring networks and deterministic air pollution model(s) with geographic information system (GIS) covariates. The model presented in this paper has been implemented in an R package, SpatioTemporal, available on CRAN. The model is used by the EPA funded Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air) to produce estimates of ambient air pollution; MESA Air uses the estimates to investigate the relationship between chronic exposure to air pollution and cardiovascular disease. In this paper we use the model to predict long-term average concentrations of NO x in the Los Angeles area during a ten year period. Predictions are based on measurements from the EPA Air Quality System, MESA Air specific monitoring, and output from a source dispersion model for traffic related air pollution (Caline3QHCR). Accuracy in predicting long-term average concentrations is evaluated using an elaborate cross-validation setup that accounts for a sparse spatio-temporal sampling pattern in the data, and adjusts for temporal effects. The predictive ability of the model is good with cross-validated R 2 of approximately 0.7 at subject sites. Replacing four geographic covariate indicators of traffic density with the Caline3QHCR dispersion model output resulted in very similar prediction accuracy from a more parsimonious and more interpretable model. Adding traffic-related geographic covariates to the model that included Caline3QHCR did not further improve the prediction accuracy.

Data Prediction for Public Events in Professional Domains Based on Improved RNN- LSTM

NASA Astrophysics Data System (ADS)

Song, Bonan; Fan, Chunxiao; Wu, Yuexin; Sun, Juanjuan

2018-02-01

The traditional data services of prediction for emergency or non-periodic events usually cannot generate satisfying result or fulfill the correct prediction purpose. However, these events are influenced by external causes, which mean certain a priori information of these events generally can be collected through the Internet. This paper studied the above problems and proposed an improved model—LSTM (Long Short-term Memory) dynamic prediction and a priori information sequence generation model by combining RNN-LSTM and public events a priori information. In prediction tasks, the model is qualified for determining trends, and its accuracy also is validated. This model generates a better performance and prediction results than the previous one. Using a priori information can increase the accuracy of prediction; LSTM can better adapt to the changes of time sequence; LSTM can be widely applied to the same type of prediction tasks, and other prediction tasks related to time sequence.

Iowa calibration of MEPDG performance prediction models.

DOT National Transportation Integrated Search

2013-06-01

This study aims to improve the accuracy of AASHTO Mechanistic-Empirical Pavement Design Guide (MEPDG) pavement : performance predictions for Iowa pavement systems through local calibration of MEPDG prediction models. A total of 130 : representative p...

Predicting grain yield using canopy hyperspectral reflectance in wheat breeding data.

PubMed

Montesinos-López, Osval A; Montesinos-López, Abelardo; Crossa, José; de Los Campos, Gustavo; Alvarado, Gregorio; Suchismita, Mondal; Rutkoski, Jessica; González-Pérez, Lorena; Burgueño, Juan

2017-01-01

Modern agriculture uses hyperspectral cameras to obtain hundreds of reflectance data measured at discrete narrow bands to cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra, depending on the camera. This information is used to construct vegetation indices (VI) (e.g., green normalized difference vegetation index or GNDVI, simple ratio or SRa, etc.) which are used for the prediction of primary traits (e.g., biomass). However, these indices only use some bands and are cultivar-specific; therefore they lose considerable information and are not robust for all cultivars. This study proposes models that use all available bands as predictors to increase prediction accuracy; we compared these approaches with eight conventional vegetation indexes (VIs) constructed using only some bands. The data set we used comes from CIMMYT's global wheat program and comprises 1170 genotypes evaluated for grain yield (ton/ha) in five environments (Drought, Irrigated, EarlyHeat, Melgas and Reduced Irrigated); the reflectance data were measured in 250 discrete narrow bands ranging between 392 and 851 nm. The proposed models for the simultaneous analysis of all the bands were ordinal least square (OLS), Bayes B, principal components with Bayes B, functional B-spline, functional Fourier and functional partial least square. The results of these models were compared with the OLS performed using as predictors each of the eight VIs individually and combined. We found that using all bands simultaneously increased prediction accuracy more than using VI alone. The Splines and Fourier models had the best prediction accuracy for each of the nine time-points under study. Combining image data collected at different time-points led to a small increase in prediction accuracy relative to models that use data from a single time-point. Also, using bands with heritabilities larger than 0.5 only in Drought as predictor variables showed improvements in prediction accuracy.

RNA secondary structure prediction with pseudoknots: Contribution of algorithm versus energy model.

PubMed

Jabbari, Hosna; Wark, Ian; Montemagno, Carlo

2018-01-01

RNA is a biopolymer with various applications inside the cell and in biotechnology. Structure of an RNA molecule mainly determines its function and is essential to guide nanostructure design. Since experimental structure determination is time-consuming and expensive, accurate computational prediction of RNA structure is of great importance. Prediction of RNA secondary structure is relatively simpler than its tertiary structure and provides information about its tertiary structure, therefore, RNA secondary structure prediction has received attention in the past decades. Numerous methods with different folding approaches have been developed for RNA secondary structure prediction. While methods for prediction of RNA pseudoknot-free structure (structures with no crossing base pairs) have greatly improved in terms of their accuracy, methods for prediction of RNA pseudoknotted secondary structure (structures with crossing base pairs) still have room for improvement. A long-standing question for improving the prediction accuracy of RNA pseudoknotted secondary structure is whether to focus on the prediction algorithm or the underlying energy model, as there is a trade-off on computational cost of the prediction algorithm versus the generality of the method. The aim of this work is to argue when comparing different methods for RNA pseudoknotted structure prediction, the combination of algorithm and energy model should be considered and a method should not be considered superior or inferior to others if they do not use the same scoring model. We demonstrate that while the folding approach is important in structure prediction, it is not the only important factor in prediction accuracy of a given method as the underlying energy model is also as of great value. Therefore we encourage researchers to pay particular attention in comparing methods with different energy models.

A multivariate model for predicting segmental body composition.

PubMed

Tian, Simiao; Mioche, Laurence; Denis, Jean-Baptiste; Morio, Béatrice

2013-12-01

The aims of the present study were to propose a multivariate model for predicting simultaneously body, trunk and appendicular fat and lean masses from easily measured variables and to compare its predictive capacity with that of the available univariate models that predict body fat percentage (BF%). The dual-energy X-ray absorptiometry (DXA) dataset (52% men and 48% women) with White, Black and Hispanic ethnicities (1999-2004, National Health and Nutrition Examination Survey) was randomly divided into three sub-datasets: a training dataset (TRD), a test dataset (TED); a validation dataset (VAD), comprising 3835, 1917 and 1917 subjects. For each sex, several multivariate prediction models were fitted from the TRD using age, weight, height and possibly waist circumference. The most accurate model was selected from the TED and then applied to the VAD and a French DXA dataset (French DB) (526 men and 529 women) to assess the prediction accuracy in comparison with that of five published univariate models, for which adjusted formulas were re-estimated using the TRD. Waist circumference was found to improve the prediction accuracy, especially in men. For BF%, the standard error of prediction (SEP) values were 3.26 (3.75) % for men and 3.47 (3.95)% for women in the VAD (French DB), as good as those of the adjusted univariate models. Moreover, the SEP values for the prediction of body and appendicular lean masses ranged from 1.39 to 2.75 kg for both the sexes. The prediction accuracy was best for age < 65 years, BMI < 30 kg/m2 and the Hispanic ethnicity. The application of our multivariate model to large populations could be useful to address various public health issues.

Lunar Reconnaissance Orbiter Orbit Determination Accuracy Analysis

NASA Technical Reports Server (NTRS)

Slojkowski, Steven E.

2014-01-01

Results from operational OD produced by the NASA Goddard Flight Dynamics Facility for the LRO nominal and extended mission are presented. During the LRO nominal mission, when LRO flew in a low circular orbit, orbit determination requirements were met nearly 100% of the time. When the extended mission began, LRO returned to a more elliptical frozen orbit where gravity and other modeling errors caused numerous violations of mission accuracy requirements. Prediction accuracy is particularly challenged during periods when LRO is in full-Sun. A series of improvements to LRO orbit determination are presented, including implementation of new lunar gravity models, improved spacecraft solar radiation pressure modeling using a dynamic multi-plate area model, a shorter orbit determination arc length, and a constrained plane method for estimation. The analysis presented in this paper shows that updated lunar gravity models improved accuracy in the frozen orbit, and a multiplate dynamic area model improves prediction accuracy during full-Sun orbit periods. Implementation of a 36-hour tracking data arc and plane constraints during edge-on orbit geometry also provide benefits. A comparison of the operational solutions to precision orbit determination solutions shows agreement on a 100- to 250-meter level in definitive accuracy.

Prediction of high-energy radiation belt electron fluxes using a combined VERB-NARMAX model

NASA Astrophysics Data System (ADS)

Pakhotin, I. P.; Balikhin, M. A.; Shprits, Y.; Subbotin, D.; Boynton, R.

2013-12-01

This study is concerned with the modelling and forecasting of energetic electron fluxes that endanger satellites in space. By combining data-driven predictions from the NARMAX methodology with the physics-based VERB code, it becomes possible to predict electron fluxes with a high level of accuracy and across a radial distance from inside the local acceleration region to out beyond geosynchronous orbit. The model coupling also makes is possible to avoid accounting for seed electron variations at the outer boundary. Conversely, combining a convection code with the VERB and NARMAX models has the potential to provide even greater accuracy in forecasting that is not limited to geostationary orbit but makes predictions across the entire outer radiation belt region.

Analysis and correlation of the test data from an advanced technology rotor system

NASA Technical Reports Server (NTRS)

Jepson, D.; Moffitt, R.; Hilzinger, K.; Bissell, J.

1983-01-01

Comparisons were made of the performance and blade vibratory loads characteristics for an advanced rotor system as predicted by analysis and as measured in a 1/5 scale model wind tunnel test, a full scale model wind tunnel test and flight test. The accuracy with which the various tools available at the various stages in the design/development process (analysis, model test etc.) could predict final characteristics as measured on the aircraft was determined. The accuracy of the analyses in predicting the effects of systematic tip planform variations investigated in the full scale wind tunnel test was evaluated.

Calibration of PMIS pavement performance prediction models.

DOT National Transportation Integrated Search

2012-02-01

Improve the accuracy of TxDOTs existing pavement performance prediction models through calibrating these models using actual field data obtained from the Pavement Management Information System (PMIS). : Ensure logical performance superiority patte...

PREDICTING CLIMATE-INDUCED RANGE SHIFTS: MODEL DIFFERENCES AND MODEL RELIABILITY

EPA Science Inventory

Predicted changes in the global climate are likely to cause large shifts in the geographic ranges of many plant and animal species. To date, predictions of future range shifts have relied on a variety of modeling approaches with different levels of model accuracy. Using a common ...

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

NASA Astrophysics Data System (ADS)

Zhan, Liwei; Li, Chengwei

2017-02-01

A hybrid PSO-SVM-based model is proposed to predict the friction coefficient between aircraft tire and coating. The presented hybrid model combines a support vector machine (SVM) with particle swarm optimization (PSO) technique. SVM has been adopted to solve regression problems successfully. Its regression accuracy is greatly related to optimizing parameters such as the regularization constant C , the parameter gamma γ corresponding to RBF kernel and the epsilon parameter \\varepsilon in the SVM training procedure. However, the friction coefficient which is predicted based on SVM has yet to be explored between aircraft tire and coating. The experiment reveals that drop height and tire rotational speed are the factors affecting friction coefficient. Bearing in mind, the friction coefficient can been predicted using the hybrid PSO-SVM-based model by the measured friction coefficient between aircraft tire and coating. To compare regression accuracy, a grid search (GS) method and a genetic algorithm (GA) are used to optimize the relevant parameters (C , γ and \\varepsilon ), respectively. The regression accuracy could be reflected by the coefficient of determination ({{R}2} ). The result shows that the hybrid PSO-RBF-SVM-based model has better accuracy compared with the GS-RBF-SVM- and GA-RBF-SVM-based models. The agreement of this model (PSO-RBF-SVM) with experiment data confirms its good performance.

A reexamination of age-related variation in body weight and morphometry of Maryland nutria

USGS Publications Warehouse

Sherfy, M.H.; Mollett, T.A.; McGowan, K.R.; Daugherty, S.L.

2006-01-01

Age-related variation in morphometry has been documented for many species. Knowledge of growth patterns can be useful for modeling energetics, detecting physiological influences on populations, and predicting age. These benefits have shown value in understanding population dynamics of invasive species, particularly in developing efficient control and eradication programs. However, development and evaluation of descriptive and predictive models is a critical initial step in this process. Accordingly, we used data from necropsies of 1,544 nutria (Myocastor coypus) collected in Maryland, USA, to evaluate the accuracy of previously published models for prediction of nutria age from body weight. Published models underestimated body weights of our animals, especially for ages <3. We used cross-validation procedures to develop and evaluate models for describing nutria growth patterns and for predicting nutria age. We derived models from a randomly selected model-building data set (n = 192-193 M, 217-222 F) and evaluated them with the remaining animals (n = 487-488 M, 642-647 F). We used nonlinear regression to develop Gompertz growth-curve models relating morphometric variables to age. Predicted values of morphometric variables fell within the 95% confidence limits of their true values for most age classes. We also developed predictive models for estimating nutria age from morphometry, using linear regression of log-transformed age on morphometric variables. The evaluation data set corresponded with 95% prediction intervals from the new models. Predictive models for body weight and length provided greater accuracy and less bias than models for foot length and axillary girth. Our growth models accurately described age-related variation in nutria morphometry, and our predictive models provided accurate estimates of ages from morphometry that will be useful for live-captured individuals. Our models offer better accuracy and precision than previously published models, providing a capacity for modeling energetics and growth patterns of Maryland nutria as well as an empirical basis for determining population age structure from live-captured animals.

Protein Secondary Structure Prediction Using AutoEncoder Network and Bayes Classifier

NASA Astrophysics Data System (ADS)

Wang, Leilei; Cheng, Jinyong

2018-03-01

Protein secondary structure prediction is belong to bioinformatics,and it's important in research area. In this paper, we propose a new prediction way of protein using bayes classifier and autoEncoder network. Our experiments show some algorithms including the construction of the model, the classification of parameters and so on. The data set is a typical CB513 data set for protein. In terms of accuracy, the method is the cross validation based on the 3-fold. Then we can get the Q3 accuracy. Paper results illustrate that the autoencoder network improved the prediction accuracy of protein secondary structure.

Accuracy of travel time distribution (TTD) models as affected by TTD complexity, observation errors, and model and tracer selection

USGS Publications Warehouse

Green, Christopher T.; Zhang, Yong; Jurgens, Bryant C.; Starn, J. Jeffrey; Landon, Matthew K.

2014-01-01

Analytical models of the travel time distribution (TTD) from a source area to a sample location are often used to estimate groundwater ages and solute concentration trends. The accuracies of these models are not well known for geologically complex aquifers. In this study, synthetic datasets were used to quantify the accuracy of four analytical TTD models as affected by TTD complexity, observation errors, model selection, and tracer selection. Synthetic TTDs and tracer data were generated from existing numerical models with complex hydrofacies distributions for one public-supply well and 14 monitoring wells in the Central Valley, California. Analytical TTD models were calibrated to synthetic tracer data, and prediction errors were determined for estimates of TTDs and conservative tracer (NO3−) concentrations. Analytical models included a new, scale-dependent dispersivity model (SDM) for two-dimensional transport from the watertable to a well, and three other established analytical models. The relative influence of the error sources (TTD complexity, observation error, model selection, and tracer selection) depended on the type of prediction. Geological complexity gave rise to complex TTDs in monitoring wells that strongly affected errors of the estimated TTDs. However, prediction errors for NO3− and median age depended more on tracer concentration errors. The SDM tended to give the most accurate estimates of the vertical velocity and other predictions, although TTD model selection had minor effects overall. Adding tracers improved predictions if the new tracers had different input histories. Studies using TTD models should focus on the factors that most strongly affect the desired predictions.

Improving accuracy of genomic prediction in Brangus cattle by adding animals with imputed low-density SNP genotypes.

PubMed

Lopes, F B; Wu, X-L; Li, H; Xu, J; Perkins, T; Genho, J; Ferretti, R; Tait, R G; Bauck, S; Rosa, G J M

2018-02-01

Reliable genomic prediction of breeding values for quantitative traits requires the availability of sufficient number of animals with genotypes and phenotypes in the training set. As of 31 October 2016, there were 3,797 Brangus animals with genotypes and phenotypes. These Brangus animals were genotyped using different commercial SNP chips. Of them, the largest group consisted of 1,535 animals genotyped by the GGP-LDV4 SNP chip. The remaining 2,262 genotypes were imputed to the SNP content of the GGP-LDV4 chip, so that the number of animals available for training the genomic prediction models was more than doubled. The present study showed that the pooling of animals with both original or imputed 40K SNP genotypes substantially increased genomic prediction accuracies on the ten traits. By supplementing imputed genotypes, the relative gains in genomic prediction accuracies on estimated breeding values (EBV) were from 12.60% to 31.27%, and the relative gain in genomic prediction accuracies on de-regressed EBV was slightly small (i.e. 0.87%-18.75%). The present study also compared the performance of five genomic prediction models and two cross-validation methods. The five genomic models predicted EBV and de-regressed EBV of the ten traits similarly well. Of the two cross-validation methods, leave-one-out cross-validation maximized the number of animals at the stage of training for genomic prediction. Genomic prediction accuracy (GPA) on the ten quantitative traits was validated in 1,106 newly genotyped Brangus animals based on the SNP effects estimated in the previous set of 3,797 Brangus animals, and they were slightly lower than GPA in the original data. The present study was the first to leverage currently available genotype and phenotype resources in order to harness genomic prediction in Brangus beef cattle. © 2018 Blackwell Verlag GmbH.

Prediction of composite fatigue life under variable amplitude loading using artificial neural network trained by genetic algorithm

NASA Astrophysics Data System (ADS)

Rohman, Muhamad Nur; Hidayat, Mas Irfan P.; Purniawan, Agung

2018-04-01

Neural networks (NN) have been widely used in application of fatigue life prediction. In the use of fatigue life prediction for polymeric-base composite, development of NN model is necessary with respect to the limited fatigue data and applicable to be used to predict the fatigue life under varying stress amplitudes in the different stress ratios. In the present paper, Multilayer-Perceptrons (MLP) model of neural network is developed, and Genetic Algorithm was employed to optimize the respective weights of NN for prediction of polymeric-base composite materials under variable amplitude loading. From the simulation result obtained with two different composite systems, named E-glass fabrics/epoxy (layups [(±45)/(0)2]S), and E-glass/polyester (layups [90/0/±45/0]S), NN model were trained with fatigue data from two different stress ratios, which represent limited fatigue data, can be used to predict another four and seven stress ratios respectively, with high accuracy of fatigue life prediction. The accuracy of NN prediction were quantified with the small value of mean square error (MSE). When using 33% from the total fatigue data for training, the NN model able to produce high accuracy for all stress ratios. When using less fatigue data during training (22% from the total fatigue data), the NN model still able to produce high coefficient of determination between the prediction result compared with obtained by experiment.

Mixed Model Methods for Genomic Prediction and Variance Component Estimation of Additive and Dominance Effects Using SNP Markers

PubMed Central

Da, Yang; Wang, Chunkao; Wang, Shengwen; Hu, Guo

2014-01-01

We established a genomic model of quantitative trait with genomic additive and dominance relationships that parallels the traditional quantitative genetics model, which partitions a genotypic value as breeding value plus dominance deviation and calculates additive and dominance relationships using pedigree information. Based on this genomic model, two sets of computationally complementary but mathematically identical mixed model methods were developed for genomic best linear unbiased prediction (GBLUP) and genomic restricted maximum likelihood estimation (GREML) of additive and dominance effects using SNP markers. These two sets are referred to as the CE and QM sets, where the CE set was designed for large numbers of markers and the QM set was designed for large numbers of individuals. GBLUP and associated accuracy formulations for individuals in training and validation data sets were derived for breeding values, dominance deviations and genotypic values. Simulation study showed that GREML and GBLUP generally were able to capture small additive and dominance effects that each accounted for 0.00005–0.0003 of the phenotypic variance and GREML was able to differentiate true additive and dominance heritability levels. GBLUP of the total genetic value as the summation of additive and dominance effects had higher prediction accuracy than either additive or dominance GBLUP, causal variants had the highest accuracy of GREML and GBLUP, and predicted accuracies were in agreement with observed accuracies. Genomic additive and dominance relationship matrices using SNP markers were consistent with theoretical expectations. The GREML and GBLUP methods can be an effective tool for assessing the type and magnitude of genetic effects affecting a phenotype and for predicting the total genetic value at the whole genome level. PMID:24498162

Mixed model methods for genomic prediction and variance component estimation of additive and dominance effects using SNP markers.

PubMed

Da, Yang; Wang, Chunkao; Wang, Shengwen; Hu, Guo

2014-01-01

We established a genomic model of quantitative trait with genomic additive and dominance relationships that parallels the traditional quantitative genetics model, which partitions a genotypic value as breeding value plus dominance deviation and calculates additive and dominance relationships using pedigree information. Based on this genomic model, two sets of computationally complementary but mathematically identical mixed model methods were developed for genomic best linear unbiased prediction (GBLUP) and genomic restricted maximum likelihood estimation (GREML) of additive and dominance effects using SNP markers. These two sets are referred to as the CE and QM sets, where the CE set was designed for large numbers of markers and the QM set was designed for large numbers of individuals. GBLUP and associated accuracy formulations for individuals in training and validation data sets were derived for breeding values, dominance deviations and genotypic values. Simulation study showed that GREML and GBLUP generally were able to capture small additive and dominance effects that each accounted for 0.00005-0.0003 of the phenotypic variance and GREML was able to differentiate true additive and dominance heritability levels. GBLUP of the total genetic value as the summation of additive and dominance effects had higher prediction accuracy than either additive or dominance GBLUP, causal variants had the highest accuracy of GREML and GBLUP, and predicted accuracies were in agreement with observed accuracies. Genomic additive and dominance relationship matrices using SNP markers were consistent with theoretical expectations. The GREML and GBLUP methods can be an effective tool for assessing the type and magnitude of genetic effects affecting a phenotype and for predicting the total genetic value at the whole genome level.

Utilizing multiple scale models to improve predictions of extra-axial hemorrhage in the immature piglet.

PubMed

Scott, Gregory G; Margulies, Susan S; Coats, Brittany

2016-10-01

Traumatic brain injury (TBI) is a leading cause of death and disability in the USA. To help understand and better predict TBI, researchers have developed complex finite element (FE) models of the head which incorporate many biological structures such as scalp, skull, meninges, brain (with gray/white matter differentiation), and vasculature. However, most models drastically simplify the membranes and substructures between the pia and arachnoid membranes. We hypothesize that substructures in the pia-arachnoid complex (PAC) contribute substantially to brain deformation following head rotation, and that when included in FE models accuracy of extra-axial hemorrhage prediction improves. To test these hypotheses, microscale FE models of the PAC were developed to span the variability of PAC substructure anatomy and regional density. The constitutive response of these models were then integrated into an existing macroscale FE model of the immature piglet brain to identify changes in cortical stress distribution and predictions of extra-axial hemorrhage (EAH). Incorporating regional variability of PAC substructures substantially altered the distribution of principal stress on the cortical surface of the brain compared to a uniform representation of the PAC. Simulations of 24 non-impact rapid head rotations in an immature piglet animal model resulted in improved accuracy of EAH prediction (to 94 % sensitivity, 100 % specificity), as well as a high accuracy in regional hemorrhage prediction (to 82-100 % sensitivity, 100 % specificity). We conclude that including a biofidelic PAC substructure variability in FE models of the head is essential for improved predictions of hemorrhage at the brain/skull interface.

Bayesian model aggregation for ensemble-based estimates of protein pKa values

DOE Office of Scientific and Technical Information (OSTI.GOV)

Gosink, Luke J.; Hogan, Emilie A.; Pulsipher, Trenton C.

2014-03-01

This paper investigates an ensemble-based technique called Bayesian Model Averaging (BMA) to improve the performance of protein amino acid pmore » $$K_a$$ predictions. Structure-based p$$K_a$$ calculations play an important role in the mechanistic interpretation of protein structure and are also used to determine a wide range of protein properties. A diverse set of methods currently exist for p$$K_a$$ prediction, ranging from empirical statistical models to {\\it ab initio} quantum mechanical approaches. However, each of these methods are based on a set of assumptions that have inherent bias and sensitivities that can effect a model's accuracy and generalizability for p$$K_a$$ prediction in complicated biomolecular systems. We use BMA to combine eleven diverse prediction methods that each estimate pKa values of amino acids in staphylococcal nuclease. These methods are based on work conducted for the pKa Cooperative and the pKa measurements are based on experimental work conducted by the Garc{\\'i}a-Moreno lab. Our study demonstrates that the aggregated estimate obtained from BMA outperforms all individual prediction methods in our cross-validation study with improvements from 40-70\\% over other method classes. This work illustrates a new possible mechanism for improving the accuracy of p$$K_a$$ prediction and lays the foundation for future work on aggregate models that balance computational cost with prediction accuracy.« less

Accuracy of three-dimensional facial soft tissue simulation in post-traumatic zygoma reconstruction.

PubMed

Li, P; Zhou, Z W; Ren, J Y; Zhang, Y; Tian, W D; Tang, W

2016-12-01

The aim of this study was to evaluate the accuracy of novel software-CMF-preCADS-for the prediction of soft tissue changes following repositioning surgery for zygomatic fractures. Twenty patients who had sustained an isolated zygomatic fracture accompanied by facial deformity and who were treated with repositioning surgery participated in this study. Cone beam computed tomography (CBCT) scans and three-dimensional (3D) stereophotographs were acquired preoperatively and postoperatively. The 3D skeletal model from the preoperative CBCT data was matched with the postoperative one, and the fractured zygomatic fragments were segmented and aligned to the postoperative position for prediction. Then, the predicted model was matched with the postoperative 3D stereophotograph for quantification of the simulation error. The mean absolute error in the zygomatic soft tissue region between the predicted model and the real one was 1.42±1.56mm for all cases. The accuracy of the prediction (mean absolute error ≤2mm) was 87%. In the subjective assessment it was found that the majority of evaluators considered the predicted model and the postoperative model to be 'very similar'. CMF-preCADS software can provide a realistic, accurate prediction of the facial soft tissue appearance after repositioning surgery for zygomatic fractures. The reliability of this software for other types of repositioning surgery for maxillofacial fractures should be validated in the future. Copyright © 2016. Published by Elsevier Ltd.

Software reliability studies

NASA Technical Reports Server (NTRS)

Hoppa, Mary Ann; Wilson, Larry W.

1994-01-01

There are many software reliability models which try to predict future performance of software based on data generated by the debugging process. Our research has shown that by improving the quality of the data one can greatly improve the predictions. We are working on methodologies which control some of the randomness inherent in the standard data generation processes in order to improve the accuracy of predictions. Our contribution is twofold in that we describe an experimental methodology using a data structure called the debugging graph and apply this methodology to assess the robustness of existing models. The debugging graph is used to analyze the effects of various fault recovery orders on the predictive accuracy of several well-known software reliability algorithms. We found that, along a particular debugging path in the graph, the predictive performance of different models can vary greatly. Similarly, just because a model 'fits' a given path's data well does not guarantee that the model would perform well on a different path. Further we observed bug interactions and noted their potential effects on the predictive process. We saw that not only do different faults fail at different rates, but that those rates can be affected by the particular debugging stage at which the rates are evaluated. Based on our experiment, we conjecture that the accuracy of a reliability prediction is affected by the fault recovery order as well as by fault interaction.

Assessing the capacity of social determinants of health data to augment predictive models identifying patients in need of wraparound social services.

PubMed

Kasthurirathne, Suranga N; Vest, Joshua R; Menachemi, Nir; Halverson, Paul K; Grannis, Shaun J

2018-01-01

A growing variety of diverse data sources is emerging to better inform health care delivery and health outcomes. We sought to evaluate the capacity for clinical, socioeconomic, and public health data sources to predict the need for various social service referrals among patients at a safety-net hospital. We integrated patient clinical data and community-level data representing patients' social determinants of health (SDH) obtained from multiple sources to build random forest decision models to predict the need for any, mental health, dietitian, social work, or other SDH service referrals. To assess the impact of SDH on improving performance, we built separate decision models using clinical and SDH determinants and clinical data only. Decision models predicting the need for any, mental health, and dietitian referrals yielded sensitivity, specificity, and accuracy measures ranging between 60% and 75%. Specificity and accuracy scores for social work and other SDH services ranged between 67% and 77%, while sensitivity scores were between 50% and 63%. Area under the receiver operating characteristic curve values for the decision models ranged between 70% and 78%. Models for predicting the need for any services reported positive predictive values between 65% and 73%. Positive predictive values for predicting individual outcomes were below 40%. The need for various social service referrals can be predicted with considerable accuracy using a wide range of readily available clinical and community data that measure socioeconomic and public health conditions. While the use of SDH did not result in significant performance improvements, our approach represents a novel and important application of risk predictive modeling. © The Author 2017. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Prediction of drug synergy in cancer using ensemble-based machine learning techniques

NASA Astrophysics Data System (ADS)

Singh, Harpreet; Rana, Prashant Singh; Singh, Urvinder

2018-04-01

Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug-drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

Experimental evaluation of radiosity for room sound-field prediction.

PubMed

Hodgson, Murray; Nosal, Eva-Marie

2006-08-01

An acoustical radiosity model was evaluated for how it performs in predicting real room sound fields. This was done by comparing radiosity predictions with experimental results for three existing rooms--a squash court, a classroom, and an office. Radiosity predictions were also compared with those by ray tracing--a "reference" prediction model--for both specular and diffuse surface reflection. Comparisons were made for detailed and discretized echograms, sound-decay curves, sound-propagation curves, and the variations with frequency of four room-acoustical parameters--EDT, RT, D50, and C80. In general, radiosity and diffuse ray tracing gave very similar predictions. Predictions by specular ray tracing were often very different. Radiosity agreed well with experiment in some cases, less well in others. Definitive conclusions regarding the accuracy with which the rooms were modeled, or the accuracy of the radiosity approach, were difficult to draw. The results suggest that radiosity predicts room sound fields with some accuracy, at least as well as diffuse ray tracing and, in general, better than specular ray tracing. The predictions of detailed echograms are less accurate, those of derived room-acoustical parameters more accurate. The results underline the need to develop experimental methods for accurately characterizing the absorptive and reflective characteristics of room surfaces, possible including phase.

Bio-knowledge based filters improve residue-residue contact prediction accuracy.

PubMed

Wozniak, P P; Pelc, J; Skrzypecki, M; Vriend, G; Kotulska, M

2018-05-29

Residue-residue contact prediction through direct coupling analysis has reached impressive accuracy, but yet higher accuracy will be needed to allow for routine modelling of protein structures. One way to improve the prediction accuracy is to filter predicted contacts using knowledge about the particular protein of interest or knowledge about protein structures in general. We focus on the latter and discuss a set of filters that can be used to remove false positive contact predictions. Each filter depends on one or a few cut-off parameters for which the filter performance was investigated. Combining all filters while using default parameters resulted for a test-set of 851 protein domains in the removal of 29% of the predictions of which 92% were indeed false positives. All data and scripts are available from http://comprec-lin.iiar.pwr.edu.pl/FPfilter/. malgorzata.kotulska@pwr.edu.pl. Supplementary data are available at Bioinformatics online.

Prospects and Potential Uses of Genomic Prediction of Key Performance Traits in Tetraploid Potato.

PubMed

Stich, Benjamin; Van Inghelandt, Delphine

2018-01-01

Genomic prediction is a routine tool in breeding programs of most major animal and plant species. However, its usefulness for potato breeding has not yet been evaluated in detail. The objectives of this study were to (i) examine the prospects of genomic prediction of key performance traits in a diversity panel of tetraploid potato modeling additive, dominance, and epistatic effects, (ii) investigate the effects of size and make up of training set, number of test environments and molecular markers on prediction accuracy, and (iii) assess the effect of including markers from candidate genes on the prediction accuracy. With genomic best linear unbiased prediction (GBLUP), BayesA, BayesCπ, and Bayesian LASSO, four different prediction methods were used for genomic prediction of relative area under disease progress curve after a Phytophthora infestans infection, plant maturity, maturity corrected resistance, tuber starch content, tuber starch yield (TSY), and tuber yield (TY) of 184 tetraploid potato clones or subsets thereof genotyped with the SolCAP 8.3k SNP array. The cross-validated prediction accuracies with GBLUP and the three Bayesian approaches for the six evaluated traits ranged from about 0.5 to about 0.8. For traits with a high expected genetic complexity, such as TSY and TY, we observed an 8% higher prediction accuracy using a model with additive and dominance effects compared with a model with additive effects only. Our results suggest that for oligogenic traits in general and when diagnostic markers are available in particular, the use of Bayesian methods for genomic prediction is highly recommended and that the diagnostic markers should be modeled as fixed effects. The evaluation of the relative performance of genomic prediction vs. phenotypic selection indicated that the former is superior, assuming cycle lengths and selection intensities that are possible to realize in commercial potato breeding programs.

Prospects and Potential Uses of Genomic Prediction of Key Performance Traits in Tetraploid Potato

PubMed Central

Stich, Benjamin; Van Inghelandt, Delphine

2018-01-01

Genomic prediction is a routine tool in breeding programs of most major animal and plant species. However, its usefulness for potato breeding has not yet been evaluated in detail. The objectives of this study were to (i) examine the prospects of genomic prediction of key performance traits in a diversity panel of tetraploid potato modeling additive, dominance, and epistatic effects, (ii) investigate the effects of size and make up of training set, number of test environments and molecular markers on prediction accuracy, and (iii) assess the effect of including markers from candidate genes on the prediction accuracy. With genomic best linear unbiased prediction (GBLUP), BayesA, BayesCπ, and Bayesian LASSO, four different prediction methods were used for genomic prediction of relative area under disease progress curve after a Phytophthora infestans infection, plant maturity, maturity corrected resistance, tuber starch content, tuber starch yield (TSY), and tuber yield (TY) of 184 tetraploid potato clones or subsets thereof genotyped with the SolCAP 8.3k SNP array. The cross-validated prediction accuracies with GBLUP and the three Bayesian approaches for the six evaluated traits ranged from about 0.5 to about 0.8. For traits with a high expected genetic complexity, such as TSY and TY, we observed an 8% higher prediction accuracy using a model with additive and dominance effects compared with a model with additive effects only. Our results suggest that for oligogenic traits in general and when diagnostic markers are available in particular, the use of Bayesian methods for genomic prediction is highly recommended and that the diagnostic markers should be modeled as fixed effects. The evaluation of the relative performance of genomic prediction vs. phenotypic selection indicated that the former is superior, assuming cycle lengths and selection intensities that are possible to realize in commercial potato breeding programs. PMID:29563919

Application of a stochastic snowmelt model for probabilistic decisionmaking

NASA Technical Reports Server (NTRS)

Mccuen, R. H.

1983-01-01

A stochastic form of the snowmelt runoff model that can be used for probabilistic decision-making was developed. The use of probabilistic streamflow predictions instead of single valued deterministic predictions leads to greater accuracy in decisions. While the accuracy of the output function is important in decisionmaking, it is also important to understand the relative importance of the coefficients. Therefore, a sensitivity analysis was made for each of the coefficients.

Automatic Prediction of Conversion from Mild Cognitive Impairment to Probable Alzheimer’s Disease using Structural Magnetic Resonance Imaging

PubMed Central

Nho, Kwangsik; Shen, Li; Kim, Sungeun; Risacher, Shannon L.; West, John D.; Foroud, Tatiana; Jack, Clifford R.; Weiner, Michael W.; Saykin, Andrew J.

2010-01-01

Mild Cognitive Impairment (MCI) is thought to be a precursor to the development of early Alzheimer’s disease (AD). For early diagnosis of AD, the development of a model that is able to predict the conversion of amnestic MCI to AD is challenging. Using automatic whole-brain MRI analysis techniques and pattern classification methods, we developed a model to differentiate AD from healthy controls (HC), and then applied it to the prediction of MCI conversion to AD. Classification was performed using support vector machines (SVMs) together with a SVM-based feature selection method, which selected a set of most discriminating predictors for optimizing prediction accuracy. We obtained 90.5% cross-validation accuracy for classifying AD and HC, and 72.3% accuracy for predicting MCI conversion to AD. These analyses suggest that a classifier trained to separate HC vs. AD has substantial potential for predicting MCI conversion to AD. PMID:21347037

Feature Selection Methods for Zero-Shot Learning of Neural Activity.

PubMed

Caceres, Carlos A; Roos, Matthew J; Rupp, Kyle M; Milsap, Griffin; Crone, Nathan E; Wolmetz, Michael E; Ratto, Christopher R

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy.

Modeling time-to-event (survival) data using classification tree analysis.

PubMed

Linden, Ariel; Yarnold, Paul R

2017-12-01

Time to the occurrence of an event is often studied in health research. Survival analysis differs from other designs in that follow-up times for individuals who do not experience the event by the end of the study (called censored) are accounted for in the analysis. Cox regression is the standard method for analysing censored data, but the assumptions required of these models are easily violated. In this paper, we introduce classification tree analysis (CTA) as a flexible alternative for modelling censored data. Classification tree analysis is a "decision-tree"-like classification model that provides parsimonious, transparent (ie, easy to visually display and interpret) decision rules that maximize predictive accuracy, derives exact P values via permutation tests, and evaluates model cross-generalizability. Using empirical data, we identify all statistically valid, reproducible, longitudinally consistent, and cross-generalizable CTA survival models and then compare their predictive accuracy to estimates derived via Cox regression and an unadjusted naïve model. Model performance is assessed using integrated Brier scores and a comparison between estimated survival curves. The Cox regression model best predicts average incidence of the outcome over time, whereas CTA survival models best predict either relatively high, or low, incidence of the outcome over time. Classification tree analysis survival models offer many advantages over Cox regression, such as explicit maximization of predictive accuracy, parsimony, statistical robustness, and transparency. Therefore, researchers interested in accurate prognoses and clear decision rules should consider developing models using the CTA-survival framework. © 2017 John Wiley & Sons, Ltd.

Maintenance of equilibrium point control during an unexpectedly loaded rapid limb movement.

PubMed

Simmons, R W; Richardson, C

1984-06-08

Two experiments investigated whether the equilibrium point hypothesis or the mass-spring model of motor control subserves positioning accuracy during spring loaded, rapid, bi-articulated movement. For intact preparations, the equilibrium point hypothesis predicts response accuracy to be determined by a mixture of afferent and efferent information, whereas the mass-spring model predicts positioning to be under a direct control system. Subjects completed a series of load-resisted training trials to a spatial target. The magnitude of a sustained spring load was unexpectedly increased on selected trials. Results indicated positioning accuracy and applied force varied with increases in load, which suggests that the original efferent commands are modified by afferent information during the movement as predicted by the equilibrium point hypothesis.

Estimating the Accuracy of the Chedoke-McMaster Stroke Assessment Predictive Equations for Stroke Rehabilitation.

PubMed

Dang, Mia; Ramsaran, Kalinda D; Street, Melissa E; Syed, S Noreen; Barclay-Goddard, Ruth; Stratford, Paul W; Miller, Patricia A

2011-01-01

To estimate the predictive accuracy and clinical usefulness of the Chedoke-McMaster Stroke Assessment (CMSA) predictive equations. A longitudinal prognostic study using historical data obtained from 104 patients admitted post cerebrovascular accident was undertaken. Data were abstracted for all patients undergoing rehabilitation post stroke who also had documented admission and discharge CMSA scores. Published predictive equations were used to determine predicted outcomes. To determine the accuracy and clinical usefulness of the predictive model, shrinkage coefficients and predictions with 95% confidence bands were calculated. Complete data were available for 74 patients with a mean age of 65.3±12.4 years. The shrinkage values for the six Impairment Inventory (II) dimensions varied from -0.05 to 0.09; the shrinkage value for the Activity Inventory (AI) was 0.21. The error associated with predictive values was greater than ±1.5 stages for the II dimensions and greater than ±24 points for the AI. This study shows that the large error associated with the predictions (as defined by the confidence band) for the CMSA II and AI limits their clinical usefulness as a predictive measure. Further research to establish predictive models using alternative statistical procedures is warranted.

Accuracy of gap analysis habitat models in predicting physical features for wildlife-habitat associations in the southwest U.S.

USGS Publications Warehouse

Boykin, K.G.; Thompson, B.C.; Propeck-Gray, S.

2010-01-01

Despite widespread and long-standing efforts to model wildlife-habitat associations using remotely sensed and other spatially explicit data, there are relatively few evaluations of the performance of variables included in predictive models relative to actual features on the landscape. As part of the National Gap Analysis Program, we specifically examined physical site features at randomly selected sample locations in the Southwestern U.S. to assess degree of concordance with predicted features used in modeling vertebrate habitat distribution. Our analysis considered hypotheses about relative accuracy with respect to 30 vertebrate species selected to represent the spectrum of habitat generalist to specialist and categorization of site by relative degree of conservation emphasis accorded to the site. Overall comparison of 19 variables observed at 382 sample sites indicated ???60% concordance for 12 variables. Directly measured or observed variables (slope, soil composition, rock outcrop) generally displayed high concordance, while variables that required judgments regarding descriptive categories (aspect, ecological system, landform) were less concordant. There were no differences detected in concordance among taxa groups, degree of specialization or generalization of selected taxa, or land conservation categorization of sample sites with respect to all sites. We found no support for the hypothesis that accuracy of habitat models is inversely related to degree of taxa specialization when model features for a habitat specialist could be more difficult to represent spatially. Likewise, we did not find support for the hypothesis that physical features will be predicted with higher accuracy on lands with greater dedication to biodiversity conservation than on other lands because of relative differences regarding available information. Accuracy generally was similar (>60%) to that observed for land cover mapping at the ecological system level. These patterns demonstrate resilience of gap analysis deductive model processes to the type of remotely sensed or interpreted data used in habitat feature predictions. ?? 2010 Elsevier B.V.

Improvement of shallow landslide prediction accuracy using soil parameterisation for a granite area in South Korea

NASA Astrophysics Data System (ADS)

Kim, M. S.; Onda, Y.; Kim, J. K.

2015-01-01

SHALSTAB model applied to shallow landslides induced by rainfall to evaluate soil properties related with the effect of soil depth for a granite area in Jinbu region, Republic of Korea. Soil depth measured by a knocking pole test and two soil parameters from direct shear test (a and b) as well as one soil parameters from a triaxial compression test (c) were collected to determine the input parameters for the model. Experimental soil data were used for the first simulation (Case I) and, soil data represented the effect of measured soil depth and average soil depth from soil data of Case I were used in the second (Case II) and third simulations (Case III), respectively. All simulations were analysed using receiver operating characteristic (ROC) analysis to determine the accuracy of prediction. ROC analysis results for first simulation showed the low ROC values under 0.75 may be due to the internal friction angle and particularly the cohesion value. Soil parameters calculated from a stochastic hydro-geomorphological model were applied to the SHALSTAB model. The accuracy of Case II and Case III using ROC analysis showed higher accuracy values rather than first simulation. Our results clearly demonstrate that the accuracy of shallow landslide prediction can be improved when soil parameters represented the effect of soil thickness.

Applicability of linear regression equation for prediction of chlorophyll content in rice leaves

NASA Astrophysics Data System (ADS)

Li, Yunmei

2005-09-01

A modeling approach is used to assess the applicability of the derived equations which are capable to predict chlorophyll content of rice leaves at a given view direction. Two radiative transfer models, including PROSPECT model operated at leaf level and FCR model operated at canopy level, are used in the study. The study is consisted of three steps: (1) Simulation of bidirectional reflectance from canopy with different leaf chlorophyll contents, leaf-area-index (LAI) and under storey configurations; (2) Establishment of prediction relations of chlorophyll content by stepwise regression; and (3) Assessment of the applicability of these relations. The result shows that the accuracy of prediction is affected by different under storey configurations and, however, the accuracy tends to be greatly improved with increase of LAI.

Combining cow and bull reference populations to increase accuracy of genomic prediction and genome-wide association studies.

PubMed

Calus, M P L; de Haas, Y; Veerkamp, R F

2013-10-01

Genomic selection holds the promise to be particularly beneficial for traits that are difficult or expensive to measure, such that access to phenotypes on large daughter groups of bulls is limited. Instead, cow reference populations can be generated, potentially supplemented with existing information from the same or (highly) correlated traits available on bull reference populations. The objective of this study, therefore, was to develop a model to perform genomic predictions and genome-wide association studies based on a combined cow and bull reference data set, with the accuracy of the phenotypes differing between the cow and bull genomic selection reference populations. The developed bivariate Bayesian stochastic search variable selection model allowed for an unbalanced design by imputing residuals in the residual updating scheme for all missing records. The performance of this model is demonstrated on a real data example, where the analyzed trait, being milk fat or protein yield, was either measured only on a cow or a bull reference population, or recorded on both. Our results were that the developed bivariate Bayesian stochastic search variable selection model was able to analyze 2 traits, even though animals had measurements on only 1 of 2 traits. The Bayesian stochastic search variable selection model yielded consistently higher accuracy for fat yield compared with a model without variable selection, both for the univariate and bivariate analyses, whereas the accuracy of both models was very similar for protein yield. The bivariate model identified several additional quantitative trait loci peaks compared with the single-trait models on either trait. In addition, the bivariate models showed a marginal increase in accuracy of genomic predictions for the cow traits (0.01-0.05), although a greater increase in accuracy is expected as the size of the bull population increases. Our results emphasize that the chosen value of priors in Bayesian genomic prediction models are especially important in small data sets. Copyright © 2013 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Alcohol use among university students: Considering a positive deviance approach.

PubMed

Tucker, Maryanne; Harris, Gregory E

2016-09-01

Harmful alcohol consumption among university students continues to be a significant issue. This study examined whether variables identified in the positive deviance literature would predict responsible alcohol consumption among university students. Surveyed students were categorized into three groups: abstainers, responsible drinkers and binge drinkers. Multinomial logistic regression modelling was significant (χ(2) = 274.49, degrees of freedom = 24, p < .001), with several variables predicting group membership. While the model classification accuracy rate (i.e. 71.2%) exceeded the proportional by chance accuracy rate (i.e. 38.4%), providing further support for the model, the model itself best predicted binge drinker membership over the other two groups. © The Author(s) 2015.

Assessment of a virtual functional prototyping process for the rapid manufacture of passive-dynamic ankle-foot orthoses.

PubMed

Schrank, Elisa S; Hitch, Lester; Wallace, Kevin; Moore, Richard; Stanhope, Steven J

2013-10-01

Passive-dynamic ankle-foot orthosis (PD-AFO) bending stiffness is a key functional characteristic for achieving enhanced gait function. However, current orthosis customization methods inhibit objective premanufacture tuning of the PD-AFO bending stiffness, making optimization of orthosis function challenging. We have developed a novel virtual functional prototyping (VFP) process, which harnesses the strengths of computer aided design (CAD) model parameterization and finite element analysis, to quantitatively tune and predict the functional characteristics of a PD-AFO, which is rapidly manufactured via fused deposition modeling (FDM). The purpose of this study was to assess the VFP process for PD-AFO bending stiffness. A PD-AFO CAD model was customized for a healthy subject and tuned to four bending stiffness values via VFP. Two sets of each tuned model were fabricated via FDM using medical-grade polycarbonate (PC-ISO). Dimensional accuracy of the fabricated orthoses was excellent (average 0.51 ± 0.39 mm). Manufacturing precision ranged from 0.0 to 0.74 Nm/deg (average 0.30 ± 0.36 Nm/deg). Bending stiffness prediction accuracy was within 1 Nm/deg using the manufacturer provided PC-ISO elastic modulus (average 0.48 ± 0.35 Nm/deg). Using an experimentally derived PC-ISO elastic modulus improved the optimized bending stiffness prediction accuracy (average 0.29 ± 0.57 Nm/deg). Robustness of the derived modulus was tested by carrying out the VFP process for a disparate subject, tuning the PD-AFO model to five bending stiffness values. For this disparate subject, bending stiffness prediction accuracy was strong (average 0.20 ± 0.14 Nm/deg). Overall, the VFP process had excellent dimensional accuracy, good manufacturing precision, and strong prediction accuracy with the derived modulus. Implementing VFP as part of our PD-AFO customization and manufacturing framework, which also includes fit customization, provides a novel and powerful method to predictably tune and precisely manufacture orthoses with objectively customized fit and functional characteristics.

Prediction and validation of residual feed intake and dry matter intake in Danish lactating dairy cows using mid-infrared spectroscopy of milk.

PubMed

Shetty, N; Løvendahl, P; Lund, M S; Buitenhuis, A J

2017-01-01

The present study explored the effectiveness of Fourier transform mid-infrared (FT-IR) spectral profiles as a predictor for dry matter intake (DMI) and residual feed intake (RFI). The partial least squares regression method was used to develop the prediction models. The models were validated using different external test sets, one randomly leaving out 20% of the records (validation A), the second randomly leaving out 20% of cows (validation B), and a third (for DMI prediction models) randomly leaving out one cow (validation C). The data included 1,044 records from 140 cows; 97 were Danish Holstein and 43 Danish Jersey. Results showed better accuracies for validation A compared with other validation methods. Milk yield (MY) contributed largely to DMI prediction; MY explained 59% of the variation and the validated model error root mean square error of prediction (RMSEP) was 2.24kg. The model was improved by adding live weight (LW) as an additional predictor trait, where the accuracy R 2 increased from 0.59 to 0.72 and error RMSEP decreased from 2.24 to 1.83kg. When only the milk FT-IR spectral profile was used in DMI prediction, a lower prediction ability was obtained, with R 2 =0.30 and RMSEP=2.91kg. However, once the spectral information was added, along with MY and LW as predictors, model accuracy improved and R 2 increased to 0.81 and RMSEP decreased to 1.49kg. Prediction accuracies of RFI changed throughout lactation. The RFI prediction model for the early-lactation stage was better compared with across lactation or mid- and late-lactation stages, with R 2 =0.46 and RMSEP=1.70. The most important spectral wavenumbers that contributed to DMI and RFI prediction models included fat, protein, and lactose peaks. Comparable prediction results were obtained when using infrared-predicted fat, protein, and lactose instead of full spectra, indicating that FT-IR spectral data do not add significant new information to improve DMI and RFI prediction models. Therefore, in practice, if full FT-IR spectral data are not stored, it is possible to achieve similar DMI or RFI prediction results based on standard milk control data. For DMI, the milk fat region was responsible for the major variation in milk spectra; for RFI, the major variation in milk spectra was within the milk protein region. Copyright © 2017 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Spindle Thermal Error Optimization Modeling of a Five-axis Machine Tool

NASA Astrophysics Data System (ADS)

Guo, Qianjian; Fan, Shuo; Xu, Rufeng; Cheng, Xiang; Zhao, Guoyong; Yang, Jianguo

2017-05-01

Aiming at the problem of low machining accuracy and uncontrollable thermal errors of NC machine tools, spindle thermal error measurement, modeling and compensation of a two turntable five-axis machine tool are researched. Measurement experiment of heat sources and thermal errors are carried out, and GRA(grey relational analysis) method is introduced into the selection of temperature variables used for thermal error modeling. In order to analyze the influence of different heat sources on spindle thermal errors, an ANN (artificial neural network) model is presented, and ABC(artificial bee colony) algorithm is introduced to train the link weights of ANN, a new ABC-NN(Artificial bee colony-based neural network) modeling method is proposed and used in the prediction of spindle thermal errors. In order to test the prediction performance of ABC-NN model, an experiment system is developed, the prediction results of LSR (least squares regression), ANN and ABC-NN are compared with the measurement results of spindle thermal errors. Experiment results show that the prediction accuracy of ABC-NN model is higher than LSR and ANN, and the residual error is smaller than 3 μm, the new modeling method is feasible. The proposed research provides instruction to compensate thermal errors and improve machining accuracy of NC machine tools.

Genetic Programming as Alternative for Predicting Development Effort of Individual Software Projects

PubMed Central

Chavoya, Arturo; Lopez-Martin, Cuauhtemoc; Andalon-Garcia, Irma R.; Meda-Campaña, M. E.

2012-01-01

Statistical and genetic programming techniques have been used to predict the software development effort of large software projects. In this paper, a genetic programming model was used for predicting the effort required in individually developed projects. Accuracy obtained from a genetic programming model was compared against one generated from the application of a statistical regression model. A sample of 219 projects developed by 71 practitioners was used for generating the two models, whereas another sample of 130 projects developed by 38 practitioners was used for validating them. The models used two kinds of lines of code as well as programming language experience as independent variables. Accuracy results from the model obtained with genetic programming suggest that it could be used to predict the software development effort of individual projects when these projects have been developed in a disciplined manner within a development-controlled environment. PMID:23226305

Mammographic density, breast cancer risk and risk prediction

PubMed Central

Vachon, Celine M; van Gils, Carla H; Sellers, Thomas A; Ghosh, Karthik; Pruthi, Sandhya; Brandt, Kathleen R; Pankratz, V Shane

2007-01-01

In this review, we examine the evidence for mammographic density as an independent risk factor for breast cancer, describe the risk prediction models that have incorporated density, and discuss the current and future implications of using mammographic density in clinical practice. Mammographic density is a consistent and strong risk factor for breast cancer in several populations and across age at mammogram. Recently, this risk factor has been added to existing breast cancer risk prediction models, increasing the discriminatory accuracy with its inclusion, albeit slightly. With validation, these models may replace the existing Gail model for clinical risk assessment. However, absolute risk estimates resulting from these improved models are still limited in their ability to characterize an individual's probability of developing cancer. Promising new measures of mammographic density, including volumetric density, which can be standardized using full-field digital mammography, will likely result in a stronger risk factor and improve accuracy of risk prediction models. PMID:18190724

Clinical time series prediction: Toward a hierarchical dynamical system framework.

PubMed

Liu, Zitao; Hauskrecht, Milos

2015-09-01

Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. We tested our framework by first learning the time series model from data for the patients in the training set, and then using it to predict future time series values for the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. Copyright © 2014 Elsevier B.V. All rights reserved.

Use of the HR index to predict maximal oxygen uptake during different exercise protocols.

PubMed

Haller, Jeannie M; Fehling, Patricia C; Barr, David A; Storer, Thomas W; Cooper, Christopher B; Smith, Denise L

2013-10-01

This study examined the ability of the HRindex model to accurately predict maximal oxygen uptake ([Formula: see text]O2max) across a variety of incremental exercise protocols. Ten men completed five incremental protocols to volitional exhaustion. Protocols included three treadmill (Bruce, UCLA running, Wellness Fitness Initiative [WFI]), one cycle, and one field (shuttle) test. The HRindex prediction equation (METs = 6 × HRindex - 5, where HRindex = HRmax/HRrest) was used to generate estimates of energy expenditure, which were converted to body mass-specific estimates of [Formula: see text]O2max. Estimated [Formula: see text]O2max was compared with measured [Formula: see text]O2max. Across all protocols, the HRindex model significantly underestimated [Formula: see text]O2max by 5.1 mL·kg(-1)·min(-1) (95% CI: -7.4, -2.7) and the standard error of the estimate (SEE) was 6.7 mL·kg(-1)·min(-1). Accuracy of the model was protocol-dependent, with [Formula: see text]O2max significantly underestimated for the Bruce and WFI protocols but not the UCLA, Cycle, or Shuttle protocols. Although no significant differences in [Formula: see text]O2max estimates were identified for these three protocols, predictive accuracy among them was not high, with root mean squared errors and SEEs ranging from 7.6 to 10.3 mL·kg(-1)·min(-1) and from 4.5 to 8.0 mL·kg(-1)·min(-1), respectively. Correlations between measured and predicted [Formula: see text]O2max were between 0.27 and 0.53. Individual prediction errors indicated that prediction accuracy varied considerably within protocols and among participants. In conclusion, across various protocols the HRindex model significantly underestimated [Formula: see text]O2max in a group of aerobically fit young men. Estimates generated using the model did not differ from measured [Formula: see text]O2max for three of the five protocols studied; nevertheless, some individual prediction errors were large. The lack of precision among estimates may limit the utility of the HRindex model; however, further investigation to establish the model's predictive accuracy is warranted.

Genomic Prediction for Quantitative Traits Is Improved by Mapping Variants to Gene Ontology Categories in Drosophila melanogaster

PubMed Central

Edwards, Stefan M.; Sørensen, Izel F.; Sarup, Pernille; Mackay, Trudy F. C.; Sørensen, Peter

2016-01-01

Predicting individual quantitative trait phenotypes from high-resolution genomic polymorphism data is important for personalized medicine in humans, plant and animal breeding, and adaptive evolution. However, this is difficult for populations of unrelated individuals when the number of causal variants is low relative to the total number of polymorphisms and causal variants individually have small effects on the traits. We hypothesized that mapping molecular polymorphisms to genomic features such as genes and their gene ontology categories could increase the accuracy of genomic prediction models. We developed a genomic feature best linear unbiased prediction (GFBLUP) model that implements this strategy and applied it to three quantitative traits (startle response, starvation resistance, and chill coma recovery) in the unrelated, sequenced inbred lines of the Drosophila melanogaster Genetic Reference Panel. Our results indicate that subsetting markers based on genomic features increases the predictive ability relative to the standard genomic best linear unbiased prediction (GBLUP) model. Both models use all markers, but GFBLUP allows differential weighting of the individual genetic marker relationships, whereas GBLUP weighs the genetic marker relationships equally. Simulation studies show that it is possible to further increase the accuracy of genomic prediction for complex traits using this model, provided the genomic features are enriched for causal variants. Our GFBLUP model using prior information on genomic features enriched for causal variants can increase the accuracy of genomic predictions in populations of unrelated individuals and provides a formal statistical framework for leveraging and evaluating information across multiple experimental studies to provide novel insights into the genetic architecture of complex traits. PMID:27235308

Personalized Risk Prediction in Clinical Oncology Research: Applications and Practical Issues Using Survival Trees and Random Forests.

PubMed

Hu, Chen; Steingrimsson, Jon Arni

2018-01-01

A crucial component of making individualized treatment decisions is to accurately predict each patient's disease risk. In clinical oncology, disease risks are often measured through time-to-event data, such as overall survival and progression/recurrence-free survival, and are often subject to censoring. Risk prediction models based on recursive partitioning methods are becoming increasingly popular largely due to their ability to handle nonlinear relationships, higher-order interactions, and/or high-dimensional covariates. The most popular recursive partitioning methods are versions of the Classification and Regression Tree (CART) algorithm, which builds a simple interpretable tree structured model. With the aim of increasing prediction accuracy, the random forest algorithm averages multiple CART trees, creating a flexible risk prediction model. Risk prediction models used in clinical oncology commonly use both traditional demographic and tumor pathological factors as well as high-dimensional genetic markers and treatment parameters from multimodality treatments. In this article, we describe the most commonly used extensions of the CART and random forest algorithms to right-censored outcomes. We focus on how they differ from the methods for noncensored outcomes, and how the different splitting rules and methods for cost-complexity pruning impact these algorithms. We demonstrate these algorithms by analyzing a randomized Phase III clinical trial of breast cancer. We also conduct Monte Carlo simulations to compare the prediction accuracy of survival forests with more commonly used regression models under various scenarios. These simulation studies aim to evaluate how sensitive the prediction accuracy is to the underlying model specifications, the choice of tuning parameters, and the degrees of missing covariates.

An evaluation of the accuracy of the Federal Transit Administration approved, groundborne noise and vibration prediction model for rail transit systems; a case study for a new subway line using post construction, transit operation measurements

NASA Astrophysics Data System (ADS)

Carman, Richard A.; Reyes, Carlos H.

2005-09-01

The groundborne noise and vibration model developed by Nelson and Saurenman in 1984, now recognized by the Federal Transit Administration as the approved model for new transit system facilities, is entering its third decade of use by engineers and consultants in the transit industry. The accuracy of the model has been explored in the past (e.g., Carman and Wolfe). New data obtained for a recently completed extension to a major heavy rail transit system provides an opportunity to evaluate the accuracy of the model once more. During the engineering design phase of the project, noise and vibration predictions were performed for numerous buildings adjacent to the new subway line. The values predicted by the model were used to determine the need for and type of noise and/or vibration control measures. After the start of transit operations on the new line, noise and vibration measurements were made inside several of the buildings to determine whether the criteria were in fact achieved. The measurement results are compared with the values predicted by the model. The predicted and measured, overall noise and vibration levels show very good agreement, whereas the spectral comparisons indicate some differences. Possible reasons for these differences are offered.

Clinical models are inaccurate in predicting bile duct stones in situ for patients with gallbladder.

PubMed

Topal, B; Fieuws, S; Tomczyk, K; Aerts, R; Van Steenbergen, W; Verslype, C; Penninckx, F

2009-01-01

The probability that a patient has common bile duct stones (CBDS) is a key factor in determining diagnostic and treatment strategies. This prospective cohort study evaluated the accuracy of clinical models in predicting CBDS for patients who will undergo cholecystectomy for lithiasis. From October 2005 until September 2006, 335 consecutive patients with symptoms of gallstone disease underwent cholecystectomy. Statistical analysis was performed on prospective patient data obtained at the time of first presentation to the hospital. Demonstrable CBDS at the time of endoscopic retrograde cholangiopancreatography (ERCP) or intraoperative cholangiography (IOC) was considered the gold standard for the presence of CBDS. Common bile duct stones were demonstrated in 53 patients. For 35 patients, ERCP was performed, with successful stone clearance in 24 of 30 patients who had proven CBDS. In 29 patients, IOC showed CBDS, which were managed successfully via laparoscopic common bile duct exploration, with stone extraction at the time of cholecystectomy. Prospective validation of the existing model for CBDS resulted in a predictive accuracy rate of 73%. The new model showed a predictive accuracy rate of 79%. Clinical models are inaccurate in predicting CBDS in patients with cholelithiasis. Management strategies should be based on the local availability of therapeutic expertise.

The development of a probabilistic approach to forecast coastal change

USGS Publications Warehouse

Lentz, Erika E.; Hapke, Cheryl J.; Rosati, Julie D.; Wang, Ping; Roberts, Tiffany M.

2011-01-01

This study demonstrates the applicability of a Bayesian probabilistic model as an effective tool in predicting post-storm beach changes along sandy coastlines. Volume change and net shoreline movement are modeled for two study sites at Fire Island, New York in response to two extratropical storms in 2007 and 2009. Both study areas include modified areas adjacent to unmodified areas in morphologically different segments of coast. Predicted outcomes are evaluated against observed changes to test model accuracy and uncertainty along 163 cross-shore transects. Results show strong agreement in the cross validation of predictions vs. observations, with 70-82% accuracies reported. Although no consistent spatial pattern in inaccurate predictions could be determined, the highest prediction uncertainties appeared in locations that had been recently replenished. Further testing and model refinement are needed; however, these initial results show that Bayesian networks have the potential to serve as important decision-support tools in forecasting coastal change.

Using models to manage systems subject to sustainability indicators

USGS Publications Warehouse

Hill, M.C.

2006-01-01

Mathematical and numerical models can provide insight into sustainability indicators using relevant simulated quantities, which are referred to here as predictions. To be useful, many concerns need to be considered. Four are discussed here: (a) mathematical and numerical accuracy of the model; (b) the accuracy of the data used in model development, (c) the information observations provide to aspects of the model important to predictions of interest as measured using sensitivity analysis; and (d) the existence of plausible alternative models for a given system. The four issues are illustrated using examples from conservative and transport modelling, and using conceptual arguments. Results suggest that ignoring these issues can produce misleading conclusions.

Evaluation of Gravitational Field Models Based on the Laser Range Observation of Low Earth Orbit Satellites

NASA Astrophysics Data System (ADS)

Hong-bo, Wang; Chang-yin, Zhao; Wei, Zhang; Jin-wei, Zhan; Sheng-xian, Yu

2016-07-01

The Earth gravitational field model is one of the most important dynamic models in satellite orbit computation. Several space gravity missions made great successes in recent years, prompting the publishing of several gravitational filed models. In this paper, two classical (JGM3, EGM96) and four latest (EIGEN-CHAMP05S, GGM03S, GOCE02S, EGM2008) models are evaluated by employing them in the precision orbit determination (POD) and prediction. These calculations are performed based on the laser ranging observation of four Low Earth Orbit (LEO) satellites, including CHAMP, GFZ-1, GRACE-A, and SWARM-A. The residual error of observation in POD is adopted to describe the accuracy of six gravitational field models. The main results we obtained are as follows. (1) For the POD of LEOs, the accuracies of 4 latest models are at the same level, and better than those of 2 classical models; (2) Taking JGM3 as reference, EGM96 model's accuracy is better in most situations, and the accuracies of the 4 latest models are improved by 12%-47% in POD and 63% in prediction, respectively. We also confirm that the model's accuracy in POD is enhanced with the increasing degree and order if they are smaller than 70, and when they exceed 70, the accuracy keeps constant, implying that the model's degree and order truncated to 70 are sufficient to meet the requirement of LEO computation of centimeter precision.

A simplified clinical prediction rule for prognosticating independent walking after spinal cord injury: a prospective study from a Canadian multicenter spinal cord injury registry.

PubMed

Hicks, Katharine E; Zhao, Yichen; Fallah, Nader; Rivers, Carly S; Noonan, Vanessa K; Plashkes, Tova; Wai, Eugene K; Roffey, Darren M; Tsai, Eve C; Paquet, Jerome; Attabib, Najmedden; Marion, Travis; Ahn, Henry; Phan, Philippe

2017-10-01

Traumatic spinal cord injury (SCI) is a debilitating condition with limited treatment options for neurologic or functional recovery. The ability to predict the prognosis of walking post injury with emerging prediction models could aid in rehabilitation strategies and reintegration into the community. To revalidate an existing clinical prediction model for independent ambulation (van Middendorp et al., 2011) using acute and long-term post-injury follow-up data, and to investigatethe accuracy of a simplified model using prospectively collected data from a Canadian multicenter SCI database, the Rick Hansen Spinal Cord Injury Registry (RHSCIR). Prospective cohort study. The analysis cohort consisted of 278 adult individuals with traumatic SCI enrolled in the RHSCIR for whom complete neurologic examination data and Functional Independence Measure (FIM) outcome data were available. The FIM locomotor score was used to assess independent walking ability (defined as modified or complete independence in walk or combined walk and wheelchair modality) at 1-year follow-up for each participant. A logistic regression (LR) model based on age and four neurologic variables was applied to our cohort of 278 RHSCIR participants. Additionally, a simplified LR model was created. The Hosmer-Lemeshow goodness of fit test was used to check if the predictive model is applicable to our data set. The performance of the model was verified by calculating the area under the receiver operating characteristic curve (AUC). The accuracy of the model was tested using a cross-validation technique. This study was supported by a grant from The Ottawa Hospital Academic Medical Organization ($50,000 over 2 years). The RHSCIR is sponsored by the Rick Hansen Institute and is supported by funding from Health Canada, Western Economic Diversification Canada, and the provincial governments of Alberta, British Columbia, Manitoba, and Ontario. ET and JP report receiving grants from the Rick Hansen Institute (approximately $60,000 and $30,000 per year, respectively). DMR reports receiving remuneration for consulting services provided to Palladian Health, LLC and Pacira Pharmaceuticals, Inc ($20,000-$30,000 annually), although neither relationship presents a potential conflict of interest with the submitted work. KEH received a grant for involvement in the present study from the Government of Canada as part of the Canada Summer Jobs Program ($3,000). JP reports receiving an educational grant from Medtronic Canada outside of the submitted work ($75,000 annually). TM reports receiving educational fellowship support from AO Spine, AO Trauma, and Medtronic; however, none of these relationships are financial in nature. All remaining authors have no conflicts of interest to disclose. The fitted prediction model generated 85% overall classification accuracy, 79% sensitivity, and 90% specificity. The prediction model was able to accurately classify independent walking ability (AUC 0.889, 95% confidence interval [CI] 0.846-0.933, p<.001) compared with the existing prediction model, despite the use of a different outcome measure (FIM vs. Spinal Cord Independence Measure) to qualify walking ability. A simplified, three-variable LR model based on age and two neurologic variables had an overall classification accuracy of 84%, with 76% sensitivity and 90% specificity, demonstrating comparable accuracy with its five-variable prediction model counterpart. The AUC was 0.866 (95% CI 0.816-0.916, p<.01), only marginally less than that of the existing prediction model. A simplified predictive model with similar accuracy to a more complex model for predicting independent walking was created, which improves utility in a clinical setting. Such models will allow clinicians to better predict the prognosis of ambulation in individuals who have sustained a traumatic SCI. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.

Effects of modeled tropical sea surface temperature variability on coral reef bleaching predictions

NASA Astrophysics Data System (ADS)

van Hooidonk, R.; Huber, M.

2012-03-01

Future widespread coral bleaching and subsequent mortality has been projected using sea surface temperature (SST) data derived from global, coupled ocean-atmosphere general circulation models (GCMs). While these models possess fidelity in reproducing many aspects of climate, they vary in their ability to correctly capture such parameters as the tropical ocean seasonal cycle and El Niño Southern Oscillation (ENSO) variability. Such weaknesses most likely reduce the accuracy of predicting coral bleaching, but little attention has been paid to the important issue of understanding potential errors and biases, the interaction of these biases with trends, and their propagation in predictions. To analyze the relative importance of various types of model errors and biases in predicting coral bleaching, various intra- and inter-annual frequency bands of observed SSTs were replaced with those frequencies from 24 GCMs 20th century simulations included in the Intergovernmental Panel on Climate Change (IPCC) 4th assessment report. Subsequent thermal stress was calculated and predictions of bleaching were made. These predictions were compared with observations of coral bleaching in the period 1982-2007 to calculate accuracy using an objective measure of forecast quality, the Peirce skill score (PSS). Major findings are that: (1) predictions are most sensitive to the seasonal cycle and inter-annual variability in the ENSO 24-60 months frequency band and (2) because models tend to understate the seasonal cycle at reef locations, they systematically underestimate future bleaching. The methodology we describe can be used to improve the accuracy of bleaching predictions by characterizing the errors and uncertainties involved in the predictions.

Comparing stream-specific to generalized temperature models to guide salmonid management in a changing climate

USGS Publications Warehouse

Andrew K. Carlson,; William W. Taylor,; Hartikainen, Kelsey M.; Dana M. Infante,; Beard, Douglas; Lynch, Abigail

2017-01-01

Global climate change is predicted to increase air and stream temperatures and alter thermal habitat suitability for growth and survival of coldwater fishes, including brook charr (Salvelinus fontinalis), brown trout (Salmo trutta), and rainbow trout (Oncorhynchus mykiss). In a changing climate, accurate stream temperature modeling is increasingly important for sustainable salmonid management throughout the world. However, finite resource availability (e.g. funding, personnel) drives a tradeoff between thermal model accuracy and efficiency (i.e. cost-effective applicability at management-relevant spatial extents). Using different projected climate change scenarios, we compared the accuracy and efficiency of stream-specific and generalized (i.e. region-specific) temperature models for coldwater salmonids within and outside the State of Michigan, USA, a region with long-term stream temperature data and productive coldwater fisheries. Projected stream temperature warming between 2016 and 2056 ranged from 0.1 to 3.8 °C in groundwater-dominated streams and 0.2–6.8 °C in surface-runoff dominated systems in the State of Michigan. Despite their generally lower accuracy in predicting exact stream temperatures, generalized models accurately projected salmonid thermal habitat suitability in 82% of groundwater-dominated streams, including those with brook charr (80% accuracy), brown trout (89% accuracy), and rainbow trout (75% accuracy). In contrast, generalized models predicted thermal habitat suitability in runoff-dominated streams with much lower accuracy (54%). These results suggest that, amidst climate change and constraints in resource availability, generalized models are appropriate to forecast thermal conditions in groundwater-dominated streams within and outside Michigan and inform regional-level salmonid management strategies that are practical for coldwater fisheries managers, policy makers, and the public. We recommend fisheries professionals reserve resource-intensive stream-specific models for runoff-dominated systems containing high-priority fisheries resources (e.g. trophy individuals, endangered species) that will be directly impacted by projected stream warming.

Accuracy of Predicted Genomic Breeding Values in Purebred and Crossbred Pigs.

PubMed

Hidalgo, André M; Bastiaansen, John W M; Lopes, Marcos S; Harlizius, Barbara; Groenen, Martien A M; de Koning, Dirk-Jan

2015-05-26

Genomic selection has been widely implemented in dairy cattle breeding when the aim is to improve performance of purebred animals. In pigs, however, the final product is a crossbred animal. This may affect the efficiency of methods that are currently implemented for dairy cattle. Therefore, the objective of this study was to determine the accuracy of predicted breeding values in crossbred pigs using purebred genomic and phenotypic data. A second objective was to compare the predictive ability of SNPs when training is done in either single or multiple populations for four traits: age at first insemination (AFI); total number of piglets born (TNB); litter birth weight (LBW); and litter variation (LVR). We performed marker-based and pedigree-based predictions. Within-population predictions for the four traits ranged from 0.21 to 0.72. Multi-population prediction yielded accuracies ranging from 0.18 to 0.67. Predictions across purebred populations as well as predicting genetic merit of crossbreds from their purebred parental lines for AFI performed poorly (not significantly different from zero). In contrast, accuracies of across-population predictions and accuracies of purebred to crossbred predictions for LBW and LVR ranged from 0.08 to 0.31 and 0.11 to 0.31, respectively. Accuracy for TNB was zero for across-population prediction, whereas for purebred to crossbred prediction it ranged from 0.08 to 0.22. In general, marker-based outperformed pedigree-based prediction across populations and traits. However, in some cases pedigree-based prediction performed similarly or outperformed marker-based prediction. There was predictive ability when purebred populations were used to predict crossbred genetic merit using an additive model in the populations studied. AFI was the only exception, indicating that predictive ability depends largely on the genetic correlation between PB and CB performance, which was 0.31 for AFI. Multi-population prediction was no better than within-population prediction for the purebred validation set. Accuracy of prediction was very trait-dependent. Copyright © 2015 Hidalgo et al.

Refining Prediction in Treatment-Resistant Depression: Results of Machine Learning Analyses in the TRD III Sample.

PubMed

Kautzky, Alexander; Dold, Markus; Bartova, Lucie; Spies, Marie; Vanicek, Thomas; Souery, Daniel; Montgomery, Stuart; Mendlewicz, Julien; Zohar, Joseph; Fabbri, Chiara; Serretti, Alessandro; Lanzenberger, Rupert; Kasper, Siegfried

The study objective was to generate a prediction model for treatment-resistant depression (TRD) using machine learning featuring a large set of 47 clinical and sociodemographic predictors of treatment outcome. 552 Patients diagnosed with major depressive disorder (MDD) according to DSM-IV criteria were enrolled between 2011 and 2016. TRD was defined as failure to reach response to antidepressant treatment, characterized by a Montgomery-Asberg Depression Rating Scale (MADRS) score below 22 after at least 2 antidepressant trials of adequate length and dosage were administered. RandomForest (RF) was used for predicting treatment outcome phenotypes in a 10-fold cross-validation. The full model with 47 predictors yielded an accuracy of 75.0%. When the number of predictors was reduced to 15, accuracies between 67.6% and 71.0% were attained for different test sets. The most informative predictors of treatment outcome were baseline MADRS score for the current episode; impairment of family, social, and work life; the timespan between first and last depressive episode; severity; suicidal risk; age; body mass index; and the number of lifetime depressive episodes as well as lifetime duration of hospitalization. With the application of the machine learning algorithm RF, an efficient prediction model with an accuracy of 75.0% for forecasting treatment outcome could be generated, thus surpassing the predictive capabilities of clinical evaluation. We also supply a simplified algorithm of 15 easily collected clinical and sociodemographic predictors that can be obtained within approximately 10 minutes, which reached an accuracy of 70.6%. Thus, we are confident that our model will be validated within other samples to advance an accurate prediction model fit for clinical usage in TRD. © Copyright 2017 Physicians Postgraduate Press, Inc.

High accuracy operon prediction method based on STRING database scores.

PubMed

Taboada, Blanca; Verde, Cristina; Merino, Enrique

2010-07-01

We present a simple and highly accurate computational method for operon prediction, based on intergenic distances and functional relationships between the protein products of contiguous genes, as defined by STRING database (Jensen,L.J., Kuhn,M., Stark,M., Chaffron,S., Creevey,C., Muller,J., Doerks,T., Julien,P., Roth,A., Simonovic,M. et al. (2009) STRING 8-a global view on proteins and their functional interactions in 630 organisms. Nucleic Acids Res., 37, D412-D416). These two parameters were used to train a neural network on a subset of experimentally characterized Escherichia coli and Bacillus subtilis operons. Our predictive model was successfully tested on the set of experimentally defined operons in E. coli and B. subtilis, with accuracies of 94.6 and 93.3%, respectively. As far as we know, these are the highest accuracies ever obtained for predicting bacterial operons. Furthermore, in order to evaluate the predictable accuracy of our model when using an organism's data set for the training procedure, and a different organism's data set for testing, we repeated the E. coli operon prediction analysis using a neural network trained with B. subtilis data, and a B. subtilis analysis using a neural network trained with E. coli data. Even for these cases, the accuracies reached with our method were outstandingly high, 91.5 and 93%, respectively. These results show the potential use of our method for accurately predicting the operons of any other organism. Our operon predictions for fully-sequenced genomes are available at http://operons.ibt.unam.mx/OperonPredictor/.

The effect of using genealogy-based haplotypes for genomic prediction

PubMed Central

2013-01-01

Background Genomic prediction uses two sources of information: linkage disequilibrium between markers and quantitative trait loci, and additive genetic relationships between individuals. One way to increase the accuracy of genomic prediction is to capture more linkage disequilibrium by regression on haplotypes instead of regression on individual markers. The aim of this study was to investigate the accuracy of genomic prediction using haplotypes based on local genealogy information. Methods A total of 4429 Danish Holstein bulls were genotyped with the 50K SNP chip. Haplotypes were constructed using local genealogical trees. Effects of haplotype covariates were estimated with two types of prediction models: (1) assuming that effects had the same distribution for all haplotype covariates, i.e. the GBLUP method and (2) assuming that a large proportion (π) of the haplotype covariates had zero effect, i.e. a Bayesian mixture method. Results About 7.5 times more covariate effects were estimated when fitting haplotypes based on local genealogical trees compared to fitting individuals markers. Genealogy-based haplotype clustering slightly increased the accuracy of genomic prediction and, in some cases, decreased the bias of prediction. With the Bayesian method, accuracy of prediction was less sensitive to parameter π when fitting haplotypes compared to fitting markers. Conclusions Use of haplotypes based on genealogy can slightly increase the accuracy of genomic prediction. Improved methods to cluster the haplotypes constructed from local genealogy could lead to additional gains in accuracy. PMID:23496971

The effect of using genealogy-based haplotypes for genomic prediction.

PubMed

Edriss, Vahid; Fernando, Rohan L; Su, Guosheng; Lund, Mogens S; Guldbrandtsen, Bernt

2013-03-06

Genomic prediction uses two sources of information: linkage disequilibrium between markers and quantitative trait loci, and additive genetic relationships between individuals. One way to increase the accuracy of genomic prediction is to capture more linkage disequilibrium by regression on haplotypes instead of regression on individual markers. The aim of this study was to investigate the accuracy of genomic prediction using haplotypes based on local genealogy information. A total of 4429 Danish Holstein bulls were genotyped with the 50K SNP chip. Haplotypes were constructed using local genealogical trees. Effects of haplotype covariates were estimated with two types of prediction models: (1) assuming that effects had the same distribution for all haplotype covariates, i.e. the GBLUP method and (2) assuming that a large proportion (π) of the haplotype covariates had zero effect, i.e. a Bayesian mixture method. About 7.5 times more covariate effects were estimated when fitting haplotypes based on local genealogical trees compared to fitting individuals markers. Genealogy-based haplotype clustering slightly increased the accuracy of genomic prediction and, in some cases, decreased the bias of prediction. With the Bayesian method, accuracy of prediction was less sensitive to parameter π when fitting haplotypes compared to fitting markers. Use of haplotypes based on genealogy can slightly increase the accuracy of genomic prediction. Improved methods to cluster the haplotypes constructed from local genealogy could lead to additional gains in accuracy.

Evaluation of hydrodynamic ocean models as a first step in larval dispersal modelling

NASA Astrophysics Data System (ADS)

Vasile, Roxana; Hartmann, Klaas; Hobday, Alistair J.; Oliver, Eric; Tracey, Sean

2018-01-01

Larval dispersal modelling, a powerful tool in studying population connectivity and species distribution, requires accurate estimates of the ocean state, on a high-resolution grid in both space (e.g. 0.5-1 km horizontal grid) and time (e.g. hourly outputs), particularly of current velocities and water temperature. These estimates are usually provided by hydrodynamic models based on which larval trajectories and survival are computed. In this study we assessed the accuracy of two hydrodynamic models around Australia - Bluelink ReANalysis (BRAN) and Hybrid Coordinate Ocean Model (HYCOM) - through comparison with empirical data from the Australian National Moorings Network (ANMN). We evaluated the models' predictions of seawater parameters most relevant to larval dispersal - temperature, u and v velocities and current speed and direction - on the continental shelf where spawning and nursery areas for major fishery species are located. The performance of each model in estimating ocean parameters was found to depend on the parameter investigated and to vary from one geographical region to another. Both BRAN and HYCOM models systematically overestimated the mean water temperature, particularly in the top 140 m of water column, with over 2 °C bias at some of the mooring stations. HYCOM model was more accurate than BRAN for water temperature predictions in the Great Australian Bight and along the east coast of Australia. Skill scores between each model and the in situ observations showed lower accuracy in the models' predictions of u and v ocean current velocities compared to water temperature predictions. For both models, the lowest accuracy in predicting ocean current velocities, speed and direction was observed at 200 m depth. Low accuracy of both model predictions was also observed in the top 10 m of the water column. BRAN had more accurate predictions of both u and v velocities in the upper 50 m of water column at all mooring station locations. While HYCOM predictions of ocean current speed were generally more accurate than BRAN, BRAN predictions of both ocean current speed and direction were more accurate than HYCOM along the southeast coast of Australia and Tasmania. This study identified important inaccuracies in the hydrodynamic models' estimations of the real ocean parameters and on time scales relevant to larval dispersal studies. These findings highlight the importance of the choice and validation of hydrodynamic models, and calls for estimates of such bias to be incorporated in dispersal studies.

Breeding Jatropha curcas by genomic selection: A pilot assessment of the accuracy of predictive models.

PubMed

Azevedo Peixoto, Leonardo de; Laviola, Bruno Galvêas; Alves, Alexandre Alonso; Rosado, Tatiana Barbosa; Bhering, Leonardo Lopes

2017-01-01

Genomic wide selection is a promising approach for improving the selection accuracy in plant breeding, particularly in species with long life cycles, such as Jatropha. Therefore, the objectives of this study were to estimate the genetic parameters for grain yield (GY) and the weight of 100 seeds (W100S) using restricted maximum likelihood (REML); to compare the performance of GWS methods to predict GY and W100S; and to estimate how many markers are needed to train the GWS model to obtain the maximum accuracy. Eight GWS models were compared in terms of predictive ability. The impact that the marker density had on the predictive ability was investigated using a varying number of markers, from 2 to 1,248. Because the genetic variance between evaluated genotypes was significant, it was possible to obtain selection gain. All of the GWS methods tested in this study can be used to predict GY and W100S in Jatropha. A training model fitted using 1,000 and 800 markers is sufficient to capture the maximum genetic variance and, consequently, maximum prediction ability of GY and W100S, respectively. This study demonstrated the applicability of genome-wide prediction to identify useful genetic sources of GY and W100S for Jatropha breeding. Further research is needed to confirm the applicability of the proposed approach to other complex traits.

Predicting carcinogenicity of diverse chemicals using probabilistic neural network modeling approaches

DOE Office of Scientific and Technical Information (OSTI.GOV)

Singh, Kunwar P., E-mail: kpsingh_52@yahoo.com; Environmental Chemistry Division, CSIR-Indian Institute of Toxicology Research, Post Box 80, Mahatma Gandhi Marg, Lucknow 226 001; Gupta, Shikha

Robust global models capable of discriminating positive and non-positive carcinogens; and predicting carcinogenic potency of chemicals in rodents were developed. The dataset of 834 structurally diverse chemicals extracted from Carcinogenic Potency Database (CPDB) was used which contained 466 positive and 368 non-positive carcinogens. Twelve non-quantum mechanical molecular descriptors were derived. Structural diversity of the chemicals and nonlinearity in the data were evaluated using Tanimoto similarity index and Brock–Dechert–Scheinkman statistics. Probabilistic neural network (PNN) and generalized regression neural network (GRNN) models were constructed for classification and function optimization problems using the carcinogenicity end point in rat. Validation of the models wasmore » performed using the internal and external procedures employing a wide series of statistical checks. PNN constructed using five descriptors rendered classification accuracy of 92.09% in complete rat data. The PNN model rendered classification accuracies of 91.77%, 80.70% and 92.08% in mouse, hamster and pesticide data, respectively. The GRNN constructed with nine descriptors yielded correlation coefficient of 0.896 between the measured and predicted carcinogenic potency with mean squared error (MSE) of 0.44 in complete rat data. The rat carcinogenicity model (GRNN) applied to the mouse and hamster data yielded correlation coefficient and MSE of 0.758, 0.71 and 0.760, 0.46, respectively. The results suggest for wide applicability of the inter-species models in predicting carcinogenic potency of chemicals. Both the PNN and GRNN (inter-species) models constructed here can be useful tools in predicting the carcinogenicity of new chemicals for regulatory purposes. - Graphical abstract: Figure (a) shows classification accuracies (positive and non-positive carcinogens) in rat, mouse, hamster, and pesticide data yielded by optimal PNN model. Figure (b) shows generalization and predictive abilities of the interspecies GRNN model to predict the carcinogenic potency of diverse chemicals. - Highlights: • Global robust models constructed for carcinogenicity prediction of diverse chemicals. • Tanimoto/BDS test revealed structural diversity of chemicals and nonlinearity in data. • PNN/GRNN successfully predicted carcinogenicity/carcinogenic potency of chemicals. • Developed interspecies PNN/GRNN models for carcinogenicity prediction. • Proposed models can be used as tool to predict carcinogenicity of new chemicals.« less

Neural Network Prediction of ICU Length of Stay Following Cardiac Surgery Based on Pre-Incision Variables

PubMed Central

Pothula, Venu M.; Yuan, Stanley C.; Maerz, David A.; Montes, Lucresia; Oleszkiewicz, Stephen M.; Yusupov, Albert; Perline, Richard

2015-01-01

Background Advanced predictive analytical techniques are being increasingly applied to clinical risk assessment. This study compared a neural network model to several other models in predicting the length of stay (LOS) in the cardiac surgical intensive care unit (ICU) based on pre-incision patient characteristics. Methods Thirty six variables collected from 185 cardiac surgical patients were analyzed for contribution to ICU LOS. The Automatic Linear Modeling (ALM) module of IBM-SPSS software identified 8 factors with statistically significant associations with ICU LOS; these factors were also analyzed with the Artificial Neural Network (ANN) module of the same software. The weighted contributions of each factor (“trained” data) were then applied to data for a “new” patient to predict ICU LOS for that individual. Results Factors identified in the ALM model were: use of an intra-aortic balloon pump; O2 delivery index; age; use of positive cardiac inotropic agents; hematocrit; serum creatinine ≥ 1.3 mg/deciliter; gender; arterial pCO2. The r2 value for ALM prediction of ICU LOS in the initial (training) model was 0.356, p <0.0001. Cross validation in prediction of a “new” patient yielded r2 = 0.200, p <0.0001. The same 8 factors analyzed with ANN yielded a training prediction r2 of 0.535 (p <0.0001) and a cross validation prediction r2 of 0.410, p <0.0001. Two additional predictive algorithms were studied, but they had lower prediction accuracies. Our validated neural network model identified the upper quartile of ICU LOS with an odds ratio of 9.8(p <0.0001). Conclusions ANN demonstrated a 2-fold greater accuracy than ALM in prediction of observed ICU LOS. This greater accuracy would be presumed to result from the capacity of ANN to capture nonlinear effects and higher order interactions. Predictive modeling may be of value in early anticipation of risks of post-operative morbidity and utilization of ICU facilities. PMID:26710254

Can species distribution models really predict the expansion of invasive species?

PubMed

Barbet-Massin, Morgane; Rome, Quentin; Villemant, Claire; Courchamp, Franck

2018-01-01

Predictive studies are of paramount importance for biological invasions, one of the biggest threats for biodiversity. To help and better prioritize management strategies, species distribution models (SDMs) are often used to predict the potential invasive range of introduced species. Yet, SDMs have been regularly criticized, due to several strong limitations, such as violating the equilibrium assumption during the invasion process. Unfortunately, validation studies-with independent data-are too scarce to assess the predictive accuracy of SDMs in invasion biology. Yet, biological invasions allow to test SDMs usefulness, by retrospectively assessing whether they would have accurately predicted the latest ranges of invasion. Here, we assess the predictive accuracy of SDMs in predicting the expansion of invasive species. We used temporal occurrence data for the Asian hornet Vespa velutina nigrithorax, a species native to China that is invading Europe with a very fast rate. Specifically, we compared occurrence data from the last stage of invasion (independent validation points) to the climate suitability distribution predicted from models calibrated with data from the early stage of invasion. Despite the invasive species not being at equilibrium yet, the predicted climate suitability of validation points was high. SDMs can thus adequately predict the spread of V. v. nigrithorax, which appears to be-at least partially-climatically driven. In the case of V. v. nigrithorax, SDMs predictive accuracy was slightly but significantly better when models were calibrated with invasive data only, excluding native data. Although more validation studies for other invasion cases are needed to generalize our results, our findings are an important step towards validating the use of SDMs in invasion biology.

Can species distribution models really predict the expansion of invasive species?

PubMed Central

Rome, Quentin; Villemant, Claire; Courchamp, Franck

2018-01-01

Predictive studies are of paramount importance for biological invasions, one of the biggest threats for biodiversity. To help and better prioritize management strategies, species distribution models (SDMs) are often used to predict the potential invasive range of introduced species. Yet, SDMs have been regularly criticized, due to several strong limitations, such as violating the equilibrium assumption during the invasion process. Unfortunately, validation studies–with independent data–are too scarce to assess the predictive accuracy of SDMs in invasion biology. Yet, biological invasions allow to test SDMs usefulness, by retrospectively assessing whether they would have accurately predicted the latest ranges of invasion. Here, we assess the predictive accuracy of SDMs in predicting the expansion of invasive species. We used temporal occurrence data for the Asian hornet Vespa velutina nigrithorax, a species native to China that is invading Europe with a very fast rate. Specifically, we compared occurrence data from the last stage of invasion (independent validation points) to the climate suitability distribution predicted from models calibrated with data from the early stage of invasion. Despite the invasive species not being at equilibrium yet, the predicted climate suitability of validation points was high. SDMs can thus adequately predict the spread of V. v. nigrithorax, which appears to be—at least partially–climatically driven. In the case of V. v. nigrithorax, SDMs predictive accuracy was slightly but significantly better when models were calibrated with invasive data only, excluding native data. Although more validation studies for other invasion cases are needed to generalize our results, our findings are an important step towards validating the use of SDMs in invasion biology. PMID:29509789

Artificial neural networks: Predicting head CT findings in elderly patients presenting with minor head injury after a fall.

PubMed

Dusenberry, Michael W; Brown, Charles K; Brewer, Kori L

2017-02-01

To construct an artificial neural network (ANN) model that can predict the presence of acute CT findings with both high sensitivity and high specificity when applied to the population of patients≥age 65years who have incurred minor head injury after a fall. An ANN was created in the Python programming language using a population of 514 patients ≥ age 65 years presenting to the ED with minor head injury after a fall. The patient dataset was divided into three parts: 60% for "training", 20% for "cross validation", and 20% for "testing". Sensitivity, specificity, positive and negative predictive values, and accuracy were determined by comparing the model's predictions to the actual correct answers for each patient. On the "cross validation" data, the model attained a sensitivity ("recall") of 100.00%, specificity of 78.95%, PPV ("precision") of 78.95%, NPV of 100.00%, and accuracy of 88.24% in detecting the presence of positive head CTs. On the "test" data, the model attained a sensitivity of 97.78%, specificity of 89.47%, PPV of 88.00%, NPV of 98.08%, and accuracy of 93.14% in detecting the presence of positive head CTs. ANNs show great potential for predicting CT findings in the population of patients ≥ 65 years of age presenting with minor head injury after a fall. As a good first step, the ANN showed comparable sensitivity, predictive values, and accuracy, with a much higher specificity than the existing decision rules in clinical usage for predicting head CTs with acute intracranial findings. Copyright © 2016 Elsevier Inc. All rights reserved.

Predicting climate-induced range shifts: model differences and model reliability.

Treesearch

Joshua J. Lawler; Denis White; Ronald P. Neilson; Andrew R. Blaustein

2006-01-01

Predicted changes in the global climate are likely to cause large shifts in the geographic ranges of many plant and animal species. To date, predictions of future range shifts have relied on a variety of modeling approaches with different levels of model accuracy. Using a common data set, we investigated the potential implications of alternative modeling approaches for...

Error associated with model predictions of wildland fire rate of spread

Treesearch

Miguel G. Cruz; Martin E. Alexander

2015-01-01

How well can we expect to predict the spread rate of wildfires and prescribed fires? The degree of accuracy in model predictions of wildland fire behaviour characteristics are dependent on the model's applicability to a given situation, the validity of the model's relationships, and the reliability of the model input data (Alexander and Cruz 2013b#. We...

Determination of heat capacity of ionic liquid based nanofluids using group method of data handling technique

NASA Astrophysics Data System (ADS)

Sadi, Maryam

2018-01-01

In this study a group method of data handling model has been successfully developed to predict heat capacity of ionic liquid based nanofluids by considering reduced temperature, acentric factor and molecular weight of ionic liquids, and nanoparticle concentration as input parameters. In order to accomplish modeling, 528 experimental data points extracted from the literature have been divided into training and testing subsets. The training set has been used to predict model coefficients and the testing set has been applied for model validation. The ability and accuracy of developed model, has been evaluated by comparison of model predictions with experimental values using different statistical parameters such as coefficient of determination, mean square error and mean absolute percentage error. The mean absolute percentage error of developed model for training and testing sets are 1.38% and 1.66%, respectively, which indicate excellent agreement between model predictions and experimental data. Also, the results estimated by the developed GMDH model exhibit a higher accuracy when compared to the available theoretical correlations.

Improving satellite-driven PM2.5 models with Moderate Resolution Imaging Spectroradiometer fire counts in the southeastern U.S.

PubMed

Hu, Xuefei; Waller, Lance A; Lyapustin, Alexei; Wang, Yujie; Liu, Yang

2014-10-16

Multiple studies have developed surface PM 2.5 (particle size less than 2.5 µm in aerodynamic diameter) prediction models using satellite-derived aerosol optical depth as the primary predictor and meteorological and land use variables as secondary variables. To our knowledge, satellite-retrieved fire information has not been used for PM 2.5 concentration prediction in statistical models. Fire data could be a useful predictor since fires are significant contributors of PM 2.5 . In this paper, we examined whether remotely sensed fire count data could improve PM 2.5 prediction accuracy in the southeastern U.S. in a spatial statistical model setting. A sensitivity analysis showed that when the radius of the buffer zone centered at each PM 2.5 monitoring site reached 75 km, fire count data generally have the greatest predictive power of PM 2.5 across the models considered. Cross validation (CV) generated an R 2 of 0.69, a mean prediction error of 2.75 µg/m 3 , and root-mean-square prediction errors (RMSPEs) of 4.29 µg/m 3 , indicating a good fit between the dependent and predictor variables. A comparison showed that the prediction accuracy was improved more substantially from the nonfire model to the fire model at sites with higher fire counts. With increasing fire counts, CV RMSPE decreased by values up to 1.5 µg/m 3 , exhibiting a maximum improvement of 13.4% in prediction accuracy. Fire count data were shown to have better performance in southern Georgia and in the spring season due to higher fire occurrence. Our findings indicate that fire count data provide a measurable improvement in PM 2.5 concentration estimation, especially in areas and seasons prone to fire events.

Improving satellite-driven PM2.5 models with Moderate Resolution Imaging Spectroradiometer fire counts in the southeastern U.S

PubMed Central

Hu, Xuefei; Waller, Lance A.; Lyapustin, Alexei; Wang, Yujie; Liu, Yang

2017-01-01

Multiple studies have developed surface PM2.5 (particle size less than 2.5 µm in aerodynamic diameter) prediction models using satellite-derived aerosol optical depth as the primary predictor and meteorological and land use variables as secondary variables. To our knowledge, satellite-retrieved fire information has not been used for PM2.5 concentration prediction in statistical models. Fire data could be a useful predictor since fires are significant contributors of PM2.5. In this paper, we examined whether remotely sensed fire count data could improve PM2.5 prediction accuracy in the southeastern U.S. in a spatial statistical model setting. A sensitivity analysis showed that when the radius of the buffer zone centered at each PM2.5 monitoring site reached 75 km, fire count data generally have the greatest predictive power of PM2.5 across the models considered. Cross validation (CV) generated an R2 of 0.69, a mean prediction error of 2.75 µg/m3, and root-mean-square prediction errors (RMSPEs) of 4.29 µg/m3, indicating a good fit between the dependent and predictor variables. A comparison showed that the prediction accuracy was improved more substantially from the nonfire model to the fire model at sites with higher fire counts. With increasing fire counts, CV RMSPE decreased by values up to 1.5 µg/m3, exhibiting a maximum improvement of 13.4% in prediction accuracy. Fire count data were shown to have better performance in southern Georgia and in the spring season due to higher fire occurrence. Our findings indicate that fire count data provide a measurable improvement in PM2.5 concentration estimation, especially in areas and seasons prone to fire events. PMID:28967648

SVM-PB-Pred: SVM based protein block prediction method using sequence profiles and secondary structures.

PubMed

Suresh, V; Parthasarathy, S

2014-01-01

We developed a support vector machine based web server called SVM-PB-Pred, to predict the Protein Block for any given amino acid sequence. The input features of SVM-PB-Pred include i) sequence profiles (PSSM) and ii) actual secondary structures (SS) from DSSP method or predicted secondary structures from NPS@ and GOR4 methods. There were three combined input features PSSM+SS(DSSP), PSSM+SS(NPS@) and PSSM+SS(GOR4) used to test and train the SVM models. Similarly, four datasets RS90, DB433, LI1264 and SP1577 were used to develop the SVM models. These four SVM models developed were tested using three different benchmarking tests namely; (i) self consistency, (ii) seven fold cross validation test and (iii) independent case test. The maximum possible prediction accuracy of ~70% was observed in self consistency test for the SVM models of both LI1264 and SP1577 datasets, where PSSM+SS(DSSP) input features was used to test. The prediction accuracies were reduced to ~53% for PSSM+SS(NPS@) and ~43% for PSSM+SS(GOR4) in independent case test, for the SVM models of above two same datasets. Using our method, it is possible to predict the protein block letters for any query protein sequence with ~53% accuracy, when the SP1577 dataset and predicted secondary structure from NPS@ server were used. The SVM-PB-Pred server can be freely accessed through http://bioinfo.bdu.ac.in/~svmpbpred.

Sequence-based prediction of protein-binding sites in DNA: comparative study of two SVM models.

PubMed

Park, Byungkyu; Im, Jinyong; Tuvshinjargal, Narankhuu; Lee, Wook; Han, Kyungsook

2014-11-01

As many structures of protein-DNA complexes have been known in the past years, several computational methods have been developed to predict DNA-binding sites in proteins. However, its inverse problem (i.e., predicting protein-binding sites in DNA) has received much less attention. One of the reasons is that the differences between the interaction propensities of nucleotides are much smaller than those between amino acids. Another reason is that DNA exhibits less diverse sequence patterns than protein. Therefore, predicting protein-binding DNA nucleotides is much harder than predicting DNA-binding amino acids. We computed the interaction propensity (IP) of nucleotide triplets with amino acids using an extensive dataset of protein-DNA complexes, and developed two support vector machine (SVM) models that predict protein-binding nucleotides from sequence data alone. One SVM model predicts protein-binding nucleotides using DNA sequence data alone, and the other SVM model predicts protein-binding nucleotides using both DNA and protein sequences. In a 10-fold cross-validation with 1519 DNA sequences, the SVM model that uses DNA sequence data only predicted protein-binding nucleotides with an accuracy of 67.0%, an F-measure of 67.1%, and a Matthews correlation coefficient (MCC) of 0.340. With an independent dataset of 181 DNAs that were not used in training, it achieved an accuracy of 66.2%, an F-measure 66.3% and a MCC of 0.324. Another SVM model that uses both DNA and protein sequences achieved an accuracy of 69.6%, an F-measure of 69.6%, and a MCC of 0.383 in a 10-fold cross-validation with 1519 DNA sequences and 859 protein sequences. With an independent dataset of 181 DNAs and 143 proteins, it showed an accuracy of 67.3%, an F-measure of 66.5% and a MCC of 0.329. Both in cross-validation and independent testing, the second SVM model that used both DNA and protein sequence data showed better performance than the first model that used DNA sequence data. To the best of our knowledge, this is the first attempt to predict protein-binding nucleotides in a given DNA sequence from the sequence data alone. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Effects of field plot size on prediction accuracy of aboveground biomass in airborne laser scanning-assisted inventories in tropical rain forests of Tanzania.

PubMed

Mauya, Ernest William; Hansen, Endre Hofstad; Gobakken, Terje; Bollandsås, Ole Martin; Malimbwi, Rogers Ernest; Næsset, Erik

2015-12-01

Airborne laser scanning (ALS) has recently emerged as a promising tool to acquire auxiliary information for improving aboveground biomass (AGB) estimation in sample-based forest inventories. Under design-based and model-assisted inferential frameworks, the estimation relies on a model that relates the auxiliary ALS metrics to AGB estimated on ground plots. The size of the field plots has been identified as one source of model uncertainty because of the so-called boundary effects which increases with decreasing plot size. Recent research in tropical forests has aimed to quantify the boundary effects on model prediction accuracy, but evidence of the consequences for the final AGB estimates is lacking. In this study we analyzed the effect of field plot size on model prediction accuracy and its implication when used in a model-assisted inferential framework. The results showed that the prediction accuracy of the model improved as the plot size increased. The adjusted R 2 increased from 0.35 to 0.74 while the relative root mean square error decreased from 63.6 to 29.2%. Indicators of boundary effects were identified and confirmed to have significant effects on the model residuals. Variance estimates of model-assisted mean AGB relative to corresponding variance estimates of pure field-based AGB, decreased with increasing plot size in the range from 200 to 3000 m 2 . The variance ratio of field-based estimates relative to model-assisted variance ranged from 1.7 to 7.7. This study showed that the relative improvement in precision of AGB estimation when increasing field-plot size, was greater for an ALS-assisted inventory compared to that of a pure field-based inventory.

Accurate disulfide-bonding network predictions improve ab initio structure prediction of cysteine-rich proteins

PubMed Central

Yang, Jing; He, Bao-Ji; Jang, Richard; Zhang, Yang; Shen, Hong-Bin

2015-01-01

Abstract Motivation: Cysteine-rich proteins cover many important families in nature but there are currently no methods specifically designed for modeling the structure of these proteins. The accuracy of disulfide connectivity pattern prediction, particularly for the proteins of higher-order connections, e.g. >3 bonds, is too low to effectively assist structure assembly simulations. Results: We propose a new hierarchical order reduction protocol called Cyscon for disulfide-bonding prediction. The most confident disulfide bonds are first identified and bonding prediction is then focused on the remaining cysteine residues based on SVR training. Compared with purely machine learning-based approaches, Cyscon improved the average accuracy of connectivity pattern prediction by 21.9%. For proteins with more than 5 disulfide bonds, Cyscon improved the accuracy by 585% on the benchmark set of PDBCYS. When applied to 158 non-redundant cysteine-rich proteins, Cyscon predictions helped increase (or decrease) the TM-score (or RMSD) of the ab initio QUARK modeling by 12.1% (or 14.4%). This result demonstrates a new avenue to improve the ab initio structure modeling for cysteine-rich proteins. Availability and implementation: http://www.csbio.sjtu.edu.cn/bioinf/Cyscon/ Contact: zhng@umich.edu or hbshen@sjtu.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online. PMID:26254435

Voxel inversion of airborne electromagnetic data for improved groundwater model construction and prediction accuracy

NASA Astrophysics Data System (ADS)

Kruse Christensen, Nikolaj; Ferre, Ty Paul A.; Fiandaca, Gianluca; Christensen, Steen

2017-03-01

We present a workflow for efficient construction and calibration of large-scale groundwater models that includes the integration of airborne electromagnetic (AEM) data and hydrological data. In the first step, the AEM data are inverted to form a 3-D geophysical model. In the second step, the 3-D geophysical model is translated, using a spatially dependent petrophysical relationship, to form a 3-D hydraulic conductivity distribution. The geophysical models and the hydrological data are used to estimate spatially distributed petrophysical shape factors. The shape factors primarily work as translators between resistivity and hydraulic conductivity, but they can also compensate for structural defects in the geophysical model. The method is demonstrated for a synthetic case study with sharp transitions among various types of deposits. Besides demonstrating the methodology, we demonstrate the importance of using geophysical regularization constraints that conform well to the depositional environment. This is done by inverting the AEM data using either smoothness (smooth) constraints or minimum gradient support (sharp) constraints, where the use of sharp constraints conforms best to the environment. The dependency on AEM data quality is also tested by inverting the geophysical model using data corrupted with four different levels of background noise. Subsequently, the geophysical models are used to construct competing groundwater models for which the shape factors are calibrated. The performance of each groundwater model is tested with respect to four types of prediction that are beyond the calibration base: a pumping well's recharge area and groundwater age, respectively, are predicted by applying the same stress as for the hydrologic model calibration; and head and stream discharge are predicted for a different stress situation. As expected, in this case the predictive capability of a groundwater model is better when it is based on a sharp geophysical model instead of a smoothness constraint. This is true for predictions of recharge area, head change, and stream discharge, while we find no improvement for prediction of groundwater age. Furthermore, we show that the model prediction accuracy improves with AEM data quality for predictions of recharge area, head change, and stream discharge, while there appears to be no accuracy improvement for the prediction of groundwater age.

Predicting Football Matches Results using Bayesian Networks for English Premier League (EPL)

NASA Astrophysics Data System (ADS)

Razali, Nazim; Mustapha, Aida; Yatim, Faiz Ahmad; Aziz, Ruhaya Ab

2017-08-01

The issues of modeling asscoiation football prediction model has become increasingly popular in the last few years and many different approaches of prediction models have been proposed with the point of evaluating the attributes that lead a football team to lose, draw or win the match. There are three types of approaches has been considered for predicting football matches results which include statistical approaches, machine learning approaches and Bayesian approaches. Lately, many studies regarding football prediction models has been produced using Bayesian approaches. This paper proposes a Bayesian Networks (BNs) to predict the results of football matches in term of home win (H), away win (A) and draw (D). The English Premier League (EPL) for three seasons of 2010-2011, 2011-2012 and 2012-2013 has been selected and reviewed. K-fold cross validation has been used for testing the accuracy of prediction model. The required information about the football data is sourced from a legitimate site at http://www.football-data.co.uk. BNs achieved predictive accuracy of 75.09% in average across three seasons. It is hoped that the results could be used as the benchmark output for future research in predicting football matches results.

Adjustment of regional regression models of urban-runoff quality using data for Chattanooga, Knoxville, and Nashville, Tennessee

USGS Publications Warehouse

Hoos, Anne B.; Patel, Anant R.

1996-01-01

Model-adjustment procedures were applied to the combined data bases of storm-runoff quality for Chattanooga, Knoxville, and Nashville, Tennessee, to improve predictive accuracy for storm-runoff quality for urban watersheds in these three cities and throughout Middle and East Tennessee. Data for 45 storms at 15 different sites (five sites in each city) constitute the data base. Comparison of observed values of storm-runoff load and event-mean concentration to the predicted values from the regional regression models for 10 constituents shows prediction errors, as large as 806,000 percent. Model-adjustment procedures, which combine the regional model predictions with local data, are applied to improve predictive accuracy. Standard error of estimate after model adjustment ranges from 67 to 322 percent. Calibration results may be biased due to sampling error in the Tennessee data base. The relatively large values of standard error of estimate for some of the constituent models, although representing significant reduction (at least 50 percent) in prediction error compared to estimation with unadjusted regional models, may be unacceptable for some applications. The user may wish to collect additional local data for these constituents and repeat the analysis, or calibrate an independent local regression model.

Improving CSF biomarker accuracy in predicting prevalent and incident Alzheimer disease

PubMed Central

Fagan, A.M.; Williams, M.M.; Ghoshal, N.; Aeschleman, M.; Grant, E.A.; Marcus, D.S.; Mintun, M.A.; Holtzman, D.M.; Morris, J.C.

2011-01-01

Objective: To investigate factors, including cognitive and brain reserve, which may independently predict prevalent and incident dementia of the Alzheimer type (DAT) and to determine whether inclusion of identified factors increases the predictive accuracy of the CSF biomarkers Aβ42, tau, ptau181, tau/Aβ42, and ptau181/Aβ42. Methods: Logistic regression identified variables that predicted prevalent DAT when considered together with each CSF biomarker in a cross-sectional sample of 201 participants with normal cognition and 46 with DAT. The area under the receiver operating characteristic curve (AUC) from the resulting model was compared with the AUC generated using the biomarker alone. In a second sample with normal cognition at baseline and longitudinal data available (n = 213), Cox proportional hazards models identified variables that predicted incident DAT together with each biomarker, and the models' concordance probability estimate (CPE), which was compared to the CPE generated using the biomarker alone. Results: APOE genotype including an ε4 allele, male gender, and smaller normalized whole brain volumes (nWBV) were cross-sectionally associated with DAT when considered together with every biomarker. In the longitudinal sample (mean follow-up = 3.2 years), 14 participants (6.6%) developed DAT. Older age predicted a faster time to DAT in every model, and greater education predicted a slower time in 4 of 5 models. Inclusion of ancillary variables resulted in better cross-sectional prediction of DAT for all biomarkers (p < 0.0021), and better longitudinal prediction for 4 of 5 biomarkers (p < 0.0022). Conclusions: The predictive accuracy of CSF biomarkers is improved by including age, education, and nWBV in analyses. PMID:21228296

Factors affecting GEBV accuracy with single-step Bayesian models.

PubMed

Zhou, Lei; Mrode, Raphael; Zhang, Shengli; Zhang, Qin; Li, Bugao; Liu, Jian-Feng

2018-01-01

A single-step approach to obtain genomic prediction was first proposed in 2009. Many studies have investigated the components of GEBV accuracy in genomic selection. However, it is still unclear how the population structure and the relationships between training and validation populations influence GEBV accuracy in terms of single-step analysis. Here, we explored the components of GEBV accuracy in single-step Bayesian analysis with a simulation study. Three scenarios with various numbers of QTL (5, 50, and 500) were simulated. Three models were implemented to analyze the simulated data: single-step genomic best linear unbiased prediction (GBLUP; SSGBLUP), single-step BayesA (SS-BayesA), and single-step BayesB (SS-BayesB). According to our results, GEBV accuracy was influenced by the relationships between the training and validation populations more significantly for ungenotyped animals than for genotyped animals. SS-BayesA/BayesB showed an obvious advantage over SSGBLUP with the scenarios of 5 and 50 QTL. SS-BayesB model obtained the lowest accuracy with the 500 QTL in the simulation. SS-BayesA model was the most efficient and robust considering all QTL scenarios. Generally, both the relationships between training and validation populations and LD between markers and QTL contributed to GEBV accuracy in the single-step analysis, and the advantages of single-step Bayesian models were more apparent when the trait is controlled by fewer QTL.

Connecting clinical and actuarial prediction with rule-based methods.

PubMed

Fokkema, Marjolein; Smits, Niels; Kelderman, Henk; Penninx, Brenda W J H

2015-06-01

Meta-analyses comparing the accuracy of clinical versus actuarial prediction have shown actuarial methods to outperform clinical methods, on average. However, actuarial methods are still not widely used in clinical practice, and there has been a call for the development of actuarial prediction methods for clinical practice. We argue that rule-based methods may be more useful than the linear main effect models usually employed in prediction studies, from a data and decision analytic as well as a practical perspective. In addition, decision rules derived with rule-based methods can be represented as fast and frugal trees, which, unlike main effects models, can be used in a sequential fashion, reducing the number of cues that have to be evaluated before making a prediction. We illustrate the usability of rule-based methods by applying RuleFit, an algorithm for deriving decision rules for classification and regression problems, to a dataset on prediction of the course of depressive and anxiety disorders from Penninx et al. (2011). The RuleFit algorithm provided a model consisting of 2 simple decision rules, requiring evaluation of only 2 to 4 cues. Predictive accuracy of the 2-rule model was very similar to that of a logistic regression model incorporating 20 predictor variables, originally applied to the dataset. In addition, the 2-rule model required, on average, evaluation of only 3 cues. Therefore, the RuleFit algorithm appears to be a promising method for creating decision tools that are less time consuming and easier to apply in psychological practice, and with accuracy comparable to traditional actuarial methods. (c) 2015 APA, all rights reserved).

Feature Selection Methods for Zero-Shot Learning of Neural Activity

PubMed Central

Caceres, Carlos A.; Roos, Matthew J.; Rupp, Kyle M.; Milsap, Griffin; Crone, Nathan E.; Wolmetz, Michael E.; Ratto, Christopher R.

2017-01-01

Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows) have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy. PMID:28690513

A Coupled Surface Nudging Scheme for use in Retrospective ...

EPA Pesticide Factsheets

A surface analysis nudging scheme coupling atmospheric and land surface thermodynamic parameters has been implemented into WRF v3.8 (latest version) for use with retrospective weather and climate simulations, as well as for applications in air quality, hydrology, and ecosystem modeling. This scheme is known as the flux-adjusting surface data assimilation system (FASDAS) developed by Alapaty et al. (2008). This scheme provides continuous adjustments for soil moisture and temperature (via indirect nudging) and for surface air temperature and water vapor mixing ratio (via direct nudging). The simultaneous application of indirect and direct nudging maintains greater consistency between the soil temperature–moisture and the atmospheric surface layer mass-field variables. The new method, FASDAS, consistently improved the accuracy of the model simulations at weather prediction scales for different horizontal grid resolutions, as well as for high resolution regional climate predictions. This new capability has been released in WRF Version 3.8 as option grid_sfdda = 2. This new capability increased the accuracy of atmospheric inputs for use air quality, hydrology, and ecosystem modeling research to improve the accuracy of respective end-point research outcome. IMPACT: A new method, FASDAS, was implemented into the WRF model to consistently improve the accuracy of the model simulations at weather prediction scales for different horizontal grid resolutions, as wel

A polynomial based model for cell fate prediction in human diseases.

PubMed

Ma, Lichun; Zheng, Jie

2017-12-21

Cell fate regulation directly affects tissue homeostasis and human health. Research on cell fate decision sheds light on key regulators, facilitates understanding the mechanisms, and suggests novel strategies to treat human diseases that are related to abnormal cell development. In this study, we proposed a polynomial based model to predict cell fate. This model was derived from Taylor series. As a case study, gene expression data of pancreatic cells were adopted to test and verify the model. As numerous features (genes) are available, we employed two kinds of feature selection methods, i.e. correlation based and apoptosis pathway based. Then polynomials of different degrees were used to refine the cell fate prediction function. 10-fold cross-validation was carried out to evaluate the performance of our model. In addition, we analyzed the stability of the resultant cell fate prediction model by evaluating the ranges of the parameters, as well as assessing the variances of the predicted values at randomly selected points. Results show that, within both the two considered gene selection methods, the prediction accuracies of polynomials of different degrees show little differences. Interestingly, the linear polynomial (degree 1 polynomial) is more stable than others. When comparing the linear polynomials based on the two gene selection methods, it shows that although the accuracy of the linear polynomial that uses correlation analysis outcomes is a little higher (achieves 86.62%), the one within genes of the apoptosis pathway is much more stable. Considering both the prediction accuracy and the stability of polynomial models of different degrees, the linear model is a preferred choice for cell fate prediction with gene expression data of pancreatic cells. The presented cell fate prediction model can be extended to other cells, which may be important for basic research as well as clinical study of cell development related diseases.

Genomic prediction of the polled and horned phenotypes in Merino sheep.

PubMed

Duijvesteijn, Naomi; Bolormaa, Sunduimijid; Daetwyler, Hans D; van der Werf, Julius H J

2018-05-22

In horned sheep breeds, breeding for polledness has been of interest for decades. The objective of this study was to improve prediction of the horned and polled phenotypes using horn scores classified as polled, scurs, knobs or horns. Derived phenotypes polled/non-polled (P/NP) and horned/non-horned (H/NH) were used to test four different strategies for prediction in 4001 purebred Merino sheep. These strategies include the use of single 'single nucleotide polymorphism' (SNP) genotypes, multiple-SNP haplotypes, genome-wide and chromosome-wide genomic best linear unbiased prediction and information from imputed sequence variants from the region including the RXFP2 gene. Low-density genotypes of these animals were imputed to the Illumina Ovine high-density (600k) chip and the 1.78-kb insertion polymorphism in RXFP2 was included in the imputation process to whole-genome sequence. We evaluated the mode of inheritance and validated models by a fivefold cross-validation and across- and between-family prediction. The most significant SNPs for prediction of P/NP and H/NH were OAR10_29546872.1 and OAR10_29458450, respectively, located on chromosome 10 close to the 1.78-kb insertion at 29.5 Mb. The mode of inheritance included an additive effect and a sex-dependent effect for dominance for P/NP and a sex-dependent additive and dominance effect for H/NH. Models with the highest prediction accuracies for H/NH used either single SNPs or 3-SNP haplotypes and included a polygenic effect estimated based on traditional pedigree relationships. Prediction accuracies for H/NH were 0.323 for females and 0.725 for males. For predicting P/NP, the best models were the same as for H/NH but included a genomic relationship matrix with accuracies of 0.713 for females and 0.620 for males. Our results show that prediction accuracy is high using a single SNP, but does not reach 1 since the causative mutation is not genotyped. Incomplete penetrance or allelic heterogeneity, which can influence expression of the phenotype, may explain why prediction accuracy did not approach 1 with any of the genetic models tested here. Nevertheless, a breeding program to eradicate horns from Merino sheep can be effective by selecting genotypes GG of SNP OAR10_29458450 or TT of SNP OAR10_29546872.1 since all sheep with these genotypes will be non-horned.

Practical approach to subject-specific estimation of knee joint contact force.

PubMed

Knarr, Brian A; Higginson, Jill S

2015-08-20

Compressive forces experienced at the knee can significantly contribute to cartilage degeneration. Musculoskeletal models enable predictions of the internal forces experienced at the knee, but validation is often not possible, as experimental data detailing loading at the knee joint is limited. Recently available data reporting compressive knee force through direct measurement using instrumented total knee replacements offer a unique opportunity to evaluate the accuracy of models. Previous studies have highlighted the importance of subject-specificity in increasing the accuracy of model predictions; however, these techniques may be unrealistic outside of a research setting. Therefore, the goal of our work was to identify a practical approach for accurate prediction of tibiofemoral knee contact force (KCF). Four methods for prediction of knee contact force were compared: (1) standard static optimization, (2) uniform muscle coordination weighting, (3) subject-specific muscle coordination weighting and (4) subject-specific strength adjustments. Walking trials for three subjects with instrumented knee replacements were used to evaluate the accuracy of model predictions. Predictions utilizing subject-specific muscle coordination weighting yielded the best agreement with experimental data; however this method required in vivo data for weighting factor calibration. Including subject-specific strength adjustments improved models' predictions compared to standard static optimization, with errors in peak KCF less than 0.5 body weight for all subjects. Overall, combining clinical assessments of muscle strength with standard tools available in the OpenSim software package, such as inverse kinematics and static optimization, appears to be a practical method for predicting joint contact force that can be implemented for many applications. Copyright © 2015 Elsevier Ltd. All rights reserved.

Predict the fatigue life of crack based on extended finite element method and SVR

NASA Astrophysics Data System (ADS)

Song, Weizhen; Jiang, Zhansi; Jiang, Hui

2018-05-01

Using extended finite element method (XFEM) and support vector regression (SVR) to predict the fatigue life of plate crack. Firstly, the XFEM is employed to calculate the stress intensity factors (SIFs) with given crack sizes. Then predicetion model can be built based on the function relationship of the SIFs with the fatigue life or crack length. Finally, according to the prediction model predict the SIFs at different crack sizes or different cycles. Because of the accuracy of the forward Euler method only ensured by the small step size, a new prediction method is presented to resolve the issue. The numerical examples were studied to demonstrate the proposed method allow a larger step size and have a high accuracy.

Estimating the Accuracy of the Chedoke–McMaster Stroke Assessment Predictive Equations for Stroke Rehabilitation

PubMed Central

Dang, Mia; Ramsaran, Kalinda D.; Street, Melissa E.; Syed, S. Noreen; Barclay-Goddard, Ruth; Miller, Patricia A.

2011-01-01

ABSTRACT Purpose: To estimate the predictive accuracy and clinical usefulness of the Chedoke–McMaster Stroke Assessment (CMSA) predictive equations. Method: A longitudinal prognostic study using historical data obtained from 104 patients admitted post cerebrovascular accident was undertaken. Data were abstracted for all patients undergoing rehabilitation post stroke who also had documented admission and discharge CMSA scores. Published predictive equations were used to determine predicted outcomes. To determine the accuracy and clinical usefulness of the predictive model, shrinkage coefficients and predictions with 95% confidence bands were calculated. Results: Complete data were available for 74 patients with a mean age of 65.3±12.4 years. The shrinkage values for the six Impairment Inventory (II) dimensions varied from −0.05 to 0.09; the shrinkage value for the Activity Inventory (AI) was 0.21. The error associated with predictive values was greater than ±1.5 stages for the II dimensions and greater than ±24 points for the AI. Conclusions: This study shows that the large error associated with the predictions (as defined by the confidence band) for the CMSA II and AI limits their clinical usefulness as a predictive measure. Further research to establish predictive models using alternative statistical procedures is warranted. PMID:22654239

Modeling additive and non-additive effects in a hybrid population using genome-wide genotyping: prediction accuracy implications

PubMed Central

Bouvet, J-M; Makouanzi, G; Cros, D; Vigneron, Ph

2016-01-01

Hybrids are broadly used in plant breeding and accurate estimation of variance components is crucial for optimizing genetic gain. Genome-wide information may be used to explore models designed to assess the extent of additive and non-additive variance and test their prediction accuracy for the genomic selection. Ten linear mixed models, involving pedigree- and marker-based relationship matrices among parents, were developed to estimate additive (A), dominance (D) and epistatic (AA, AD and DD) effects. Five complementary models, involving the gametic phase to estimate marker-based relationships among hybrid progenies, were developed to assess the same effects. The models were compared using tree height and 3303 single-nucleotide polymorphism markers from 1130 cloned individuals obtained via controlled crosses of 13 Eucalyptus urophylla females with 9 Eucalyptus grandis males. Akaike information criterion (AIC), variance ratios, asymptotic correlation matrices of estimates, goodness-of-fit, prediction accuracy and mean square error (MSE) were used for the comparisons. The variance components and variance ratios differed according to the model. Models with a parent marker-based relationship matrix performed better than those that were pedigree-based, that is, an absence of singularities, lower AIC, higher goodness-of-fit and accuracy and smaller MSE. However, AD and DD variances were estimated with high s.es. Using the same criteria, progeny gametic phase-based models performed better in fitting the observations and predicting genetic values. However, DD variance could not be separated from the dominance variance and null estimates were obtained for AA and AD effects. This study highlighted the advantages of progeny models using genome-wide information. PMID:26328760

BIG DATA ANALYTICS AND PRECISION ANIMAL AGRICULTURE SYMPOSIUM: Data to decisions.

PubMed

White, B J; Amrine, D E; Larson, R L

2018-04-14

Big data are frequently used in many facets of business and agronomy to enhance knowledge needed to improve operational decisions. Livestock operations collect data of sufficient quantity to perform predictive analytics. Predictive analytics can be defined as a methodology and suite of data evaluation techniques to generate a prediction for specific target outcomes. The objective of this manuscript is to describe the process of using big data and the predictive analytic framework to create tools to drive decisions in livestock production, health, and welfare. The predictive analytic process involves selecting a target variable, managing the data, partitioning the data, then creating algorithms, refining algorithms, and finally comparing accuracy of the created classifiers. The partitioning of the datasets allows model building and refining to occur prior to testing the predictive accuracy of the model with naive data to evaluate overall accuracy. Many different classification algorithms are available for predictive use and testing multiple algorithms can lead to optimal results. Application of a systematic process for predictive analytics using data that is currently collected or that could be collected on livestock operations will facilitate precision animal management through enhanced livestock operational decisions.

Thoracic injury rule out criteria and NEXUS chest in predicting the risk of traumatic intra-thoracic injuries: A diagnostic accuracy study.

PubMed

Safari, Saeed; Radfar, Fatemeh; Baratloo, Alireza

2018-05-01

This study aimed to compare the diagnostic accuracy of NEXUS chest and Thoracic Injury Rule out criteria (TIRC) models in predicting the risk of intra-thoracic injuries following blunt multiple trauma. In this diagnostic accuracy study, using the 2 mentioned models, blunt multiple trauma patients over the age of 15 years presenting to emergency department were screened regarding the presence of intra-thoracic injuries that are detectable via chest x-ray and screening performance characteristics of the models were compared. In this study, 3118 patients with the mean (SD) age of 37.4 (16.9) years were studied (57.4% male). Based on TIRC and NEXUS chest, respectively, 1340 (43%) and 1417 (45.4%) patients were deemed in need of radiography performance. Sensitivity, specificity, and positive and negative predictive values of TIRC were 98.95%, 62.70%, 21.19% and 99.83%. These values were 98.61%, 59.94%, 19.97% and 99.76%, for NEXUS chest, respectively. Accuracy of TIRC and NEXUS chest models were 66.04 (95% CI: 64.34-67.70) and 63.50 (95% CI: 61.78-65.19), respectively. TIRC and NEXUS chest models have proper and similar sensitivity in prediction of blunt traumatic intra-thoracic injuries that are detectable via chest x-ray. However, TIRC had a significantly higher specificity in this regard. Copyright © 2018 Elsevier Ltd. All rights reserved.

Alternatives to accuracy and bias metrics based on percentage errors for radiation belt modeling applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Morley, Steven Karl

This report reviews existing literature describing forecast accuracy metrics, concentrating on those based on relative errors and percentage errors. We then review how the most common of these metrics, the mean absolute percentage error (MAPE), has been applied in recent radiation belt modeling literature. Finally, we describe metrics based on the ratios of predicted to observed values (the accuracy ratio) that address the drawbacks inherent in using MAPE. Specifically, we define and recommend the median log accuracy ratio as a measure of bias and the median symmetric accuracy as a measure of accuracy.

The effect of concurrent hand movement on estimated time to contact in a prediction motion task.

PubMed

Zheng, Ran; Maraj, Brian K V

2018-04-27

In many activities, we need to predict the arrival of an occluded object. This action is called prediction motion or motion extrapolation. Previous researchers have found that both eye tracking and the internal clocking model are involved in the prediction motion task. Additionally, it is reported that concurrent hand movement facilitates the eye tracking of an externally generated target in a tracking task, even if the target is occluded. The present study examined the effect of concurrent hand movement on the estimated time to contact in a prediction motion task. We found different (accurate/inaccurate) concurrent hand movements had the opposite effect on the eye tracking accuracy and estimated TTC in the prediction motion task. That is, the accurate concurrent hand tracking enhanced eye tracking accuracy and had the trend to increase the precision of estimated TTC, but the inaccurate concurrent hand tracking decreased eye tracking accuracy and disrupted estimated TTC. However, eye tracking accuracy does not determine the precision of estimated TTC.

Can nutrient status of four woody plant species be predicted using field spectrometry?

NASA Astrophysics Data System (ADS)

Ferwerda, Jelle G.; Skidmore, Andrew K.

This paper demonstrates the potential of hyperspectral remote sensing to predict the chemical composition (i.e., nitrogen, phosphorous, calcium, potassium, sodium, and magnesium) of three tree species (i.e., willow, mopane and olive) and one shrub species (i.e., heather). Reflectance spectra, derivative spectra and continuum-removed spectra were compared in terms of predictive power. Results showed that the best predictions for nitrogen, phosphorous, and magnesium occur when using derivative spectra, and the best predictions for sodium, potassium, and calcium occur when using continuum-removed data. To test whether a general model for multiple species is also valid for individual species, a bootstrapping routine was applied. Prediction accuracies for the individual species were lower then prediction accuracies obtained for the combined dataset for all except one element/species combination, indicating that indices with high prediction accuracies at the landscape scale are less appropriate to detect the chemical content of individual species.

Analysing the accuracy of machine learning techniques to develop an integrated influent time series model: case study of a sewage treatment plant, Malaysia.

PubMed

Ansari, Mozafar; Othman, Faridah; Abunama, Taher; El-Shafie, Ahmed

2018-04-01

The function of a sewage treatment plant is to treat the sewage to acceptable standards before being discharged into the receiving waters. To design and operate such plants, it is necessary to measure and predict the influent flow rate. In this research, the influent flow rate of a sewage treatment plant (STP) was modelled and predicted by autoregressive integrated moving average (ARIMA), nonlinear autoregressive network (NAR) and support vector machine (SVM) regression time series algorithms. To evaluate the models' accuracy, the root mean square error (RMSE) and coefficient of determination (R 2 ) were calculated as initial assessment measures, while relative error (RE), peak flow criterion (PFC) and low flow criterion (LFC) were calculated as final evaluation measures to demonstrate the detailed accuracy of the selected models. An integrated model was developed based on the individual models' prediction ability for low, average and peak flow. An initial assessment of the results showed that the ARIMA model was the least accurate and the NAR model was the most accurate. The RE results also prove that the SVM model's frequency of errors above 10% or below - 10% was greater than the NAR model's. The influent was also forecasted up to 44 weeks ahead by both models. The graphical results indicate that the NAR model made better predictions than the SVM model. The final evaluation of NAR and SVM demonstrated that SVM made better predictions at peak flow and NAR fit well for low and average inflow ranges. The integrated model developed includes the NAR model for low and average influent and the SVM model for peak inflow.

Concurrent prediction of ground reaction forces and moments and tibiofemoral contact forces during walking using musculoskeletal modelling.

PubMed

Peng, Yinghu; Zhang, Zhifeng; Gao, Yongchang; Chen, Zhenxian; Xin, Hua; Zhang, Qida; Fan, Xunjian; Jin, Zhongmin

2018-02-01

Ground reaction forces and moments (GRFs and GRMs) measured from force plates in a gait laboratory are usually used as the input conditions to predict the knee joint forces and moments via musculoskeletal (MSK) multibody dynamics (MBD) model. However, the measurements of the GRFs and GRMs data rely on force plates and sometimes are limited by the difficulty in some patient's gait patterns (e.g. treadmill gait). In addition, the force plate calibration error may influence the prediction accuracy of the MSK model. In this study, a prediction method of the GRFs and GRMs based on elastic contact element was integrated into a subject-specific MSK MBD modelling framework of total knee arthroplasty (TKA), and the GRFs and GRMs and knee contact forces (KCFs) during walking were predicted simultaneously with reasonable accuracy. The ground reaction forces and moments were predicted with an average root mean square errors (RMSEs) of 0.021 body weight (BW), 0.014 BW and 0.089 BW in the antero-posterior, medio-lateral and vertical directions and 0.005 BW•body height (BH), 0.011 BW•BH, 0.004 BW•BH in the sagittal, frontal and transverse planes, respectively. Meanwhile, the medial, lateral and total tibiofemoral (TF) contact forces were predicted by the developed MSK model with RMSEs of 0.025-0.032 BW, 0.018-0.022 BW, and 0.089-0.132 BW, respectively. The accuracy of the predicted medial TF contact force was improved by 12% using the present method. The proposed method can extend the application of the MSK model of TKA and is valuable for understanding the in vivo knee biomechanics and tribological conditions without the force plate data. Copyright © 2017 IPEM. Published by Elsevier Ltd. All rights reserved.

Using a generalized linear mixed model approach to explore the role of age, motor proficiency, and cognitive styles in children's reach estimation accuracy.

PubMed

Caçola, Priscila M; Pant, Mohan D

2014-10-01

The purpose was to use a multi-level statistical technique to analyze how children's age, motor proficiency, and cognitive styles interact to affect accuracy on reach estimation tasks via Motor Imagery and Visual Imagery. Results from the Generalized Linear Mixed Model analysis (GLMM) indicated that only the 7-year-old age group had significant random intercepts for both tasks. Motor proficiency predicted accuracy in reach tasks, and cognitive styles (object scale) predicted accuracy in the motor imagery task. GLMM analysis is suitable to explore age and other parameters of development. In this case, it allowed an assessment of motor proficiency interacting with age to shape how children represent, plan, and act on the environment.

Development and evaluation of a regression-based model to predict cesium concentration ratios for freshwater fish.

PubMed

Pinder, John E; Rowan, David J; Rasmussen, Joseph B; Smith, Jim T; Hinton, Thomas G; Whicker, F W

2014-08-01

Data from published studies and World Wide Web sources were combined to produce and test a regression model to predict Cs concentration ratios for freshwater fish species. The accuracies of predicted concentration ratios, which were computed using 1) species trophic levels obtained from random resampling of known food items and 2) K concentrations in the water for 207 fish from 44 species and 43 locations, were tested against independent observations of ratios for 57 fish from 17 species from 25 locations. Accuracy was assessed as the percent of observed to predicted ratios within factors of 2 or 3. Conservatism, expressed as the lack of under prediction, was assessed as the percent of observed to predicted ratios that were less than 2 or less than 3. The model's median observed to predicted ratio was 1.26, which was not significantly different from 1, and 50% of the ratios were between 0.73 and 1.85. The percentages of ratios within factors of 2 or 3 were 67 and 82%, respectively. The percentages of ratios that were <2 or <3 were 79 and 88%, respectively. An example for Perca fluviatilis demonstrated that increased prediction accuracy could be obtained when more detailed knowledge of diet was available to estimate trophic level. Copyright © 2014 Elsevier Ltd. All rights reserved.

A 30-day-ahead forecast model for grass pollen in north London, United Kingdom.

PubMed

Smith, Matt; Emberlin, Jean

2006-03-01

A 30-day-ahead forecast method has been developed for grass pollen in north London. The total period of the grass pollen season is covered by eight multiple regression models, each covering a 10-day period running consecutively from 21 May to 8 August. This means that three models were used for each 30-day forecast. The forecast models were produced using grass pollen and environmental data from 1961 to 1999 and tested on data from 2000 and 2002. Model accuracy was judged in two ways: the number of times the forecast model was able to successfully predict the severity (relative to the 1961-1999 dataset as a whole) of grass pollen counts in each of the eight forecast periods on a scale of 1 to 4; the number of times the forecast model was able to predict whether grass pollen counts were higher or lower than the mean. The models achieved 62.5% accuracy in both assessment years when predicting the relative severity of grass pollen counts on a scale of 1 to 4, which equates to six of the eight 10-day periods being forecast correctly. The models attained 87.5% and 100% accuracy in 2000 and 2002, respectively, when predicting whether grass pollen counts would be higher or lower than the mean. Attempting to predict pollen counts during distinct 10-day periods throughout the grass pollen season is a novel approach. The models also employed original methodology in the use of winter averages of the North Atlantic Oscillation to forecast 10-day means of allergenic pollen counts.

A new computational strategy for predicting essential genes.

PubMed

Cheng, Jian; Wu, Wenwu; Zhang, Yinwen; Li, Xiangchen; Jiang, Xiaoqian; Wei, Gehong; Tao, Shiheng

2013-12-21

Determination of the minimum gene set for cellular life is one of the central goals in biology. Genome-wide essential gene identification has progressed rapidly in certain bacterial species; however, it remains difficult to achieve in most eukaryotic species. Several computational models have recently been developed to integrate gene features and used as alternatives to transfer gene essentiality annotations between organisms. We first collected features that were widely used by previous predictive models and assessed the relationships between gene features and gene essentiality using a stepwise regression model. We found two issues that could significantly reduce model accuracy: (i) the effect of multicollinearity among gene features and (ii) the diverse and even contrasting correlations between gene features and gene essentiality existing within and among different species. To address these issues, we developed a novel model called feature-based weighted Naïve Bayes model (FWM), which is based on Naïve Bayes classifiers, logistic regression, and genetic algorithm. The proposed model assesses features and filters out the effects of multicollinearity and diversity. The performance of FWM was compared with other popular models, such as support vector machine, Naïve Bayes model, and logistic regression model, by applying FWM to reciprocally predict essential genes among and within 21 species. Our results showed that FWM significantly improves the accuracy and robustness of essential gene prediction. FWM can remarkably improve the accuracy of essential gene prediction and may be used as an alternative method for other classification work. This method can contribute substantially to the knowledge of the minimum gene sets required for living organisms and the discovery of new drug targets.

Research on light rail electric load forecasting based on ARMA model

NASA Astrophysics Data System (ADS)

Huang, Yifan

2018-04-01

The article compares a variety of time series models and combines the characteristics of power load forecasting. Then, a light load forecasting model based on ARMA model is established. Based on this model, a light rail system is forecasted. The prediction results show that the accuracy of the model prediction is high.

Sweat loss prediction using a multi-model approach

NASA Astrophysics Data System (ADS)

Xu, Xiaojiang; Santee, William R.

2011-07-01

A new multi-model approach (MMA) for sweat loss prediction is proposed to improve prediction accuracy. MMA was computed as the average of sweat loss predicted by two existing thermoregulation models: i.e., the rational model SCENARIO and the empirical model Heat Strain Decision Aid (HSDA). Three independent physiological datasets, a total of 44 trials, were used to compare predictions by MMA, SCENARIO, and HSDA. The observed sweat losses were collected under different combinations of uniform ensembles, environmental conditions (15-40°C, RH 25-75%), and exercise intensities (250-600 W). Root mean square deviation (RMSD), residual plots, and paired t tests were used to compare predictions with observations. Overall, MMA reduced RMSD by 30-39% in comparison with either SCENARIO or HSDA, and increased the prediction accuracy to 66% from 34% or 55%. Of the MMA predictions, 70% fell within the range of mean observed value ± SD, while only 43% of SCENARIO and 50% of HSDA predictions fell within the same range. Paired t tests showed that differences between observations and MMA predictions were not significant, but differences between observations and SCENARIO or HSDA predictions were significantly different for two datasets. Thus, MMA predicted sweat loss more accurately than either of the two single models for the three datasets used. Future work will be to evaluate MMA using additional physiological data to expand the scope of populations and conditions.

Measuring diagnostic and predictive accuracy in disease management: an introduction to receiver operating characteristic (ROC) analysis.

PubMed

Linden, Ariel

2006-04-01

Diagnostic or predictive accuracy concerns are common in all phases of a disease management (DM) programme, and ultimately play an influential role in the assessment of programme effectiveness. Areas, such as the identification of diseased patients, predictive modelling of future health status and costs and risk stratification, are just a few of the domains in which assessment of accuracy is beneficial, if not critical. The most commonly used analytical model for this purpose is the standard 2 x 2 table method in which sensitivity and specificity are calculated. However, there are several limitations to this approach, including the reliance on a single defined criterion or cut-off for determining a true-positive result, use of non-standardized measurement instruments and sensitivity to outcome prevalence. This paper introduces the receiver operator characteristic (ROC) analysis as a more appropriate and useful technique for assessing diagnostic and predictive accuracy in DM. Its advantages include; testing accuracy across the entire range of scores and thereby not requiring a predetermined cut-off point, easily examined visual and statistical comparisons across tests or scores, and independence from outcome prevalence. Therefore the implementation of ROC as an evaluation tool should be strongly considered in the various phases of a DM programme.

Experimental and computational prediction of glass transition temperature of drugs.

PubMed

Alzghoul, Ahmad; Alhalaweh, Amjad; Mahlin, Denny; Bergström, Christel A S

2014-12-22

Glass transition temperature (Tg) is an important inherent property of an amorphous solid material which is usually determined experimentally. In this study, the relation between Tg and melting temperature (Tm) was evaluated using a data set of 71 structurally diverse druglike compounds. Further, in silico models for prediction of Tg were developed based on calculated molecular descriptors and linear (multilinear regression, partial least-squares, principal component regression) and nonlinear (neural network, support vector regression) modeling techniques. The models based on Tm predicted Tg with an RMSE of 19.5 K for the test set. Among the five computational models developed herein the support vector regression gave the best result with RMSE of 18.7 K for the test set using only four chemical descriptors. Hence, two different models that predict Tg of drug-like molecules with high accuracy were developed. If Tm is available, a simple linear regression can be used to predict Tg. However, the results also suggest that support vector regression and calculated molecular descriptors can predict Tg with equal accuracy, already before compound synthesis.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine.

PubMed

Shang, Qiang; Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine

PubMed Central

Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust. PMID:27551829

Application of a Novel Grey Self-Memory Coupling Model to Forecast the Incidence Rates of Two Notifiable Diseases in China: Dysentery and Gonorrhea

PubMed Central

Guo, Xiaojun; Liu, Sifeng; Wu, Lifeng; Tang, Lingling

2014-01-01

Objective In this study, a novel grey self-memory coupling model was developed to forecast the incidence rates of two notifiable infectious diseases (dysentery and gonorrhea); the effectiveness and applicability of this model was assessed based on its ability to predict the epidemiological trend of infectious diseases in China. Methods The linear model, the conventional GM(1,1) model and the GM(1,1) model with self-memory principle (SMGM(1,1) model) were used to predict the incidence rates of the two notifiable infectious diseases based on statistical incidence data. Both simulation accuracy and prediction accuracy were assessed to compare the predictive performances of the three models. The best-fit model was applied to predict future incidence rates. Results Simulation results show that the SMGM(1,1) model can take full advantage of the systematic multi-time historical data and possesses superior predictive performance compared with the linear model and the conventional GM(1,1) model. By applying the novel SMGM(1,1) model, we obtained the possible incidence rates of the two representative notifiable infectious diseases in China. Conclusion The disadvantages of the conventional grey prediction model, such as sensitivity to initial value, can be overcome by the self-memory principle. The novel grey self-memory coupling model can predict the incidence rates of infectious diseases more accurately than the conventional model, and may provide useful references for making decisions involving infectious disease prevention and control. PMID:25546054

Application of a novel grey self-memory coupling model to forecast the incidence rates of two notifiable diseases in China: dysentery and gonorrhea.

PubMed

Guo, Xiaojun; Liu, Sifeng; Wu, Lifeng; Tang, Lingling

2014-01-01

In this study, a novel grey self-memory coupling model was developed to forecast the incidence rates of two notifiable infectious diseases (dysentery and gonorrhea); the effectiveness and applicability of this model was assessed based on its ability to predict the epidemiological trend of infectious diseases in China. The linear model, the conventional GM(1,1) model and the GM(1,1) model with self-memory principle (SMGM(1,1) model) were used to predict the incidence rates of the two notifiable infectious diseases based on statistical incidence data. Both simulation accuracy and prediction accuracy were assessed to compare the predictive performances of the three models. The best-fit model was applied to predict future incidence rates. Simulation results show that the SMGM(1,1) model can take full advantage of the systematic multi-time historical data and possesses superior predictive performance compared with the linear model and the conventional GM(1,1) model. By applying the novel SMGM(1,1) model, we obtained the possible incidence rates of the two representative notifiable infectious diseases in China. The disadvantages of the conventional grey prediction model, such as sensitivity to initial value, can be overcome by the self-memory principle. The novel grey self-memory coupling model can predict the incidence rates of infectious diseases more accurately than the conventional model, and may provide useful references for making decisions involving infectious disease prevention and control.

Use of Cell Viability Assay Data Improves the Prediction Accuracy of Conventional Quantitative Structure–Activity Relationship Models of Animal Carcinogenicity

PubMed Central

Zhu, Hao; Rusyn, Ivan; Richard, Ann; Tropsha, Alexander

2008-01-01

Background To develop efficient approaches for rapid evaluation of chemical toxicity and human health risk of environmental compounds, the National Toxicology Program (NTP) in collaboration with the National Center for Chemical Genomics has initiated a project on high-throughput screening (HTS) of environmental chemicals. The first HTS results for a set of 1,408 compounds tested for their effects on cell viability in six different cell lines have recently become available via PubChem. Objectives We have explored these data in terms of their utility for predicting adverse health effects of the environmental agents. Methods and results Initially, the classification k nearest neighbor (kNN) quantitative structure–activity relationship (QSAR) modeling method was applied to the HTS data only, for a curated data set of 384 compounds. The resulting models had prediction accuracies for training, test (containing 275 compounds together), and external validation (109 compounds) sets as high as 89%, 71%, and 74%, respectively. We then asked if HTS results could be of value in predicting rodent carcinogenicity. We identified 383 compounds for which data were available from both the Berkeley Carcinogenic Potency Database and NTP–HTS studies. We found that compounds classified by HTS as “actives” in at least one cell line were likely to be rodent carcinogens (sensitivity 77%); however, HTS “inactives” were far less informative (specificity 46%). Using chemical descriptors only, kNN QSAR modeling resulted in 62.3% prediction accuracy for rodent carcinogenicity applied to this data set. Importantly, the prediction accuracy of the model was significantly improved (72.7%) when chemical descriptors were augmented by HTS data, which were regarded as biological descriptors. Conclusions Our studies suggest that combining NTP–HTS profiles with conventional chemical descriptors could considerably improve the predictive power of computational approaches in toxicology. PMID:18414635

The predictability of consumer visitation patterns

NASA Astrophysics Data System (ADS)

Krumme, Coco; Llorente, Alejandro; Cebrian, Manuel; Pentland, Alex ("Sandy"); Moro, Esteban

2013-04-01

We consider hundreds of thousands of individual economic transactions to ask: how predictable are consumers in their merchant visitation patterns? Our results suggest that, in the long-run, much of our seemingly elective activity is actually highly predictable. Notwithstanding a wide range of individual preferences, shoppers share regularities in how they visit merchant locations over time. Yet while aggregate behavior is largely predictable, the interleaving of shopping events introduces important stochastic elements at short time scales. These short- and long-scale patterns suggest a theoretical upper bound on predictability, and describe the accuracy of a Markov model in predicting a person's next location. We incorporate population-level transition probabilities in the predictive models, and find that in many cases these improve accuracy. While our results point to the elusiveness of precise predictions about where a person will go next, they suggest the existence, at large time-scales, of regularities across the population.

The predictability of consumer visitation patterns

PubMed Central

Krumme, Coco; Llorente, Alejandro; Cebrian, Manuel; Pentland, Alex ("Sandy"); Moro, Esteban

2013-01-01

We consider hundreds of thousands of individual economic transactions to ask: how predictable are consumers in their merchant visitation patterns? Our results suggest that, in the long-run, much of our seemingly elective activity is actually highly predictable. Notwithstanding a wide range of individual preferences, shoppers share regularities in how they visit merchant locations over time. Yet while aggregate behavior is largely predictable, the interleaving of shopping events introduces important stochastic elements at short time scales. These short- and long-scale patterns suggest a theoretical upper bound on predictability, and describe the accuracy of a Markov model in predicting a person's next location. We incorporate population-level transition probabilities in the predictive models, and find that in many cases these improve accuracy. While our results point to the elusiveness of precise predictions about where a person will go next, they suggest the existence, at large time-scales, of regularities across the population. PMID:23598917

Compound activity prediction using models of binding pockets or ligand properties in 3D

PubMed Central

Kufareva, Irina; Chen, Yu-Chen; Ilatovskiy, Andrey V.; Abagyan, Ruben

2014-01-01

Transient interactions of endogenous and exogenous small molecules with flexible binding sites in proteins or macromolecular assemblies play a critical role in all biological processes. Current advances in high-resolution protein structure determination, database development, and docking methodology make it possible to design three-dimensional models for prediction of such interactions with increasing accuracy and specificity. Using the data collected in the Pocketome encyclopedia, we here provide an overview of two types of the three-dimensional ligand activity models, pocket-based and ligand property-based, for two important classes of proteins, nuclear and G-protein coupled receptors. For half the targets, the pocket models discriminate actives from property matched decoys with acceptable accuracy (the area under ROC curve, AUC, exceeding 84%) and for about one fifth of the targets with high accuracy (AUC > 95%). The 3D ligand property field models performed better than 95% in half of the cases. The high performance models can already become a basis of activity predictions for new chemicals. Family-wide benchmarking of the models highlights strengths of both approaches and helps identify their inherent bottlenecks and challenges. PMID:23116466

Genome-Enabled Estimates of Additive and Nonadditive Genetic Variances and Prediction of Apple Phenotypes Across Environments

PubMed Central

Kumar, Satish; Molloy, Claire; Muñoz, Patricio; Daetwyler, Hans; Chagné, David; Volz, Richard

2015-01-01

The nonadditive genetic effects may have an important contribution to total genetic variation of phenotypes, so estimates of both the additive and nonadditive effects are desirable for breeding and selection purposes. Our main objectives were to: estimate additive, dominance and epistatic variances of apple (Malus × domestica Borkh.) phenotypes using relationship matrices constructed from genome-wide dense single nucleotide polymorphism (SNP) markers; and compare the accuracy of genomic predictions using genomic best linear unbiased prediction models with or without including nonadditive genetic effects. A set of 247 clonally replicated individuals was assessed for six fruit quality traits at two sites, and also genotyped using an Illumina 8K SNP array. Across several fruit quality traits, the additive, dominance, and epistatic effects contributed about 30%, 16%, and 19%, respectively, to the total phenotypic variance. Models ignoring nonadditive components yielded upwardly biased estimates of additive variance (heritability) for all traits in this study. The accuracy of genomic predicted genetic values (GEGV) varied from about 0.15 to 0.35 for various traits, and these were almost identical for models with or without including nonadditive effects. However, models including nonadditive genetic effects further reduced the bias of GEGV. Between-site genotypic correlations were high (>0.85) for all traits, and genotype-site interaction accounted for <10% of the phenotypic variability. The accuracy of prediction, when the validation set was present only at one site, was generally similar for both sites, and varied from about 0.50 to 0.85. The prediction accuracies were strongly influenced by trait heritability, and genetic relatedness between the training and validation families. PMID:26497141

Improving transmembrane protein consensus topology prediction using inter-helical interaction.

PubMed

Wang, Han; Zhang, Chao; Shi, Xiaohu; Zhang, Li; Zhou, You

2012-11-01

Alpha helix transmembrane proteins (αTMPs) represent roughly 30% of all open reading frames (ORFs) in a typical genome and are involved in many critical biological processes. Due to the special physicochemical properties, it is hard to crystallize and obtain high resolution structures experimentally, thus, sequence-based topology prediction is highly desirable for the study of transmembrane proteins (TMPs), both in structure prediction and function prediction. Various model-based topology prediction methods have been developed, but the accuracy of those individual predictors remain poor due to the limitation of the methods or the features they used. Thus, the consensus topology prediction method becomes practical for high accuracy applications by combining the advances of the individual predictors. Here, based on the observation that inter-helical interactions are commonly found within the transmembrane helixes (TMHs) and strongly indicate the existence of them, we present a novel consensus topology prediction method for αTMPs, CNTOP, which incorporates four top leading individual topology predictors, and further improves the prediction accuracy by using the predicted inter-helical interactions. The method achieved 87% prediction accuracy based on a benchmark dataset and 78% accuracy based on a non-redundant dataset which is composed of polytopic αTMPs. Our method derives the highest topology accuracy than any other individual predictors and consensus predictors, at the same time, the TMHs are more accurately predicted in their length and locations, where both the false positives (FPs) and the false negatives (FNs) decreased dramatically. The CNTOP is available at: http://ccst.jlu.edu.cn/JCSB/cntop/CNTOP.html. Copyright © 2012 Elsevier B.V. All rights reserved.

Comparison of Adjacency and Distance-Based Approaches for Spatial Analysis of Multimodal Traffic Crash Data

NASA Astrophysics Data System (ADS)

Gill, G.; Sakrani, T.; Cheng, W.; Zhou, J.

2017-09-01

Many studies have utilized the spatial correlations among traffic crash data to develop crash prediction models with the aim to investigate the influential factors or predict crash counts at different sites. The spatial correlation have been observed to account for heterogeneity in different forms of weight matrices which improves the estimation performance of models. But very rarely have the weight matrices been compared for the prediction accuracy for estimation of crash counts. This study was targeted at the comparison of two different approaches for modelling the spatial correlations among crash data at macro-level (County). Multivariate Full Bayesian crash prediction models were developed using Decay-50 (distance-based) and Queen-1 (adjacency-based) weight matrices for simultaneous estimation crash counts of four different modes: vehicle, motorcycle, bike, and pedestrian. The goodness-of-fit and different criteria for accuracy at prediction of crash count reveled the superiority of Decay-50 over Queen-1. Decay-50 was essentially different from Queen-1 with the selection of neighbors and more robust spatial weight structure which rendered the flexibility to accommodate the spatially correlated crash data. The consistently better performance of Decay-50 at prediction accuracy further bolstered its superiority. Although the data collection efforts to gather centroid distance among counties for Decay-50 may appear to be a downside, but the model has a significant edge to fit the crash data without losing the simplicity of computation of estimated crash count.

Bayesian averaging over Decision Tree models for trauma severity scoring.

PubMed

Schetinin, V; Jakaite, L; Krzanowski, W

2018-01-01

Health care practitioners analyse possible risks of misleading decisions and need to estimate and quantify uncertainty in predictions. We have examined the "gold" standard of screening a patient's conditions for predicting survival probability, based on logistic regression modelling, which is used in trauma care for clinical purposes and quality audit. This methodology is based on theoretical assumptions about data and uncertainties. Models induced within such an approach have exposed a number of problems, providing unexplained fluctuation of predicted survival and low accuracy of estimating uncertainty intervals within which predictions are made. Bayesian method, which in theory is capable of providing accurate predictions and uncertainty estimates, has been adopted in our study using Decision Tree models. Our approach has been tested on a large set of patients registered in the US National Trauma Data Bank and has outperformed the standard method in terms of prediction accuracy, thereby providing practitioners with accurate estimates of the predictive posterior densities of interest that are required for making risk-aware decisions. Copyright © 2017 Elsevier B.V. All rights reserved.

Comparison of Two Predictive Models for Short-Term Mortality in Patients after Severe Traumatic Brain Injury.

PubMed

Kesmarky, Klara; Delhumeau, Cecile; Zenobi, Marie; Walder, Bernhard

2017-07-15

The Glasgow Coma Scale (GCS) and the Abbreviated Injury Score of the head region (HAIS) are validated prognostic factors in traumatic brain injury (TBI). The aim of this study was to compare the prognostic performance of an alternative predictive model including motor GCS, pupillary reactivity, age, HAIS, and presence of multi-trauma for short-term mortality with a reference predictive model including motor GCS, pupil reaction, and age (IMPACT core model). A secondary analysis of a prospective epidemiological cohort study in Switzerland including patients after severe TBI (HAIS >3) with the outcome death at 14 days was performed. Performance of prediction, accuracy of discrimination (area under the receiver operating characteristic curve [AUROC]), calibration, and validity of the two predictive models were investigated. The cohort included 808 patients (median age, 56; interquartile range, 33-71), median GCS at hospital admission 3 (3-14), abnormal pupil reaction 29%, with a death rate of 29.7% at 14 days. The alternative predictive model had a higher accuracy of discrimination to predict death at 14 days than the reference predictive model (AUROC 0.852, 95% confidence interval [CI] 0.824-0.880 vs. AUROC 0.826, 95% CI 0.795-0.857; p < 0.0001). The alternative predictive model had an equivalent calibration, compared with the reference predictive model Hosmer-Lemeshow p values (Chi2 8.52, Hosmer-Lemeshow p = 0.345 vs. Chi2 8.66, Hosmer-Lemeshow p = 0.372). The optimism-corrected value of AUROC for the alternative predictive model was 0.845. After severe TBI, a higher performance of prediction for short-term mortality was observed with the alternative predictive model, compared with the reference predictive model.

Effects of sample survey design on the accuracy of classification tree models in species distribution models

Treesearch

Thomas C. Edwards; D. Richard Cutler; Niklaus E. Zimmermann; Linda Geiser; Gretchen G. Moisen

2006-01-01

We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by...

Can plantar soft tissue mechanics enhance prognosis of diabetic foot ulcer?

PubMed

Naemi, R; Chatzistergos, P; Suresh, S; Sundar, L; Chockalingam, N; Ramachandran, A

2017-04-01

To investigate if the assessment of the mechanical properties of plantar soft tissue can increase the accuracy of predicting Diabetic Foot Ulceration (DFU). 40 patients with diabetic neuropathy and no DFU were recruited. Commonly assessed clinical parameters along with plantar soft tissue stiffness and thickness were measured at baseline using ultrasound elastography technique. 7 patients developed foot ulceration during a 12months follow-up. Logistic regression was used to identify parameters that contribute to predicting the DFU incidence. The effect of using parameters related to the mechanical behaviour of plantar soft tissue on the specificity, sensitivity, prediction strength and accuracy of the predicting models for DFU was assessed. Patients with higher plantar soft tissue thickness and lower stiffness at the 1st Metatarsal head area showed an increased risk of DFU. Adding plantar soft tissue stiffness and thickness to the model improved its specificity (by 3%), sensitivity (by 14%), prediction accuracy (by 5%) and prognosis strength (by 1%). The model containing all predictors was able to effectively (χ 2 (8, N=40)=17.55, P<0.05) distinguish between the patients with and without DFU incidence. The mechanical properties of plantar soft tissue can be used to improve the predictability of DFU in moderate/high risk patients. Copyright © 2017 Elsevier B.V. All rights reserved.

Increased prediction accuracy in wheat breeding trials using a marker x environment interaction genomic selection model

USDA-ARS?s Scientific Manuscript database

Genomic selection (GS) models use genome-wide genetic information to predict genetic values of candidates for selection. Originally these models were developed without considering genotype ' environment interaction (GE). Several authors have proposed extensions of the cannonical GS model that accomm...

Adjusting the Stems Regional Forest Growth Model to Improve Local Predictions

Treesearch

W. Brad Smith

1983-01-01

A simple procedure using double sampling is described for adjusting growth in the STEMS regional forest growth model to compensate for subregional variations. Predictive accuracy of the STEMS model (a distance-independent, individual tree growth model for Lake States forests) was improved by using this procedure

Evaluating Forest Vegetation Simulator predictions for southern Appalachian upland hardwoods with a modified mortality model

Treesearch

Philip J. Radtke; Nathan D. Herring; David L. Loftis; Chad E. Keyser

2012-01-01

Prediction accuracy for projected basal area and trees per acre was assessed for the growth and yield model of the Forest Vegetation Simulator Southern Variant (FVS-Sn). Data for comparison with FVS-Sn predictions were compiled from a collection of n

Analysis of Mining-Induced Subsidence Prediction by Exponent Knothe Model Combined with Insar and Leveling

NASA Astrophysics Data System (ADS)

Chen, Lei; Zhang, Liguo; Tang, Yixian; Zhang, Hong

2018-04-01

The principle of exponent Knothe model was introduced in detail and the variation process of mining subsidence with time was analysed based on the formulas of subsidence, subsidence velocity and subsidence acceleration in the paper. Five scenes of radar images and six levelling measurements were collected to extract ground deformation characteristics in one coal mining area in this study. Then the unknown parameters of exponent Knothe model were estimated by combined levelling data with deformation information along the line of sight obtained by InSAR technique. By compared the fitting and prediction results obtained by InSAR and levelling with that obtained only by levelling, it was shown that the accuracy of fitting and prediction combined with InSAR and levelling was obviously better than the other that. Therefore, the InSAR measurements can significantly improve the fitting and prediction accuracy of exponent Knothe model.

Checking the predictive accuracy of basic symptoms against ultra high-risk criteria and testing of a multivariable prediction model: Evidence from a prospective three-year observational study of persons at clinical high-risk for psychosis.

PubMed

Hengartner, M P; Heekeren, K; Dvorsky, D; Walitza, S; Rössler, W; Theodoridou, A

2017-09-01

The aim of this study was to critically examine the prognostic validity of various clinical high-risk (CHR) criteria alone and in combination with additional clinical characteristics. A total of 188 CHR positive persons from the region of Zurich, Switzerland (mean age 20.5 years; 60.2% male), meeting ultra high-risk (UHR) and/or basic symptoms (BS) criteria, were followed over three years. The test battery included the Structured Interview for Prodromal Syndromes (SIPS), verbal IQ and many other screening tools. Conversion to psychosis was defined according to ICD-10 criteria for schizophrenia (F20) or brief psychotic disorder (F23). Altogether n=24 persons developed manifest psychosis within three years and according to Kaplan-Meier survival analysis, the projected conversion rate was 17.5%. The predictive accuracy of UHR was statistically significant but poor (area under the curve [AUC]=0.65, P<.05), whereas BS did not predict psychosis beyond mere chance (AUC=0.52, P=.730). Sensitivity and specificity were 0.83 and 0.47 for UHR, and 0.96 and 0.09 for BS. UHR plus BS achieved an AUC=0.66, with sensitivity and specificity of 0.75 and 0.56. In comparison, baseline antipsychotic medication yielded a predictive accuracy of AUC=0.62 (sensitivity=0.42; specificity=0.82). A multivariable prediction model comprising continuous measures of positive symptoms and verbal IQ achieved a substantially improved prognostic accuracy (AUC=0.85; sensitivity=0.86; specificity=0.85; positive predictive value=0.54; negative predictive value=0.97). We showed that BS have no predictive accuracy beyond chance, while UHR criteria poorly predict conversion to psychosis. Combining BS with UHR criteria did not improve the predictive accuracy of UHR alone. In contrast, dimensional measures of both positive symptoms and verbal IQ showed excellent prognostic validity. A critical re-thinking of binary at-risk criteria is necessary in order to improve the prognosis of psychotic disorders. Copyright © 2017 Elsevier Masson SAS. All rights reserved.

Accuracy of the actuator disc-RANS approach for predicting the performance and wake of tidal turbines.

PubMed

Batten, W M J; Harrison, M E; Bahaj, A S

2013-02-28

The actuator disc-RANS model has widely been used in wind and tidal energy to predict the wake of a horizontal axis turbine. The model is appropriate where large-scale effects of the turbine on a flow are of interest, for example, when considering environmental impacts, or arrays of devices. The accuracy of the model for modelling the wake of tidal stream turbines has not been demonstrated, and flow predictions presented in the literature for similar modelled scenarios vary significantly. This paper compares the results of the actuator disc-RANS model, where the turbine forces have been derived using a blade-element approach, to experimental data measured in the wake of a scaled turbine. It also compares the results with those of a simpler uniform actuator disc model. The comparisons show that the model is accurate and can predict up to 94 per cent of the variation in the experimental velocity data measured on the centreline of the wake, therefore demonstrating that the actuator disc-RANS model is an accurate approach for modelling a turbine wake, and a conservative approach to predict performance and loads. It can therefore be applied to similar scenarios with confidence.

Multivariate Models for Prediction of Human Skin Sensitization Hazard

PubMed Central

Strickland, Judy; Zang, Qingda; Paris, Michael; Lehmann, David M.; Allen, David; Choksi, Neepa; Matheson, Joanna; Jacobs, Abigail; Casey, Warren; Kleinstreuer, Nicole

2016-01-01

One of ICCVAM’s top priorities is the development and evaluation of non-animal approaches to identify potential skin sensitizers. The complexity of biological events necessary to produce skin sensitization suggests that no single alternative method will replace the currently accepted animal tests. ICCVAM is evaluating an integrated approach to testing and assessment based on the adverse outcome pathway for skin sensitization that uses machine learning approaches to predict human skin sensitization hazard. We combined data from three in chemico or in vitro assays—the direct peptide reactivity assay (DPRA), human cell line activation test (h-CLAT), and KeratinoSens™ assay—six physicochemical properties, and an in silico read-across prediction of skin sensitization hazard into 12 variable groups. The variable groups were evaluated using two machine learning approaches, logistic regression (LR) and support vector machine (SVM), to predict human skin sensitization hazard. Models were trained on 72 substances and tested on an external set of 24 substances. The six models (three LR and three SVM) with the highest accuracy (92%) used: (1) DPRA, h-CLAT, and read-across; (2) DPRA, h-CLAT, read-across, and KeratinoSens; or (3) DPRA, h-CLAT, read-across, KeratinoSens, and log P. The models performed better at predicting human skin sensitization hazard than the murine local lymph node assay (accuracy = 88%), any of the alternative methods alone (accuracy = 63–79%), or test batteries combining data from the individual methods (accuracy = 75%). These results suggest that computational methods are promising tools to effectively identify potential human skin sensitizers without animal testing. PMID:27480324

Testing the predictive value of peripheral gene expression for nonremission following citalopram treatment for major depression.

PubMed

Guilloux, Jean-Philippe; Bassi, Sabrina; Ding, Ying; Walsh, Chris; Turecki, Gustavo; Tseng, George; Cyranowski, Jill M; Sibille, Etienne

2015-02-01

Major depressive disorder (MDD) in general, and anxious-depression in particular, are characterized by poor rates of remission with first-line treatments, contributing to the chronic illness burden suffered by many patients. Prospective research is needed to identify the biomarkers predicting nonremission prior to treatment initiation. We collected blood samples from a discovery cohort of 34 adult MDD patients with co-occurring anxiety and 33 matched, nondepressed controls at baseline and after 12 weeks (of citalopram plus psychotherapy treatment for the depressed cohort). Samples were processed on gene arrays and group differences in gene expression were investigated. Exploratory analyses suggest that at pretreatment baseline, nonremitting patients differ from controls with gene function and transcription factor analyses potentially related to elevated inflammation and immune activation. In a second phase, we applied an unbiased machine learning prediction model and corrected for model-selection bias. Results show that baseline gene expression predicted nonremission with 79.4% corrected accuracy with a 13-gene model. The same gene-only model predicted nonremission after 8 weeks of citalopram treatment with 76% corrected accuracy in an independent validation cohort of 63 MDD patients treated with citalopram at another institution. Together, these results demonstrate the potential, but also the limitations, of baseline peripheral blood-based gene expression to predict nonremission after citalopram treatment. These results not only support their use in future prediction tools but also suggest that increased accuracy may be obtained with the inclusion of additional predictors (eg, genetics and clinical scales).

[GSH fermentation process modeling using entropy-criterion based RBF neural network model].

PubMed

Tan, Zuoping; Wang, Shitong; Deng, Zhaohong; Du, Guocheng

2008-05-01

The prediction accuracy and generalization of GSH fermentation process modeling are often deteriorated by noise existing in the corresponding experimental data. In order to avoid this problem, we present a novel RBF neural network modeling approach based on entropy criterion. It considers the whole distribution structure of the training data set in the parameter learning process compared with the traditional MSE-criterion based parameter learning, and thus effectively avoids the weak generalization and over-learning. Then the proposed approach is applied to the GSH fermentation process modeling. Our results demonstrate that this proposed method has better prediction accuracy, generalization and robustness such that it offers a potential application merit for the GSH fermentation process modeling.

Real estate value prediction using multivariate regression models

NASA Astrophysics Data System (ADS)

Manjula, R.; Jain, Shubham; Srivastava, Sharad; Rajiv Kher, Pranav

2017-11-01

The real estate market is one of the most competitive in terms of pricing and the same tends to vary significantly based on a lot of factors, hence it becomes one of the prime fields to apply the concepts of machine learning to optimize and predict the prices with high accuracy. Therefore in this paper, we present various important features to use while predicting housing prices with good accuracy. We have described regression models, using various features to have lower Residual Sum of Squares error. While using features in a regression model some feature engineering is required for better prediction. Often a set of features (multiple regressions) or polynomial regression (applying a various set of powers in the features) is used for making better model fit. For these models are expected to be susceptible towards over fitting ridge regression is used to reduce it. This paper thus directs to the best application of regression models in addition to other techniques to optimize the result.

Modeling observations of solar coronal mass ejections with heliospheric imagers verified with the Heliophysics System Observatory.

PubMed

Möstl, C; Isavnin, A; Boakes, P D; Kilpua, E K J; Davies, J A; Harrison, R A; Barnes, D; Krupar, V; Eastwood, J P; Good, S W; Forsyth, R J; Bothmer, V; Reiss, M A; Amerstorfer, T; Winslow, R M; Anderson, B J; Philpott, L C; Rodriguez, L; Rouillard, A P; Gallagher, P; Nieves-Chinchilla, T; Zhang, T L

2017-07-01

We present an advance toward accurately predicting the arrivals of coronal mass ejections (CMEs) at the terrestrial planets, including Earth. For the first time, we are able to assess a CME prediction model using data over two thirds of a solar cycle of observations with the Heliophysics System Observatory. We validate modeling results of 1337 CMEs observed with the Solar Terrestrial Relations Observatory (STEREO) heliospheric imagers (HI) (science data) from 8 years of observations by five in situ observing spacecraft. We use the self-similar expansion model for CME fronts assuming 60° longitudinal width, constant speed, and constant propagation direction. With these assumptions we find that 23%-35% of all CMEs that were predicted to hit a certain spacecraft lead to clear in situ signatures, so that for one correct prediction, two to three false alarms would have been issued. In addition, we find that the prediction accuracy does not degrade with the HI longitudinal separation from Earth. Predicted arrival times are on average within 2.6 ± 16.6 h difference of the in situ arrival time, similar to analytical and numerical modeling, and a true skill statistic of 0.21. We also discuss various factors that may improve the accuracy of space weather forecasting using wide-angle heliospheric imager observations. These results form a first-order approximated baseline of the prediction accuracy that is possible with HI and other methods used for data by an operational space weather mission at the Sun-Earth L5 point.

Modeling observations of solar coronal mass ejections with heliospheric imagers verified with the Heliophysics System Observatory

PubMed Central

Isavnin, A.; Boakes, P. D.; Kilpua, E. K. J.; Davies, J. A.; Harrison, R. A.; Barnes, D.; Krupar, V.; Eastwood, J. P.; Good, S. W.; Forsyth, R. J.; Bothmer, V.; Reiss, M. A.; Amerstorfer, T.; Winslow, R. M.; Anderson, B. J.; Philpott, L. C.; Rodriguez, L.; Rouillard, A. P.; Gallagher, P.; Nieves‐Chinchilla, T.; Zhang, T. L.

2017-01-01

Abstract We present an advance toward accurately predicting the arrivals of coronal mass ejections (CMEs) at the terrestrial planets, including Earth. For the first time, we are able to assess a CME prediction model using data over two thirds of a solar cycle of observations with the Heliophysics System Observatory. We validate modeling results of 1337 CMEs observed with the Solar Terrestrial Relations Observatory (STEREO) heliospheric imagers (HI) (science data) from 8 years of observations by five in situ observing spacecraft. We use the self‐similar expansion model for CME fronts assuming 60° longitudinal width, constant speed, and constant propagation direction. With these assumptions we find that 23%–35% of all CMEs that were predicted to hit a certain spacecraft lead to clear in situ signatures, so that for one correct prediction, two to three false alarms would have been issued. In addition, we find that the prediction accuracy does not degrade with the HI longitudinal separation from Earth. Predicted arrival times are on average within 2.6 ± 16.6 h difference of the in situ arrival time, similar to analytical and numerical modeling, and a true skill statistic of 0.21. We also discuss various factors that may improve the accuracy of space weather forecasting using wide‐angle heliospheric imager observations. These results form a first‐order approximated baseline of the prediction accuracy that is possible with HI and other methods used for data by an operational space weather mission at the Sun‐Earth L5 point. PMID:28983209

Cross-trial prediction of treatment outcome in depression: a machine learning approach.

PubMed

Chekroud, Adam Mourad; Zotti, Ryan Joseph; Shehzad, Zarrar; Gueorguieva, Ralitza; Johnson, Marcia K; Trivedi, Madhukar H; Cannon, Tyrone D; Krystal, John Harrison; Corlett, Philip Robert

2016-03-01

Antidepressant treatment efficacy is low, but might be improved by matching patients to interventions. At present, clinicians have no empirically validated mechanisms to assess whether a patient with depression will respond to a specific antidepressant. We aimed to develop an algorithm to assess whether patients will achieve symptomatic remission from a 12-week course of citalopram. We used patient-reported data from patients with depression (n=4041, with 1949 completers) from level 1 of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D; ClinicalTrials.gov, number NCT00021528) to identify variables that were most predictive of treatment outcome, and used these variables to train a machine-learning model to predict clinical remission. We externally validated the model in the escitalopram treatment group (n=151) of an independent clinical trial (Combining Medications to Enhance Depression Outcomes [COMED]; ClinicalTrials.gov, number NCT00590863). We identified 25 variables that were most predictive of treatment outcome from 164 patient-reportable variables, and used these to train the model. The model was internally cross-validated, and predicted outcomes in the STAR*D cohort with accuracy significantly above chance (64·6% [SD 3·2]; p<0·0001). The model was externally validated in the escitalopram treatment group (N=151) of COMED (accuracy 59·6%, p=0.043). The model also performed significantly above chance in a combined escitalopram-buproprion treatment group in COMED (n=134; accuracy 59·7%, p=0·023), but not in a combined venlafaxine-mirtazapine group (n=140; accuracy 51·4%, p=0·53), suggesting specificity of the model to underlying mechanisms. Building statistical models by mining existing clinical trial data can enable prospective identification of patients who are likely to respond to a specific antidepressant. Yale University. Copyright © 2016 Elsevier Ltd. All rights reserved.

Clinical time series prediction: towards a hierarchical dynamical system framework

PubMed Central

Liu, Zitao; Hauskrecht, Milos

2014-01-01

Objective Developing machine learning and data mining algorithms for building temporal models of clinical time series is important for understanding of the patient condition, the dynamics of a disease, effect of various patient management interventions and clinical decision making. In this work, we propose and develop a novel hierarchical framework for modeling clinical time series data of varied length and with irregularly sampled observations. Materials and methods Our hierarchical dynamical system framework for modeling clinical time series combines advantages of the two temporal modeling approaches: the linear dynamical system and the Gaussian process. We model the irregularly sampled clinical time series by using multiple Gaussian process sequences in the lower level of our hierarchical framework and capture the transitions between Gaussian processes by utilizing the linear dynamical system. The experiments are conducted on the complete blood count (CBC) panel data of 1000 post-surgical cardiac patients during their hospitalization. Our framework is evaluated and compared to multiple baseline approaches in terms of the mean absolute prediction error and the absolute percentage error. Results We tested our framework by first learning the time series model from data for the patient in the training set, and then applying the model in order to predict future time series values on the patients in the test set. We show that our model outperforms multiple existing models in terms of its predictive accuracy. Our method achieved a 3.13% average prediction accuracy improvement on ten CBC lab time series when it was compared against the best performing baseline. A 5.25% average accuracy improvement was observed when only short-term predictions were considered. Conclusion A new hierarchical dynamical system framework that lets us model irregularly sampled time series data is a promising new direction for modeling clinical time series and for improving their predictive performance. PMID:25534671

Fuzzy regression modeling for tool performance prediction and degradation detection.

PubMed

Li, X; Er, M J; Lim, B S; Zhou, J H; Gan, O P; Rutkowski, L

2010-10-01

In this paper, the viability of using Fuzzy-Rule-Based Regression Modeling (FRM) algorithm for tool performance and degradation detection is investigated. The FRM is developed based on a multi-layered fuzzy-rule-based hybrid system with Multiple Regression Models (MRM) embedded into a fuzzy logic inference engine that employs Self Organizing Maps (SOM) for clustering. The FRM converts a complex nonlinear problem to a simplified linear format in order to further increase the accuracy in prediction and rate of convergence. The efficacy of the proposed FRM is tested through a case study - namely to predict the remaining useful life of a ball nose milling cutter during a dry machining process of hardened tool steel with a hardness of 52-54 HRc. A comparative study is further made between four predictive models using the same set of experimental data. It is shown that the FRM is superior as compared with conventional MRM, Back Propagation Neural Networks (BPNN) and Radial Basis Function Networks (RBFN) in terms of prediction accuracy and learning speed.

Prediction Accuracy of Error Rates for MPTB Space Experiment

NASA Technical Reports Server (NTRS)

Buchner, S. P.; Campbell, A. B.; Davis, D.; McMorrow, D.; Petersen, E. L.; Stassinopoulos, E. G.; Ritter, J. C.

1998-01-01

This paper addresses the accuracy of radiation-induced upset-rate predictions in space using the results of ground-based measurements together with standard environmental and device models. The study is focused on two part types - 16 Mb NEC DRAM's (UPD4216) and 1 Kb SRAM's (AMD93L422) - both of which are currently in space on board the Microelectronics and Photonics Test Bed (MPTB). To date, ground-based measurements of proton-induced single event upset (SEM cross sections as a function of energy have been obtained and combined with models of the proton environment to predict proton-induced error rates in space. The role played by uncertainties in the environmental models will be determined by comparing the modeled radiation environment with the actual environment measured aboard MPTB. Heavy-ion induced upsets have also been obtained from MPTB and will be compared with the "predicted" error rate following ground testing that will be done in the near future. These results should help identify sources of uncertainty in predictions of SEU rates in space.

Effects of urban microcellular environments on ray-tracing-based coverage predictions.

PubMed

Liu, Zhongyu; Guo, Lixin; Guan, Xiaowei; Sun, Jiejing

2016-09-01

The ray-tracing (RT) algorithm, which is based on geometrical optics and the uniform theory of diffraction, has become a typical deterministic approach of studying wave-propagation characteristics. Under urban microcellular environments, the RT method highly depends on detailed environmental information. The aim of this paper is to provide help in selecting the appropriate level of accuracy required in building databases to achieve good tradeoffs between database costs and prediction accuracy. After familiarization with the operating procedures of the RT-based prediction model, this study focuses on the effect of errors in environmental information on prediction results. The environmental information consists of two parts, namely, geometric and electrical parameters. The geometric information can be obtained from a digital map of a city. To study the effects of inaccuracies in geometry information (building layout) on RT-based coverage prediction, two different artificial erroneous maps are generated based on the original digital map, and systematic analysis is performed by comparing the predictions with the erroneous maps and measurements or the predictions with the original digital map. To make the conclusion more persuasive, the influence of random errors on RMS delay spread results is investigated. Furthermore, given the electrical parameters' effect on the accuracy of the predicted results of the RT model, the dielectric constant and conductivity of building materials are set with different values. The path loss and RMS delay spread under the same circumstances are simulated by the RT prediction model.

COMPASS: A computational model to predict changes in MMSE scores 24-months after initial assessment of Alzheimer's disease.

PubMed

Zhu, Fan; Panwar, Bharat; Dodge, Hiroko H; Li, Hongdong; Hampstead, Benjamin M; Albin, Roger L; Paulson, Henry L; Guan, Yuanfang

2016-10-05

We present COMPASS, a COmputational Model to Predict the development of Alzheimer's diSease Spectrum, to model Alzheimer's disease (AD) progression. This was the best-performing method in recent crowdsourcing benchmark study, DREAM Alzheimer's Disease Big Data challenge to predict changes in Mini-Mental State Examination (MMSE) scores over 24-months using standardized data. In the present study, we conducted three additional analyses beyond the DREAM challenge question to improve the clinical contribution of our approach, including: (1) adding pre-validated baseline cognitive composite scores of ADNI-MEM and ADNI-EF, (2) identifying subjects with significant declines in MMSE scores, and (3) incorporating SNPs of top 10 genes connected to APOE identified from functional-relationship network. For (1) above, we significantly improved predictive accuracy, especially for the Mild Cognitive Impairment (MCI) group. For (2), we achieved an area under ROC of 0.814 in predicting significant MMSE decline: our model has 100% precision at 5% recall, and 91% accuracy at 10% recall. For (3), "genetic only" model has Pearson's correlation of 0.15 to predict progression in the MCI group. Even though addition of this limited genetic model to COMPASS did not improve prediction of progression of MCI group, the predictive ability of SNP information extended beyond well-known APOE allele.

In silico models for predicting ready biodegradability under REACH: a comparative study.

PubMed

Pizzo, Fabiola; Lombardo, Anna; Manganaro, Alberto; Benfenati, Emilio

2013-10-01

REACH (Registration Evaluation Authorization and restriction of Chemicals) legislation is a new European law which aims to raise the human protection level and environmental health. Under REACH all chemicals manufactured or imported for more than one ton per year must be evaluated for their ready biodegradability. Ready biodegradability is also used as a screening test for persistent, bioaccumulative and toxic (PBT) substances. REACH encourages the use of non-testing methods such as QSAR (quantitative structure-activity relationship) models in order to save money and time and to reduce the number of animals used for scientific purposes. Some QSAR models are available for predicting ready biodegradability. We used a dataset of 722 compounds to test four models: VEGA, TOPKAT, BIOWIN 5 and 6 and START and compared their performance on the basis of the following parameters: accuracy, sensitivity, specificity and Matthew's correlation coefficient (MCC). Performance was analyzed from different points of view. The first calculation was done on the whole dataset and VEGA and TOPKAT gave the best accuracy (88% and 87% respectively). Then we considered the compounds inside and outside the training set: BIOWIN 6 and 5 gave the best results for accuracy (81%) outside training set. Another analysis examined the applicability domain (AD). VEGA had the highest value for compounds inside the AD for all the parameters taken into account. Finally, compounds outside the training set and in the AD of the models were considered to assess predictive ability. VEGA gave the best accuracy results (99%) for this group of chemicals. Generally, START model gave poor results. Since BIOWIN, TOPKAT and VEGA models performed well, they may be used to predict ready biodegradability. Copyright © 2013 Elsevier B.V. All rights reserved.

Comparison of Marker-Based Genomic Estimated Breeding Values and Phenotypic Evaluation for Selection of Bacterial Spot Resistance in Tomato.

PubMed

Liabeuf, Debora; Sim, Sung-Chur; Francis, David M

2018-03-01

Bacterial spot affects tomato crops (Solanum lycopersicum) grown under humid conditions. Major genes and quantitative trait loci (QTL) for resistance have been described, and multiple loci from diverse sources need to be combined to improve disease control. We investigated genomic selection (GS) prediction models for resistance to Xanthomonas euvesicatoria and experimentally evaluated the accuracy of these models. The training population consisted of 109 families combining resistance from four sources and directionally selected from a population of 1,100 individuals. The families were evaluated on a plot basis in replicated inoculated trials and genotyped with single nucleotide polymorphisms (SNP). We compared the prediction ability of models developed with 14 to 387 SNP. Genomic estimated breeding values (GEBV) were derived using Bayesian least absolute shrinkage and selection operator regression (BL) and ridge regression (RR). Evaluations were based on leave-one-out cross validation and on empirical observations in replicated field trials using the next generation of inbred progeny and a hybrid population resulting from selections in the training population. Prediction ability was evaluated based on correlations between GEBV and phenotypes (r g ), percentage of coselection between genomic and phenotypic selection, and relative efficiency of selection (r g /r p ). Results were similar with BL and RR models. Models using only markers previously identified as significantly associated with resistance but weighted based on GEBV and mixed models with markers associated with resistance treated as fixed effects and markers distributed in the genome treated as random effects offered greater accuracy and a high percentage of coselection. The accuracy of these models to predict the performance of progeny and hybrids exceeded the accuracy of phenotypic selection.

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity

NASA Astrophysics Data System (ADS)

Huang, Bing; von Lilienfeld, O. Anatole

2016-10-01

The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation. Inspired by the postulates of quantum mechanics, we introduce a hierarchy of representations which meet uniqueness and target similarity criteria. To systematically control target similarity, we simply rely on interatomic many body expansions, as implemented in universal force-fields, including Bonding, Angular (BA), and higher order terms. Addition of higher order contributions systematically increases similarity to the true potential energy and predictive accuracy of the resulting ML models. We report numerical evidence for the performance of BAML models trained on molecular properties pre-calculated at electron-correlated and density functional theory level of theory for thousands of small organic molecules. Properties studied include enthalpies and free energies of atomization, heat capacity, zero-point vibrational energies, dipole-moment, polarizability, HOMO/LUMO energies and gap, ionization potential, electron affinity, and electronic excitations. After training, BAML predicts energies or electronic properties of out-of-sample molecules with unprecedented accuracy and speed.

A generic approach for the development of short-term predictions of Escherichia coli and biotoxins in shellfish

PubMed Central

Schmidt, Wiebke; Evers-King, Hayley L.; Campos, Carlos J. A.; Jones, Darren B.; Miller, Peter I.; Davidson, Keith; Shutler, Jamie D.

2018-01-01

Microbiological contamination or elevated marine biotoxin concentrations within shellfish can result in temporary closure of shellfish aquaculture harvesting, leading to financial loss for the aquaculture business and a potential reduction in consumer confidence in shellfish products. We present a method for predicting short-term variations in shellfish concentrations of Escherichia coli and biotoxin (okadaic acid and its derivates dinophysistoxins and pectenotoxins). The approach was evaluated for 2 contrasting shellfish harvesting areas. Through a meta-data analysis and using environmental data (in situ, satellite observations and meteorological nowcasts and forecasts), key environmental drivers were identified and used to develop models to predict E. coli and biotoxin concentrations within shellfish. Models were trained and evaluated using independent datasets, and the best models were identified based on the model exhibiting the lowest root mean square error. The best biotoxin model was able to provide 1 wk forecasts with an accuracy of 86%, a 0% false positive rate and a 0% false discovery rate (n = 78 observations) when used to predict the closure of shellfish beds due to biotoxin. The best E. coli models were used to predict the European hygiene classification of the shellfish beds to an accuracy of 99% (n = 107 observations) and 98% (n = 63 observations) for a bay (St Austell Bay) and an estuary (Turnaware Bar), respectively. This generic approach enables high accuracy short-term farm-specific forecasts, based on readily accessible environmental data and observations. PMID:29805719

Comparative Analysis of Hybrid Models for Prediction of BP Reactivity to Crossed Legs.

PubMed

Kaur, Gurmanik; Arora, Ajat Shatru; Jain, Vijender Kumar

2017-01-01

Crossing the legs at the knees, during BP measurement, is one of the several physiological stimuli that considerably influence the accuracy of BP measurements. Therefore, it is paramount to develop an appropriate prediction model for interpreting influence of crossed legs on BP. This research work described the use of principal component analysis- (PCA-) fused forward stepwise regression (FSWR), artificial neural network (ANN), adaptive neuro fuzzy inference system (ANFIS), and least squares support vector machine (LS-SVM) models for prediction of BP reactivity to crossed legs among the normotensive and hypertensive participants. The evaluation of the performance of the proposed prediction models using appropriate statistical indices showed that the PCA-based LS-SVM (PCA-LS-SVM) model has the highest prediction accuracy with coefficient of determination ( R 2 ) = 93.16%, root mean square error (RMSE) = 0.27, and mean absolute percentage error (MAPE) = 5.71 for SBP prediction in normotensive subjects. Furthermore, R 2  = 96.46%, RMSE = 0.19, and MAPE = 1.76 for SBP prediction and R 2  = 95.44%, RMSE = 0.21, and MAPE = 2.78 for DBP prediction in hypertensive subjects using the PCA-LSSVM model. This assessment presents the importance and advantages posed by hybrid computing models for the prediction of variables in biomedical research studies.

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China

PubMed Central

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-01-01

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%–19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides. PMID:27187430

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China.

PubMed

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-05-11

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%-19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides.

Population variation in isotopic composition of shorebird feathers: Implications for determining molting grounds

USGS Publications Warehouse

Torres-Dowdall, J.; Farmer, A.H.; Bucher, E.H.; Rye, R.O.; Landis, G.

2009-01-01

Stable isotope analyses have revolutionized the study of migratory connectivity. However, as with all tools, their limitations must be understood in order to derive the maximum benefit of a particular application. The goal of this study was to evaluate the efficacy of stable isotopes of C, N, H, O and S for assigning known-origin feathers to the molting sites of migrant shorebird species wintering and breeding in Argentina. Specific objectives were to: 1) compare the efficacy of the technique for studying shorebird species with different migration patterns, life histories and habitat-use patterns; 2) evaluate the grouping of species with similar migration and habitat use patterns in a single analysis to potentially improve prediction accuracy; and 3) evaluate the potential gains in prediction accuracy that might be achieved from using multiple stable isotopes. The efficacy of stable isotope ratios to determine origin was found to vary with species. While one species (White-rumped Sandpiper, Calidris fuscicollis) had high levels of accuracy assigning samples to known origin (91% of samples correctly assigned), another (Collared Plover, Charadrius collaris) showed low levels of accuracy (52% of samples correctly assigned). Intra-individual variability may account for this difference in efficacy. The prediction model for three species with similar migration and habitat-use patterns performed poorly compared with the model for just one of the species (71% versus 91% of samples correctly assigned). Thus, combining multiple sympatric species may not improve model prediction accuracy. Increasing the number of stable isotopes in the analyses increased the accuracy of assigning shorebirds to their molting origin, but the best combination - involving a subset of all the isotopes analyzed - varied among species.

Structural reliability analysis under evidence theory using the active learning kriging model

NASA Astrophysics Data System (ADS)

Yang, Xufeng; Liu, Yongshou; Ma, Panke

2017-11-01

Structural reliability analysis under evidence theory is investigated. It is rigorously proved that a surrogate model providing only correct sign prediction of the performance function can meet the accuracy requirement of evidence-theory-based reliability analysis. Accordingly, a method based on the active learning kriging model which only correctly predicts the sign of the performance function is proposed. Interval Monte Carlo simulation and a modified optimization method based on Karush-Kuhn-Tucker conditions are introduced to make the method more efficient in estimating the bounds of failure probability based on the kriging model. Four examples are investigated to demonstrate the efficiency and accuracy of the proposed method.

Predictive model for survival in patients with gastric cancer.

PubMed

Goshayeshi, Ladan; Hoseini, Benyamin; Yousefli, Zahra; Khooie, Alireza; Etminani, Kobra; Esmaeilzadeh, Abbas; Golabpour, Amin

2017-12-01

Gastric cancer is one of the most prevalent cancers in the world. Characterized by poor prognosis, it is a frequent cause of cancer in Iran. The aim of the study was to design a predictive model of survival time for patients suffering from gastric cancer. This was a historical cohort conducted between 2011 and 2016. Study population were 277 patients suffering from gastric cancer. Data were gathered from the Iranian Cancer Registry and the laboratory of Emam Reza Hospital in Mashhad, Iran. Patients or their relatives underwent interviews where it was needed. Missing values were imputed by data mining techniques. Fifteen factors were analyzed. Survival was addressed as a dependent variable. Then, the predictive model was designed by combining both genetic algorithm and logistic regression. Matlab 2014 software was used to combine them. Of the 277 patients, only survival of 80 patients was available whose data were used for designing the predictive model. Mean ?SD of missing values for each patient was 4.43?.41 combined predictive model achieved 72.57% accuracy. Sex, birth year, age at diagnosis time, age at diagnosis time of patients' family, family history of gastric cancer, and family history of other gastrointestinal cancers were six parameters associated with patient survival. The study revealed that imputing missing values by data mining techniques have a good accuracy. And it also revealed six parameters extracted by genetic algorithm effect on the survival of patients with gastric cancer. Our combined predictive model, with a good accuracy, is appropriate to forecast the survival of patients suffering from Gastric cancer. So, we suggest policy makers and specialists to apply it for prediction of patients' survival.

Prediction of clinical behaviour and treatment for cancers.

PubMed

Futschik, Matthias E; Sullivan, Mike; Reeve, Anthony; Kasabov, Nikola

2003-01-01

Prediction of clinical behaviour and treatment for cancers is based on the integration of clinical and pathological parameters. Recent reports have demonstrated that gene expression profiling provides a powerful new approach for determining disease outcome. If clinical and microarray data each contain independent information then it should be possible to combine these datasets to gain more accurate prognostic information. Here, we have used existing clinical information and microarray data to generate a combined prognostic model for outcome prediction for diffuse large B-cell lymphoma (DLBCL). A prediction accuracy of 87.5% was achieved. This constitutes a significant improvement compared to the previously most accurate prognostic model with an accuracy of 77.6%. The model introduced here may be generally applicable to the combination of various types of molecular and clinical data for improving medical decision support systems and individualising patient care.

Prediction of brittleness based on anisotropic rock physics model for kerogen-rich shale

NASA Astrophysics Data System (ADS)

Qian, Ke-Ran; He, Zhi-Liang; Chen, Ye-Quan; Liu, Xi-Wu; Li, Xiang-Yang

2017-12-01

The construction of a shale rock physics model and the selection of an appropriate brittleness index ( BI) are two significant steps that can influence the accuracy of brittleness prediction. On one hand, the existing models of kerogen-rich shale are controversial, so a reasonable rock physics model needs to be built. On the other hand, several types of equations already exist for predicting the BI whose feasibility needs to be carefully considered. This study constructed a kerogen-rich rock physics model by performing the selfconsistent approximation and the differential effective medium theory to model intercoupled clay and kerogen mixtures. The feasibility of our model was confirmed by comparison with classical models, showing better accuracy. Templates were constructed based on our model to link physical properties and the BI. Different equations for the BI had different sensitivities, making them suitable for different types of formations. Equations based on Young's Modulus were sensitive to variations in lithology, while those using Lame's Coefficients were sensitive to porosity and pore fluids. Physical information must be considered to improve brittleness prediction.

Analysis of the Mean Absolute Error (MAE) and the Root Mean Square Error (RMSE) in Assessing Rounding Model

NASA Astrophysics Data System (ADS)

Wang, Weijie; Lu, Yanmin

2018-03-01

Most existing Collaborative Filtering (CF) algorithms predict a rating as the preference of an active user toward a given item, which is always a decimal fraction. Meanwhile, the actual ratings in most data sets are integers. In this paper, we discuss and demonstrate why rounding can bring different influences to these two metrics; prove that rounding is necessary in post-processing of the predicted ratings, eliminate of model prediction bias, improving the accuracy of the prediction. In addition, we also propose two new rounding approaches based on the predicted rating probability distribution, which can be used to round the predicted rating to an optimal integer rating, and get better prediction accuracy compared to the Basic Rounding approach. Extensive experiments on different data sets validate the correctness of our analysis and the effectiveness of our proposed rounding approaches.

Rapid high performance liquid chromatography method development with high prediction accuracy, using 5cm long narrow bore columns packed with sub-2microm particles and Design Space computer modeling.

PubMed

Fekete, Szabolcs; Fekete, Jeno; Molnár, Imre; Ganzler, Katalin

2009-11-06

Many different strategies of reversed phase high performance liquid chromatographic (RP-HPLC) method development are used today. This paper describes a strategy for the systematic development of ultrahigh-pressure liquid chromatographic (UHPLC or UPLC) methods using 5cmx2.1mm columns packed with sub-2microm particles and computer simulation (DryLab((R)) package). Data for the accuracy of computer modeling in the Design Space under ultrahigh-pressure conditions are reported. An acceptable accuracy for these predictions of the computer models is presented. This work illustrates a method development strategy, focusing on time reduction up to a factor 3-5, compared to the conventional HPLC method development and exhibits parts of the Design Space elaboration as requested by the FDA and ICH Q8R1. Furthermore this paper demonstrates the accuracy of retention time prediction at elevated pressure (enhanced flow-rate) and shows that the computer-assisted simulation can be applied with sufficient precision for UHPLC applications (p>400bar). Examples of fast and effective method development in pharmaceutical analysis, both for gradient and isocratic separations are presented.

In Search of Black Swans: Identifying Students at Risk of Failing Licensing Examinations.

PubMed

Barber, Cassandra; Hammond, Robert; Gula, Lorne; Tithecott, Gary; Chahine, Saad

2018-03-01

To determine which admissions variables and curricular outcomes are predictive of being at risk of failing the Medical Council of Canada Qualifying Examination Part 1 (MCCQE1), how quickly student risk of failure can be predicted, and to what extent predictive modeling is possible and accurate in estimating future student risk. Data from five graduating cohorts (2011-2015), Schulich School of Medicine & Dentistry, Western University, were collected and analyzed using hierarchical generalized linear models (HGLMs). Area under the receiver operating characteristic curve (AUC) was used to evaluate the accuracy of predictive models and determine whether they could be used to predict future risk, using the 2016 graduating cohort. Four predictive models were developed to predict student risk of failure at admissions, year 1, year 2, and pre-MCCQE1. The HGLM analyses identified gender, MCAT verbal reasoning score, two preclerkship course mean grades, and the year 4 summative objective structured clinical examination score as significant predictors of student risk. The predictive accuracy of the models varied. The pre-MCCQE1 model was the most accurate at predicting a student's risk of failing (AUC 0.66-0.93), while the admissions model was not predictive (AUC 0.25-0.47). Key variables predictive of students at risk were found. The predictive models developed suggest, while it is not possible to identify student risk at admission, we can begin to identify and monitor students within the first year. Using such models, programs may be able to identify and monitor students at risk quantitatively and develop tailored intervention strategies.

Predicting outcome of Morris water maze test in vascular dementia mouse model with deep learning

PubMed Central

Mogi, Masaki; Iwanami, Jun; Min, Li-Juan; Bai, Hui-Yu; Shan, Bao-Shuai; Kukida, Masayoshi; Kan-no, Harumi; Ikeda, Shuntaro; Higaki, Jitsuo; Horiuchi, Masatsugu

2018-01-01

The Morris water maze test (MWM) is one of the most popular and established behavioral tests to evaluate rodents’ spatial learning ability. The conventional training period is around 5 days, but there is no clear evidence or guidelines about the appropriate duration. In many cases, the final outcome of the MWM seems predicable from previous data and their trend. So, we assumed that if we can predict the final result with high accuracy, the experimental period could be shortened and the burden on testers reduced. An artificial neural network (ANN) is a useful modeling method for datasets that enables us to obtain an accurate mathematical model. Therefore, we constructed an ANN system to estimate the final outcome in MWM from the previously obtained 4 days of data in both normal mice and vascular dementia model mice. Ten-week-old male C57B1/6 mice (wild type, WT) were subjected to bilateral common carotid artery stenosis (WT-BCAS) or sham-operation (WT-sham). At 6 weeks after surgery, we evaluated their cognitive function with MWM. Mean escape latency was significantly longer in WT-BCAS than in WT-sham. All data were collected and used as training data and test data for the ANN system. We defined a multiple layer perceptron (MLP) as a prediction model using an open source framework for deep learning, Chainer. After a certain number of updates, we compared the predicted values and actual measured values with test data. A significant correlation coefficient was derived form the updated ANN model in both WT-sham and WT-BCAS. Next, we analyzed the predictive capability of human testers with the same datasets. There was no significant difference in the prediction accuracy between human testers and ANN models in both WT-sham and WT-BCAS. In conclusion, deep learning method with ANN could predict the final outcome in MWM from 4 days of data with high predictive accuracy in a vascular dementia model. PMID:29415035

Predicting outcome of Morris water maze test in vascular dementia mouse model with deep learning.

PubMed

Higaki, Akinori; Mogi, Masaki; Iwanami, Jun; Min, Li-Juan; Bai, Hui-Yu; Shan, Bao-Shuai; Kukida, Masayoshi; Kan-No, Harumi; Ikeda, Shuntaro; Higaki, Jitsuo; Horiuchi, Masatsugu

2018-01-01

The Morris water maze test (MWM) is one of the most popular and established behavioral tests to evaluate rodents' spatial learning ability. The conventional training period is around 5 days, but there is no clear evidence or guidelines about the appropriate duration. In many cases, the final outcome of the MWM seems predicable from previous data and their trend. So, we assumed that if we can predict the final result with high accuracy, the experimental period could be shortened and the burden on testers reduced. An artificial neural network (ANN) is a useful modeling method for datasets that enables us to obtain an accurate mathematical model. Therefore, we constructed an ANN system to estimate the final outcome in MWM from the previously obtained 4 days of data in both normal mice and vascular dementia model mice. Ten-week-old male C57B1/6 mice (wild type, WT) were subjected to bilateral common carotid artery stenosis (WT-BCAS) or sham-operation (WT-sham). At 6 weeks after surgery, we evaluated their cognitive function with MWM. Mean escape latency was significantly longer in WT-BCAS than in WT-sham. All data were collected and used as training data and test data for the ANN system. We defined a multiple layer perceptron (MLP) as a prediction model using an open source framework for deep learning, Chainer. After a certain number of updates, we compared the predicted values and actual measured values with test data. A significant correlation coefficient was derived form the updated ANN model in both WT-sham and WT-BCAS. Next, we analyzed the predictive capability of human testers with the same datasets. There was no significant difference in the prediction accuracy between human testers and ANN models in both WT-sham and WT-BCAS. In conclusion, deep learning method with ANN could predict the final outcome in MWM from 4 days of data with high predictive accuracy in a vascular dementia model.

Practical approach to subject-specific estimation of knee joint contact force

PubMed Central

Knarr, Brian A.; Higginson, Jill S.

2015-01-01

Compressive forces experienced at the knee can significantly contribute to cartilage degeneration. Musculoskeletal models enable predictions of the internal forces experienced at the knee, but validation is often not possible, as experimental data detailing loading at the knee joint is limited. Recently available data reporting compressive knee force through direct measurement using instrumented total knee replacements offer a unique opportunity to evaluate the accuracy of models. Previous studies have highlighted the importance of subject-specificity in increasing the accuracy of model predictions; however, these techniques may be unrealistic outside of a research setting. Therefore, the goal of our work was to identify a practical approach for accurate prediction of tibiofemoral knee contact force (KCF). Four methods for prediction of knee contact force were compared: (1) standard static optimization, (2) uniform muscle coordination weighting, (3) subject-specific muscle coordination weighting and (4) subject-specific strength adjustments. Walking trials for three subjects with instrumented knee replacements were used to evaluate the accuracy of model predictions. Predictions utilizing subject-specific muscle coordination weighting yielded the best agreement with experimental data, however this method required in vivo data for weighting factor calibration. Including subject-specific strength adjustments improved models’ predictions compared to standard static optimization, with errors in peak KCF less than 0.5 body weight for all subjects. Overall, combining clinical assessments of muscle strength with standard tools available in the OpenSim software package, such as inverse kinematics and static optimization, appears to be a practical method for predicting joint contact force that can be implemented for many applications. PMID:25952546

ZY3-02 Laser Altimeter Footprint Geolocation Prediction

PubMed Central

Xie, Junfeng; Tang, Xinming; Mo, Fan; Li, Guoyuan; Zhu, Guangbin; Wang, Zhenming; Fu, Xingke; Gao, Xiaoming; Dou, Xianhui

2017-01-01

Successfully launched on 30 May 2016, ZY3-02 is the first Chinese surveying and mapping satellite equipped with a lightweight laser altimeter. Calibration is necessary before the laser altimeter becomes operational. Laser footprint location prediction is the first step in calibration that is based on ground infrared detectors, and it is difficult because the sample frequency of the ZY3-02 laser altimeter is 2 Hz, and the distance between two adjacent laser footprints is about 3.5 km. In this paper, we build an on-orbit rigorous geometric prediction model referenced to the rigorous geometric model of optical remote sensing satellites. The model includes three kinds of data that must be predicted: pointing angle, orbit parameters, and attitude angles. The proposed method is verified by a ZY3-02 laser altimeter on-orbit geometric calibration test. Five laser footprint prediction experiments are conducted based on the model, and the laser footprint prediction accuracy is better than 150 m on the ground. The effectiveness and accuracy of the on-orbit rigorous geometric prediction model are confirmed by the test results. The geolocation is predicted precisely by the proposed method, and this will give a reference to the geolocation prediction of future land laser detectors in other laser altimeter calibration test. PMID:28934160

ZY3-02 Laser Altimeter Footprint Geolocation Prediction.

PubMed

Xie, Junfeng; Tang, Xinming; Mo, Fan; Li, Guoyuan; Zhu, Guangbin; Wang, Zhenming; Fu, Xingke; Gao, Xiaoming; Dou, Xianhui

2017-09-21

Successfully launched on 30 May 2016, ZY3-02 is the first Chinese surveying and mapping satellite equipped with a lightweight laser altimeter. Calibration is necessary before the laser altimeter becomes operational. Laser footprint location prediction is the first step in calibration that is based on ground infrared detectors, and it is difficult because the sample frequency of the ZY3-02 laser altimeter is 2 Hz, and the distance between two adjacent laser footprints is about 3.5 km. In this paper, we build an on-orbit rigorous geometric prediction model referenced to the rigorous geometric model of optical remote sensing satellites. The model includes three kinds of data that must be predicted: pointing angle, orbit parameters, and attitude angles. The proposed method is verified by a ZY3-02 laser altimeter on-orbit geometric calibration test. Five laser footprint prediction experiments are conducted based on the model, and the laser footprint prediction accuracy is better than 150 m on the ground. The effectiveness and accuracy of the on-orbit rigorous geometric prediction model are confirmed by the test results. The geolocation is predicted precisely by the proposed method, and this will give a reference to the geolocation prediction of future land laser detectors in other laser altimeter calibration test.

Simultaneous Co-Clustering and Classification in Customers Insight

NASA Astrophysics Data System (ADS)

Anggistia, M.; Saefuddin, A.; Sartono, B.

2017-04-01

Building predictive model based on the heterogeneous dataset may yield many problems, such as less precise in parameter and prediction accuracy. Such problem can be solved by segmenting the data into relatively homogeneous groups and then build a predictive model for each cluster. The advantage of using this strategy usually gives result in simpler models, more interpretable, and more actionable without any loss in accuracy and reliability. This work concerns on marketing data set which recorded a customer behaviour across products. There are some variables describing customer and product as attributes. The basic idea of this approach is to combine co-clustering and classification simultaneously. The objective of this research is to analyse the customer across product characteristics, so the marketing strategy implemented precisely.

SITE CHARACTERIZATION TO SUPPORT MODEL DEVELOPMENT FOR CONTAMINANTS IN GROUND WATER

EPA Science Inventory

The development of conceptual and predictive models is an important tool to guide site characterization in support of monitoring contaminants in ground water. The accuracy of predictive models is limited by the adequacy of the input data and the assumptions made to constrain mod...

AGDRIFT: A MODEL FOR ESTIMATING NEAR-FIELD SPRAY DRIFT FROM AERIAL APPLICATIONS

EPA Science Inventory

The aerial spray prediction model AgDRIFT(R) embodies the computational engine found in the near-wake Lagrangian model AGricultural DISPersal (AGDISP) but with several important features added that improve the speed and accuracy of its predictions. This article summarizes those c...

Effects of model complexity and priors on estimation using sequential importance sampling/resampling for species conservation

USGS Publications Warehouse

Dunham, Kylee; Grand, James B.

2016-01-01

We examined the effects of complexity and priors on the accuracy of models used to estimate ecological and observational processes, and to make predictions regarding population size and structure. State-space models are useful for estimating complex, unobservable population processes and making predictions about future populations based on limited data. To better understand the utility of state space models in evaluating population dynamics, we used them in a Bayesian framework and compared the accuracy of models with differing complexity, with and without informative priors using sequential importance sampling/resampling (SISR). Count data were simulated for 25 years using known parameters and observation process for each model. We used kernel smoothing to reduce the effect of particle depletion, which is common when estimating both states and parameters with SISR. Models using informative priors estimated parameter values and population size with greater accuracy than their non-informative counterparts. While the estimates of population size and trend did not suffer greatly in models using non-informative priors, the algorithm was unable to accurately estimate demographic parameters. This model framework provides reasonable estimates of population size when little to no information is available; however, when information on some vital rates is available, SISR can be used to obtain more precise estimates of population size and process. Incorporating model complexity such as that required by structured populations with stage-specific vital rates affects precision and accuracy when estimating latent population variables and predicting population dynamics. These results are important to consider when designing monitoring programs and conservation efforts requiring management of specific population segments.

Ecological niche modelling of bank voles in Western Europe.

PubMed

Amirpour Haredasht, Sara; Barrios, Miguel; Farifteh, Jamshid; Maes, Piet; Clement, Jan; Verstraeten, Willem W; Tersago, Katrien; Van Ranst, Marc; Coppin, Pol; Berckmans, Daniel; Aerts, Jean-Marie

2013-01-28

The bank vole (Myodes glareolus) is the natural host of Puumala virus (PUUV) in vast areas of Europe. PUUV is one of the hantaviruses which are transmitted to humans by infected rodents. PUUV causes a general mild form of hemorrhagic fever with renal syndrome (HFRS) called nephropathia epidemica (NE). Vector-borne and zoonotic diseases generally display clear spatial patterns due to different space-dependent factors. Land cover influences disease transmission by controlling both the spatial distribution of vectors or hosts, as well as by facilitating the human contact with them. In this study the use of ecological niche modelling (ENM) for predicting the geographical distribution of bank vole population on the basis of spatial climate information is tested. The Genetic Algorithm for Rule-set Prediction (GARP) is used to model the ecological niche of bank voles in Western Europe. The meteorological data, land cover types and geo-referenced points representing the locations of the bank voles (latitude/longitude) in the study area are used as the primary model input value. The predictive accuracy of the bank vole ecologic niche model was significant (training accuracy of 86%). The output of the GARP models based on the 50% subsets of points used for testing the model showed an accuracy of 75%. Compared with random models, the probability of such high predictivity was low (χ(2) tests, p < 10(-6)). As such, the GARP models were predictive and the used ecologic niche model indeed indicates the ecologic requirements of bank voles. This approach successfully identified the areas of infection risk across the study area. The result suggests that the niche modelling approach can be implemented in a next step towards the development of new tools for monitoring the bank vole's population.

Ecological Niche Modelling of Bank Voles in Western Europe

PubMed Central

Amirpour Haredasht, Sara; Barrios, Miguel; Farifteh, Jamshid; Maes, Piet; Clement, Jan; Verstraeten, Willem W.; Tersago, Katrien; Van Ranst, Marc; Coppin, Pol; Berckmans, Daniel; Aerts, Jean-Marie

2013-01-01

The bank vole (Myodes glareolus) is the natural host of Puumala virus (PUUV) in vast areas of Europe. PUUV is one of the hantaviruses which are transmitted to humans by infected rodents. PUUV causes a general mild form of hemorrhagic fever with renal syndrome (HFRS) called nephropathia epidemica (NE). Vector-borne and zoonotic diseases generally display clear spatial patterns due to different space-dependent factors. Land cover influences disease transmission by controlling both the spatial distribution of vectors or hosts, as well as by facilitating the human contact with them. In this study the use of ecological niche modelling (ENM) for predicting the geographical distribution of bank vole population on the basis of spatial climate information is tested. The Genetic Algorithm for Rule-set Prediction (GARP) is used to model the ecological niche of bank voles in Western Europe. The meteorological data, land cover types and geo-referenced points representing the locations of the bank voles (latitude/longitude) in the study area are used as the primary model input value. The predictive accuracy of the bank vole ecologic niche model was significant (training accuracy of 86%). The output of the GARP models based on the 50% subsets of points used for testing the model showed an accuracy of 75%. Compared with random models, the probability of such high predictivity was low (χ2 tests, p < 10−6). As such, the GARP models were predictive and the used ecologic niche model indeed indicates the ecologic requirements of bank voles. This approach successfully identified the areas of infection risk across the study area. The result suggests that the niche modelling approach can be implemented in a next step towards the development of new tools for monitoring the bank vole’s population. PMID:23358234

Accuracy and biases in newlyweds' perceptions of each other: not mutually exclusive but mutually beneficial.

PubMed

Luo, Shanhong; Snider, Anthony G

2009-11-01

There has been a long-standing debate about whether having accurate self-perceptions or holding positive illusions of self is more adaptive. This debate has recently expanded to consider the role of accuracy and bias of partner perceptions in romantic relationships. In the present study, we hypothesized that because accuracy, positivity bias, and similarity bias are likely to serve distinct functions in relationships, they should all make independent contributions to the prediction of marital satisfaction. In a sample of 288 newlywed couples, we tested this hypothesis by simultaneously modeling the actor effects and partner effects of accuracy, positivity bias, and similarity bias in predicting husbands' and wives' satisfaction. Findings across several perceptual domains suggest that all three perceptual indices independently predicted the perceiver's satisfaction. Accuracy and similarity bias, but not positivity bias, made unique contributions to the target's satisfaction. No sex differences were found.

Quantifying and estimating the predictive accuracy for censored time-to-event data with competing risks.

PubMed

Wu, Cai; Li, Liang

2018-05-15

This paper focuses on quantifying and estimating the predictive accuracy of prognostic models for time-to-event outcomes with competing events. We consider the time-dependent discrimination and calibration metrics, including the receiver operating characteristics curve and the Brier score, in the context of competing risks. To address censoring, we propose a unified nonparametric estimation framework for both discrimination and calibration measures, by weighting the censored subjects with the conditional probability of the event of interest given the observed data. The proposed method can be extended to time-dependent predictive accuracy metrics constructed from a general class of loss functions. We apply the methodology to a data set from the African American Study of Kidney Disease and Hypertension to evaluate the predictive accuracy of a prognostic risk score in predicting end-stage renal disease, accounting for the competing risk of pre-end-stage renal disease death, and evaluate its numerical performance in extensive simulation studies. Copyright © 2018 John Wiley & Sons, Ltd.

How long will my mouse live? Machine learning approaches for prediction of mouse life span.

PubMed

Swindell, William R; Harper, James M; Miller, Richard A

2008-09-01

Prediction of individual life span based on characteristics evaluated at middle-age represents a challenging objective for aging research. In this study, we used machine learning algorithms to construct models that predict life span in a stock of genetically heterogeneous mice. Life-span prediction accuracy of 22 algorithms was evaluated using a cross-validation approach, in which models were trained and tested with distinct subsets of data. Using a combination of body weight and T-cell subset measures evaluated before 2 years of age, we show that the life-span quartile to which an individual mouse belongs can be predicted with an accuracy of 35.3% (+/-0.10%). This result provides a new benchmark for the development of life-span-predictive models, but improvement can be expected through identification of new predictor variables and development of computational approaches. Future work in this direction can provide tools for aging research and will shed light on associations between phenotypic traits and longevity.

RaptorX-Property: a web server for protein structure property prediction.

PubMed

Wang, Sheng; Li, Wei; Liu, Shiwang; Xu, Jinbo

2016-07-08

RaptorX Property (http://raptorx2.uchicago.edu/StructurePropertyPred/predict/) is a web server predicting structure property of a protein sequence without using any templates. It outperforms other servers, especially for proteins without close homologs in PDB or with very sparse sequence profile (i.e. carries little evolutionary information). This server employs a powerful in-house deep learning model DeepCNF (Deep Convolutional Neural Fields) to predict secondary structure (SS), solvent accessibility (ACC) and disorder regions (DISO). DeepCNF not only models complex sequence-structure relationship by a deep hierarchical architecture, but also interdependency between adjacent property labels. Our experimental results show that, tested on CASP10, CASP11 and the other benchmarks, this server can obtain ∼84% Q3 accuracy for 3-state SS, ∼72% Q8 accuracy for 8-state SS, ∼66% Q3 accuracy for 3-state solvent accessibility, and ∼0.89 area under the ROC curve (AUC) for disorder prediction. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

Evaluation of Gravitational Field Models Based on the Laser Range Observation of Low Earth Orbit Satellites

NASA Astrophysics Data System (ADS)

Wang, H. B.; Zhao, C. Y.; Zhang, W.; Zhan, J. W.; Yu, S. X.

2015-09-01

The Earth gravitational filed model is a kind of important dynamic model in satellite orbit computation. In recent years, several space gravity missions have obtained great success, prompting a lot of gravitational filed models to be published. In this paper, 2 classical models (JGM3, EGM96) and 4 latest models, including EIGEN-CHAMP05S, GGM03S, GOCE02S, and EGM2008 are evaluated by being employed in the precision orbit determination (POD) and prediction, based on the laser range observation of four low earth orbit (LEO) satellites, including CHAMP, GFZ-1, GRACE-A, and SWARM-A. The residual error of observation in POD is adopted to describe the accuracy of six gravitational field models. We show the main results as follows: (1) for LEO POD, the accuracies of 4 latest models (EIGEN-CHAMP05S, GGM03S, GOCE02S, and EGM2008) are at the same level, and better than those of 2 classical models (JGM3, EGM96); (2) If taking JGM3 as reference, EGM96 model's accuracy is better in most situations, and the accuracies of the 4 latest models are improved by 12%-47% in POD and 63% in prediction, respectively. We also confirm that the model's accuracy in POD is enhanced with the increasing degree and order if they are smaller than 70, and when they exceed 70 the accuracy keeps stable, and is unrelated with the increasing degree, meaning that the model's degree and order truncated to 70 are sufficient to meet the requirement of LEO orbit computation with centimeter level precision.

Development of predictive mapping techniques for soil survey and salinity mapping

NASA Astrophysics Data System (ADS)

Elnaggar, Abdelhamid A.

Conventional soil maps represent a valuable source of information about soil characteristics, however they are subjective, very expensive, and time-consuming to prepare. Also, they do not include explicit information about the conceptual mental model used in developing them nor information about their accuracy, in addition to the error associated with them. Decision tree analysis (DTA) was successfully used in retrieving the expert knowledge embedded in old soil survey data. This knowledge was efficiently used in developing predictive soil maps for the study areas in Benton and Malheur Counties, Oregon and accessing their consistency. A retrieved soil-landscape model from a reference area in Harney County was extrapolated to develop a preliminary soil map for the neighboring unmapped part of Malheur County. The developed map had a low prediction accuracy and only a few soil map units (SMUs) were predicted with significant accuracy, mostly those shallow SMUs that have either a lithic contact with the bedrock or developed on a duripan. On the other hand, the developed soil map based on field data was predicted with very high accuracy (overall was about 97%). Salt-affected areas of the Malheur County study area are indicated by their high spectral reflectance and they are easily discriminated from the remote sensing data. However, remote sensing data fails to distinguish between the different classes of soil salinity. Using the DTA method, five classes of soil salinity were successfully predicted with an overall accuracy of about 99%. Moreover, the calculated area of salt-affected soil was overestimated when mapped using remote sensing data compared to that predicted by using DTA. Hence, DTA could be a very helpful approach in developing soil survey and soil salinity maps in more objective, effective, less-expensive and quicker ways based on field data.

Towards an Online Seizure Advisory System-An Adaptive Seizure Prediction Framework Using Active Learning Heuristics.

PubMed

Karuppiah Ramachandran, Vignesh Raja; Alblas, Huibert J; Le, Duc V; Meratnia, Nirvana

2018-05-24

In the last decade, seizure prediction systems have gained a lot of attention because of their enormous potential to largely improve the quality-of-life of the epileptic patients. The accuracy of the prediction algorithms to detect seizure in real-world applications is largely limited because the brain signals are inherently uncertain and affected by various factors, such as environment, age, drug intake, etc., in addition to the internal artefacts that occur during the process of recording the brain signals. To deal with such ambiguity, researchers transitionally use active learning, which selects the ambiguous data to be annotated by an expert and updates the classification model dynamically. However, selecting the particular data from a pool of large ambiguous datasets to be labelled by an expert is still a challenging problem. In this paper, we propose an active learning-based prediction framework that aims to improve the accuracy of the prediction with a minimum number of labelled data. The core technique of our framework is employing the Bernoulli-Gaussian Mixture model (BGMM) to determine the feature samples that have the most ambiguity to be annotated by an expert. By doing so, our approach facilitates expert intervention as well as increasing medical reliability. We evaluate seven different classifiers in terms of the classification time and memory required. An active learning framework built on top of the best performing classifier is evaluated in terms of required annotation effort to achieve a high level of prediction accuracy. The results show that our approach can achieve the same accuracy as a Support Vector Machine (SVM) classifier using only 20 % of the labelled data and also improve the prediction accuracy even under the noisy condition.

Estimation of genomic prediction accuracy from reference populations with varying degrees of relationship.

PubMed

Lee, S Hong; Clark, Sam; van der Werf, Julius H J

2017-01-01

Genomic prediction is emerging in a wide range of fields including animal and plant breeding, risk prediction in human precision medicine and forensic. It is desirable to establish a theoretical framework for genomic prediction accuracy when the reference data consists of information sources with varying degrees of relationship to the target individuals. A reference set can contain both close and distant relatives as well as 'unrelated' individuals from the wider population in the genomic prediction. The various sources of information were modeled as different populations with different effective population sizes (Ne). Both the effective number of chromosome segments (Me) and Ne are considered to be a function of the data used for prediction. We validate our theory with analyses of simulated as well as real data, and illustrate that the variation in genomic relationships with the target is a predictor of the information content of the reference set. With a similar amount of data available for each source, we show that close relatives can have a substantially larger effect on genomic prediction accuracy than lesser related individuals. We also illustrate that when prediction relies on closer relatives, there is less improvement in prediction accuracy with an increase in training data or marker panel density. We release software that can estimate the expected prediction accuracy and power when combining different reference sources with various degrees of relationship to the target, which is useful when planning genomic prediction (before or after collecting data) in animal, plant and human genetics.

Exploring the genetic architecture and improving genomic prediction accuracy for mastitis and milk production traits in dairy cattle by mapping variants to hepatic transcriptomic regions responsive to intra-mammary infection.

PubMed

Fang, Lingzhao; Sahana, Goutam; Ma, Peipei; Su, Guosheng; Yu, Ying; Zhang, Shengli; Lund, Mogens Sandø; Sørensen, Peter

2017-05-12

A better understanding of the genetic architecture of complex traits can contribute to improve genomic prediction. We hypothesized that genomic variants associated with mastitis and milk production traits in dairy cattle are enriched in hepatic transcriptomic regions that are responsive to intra-mammary infection (IMI). Genomic markers [e.g. single nucleotide polymorphisms (SNPs)] from those regions, if included, may improve the predictive ability of a genomic model. We applied a genomic feature best linear unbiased prediction model (GFBLUP) to implement the above strategy by considering the hepatic transcriptomic regions responsive to IMI as genomic features. GFBLUP, an extension of GBLUP, includes a separate genomic effect of SNPs within a genomic feature, and allows differential weighting of the individual marker relationships in the prediction equation. Since GFBLUP is computationally intensive, we investigated whether a SNP set test could be a computationally fast way to preselect predictive genomic features. The SNP set test assesses the association between a genomic feature and a trait based on single-SNP genome-wide association studies. We applied these two approaches to mastitis and milk production traits (milk, fat and protein yield) in Holstein (HOL, n = 5056) and Jersey (JER, n = 1231) cattle. We observed that a majority of genomic features were enriched in genomic variants that were associated with mastitis and milk production traits. Compared to GBLUP, the accuracy of genomic prediction with GFBLUP was marginally improved (3.2 to 3.9%) in within-breed prediction. The highest increase (164.4%) in prediction accuracy was observed in across-breed prediction. The significance of genomic features based on the SNP set test were correlated with changes in prediction accuracy of GFBLUP (P < 0.05). GFBLUP provides a framework for integrating multiple layers of biological knowledge to provide novel insights into the biological basis of complex traits, and to improve the accuracy of genomic prediction. The SNP set test might be used as a first-step to improve GFBLUP models. Approaches like GFBLUP and SNP set test will become increasingly useful, as the functional annotations of genomes keep accumulating for a range of species and traits.

[Spatial distribution prediction of surface soil Pb in a battery contaminated site].

PubMed

Liu, Geng; Niu, Jun-Jie; Zhang, Chao; Zhao, Xin; Guo, Guan-Lin

2014-12-01

In order to enhance the reliability of risk estimation and to improve the accuracy of pollution scope determination in a battery contaminated site with the soil characteristic pollutant Pb, four spatial interpolation models, including Combination Prediction Model (OK(LG) + TIN), kriging model (OK(BC)), Inverse Distance Weighting model (IDW), and Spline model were employed to compare their effects on the spatial distribution and pollution assessment of soil Pb. The results showed that Pb concentration varied significantly and the data was severely skewed. The variation coefficient of the site was higher in the local region. OK(LG) + TIN was found to be more accurate than the other three models in predicting the actual pollution situations of the contaminated site. The prediction accuracy of other models was lower, due to the effect of the principle of different models and datum feature. The interpolation results of OK(BC), IDW and Spline could not reflect the detailed characteristics of seriously contaminated areas, and were not suitable for mapping and spatial distribution prediction of soil Pb in this site. This study gives great contributions and provides useful references for defining the remediation boundary and making remediation decision of contaminated sites.

Prognostic models for renal cell carcinoma recurrence: external validation in a Japanese population.

PubMed

Utsumi, Takanobu; Ueda, Takeshi; Fukasawa, Satoshi; Komaru, Atsushi; Sazuka, Tomokazu; Kawamura, Koji; Imamoto, Takashi; Nihei, Naoki; Suzuki, Hiroyoshi; Ichikawa, Tomohiko

2011-09-01

The aim of the present study was to compare the accuracy of three prognostic models in predicting recurrence-free survival among Japanese patients who underwent nephrectomy for non-metastatic renal cell carcinoma (RCC). Patients originated from two centers: Chiba University Hospital (n = 152) and Chiba Cancer Center (n = 65). The following data were collected: age, sex, clinical presentation, Eastern Cooperative Oncology Group performance status, surgical technique, 1997 tumor-node-metastasis stage, clinical and pathological tumor size, histological subtype, disease recurrence, and progression. Three western models, including Yaycioglu's model, Cindolo's model and Kattan's nomogram, were used to predict recurrence-free survival. Predictive accuracy of these models were validated by using Harrell's concordance-index. Concordance-indexes were 0.795 and 0.745 for Kattan's nomogram, 0.700 and 0.634 for Yaycioglu's model, and 0.700 and 0.634 for Cindolo's model, respectively. Furthermore, the constructed calibration plots of Kattan's nomogram overestimated the predicted probability of recurrence-free survival after 5 years compared with the actual probability. Our findings suggest that despite working better than other predictive tools, Kattan's nomogram needs be used with caution when applied to Japanese patients who have undergone nephrectomy for non-metastatic RCC. © 2011 The Japanese Urological Association.

Decision curve analysis assessing the clinical benefit of NMP22 in the detection of bladder cancer: secondary analysis of a prospective trial.

PubMed

Barbieri, Christopher E; Cha, Eugene K; Chromecki, Thomas F; Dunning, Allison; Lotan, Yair; Svatek, Robert S; Scherr, Douglas S; Karakiewicz, Pierre I; Sun, Maxine; Mazumdar, Madhu; Shariat, Shahrokh F

2012-03-01

• To employ decision curve analysis to determine the impact of nuclear matrix protein 22 (NMP22) on clinical decision making in the detection of bladder cancer using data from a prospective trial. • The study included 1303 patients at risk for bladder cancer who underwent cystoscopy, urine cytology and measurement of urinary NMP22 levels. • We constructed several prediction models to estimate risk of bladder cancer. The base model was generated using patient characteristics (age, gender, race, smoking and haematuria); cytology and NMP22 were added to the base model to determine effects on predictive accuracy. • Clinical net benefit was calculated by summing the benefits and subtracting the harms and weighting these by the threshold probability at which a patient or clinician would opt for cystoscopy. • In all, 72 patients were found to have bladder cancer (5.5%). In univariate analyses, NMP22 was the strongest predictor of bladder cancer presence (predictive accuracy 71.3%), followed by age (67.5%) and cytology (64.3%). • In multivariable prediction models, NMP22 improved the predictive accuracy of the base model by 8.2% (area under the curve 70.2-78.4%) and of the base model plus cytology by 4.2% (area under the curve 75.9-80.1%). • Decision curve analysis revealed that adding NMP22 to other models increased clinical benefit, particularly at higher threshold probabilities. • NMP22 is a strong, independent predictor of bladder cancer. • Addition of NMP22 improves the accuracy of standard predictors by a statistically and clinically significant margin. • Decision curve analysis suggests that integration of NMP22 into clinical decision making helps avoid unnecessary cystoscopies, with minimal increased risk of missing a cancer. © 2011 THE AUTHORS. BJU INTERNATIONAL © 2011 BJU INTERNATIONAL.

Video image analysis in the Australian meat industry - precision and accuracy of predicting lean meat yield in lamb carcasses.

PubMed

Hopkins, D L; Safari, E; Thompson, J M; Smith, C R

2004-06-01

A wide selection of lamb types of mixed sex (ewes and wethers) were slaughtered at a commercial abattoir and during this process images of 360 carcasses were obtained online using the VIAScan® system developed by Meat and Livestock Australia. Soft tissue depth at the GR site (thickness of tissue over the 12th rib 110 mm from the midline) was measured by an abattoir employee using the AUS-MEAT sheep probe (PGR). Another measure of this thickness was taken in the chiller using a GR knife (NGR). Each carcass was subsequently broken down to a range of trimmed boneless retail cuts and the lean meat yield determined. The current industry model for predicting meat yield uses hot carcass weight (HCW) and tissue depth at the GR site. A low level of accuracy and precision was found when HCW and PGR were used to predict lean meat yield (R(2)=0.19, r.s.d.=2.80%), which could be improved markedly when PGR was replaced by NGR (R(2)=0.41, r.s.d.=2.39%). If the GR measures were replaced by 8 VIAScan® measures then greater prediction accuracy could be achieved (R(2)=0.52, r.s.d.=2.17%). A similar result was achieved when the model was based on principal components (PCs) computed from the 8 VIAScan® measures (R(2)=0.52, r.s.d.=2.17%). The use of PCs also improved the stability of the model compared to a regression model based on HCW and NGR. The transportability of the models was tested by randomly dividing the data set and comparing coefficients and the level of accuracy and precision. Those models based on PCs were superior to those based on regression. It is demonstrated that with the appropriate modeling the VIAScan® system offers a workable method for predicting lean meat yield automatically.

SITE CHARACTERIZATION TO SUPPORT DEVELOPMENT OF CONCEPTUAL SITE MODELS AND TRANSPORT MODELS FOR MONITORING CONTAMINANTS IN GROUND WATER

EPA Science Inventory

The development of conceptual and predictive models is an important tool to guide site characterization in support of monitoring contaminants in ground water. The accuracy of predictive models is limited by the adequacy of the input data and the assumptions made to constrain mod...

Testing DRAINMOD-FOREST for predicting evapotranspiration in a mid-rotation pine plantation

Treesearch

Shiying Tian; Mohamed A. Youssef; Ge Sun; George M. Chescheir; Asko Noormets; Devendra M. Amatya; R. Wayne Skaggs; John S. King; Steve McNulty; Michael Gavazzi; Guofang Miao; Jean-Christophe Domec

2015-01-01

Evapotranspiration (ET) is a key component of the hydrologic cycle in terrestrial ecosystems and accurate description of ET processes is essential for developing reliable ecohydrological models. This study investigated the accuracy of ET prediction by the DRAINMOD-FOREST after its calibration/validation for predicting commonly measured hydrological variables. The model...

Ensemble modeling to predict habitat suitability for a large-scale disturbance specialist

Treesearch

Quresh S. Latif; Victoria A. Saab; Jonathan G. Dudley; Jeff P. Hollenbeck

2013-01-01

To conserve habitat for disturbance specialist species, ecologists must identify where individuals will likely settle in newly disturbed areas. Habitat suitability models can predict which sites at new disturbances will most likely attract specialists. Without validation data from newly disturbed areas, however, the best approach for maximizing predictive accuracy can...

Performance of ANFIS versus MLP-NN dissolved oxygen prediction models in water quality monitoring.

PubMed

Najah, A; El-Shafie, A; Karim, O A; El-Shafie, Amr H

2014-02-01

We discuss the accuracy and performance of the adaptive neuro-fuzzy inference system (ANFIS) in training and prediction of dissolved oxygen (DO) concentrations. The model was used to analyze historical data generated through continuous monitoring of water quality parameters at several stations on the Johor River to predict DO concentrations. Four water quality parameters were selected for ANFIS modeling, including temperature, pH, nitrate (NO3) concentration, and ammoniacal nitrogen concentration (NH3-NL). Sensitivity analysis was performed to evaluate the effects of the input parameters. The inputs with the greatest effect were those related to oxygen content (NO3) or oxygen demand (NH3-NL). Temperature was the parameter with the least effect, whereas pH provided the lowest contribution to the proposed model. To evaluate the performance of the model, three statistical indices were used: the coefficient of determination (R (2)), the mean absolute prediction error, and the correlation coefficient. The performance of the ANFIS model was compared with an artificial neural network model. The ANFIS model was capable of providing greater accuracy, particularly in the case of extreme events.

Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae

DOE PAGES

Nguyen, Marcus; Brettin, Thomas; Long, S. Wesley; ...

2018-01-11

Here, antimicrobial resistant infections are a serious public health threat worldwide. Whole genome sequencing approaches to rapidly identify pathogens and predict antibiotic resistance phenotypes are becoming more feasible and may offer a way to reduce clinical test turnaround times compared to conventional culture-based methods, and in turn, improve patient outcomes. In this study, we use whole genome sequence data from 1668 clinical isolates of Klebsiella pneumoniae to develop a XGBoost-based machine learning model that accurately predicts minimum inhibitory concentrations (MICs) for 20 antibiotics. The overall accuracy of the model, within ± 1 two-fold dilution factor, is 92%. Individual accuracies aremore » >= 90% for 15/20 antibiotics. We show that the MICs predicted by the model correlate with known antimicrobial resistance genes. Importantly, the genome-wide approach described in this study offers a way to predict MICs for isolates without knowledge of the underlying gene content. This study shows that machine learning can be used to build a complete in silico MIC prediction panel for K. pneumoniae and provides a framework for building MIC prediction models for other pathogenic bacteria.« less

Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nguyen, Marcus; Brettin, Thomas; Long, S. Wesley

Here, antimicrobial resistant infections are a serious public health threat worldwide. Whole genome sequencing approaches to rapidly identify pathogens and predict antibiotic resistance phenotypes are becoming more feasible and may offer a way to reduce clinical test turnaround times compared to conventional culture-based methods, and in turn, improve patient outcomes. In this study, we use whole genome sequence data from 1668 clinical isolates of Klebsiella pneumoniae to develop a XGBoost-based machine learning model that accurately predicts minimum inhibitory concentrations (MICs) for 20 antibiotics. The overall accuracy of the model, within ± 1 two-fold dilution factor, is 92%. Individual accuracies aremore » >= 90% for 15/20 antibiotics. We show that the MICs predicted by the model correlate with known antimicrobial resistance genes. Importantly, the genome-wide approach described in this study offers a way to predict MICs for isolates without knowledge of the underlying gene content. This study shows that machine learning can be used to build a complete in silico MIC prediction panel for K. pneumoniae and provides a framework for building MIC prediction models for other pathogenic bacteria.« less

Integrative Approaches for Predicting in vivo Effects of Chemicals from their Structural Descriptors and the Results of Short-term Biological Assays

PubMed Central

Low, Yen S.; Sedykh, Alexander; Rusyn, Ivan; Tropsha, Alexander

2017-01-01

Cheminformatics approaches such as Quantitative Structure Activity Relationship (QSAR) modeling have been used traditionally for predicting chemical toxicity. In recent years, high throughput biological assays have been increasingly employed to elucidate mechanisms of chemical toxicity and predict toxic effects of chemicals in vivo. The data generated in such assays can be considered as biological descriptors of chemicals that can be combined with molecular descriptors and employed in QSAR modeling to improve the accuracy of toxicity prediction. In this review, we discuss several approaches for integrating chemical and biological data for predicting biological effects of chemicals in vivo and compare their performance across several data sets. We conclude that while no method consistently shows superior performance, the integrative approaches rank consistently among the best yet offer enriched interpretation of models over those built with either chemical or biological data alone. We discuss the outlook for such interdisciplinary methods and offer recommendations to further improve the accuracy and interpretability of computational models that predict chemical toxicity. PMID:24805064

Identification of Phragmites australis and Spartina alterniflora in the Yangtze Estuary between Bayes and BP neural network using hyper-spectral data

NASA Astrophysics Data System (ADS)

Liu, Pudong; Zhou, Jiayuan; Shi, Runhe; Zhang, Chao; Liu, Chaoshun; Sun, Zhibin; Gao, Wei

2016-09-01

The aim of this work was to identify the coastal wetland plants between Bayes and BP neural network using hyperspectral data in order to optimize the classification method. For this purpose, we chose two dominant plants (invasive S. alterniflora and native P. australis) in the Yangtze Estuary, the leaf spectral reflectance of P. australis and S. alterniflora were measured by ASD field spectral machine. We tested the Bayes method and BP neural network for the identification of these two species. Results showed that three different bands (i.e., 555 nm 711 nm and 920 nm) could be identified as the sensitive bands for the input parameters for the two methods. Bayes method and BP neural network prediction model both performed well (Bayes prediction for 88.57% accuracy, BP neural network model prediction for about 80% accuracy), but Bayes theorem method could give higher accuracy and stability.

Prediction of pesticide acute toxicity using two-dimensional chemical descriptors and target species classification

EPA Science Inventory

Previous modelling of the median lethal dose (oral rat LD50) has indicated that local class-based models yield better correlations than global models. We evaluated the hypothesis that dividing the dataset by pesticidal mechanisms would improve prediction accuracy. A linear discri...

Predictive models for Escherichia coli concentrations at inland lake beaches and relationship of model variables to pathogen detection

EPA Science Inventory

Methods are needed improve the timeliness and accuracy of recreational water‐quality assessments. Traditional culture methods require 18–24 h to obtain results and may not reflect current conditions. Predictive models, based on environmental and water quality variables, have been...

The Comparative Accuracy of Two Hydrologic Models in Simulating Warm-Season Runoff for Two Small, Hillslope Catchments

EPA Science Inventory

Runoff prediction is a cornerstone of water resources planning, and therefore modeling performance is a key issue. This paper investigates the comparative advantages of conceptual versus process- based models in predicting warm season runoff for upland, low-yield micro-catchments...

Response Errors in Females' and Males' Sentence Lipreading Necessitate Structurally Different Models for Predicting Lipreading Accuracy

ERIC Educational Resources Information Center

Bernstein, Lynne E.

2018-01-01

Lipreaders recognize words with phonetically impoverished stimuli, an ability that varies widely in normal-hearing adults. Lipreading accuracy for sentence stimuli was modeled with data from 339 normal-hearing adults. Models used measures of phonemic perceptual errors, insertion of text that was not in the stimulus, gender, and auditory speech…

Predicting Earth orientation changes from global forecasts of atmosphere-hydrosphere dynamics

NASA Astrophysics Data System (ADS)

Dobslaw, Henryk; Dill, Robert

2018-02-01

Effective Angular Momentum (EAM) functions obtained from global numerical simulations of atmosphere, ocean, and land surface dynamics are routinely processed by the Earth System Modelling group at Deutsches GeoForschungsZentrum. EAM functions are available since January 1976 with up to 3 h temporal resolution. Additionally, 6 days-long EAM forecasts are routinely published every day. Based on hindcast experiments with 305 individual predictions distributed over 15 months, we demonstrate that EAM forecasts improve the prediction accuracy of the Earth Orientation Parameters at all forecast horizons between 1 and 6 days. At day 6, prediction accuracy improves down to 1.76 mas for the terrestrial pole offset, and 2.6 mas for Δ UT1, which correspond to an accuracy increase of about 41% over predictions published in Bulletin A by the International Earth Rotation and Reference System Service.

Prediction of beta-turns from amino acid sequences using the residue-coupled model.

PubMed

Guruprasad, K; Shukla, S

2003-04-01

We evaluated the prediction of beta-turns from amino acid sequences using the residue-coupled model with an enlarged representative protein data set selected from the Protein Data Bank. Our results show that the probability values derived from a data set comprising 425 protein chains yielded an overall beta-turn prediction accuracy 68.74%, compared with 94.7% reported earlier on a data set of 30 proteins using the same method. However, we noted that the overall beta-turn prediction accuracy using probability values derived from the 30-protein data set reduces to 40.74% when tested on the data set comprising 425 protein chains. In contrast, using probability values derived from the 425 data set used in this analysis, the overall beta-turn prediction accuracy yielded consistent results when tested on either the 30-protein data set (64.62%) used earlier or a more recent representative data set comprising 619 protein chains (64.66%) or on a jackknife data set comprising 476 representative protein chains (63.38%). We therefore recommend the use of probability values derived from the 425 representative protein chains data set reported here, which gives more realistic and consistent predictions of beta-turns from amino acid sequences.

Genomic and pedigree-based prediction for leaf, stem, and stripe rust resistance in wheat.

PubMed

Juliana, Philomin; Singh, Ravi P; Singh, Pawan K; Crossa, Jose; Huerta-Espino, Julio; Lan, Caixia; Bhavani, Sridhar; Rutkoski, Jessica E; Poland, Jesse A; Bergstrom, Gary C; Sorrells, Mark E

2017-07-01

Genomic prediction for seedling and adult plant resistance to wheat rusts was compared to prediction using few markers as fixed effects in a least-squares approach and pedigree-based prediction. The unceasing plant-pathogen arms race and ephemeral nature of some rust resistance genes have been challenging for wheat (Triticum aestivum L.) breeding programs and farmers. Hence, it is important to devise strategies for effective evaluation and exploitation of quantitative rust resistance. One promising approach that could accelerate gain from selection for rust resistance is 'genomic selection' which utilizes dense genome-wide markers to estimate the breeding values (BVs) for quantitative traits. Our objective was to compare three genomic prediction models including genomic best linear unbiased prediction (GBLUP), GBLUP A that was GBLUP with selected loci as fixed effects and reproducing kernel Hilbert spaces-markers (RKHS-M) with least-squares (LS) approach, RKHS-pedigree (RKHS-P), and RKHS markers and pedigree (RKHS-MP) to determine the BVs for seedling and/or adult plant resistance (APR) to leaf rust (LR), stem rust (SR), and stripe rust (YR). The 333 lines in the 45th IBWSN and the 313 lines in the 46th IBWSN were genotyped using genotyping-by-sequencing and phenotyped in replicated trials. The mean prediction accuracies ranged from 0.31-0.74 for LR seedling, 0.12-0.56 for LR APR, 0.31-0.65 for SR APR, 0.70-0.78 for YR seedling, and 0.34-0.71 for YR APR. For most datasets, the RKHS-MP model gave the highest accuracies, while LS gave the lowest. GBLUP, GBLUP A, RKHS-M, and RKHS-P models gave similar accuracies. Using genome-wide marker-based models resulted in an average of 42% increase in accuracy over LS. We conclude that GS is a promising approach for improvement of quantitative rust resistance and can be implemented in the breeding pipeline.

CPO Prediction: Accuracy Assessment and Impact on UT1 Intensive Results

NASA Technical Reports Server (NTRS)

Malkin, Zinovy

2010-01-01

The UT1 Intensive results heavily depend on the celestial pole offset (CPO) model used during data processing. Since accurate CPO values are available with a delay of two to four weeks, CPO predictions are necessarily applied to the UT1 Intensive data analysis, and errors in the predictions can influence the operational UT1 accuracy. In this paper we assess the real accuracy of CPO prediction using the actual IERS and PUL predictions made in 2007-2009. Also, results of operational processing were analyzed to investigate the actual impact of EOP prediction errors on the rapid UT1 results. It was found that the impact of CPO prediction errors is at a level of several microseconds, whereas the impact of the inaccuracy in the polar motion prediction may be about one order of magnitude larger for ultra-rapid UT1 results. The situation can be amended if the IERS Rapid solution will be updated more frequently.

Thermal cut-off response modelling of universal motors

NASA Astrophysics Data System (ADS)

Thangaveloo, Kashveen; Chin, Yung Shin

2017-04-01

This paper presents a model to predict the thermal cut-off (TCO) response behaviour in universal motors. The mathematical model includes the calculations of heat loss in the universal motor and the flow characteristics around the TCO component which together are the main parameters for TCO response prediction. In order to accurately predict the TCO component temperature, factors like the TCO component resistance, the effect of ambient, and the flow conditions through the motor are taken into account to improve the prediction accuracy of the model.

Mitigating Errors in External Respiratory Surrogate-Based Models of Tumor Position

DOE Office of Scientific and Technical Information (OSTI.GOV)

Malinowski, Kathleen T.; Fischell Department of Bioengineering, University of Maryland, College Park, MD; McAvoy, Thomas J.

2012-04-01

Purpose: To investigate the effect of tumor site, measurement precision, tumor-surrogate correlation, training data selection, model design, and interpatient and interfraction variations on the accuracy of external marker-based models of tumor position. Methods and Materials: Cyberknife Synchrony system log files comprising synchronously acquired positions of external markers and the tumor from 167 treatment fractions were analyzed. The accuracy of Synchrony, ordinary-least-squares regression, and partial-least-squares regression models for predicting the tumor position from the external markers was evaluated. The quantity and timing of the data used to build the predictive model were varied. The effects of tumor-surrogate correlation and the precisionmore » in both the tumor and the external surrogate position measurements were explored by adding noise to the data. Results: The tumor position prediction errors increased during the duration of a fraction. Increasing the training data quantities did not always lead to more accurate models. Adding uncorrelated noise to the external marker-based inputs degraded the tumor-surrogate correlation models by 16% for partial-least-squares and 57% for ordinary-least-squares. External marker and tumor position measurement errors led to tumor position prediction changes 0.3-3.6 times the magnitude of the measurement errors, varying widely with model algorithm. The tumor position prediction errors were significantly associated with the patient index but not with the fraction index or tumor site. Partial-least-squares was as accurate as Synchrony and more accurate than ordinary-least-squares. Conclusions: The accuracy of surrogate-based inferential models of tumor position was affected by all the investigated factors, except for the tumor site and fraction index.« less

BDDCS Class Prediction for New Molecular Entities

PubMed Central

Broccatelli, Fabio; Cruciani, Gabriele; Benet, Leslie Z.; Oprea, Tudor I.

2012-01-01

The Biopharmaceutics Drug Disposition Classification System (BDDCS) was successfully employed for predicting drug-drug interactions (DDIs) with respect to drug metabolizing enzymes (DMEs), drug transporters and their interplay. The major assumption of BDDCS is that the extent of metabolism (EoM) predicts high versus low intestinal permeability rate, and vice versa, at least when uptake transporters or paracellular transport are not involved. We recently published a collection of over 900 marketed drugs classified for BDDCS. We suggest that a reliable model for predicting BDDCS class, integrated with in vitro assays, could anticipate disposition and potential DDIs of new molecular entities (NMEs). Here we describe a computational procedure for predicting BDDCS class from molecular structures. The model was trained on a set of 300 oral drugs, and validated on an external set of 379 oral drugs, using 17 descriptors calculated or derived from the VolSurf+ software. For each molecule, a probability of BDDCS class membership was given, based on predicted EoM, FDA solubility (FDAS) and their confidence scores. The accuracy in predicting FDAS was 78% in training and 77% in validation, while for EoM prediction the accuracy was 82% in training and 79% in external validation. The actual BDDCS class corresponded to the highest ranked calculated class for 55% of the validation molecules, and it was within the top two ranked more than 92% of the times. The unbalanced stratification of the dataset didn’t affect the prediction, which showed highest accuracy in predicting classes 2 and 3 with respect to the most populated class 1. For class 4 drugs a general lack of predictability was observed. A linear discriminant analysis (LDA) confirmed the degree of accuracy for the prediction of the different BDDCS classes is tied to the structure of the dataset. This model could routinely be used in early drug discovery to prioritize in vitro tests for NMEs (e.g., affinity to transporters, intestinal metabolism, intestinal absorption and plasma protein binding). We further applied the BDDCS prediction model on a large set of medicinal chemistry compounds (over 30,000 chemicals). Based on this application, we suggest that solubility, and not permeability, is the major difference between NMEs and drugs. We anticipate that the forecast of BDDCS categories in early drug discovery may lead to a significant R&D cost reduction. PMID:22224483

[Formulation of combined predictive indicators using logistic regression model in predicting sepsis and prognosis].

PubMed

Duan, Liwei; Zhang, Sheng; Lin, Zhaofen

2017-02-01

To explore the method and performance of using multiple indices to diagnose sepsis and to predict the prognosis of severe ill patients. Critically ill patients at first admission to intensive care unit (ICU) of Changzheng Hospital, Second Military Medical University, from January 2014 to September 2015 were enrolled if the following conditions were satisfied: (1) patients were 18-75 years old; (2) the length of ICU stay was more than 24 hours; (3) All records of the patients were available. Data of the patients was collected by searching the electronic medical record system. Logistic regression model was formulated to create the new combined predictive indicator and the receiver operating characteristic (ROC) curve for the new predictive indicator was built. The area under the ROC curve (AUC) for both the new indicator and original ones were compared. The optimal cut-off point was obtained where the Youden index reached the maximum value. Diagnostic parameters such as sensitivity, specificity and predictive accuracy were also calculated for comparison. Finally, individual values were substituted into the equation to test the performance in predicting clinical outcomes. A total of 362 patients (218 males and 144 females) were enrolled in our study and 66 patients died. The average age was (48.3±19.3) years old. (1) For the predictive model only containing categorical covariants [including procalcitonin (PCT), lipopolysaccharide (LPS), infection, white blood cells count (WBC) and fever], increased PCT, increased WBC and fever were demonstrated to be independent risk factors for sepsis in the logistic equation. The AUC for the new combined predictive indicator was higher than that of any other indictor, including PCT, LPS, infection, WBC and fever (0.930 vs. 0.661, 0.503, 0.570, 0.837, 0.800). The optimal cut-off value for the new combined predictive indicator was 0.518. Using the new indicator to diagnose sepsis, the sensitivity, specificity and diagnostic accuracy rate were 78.00%, 93.36% and 87.47%, respectively. One patient was randomly selected, and the clinical data was substituted into the probability equation for prediction. The calculated value was 0.015, which was less than the cut-off value (0.518), indicating that the prognosis was non-sepsis at an accuracy of 87.47%. (2) For the predictive model only containing continuous covariants, the logistic model which combined acute physiology and chronic health evaluation II (APACHE II) score and sequential organ failure assessment (SOFA) score to predict in-hospital death events, both APACHE II score and SOFA score were independent risk factors for death. The AUC for the new predictive indicator was higher than that of APACHE II score and SOFA score (0.834 vs. 0.812, 0.813). The optimal cut-off value for the new combined predictive indicator in predicting in-hospital death events was 0.236, and the corresponding sensitivity, specificity and diagnostic accuracy for the combined predictive indicator were 73.12%, 76.51% and 75.70%, respectively. One patient was randomly selected, and the APACHE II score and SOFA score was substituted into the probability equation for prediction. The calculated value was 0.570, which was higher than the cut-off value (0.236), indicating that the death prognosis at an accuracy of 75.70%. The combined predictive indicator, which is formulated by logistic regression models, is superior to any single indicator in predicting sepsis or in-hospital death events.

Weather models as virtual sensors to data-driven rainfall predictions in urban watersheds

NASA Astrophysics Data System (ADS)

Cozzi, Lorenzo; Galelli, Stefano; Pascal, Samuel Jolivet De Marc; Castelletti, Andrea

2013-04-01

Weather and climate predictions are a key element of urban hydrology where they are used to inform water management and assist in flood warning delivering. Indeed, the modelling of the very fast dynamics of urbanized catchments can be substantially improved by the use of weather/rainfall predictions. For example, in Singapore Marina Reservoir catchment runoff processes have a very short time of concentration (roughly one hour) and observational data are thus nearly useless for runoff predictions and weather prediction are required. Unfortunately, radar nowcasting methods do not allow to carrying out long - term weather predictions, whereas numerical models are limited by their coarse spatial scale. Moreover, numerical models are usually poorly reliable because of the fast motion and limited spatial extension of rainfall events. In this study we investigate the combined use of data-driven modelling techniques and weather variables observed/simulated with a numerical model as a way to improve rainfall prediction accuracy and lead time in the Singapore metropolitan area. To explore the feasibility of the approach, we use a Weather Research and Forecast (WRF) model as a virtual sensor network for the input variables (the states of the WRF model) to a machine learning rainfall prediction model. More precisely, we combine an input variable selection method and a non-parametric tree-based model to characterize the empirical relation between the rainfall measured at the catchment level and all possible weather input variables provided by WRF model. We explore different lead time to evaluate the model reliability for different long - term predictions, as well as different time lags to see how past information could improve results. Results show that the proposed approach allow a significant improvement of the prediction accuracy of the WRF model on the Singapore urban area.

Predictors of Mortality in the Critically Ill Cirrhotic Patient: Is the Model for End-Stage Liver Disease Enough?

PubMed

Annamalai, Alagappan; Harada, Megan Y; Chen, Melissa; Tran, Tram; Ko, Ara; Ley, Eric J; Nuno, Miriam; Klein, Andrew; Nissen, Nicholas; Noureddin, Mazen

2017-03-01

Critically ill cirrhotics require liver transplantation urgently, but are at high risk for perioperative mortality. The Model for End-stage Liver Disease (MELD) score, recently updated to incorporate serum sodium, estimates survival probability in patients with cirrhosis, but needs additional evaluation in the critically ill. The purpose of this study was to evaluate the predictive power of ICU admission MELD scores and identify clinical risk factors associated with increased mortality. This was a retrospective review of cirrhotic patients admitted to the ICU between January 2011 and December 2014. Patients who were discharged or underwent transplantation (survivors) were compared with those who died (nonsurvivors). Demographic characteristics, admission MELD scores, and clinical risk factors were recorded. Multivariate regression was used to identify independent predictors of mortality, and measures of model performance were assessed to determine predictive accuracy. Of 276 patients who met inclusion criteria, 153 were considered survivors and 123 were nonsurvivors. Survivor and nonsurvivor cohorts had similar demographic characteristics. Nonsurvivors had increased MELD, gastrointestinal bleeding, infection, mechanical ventilation, encephalopathy, vasopressors, dialysis, renal replacement therapy, requirement of blood products, and ICU length of stay. The MELD demonstrated low predictive power (c-statistic 0.73). Multivariate analysis identified MELD score (adjusted odds ratio [AOR] = 1.05), mechanical ventilation (AOR = 4.55), vasopressors (AOR = 3.87), and continuous renal replacement therapy (AOR = 2.43) as independent predictors of mortality, with stronger predictive accuracy (c-statistic 0.87). The MELD demonstrated relatively poor predictive accuracy in critically ill patients with cirrhosis and might not be the best indicator for prognosis in the ICU population. Prognostic accuracy is significantly improved when variables indicating organ support (mechanical ventilation, vasopressors, and continuous renal replacement therapy) are included in the model. Copyright © 2016. Published by Elsevier Inc.

Failure prediction using machine learning and time series in optical network.

PubMed

Wang, Zhilong; Zhang, Min; Wang, Danshi; Song, Chuang; Liu, Min; Li, Jin; Lou, Liqi; Liu, Zhuo

2017-08-07

In this paper, we propose a performance monitoring and failure prediction method in optical networks based on machine learning. The primary algorithms of this method are the support vector machine (SVM) and double exponential smoothing (DES). With a focus on risk-aware models in optical networks, the proposed protection plan primarily investigates how to predict the risk of an equipment failure. To the best of our knowledge, this important problem has not yet been fully considered. Experimental results showed that the average prediction accuracy of our method was 95% when predicting the optical equipment failure state. This finding means that our method can forecast an equipment failure risk with high accuracy. Therefore, our proposed DES-SVM method can effectively improve traditional risk-aware models to protect services from possible failures and enhance the optical network stability.

Improving Genomic Prediction in Cassava Field Experiments Using Spatial Analysis.

PubMed

Elias, Ani A; Rabbi, Ismail; Kulakow, Peter; Jannink, Jean-Luc

2018-01-04

Cassava ( Manihot esculenta Crantz) is an important staple food in sub-Saharan Africa. Breeding experiments were conducted at the International Institute of Tropical Agriculture in cassava to select elite parents. Taking into account the heterogeneity in the field while evaluating these trials can increase the accuracy in estimation of breeding values. We used an exploratory approach using the parametric spatial kernels Power, Spherical, and Gaussian to determine the best kernel for a given scenario. The spatial kernel was fit simultaneously with a genomic kernel in a genomic selection model. Predictability of these models was tested through a 10-fold cross-validation method repeated five times. The best model was chosen as the one with the lowest prediction root mean squared error compared to that of the base model having no spatial kernel. Results from our real and simulated data studies indicated that predictability can be increased by accounting for spatial variation irrespective of the heritability of the trait. In real data scenarios we observed that the accuracy can be increased by a median value of 3.4%. Through simulations, we showed that a 21% increase in accuracy can be achieved. We also found that Range (row) directional spatial kernels, mostly Gaussian, explained the spatial variance in 71% of the scenarios when spatial correlation was significant. Copyright © 2018 Elias et al.

Genomic relationships based on X chromosome markers and accuracy of genomic predictions with and without X chromosome markers

PubMed Central

2014-01-01

Background Although the X chromosome is the second largest bovine chromosome, markers on the X chromosome are not used for genomic prediction in some countries and populations. In this study, we presented a method for computing genomic relationships using X chromosome markers, investigated the accuracy of imputation from a low density (7K) to the 54K SNP (single nucleotide polymorphism) panel, and compared the accuracy of genomic prediction with and without using X chromosome markers. Methods The impact of considering X chromosome markers on prediction accuracy was assessed using data from Nordic Holstein bulls and different sets of SNPs: (a) the 54K SNPs for reference and test animals, (b) SNPs imputed from the 7K to the 54K SNP panel for test animals, (c) SNPs imputed from the 7K to the 54K panel for half of the reference animals, and (d) the 7K SNP panel for all animals. Beagle and Findhap were used for imputation. GBLUP (genomic best linear unbiased prediction) models with or without X chromosome markers and with or without a residual polygenic effect were used to predict genomic breeding values for 15 traits. Results Averaged over the two imputation datasets, correlation coefficients between imputed and true genotypes for autosomal markers, pseudo-autosomal markers, and X-specific markers were 0.971, 0.831 and 0.935 when using Findhap, and 0.983, 0.856 and 0.937 when using Beagle. Estimated reliabilities of genomic predictions based on the imputed datasets using Findhap or Beagle were very close to those using the real 54K data. Genomic prediction using all markers gave slightly higher reliabilities than predictions without X chromosome markers. Based on our data which included only bulls, using a G matrix that accounted for sex-linked relationships did not improve prediction, compared with a G matrix that did not account for sex-linked relationships. A model that included a polygenic effect did not recover the loss of prediction accuracy from exclusion of X chromosome markers. Conclusions The results from this study suggest that markers on the X chromosome contribute to accuracy of genomic predictions and should be used for routine genomic evaluation. PMID:25080199

Comparison of univariate and multivariate models for prediction of major and minor elements from laser-induced breakdown spectra with and without masking

NASA Astrophysics Data System (ADS)

Dyar, M. Darby; Fassett, Caleb I.; Giguere, Stephen; Lepore, Kate; Byrne, Sarah; Boucher, Thomas; Carey, CJ; Mahadevan, Sridhar

2016-09-01

This study uses 1356 spectra from 452 geologically-diverse samples, the largest suite of LIBS rock spectra ever assembled, to compare the accuracy of elemental predictions in models that use only spectral regions thought to contain peaks arising from the element of interest versus those that use information in the entire spectrum. Results show that for the elements Si, Al, Ti, Fe, Mg, Ca, Na, K, Ni, Mn, Cr, Co, and Zn, univariate predictions based on single emission lines are by far the least accurate, no matter how carefully the region of channels/wavelengths is chosen and despite the prominence of the selected emission lines. An automated iterative algorithm was developed to sweep through all 5485 channels of data and select the single region that produces the optimal prediction accuracy for each element using univariate analysis. For the eight major elements, use of this technique results in a 35% improvement in prediction accuracy; for minors, the improvement is 13%. The best wavelength region choice for any given univariate analysis is likely to be an inherent property of the specific training set that cannot be generalized. In comparison, multivariate analysis using partial least-squares (PLS) almost universally outperforms univariate analysis. PLS using all the same wavelength regions from the univariate analysis produces results that improve in accuracy by 63% for major elements and 3% for minor element. This difference is likely a reflection of signal to noise ratios, which are far better for major elements than for minor elements, and likely limit their prediction accuracy by any technique. We also compare predictions using specific wavelength ranges for each element against those employing all channels. Masking out channels to focus on emission lines from a specific element that occurs decreases prediction accuracy for major elements but is useful for minor elements with low signals and proportionally much higher noise; use of PLS rather than univariate analysis is still recommended. Finally, we tested the generalizability of our results by analyzing a second data set from a different instrument. Overall prediction accuracies for the mixed data sets are higher than for either set alone for all major and minor elements except Ni, Cr, and Co, where results are roughly comparable.

Bridging the gap between marker-assisted and genomic selection of heading time and plant height in hybrid wheat.

PubMed

Zhao, Y; Mette, M F; Gowda, M; Longin, C F H; Reif, J C

2014-06-01

Based on data from field trials with a large collection of 135 elite winter wheat inbred lines and 1604 F1 hybrids derived from them, we compared the accuracy of prediction of marker-assisted selection and current genomic selection approaches for the model traits heading time and plant height in a cross-validation approach. For heading time, the high accuracy seen with marker-assisted selection severely dropped with genomic selection approaches RR-BLUP (ridge regression best linear unbiased prediction) and BayesCπ, whereas for plant height, accuracy was low with marker-assisted selection as well as RR-BLUP and BayesCπ. Differences in the linkage disequilibrium structure of the functional and single-nucleotide polymorphism markers relevant for the two traits were identified in a simulation study as a likely explanation for the different trends in accuracies of prediction. A new genomic selection approach, weighted best linear unbiased prediction (W-BLUP), designed to treat the effects of known functional markers more appropriately, proved to increase the accuracy of prediction for both traits and thus closes the gap between marker-assisted and genomic selection.

Bridging the gap between marker-assisted and genomic selection of heading time and plant height in hybrid wheat

PubMed Central

Zhao, Y; Mette, M F; Gowda, M; Longin, C F H; Reif, J C

2014-01-01

Based on data from field trials with a large collection of 135 elite winter wheat inbred lines and 1604 F1 hybrids derived from them, we compared the accuracy of prediction of marker-assisted selection and current genomic selection approaches for the model traits heading time and plant height in a cross-validation approach. For heading time, the high accuracy seen with marker-assisted selection severely dropped with genomic selection approaches RR-BLUP (ridge regression best linear unbiased prediction) and BayesCπ, whereas for plant height, accuracy was low with marker-assisted selection as well as RR-BLUP and BayesCπ. Differences in the linkage disequilibrium structure of the functional and single-nucleotide polymorphism markers relevant for the two traits were identified in a simulation study as a likely explanation for the different trends in accuracies of prediction. A new genomic selection approach, weighted best linear unbiased prediction (W-BLUP), designed to treat the effects of known functional markers more appropriately, proved to increase the accuracy of prediction for both traits and thus closes the gap between marker-assisted and genomic selection. PMID:24518889

Efficiency and Accuracy of Time-Accurate Turbulent Navier-Stokes Computations

NASA Technical Reports Server (NTRS)

Rumsey, Christopher L.; Sanetrik, Mark D.; Biedron, Robert T.; Melson, N. Duane; Parlette, Edward B.

1995-01-01

The accuracy and efficiency of two types of subiterations in both explicit and implicit Navier-Stokes codes are explored for unsteady laminar circular-cylinder flow and unsteady turbulent flow over an 18-percent-thick circular-arc (biconvex) airfoil. Grid and time-step studies are used to assess the numerical accuracy of the methods. Nonsubiterative time-stepping schemes and schemes with physical time subiterations are subject to time-step limitations in practice that are removed by pseudo time sub-iterations. Computations for the circular-arc airfoil indicate that a one-equation turbulence model predicts the unsteady separated flow better than an algebraic turbulence model; also, the hysteresis with Mach number of the self-excited unsteadiness due to shock and boundary-layer separation is well predicted.

Bootstrap study of genome-enabled prediction reliabilities using haplotype blocks across Nordic Red cattle breeds.

PubMed

Cuyabano, B C D; Su, G; Rosa, G J M; Lund, M S; Gianola, D

2015-10-01

This study compared the accuracy of genome-enabled prediction models using individual single nucleotide polymorphisms (SNP) or haplotype blocks as covariates when using either a single breed or a combined population of Nordic Red cattle. The main objective was to compare predictions of breeding values of complex traits using a combined training population with haplotype blocks, with predictions using a single breed as training population and individual SNP as predictors. To compare the prediction reliabilities, bootstrap samples were taken from the test data set. With the bootstrapped samples of prediction reliabilities, we built and graphed confidence ellipses to allow comparisons. Finally, measures of statistical distances were used to calculate the gain in predictive ability. Our analyses are innovative in the context of assessment of predictive models, allowing a better understanding of prediction reliabilities and providing a statistical basis to effectively calibrate whether one prediction scenario is indeed more accurate than another. An ANOVA indicated that use of haplotype blocks produced significant gains mainly when Bayesian mixture models were used but not when Bayesian BLUP was fitted to the data. Furthermore, when haplotype blocks were used to train prediction models in a combined Nordic Red cattle population, we obtained up to a statistically significant 5.5% average gain in prediction accuracy, over predictions using individual SNP and training the model with a single breed. Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Assessing the prediction accuracy of a cure model for censored survival data with long-term survivors: Application to breast cancer data.

PubMed

Asano, Junichi; Hirakawa, Akihiro

2017-01-01

The Cox proportional hazards cure model is a survival model incorporating a cure rate with the assumption that the population contains both uncured and cured individuals. It contains a logistic regression for the cure rate, and a Cox regression to estimate the hazard for uncured patients. A single predictive model for both the cure and hazard can be developed by using a cure model that simultaneously predicts the cure rate and hazards for uncured patients; however, model selection is a challenge because of the lack of a measure for quantifying the predictive accuracy of a cure model. Recently, we developed an area under the receiver operating characteristic curve (AUC) for determining the cure rate in a cure model (Asano et al., 2014), but the hazards measure for uncured patients was not resolved. In this article, we propose novel C-statistics that are weighted by the patients' cure status (i.e., cured, uncured, or censored cases) for the cure model. The operating characteristics of the proposed C-statistics and their confidence interval were examined by simulation analyses. We also illustrate methods for predictive model selection and for further interpretation of variables using the proposed AUCs and C-statistics via application to breast cancer data.

Comparison of prediction methods for octanol-air partition coefficients of diverse organic compounds.

PubMed

Fu, Zhiqiang; Chen, Jingwen; Li, Xuehua; Wang, Ya'nan; Yu, Haiying

2016-04-01

The octanol-air partition coefficient (KOA) is needed for assessing multimedia transport and bioaccumulability of organic chemicals in the environment. As experimental determination of KOA for various chemicals is costly and laborious, development of KOA estimation methods is necessary. We investigated three methods for KOA prediction, conventional quantitative structure-activity relationship (QSAR) models based on molecular structural descriptors, group contribution models based on atom-centered fragments, and a novel model that predicts KOA via solvation free energy from air to octanol phase (ΔGO(0)), with a collection of 939 experimental KOA values for 379 compounds at different temperatures (263.15-323.15 K) as validation or training sets. The developed models were evaluated with the OECD guidelines on QSAR models validation and applicability domain (AD) description. Results showed that although the ΔGO(0) model is theoretically sound and has a broad AD, the prediction accuracy of the model is the poorest. The QSAR models perform better than the group contribution models, and have similar predictability and accuracy with the conventional method that estimates KOA from the octanol-water partition coefficient and Henry's law constant. One QSAR model, which can predict KOA at different temperatures, was recommended for application as to assess the long-range transport potential of chemicals. Copyright © 2016 Elsevier Ltd. All rights reserved.

Assessing the accuracy and stability of variable selection ...

EPA Pesticide Factsheets

Random forest (RF) modeling has emerged as an important statistical learning method in ecology due to its exceptional predictive performance. However, for large and complex ecological datasets there is limited guidance on variable selection methods for RF modeling. Typically, either a preselected set of predictor variables are used, or stepwise procedures are employed which iteratively add/remove variables according to their importance measures. This paper investigates the application of variable selection methods to RF models for predicting probable biological stream condition. Our motivating dataset consists of the good/poor condition of n=1365 stream survey sites from the 2008/2009 National Rivers and Stream Assessment, and a large set (p=212) of landscape features from the StreamCat dataset. Two types of RF models are compared: a full variable set model with all 212 predictors, and a reduced variable set model selected using a backwards elimination approach. We assess model accuracy using RF's internal out-of-bag estimate, and a cross-validation procedure with validation folds external to the variable selection process. We also assess the stability of the spatial predictions generated by the RF models to changes in the number of predictors, and argue that model selection needs to consider both accuracy and stability. The results suggest that RF modeling is robust to the inclusion of many variables of moderate to low importance. We found no substanti

A fragmentation and reassembly method for ab initio phasing.

PubMed

Shrestha, Rojan; Zhang, Kam Y J

2015-02-01

Ab initio phasing with de novo models has become a viable approach for structural solution from protein crystallographic diffraction data. This approach takes advantage of the known protein sequence information, predicts de novo models and uses them for structure determination by molecular replacement. However, even the current state-of-the-art de novo modelling method has a limit as to the accuracy of the model predicted, which is sometimes insufficient to be used as a template for successful molecular replacement. A fragment-assembly phasing method has been developed that starts from an ensemble of low-accuracy de novo models, disassembles them into fragments, places them independently in the crystallographic unit cell by molecular replacement and then reassembles them into a whole structure that can provide sufficient phase information to enable complete structure determination by automated model building. Tests on ten protein targets showed that the method could solve structures for eight of these targets, although the predicted de novo models cannot be used as templates for successful molecular replacement since the best model for each target is on average more than 4.0 Å away from the native structure. The method has extended the applicability of the ab initio phasing by de novo models approach. The method can be used to solve structures when the best de novo models are still of low accuracy.

Quantifying the Effect of Polymer Blending through Molecular Modelling of Cyanurate Polymers

PubMed Central

Crawford, Alasdair O.; Hamerton, Ian; Cavalli, Gabriel; Howlin, Brendan J.

2012-01-01

Modification of polymer properties by blending is a common practice in the polymer industry. We report here a study of blends of cyanurate polymers by molecular modelling that shows that the final experimentally determined properties can be predicted from first principles modelling to a good degree of accuracy. There is always a compromise between simulation length, accuracy and speed of prediction. A comparison of simulation times shows that 125ps of molecular dynamics simulation at each temperature provides the optimum compromise for models of this size with current technology. This study opens up the possibility of computer aided design of polymer blends with desired physical and mechanical properties. PMID:22970230

Predicting Barrett's Esophagus in Families: An Esophagus Translational Research Network (BETRNet) Model Fitting Clinical Data to a Familial Paradigm.

PubMed

Sun, Xiangqing; Elston, Robert C; Barnholtz-Sloan, Jill S; Falk, Gary W; Grady, William M; Faulx, Ashley; Mittal, Sumeet K; Canto, Marcia; Shaheen, Nicholas J; Wang, Jean S; Iyer, Prasad G; Abrams, Julian A; Tian, Ye D; Willis, Joseph E; Guda, Kishore; Markowitz, Sanford D; Chandar, Apoorva; Warfe, James M; Brock, Wendy; Chak, Amitabh

2016-05-01

Barrett's esophagus is often asymptomatic and only a small portion of Barrett's esophagus patients are currently diagnosed and under surveillance. Therefore, it is important to develop risk prediction models to identify high-risk individuals with Barrett's esophagus. Familial aggregation of Barrett's esophagus and esophageal adenocarcinoma, and the increased risk of esophageal adenocarcinoma for individuals with a family history, raise the necessity of including genetic factors in the prediction model. Methods to determine risk prediction models using both risk covariates and ascertained family data are not well developed. We developed a Barrett's Esophagus Translational Research Network (BETRNet) risk prediction model from 787 singly ascertained Barrett's esophagus pedigrees and 92 multiplex Barrett's esophagus pedigrees, fitting a multivariate logistic model that incorporates family history and clinical risk factors. The eight risk factors, age, sex, education level, parental status, smoking, heartburn frequency, regurgitation frequency, and use of acid suppressant, were included in the model. The prediction accuracy was evaluated on the training dataset and an independent validation dataset of 643 multiplex Barrett's esophagus pedigrees. Our results indicate family information helps to predict Barrett's esophagus risk, and predicting in families improves both prediction calibration and discrimination accuracy. Our model can predict Barrett's esophagus risk for anyone with family members known to have, or not have, had Barrett's esophagus. It can predict risk for unrelated individuals without knowing any relatives' information. Our prediction model will shed light on effectively identifying high-risk individuals for Barrett's esophagus screening and surveillance, consequently allowing intervention at an early stage, and reducing mortality from esophageal adenocarcinoma. Cancer Epidemiol Biomarkers Prev; 25(5); 727-35. ©2016 AACR. ©2016 American Association for Cancer Research.

Genomic prediction in a nuclear population of layers using single-step models.

PubMed

Yan, Yiyuan; Wu, Guiqin; Liu, Aiqiao; Sun, Congjiao; Han, Wenpeng; Li, Guangqi; Yang, Ning

2018-02-01

Single-step genomic prediction method has been proposed to improve the accuracy of genomic prediction by incorporating information of both genotyped and ungenotyped animals. The objective of this study is to compare the prediction performance of single-step model with a 2-step models and the pedigree-based models in a nuclear population of layers. A total of 1,344 chickens across 4 generations were genotyped by a 600 K SNP chip. Four traits were analyzed, i.e., body weight at 28 wk (BW28), egg weight at 28 wk (EW28), laying rate at 38 wk (LR38), and Haugh unit at 36 wk (HU36). In predicting offsprings, individuals from generation 1 to 3 were used as training data and females from generation 4 were used as validation set. The accuracies of predicted breeding values by pedigree BLUP (PBLUP), genomic BLUP (GBLUP), SSGBLUP and single-step blending (SSBlending) were compared for both genotyped and ungenotyped individuals. For genotyped females, GBLUP performed no better than PBLUP because of the small size of training data, while the 2 single-step models predicted more accurately than the PBLUP model. The average predictive ability of SSGBLUP and SSBlending were 16.0% and 10.8% higher than the PBLUP model across traits, respectively. Furthermore, the predictive abilities for ungenotyped individuals were also enhanced. The average improvements of prediction abilities were 5.9% and 1.5% for SSGBLUP and SSBlending model, respectively. It was concluded that single-step models, especially the SSGBLUP model, can yield more accurate prediction of genetic merits and are preferable for practical implementation of genomic selection in layers. © 2017 Poultry Science Association Inc.

Simple to complex modeling of breathing volume using a motion sensor.

PubMed

John, Dinesh; Staudenmayer, John; Freedson, Patty

2013-06-01

To compare simple and complex modeling techniques to estimate categories of low, medium, and high ventilation (VE) from ActiGraph™ activity counts. Vertical axis ActiGraph™ GT1M activity counts, oxygen consumption and VE were measured during treadmill walking and running, sports, household chores and labor-intensive employment activities. Categories of low (<19.3 l/min), medium (19.3 to 35.4 l/min) and high (>35.4 l/min) VEs were derived from activity intensity classifications (light <2.9 METs, moderate 3.0 to 5.9 METs and vigorous >6.0 METs). We examined the accuracy of two simple techniques (multiple regression and activity count cut-point analyses) and one complex (random forest technique) modeling technique in predicting VE from activity counts. Prediction accuracy of the complex random forest technique was marginally better than the simple multiple regression method. Both techniques accurately predicted VE categories almost 80% of the time. The multiple regression and random forest techniques were more accurate (85 to 88%) in predicting medium VE. Both techniques predicted the high VE (70 to 73%) with greater accuracy than low VE (57 to 60%). Actigraph™ cut-points for light, medium and high VEs were <1381, 1381 to 3660 and >3660 cpm. There were minor differences in prediction accuracy between the multiple regression and the random forest technique. This study provides methods to objectively estimate VE categories using activity monitors that can easily be deployed in the field. Objective estimates of VE should provide a better understanding of the dose-response relationship between internal exposure to pollutants and disease. Copyright © 2013 Elsevier B.V. All rights reserved.

MicroRNA based Pan-Cancer Diagnosis and Treatment Recommendation.

PubMed

Cheerla, Nikhil; Gevaert, Olivier

2017-01-13

The current state-of-the-art in cancer diagnosis and treatment is not ideal; diagnostic tests are accurate but invasive, and treatments are "one-size fits-all" instead of being personalized. Recently, miRNA's have garnered significant attention as cancer biomarkers, owing to their ease of access (circulating miRNA in the blood) and stability. There have been many studies showing the effectiveness of miRNA data in diagnosing specific cancer types, but few studies explore the role of miRNA in predicting treatment outcome. Here we go a step further, using tissue miRNA and clinical data across 21 cancers from the 'The Cancer Genome Atlas' (TCGA) database. We use machine learning techniques to create an accurate pan-cancer diagnosis system, and a prediction model for treatment outcomes. Finally, using these models, we create a web-based tool that diagnoses cancer and recommends the best treatment options. We achieved 97.2% accuracy for classification using a support vector machine classifier with radial basis. The accuracies improved to 99.9-100% when climbing up the embryonic tree and classifying cancers at different stages. We define the accuracy as the ratio of the total number of instances correctly classified to the total instances. The classifier also performed well, achieving greater than 80% sensitivity for many cancer types on independent validation datasets. Many miRNAs selected by our feature selection algorithm had strong previous associations to various cancers and tumor progression. Then, using miRNA, clinical and treatment data and encoding it in a machine-learning readable format, we built a prognosis predictor model to predict the outcome of treatment with 85% accuracy. We used this model to create a tool that recommends personalized treatment regimens. Both the diagnosis and prognosis model, incorporating semi-supervised learning techniques to improve their accuracies with repeated use, were uploaded online for easy access. Our research is a step towards the final goal of diagnosing cancer and predicting treatment recommendations using non-invasive blood tests.

A time series modeling approach in risk appraisal of violent and sexual recidivism.

PubMed

Bani-Yaghoub, Majid; Fedoroff, J Paul; Curry, Susan; Amundsen, David E

2010-10-01

For over half a century, various clinical and actuarial methods have been employed to assess the likelihood of violent recidivism. Yet there is a need for new methods that can improve the accuracy of recidivism predictions. This study proposes a new time series modeling approach that generates high levels of predictive accuracy over short and long periods of time. The proposed approach outperformed two widely used actuarial instruments (i.e., the Violence Risk Appraisal Guide and the Sex Offender Risk Appraisal Guide). Furthermore, analysis of temporal risk variations based on specific time series models can add valuable information into risk assessment and management of violent offenders.

Genome-wide association study and accuracy of genomic prediction for teat number in Duroc pigs using genotyping-by-sequencing.

PubMed

Tan, Cheng; Wu, Zhenfang; Ren, Jiangli; Huang, Zhuolin; Liu, Dewu; He, Xiaoyan; Prakapenka, Dzianis; Zhang, Ran; Li, Ning; Da, Yang; Hu, Xiaoxiang

2017-03-29

The number of teats in pigs is related to a sow's ability to rear piglets to weaning age. Several studies have identified genes and genomic regions that affect teat number in swine but few common results were reported. The objective of this study was to identify genetic factors that affect teat number in pigs, evaluate the accuracy of genomic prediction, and evaluate the contribution of significant genes and genomic regions to genomic broad-sense heritability and prediction accuracy using 41,108 autosomal single nucleotide polymorphisms (SNPs) from genotyping-by-sequencing on 2936 Duroc boars. Narrow-sense heritability and dominance heritability of teat number estimated by genomic restricted maximum likelihood were 0.365 ± 0.030 and 0.035 ± 0.019, respectively. The accuracy of genomic predictions, calculated as the average correlation between the genomic best linear unbiased prediction and phenotype in a tenfold validation study, was 0.437 ± 0.064 for the model with additive and dominance effects and 0.435 ± 0.064 for the model with additive effects only. Genome-wide association studies (GWAS) using three methods of analysis identified 85 significant SNP effects for teat number on chromosomes 1, 6, 7, 10, 11, 12 and 14. The region between 102.9 and 106.0 Mb on chromosome 7, which was reported in several studies, had the most significant SNP effects in or near the PTGR2, FAM161B, LIN52, VRTN, FCF1, AREL1 and LRRC74A genes. This region accounted for 10.0% of the genomic additive heritability and 8.0% of the accuracy of prediction. The second most significant chromosome region not reported by previous GWAS was the region between 77.7 and 79.7 Mb on chromosome 11, where SNPs in the FGF14 gene had the most significant effect and accounted for 5.1% of the genomic additive heritability and 5.2% of the accuracy of prediction. The 85 significant SNPs accounted for 28.5 to 28.8% of the genomic additive heritability and 35.8 to 36.8% of the accuracy of prediction. The three methods used for the GWAS identified 85 significant SNPs with additive effects on teat number, including SNPs in a previously reported chromosomal region and SNPs in novel chromosomal regions. Most significant SNPs with larger estimated effects also had larger contributions to the total genomic heritability and accuracy of prediction than other SNPs.

Common polygenic variation enhances risk prediction for Alzheimer’s disease

PubMed Central

Sims, Rebecca; Bannister, Christian; Harold, Denise; Vronskaya, Maria; Majounie, Elisa; Badarinarayan, Nandini; Morgan, Kevin; Passmore, Peter; Holmes, Clive; Powell, John; Brayne, Carol; Gill, Michael; Mead, Simon; Goate, Alison; Cruchaga, Carlos; Lambert, Jean-Charles; van Duijn, Cornelia; Maier, Wolfgang; Ramirez, Alfredo; Holmans, Peter; Jones, Lesley; Hardy, John; Seshadri, Sudha; Schellenberg, Gerard D.; Amouyel, Philippe

2015-01-01

The identification of subjects at high risk for Alzheimer’s disease is important for prognosis and early intervention. We investigated the polygenic architecture of Alzheimer’s disease and the accuracy of Alzheimer’s disease prediction models, including and excluding the polygenic component in the model. This study used genotype data from the powerful dataset comprising 17 008 cases and 37 154 controls obtained from the International Genomics of Alzheimer’s Project (IGAP). Polygenic score analysis tested whether the alleles identified to associate with disease in one sample set were significantly enriched in the cases relative to the controls in an independent sample. The disease prediction accuracy was investigated in a subset of the IGAP data, a sample of 3049 cases and 1554 controls (for whom APOE genotype data were available) by means of sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and positive and negative predictive values. We observed significant evidence for a polygenic component enriched in Alzheimer’s disease (P = 4.9 × 10−26). This enrichment remained significant after APOE and other genome-wide associated regions were excluded (P = 3.4 × 10−19). The best prediction accuracy AUC = 78.2% (95% confidence interval 77–80%) was achieved by a logistic regression model with APOE, the polygenic score, sex and age as predictors. In conclusion, Alzheimer’s disease has a significant polygenic component, which has predictive utility for Alzheimer’s disease risk and could be a valuable research tool complementing experimental designs, including preventative clinical trials, stem cell selection and high/low risk clinical studies. In modelling a range of sample disease prevalences, we found that polygenic scores almost doubles case prediction from chance with increased prediction at polygenic extremes. PMID:26490334

Relationship of physiography and snow area to stream discharge. [Kings River Watershed, California

NASA Technical Reports Server (NTRS)

Mccuen, R. H. (Principal Investigator)

1979-01-01

The author has identified the following significant results. A comparison of snowmelt runoff models shows that the accuracy of the Tangborn model and regression models is greater if the test data falls within the range of calibration than if the test data lies outside the range of calibration data. The regression models are significantly more accurate for forecasts of 60 days or more than for shorter prediction periods. The Tangborn model is more accurate for forecasts of 90 days or more than for shorter prediction periods. The Martinec model is more accurate for forecasts of one or two days than for periods of 3,5,10, or 15 days. Accuracy of the long-term models seems to be independent of forecast data. The sufficiency of the calibration data base is a function not only of the number of years of record but also of the accuracy with which the calibration years represent the total population of data years. Twelve years appears to be a sufficient length of record for each of the models considered, as long as the twelve years are representative of the population.

Application of the aeroacoustic analogy to a shrouded, subsonic, radial fan

NASA Astrophysics Data System (ADS)

Buccieri, Bryan M.; Richards, Christopher M.

2016-12-01

A study was conducted to investigate the predictive capability of computational aeroacoustics with respect to a shrouded, subsonic, radial fan. A three dimensional unsteady fluid dynamics simulation was conducted to produce aerodynamic data used as the acoustic source for an aeroacoustics simulation. Two acoustic models were developed: one modeling the forces on the rotating fan blades as a set of rotating dipoles located at the center of mass of each fan blade and one modeling the forces on the stationary fan shroud as a field of distributed stationary dipoles. Predicted acoustic response was compared to experimental data measured at two operating speeds using three different outlet restrictions. The blade source model predicted overall far field sound power levels within 5 dB averaged over the six different operating conditions while the shroud model predicted overall far field sound power levels within 7 dB averaged over the same conditions. Doubling the density of the computational fluids mesh and using a scale adaptive simulation turbulence model increased broadband noise accuracy. However, computation time doubled and the accuracy of the overall sound power level prediction improved by only 1 dB.

Channelized relevance vector machine as a numerical observer for cardiac perfusion defect detection task

NASA Astrophysics Data System (ADS)

Kalayeh, Mahdi M.; Marin, Thibault; Pretorius, P. Hendrik; Wernick, Miles N.; Yang, Yongyi; Brankov, Jovan G.

2011-03-01

In this paper, we present a numerical observer for image quality assessment, aiming to predict human observer accuracy in a cardiac perfusion defect detection task for single-photon emission computed tomography (SPECT). In medical imaging, image quality should be assessed by evaluating the human observer accuracy for a specific diagnostic task. This approach is known as task-based assessment. Such evaluations are important for optimizing and testing imaging devices and algorithms. Unfortunately, human observer studies with expert readers are costly and time-demanding. To address this problem, numerical observers have been developed as a surrogate for human readers to predict human diagnostic performance. The channelized Hotelling observer (CHO) with internal noise model has been found to predict human performance well in some situations, but does not always generalize well to unseen data. We have argued in the past that finding a model to predict human observers could be viewed as a machine learning problem. Following this approach, in this paper we propose a channelized relevance vector machine (CRVM) to predict human diagnostic scores in a detection task. We have previously used channelized support vector machines (CSVM) to predict human scores and have shown that this approach offers better and more robust predictions than the classical CHO method. The comparison of the proposed CRVM with our previously introduced CSVM method suggests that CRVM can achieve similar generalization accuracy, while dramatically reducing model complexity and computation time.

Modelling for Prediction vs. Modelling for Understanding: Commentary on Musso et al. (2013)

ERIC Educational Resources Information Center

Edelsbrunner, Peter; Schneider, Michael

2013-01-01

Musso et al. (2013) predict students' academic achievement with high accuracy one year in advance from cognitive and demographic variables, using artificial neural networks (ANNs). They conclude that ANNs have high potential for theoretical and practical improvements in learning sciences. ANNs are powerful statistical modelling tools but they can…

Comparing large-scale hydrological model predictions with observed streamflow in the Pacific Northwest: effects of climate and groundwater

Treesearch

Mohammad Safeeq; Guillaume S. Mauger; Gordon E. Grant; Ivan Arismendi; Alan F. Hamlet; Se-Yeun Lee

2014-01-01

Assessing uncertainties in hydrologic models can improve accuracy in predicting future streamflow. Here, simulated streamflows using the Variable Infiltration Capacity (VIC) model at coarse (1/16°) and fine (1/120°) spatial resolutions were evaluated against observed streamflows from 217 watersheds. In...

Prediction of apoptosis protein locations with genetic algorithms and support vector machines through a new mode of pseudo amino acid composition.

PubMed

Kandaswamy, Krishna Kumar; Pugalenthi, Ganesan; Möller, Steffen; Hartmann, Enno; Kalies, Kai-Uwe; Suganthan, P N; Martinetz, Thomas

2010-12-01

Apoptosis is an essential process for controlling tissue homeostasis by regulating a physiological balance between cell proliferation and cell death. The subcellular locations of proteins performing the cell death are determined by mostly independent cellular mechanisms. The regular bioinformatics tools to predict the subcellular locations of such apoptotic proteins do often fail. This work proposes a model for the sorting of proteins that are involved in apoptosis, allowing us to both the prediction of their subcellular locations as well as the molecular properties that contributed to it. We report a novel hybrid Genetic Algorithm (GA)/Support Vector Machine (SVM) approach to predict apoptotic protein sequences using 119 sequence derived properties like frequency of amino acid groups, secondary structure, and physicochemical properties. GA is used for selecting a near-optimal subset of informative features that is most relevant for the classification. Jackknife cross-validation is applied to test the predictive capability of the proposed method on 317 apoptosis proteins. Our method achieved 85.80% accuracy using all 119 features and 89.91% accuracy for 25 features selected by GA. Our models were examined by a test dataset of 98 apoptosis proteins and obtained an overall accuracy of 90.34%. The results show that the proposed approach is promising; it is able to select small subsets of features and still improves the classification accuracy. Our model can contribute to the understanding of programmed cell death and drug discovery. The software and dataset are available at http://www.inb.uni-luebeck.de/tools-demos/apoptosis/GASVM.

Transition index maps for urban growth simulation: application of artificial neural networks, weight of evidence and fuzzy multi-criteria evaluation.

PubMed

Shafizadeh-Moghadam, Hossein; Tayyebi, Amin; Helbich, Marco

2017-06-01

Transition index maps (TIMs) are key products in urban growth simulation models. However, their operationalization is still conflicting. Our aim was to compare the prediction accuracy of three TIM-based spatially explicit land cover change (LCC) models in the mega city of Mumbai, India. These LCC models include two data-driven approaches, namely artificial neural networks (ANNs) and weight of evidence (WOE), and one knowledge-based approach which integrates an analytical hierarchical process with fuzzy membership functions (FAHP). Using the relative operating characteristics (ROC), the performance of these three LCC models were evaluated. The results showed 85%, 75%, and 73% accuracy for the ANN, FAHP, and WOE. The ANN was clearly superior compared to the other LCC models when simulating urban growth for the year 2010; hence, ANN was used to predict urban growth for 2020 and 2030. Projected urban growth maps were assessed using statistical measures, including figure of merit, average spatial distance deviation, producer accuracy, and overall accuracy. Based on our findings, we recomend ANNs as an and accurate method for simulating future patterns of urban growth.

Mental models accurately predict emotion transitions.

PubMed

Thornton, Mark A; Tamir, Diana I

2017-06-06

Successful social interactions depend on people's ability to predict others' future actions and emotions. People possess many mechanisms for perceiving others' current emotional states, but how might they use this information to predict others' future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others' emotional dynamics. People could then use these mental models of emotion transitions to predict others' future emotions from currently observable emotions. To test this hypothesis, studies 1-3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants' ratings of emotion transitions predicted others' experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation-valence, social impact, rationality, and human mind-inform participants' mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants' accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone.

Development and validation of a preoperative prediction model for colorectal cancer T-staging based on MDCT images and clinical information.

PubMed

Sa, Sha; Li, Jing; Li, Xiaodong; Li, Yongrui; Liu, Xiaoming; Wang, Defeng; Zhang, Huimao; Fu, Yu

2017-08-15

This study aimed to establish and evaluate the efficacy of a prediction model for colorectal cancer T-staging. T-staging was positively correlated with the level of carcinoembryonic antigen (CEA), expression of carbohydrate antigen 19-9 (CA19-9), wall deformity, blurred outer edges, fat infiltration, infiltration into the surrounding tissue, tumor size and wall thickness. Age, location, enhancement rate and enhancement homogeneity were negatively correlated with T-staging. The predictive results of the model were consistent with the pathological gold standard, and the kappa value was 0.805. The total accuracy of staging improved from 51.04% to 86.98% with the proposed model. The clinical, imaging and pathological data of 611 patients with colorectal cancer (419 patients in the training group and 192 patients in the validation group) were collected. A spearman correlation analysis was used to validate the relationship among these factors and pathological T-staging. A prediction model was trained with the random forest algorithm. T staging of the patients in the validation group was predicted by both prediction model and traditional method. The consistency, accuracy, sensitivity, specificity and area under the curve (AUC) were used to compare the efficacy of the two methods. The newly established comprehensive model can improve the predictive efficiency of preoperative colorectal cancer T-staging.

Development of a new outcome prediction model for Chinese patients with penile squamous cell carcinoma based on preoperative serum C-reactive protein, body mass index, and standard pathological risk factors: the TNCB score group system.

PubMed

Li, Zai-Shang; Chen, Peng; Yao, Kai; Wang, Bin; Li, Jing; Mi, Qi-Wu; Chen, Xiao-Feng; Zhao, Qi; Li, Yong-Hong; Chen, Jie-Ping; Deng, Chuang-Zhong; Ye, Yun-Lin; Zhong, Ming-Zhu; Liu, Zhuo-Wei; Qin, Zi-Ke; Lin, Xiang-Tian; Liang, Wei-Cong; Han, Hui; Zhou, Fang-Jian

2016-04-12

To determine the predictive value and feasibility of the new outcome prediction model for Chinese patients with penile squamous cell carcinoma. The 3-year disease-specific survival (DSS) survival (DSS) was 92.3% in patients with < 8.70 mg/L CRP and 54.9% in those with elevated CRP (P < 0.001). The 3-year DSS was 86.5% in patients with a BMI < 22.6 Kg/m2 and 69.9% in those with a higher BMI (P = 0.025). In a multivariate analysis, pathological T stage (P < 0.001), pathological N stage (P = 0.002), BMI (P = 0.002), and CRP (P = 0.004) were independent predictors of DSS. A new scoring model was developed, consisting of BMI, CRP, and tumor T and N classification. In our study, we found that the addition of the above-mentioned parameters significantly increased the predictive accuracy of the system of the American Joint Committee on Cancer (AJCC) anatomic stage group. The accuracy of the new prediction category was verified. A total of 172 Chinese patients with penile squamous cell cancer were analyzed retrospectively between November 2005 and November 2014. Statistical data analysis was conducted using the nonparametric method. Survival analysis was performed with the log-rank test and the Cox proportional hazard model. Based on regression estimates of significant parameters in multivariate analysis, a new BMI-, CRP- and pathologic factors-based scoring model was developed to predict disease--specific outcomes. The predictive accuracy of the model was evaluated using the internal and external validation. The present study demonstrated that the TNCB score group system maybe a precise and easy to use tool for predicting outcomes in Chinese penile squamous cell carcinoma patients.

Dynamic Filtering Improves Attentional State Prediction with fNIRS

NASA Technical Reports Server (NTRS)

Harrivel, Angela R.; Weissman, Daniel H.; Noll, Douglas C.; Huppert, Theodore; Peltier, Scott J.

2016-01-01

Brain activity can predict a person's level of engagement in an attentional task. However, estimates of brain activity are often confounded by measurement artifacts and systemic physiological noise. The optimal method for filtering this noise - thereby increasing such state prediction accuracy - remains unclear. To investigate this, we asked study participants to perform an attentional task while we monitored their brain activity with functional near infrared spectroscopy (fNIRS). We observed higher state prediction accuracy when noise in the fNIRS hemoglobin [Hb] signals was filtered with a non-stationary (adaptive) model as compared to static regression (84% +/- 6% versus 72% +/- 15%).

The Systematics of Strong Lens Modeling Quantified: The Effects of Constraint Selection and Redshift Information on Magnification, Mass, and Multiple Image Predictability

NASA Astrophysics Data System (ADS)

Johnson, Traci L.; Sharon, Keren

2016-11-01

Until now, systematic errors in strong gravitational lens modeling have been acknowledged but have never been fully quantified. Here, we launch an investigation into the systematics induced by constraint selection. We model the simulated cluster Ares 362 times using random selections of image systems with and without spectroscopic redshifts and quantify the systematics using several diagnostics: image predictability, accuracy of model-predicted redshifts, enclosed mass, and magnification. We find that for models with >15 image systems, the image plane rms does not decrease significantly when more systems are added; however, the rms values quoted in the literature may be misleading as to the ability of a model to predict new multiple images. The mass is well constrained near the Einstein radius in all cases, and systematic error drops to <2% for models using >10 image systems. Magnification errors are smallest along the straight portions of the critical curve, and the value of the magnification is systematically lower near curved portions. For >15 systems, the systematic error on magnification is ∼2%. We report no trend in magnification error with the fraction of spectroscopic image systems when selecting constraints at random; however, when using the same selection of constraints, increasing this fraction up to ∼0.5 will increase model accuracy. The results suggest that the selection of constraints, rather than quantity alone, determines the accuracy of the magnification. We note that spectroscopic follow-up of at least a few image systems is crucial because models without any spectroscopic redshifts are inaccurate across all of our diagnostics.

Predicting the probability of mortality of gastric cancer patients using decision tree.

PubMed

Mohammadzadeh, F; Noorkojuri, H; Pourhoseingholi, M A; Saadat, S; Baghestani, A R

2015-06-01

Gastric cancer is the fourth most common cancer worldwide. This reason motivated us to investigate and introduce gastric cancer risk factors utilizing statistical methods. The aim of this study was to identify the most important factors influencing the mortality of patients who suffer from gastric cancer disease and to introduce a classification approach according to decision tree model for predicting the probability of mortality from this disease. Data on 216 patients with gastric cancer, who were registered in Taleghani hospital in Tehran,Iran, were analyzed. At first, patients were divided into two groups: the dead and alive. Then, to fit decision tree model to our data, we randomly selected 20% of dataset to the test sample and remaining dataset considered as the training sample. Finally, the validity of the model examined with sensitivity, specificity, diagnosis accuracy and the area under the receiver operating characteristic curve. The CART version 6.0 and SPSS version 19.0 softwares were used for the analysis of the data. Diabetes, ethnicity, tobacco, tumor size, surgery, pathologic stage, age at diagnosis, exposure to chemical weapons and alcohol consumption were determined as effective factors on mortality of gastric cancer. The sensitivity, specificity and accuracy of decision tree were 0.72, 0.75 and 0.74 respectively. The indices of sensitivity, specificity and accuracy represented that the decision tree model has acceptable accuracy to prediction the probability of mortality in gastric cancer patients. So a simple decision tree consisted of factors affecting on mortality of gastric cancer may help clinicians as a reliable and practical tool to predict the probability of mortality in these patients.

Modeling the distribution of white spruce (Picea glauca) for Alaska with high accuracy: an open access role-model for predicting tree species in last remaining wilderness areas

Treesearch

Bettina Ohse; Falk Huettmann; Stefanie M. Ickert-Bond; Glenn P. Juday

2009-01-01

Most wilderness areas still lack accurate distribution information on tree species. We met this need with a predictive GIS modeling approach, using freely available digital data and computer programs to efficiently obtain high-quality species distribution maps. Here we present a digital map with the predicted distribution of white spruce (Picea glauca...

Predicting juvenile recidivism: new method, old problems.

PubMed

Benda, B B

1987-01-01

This prediction study compared three statistical procedures for accuracy using two assessment methods. The criterion is return to a juvenile prison after the first release, and the models tested are logit analysis, predictive attribute analysis, and a Burgess procedure. No significant differences are found between statistics in prediction.

[Application of ARIMA model to predict number of malaria cases in China].

PubMed

Hui-Yu, H; Hua-Qin, S; Shun-Xian, Z; Lin, A I; Yan, L U; Yu-Chun, C; Shi-Zhu, L I; Xue-Jiao, T; Chun-Li, Y; Wei, H U; Jia-Xu, C

2017-08-15

Objective To study the application of autoregressive integrated moving average (ARIMA) model to predict the monthly reported malaria cases in China, so as to provide a reference for prevention and control of malaria. Methods SPSS 24.0 software was used to construct the ARIMA models based on the monthly reported malaria cases of the time series of 20062015 and 2011-2015, respectively. The data of malaria cases from January to December, 2016 were used as validation data to compare the accuracy of the two ARIMA models. Results The models of the monthly reported cases of malaria in China were ARIMA (2, 1, 1) (1, 1, 0) 12 and ARIMA (1, 0, 0) (1, 1, 0) 12 respectively. The comparison between the predictions of the two models and actual situation of malaria cases showed that the ARIMA model based on the data of 2011-2015 had a higher accuracy of forecasting than the model based on the data of 2006-2015 had. Conclusion The establishment and prediction of ARIMA model is a dynamic process, which needs to be adjusted unceasingly according to the accumulated data, and in addition, the major changes of epidemic characteristics of infectious diseases must be considered.

Study design requirements for RNA sequencing-based breast cancer diagnostics.

PubMed

Mer, Arvind Singh; Klevebring, Daniel; Grönberg, Henrik; Rantalainen, Mattias

2016-02-01

Sequencing-based molecular characterization of tumors provides information required for individualized cancer treatment. There are well-defined molecular subtypes of breast cancer that provide improved prognostication compared to routine biomarkers. However, molecular subtyping is not yet implemented in routine breast cancer care. Clinical translation is dependent on subtype prediction models providing high sensitivity and specificity. In this study we evaluate sample size and RNA-sequencing read requirements for breast cancer subtyping to facilitate rational design of translational studies. We applied subsampling to ascertain the effect of training sample size and the number of RNA sequencing reads on classification accuracy of molecular subtype and routine biomarker prediction models (unsupervised and supervised). Subtype classification accuracy improved with increasing sample size up to N = 750 (accuracy = 0.93), although with a modest improvement beyond N = 350 (accuracy = 0.92). Prediction of routine biomarkers achieved accuracy of 0.94 (ER) and 0.92 (Her2) at N = 200. Subtype classification improved with RNA-sequencing library size up to 5 million reads. Development of molecular subtyping models for cancer diagnostics requires well-designed studies. Sample size and the number of RNA sequencing reads directly influence accuracy of molecular subtyping. Results in this study provide key information for rational design of translational studies aiming to bring sequencing-based diagnostics to the clinic.

Short communication: Improving the accuracy of genomic prediction of body conformation traits in Chinese Holsteins using markers derived from high-density marker panels.

PubMed

Song, H; Li, L; Ma, P; Zhang, S; Su, G; Lund, M S; Zhang, Q; Ding, X

2018-06-01

This study investigated the efficiency of genomic prediction with adding the markers identified by genome-wide association study (GWAS) using a data set of imputed high-density (HD) markers from 54K markers in Chinese Holsteins. Among 3,056 Chinese Holsteins with imputed HD data, 2,401 individuals born before October 1, 2009, were used for GWAS and a reference population for genomic prediction, and the 220 younger cows were used as a validation population. In total, 1,403, 1,536, and 1,383 significant single nucleotide polymorphisms (SNP; false discovery rate at 0.05) associated with conformation final score, mammary system, and feet and legs were identified, respectively. About 2 to 3% genetic variance of 3 traits was explained by these significant SNP. Only a very small proportion of significant SNP identified by GWAS was included in the 54K marker panel. Three new marker sets (54K+) were herein produced by adding significant SNP obtained by linear mixed model for each trait into the 54K marker panel. Genomic breeding values were predicted using a Bayesian variable selection (BVS) model. The accuracies of genomic breeding value by BVS based on the 54K+ data were 2.0 to 5.2% higher than those based on the 54K data. The imputed HD markers yielded 1.4% higher accuracy on average (BVS) than the 54K data. Both the 54K+ and HD data generated lower bias of genomic prediction, and the 54K+ data yielded the lowest bias in all situations. Our results show that the imputed HD data were not very useful for improving the accuracy of genomic prediction and that adding the significant markers derived from the imputed HD marker panel could improve the accuracy of genomic prediction and decrease the bias of genomic prediction. Copyright © 2018 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Development of a two-fluid drag law for clustered particles using direct numerical simulation and validation through experiments

NASA Astrophysics Data System (ADS)

Abbasi Baharanchi, Ahmadreza

This dissertation focused on development and utilization of numerical and experimental approaches to improve the CFD modeling of fluidization flow of cohesive micron size particles. The specific objectives of this research were: (1) Developing a cluster prediction mechanism applicable to Two-Fluid Modeling (TFM) of gas-solid systems (2) Developing more accurate drag models for Two-Fluid Modeling (TFM) of gas-solid fluidization flow with the presence of cohesive interparticle forces (3) using the developed model to explore the improvement of accuracy of TFM in simulation of fluidization flow of cohesive powders (4) Understanding the causes and influential factor which led to improvements and quantification of improvements (5) Gathering data from a fast fluidization flow and use these data for benchmark validations. Simulation results with two developed cluster-aware drag models showed that cluster prediction could effectively influence the results in both the first and second cluster-aware models. It was proven that improvement of accuracy of TFM modeling using three versions of the first hybrid model was significant and the best improvements were obtained by using the smallest values of the switch parameter which led to capturing the smallest chances of cluster prediction. In the case of the second hybrid model, dependence of critical model parameter on only Reynolds number led to the fact that improvement of accuracy was significant only in dense section of the fluidized bed. This finding may suggest that a more sophisticated particle resolved DNS model, which can span wide range of solid volume fraction, can be used in the formulation of the cluster-aware drag model. The results of experiment suing high speed imaging indicated the presence of particle clusters in the fluidization flow of FCC inside the riser of FIU-CFB facility. In addition, pressure data was successfully captured along the fluidization column of the facility and used as benchmark validation data for the second hybrid model developed in the present dissertation. It was shown the second hybrid model could predict the pressure data in the dense section of the fluidization column with better accuracy.

Prediction and visualization of redox conditions in the groundwater of Central Valley, California

NASA Astrophysics Data System (ADS)

Rosecrans, Celia Z.; Nolan, Bernard T.; Gronberg, JoAnn M.

2017-03-01

Regional-scale, three-dimensional continuous probability models, were constructed for aspects of redox conditions in the groundwater system of the Central Valley, California. These models yield grids depicting the probability that groundwater in a particular location will have dissolved oxygen (DO) concentrations less than selected threshold values representing anoxic groundwater conditions, or will have dissolved manganese (Mn) concentrations greater than selected threshold values representing secondary drinking water-quality contaminant levels (SMCL) and health-based screening levels (HBSL). The probability models were constrained by the alluvial boundary of the Central Valley to a depth of approximately 300 m. Probability distribution grids can be extracted from the 3-D models at any desired depth, and are of interest to water-resource managers, water-quality researchers, and groundwater modelers concerned with the occurrence of natural and anthropogenic contaminants related to anoxic conditions. Models were constructed using a Boosted Regression Trees (BRT) machine learning technique that produces many trees as part of an additive model and has the ability to handle many variables, automatically incorporate interactions, and is resistant to collinearity. Machine learning methods for statistical prediction are becoming increasing popular in that they do not require assumptions associated with traditional hypothesis testing. Models were constructed using measured dissolved oxygen and manganese concentrations sampled from 2767 wells within the alluvial boundary of the Central Valley, and over 60 explanatory variables representing regional-scale soil properties, soil chemistry, land use, aquifer textures, and aquifer hydrologic properties. Models were trained on a USGS dataset of 932 wells, and evaluated on an independent hold-out dataset of 1835 wells from the California Division of Drinking Water. We used cross-validation to assess the predictive performance of models of varying complexity, as a basis for selecting final models. Trained models were applied to cross-validation testing data and a separate hold-out dataset to evaluate model predictive performance by emphasizing three model metrics of fit: Kappa; accuracy; and the area under the receiver operator characteristic curve (ROC). The final trained models were used for mapping predictions at discrete depths to a depth of 304.8 m. Trained DO and Mn models had accuracies of 86-100%, Kappa values of 0.69-0.99, and ROC values of 0.92-1.0. Model accuracies for cross-validation testing datasets were 82-95% and ROC values were 0.87-0.91, indicating good predictive performance. Kappas for the cross-validation testing dataset were 0.30-0.69, indicating fair to substantial agreement between testing observations and model predictions. Hold-out data were available for the manganese model only and indicated accuracies of 89-97%, ROC values of 0.73-0.75, and Kappa values of 0.06-0.30. The predictive performance of both the DO and Mn models was reasonable, considering all three of these fit metrics and the low percentages of low-DO and high-Mn events in the data.

Evaluation of wave runup predictions from numerical and parametric models

USGS Publications Warehouse

Stockdon, Hilary F.; Thompson, David M.; Plant, Nathaniel G.; Long, Joseph W.

2014-01-01

Wave runup during storms is a primary driver of coastal evolution, including shoreline and dune erosion and barrier island overwash. Runup and its components, setup and swash, can be predicted from a parameterized model that was developed by comparing runup observations to offshore wave height, wave period, and local beach slope. Because observations during extreme storms are often unavailable, a numerical model is used to simulate the storm-driven runup to compare to the parameterized model and then develop an approach to improve the accuracy of the parameterization. Numerically simulated and parameterized runup were compared to observations to evaluate model accuracies. The analysis demonstrated that setup was accurately predicted by both the parameterized model and numerical simulations. Infragravity swash heights were most accurately predicted by the parameterized model. The numerical model suffered from bias and gain errors that depended on whether a one-dimensional or two-dimensional spatial domain was used. Nonetheless, all of the predictions were significantly correlated to the observations, implying that the systematic errors can be corrected. The numerical simulations did not resolve the incident-band swash motions, as expected, and the parameterized model performed best at predicting incident-band swash heights. An assimilated prediction using a weighted average of the parameterized model and the numerical simulations resulted in a reduction in prediction error variance. Finally, the numerical simulations were extended to include storm conditions that have not been previously observed. These results indicated that the parameterized predictions of setup may need modification for extreme conditions; numerical simulations can be used to extend the validity of the parameterized predictions of infragravity swash; and numerical simulations systematically underpredict incident swash, which is relatively unimportant under extreme conditions.

Predicting tibiotalar and subtalar joint angles from skin-marker data with dual-fluoroscopy as a reference standard.

PubMed

Nichols, Jennifer A; Roach, Koren E; Fiorentino, Niccolo M; Anderson, Andrew E

2016-09-01

Evidence suggests that the tibiotalar and subtalar joints provide near six degree-of-freedom (DOF) motion. Yet, kinematic models frequently assume one DOF at each of these joints. In this study, we quantified the accuracy of kinematic models to predict joint angles at the tibiotalar and subtalar joints from skin-marker data. Models included 1 or 3 DOF at each joint. Ten asymptomatic subjects, screened for deformities, performed 1.0m/s treadmill walking and a balanced, single-leg heel-rise. Tibiotalar and subtalar joint angles calculated by inverse kinematics for the 1 and 3 DOF models were compared to those measured directly in vivo using dual-fluoroscopy. Results demonstrated that, for each activity, the average error in tibiotalar joint angles predicted by the 1 DOF model were significantly smaller than those predicted by the 3 DOF model for inversion/eversion and internal/external rotation. In contrast, neither model consistently demonstrated smaller errors when predicting subtalar joint angles. Additionally, neither model could accurately predict discrete angles for the tibiotalar and subtalar joints on a per-subject basis. Differences between model predictions and dual-fluoroscopy measurements were highly variable across subjects, with joint angle errors in at least one rotation direction surpassing 10° for 9 out of 10 subjects. Our results suggest that both the 1 and 3 DOF models can predict trends in tibiotalar joint angles on a limited basis. However, as currently implemented, neither model can predict discrete tibiotalar or subtalar joint angles for individual subjects. Inclusion of subject-specific attributes may improve the accuracy of these models. Copyright © 2016 Elsevier B.V. All rights reserved.

Classification of suicide attempters in schizophrenia using sociocultural and clinical features: A machine learning approach.

PubMed

Hettige, Nuwan C; Nguyen, Thai Binh; Yuan, Chen; Rajakulendran, Thanara; Baddour, Jermeen; Bhagwat, Nikhil; Bani-Fatemi, Ali; Voineskos, Aristotle N; Mallar Chakravarty, M; De Luca, Vincenzo

2017-07-01

Suicide is a major concern for those afflicted by schizophrenia. Identifying patients at the highest risk for future suicide attempts remains a complex problem for psychiatric interventions. Machine learning models allow for the integration of many risk factors in order to build an algorithm that predicts which patients are likely to attempt suicide. Currently it is unclear how to integrate previously identified risk factors into a clinically relevant predictive tool to estimate the probability of a patient with schizophrenia for attempting suicide. We conducted a cross-sectional assessment on a sample of 345 participants diagnosed with schizophrenia spectrum disorders. Suicide attempters and non-attempters were clearly identified using the Columbia Suicide Severity Rating Scale (C-SSRS) and the Beck Suicide Ideation Scale (BSS). We developed four classification algorithms using a regularized regression, random forest, elastic net and support vector machine models with sociocultural and clinical variables as features to train the models. All classification models performed similarly in identifying suicide attempters and non-attempters. Our regularized logistic regression model demonstrated an accuracy of 67% and an area under the curve (AUC) of 0.71, while the random forest model demonstrated 66% accuracy and an AUC of 0.67. Support vector classifier (SVC) model demonstrated an accuracy of 67% and an AUC of 0.70, and the elastic net model demonstrated and accuracy of 65% and an AUC of 0.71. Machine learning algorithms offer a relatively successful method for incorporating many clinical features to predict individuals at risk for future suicide attempts. Increased performance of these models using clinically relevant variables offers the potential to facilitate early treatment and intervention to prevent future suicide attempts. Copyright © 2017 Elsevier Inc. All rights reserved.

Deriving Physical Properties from Broadband Photometry with Prospector: Description of the Model and a Demonstration of its Accuracy Using 129 Galaxies in the Local Universe

DOE Office of Scientific and Technical Information (OSTI.GOV)

Leja, Joel; Johnson, Benjamin D.; Conroy, Charlie

2017-03-10

Broadband photometry of galaxies measures an unresolved mix of complex stellar populations, gas, and dust. Interpreting these data is a challenge for models: many studies have shown that properties derived from modeling galaxy photometry are uncertain by a factor of two or more, and yet answering key questions in the field now requires higher accuracy than this. Here, we present a new model framework specifically designed for these complexities. Our model, Prospector- α , includes dust attenuation and re-radiation, a flexible attenuation curve, nebular emission, stellar metallicity, and a six-component nonparametric star formation history. The flexibility and range of themore » parameter space, coupled with Monte Carlo Markov chain sampling within the Prospector inference framework, is designed to provide unbiased parameters and realistic error bars. We assess the accuracy of the model with aperture-matched optical spectroscopy, which was excluded from the fits. We compare spectral features predicted solely from fits to the broadband photometry to the observed spectral features. Our model predicts H α luminosities with a scatter of ∼0.18 dex and an offset of ∼0.1 dex across a wide range of morphological types and stellar masses. This agreement is remarkable, as the H α luminosity is dependent on accurate star formation rates, dust attenuation, and stellar metallicities. The model also accurately predicts dust-sensitive Balmer decrements, spectroscopic stellar metallicities, polycyclic aromatic hydrocarbon mass fractions, and the age- and metallicity-sensitive features D{sub n}4000 and H δ . Although the model passes all these tests, we caution that we have not yet assessed its performance at higher redshift or the accuracy of recovered stellar masses.« less

Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

PubMed Central

Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K

2015-01-01

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (p<0.001) and integrated discrimination improvement (p=0.04). The HALT-C model had a c-statistic of 0.60 (95%CI 0.50-0.70) in the validation cohort and was outperformed by the machine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273

Special Issue on Uncertainty Quantification in Multiscale System Design and Simulation

DOE PAGES

Wang, Yan; Swiler, Laura

2017-09-07

The importance of uncertainty has been recognized in various modeling, simulation, and analysis applications, where inherent assumptions and simplifications affect the accuracy of model predictions for physical phenomena. As model predictions are now heavily relied upon for simulation-based system design, which includes new materials, vehicles, mechanical and civil structures, and even new drugs, wrong model predictions could potentially cause catastrophic consequences. Therefore, uncertainty and associated risks due to model errors should be quantified to support robust systems engineering.

Special Issue on Uncertainty Quantification in Multiscale System Design and Simulation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wang, Yan; Swiler, Laura

The importance of uncertainty has been recognized in various modeling, simulation, and analysis applications, where inherent assumptions and simplifications affect the accuracy of model predictions for physical phenomena. As model predictions are now heavily relied upon for simulation-based system design, which includes new materials, vehicles, mechanical and civil structures, and even new drugs, wrong model predictions could potentially cause catastrophic consequences. Therefore, uncertainty and associated risks due to model errors should be quantified to support robust systems engineering.

Surrogate Modeling of High-Fidelity Fracture Simulations for Real-Time Residual Strength Predictions

NASA Technical Reports Server (NTRS)

Spear, Ashley D.; Priest, Amanda R.; Veilleux, Michael G.; Ingraffea, Anthony R.; Hochhalter, Jacob D.

2011-01-01

A surrogate model methodology is described for predicting in real time the residual strength of flight structures with discrete-source damage. Starting with design of experiment, an artificial neural network is developed that takes as input discrete-source damage parameters and outputs a prediction of the structural residual strength. Target residual strength values used to train the artificial neural network are derived from 3D finite element-based fracture simulations. A residual strength test of a metallic, integrally-stiffened panel is simulated to show that crack growth and residual strength are determined more accurately in discrete-source damage cases by using an elastic-plastic fracture framework rather than a linear-elastic fracture mechanics-based method. Improving accuracy of the residual strength training data would, in turn, improve accuracy of the surrogate model. When combined, the surrogate model methodology and high-fidelity fracture simulation framework provide useful tools for adaptive flight technology.

Feed-Forward Neural Network Soft-Sensor Modeling of Flotation Process Based on Particle Swarm Optimization and Gravitational Search Algorithm

PubMed Central

Wang, Jie-Sheng; Han, Shuang

2015-01-01

For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, a feed-forward neural network (FNN) based soft-sensor model optimized by the hybrid algorithm combining particle swarm optimization (PSO) algorithm and gravitational search algorithm (GSA) is proposed. Although GSA has better optimization capability, it has slow convergence velocity and is easy to fall into local optimum. So in this paper, the velocity vector and position vector of GSA are adjusted by PSO algorithm in order to improve its convergence speed and prediction accuracy. Finally, the proposed hybrid algorithm is adopted to optimize the parameters of FNN soft-sensor model. Simulation results show that the model has better generalization and prediction accuracy for the concentrate grade and tailings recovery rate to meet the online soft-sensor requirements of the real-time control in the flotation process. PMID:26583034

Surrogate Modeling of High-Fidelity Fracture Simulations for Real-Time Residual Strength Predictions

NASA Technical Reports Server (NTRS)

Spear, Ashley D.; Priest, Amanda R.; Veilleux, Michael G.; Ingraffea, Anthony R.; Hochhalter, Jacob D.

2011-01-01

A surrogate model methodology is described for predicting, during flight, the residual strength of aircraft structures that sustain discrete-source damage. Starting with design of experiment, an artificial neural network is developed that takes as input discrete-source damage parameters and outputs a prediction of the structural residual strength. Target residual strength values used to train the artificial neural network are derived from 3D finite element-based fracture simulations. Two ductile fracture simulations are presented to show that crack growth and residual strength are determined more accurately in discrete-source damage cases by using an elastic-plastic fracture framework rather than a linear-elastic fracture mechanics-based method. Improving accuracy of the residual strength training data does, in turn, improve accuracy of the surrogate model. When combined, the surrogate model methodology and high fidelity fracture simulation framework provide useful tools for adaptive flight technology.

Impact of meteorological factors on the incidence of bacillary dysentery in Beijing, China: A time series analysis (1970-2012).

PubMed

Yan, Long; Wang, Hong; Zhang, Xuan; Li, Ming-Yue; He, Juan

2017-01-01

Influence of meteorological variables on the transmission of bacillary dysentery (BD) is under investigated topic and effective forecasting models as public health tool are lacking. This paper aimed to quantify the relationship between meteorological variables and BD cases in Beijing and to establish an effective forecasting model. A time series analysis was conducted in the Beijing area based upon monthly data on weather variables (i.e. temperature, rainfall, relative humidity, vapor pressure, and wind speed) and on the number of BD cases during the period 1970-2012. Autoregressive integrated moving average models with explanatory variables (ARIMAX) were built based on the data from 1970 to 2004. Prediction of monthly BD cases from 2005 to 2012 was made using the established models. The prediction accuracy was evaluated by the mean square error (MSE). Firstly, temperature with 2-month and 7-month lags and rainfall with 12-month lag were found positively correlated with the number of BD cases in Beijing. Secondly, ARIMAX model with covariates of temperature with 7-month lag (β = 0.021, 95% confidence interval(CI): 0.004-0.038) and rainfall with 12-month lag (β = 0.023, 95% CI: 0.009-0.037) displayed the highest prediction accuracy. The ARIMAX model developed in this study showed an accurate goodness of fit and precise prediction accuracy in the short term, which would be beneficial for government departments to take early public health measures to prevent and control possible BD popularity.

ShinyGPAS: interactive genomic prediction accuracy simulator based on deterministic formulas.

PubMed

Morota, Gota

2017-12-20

Deterministic formulas for the accuracy of genomic predictions highlight the relationships among prediction accuracy and potential factors influencing prediction accuracy prior to performing computationally intensive cross-validation. Visualizing such deterministic formulas in an interactive manner may lead to a better understanding of how genetic factors control prediction accuracy. The software to simulate deterministic formulas for genomic prediction accuracy was implemented in R and encapsulated as a web-based Shiny application. Shiny genomic prediction accuracy simulator (ShinyGPAS) simulates various deterministic formulas and delivers dynamic scatter plots of prediction accuracy versus genetic factors impacting prediction accuracy, while requiring only mouse navigation in a web browser. ShinyGPAS is available at: https://chikudaisei.shinyapps.io/shinygpas/ . ShinyGPAS is a shiny-based interactive genomic prediction accuracy simulator using deterministic formulas. It can be used for interactively exploring potential factors that influence prediction accuracy in genome-enabled prediction, simulating achievable prediction accuracy prior to genotyping individuals, or supporting in-class teaching. ShinyGPAS is open source software and it is hosted online as a freely available web-based resource with an intuitive graphical user interface.

A Finite Element Model to Predict the Effect of Porosity on Elastic Modulus in Low-Porosity Materials

NASA Astrophysics Data System (ADS)

Morrissey, Liam S.; Nakhla, Sam

2018-07-01

The effect of porosity on elastic modulus in low-porosity materials is investigated. First, several models used to predict the reduction in elastic modulus due to porosity are compared with a compilation of experimental data to determine their ranges of validity and accuracy. The overlapping solid spheres model is found to be most accurate with the experimental data and valid between 3 and 10 pct porosity. Next, a FEM is developed with the objective of demonstrating that a macroscale plate with a center hole can be used to model the effect of microscale porosity on elastic modulus. The FEM agrees best with the overlapping solid spheres model and shows higher accuracy with experimental data than the overlapping solid spheres model.

Conflation and aggregation of spatial data improve predictive models for species with limited habitats: a case of the threatened yellow-billed cuckoo in Arizona, USA

USGS Publications Warehouse

Villarreal, Miguel L.; van Riper, Charles; Petrakis, Roy E.

2013-01-01

Riparian vegetation provides important wildlife habitat in the Southwestern United States, but limited distributions and spatial complexity often leads to inaccurate representation in maps used to guide conservation. We test the use of data conflation and aggregation on multiple vegetation/land-cover maps to improve the accuracy of habitat models for the threatened western yellow-billed cuckoo (Coccyzus americanus occidentalis). We used species observations (n = 479) from a state-wide survey to develop habitat models from 1) three vegetation/land-cover maps produced at different geographic scales ranging from state to national, and 2) new aggregate maps defined by the spatial agreement of cover types, which were defined as high (agreement = all data sets), moderate (agreement ≥ 2), and low (no agreement required). Model accuracies, predicted habitat locations, and total area of predicted habitat varied considerably, illustrating the effects of input data quality on habitat predictions and resulting potential impacts on conservation planning. Habitat models based on aggregated and conflated data were more accurate and had higher model sensitivity than original vegetation/land-cover, but this accuracy came at the cost of reduced geographic extent of predicted habitat. Using the highest performing models, we assessed cuckoo habitat preference and distribution in Arizona and found that major watersheds containing high-probably habitat are fragmented by a wide swath of low-probability habitat. Focus on riparian restoration in these areas could provide more breeding habitat for the threatened cuckoo, offset potential future habitat losses in adjacent watershed, and increase regional connectivity for other threatened vertebrates that also use riparian corridors.

[Discrimination of donkey meat by NIR and chemometrics].

PubMed

Niu, Xiao-Ying; Shao, Li-Min; Dong, Fang; Zhao, Zhi-Lei; Zhu, Yan

2014-10-01

Donkey meat samples (n = 167) from different parts of donkey body (neck, costalia, rump, and tendon), beef (n = 47), pork (n = 51) and mutton (n = 32) samples were used to establish near-infrared reflectance spectroscopy (NIR) classification models in the spectra range of 4,000~12,500 cm(-1). The accuracies of classification models constructed by Mahalanobis distances analysis, soft independent modeling of class analogy (SIMCA) and least squares-support vector machine (LS-SVM), respectively combined with pretreatment of Savitzky-Golay smooth (5, 15 and 25 points) and derivative (first and second), multiplicative scatter correction and standard normal variate, were compared. The optimal models for intact samples were obtained by Mahalanobis distances analysis with the first 11 principal components (PCs) from original spectra as inputs and by LS-SVM with the first 6 PCs as inputs, and correctly classified 100% of calibration set and 98. 96% of prediction set. For minced samples of 7 mm diameter the optimal result was attained by LS-SVM with the first 5 PCs from original spectra as inputs, which gained an accuracy of 100% for calibration and 97.53% for prediction. For minced diameter of 5 mm SIMCA model with the first 8 PCs from original spectra as inputs correctly classified 100% of calibration and prediction. And for minced diameter of 3 mm Mahalanobis distances analysis and SIMCA models both achieved 100% accuracy for calibration and prediction respectively with the first 7 and 9 PCs from original spectra as inputs. And in these models, donkey meat samples were all correctly classified with 100% either in calibration or prediction. The results show that it is feasible that NIR with chemometrics methods is used to discriminate donkey meat from the else meat.

Implementation of Chaotic Gaussian Particle Swarm Optimization for Optimize Learning-to-Rank Software Defect Prediction Model Construction

NASA Astrophysics Data System (ADS)

Buchari, M. A.; Mardiyanto, S.; Hendradjaya, B.

2018-03-01

Finding the existence of software defect as early as possible is the purpose of research about software defect prediction. Software defect prediction activity is required to not only state the existence of defects, but also to be able to give a list of priorities which modules require a more intensive test. Therefore, the allocation of test resources can be managed efficiently. Learning to rank is one of the approach that can provide defect module ranking data for the purposes of software testing. In this study, we propose a meta-heuristic chaotic Gaussian particle swarm optimization to improve the accuracy of learning to rank software defect prediction approach. We have used 11 public benchmark data sets as experimental data. Our overall results has demonstrated that the prediction models construct using Chaotic Gaussian Particle Swarm Optimization gets better accuracy on 5 data sets, ties in 5 data sets and gets worse in 1 data sets. Thus, we conclude that the application of Chaotic Gaussian Particle Swarm Optimization in Learning-to-Rank approach can improve the accuracy of the defect module ranking in data sets that have high-dimensional features.

Machine learning models in breast cancer survival prediction.

PubMed

Montazeri, Mitra; Montazeri, Mohadeseh; Montazeri, Mahdieh; Beigzadeh, Amin

2016-01-01

Breast cancer is one of the most common cancers with a high mortality rate among women. With the early diagnosis of breast cancer survival will increase from 56% to more than 86%. Therefore, an accurate and reliable system is necessary for the early diagnosis of this cancer. The proposed model is the combination of rules and different machine learning techniques. Machine learning models can help physicians to reduce the number of false decisions. They try to exploit patterns and relationships among a large number of cases and predict the outcome of a disease using historical cases stored in datasets. The objective of this study is to propose a rule-based classification method with machine learning techniques for the prediction of different types of Breast cancer survival. We use a dataset with eight attributes that include the records of 900 patients in which 876 patients (97.3%) and 24 (2.7%) patients were females and males respectively. Naive Bayes (NB), Trees Random Forest (TRF), 1-Nearest Neighbor (1NN), AdaBoost (AD), Support Vector Machine (SVM), RBF Network (RBFN), and Multilayer Perceptron (MLP) machine learning techniques with 10-cross fold technique were used with the proposed model for the prediction of breast cancer survival. The performance of machine learning techniques were evaluated with accuracy, precision, sensitivity, specificity, and area under ROC curve. Out of 900 patients, 803 patients and 97 patients were alive and dead, respectively. In this study, Trees Random Forest (TRF) technique showed better results in comparison to other techniques (NB, 1NN, AD, SVM and RBFN, MLP). The accuracy, sensitivity and the area under ROC curve of TRF are 96%, 96%, 93%, respectively. However, 1NN machine learning technique provided poor performance (accuracy 91%, sensitivity 91% and area under ROC curve 78%). This study demonstrates that Trees Random Forest model (TRF) which is a rule-based classification model was the best model with the highest level of accuracy. Therefore, this model is recommended as a useful tool for breast cancer survival prediction as well as medical decision making.

Factoring vs linear modeling in rate estimation: a simulation study of relative accuracy.

PubMed

Maldonado, G; Greenland, S

1998-07-01

A common strategy for modeling dose-response in epidemiology is to transform ordered exposures and covariates into sets of dichotomous indicator variables (that is, to factor the variables). Factoring tends to increase estimation variance, but it also tends to decrease bias and thus may increase or decrease total accuracy. We conducted a simulation study to examine the impact of factoring on the accuracy of rate estimation. Factored and unfactored Poisson regression models were fit to follow-up study datasets that were randomly generated from 37,500 population model forms that ranged from subadditive to supramultiplicative. In the situations we examined, factoring sometimes substantially improved accuracy relative to fitting the corresponding unfactored model, sometimes substantially decreased accuracy, and sometimes made little difference. The difference in accuracy between factored and unfactored models depended in a complicated fashion on the difference between the true and fitted model forms, the strength of exposure and covariate effects in the population, and the study size. It may be difficult in practice to predict when factoring is increasing or decreasing accuracy. We recommend, therefore, that the strategy of factoring variables be supplemented with other strategies for modeling dose-response.

Prediction and measurement of thermally induced cambial tissue necrosis in tree stems

Treesearch

Joshua L. Jones; Brent W. Webb; Bret W. Butler; Matthew B. Dickinson; Daniel Jimenez; James Reardon; Anthony S. Bova

2006-01-01

A model for fire-induced heating in tree stems is linked to a recently reported model for tissue necrosis. The combined model produces cambial tissue necrosis predictions in a tree stem as a function of heating rate, heating time, tree species, and stem diameter. Model accuracy is evaluated by comparison with experimental measurements in two hardwood and two softwood...

The Application of FIA-based Data to Wildlife Habitat Modeling: A Comparative Study

Treesearch

Thomas C., Jr. Edwards; Gretchen G. Moisen; Tracey S. Frescino; Randall J. Schultz

2005-01-01

We evaluated the capability of two types of models, one based on spatially explicit variables derived from FIA data and one using so-called traditional habitat evaluation methods, for predicting the presence of cavity-nesting bird habitat in Fishlake National Forest, Utah. Both models performed equally well, in measures of predictive accuracy, with the FIA-based model...

Assessment of traffic noise levels in urban areas using different soft computing techniques.

PubMed

Tomić, J; Bogojević, N; Pljakić, M; Šumarac-Pavlović, D

2016-10-01

Available traffic noise prediction models are usually based on regression analysis of experimental data, and this paper presents the application of soft computing techniques in traffic noise prediction. Two mathematical models are proposed and their predictions are compared to data collected by traffic noise monitoring in urban areas, as well as to predictions of commonly used traffic noise models. The results show that application of evolutionary algorithms and neural networks may improve process of development, as well as accuracy of traffic noise prediction.

Accuracy of taxonomy prediction for 16S rRNA and fungal ITS sequences

PubMed Central

2018-01-01

Prediction of taxonomy for marker gene sequences such as 16S ribosomal RNA (rRNA) is a fundamental task in microbiology. Most experimentally observed sequences are diverged from reference sequences of authoritatively named organisms, creating a challenge for prediction methods. I assessed the accuracy of several algorithms using cross-validation by identity, a new benchmark strategy which explicitly models the variation in distances between query sequences and the closest entry in a reference database. When the accuracy of genus predictions was averaged over a representative range of identities with the reference database (100%, 99%, 97%, 95% and 90%), all tested methods had ≤50% accuracy on the currently-popular V4 region of 16S rRNA. Accuracy was found to fall rapidly with identity; for example, better methods were found to have V4 genus prediction accuracy of ∼100% at 100% identity but ∼50% at 97% identity. The relationship between identity and taxonomy was quantified as the probability that a rank is the lowest shared by a pair of sequences with a given pair-wise identity. With the V4 region, 95% identity was found to be a twilight zone where taxonomy is highly ambiguous because the probabilities that the lowest shared rank between pairs of sequences is genus, family, order or class are approximately equal. PMID:29682424

Application of biodynamic imaging for personalized chemotherapy in canine lymphoma

NASA Astrophysics Data System (ADS)

Custead, Michelle R.

Biodynamic imaging (BDI) is a novel phenotypic cancer profiling technology which characterizes changes in cellular and subcellular motion in living tumor tissue samples following in vitro or ex vivo treatment with chemotherapeutics. The ability of BDI to predict clinical response to single-agent doxorubicin chemotherapy was tested in ten dogs with naturally-occurring non-Hodgkin's lymphomas (NHL). Pre-treatment tumor biopsy samples were obtained from all dogs and treated with doxorubicin (10 muM) ex vivo. BDI captured cellular and subcellular motility measures on all biopsy samples at baseline and at regular intervals for 9 hours following drug application. All dogs subsequently received treatment with a standard single-agent doxorubicin protocol. Objective response (OR) to doxorubicin and progression-free survival time (PFST) following chemotherapy were recorded for all dogs. The dynamic biomarkers measured by BDI were entered into a multivariate logistic model to determine the extent to which BDI predicted OR and PFST following doxorubicin therapy. The model showed that the sensitivity, specificity, and accuracy of BDI for predicting treatment outcome were 95%, 91%, and 93%, respectively. To account for possible over-fitting of data to the predictive model, cross-validation with a one-left-out analysis was performed, and the adjusted sensitivity, specificity, and accuracy following this analysis were 93%, 87%, and 91%, respectively. These findings suggest that BDI can predict, with high accuracy, treatment outcome following single-agent doxorubicin chemotherapy in a relevant spontaneous canine cancer model, and is a promising novel technology for advancing personalized cancer medicine.

Achievable accuracy of hip screw holding power estimation by insertion torque measurement.

PubMed

Erani, Paolo; Baleani, Massimiliano

2018-02-01

To ensure stability of proximal femoral fractures, the hip screw must firmly engage into the femoral head. Some studies suggested that screw holding power into trabecular bone could be evaluated, intraoperatively, through measurement of screw insertion torque. However, those studies used synthetic bone, instead of trabecular bone, as host material or they did not evaluate accuracy of predictions. We determined prediction accuracy, also assessing the impact of screw design and host material. We measured, under highly-repeatable experimental conditions, disregarding clinical procedure complexities, insertion torque and pullout strength of four screw designs, both in 120 synthetic and 80 trabecular bone specimens of variable density. For both host materials, we calculated the root-mean-square error and the mean-absolute-percentage error of predictions based on the best fitting model of torque-pullout data, in both single-screw and merged dataset. Predictions based on screw-specific regression models were the most accurate. Host material impacts on prediction accuracy: the replacement of synthetic with trabecular bone decreased both root-mean-square errors, from 0.54 ÷ 0.76 kN to 0.21 ÷ 0.40 kN, and mean-absolute-percentage errors, from 14 ÷ 21% to 10 ÷ 12%. However, holding power predicted on low insertion torque remained inaccurate, with errors up to 40% for torques below 1 Nm. In poor-quality trabecular bone, tissue inhomogeneities likely affect pullout strength and insertion torque to different extents, limiting the predictive power of the latter. This bias decreases when the screw engages good-quality bone. Under this condition, predictions become more accurate although this result must be confirmed by close in-vitro simulation of the clinical procedure. Copyright © 2018 Elsevier Ltd. All rights reserved.

Evaluating model structure adequacy: The case of the Maggia Valley groundwater system, southern Switzerland

USGS Publications Warehouse

Hill, Mary C.; L. Foglia,; S. W. Mehl,; P. Burlando,

2013-01-01

Model adequacy is evaluated with alternative models rated using model selection criteria (AICc, BIC, and KIC) and three other statistics. Model selection criteria are tested with cross-validation experiments and insights for using alternative models to evaluate model structural adequacy are provided. The study is conducted using the computer codes UCODE_2005 and MMA (MultiModel Analysis). One recharge alternative is simulated using the TOPKAPI hydrological model. The predictions evaluated include eight heads and three flows located where ecological consequences and model precision are of concern. Cross-validation is used to obtain measures of prediction accuracy. Sixty-four models were designed deterministically and differ in representation of river, recharge, bedrock topography, and hydraulic conductivity. Results include: (1) What may seem like inconsequential choices in model construction may be important to predictions. Analysis of predictions from alternative models is advised. (2) None of the model selection criteria consistently identified models with more accurate predictions. This is a disturbing result that suggests to reconsider the utility of model selection criteria, and/or the cross-validation measures used in this work to measure model accuracy. (3) KIC displayed poor performance for the present regression problems; theoretical considerations suggest that difficulties are associated with wide variations in the sensitivity term of KIC resulting from the models being nonlinear and the problems being ill-posed due to parameter correlations and insensitivity. The other criteria performed somewhat better, and similarly to each other. (4) Quantities with high leverage are more difficult to predict. The results are expected to be generally applicable to models of environmental systems.

The creation and evaluation of a model to simulate the probability of conception in seasonal-calving pasture-based dairy heifers.

PubMed

Fenlon, Caroline; O'Grady, Luke; Butler, Stephen; Doherty, Michael L; Dunnion, John

2017-01-01

Herd fertility in pasture-based dairy farms is a key driver of farm economics. Models for predicting nulliparous reproductive outcomes are rare, but age, genetics, weight, and BCS have been identified as factors influencing heifer conception. The aim of this study was to create a simulation model of heifer conception to service with thorough evaluation. Artificial Insemination service records from two research herds and ten commercial herds were provided to build and evaluate the models. All were managed as spring-calving pasture-based systems. The factors studied were related to age, genetics, and time of service. The data were split into training and testing sets and bootstrapping was used to train the models. Logistic regression (with and without random effects) and generalised additive modelling were selected as the model-building techniques. Two types of evaluation were used to test the predictive ability of the models: discrimination and calibration. Discrimination, which includes sensitivity, specificity, accuracy and ROC analysis, measures a model's ability to distinguish between positive and negative outcomes. Calibration measures the accuracy of the predicted probabilities with the Hosmer-Lemeshow goodness-of-fit, calibration plot and calibration error. After data cleaning and the removal of services with missing values, 1396 services remained to train the models and 597 were left for testing. Age, breed, genetic predicted transmitting ability for calving interval, month and year were significant in the multivariate models. The regression models also included an interaction between age and month. Year within herd was a random effect in the mixed regression model. Overall prediction accuracy was between 77.1% and 78.9%. All three models had very high sensitivity, but low specificity. The two regression models were very well-calibrated. The mean absolute calibration errors were all below 4%. Because the models were not adept at identifying unsuccessful services, they are not suggested for use in predicting the outcome of individual heifer services. Instead, they are useful for the comparison of services with different covariate values or as sub-models in whole-farm simulations. The mixed regression model was identified as the best model for prediction, as the random effects can be ignored and the other variables can be easily obtained or simulated.

Prediction of Return-to-original-work after an Industrial Accident Using Machine Learning and Comparison of Techniques

PubMed Central

2018-01-01

Background Many studies have tried to develop predictors for return-to-work (RTW). However, since complex factors have been demonstrated to predict RTW, it is difficult to use them practically. This study investigated whether factors used in previous studies could predict whether an individual had returned to his/her original work by four years after termination of the worker's recovery period. Methods An initial logistic regression analysis of 1,567 participants of the fourth Panel Study of Worker's Compensation Insurance yielded odds ratios. The participants were divided into two subsets, a training dataset and a test dataset. Using the training dataset, logistic regression, decision tree, random forest, and support vector machine models were established, and important variables of each model were identified. The predictive abilities of the different models were compared. Results The analysis showed that only earned income and company-related factors significantly affected return-to-original-work (RTOW). The random forest model showed the best accuracy among the tested machine learning models; however, the difference was not prominent. Conclusion It is possible to predict a worker's probability of RTOW using machine learning techniques with moderate accuracy. PMID:29736160

Predicting the Types of Ion Channel-Targeted Conotoxins Based on AVC-SVM Model.

PubMed

Xianfang, Wang; Junmei, Wang; Xiaolei, Wang; Yue, Zhang

2017-01-01

The conotoxin proteins are disulfide-rich small peptides. Predicting the types of ion channel-targeted conotoxins has great value in the treatment of chronic diseases, epilepsy, and cardiovascular diseases. To solve the problem of information redundancy existing when using current methods, a new model is presented to predict the types of ion channel-targeted conotoxins based on AVC (Analysis of Variance and Correlation) and SVM (Support Vector Machine). First, the F value is used to measure the significance level of the feature for the result, and the attribute with smaller F value is filtered by rough selection. Secondly, redundancy degree is calculated by Pearson Correlation Coefficient. And the threshold is set to filter attributes with weak independence to get the result of the refinement. Finally, SVM is used to predict the types of ion channel-targeted conotoxins. The experimental results show the proposed AVC-SVM model reaches an overall accuracy of 91.98%, an average accuracy of 92.17%, and the total number of parameters of 68. The proposed model provides highly useful information for further experimental research. The prediction model will be accessed free of charge at our web server.

Predicting the Types of Ion Channel-Targeted Conotoxins Based on AVC-SVM Model

PubMed Central

Xiaolei, Wang

2017-01-01

The conotoxin proteins are disulfide-rich small peptides. Predicting the types of ion channel-targeted conotoxins has great value in the treatment of chronic diseases, epilepsy, and cardiovascular diseases. To solve the problem of information redundancy existing when using current methods, a new model is presented to predict the types of ion channel-targeted conotoxins based on AVC (Analysis of Variance and Correlation) and SVM (Support Vector Machine). First, the F value is used to measure the significance level of the feature for the result, and the attribute with smaller F value is filtered by rough selection. Secondly, redundancy degree is calculated by Pearson Correlation Coefficient. And the threshold is set to filter attributes with weak independence to get the result of the refinement. Finally, SVM is used to predict the types of ion channel-targeted conotoxins. The experimental results show the proposed AVC-SVM model reaches an overall accuracy of 91.98%, an average accuracy of 92.17%, and the total number of parameters of 68. The proposed model provides highly useful information for further experimental research. The prediction model will be accessed free of charge at our web server. PMID:28497044

Study on the medical meteorological forecast of the number of hypertension inpatient based on SVR

NASA Astrophysics Data System (ADS)

Zhai, Guangyu; Chai, Guorong; Zhang, Haifeng

2017-06-01

The purpose of this study is to build a hypertension prediction model by discussing the meteorological factors for hypertension incidence. The research method is selecting the standard data of relative humidity, air temperature, visibility, wind speed and air pressure of Lanzhou from 2010 to 2012(calculating the maximum, minimum and average value with 5 days as a unit ) as the input variables of Support Vector Regression(SVR) and the standard data of hypertension incidence of the same period as the output dependent variables to obtain the optimal prediction parameters by cross validation algorithm, then by SVR algorithm learning and training, a SVR forecast model for hypertension incidence is built. The result shows that the hypertension prediction model is composed of 15 input independent variables, the training accuracy is 0.005, the final error is 0.0026389. The forecast accuracy based on SVR model is 97.1429%, which is higher than statistical forecast equation and neural network prediction method. It is concluded that SVR model provides a new method for hypertension prediction with its simple calculation, small error as well as higher historical sample fitting and Independent sample forecast capability.

Improved Prediction of Blood-Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints.

PubMed

Yuan, Yaxia; Zheng, Fang; Zhan, Chang-Guo

2018-03-21

Blood-brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.

PockDrug: A Model for Predicting Pocket Druggability That Overcomes Pocket Estimation Uncertainties.

PubMed

Borrel, Alexandre; Regad, Leslie; Xhaard, Henri; Petitjean, Michel; Camproux, Anne-Claude

2015-04-27

Predicting protein druggability is a key interest in the target identification phase of drug discovery. Here, we assess the pocket estimation methods' influence on druggability predictions by comparing statistical models constructed from pockets estimated using different pocket estimation methods: a proximity of either 4 or 5.5 Å to a cocrystallized ligand or DoGSite and fpocket estimation methods. We developed PockDrug, a robust pocket druggability model that copes with uncertainties in pocket boundaries. It is based on a linear discriminant analysis from a pool of 52 descriptors combined with a selection of the most stable and efficient models using different pocket estimation methods. PockDrug retains the best combinations of three pocket properties which impact druggability: geometry, hydrophobicity, and aromaticity. It results in an average accuracy of 87.9% ± 4.7% using a test set and exhibits higher accuracy (∼5-10%) than previous studies that used an identical apo set. In conclusion, this study confirms the influence of pocket estimation on pocket druggability prediction and proposes PockDrug as a new model that overcomes pocket estimation variability.

The interplay of various sources of noise on reliability of species distribution models hinges on ecological specialisation.

PubMed

Soultan, Alaaeldin; Safi, Kamran

2017-01-01

Digitized species occurrence data provide an unprecedented source of information for ecologists and conservationists. Species distribution model (SDM) has become a popular method to utilise these data for understanding the spatial and temporal distribution of species, and for modelling biodiversity patterns. Our objective is to study the impact of noise in species occurrence data (namely sample size and positional accuracy) on the performance and reliability of SDM, considering the multiplicative impact of SDM algorithms, species specialisation, and grid resolution. We created a set of four 'virtual' species characterized by different specialisation levels. For each of these species, we built the suitable habitat models using five algorithms at two grid resolutions, with varying sample sizes and different levels of positional accuracy. We assessed the performance and reliability of the SDM according to classic model evaluation metrics (Area Under the Curve and True Skill Statistic) and model agreement metrics (Overall Concordance Correlation Coefficient and geographic niche overlap) respectively. Our study revealed that species specialisation had by far the most dominant impact on the SDM. In contrast to previous studies, we found that for widespread species, low sample size and low positional accuracy were acceptable, and useful distribution ranges could be predicted with as few as 10 species occurrences. Range predictions for narrow-ranged species, however, were sensitive to sample size and positional accuracy, such that useful distribution ranges required at least 20 species occurrences. Against expectations, the MAXENT algorithm poorly predicted the distribution of specialist species at low sample size.

Multi-Scale Approach for Predicting Fish Species Distributions across Coral Reef Seascapes

PubMed Central

Pittman, Simon J.; Brown, Kerry A.

2011-01-01

Two of the major limitations to effective management of coral reef ecosystems are a lack of information on the spatial distribution of marine species and a paucity of data on the interacting environmental variables that drive distributional patterns. Advances in marine remote sensing, together with the novel integration of landscape ecology and advanced niche modelling techniques provide an unprecedented opportunity to reliably model and map marine species distributions across many kilometres of coral reef ecosystems. We developed a multi-scale approach using three-dimensional seafloor morphology and across-shelf location to predict spatial distributions for five common Caribbean fish species. Seascape topography was quantified from high resolution bathymetry at five spatial scales (5–300 m radii) surrounding fish survey sites. Model performance and map accuracy was assessed for two high performing machine-learning algorithms: Boosted Regression Trees (BRT) and Maximum Entropy Species Distribution Modelling (MaxEnt). The three most important predictors were geographical location across the shelf, followed by a measure of topographic complexity. Predictor contribution differed among species, yet rarely changed across spatial scales. BRT provided ‘outstanding’ model predictions (AUC = >0.9) for three of five fish species. MaxEnt provided ‘outstanding’ model predictions for two of five species, with the remaining three models considered ‘excellent’ (AUC = 0.8–0.9). In contrast, MaxEnt spatial predictions were markedly more accurate (92% map accuracy) than BRT (68% map accuracy). We demonstrate that reliable spatial predictions for a range of key fish species can be achieved by modelling the interaction between the geographical location across the shelf and the topographic heterogeneity of seafloor structure. This multi-scale, analytic approach is an important new cost-effective tool to accurately delineate essential fish habitat and support conservation prioritization in marine protected area design, zoning in marine spatial planning, and ecosystem-based fisheries management. PMID:21637787

Multi-scale approach for predicting fish species distributions across coral reef seascapes.

PubMed

Pittman, Simon J; Brown, Kerry A

2011-01-01

Two of the major limitations to effective management of coral reef ecosystems are a lack of information on the spatial distribution of marine species and a paucity of data on the interacting environmental variables that drive distributional patterns. Advances in marine remote sensing, together with the novel integration of landscape ecology and advanced niche modelling techniques provide an unprecedented opportunity to reliably model and map marine species distributions across many kilometres of coral reef ecosystems. We developed a multi-scale approach using three-dimensional seafloor morphology and across-shelf location to predict spatial distributions for five common Caribbean fish species. Seascape topography was quantified from high resolution bathymetry at five spatial scales (5-300 m radii) surrounding fish survey sites. Model performance and map accuracy was assessed for two high performing machine-learning algorithms: Boosted Regression Trees (BRT) and Maximum Entropy Species Distribution Modelling (MaxEnt). The three most important predictors were geographical location across the shelf, followed by a measure of topographic complexity. Predictor contribution differed among species, yet rarely changed across spatial scales. BRT provided 'outstanding' model predictions (AUC = >0.9) for three of five fish species. MaxEnt provided 'outstanding' model predictions for two of five species, with the remaining three models considered 'excellent' (AUC = 0.8-0.9). In contrast, MaxEnt spatial predictions were markedly more accurate (92% map accuracy) than BRT (68% map accuracy). We demonstrate that reliable spatial predictions for a range of key fish species can be achieved by modelling the interaction between the geographical location across the shelf and the topographic heterogeneity of seafloor structure. This multi-scale, analytic approach is an important new cost-effective tool to accurately delineate essential fish habitat and support conservation prioritization in marine protected area design, zoning in marine spatial planning, and ecosystem-based fisheries management.

Faster Trees: Strategies for Accelerated Training and Prediction of Random Forests for Classification of Polsar Images

NASA Astrophysics Data System (ADS)

Hänsch, Ronny; Hellwich, Olaf

2018-04-01

Random Forests have continuously proven to be one of the most accurate, robust, as well as efficient methods for the supervised classification of images in general and polarimetric synthetic aperture radar data in particular. While the majority of previous work focus on improving classification accuracy, we aim for accelerating the training of the classifier as well as its usage during prediction while maintaining its accuracy. Unlike other approaches we mainly consider algorithmic changes to stay as much as possible independent of platform and programming language. The final model achieves an approximately 60 times faster training and a 500 times faster prediction, while the accuracy is only marginally decreased by roughly 1 %.

Predictive accuracy of a model of volatile anesthetic uptake.

PubMed

Kennedy, R Ross; French, Richard A; Spencer, Christopher

2002-12-01

A computer program that models anesthetic uptake and distribution has been in use in our department for 20 yr as a teaching tool. New anesthesia machines that electronically measure fresh gas flow rates and vaporizer settings allowed us to assess the performance of this model during clinical anesthesia. Gas flow, vaporizer settings, and end-tidal concentrations were collected from the anesthesia machine (Datex S/5 ADU) at 10-s intervals during 30 elective anesthetics. These were entered into the uptake model. Expired anesthetic vapor concentrations were calculated and compared with actual values as measured by the patient monitor (Datex AS/3). Sevoflurane was used in 16 patients and isoflurane in 14 patients. For all patients, the median performance error was -0.24%, the median absolute performance error was 13.7%, divergence was 2.3%/h, and wobble was 3.1%. There was no significant difference between sevoflurane and isoflurane. This model predicted expired concentrations well in these patients. These results are similar to those seen when comparing calculated and actual propofol concentrations in propofol infusion systems and meet published guidelines for the accuracy of models used in target-controlled anesthesia systems. This model may be useful for predicting responses to changes in fresh gas and vapor settings. We compared measured inhaled anesthetic concentrations with those predicted by a model. The method used for comparison has been used to study models of propofol administration. Our model predicts expired isoflurane and sevoflurane concentrations at least as well as common propofol models predict arterial propofol concentrations.

Wind Power Curve Modeling in Simple and Complex Terrain

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bulaevskaya, V.; Wharton, S.; Irons, Z.

2015-02-09

Our previous work on wind power curve modeling using statistical models focused on a location with a moderately complex terrain in the Altamont Pass region in northern California (CA). The work described here is the follow-up to that work, but at a location with a simple terrain in northern Oklahoma (OK). The goal of the present analysis was to determine the gain in predictive ability afforded by adding information beyond the hub-height wind speed, such as wind speeds at other heights, as well as other atmospheric variables, to the power prediction model at this new location and compare the resultsmore » to those obtained at the CA site in the previous study. While we reach some of the same conclusions at both sites, many results reported for the CA site do not hold at the OK site. In particular, using the entire vertical profile of wind speeds improves the accuracy of wind power prediction relative to using the hub-height wind speed alone at both sites. However, in contrast to the CA site, the rotor equivalent wind speed (REWS) performs almost as well as the entire profile at the OK site. Another difference is that at the CA site, adding wind veer as a predictor significantly improved the power prediction accuracy. The same was true for that site when air density was added to the model separately instead of using the standard air density adjustment. At the OK site, these additional variables result in no significant benefit for the prediction accuracy.« less

An evaluation of selected (Q)SARs/expert systems for predicting skin sensitisation potential.

PubMed

Fitzpatrick, J M; Roberts, D W; Patlewicz, G

2018-06-01

Predictive testing to characterise substances for their skin sensitisation potential has historically been based on animal models such as the Local Lymph Node Assay (LLNA) and the Guinea Pig Maximisation Test (GPMT). In recent years, EU regulations, have provided a strong incentive to develop non-animal alternatives, such as expert systems software. Here we selected three different types of expert systems: VEGA (statistical), Derek Nexus (knowledge-based) and TIMES-SS (hybrid), and evaluated their performance using two large sets of animal data: one set of 1249 substances from eChemportal and a second set of 515 substances from NICEATM. A model was considered successful at predicting skin sensitisation potential if it had at least the same balanced accuracy as the LLNA and the GPMT had in predicting the other outcomes, which ranged from 79% to 86%. We found that the highest balanced accuracy of any of the expert systems evaluated was 65% when making global predictions. For substances within the domain of TIMES-SS, however, balanced accuracies for the two datasets were found to be 79% and 82%. In those cases where a chemical was within the TIMES-SS domain, the TIMES-SS skin sensitisation hazard prediction had the same confidence as the result from LLNA or GPMT.

Operational improvements of long-term predicted ephemerides of the Tracking and Data Relay Satellites (TDRSs)

NASA Technical Reports Server (NTRS)

Kostoff, J. L.; Ward, D. T.; Cuevas, O. O.; Beckman, R. M.

1995-01-01

Tracking and Data Relay Satellite (TDRS) orbit determination and prediction are supported by the Flight Dynamics Facility (FDF) of the Goddard Space Flight Center (GSFC) Flight Dynamics Division (FDD). TDRS System (TDRSS)-user satellites require predicted TDRS ephemerides that are up to 10 weeks in length. Previously, long-term ephemerides generated by the FDF included predictions from the White Sands Complex (WSC), which plans and executes TDRS maneuvers. TDRSs typically have monthly stationkeeping maneuvers, and predicted postmaneuver state vectors are received from WSC up to a month in advance. This paper presents the results of an analysis performed in the FDF to investigate more accurate and economical long-term ephemerides for the TDRSs. As a result of this analysis, two new methods for generating long-term TDRS ephemeris predictions have been implemented by the FDF. The Center-of-Box (COB) method models a TDRS as fixed at the center of its stationkeeping box. Using this method, long-term ephemeris updates are made semiannually instead of weekly. The impulse method is used to model more maneuvers. The impulse method yields better short-term accuracy than the COB method, especially for larger stationkeeping boxes. The accuracy of the impulse method depends primarily on the accuracy of maneuver date forecasting.

3-D numerical simulations of earthquake ground motion in sedimentary basins: testing accuracy through stringent models

NASA Astrophysics Data System (ADS)

Chaljub, Emmanuel; Maufroy, Emeline; Moczo, Peter; Kristek, Jozef; Hollender, Fabrice; Bard, Pierre-Yves; Priolo, Enrico; Klin, Peter; de Martin, Florent; Zhang, Zhenguo; Zhang, Wei; Chen, Xiaofei

2015-04-01

Differences between 3-D numerical predictions of earthquake ground motion in the Mygdonian basin near Thessaloniki, Greece, led us to define four canonical stringent models derived from the complex realistic 3-D model of the Mygdonian basin. Sediments atop an elastic bedrock are modelled in the 1D-sharp and 1D-smooth models using three homogeneous layers and smooth velocity distribution, respectively. The 2D-sharp and 2D-smooth models are extensions of the 1-D models to an asymmetric sedimentary valley. In all cases, 3-D wavefields include strongly dispersive surface waves in the sediments. We compared simulations by the Fourier pseudo-spectral method (FPSM), the Legendre spectral-element method (SEM) and two formulations of the finite-difference method (FDM-S and FDM-C) up to 4 Hz. The accuracy of individual solutions and level of agreement between solutions vary with type of seismic waves and depend on the smoothness of the velocity model. The level of accuracy is high for the body waves in all solutions. However, it strongly depends on the discrete representation of the material interfaces (at which material parameters change discontinuously) for the surface waves in the sharp models. An improper discrete representation of the interfaces can cause inaccurate numerical modelling of surface waves. For all the numerical methods considered, except SEM with mesh of elements following the interfaces, a proper implementation of interfaces requires definition of an effective medium consistent with the interface boundary conditions. An orthorhombic effective medium is shown to significantly improve accuracy and preserve the computational efficiency of modelling. The conclusions drawn from the analysis of the results of the canonical cases greatly help to explain differences between numerical predictions of ground motion in realistic models of the Mygdonian basin. We recommend that any numerical method and code that is intended for numerical prediction of earthquake ground motion should be verified through stringent models that would make it possible to test the most important aspects of accuracy.

Remote sensing-based predictors improve distribution models of rare, early successional and broadleaf tree species in Utah

USGS Publications Warehouse

Zimmermann, N.E.; Edwards, T.C.; Moisen, Gretchen G.; Frescino, T.S.; Blackard, J.A.

2007-01-01

1. Compared to bioclimatic variables, remote sensing predictors are rarely used for predictive species modelling. When used, the predictors represent typically habitat classifications or filters rather than gradual spectral, surface or biophysical properties. Consequently, the full potential of remotely sensed predictors for modelling the spatial distribution of species remains unexplored. Here we analysed the partial contributions of remotely sensed and climatic predictor sets to explain and predict the distribution of 19 tree species in Utah. We also tested how these partial contributions were related to characteristics such as successional types or species traits. 2. We developed two spatial predictor sets of remotely sensed and topo-climatic variables to explain the distribution of tree species. We used variation partitioning techniques applied to generalized linear models to explore the combined and partial predictive powers of the two predictor sets. Non-parametric tests were used to explore the relationships between the partial model contributions of both predictor sets and species characteristics. 3. More than 60% of the variation explained by the models represented contributions by one of the two partial predictor sets alone, with topo-climatic variables outperforming the remotely sensed predictors. However, the partial models derived from only remotely sensed predictors still provided high model accuracies, indicating a significant correlation between climate and remote sensing variables. The overall accuracy of the models was high, but small sample sizes had a strong effect on cross-validated accuracies for rare species. 4. Models of early successional and broadleaf species benefited significantly more from adding remotely sensed predictors than did late seral and needleleaf species. The core-satellite species types differed significantly with respect to overall model accuracies. Models of satellite and urban species, both with low prevalence, benefited more from use of remotely sensed predictors than did the more frequent core species. 5. Synthesis and applications. If carefully prepared, remotely sensed variables are useful additional predictors for the spatial distribution of trees. Major improvements resulted for deciduous, early successional, satellite and rare species. The ability to improve model accuracy for species having markedly different life history strategies is a crucial step for assessing effects of global change. ?? 2007 The Authors.

Remote sensing-based predictors improve distribution models of rare, early successional and broadleaf tree species in Utah

PubMed Central

ZIMMERMANN, N E; EDWARDS, T C; MOISEN, G G; FRESCINO, T S; BLACKARD, J A

2007-01-01

Compared to bioclimatic variables, remote sensing predictors are rarely used for predictive species modelling. When used, the predictors represent typically habitat classifications or filters rather than gradual spectral, surface or biophysical properties. Consequently, the full potential of remotely sensed predictors for modelling the spatial distribution of species remains unexplored. Here we analysed the partial contributions of remotely sensed and climatic predictor sets to explain and predict the distribution of 19 tree species in Utah. We also tested how these partial contributions were related to characteristics such as successional types or species traits. We developed two spatial predictor sets of remotely sensed and topo-climatic variables to explain the distribution of tree species. We used variation partitioning techniques applied to generalized linear models to explore the combined and partial predictive powers of the two predictor sets. Non-parametric tests were used to explore the relationships between the partial model contributions of both predictor sets and species characteristics. More than 60% of the variation explained by the models represented contributions by one of the two partial predictor sets alone, with topo-climatic variables outperforming the remotely sensed predictors. However, the partial models derived from only remotely sensed predictors still provided high model accuracies, indicating a significant correlation between climate and remote sensing variables. The overall accuracy of the models was high, but small sample sizes had a strong effect on cross-validated accuracies for rare species. Models of early successional and broadleaf species benefited significantly more from adding remotely sensed predictors than did late seral and needleleaf species. The core-satellite species types differed significantly with respect to overall model accuracies. Models of satellite and urban species, both with low prevalence, benefited more from use of remotely sensed predictors than did the more frequent core species. Synthesis and applications. If carefully prepared, remotely sensed variables are useful additional predictors for the spatial distribution of trees. Major improvements resulted for deciduous, early successional, satellite and rare species. The ability to improve model accuracy for species having markedly different life history strategies is a crucial step for assessing effects of global change. PMID:18642470

The Theory and Practice of Estimating the Accuracy of Dynamic Flight-Determined Coefficients

NASA Technical Reports Server (NTRS)

Maine, R. E.; Iliff, K. W.

1981-01-01

Means of assessing the accuracy of maximum likelihood parameter estimates obtained from dynamic flight data are discussed. The most commonly used analytical predictors of accuracy are derived and compared from both statistical and simplified geometrics standpoints. The accuracy predictions are evaluated with real and simulated data, with an emphasis on practical considerations, such as modeling error. Improved computations of the Cramer-Rao bound to correct large discrepancies due to colored noise and modeling error are presented. The corrected Cramer-Rao bound is shown to be the best available analytical predictor of accuracy, and several practical examples of the use of the Cramer-Rao bound are given. Engineering judgement, aided by such analytical tools, is the final arbiter of accuracy estimation.

Cognitive Models of Risky Choice: Parameter Stability and Predictive Accuracy of Prospect Theory

ERIC Educational Resources Information Center

Glockner, Andreas; Pachur, Thorsten

2012-01-01

In the behavioral sciences, a popular approach to describe and predict behavior is cognitive modeling with adjustable parameters (i.e., which can be fitted to data). Modeling with adjustable parameters allows, among other things, measuring differences between people. At the same time, parameter estimation also bears the risk of overfitting. Are…

Predictive Models of target organ and Systemic toxicities (BOSC)

EPA Science Inventory

The objective of this work is to predict the hazard classification and point of departure (PoD) of untested chemicals in repeat-dose animal testing studies. We used supervised machine learning to objectively evaluate the predictive accuracy of different classification and regress...

A comparison between Bayes discriminant analysis and logistic regression for prediction of debris flow in southwest Sichuan, China

NASA Astrophysics Data System (ADS)

Xu, Wenbo; Jing, Shaocai; Yu, Wenjuan; Wang, Zhaoxian; Zhang, Guoping; Huang, Jianxi

2013-11-01

In this study, the high risk areas of Sichuan Province with debris flow, Panzhihua and Liangshan Yi Autonomous Prefecture, were taken as the studied areas. By using rainfall and environmental factors as the predictors and based on the different prior probability combinations of debris flows, the prediction of debris flows was compared in the areas with statistical methods: logistic regression (LR) and Bayes discriminant analysis (BDA). The results through the comprehensive analysis show that (a) with the mid-range scale prior probability, the overall predicting accuracy of BDA is higher than those of LR; (b) with equal and extreme prior probabilities, the overall predicting accuracy of LR is higher than those of BDA; (c) the regional predicting models of debris flows with rainfall factors only have worse performance than those introduced environmental factors, and the predicting accuracies of occurrence and nonoccurrence of debris flows have been changed in the opposite direction as the supplemented information.

Predicting the chance of vaginal delivery after one cesarean section: validation and elaboration of a published prediction model.

PubMed

Fagerberg, Marie C; Maršál, Karel; Källén, Karin

2015-05-01

We aimed to validate a widely used US prediction model for vaginal birth after cesarean (Grobman et al. [8]) and modify it to suit Swedish conditions. Women having experienced one cesarean section and at least one subsequent delivery (n=49,472) in the Swedish Medical Birth Registry 1992-2011 were randomly divided into two data sets. In the development data set, variables associated with successful trial of labor were identified using multiple logistic regression. The predictive ability of the estimates previously published by Grobman et al., and of our modified and new estimates, respectively, was then evaluated using the validation data set. The accuracy of the models for prediction of vaginal birth after cesarean was measured by area under the receiver operating characteristics curve. For maternal age, body mass index, prior vaginal delivery, and prior labor arrest, the odds ratio estimates for vaginal birth after cesarean were similar to those previously published. The prediction accuracy increased when information on indication for the previous cesarean section was added (from area under the receiver operating characteristics curve=0.69-0.71), and increased further when maternal height and delivery unit cesarean section rates were included (area under the receiver operating characteristics curve=0.74). The correlation between the individual predicted vaginal birth after cesarean probability and the observed trial of labor success rate was high in all the respective predicted probability decentiles. Customization of prediction models for vaginal birth after cesarean is of considerable value. Choosing relevant indicators for a Swedish setting made it possible to achieve excellent prediction accuracy for success in trial of labor after cesarean. During the delicate process of counseling about preferred delivery mode after one cesarean section, considering the results of our study may facilitate the choice between a trial of labor or an elective repeat cesarean section. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Prediction of the spectral reflectance of laser-generated color prints by combination of an optical model and learning methods.

PubMed

Nébouy, David; Hébert, Mathieu; Fournel, Thierry; Larina, Nina; Lesur, Jean-Luc

2015-09-01

Recent color printing technologies based on the principle of revealing colors on pre-functionalized achromatic supports by laser irradiation offer advanced functionalities, especially for security applications. However, for such technologies, the color prediction is challenging, compared to classic ink-transfer printing systems. The spectral properties of the coloring materials modified by the lasers are not precisely known and may strongly vary, depending on the laser settings, in a nonlinear manner. We show in this study, through the example of the color laser marking (CLM) technology, based on laser bleaching of a mixture of pigments, that the combination of an adapted optical reflectance model and learning methods to get the model's parameters enables prediction of the spectral reflectance of any printable color with rather good accuracy. Even though the pigment mixture is formulated from three colored pigments, an analysis of the dimensionality of the spectral space generated by CLM printing, thanks to a principal component analysis decomposition, shows that at least four spectral primaries are needed for accurate spectral reflectance predictions. A polynomial interpolation is then used to relate RGB laser intensities with virtual coordinates of new basis vectors. By studying the influence of the number of calibration patches on the prediction accuracy, we can conclude that a reasonable number of 130 patches are enough to achieve good accuracy in this application.

Decoding the Traumatic Memory among Women with PTSD: Implications for Neurocircuitry Models of PTSD and Real-Time fMRI Neurofeedback

PubMed Central

Cisler, Josh M.; Bush, Keith; James, G. Andrew; Smitherman, Sonet; Kilts, Clinton D.

2015-01-01

Posttraumatic Stress Disorder (PTSD) is characterized by intrusive recall of the traumatic memory. While numerous studies have investigated the neural processing mechanisms engaged during trauma memory recall in PTSD, these analyses have only focused on group-level contrasts that reveal little about the predictive validity of the identified brain regions. By contrast, a multivariate pattern analysis (MVPA) approach towards identifying the neural mechanisms engaged during trauma memory recall would entail testing whether a multivariate set of brain regions is reliably predictive of (i.e., discriminates) whether an individual is engaging in trauma or non-trauma memory recall. Here, we use a MVPA approach to test 1) whether trauma memory vs neutral memory recall can be predicted reliably using a multivariate set of brain regions among women with PTSD related to assaultive violence exposure (N=16), 2) the methodological parameters (e.g., spatial smoothing, number of memory recall repetitions, etc.) that optimize classification accuracy and reproducibility of the feature weight spatial maps, and 3) the correspondence between brain regions that discriminate trauma memory recall and the brain regions predicted by neurocircuitry models of PTSD. Cross-validation classification accuracy was significantly above chance for all methodological permutations tested; mean accuracy across participants was 76% for the methodological parameters selected as optimal for both efficiency and accuracy. Classification accuracy was significantly better for a voxel-wise approach relative to voxels within restricted regions-of-interest (ROIs); classification accuracy did not differ when using PTSD-related ROIs compared to randomly generated ROIs. ROI-based analyses suggested the reliable involvement of the left hippocampus in discriminating memory recall across participants and that the contribution of the left amygdala to the decision function was dependent upon PTSD symptom severity. These results have methodological implications for real-time fMRI neurofeedback of the trauma memory in PTSD and conceptual implications for neurocircuitry models of PTSD that attempt to explain core neural processing mechanisms mediating PTSD. PMID:26241958

Decoding the Traumatic Memory among Women with PTSD: Implications for Neurocircuitry Models of PTSD and Real-Time fMRI Neurofeedback.

PubMed

Cisler, Josh M; Bush, Keith; James, G Andrew; Smitherman, Sonet; Kilts, Clinton D

2015-01-01

Posttraumatic Stress Disorder (PTSD) is characterized by intrusive recall of the traumatic memory. While numerous studies have investigated the neural processing mechanisms engaged during trauma memory recall in PTSD, these analyses have only focused on group-level contrasts that reveal little about the predictive validity of the identified brain regions. By contrast, a multivariate pattern analysis (MVPA) approach towards identifying the neural mechanisms engaged during trauma memory recall would entail testing whether a multivariate set of brain regions is reliably predictive of (i.e., discriminates) whether an individual is engaging in trauma or non-trauma memory recall. Here, we use a MVPA approach to test 1) whether trauma memory vs neutral memory recall can be predicted reliably using a multivariate set of brain regions among women with PTSD related to assaultive violence exposure (N=16), 2) the methodological parameters (e.g., spatial smoothing, number of memory recall repetitions, etc.) that optimize classification accuracy and reproducibility of the feature weight spatial maps, and 3) the correspondence between brain regions that discriminate trauma memory recall and the brain regions predicted by neurocircuitry models of PTSD. Cross-validation classification accuracy was significantly above chance for all methodological permutations tested; mean accuracy across participants was 76% for the methodological parameters selected as optimal for both efficiency and accuracy. Classification accuracy was significantly better for a voxel-wise approach relative to voxels within restricted regions-of-interest (ROIs); classification accuracy did not differ when using PTSD-related ROIs compared to randomly generated ROIs. ROI-based analyses suggested the reliable involvement of the left hippocampus in discriminating memory recall across participants and that the contribution of the left amygdala to the decision function was dependent upon PTSD symptom severity. These results have methodological implications for real-time fMRI neurofeedback of the trauma memory in PTSD and conceptual implications for neurocircuitry models of PTSD that attempt to explain core neural processing mechanisms mediating PTSD.

The effect of stimulus strength on the speed and accuracy of a perceptual decision.

PubMed

Palmer, John; Huk, Alexander C; Shadlen, Michael N

2005-05-02

Both the speed and the accuracy of a perceptual judgment depend on the strength of the sensory stimulation. When stimulus strength is high, accuracy is high and response time is fast; when stimulus strength is low, accuracy is low and response time is slow. Although the psychometric function is well established as a tool for analyzing the relationship between accuracy and stimulus strength, the corresponding chronometric function for the relationship between response time and stimulus strength has not received as much consideration. In this article, we describe a theory of perceptual decision making based on a diffusion model. In it, a decision is based on the additive accumulation of sensory evidence over time to a bound. Combined with simple scaling assumptions, the proportional-rate and power-rate diffusion models predict simple analytic expressions for both the chronometric and psychometric functions. In a series of psychophysical experiments, we show that this theory accounts for response time and accuracy as a function of both stimulus strength and speed-accuracy instructions. In particular, the results demonstrate a close coupling between response time and accuracy. The theory is also shown to subsume the predictions of Piéron's Law, a power function dependence of response time on stimulus strength. The theory's analytic chronometric function allows one to extend theories of accuracy to response time.

Estimation of the monthly average daily solar radiation using geographic information system and advanced case-based reasoning.

PubMed

Koo, Choongwan; Hong, Taehoon; Lee, Minhyun; Park, Hyo Seon

2013-05-07

The photovoltaic (PV) system is considered an unlimited source of clean energy, whose amount of electricity generation changes according to the monthly average daily solar radiation (MADSR). It is revealed that the MADSR distribution in South Korea has very diverse patterns due to the country's climatic and geographical characteristics. This study aimed to develop a MADSR estimation model for the location without the measured MADSR data, using an advanced case based reasoning (CBR) model, which is a hybrid methodology combining CBR with artificial neural network, multiregression analysis, and genetic algorithm. The average prediction accuracy of the advanced CBR model was very high at 95.69%, and the standard deviation of the prediction accuracy was 3.67%, showing a significant improvement in prediction accuracy and consistency. A case study was conducted to verify the proposed model. The proposed model could be useful for owner or construction manager in charge of determining whether or not to introduce the PV system and where to install it. Also, it would benefit contractors in a competitive bidding process to accurately estimate the electricity generation of the PV system in advance and to conduct an economic and environmental feasibility study from the life cycle perspective.

Comparative decision models for anticipating shortage of food grain production in India

NASA Astrophysics Data System (ADS)

Chattopadhyay, Manojit; Mitra, Subrata Kumar

2018-01-01

This paper attempts to predict food shortages in advance from the analysis of rainfall during the monsoon months along with other inputs used for crop production, such as land used for cereal production, percentage of area covered under irrigation and fertiliser use. We used six binary classification data mining models viz., logistic regression, Multilayer Perceptron, kernel lab-Support Vector Machines, linear discriminant analysis, quadratic discriminant analysis and k-Nearest Neighbors Network, and found that linear discriminant analysis and kernel lab-Support Vector Machines are equally suitable for predicting per capita food shortage with 89.69 % accuracy in overall prediction and 92.06 % accuracy in predicting food shortage ( true negative rate). Advance information of food shortage can help policy makers to take remedial measures in order to prevent devastating consequences arising out of food non-availability.

Diagnostic accuracy of APRI and FIB-4 for predicting hepatitis B virus-related liver fibrosis accompanied with hepatocellular carcinoma.

PubMed

Xiao, Guangqin; Zhu, Feng; Wang, Min; Zhang, Hang; Ye, Dawei; Yang, Jiayin; Jiang, Li; Liu, Chang; Yan, Lunan; Qin, Renyi

2016-10-01

Aspartate aminotransferase to platelet ratio index (APRI) and the fibrosis index based on four factors (FIB-4) are the two most focused non-invasive models to assess liver fibrosis. We aimed to examine the validity of these two models for predicting hepatitis B virus (HBV)-related liver fibrosis accompanied with hepatocellular carcinoma (HCC). We enrolled HBV-infected patients with liver cancer who had received hepatectomy. The accuracy of APRI and FIB-4 for diagnosing liver fibrosis was assessed based on their sensitivity, specificity, diagnostic efficiency, positive predictive value (PPV), negative predictive value (NPV), kappa (κ) value and area under the receiver-operating characteristic curve (AUC). Finally 2176 patients were included, with 1682 retrospective subjects and 494 prospective subjects. APRI (rs=0.310) and FIB-4 (rs=0.278) were positively correlated with liver fibrosis. And χ(2) analysis demonstrated that APRI and FIB-4 values correlated with different levels of liver fibrosis with all P values less than 0.01. The AUC values for APRI and FIB-4 were 0.685 and 0.626 (P=0.73) for predicting significant fibrosis, 0.681 and 0.648 (P=0.81) for differentiation of advanced fibrosis and 0.676 and 0.652 (P=0.77) for diagnosing cirrhosis. APRI and FIB-4 correlate with liver fibrosis. However these two models have low accuracy for predicting HBV-related liver fibrosis in HCC patients. Copyright © 2016. Published by Elsevier Ltd.

Development of an aerobic capacity prediction model from one-mile run/walk performance in adolescents aged 13-16 years.

PubMed

Burns, Ryan D; Hannon, James C; Brusseau, Timothy A; Eisenman, Patricia A; Shultz, Barry B; Saint-Maurice, Pedro F; Welk, Gregory J; Mahar, Matthew T

2016-01-01

A popular algorithm to predict VO2Peak from the one-mile run/walk test (1MRW) includes body mass index (BMI), which manifests practical issues in school settings. The purpose of this study was to develop an aerobic capacity model from 1MRW in adolescents independent of BMI. Cardiorespiratory endurance data were collected on 90 adolescents aged 13-16 years. The 1MRW was administered on an outside track and a laboratory VO2Peak test was conducted using a maximal treadmill protocol. Multiple linear regression was employed to develop the prediction model. Results yielded the following algorithm: VO2Peak = 7.34 × (1MRW speed in m s(-1)) + 0.23 × (age × sex) + 17.75. The New Model displayed a multiple correlation and prediction error of R = 0.81, standard error of the estimate = 4.78 ml kg(-1) · min(-1), with measured VO2Peak and good criterion-referenced (CR) agreement into FITNESSGRAM's Healthy Fitness Zone (Kappa = 0.62; percentage agreement = 84.4%; Φ = 0.62). The New Model was validated using k-fold cross-validation and showed homoscedastic residuals across the range of predicted scores. The omission of BMI did not compromise accuracy of the model. In conclusion, the New Model displayed good predictive accuracy and good CR agreement with measured VO2Peak in adolescents aged 13-16 years.

Pan-Arctic modelling of net ecosystem exchange of CO2

PubMed Central

Shaver, G. R.; Rastetter, E. B.; Salmon, V.; Street, L. E.; van de Weg, M. J.; Rocha, A.; van Wijk, M. T.; Williams, M.

2013-01-01

Net ecosystem exchange (NEE) of C varies greatly among Arctic ecosystems. Here, we show that approximately 75 per cent of this variation can be accounted for in a single regression model that predicts NEE as a function of leaf area index (LAI), air temperature and photosynthetically active radiation (PAR). The model was developed in concert with a survey of the light response of NEE in Arctic and subarctic tundras in Alaska, Greenland, Svalbard and Sweden. Model parametrizations based on data collected in one part of the Arctic can be used to predict NEE in other parts of the Arctic with accuracy similar to that of predictions based on data collected in the same site where NEE is predicted. The principal requirement for the dataset is that it should contain a sufficiently wide range of measurements of NEE at both high and low values of LAI, air temperature and PAR, to properly constrain the estimates of model parameters. Canopy N content can also be substituted for leaf area in predicting NEE, with equal or greater accuracy, but substitution of soil temperature for air temperature does not improve predictions. Overall, the results suggest a remarkable convergence in regulation of NEE in diverse ecosystem types throughout the Arctic. PMID:23836790

CS-AMPPred: An Updated SVM Model for Antimicrobial Activity Prediction in Cysteine-Stabilized Peptides

PubMed Central

Porto, William F.; Pires, Állan S.; Franco, Octavio L.

2012-01-01

The antimicrobial peptides (AMP) have been proposed as an alternative to control resistant pathogens. However, due to multifunctional properties of several AMP classes, until now there has been no way to perform efficient AMP identification, except through in vitro and in vivo tests. Nevertheless, an indication of activity can be provided by prediction methods. In order to contribute to the AMP prediction field, the CS-AMPPred (Cysteine-Stabilized Antimicrobial Peptides Predictor) is presented here, consisting of an updated version of the Support Vector Machine (SVM) model for antimicrobial activity prediction in cysteine-stabilized peptides. The CS-AMPPred is based on five sequence descriptors: indexes of (i) α-helix and (ii) loop formation; and averages of (iii) net charge, (iv) hydrophobicity and (v) flexibility. CS-AMPPred was based on 310 cysteine-stabilized AMPs and 310 sequences extracted from PDB. The polynomial kernel achieves the best accuracy on 5-fold cross validation (85.81%), while the radial and linear kernels achieve 84.19%. Testing in a blind data set, the polynomial and radial kernels achieve an accuracy of 90.00%, while the linear model achieves 89.33%. The three models reach higher accuracies than previously described methods. A standalone version of CS-AMPPred is available for download at and runs on any Linux machine. PMID:23240023

Accuracy of genomic prediction using deregressed breeding values estimated from purebred and crossbred offspring phenotypes in pigs.

PubMed

Hidalgo, A M; Bastiaansen, J W M; Lopes, M S; Veroneze, R; Groenen, M A M; de Koning, D-J

2015-07-01

Genomic selection is applied to dairy cattle breeding to improve the genetic progress of purebred (PB) animals, whereas in pigs and poultry the target is a crossbred (CB) animal for which a different strategy appears to be needed. The source of information used to estimate the breeding values, i.e., using phenotypes of CB or PB animals, may affect the accuracy of prediction. The objective of our study was to assess the direct genomic value (DGV) accuracy of CB and PB pigs using different sources of phenotypic information. Data used were from 3 populations: 2,078 Dutch Landrace-based, 2,301 Large White-based, and 497 crossbreds from an F1 cross between the 2 lines. Two female reproduction traits were analyzed: gestation length (GLE) and total number of piglets born (TNB). Phenotypes used in the analyses originated from offspring of genotyped individuals. Phenotypes collected on CB and PB animals were analyzed as separate traits using a single-trait model. Breeding values were estimated separately for each trait in a pedigree BLUP analysis and subsequently deregressed. Deregressed EBV for each trait originating from different sources (CB or PB offspring) were used to study the accuracy of genomic prediction. Accuracy of prediction was computed as the correlation between DGV and the DEBV of the validation population. Accuracy of prediction within PB populations ranged from 0.43 to 0.62 across GLE and TNB. Accuracies to predict genetic merit of CB animals with one PB population in the training set ranged from 0.12 to 0.28, with the exception of using the CB offspring phenotype of the Dutch Landrace that resulted in an accuracy estimate around 0 for both traits. Accuracies to predict genetic merit of CB animals with both parental PB populations in the training set ranged from 0.17 to 0.30. We conclude that prediction within population and trait had good predictive ability regardless of the trait being the PB or CB performance, whereas using PB population(s) to predict genetic merit of CB animals had zero to moderate predictive ability. We observed that the DGV accuracy of CB animals when training on PB data was greater than or equal to training on CB data. However, when results are corrected for the different levels of reliabilities in the PB and CB training data, we showed that training on CB data does outperform PB data for the prediction of CB genetic merit, indicating that more CB animals should be phenotyped to increase the reliability and, consequently, accuracy of DGV for CB genetic merit.

Accuracy and equivalence testing of crown ratio models and assessment of their impact on diameter growth and basal area increment predictions of two variants of the Forest Vegetation Simulator

Treesearch

Laura P. Leites; Andrew P. Robinson; Nicholas L. Crookston

2009-01-01

Diameter growth (DG) equations in many existing forest growth and yield models use tree crown ratio (CR) as a predictor variable. Where CR is not measured, it is estimated from other measured variables. We evaluated CR estimation accuracy for the models in two Forest Vegetation Simulator variants: the exponential and the logistic CR models used in the North...

Analysis of precision and accuracy in a simple model of machine learning

NASA Astrophysics Data System (ADS)

Lee, Julian

2017-12-01

Machine learning is a procedure where a model for the world is constructed from a training set of examples. It is important that the model should capture relevant features of the training set, and at the same time make correct prediction for examples not included in the training set. I consider the polynomial regression, the simplest method of learning, and analyze the accuracy and precision for different levels of the model complexity.

Basic Diagnosis and Prediction of Persistent Contrail Occurrence using High-resolution Numerical Weather Analyses/Forecasts and Logistic Regression. Part I: Effects of Random Error

NASA Technical Reports Server (NTRS)

Duda, David P.; Minnis, Patrick

2009-01-01

Straightforward application of the Schmidt-Appleman contrail formation criteria to diagnose persistent contrail occurrence from numerical weather prediction data is hindered by significant bias errors in the upper tropospheric humidity. Logistic models of contrail occurrence have been proposed to overcome this problem, but basic questions remain about how random measurement error may affect their accuracy. A set of 5000 synthetic contrail observations is created to study the effects of random error in these probabilistic models. The simulated observations are based on distributions of temperature, humidity, and vertical velocity derived from Advanced Regional Prediction System (ARPS) weather analyses. The logistic models created from the simulated observations were evaluated using two common statistical measures of model accuracy, the percent correct (PC) and the Hanssen-Kuipers discriminant (HKD). To convert the probabilistic results of the logistic models into a dichotomous yes/no choice suitable for the statistical measures, two critical probability thresholds are considered. The HKD scores are higher when the climatological frequency of contrail occurrence is used as the critical threshold, while the PC scores are higher when the critical probability threshold is 0.5. For both thresholds, typical random errors in temperature, relative humidity, and vertical velocity are found to be small enough to allow for accurate logistic models of contrail occurrence. The accuracy of the models developed from synthetic data is over 85 percent for both the prediction of contrail occurrence and non-occurrence, although in practice, larger errors would be anticipated.

Predicting watershed post-fire sediment yield with the InVEST sediment retention model: Accuracy and uncertainties

USGS Publications Warehouse

Sankey, Joel B.; McVay, Jason C.; Kreitler, Jason R.; Hawbaker, Todd J.; Vaillant, Nicole; Lowe, Scott

2015-01-01

Increased sedimentation following wildland fire can negatively impact water supply and water quality. Understanding how changing fire frequency, extent, and location will affect watersheds and the ecosystem services they supply to communities is of great societal importance in the western USA and throughout the world. In this work we assess the utility of the InVEST (Integrated Valuation of Ecosystem Services and Tradeoffs) Sediment Retention Model to accurately characterize erosion and sedimentation of burned watersheds. InVEST was developed by the Natural Capital Project at Stanford University (Tallis et al., 2014) and is a suite of GIS-based implementations of common process models, engineered for high-end computing to allow the faster simulation of larger landscapes and incorporation into decision-making. The InVEST Sediment Retention Model is based on common soil erosion models (e.g., USLE – Universal Soil Loss Equation) and determines which areas of the landscape contribute the greatest sediment loads to a hydrological network and conversely evaluate the ecosystem service of sediment retention on a watershed basis. In this study, we evaluate the accuracy and uncertainties for InVEST predictions of increased sedimentation after fire, using measured postfire sediment yields available for many watersheds throughout the western USA from an existing, published large database. We show that the model can be parameterized in a relatively simple fashion to predict post-fire sediment yield with accuracy. Our ultimate goal is to use the model to accurately predict variability in post-fire sediment yield at a watershed scale as a function of future wildfire conditions.

Assessing the prediction accuracy of cure in the Cox proportional hazards cure model: an application to breast cancer data.

PubMed

Asano, Junichi; Hirakawa, Akihiro; Hamada, Chikuma

2014-01-01

A cure rate model is a survival model incorporating the cure rate with the assumption that the population contains both uncured and cured individuals. It is a powerful statistical tool for prognostic studies, especially in cancer. The cure rate is important for making treatment decisions in clinical practice. The proportional hazards (PH) cure model can predict the cure rate for each patient. This contains a logistic regression component for the cure rate and a Cox regression component to estimate the hazard for uncured patients. A measure for quantifying the predictive accuracy of the cure rate estimated by the Cox PH cure model is required, as there has been a lack of previous research in this area. We used the Cox PH cure model for the breast cancer data; however, the area under the receiver operating characteristic curve (AUC) could not be estimated because many patients were censored. In this study, we used imputation-based AUCs to assess the predictive accuracy of the cure rate from the PH cure model. We examined the precision of these AUCs using simulation studies. The results demonstrated that the imputation-based AUCs were estimable and their biases were negligibly small in many cases, although ordinary AUC could not be estimated. Additionally, we introduced the bias-correction method of imputation-based AUCs and found that the bias-corrected estimate successfully compensated the overestimation in the simulation studies. We also illustrated the estimation of the imputation-based AUCs using breast cancer data. Copyright © 2014 John Wiley & Sons, Ltd.

Comparison of the Mortality Probability Admission Model III, National Quality Forum, and Acute Physiology and Chronic Health Evaluation IV hospital mortality models: implications for national benchmarking*.

PubMed

Kramer, Andrew A; Higgins, Thomas L; Zimmerman, Jack E

2014-03-01

To examine the accuracy of the original Mortality Probability Admission Model III, ICU Outcomes Model/National Quality Forum modification of Mortality Probability Admission Model III, and Acute Physiology and Chronic Health Evaluation IVa models for comparing observed and risk-adjusted hospital mortality predictions. Retrospective paired analyses of day 1 hospital mortality predictions using three prognostic models. Fifty-five ICUs at 38 U.S. hospitals from January 2008 to December 2012. Among 174,001 intensive care admissions, 109,926 met model inclusion criteria and 55,304 had data for mortality prediction using all three models. None. We compared patient exclusions and the discrimination, calibration, and accuracy for each model. Acute Physiology and Chronic Health Evaluation IVa excluded 10.7% of all patients, ICU Outcomes Model/National Quality Forum 20.1%, and Mortality Probability Admission Model III 24.1%. Discrimination of Acute Physiology and Chronic Health Evaluation IVa was superior with area under receiver operating curve (0.88) compared with Mortality Probability Admission Model III (0.81) and ICU Outcomes Model/National Quality Forum (0.80). Acute Physiology and Chronic Health Evaluation IVa was better calibrated (lowest Hosmer-Lemeshow statistic). The accuracy of Acute Physiology and Chronic Health Evaluation IVa was superior (adjusted Brier score = 31.0%) to that for Mortality Probability Admission Model III (16.1%) and ICU Outcomes Model/National Quality Forum (17.8%). Compared with observed mortality, Acute Physiology and Chronic Health Evaluation IVa overpredicted mortality by 1.5% and Mortality Probability Admission Model III by 3.1%; ICU Outcomes Model/National Quality Forum underpredicted mortality by 1.2%. Calibration curves showed that Acute Physiology and Chronic Health Evaluation performed well over the entire risk range, unlike the Mortality Probability Admission Model and ICU Outcomes Model/National Quality Forum models. Acute Physiology and Chronic Health Evaluation IVa had better accuracy within patient subgroups and for specific admission diagnoses. Acute Physiology and Chronic Health Evaluation IVa offered the best discrimination and calibration on a large common dataset and excluded fewer patients than Mortality Probability Admission Model III or ICU Outcomes Model/National Quality Forum. The choice of ICU performance benchmarks should be based on a comparison of model accuracy using data for identical patients.

Development and validation of classifiers and variable subsets for predicting nursing home admission.

PubMed

Nuutinen, Mikko; Leskelä, Riikka-Leena; Suojalehto, Ella; Tirronen, Anniina; Komssi, Vesa

2017-04-13

In previous years a substantial number of studies have identified statistically important predictors of nursing home admission (NHA). However, as far as we know, the analyses have been done at the population-level. No prior research has analysed the prediction accuracy of a NHA model for individuals. This study is an analysis of 3056 longer-term home care customers in the city of Tampere, Finland. Data were collected from the records of social and health service usage and RAI-HC (Resident Assessment Instrument - Home Care) assessment system during January 2011 and September 2015. The aim was to find out the most efficient variable subsets to predict NHA for individuals and validate the accuracy. The variable subsets of predicting NHA were searched by sequential forward selection (SFS) method, a variable ranking metric and the classifiers of logistic regression (LR), support vector machine (SVM) and Gaussian naive Bayes (GNB). The validation of the results was guaranteed using randomly balanced data sets and cross-validation. The primary performance metrics for the classifiers were the prediction accuracy and AUC (average area under the curve). The LR and GNB classifiers achieved 78% accuracy for predicting NHA. The most important variables were RAI MAPLE (Method for Assigning Priority Levels), functional impairment (RAI IADL, Activities of Daily Living), cognitive impairment (RAI CPS, Cognitive Performance Scale), memory disorders (diagnoses G30-G32 and F00-F03) and the use of community-based health-service and prior hospital use (emergency visits and periods of care). The accuracy of the classifier for individuals was high enough to convince the officials of the city of Tampere to integrate the predictive model based on the findings of this study as a part of home care information system. Further work need to be done to evaluate variables that are modifiable and responsive to interventions.

Prediction of stock markets by the evolutionary mix-game model

NASA Astrophysics Data System (ADS)

Chen, Fang; Gou, Chengling; Guo, Xiaoqian; Gao, Jieping

2008-06-01

This paper presents the efforts of using the evolutionary mix-game model, which is a modified form of the agent-based mix-game model, to predict financial time series. Here, we have carried out three methods to improve the original mix-game model by adding the abilities of strategy evolution to agents, and then applying the new model referred to as the evolutionary mix-game model to forecast the Shanghai Stock Exchange Composite Index. The results show that these modifications can improve the accuracy of prediction greatly when proper parameters are chosen.

Patterns and predictors of skin score change in early diffuse systemic sclerosis from the European Scleroderma Observational Study

PubMed Central

Herrick, Ariane L; Peytrignet, Sebastien; Lunt, Mark; Pan, Xiaoyan; Hesselstrand, Roger; Mouthon, Luc; Silman, Alan J; Dinsdale, Graham; Brown, Edith; Czirják, László; Distler, Jörg H W; Distler, Oliver; Fligelstone, Kim; Gregory, William J; Ochiel, Rachel; Vonk, Madelon C; Ancuţa, Codrina; Ong, Voon H; Farge, Dominique; Hudson, Marie; Matucci-Cerinic, Marco; Balbir-Gurman, Alexandra; Midtvedt, Øyvind; Jobanputra, Paresh; Jordan, Alison C; Stevens, Wendy; Moinzadeh, Pia; Hall, Frances C; Agard, Christian; Anderson, Marina E; Diot, Elisabeth; Madhok, Rajan; Akil, Mohammed; Buch, Maya H; Chung, Lorinda; Damjanov, Nemanja S; Gunawardena, Harsha; Lanyon, Peter; Ahmad, Yasmeen; Chakravarty, Kuntal; Jacobsen, Søren; MacGregor, Alexander J; McHugh, Neil; Müller-Ladner, Ulf; Riemekasten, Gabriela; Becker, Michael; Roddy, Janet; Carreira, Patricia E; Fauchais, Anne Laure; Hachulla, Eric; Hamilton, Jennifer; İnanç, Murat; McLaren, John S; van Laar, Jacob M; Pathare, Sanjay; Proudman, Susanna M; Rudin, Anna; Sahhar, Joanne; Coppere, Brigitte; Serratrice, Christine; Sheeran, Tom; Veale, Douglas J; Grange, Claire; Trad, Georges-Selim; Denton, Christopher P

2018-01-01

Objectives Our aim was to use the opportunity provided by the European Scleroderma Observational Study to (1) identify and describe those patients with early diffuse cutaneous systemic sclerosis (dcSSc) with progressive skin thickness, and (2) derive prediction models for progression over 12 months, to inform future randomised controlled trials (RCTs). Methods The modified Rodnan skin score (mRSS) was recorded every 3 months in 326 patients. ‘Progressors’ were defined as those experiencing a 5-unit and 25% increase in mRSS score over 12 months (±3 months). Logistic models were fitted to predict progression and, using receiver operating characteristic (ROC) curves, were compared on the basis of the area under curve (AUC), accuracy and positive predictive value (PPV). Results 66 patients (22.5%) progressed, 227 (77.5%) did not (33 could not have their status assessed due to insufficient data). Progressors had shorter disease duration (median 8.1 vs 12.6 months, P=0.001) and lower mRSS (median 19 vs 21 units, P=0.030) than non-progressors. Skin score was highest, and peaked earliest, in the anti-RNA polymerase III (Pol3+) subgroup (n=50). A first predictive model (including mRSS, duration of skin thickening and their interaction) had an accuracy of 60.9%, AUC of 0.666 and PPV of 33.8%. By adding a variable for Pol3 positivity, the model reached an accuracy of 71%, AUC of 0.711 and PPV of 41%. Conclusions Two prediction models for progressive skin thickening were derived, for use both in clinical practice and for cohort enrichment in RCTs. These models will inform recruitment into the many clinical trials of dcSSc projected for the coming years. Trial registration number NCT02339441. PMID:29306872

Reduced Fragment Diversity for Alpha and Alpha-Beta Protein Structure Prediction using Rosetta.

PubMed

Abbass, Jad; Nebel, Jean-Christophe

2017-01-01

Protein structure prediction is considered a main challenge in computational biology. The biannual international competition, Critical Assessment of protein Structure Prediction (CASP), has shown in its eleventh experiment that free modelling target predictions are still beyond reliable accuracy, therefore, much effort should be made to improve ab initio methods. Arguably, Rosetta is considered as the most competitive method when it comes to targets with no homologues. Relying on fragments of length 9 and 3 from known structures, Rosetta creates putative structures by assembling candidate fragments. Generally, the structure with the lowest energy score, also known as first model, is chosen to be the "predicted one". A thorough study has been conducted on the role and diversity of 3-mers involved in Rosetta's model "refinement" phase. Usage of the standard number of 3-mers - i.e. 200 - has been shown to degrade alpha and alpha-beta protein conformations initially achieved by assembling 9-mers. Therefore, a new prediction pipeline is proposed for Rosetta where the "refinement" phase is customised according to a target's structural class prediction. Over 8% improvement in terms of first model structure accuracy is reported for alpha and alpha-beta classes when decreasing the number of 3- mers. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

An evaluation of the predictive performance of distributional models for flora and fauna in north-east New South Wales.

PubMed

Pearce, J; Ferrier, S; Scotts, D

2001-06-01

To use models of species distributions effectively in conservation planning, it is important to determine the predictive accuracy of such models. Extensive modelling of the distribution of vascular plant and vertebrate fauna species within north-east New South Wales has been undertaken by linking field survey data to environmental and geographical predictors using logistic regression. These models have been used in the development of a comprehensive and adequate reserve system within the region. We evaluate the predictive accuracy of models for 153 small reptile, arboreal marsupial, diurnal bird and vascular plant species for which independent evaluation data were available. The predictive performance of each model was evaluated using the relative operating characteristic curve to measure discrimination capacity. Good discrimination ability implies that a model's predictions provide an acceptable index of species occurrence. The discrimination capacity of 89% of the models was significantly better than random, with 70% of the models providing high levels of discrimination. Predictions generated by this type of modelling therefore provide a reasonably sound basis for regional conservation planning. The discrimination ability of models was highest for the less mobile biological groups, particularly the vascular plants and small reptiles. In the case of diurnal birds, poor performing models tended to be for species which occur mainly within specific habitats not well sampled by either the model development or evaluation data, highly mobile species, species that are locally nomadic or those that display very broad habitat requirements. Particular care needs to be exercised when employing models for these types of species in conservation planning.

A Mechanism-Based Model for the Prediction of the Metabolic Sites of Steroids Mediated by Cytochrome P450 3A4.

PubMed

Dai, Zi-Ru; Ai, Chun-Zhi; Ge, Guang-Bo; He, Yu-Qi; Wu, Jing-Jing; Wang, Jia-Yue; Man, Hui-Zi; Jia, Yan; Yang, Ling

2015-06-30

Early prediction of xenobiotic metabolism is essential for drug discovery and development. As the most important human drug-metabolizing enzyme, cytochrome P450 3A4 has a large active cavity and metabolizes a broad spectrum of substrates. The poor substrate specificity of CYP3A4 makes it a huge challenge to predict the metabolic site(s) on its substrates. This study aimed to develop a mechanism-based prediction model based on two key parameters, including the binding conformation and the reaction activity of ligands, which could reveal the process of real metabolic reaction(s) and the site(s) of modification. The newly established model was applied to predict the metabolic site(s) of steroids; a class of CYP3A4-preferred substrates. 38 steroids and 12 non-steroids were randomly divided into training and test sets. Two major metabolic reactions, including aliphatic hydroxylation and N-dealkylation, were involved in this study. At least one of the top three predicted metabolic sites was validated by the experimental data. The overall accuracy for the training and test were 82.14% and 86.36%, respectively. In summary, a mechanism-based prediction model was established for the first time, which could be used to predict the metabolic site(s) of CYP3A4 on steroids with high predictive accuracy.

Novel applications of multitask learning and multiple output regression to multiple genetic trait prediction.

PubMed

He, Dan; Kuhn, David; Parida, Laxmi

2016-06-15

Given a set of biallelic molecular markers, such as SNPs, with genotype values encoded numerically on a collection of plant, animal or human samples, the goal of genetic trait prediction is to predict the quantitative trait values by simultaneously modeling all marker effects. Genetic trait prediction is usually represented as linear regression models. In many cases, for the same set of samples and markers, multiple traits are observed. Some of these traits might be correlated with each other. Therefore, modeling all the multiple traits together may improve the prediction accuracy. In this work, we view the multitrait prediction problem from a machine learning angle: as either a multitask learning problem or a multiple output regression problem, depending on whether different traits share the same genotype matrix or not. We then adapted multitask learning algorithms and multiple output regression algorithms to solve the multitrait prediction problem. We proposed a few strategies to improve the least square error of the prediction from these algorithms. Our experiments show that modeling multiple traits together could improve the prediction accuracy for correlated traits. The programs we used are either public or directly from the referred authors, such as MALSAR (http://www.public.asu.edu/~jye02/Software/MALSAR/) package. The Avocado data set has not been published yet and is available upon request. dhe@us.ibm.com. © The Author 2016. Published by Oxford University Press.

Dynamic filtering improves attentional state prediction with fNIRS

PubMed Central

Harrivel, Angela R.; Weissman, Daniel H.; Noll, Douglas C.; Huppert, Theodore; Peltier, Scott J.

2016-01-01

Brain activity can predict a person’s level of engagement in an attentional task. However, estimates of brain activity are often confounded by measurement artifacts and systemic physiological noise. The optimal method for filtering this noise – thereby increasing such state prediction accuracy – remains unclear. To investigate this, we asked study participants to perform an attentional task while we monitored their brain activity with functional near infrared spectroscopy (fNIRS). We observed higher state prediction accuracy when noise in the fNIRS hemoglobin [Hb] signals was filtered with a non-stationary (adaptive) model as compared to static regression (84% ± 6% versus 72% ± 15%). PMID:27231602

Assessing participation in community-based physical activity programs in Brazil.

PubMed

Reis, Rodrigo S; Yan, Yan; Parra, Diana C; Brownson, Ross C

2014-01-01

This study aimed to develop and validate a risk prediction model to examine the characteristics that are associated with participation in community-based physical activity programs in Brazil. We used pooled data from three surveys conducted from 2007 to 2009 in state capitals of Brazil with 6166 adults. A risk prediction model was built considering program participation as an outcome. The predictive accuracy of the model was quantified through discrimination (C statistic) and calibration (Brier score) properties. Bootstrapping methods were used to validate the predictive accuracy of the final model. The final model showed sex (women: odds ratio [OR] = 3.18, 95% confidence interval [CI] = 2.14-4.71), having less than high school degree (OR = 1.71, 95% CI = 1.16-2.53), reporting a good health (OR = 1.58, 95% CI = 1.02-2.24) or very good/excellent health (OR = 1.62, 95% CI = 1.05-2.51), having any comorbidity (OR = 1.74, 95% CI = 1.26-2.39), and perceiving the environment as safe to walk at night (OR = 1.59, 95% CI = 1.18-2.15) as predictors of participation in physical activity programs. Accuracy indices were adequate (C index = 0.778, Brier score = 0.031) and similar to those obtained from bootstrapping (C index = 0.792, Brier score = 0.030). Sociodemographic and health characteristics as well as perceptions of the environment are strong predictors of participation in community-based programs in selected cities of Brazil.

Mental models accurately predict emotion transitions

PubMed Central

Thornton, Mark A.; Tamir, Diana I.

2017-01-01

Successful social interactions depend on people’s ability to predict others’ future actions and emotions. People possess many mechanisms for perceiving others’ current emotional states, but how might they use this information to predict others’ future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others’ emotional dynamics. People could then use these mental models of emotion transitions to predict others’ future emotions from currently observable emotions. To test this hypothesis, studies 1–3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants’ ratings of emotion transitions predicted others’ experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation—valence, social impact, rationality, and human mind—inform participants’ mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants’ accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone. PMID:28533373

Simpler score of routine laboratory tests predicts liver fibrosis in patients with chronic hepatitis B.

PubMed

Zhou, Kun; Gao, Chun-Fang; Zhao, Yun-Peng; Liu, Hai-Lin; Zheng, Rui-Dan; Xian, Jian-Chun; Xu, Hong-Tao; Mao, Yi-Min; Zeng, Min-De; Lu, Lun-Gen

2010-09-01

In recent years, a great interest has been dedicated to the development of noninvasive predictive models to substitute liver biopsy for fibrosis assessment and follow-up. Our aim was to provide a simpler model consisting of routine laboratory markers for predicting liver fibrosis in patients chronically infected with hepatitis B virus (HBV) in order to optimize their clinical management. Liver fibrosis was staged in 386 chronic HBV carriers who underwent liver biopsy and routine laboratory testing. Correlations between routine laboratory markers and fibrosis stage were statistically assessed. After logistic regression analysis, a novel predictive model was constructed. This S index was validated in an independent cohort of 146 chronic HBV carriers in comparison to the SLFG model, Fibrometer, Hepascore, Hui model, Forns score and APRI using receiver operating characteristic (ROC) curves. The diagnostic values of each marker panels were better than single routine laboratory markers. The S index consisting of gamma-glutamyltransferase (GGT), platelets (PLT) and albumin (ALB) (S-index: 1000 x GGT/(PLT x ALB(2))) had a higher diagnostic accuracy in predicting degree of fibrosis than any other mathematical model tested. The areas under the ROC curves (AUROC) were 0.812 and 0.890 for predicting significant fibrosis and cirrhosis in the validation cohort, respectively. The S index, a simpler mathematical model consisting of routine laboratory markers predicts significant fibrosis and cirrhosis in patients with chronic HBV infection with a high degree of accuracy, potentially decreasing the need for liver biopsy.

Clustering-based classification of road traffic accidents using hierarchical clustering and artificial neural networks.

PubMed

Taamneh, Madhar; Taamneh, Salah; Alkheder, Sharaf

2017-09-01

Artificial neural networks (ANNs) have been widely used in predicting the severity of road traffic crashes. All available information about previously occurred accidents is typically used for building a single prediction model (i.e., classifier). Too little attention has been paid to the differences between these accidents, leading, in most cases, to build less accurate predictors. Hierarchical clustering is a well-known clustering method that seeks to group data by creating a hierarchy of clusters. Using hierarchical clustering and ANNs, a clustering-based classification approach for predicting the injury severity of road traffic accidents was proposed. About 6000 road accidents occurred over a six-year period from 2008 to 2013 in Abu Dhabi were used throughout this study. In order to reduce the amount of variation in data, hierarchical clustering was applied on the data set to organize it into six different forms, each with different number of clusters (i.e., clusters from 1 to 6). Two ANN models were subsequently built for each cluster of accidents in each generated form. The first model was built and validated using all accidents (training set), whereas only 66% of the accidents were used to build the second model, and the remaining 34% were used to test it (percentage split). Finally, the weighted average accuracy was computed for each type of models in each from of data. The results show that when testing the models using the training set, clustering prior to classification achieves (11%-16%) more accuracy than without using clustering, while the percentage split achieves (2%-5%) more accuracy. The results also suggest that partitioning the accidents into six clusters achieves the best accuracy if both types of models are taken into account.

Examining speed versus selection in connectivity models using elk migration as an example

USGS Publications Warehouse

Brennan, Angela; Hanks, Ephraim M.; Merkle, Jerod A.; Cole, Eric K.; Dewey, Sarah R.; Courtemanch, Alyson B.; Cross, Paul C.

2018-01-01

ContextLandscape resistance is vital to connectivity modeling and frequently derived from resource selection functions (RSFs). RSFs estimate relative probability of use and tend to focus on understanding habitat preferences during slow, routine animal movements (e.g., foraging). Dispersal and migration, however, can produce rarer, faster movements, in which case models of movement speed rather than resource selection may be more realistic for identifying habitats that facilitate connectivity.ObjectiveTo compare two connectivity modeling approaches applied to resistance estimated from models of movement rate and resource selection.MethodsUsing movement data from migrating elk, we evaluated continuous time Markov chain (CTMC) and movement-based RSF models (i.e., step selection functions [SSFs]). We applied circuit theory and shortest random path (SRP) algorithms to CTMC, SSF and null (i.e., flat) resistance surfaces to predict corridors between elk seasonal ranges. We evaluated prediction accuracy by comparing model predictions to empirical elk movements.ResultsAll connectivity models predicted elk movements well, but models applied to CTMC resistance were more accurate than models applied to SSF and null resistance. Circuit theory models were more accurate on average than SRP models.ConclusionsCTMC can be more realistic than SSFs for estimating resistance for fast movements, though SSFs may demonstrate some predictive ability when animals also move slowly through corridors (e.g., stopover use during migration). High null model accuracy suggests seasonal range data may also be critical for predicting direct migration routes. For animals that migrate or disperse across large landscapes, we recommend incorporating CTMC into the connectivity modeling toolkit.

Machine learning methods reveal the temporal pattern of dengue incidence using meteorological factors in metropolitan Manila, Philippines.

PubMed

Carvajal, Thaddeus M; Viacrusis, Katherine M; Hernandez, Lara Fides T; Ho, Howell T; Amalin, Divina M; Watanabe, Kozo

2018-04-17

Several studies have applied ecological factors such as meteorological variables to develop models and accurately predict the temporal pattern of dengue incidence or occurrence. With the vast amount of studies that investigated this premise, the modeling approaches differ from each study and only use a single statistical technique. It raises the question of whether which technique would be robust and reliable. Hence, our study aims to compare the predictive accuracy of the temporal pattern of Dengue incidence in Metropolitan Manila as influenced by meteorological factors from four modeling techniques, (a) General Additive Modeling, (b) Seasonal Autoregressive Integrated Moving Average with exogenous variables (c) Random Forest and (d) Gradient Boosting. Dengue incidence and meteorological data (flood, precipitation, temperature, southern oscillation index, relative humidity, wind speed and direction) of Metropolitan Manila from January 1, 2009 - December 31, 2013 were obtained from respective government agencies. Two types of datasets were used in the analysis; observed meteorological factors (MF) and its corresponding delayed or lagged effect (LG). After which, these datasets were subjected to the four modeling techniques. The predictive accuracy and variable importance of each modeling technique were calculated and evaluated. Among the statistical modeling techniques, Random Forest showed the best predictive accuracy. Moreover, the delayed or lag effects of the meteorological variables was shown to be the best dataset to use for such purpose. Thus, the model of Random Forest with delayed meteorological effects (RF-LG) was deemed the best among all assessed models. Relative humidity was shown to be the top-most important meteorological factor in the best model. The study exhibited that there are indeed different predictive outcomes generated from each statistical modeling technique and it further revealed that the Random forest model with delayed meteorological effects to be the best in predicting the temporal pattern of Dengue incidence in Metropolitan Manila. It is also noteworthy that the study also identified relative humidity as an important meteorological factor along with rainfall and temperature that can influence this temporal pattern.

Modeling Soil Organic Carbon at Regional Scale by Combining Multi-Spectral Images with Laboratory Spectra.

PubMed

Peng, Yi; Xiong, Xiong; Adhikari, Kabindra; Knadel, Maria; Grunwald, Sabine; Greve, Mogens Humlekrog

2015-01-01

There is a great challenge in combining soil proximal spectra and remote sensing spectra to improve the accuracy of soil organic carbon (SOC) models. This is primarily because mixing of spectral data from different sources and technologies to improve soil models is still in its infancy. The first objective of this study was to integrate information of SOC derived from visible near-infrared reflectance (Vis-NIR) spectra in the laboratory with remote sensing (RS) images to improve predictions of topsoil SOC in the Skjern river catchment, Denmark. The second objective was to improve SOC prediction results by separately modeling uplands and wetlands. A total of 328 topsoil samples were collected and analyzed for SOC. Satellite Pour l'Observation de la Terre (SPOT5), Landsat Data Continuity Mission (Landsat 8) images, laboratory Vis-NIR and other ancillary environmental data including terrain parameters and soil maps were compiled to predict topsoil SOC using Cubist regression and Bayesian kriging. The results showed that the model developed from RS data, ancillary environmental data and laboratory spectral data yielded a lower root mean square error (RMSE) (2.8%) and higher R2 (0.59) than the model developed from only RS data and ancillary environmental data (RMSE: 3.6%, R2: 0.46). Plant-available water (PAW) was the most important predictor for all the models because of its close relationship with soil organic matter content. Moreover, vegetation indices, such as the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), were very important predictors in SOC spatial models. Furthermore, the 'upland model' was able to more accurately predict SOC compared with the 'upland & wetland model'. However, the separately calibrated 'upland and wetland model' did not improve the prediction accuracy for wetland sites, since it was not possible to adequately discriminate the vegetation in the RS summer images. We conclude that laboratory Vis-NIR spectroscopy adds critical information that significantly improves the prediction accuracy of SOC compared to using RS data alone. We recommend the incorporation of laboratory spectra with RS data and other environmental data to improve soil spatial modeling and digital soil mapping (DSM).

Evaluation of anthropogenic influence in probabilistic forecasting of coastal change

NASA Astrophysics Data System (ADS)

Hapke, C. J.; Wilson, K.; Adams, P. N.

2014-12-01

Prediction of large scale coastal behavior is especially challenging in areas of pervasive human activity. Many coastal zones on the Gulf and Atlantic coasts are moderately to highly modified through the use of soft sediment and hard stabilization techniques. These practices have the potential to alter sediment transport and availability, as well as reshape the beach profile, ultimately transforming the natural evolution of the coastal system. We present the results of a series of probabilistic models, designed to predict the observed geomorphic response to high wave events at Fire Island, New York. The island comprises a variety of land use types, including inhabited communities with modified beaches, where beach nourishment and artificial dune construction (scraping) occur, unmodified zones, and protected national seashore. This variation in land use presents an opportunity for comparison of model accuracy across highly modified and rarely modified stretches of coastline. Eight models with basic and expanded structures were developed, resulting in sixteen models, informed with observational data from Fire Island. The basic model type does not include anthropogenic modification. The expanded model includes records of nourishment and scraping, designed to quantify the improved accuracy when anthropogenic activity is represented. Modification was included as frequency of occurrence divided by the time since the most recent event, to distinguish between recent and historic events. All but one model reported improved predictive accuracy from the basic to expanded form. The addition of nourishment and scraping parameters resulted in a maximum reduction in predictive error of 36%. The seven improved models reported an average 23% reduction in error. These results indicate that it is advantageous to incorporate the human forcing into a coastal hazards probability model framework.

THE SYSTEMATICS OF STRONG LENS MODELING QUANTIFIED: THE EFFECTS OF CONSTRAINT SELECTION AND REDSHIFT INFORMATION ON MAGNIFICATION, MASS, AND MULTIPLE IMAGE PREDICTABILITY

DOE Office of Scientific and Technical Information (OSTI.GOV)

Johnson, Traci L.; Sharon, Keren, E-mail: tljohn@umich.edu

Until now, systematic errors in strong gravitational lens modeling have been acknowledged but have never been fully quantified. Here, we launch an investigation into the systematics induced by constraint selection. We model the simulated cluster Ares 362 times using random selections of image systems with and without spectroscopic redshifts and quantify the systematics using several diagnostics: image predictability, accuracy of model-predicted redshifts, enclosed mass, and magnification. We find that for models with >15 image systems, the image plane rms does not decrease significantly when more systems are added; however, the rms values quoted in the literature may be misleading asmore » to the ability of a model to predict new multiple images. The mass is well constrained near the Einstein radius in all cases, and systematic error drops to <2% for models using >10 image systems. Magnification errors are smallest along the straight portions of the critical curve, and the value of the magnification is systematically lower near curved portions. For >15 systems, the systematic error on magnification is ∼2%. We report no trend in magnification error with the fraction of spectroscopic image systems when selecting constraints at random; however, when using the same selection of constraints, increasing this fraction up to ∼0.5 will increase model accuracy. The results suggest that the selection of constraints, rather than quantity alone, determines the accuracy of the magnification. We note that spectroscopic follow-up of at least a few image systems is crucial because models without any spectroscopic redshifts are inaccurate across all of our diagnostics.« less

Predicting High Imaging Utilization Based on Initial Radiology Reports: A Feasibility Study of Machine Learning.

PubMed

Hassanpour, Saeed; Langlotz, Curtis P

2016-01-01

Imaging utilization has significantly increased over the last two decades, and is only recently showing signs of moderating. To help healthcare providers identify patients at risk for high imaging utilization, we developed a prediction model to recognize high imaging utilizers based on their initial imaging reports. The prediction model uses a machine learning text classification framework. In this study, we used radiology reports from 18,384 patients with at least one abdomen computed tomography study in their imaging record at Stanford Health Care as the training set. We modeled the radiology reports in a vector space and trained a support vector machine classifier for this prediction task. We evaluated our model on a separate test set of 4791 patients. In addition to high prediction accuracy, in our method, we aimed at achieving high specificity to identify patients at high risk for high imaging utilization. Our results (accuracy: 94.0%, sensitivity: 74.4%, specificity: 97.9%, positive predictive value: 87.3%, negative predictive value: 95.1%) show that a prediction model can enable healthcare providers to identify in advance patients who are likely to be high utilizers of imaging services. Machine learning classifiers developed from narrative radiology reports are feasible methods to predict imaging utilization. Such systems can be used to identify high utilizers, inform future image ordering behavior, and encourage judicious use of imaging. Copyright © 2016 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

STRUM: structure-based prediction of protein stability changes upon single-point mutation.

PubMed

Quan, Lijun; Lv, Qiang; Zhang, Yang

2016-10-01

Mutations in human genome are mainly through single nucleotide polymorphism, some of which can affect stability and function of proteins, causing human diseases. Several methods have been proposed to predict the effect of mutations on protein stability; but most require features from experimental structure. Given the fast progress in protein structure prediction, this work explores the possibility to improve the mutation-induced stability change prediction using low-resolution structure modeling. We developed a new method (STRUM) for predicting stability change caused by single-point mutations. Starting from wild-type sequences, 3D models are constructed by the iterative threading assembly refinement (I-TASSER) simulations, where physics- and knowledge-based energy functions are derived on the I-TASSER models and used to train STRUM models through gradient boosting regression. STRUM was assessed by 5-fold cross validation on 3421 experimentally determined mutations from 150 proteins. The Pearson correlation coefficient (PCC) between predicted and measured changes of Gibbs free-energy gap, ΔΔG, upon mutation reaches 0.79 with a root-mean-square error 1.2 kcal/mol in the mutation-based cross-validations. The PCC reduces if separating training and test mutations from non-homologous proteins, which reflects inherent correlations in the current mutation sample. Nevertheless, the results significantly outperform other state-of-the-art methods, including those built on experimental protein structures. Detailed analyses show that the most sensitive features in STRUM are the physics-based energy terms on I-TASSER models and the conservation scores from multiple-threading template alignments. However, the ΔΔG prediction accuracy has only a marginal dependence on the accuracy of protein structure models as long as the global fold is correct. These data demonstrate the feasibility to use low-resolution structure modeling for high-accuracy stability change prediction upon point mutations. http://zhanglab.ccmb.med.umich.edu/STRUM/ CONTACT: qiang@suda.edu.cn and zhng@umich.edu Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

STRUM: structure-based prediction of protein stability changes upon single-point mutation

PubMed Central

Quan, Lijun; Lv, Qiang; Zhang, Yang

2016-01-01

Motivation: Mutations in human genome are mainly through single nucleotide polymorphism, some of which can affect stability and function of proteins, causing human diseases. Several methods have been proposed to predict the effect of mutations on protein stability; but most require features from experimental structure. Given the fast progress in protein structure prediction, this work explores the possibility to improve the mutation-induced stability change prediction using low-resolution structure modeling. Results: We developed a new method (STRUM) for predicting stability change caused by single-point mutations. Starting from wild-type sequences, 3D models are constructed by the iterative threading assembly refinement (I-TASSER) simulations, where physics- and knowledge-based energy functions are derived on the I-TASSER models and used to train STRUM models through gradient boosting regression. STRUM was assessed by 5-fold cross validation on 3421 experimentally determined mutations from 150 proteins. The Pearson correlation coefficient (PCC) between predicted and measured changes of Gibbs free-energy gap, ΔΔG, upon mutation reaches 0.79 with a root-mean-square error 1.2 kcal/mol in the mutation-based cross-validations. The PCC reduces if separating training and test mutations from non-homologous proteins, which reflects inherent correlations in the current mutation sample. Nevertheless, the results significantly outperform other state-of-the-art methods, including those built on experimental protein structures. Detailed analyses show that the most sensitive features in STRUM are the physics-based energy terms on I-TASSER models and the conservation scores from multiple-threading template alignments. However, the ΔΔG prediction accuracy has only a marginal dependence on the accuracy of protein structure models as long as the global fold is correct. These data demonstrate the feasibility to use low-resolution structure modeling for high-accuracy stability change prediction upon point mutations. Availability and Implementation: http://zhanglab.ccmb.med.umich.edu/STRUM/ Contact: qiang@suda.edu.cn and zhng@umich.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27318206

An Analysis on the Constitutive Models for Forging of Ti6Al4V Alloy Considering the Softening Behavior

NASA Astrophysics Data System (ADS)

Souza, Paul M.; Beladi, Hossein; Singh, Rajkumar P.; Hodgson, Peter D.; Rolfe, Bernard

2018-05-01

This paper developed high-temperature deformation constitutive models for a Ti6Al4V alloy using an empirical-based Arrhenius equation and an enhanced version of the authors' physical-based EM + Avrami equations. The initial microstructure was a partially equiaxed α + β grain structure. A wide range of experimental data was obtained from hot compression of the Ti6Al4 V alloy at deformation temperatures ranging from 720 to 970 °C, and at strain rates varying from 0.01 to 10 s-1. The friction- and adiabatic-corrected flow curves were used to identify the parameter values of the constitutive models. Both models provided good overall accuracy of the flow stress. The generalized modified Arrhenius model was better at predicting the flow stress at lower strain rates. However, the model was inaccurate in predicting the peak strain. In contrast, the enhanced physical-based EM + Avrami model revealed very good accuracy at intermediate and high strain rates, but it was also better at predicting the peak strain. Blind sample tests revealed that the EM + Avrami maintained good predictions on new (unseen) data. Thus, the enhanced EM + Avrami model may be preferred over the Arrhenius model to predict the flow behavior of Ti6Al4V alloy during industrial forgings, when the initial microstructure is partially equiaxed.

Bayesian spatiotemporal crash frequency models with mixture components for space-time interactions.

PubMed

Cheng, Wen; Gill, Gurdiljot Singh; Zhang, Yongping; Cao, Zhong

2018-03-01

The traffic safety research has developed spatiotemporal models to explore the variations in the spatial pattern of crash risk over time. Many studies observed notable benefits associated with the inclusion of spatial and temporal correlation and their interactions. However, the safety literature lacks sufficient research for the comparison of different temporal treatments and their interaction with spatial component. This study developed four spatiotemporal models with varying complexity due to the different temporal treatments such as (I) linear time trend; (II) quadratic time trend; (III) Autoregressive-1 (AR-1); and (IV) time adjacency. Moreover, the study introduced a flexible two-component mixture for the space-time interaction which allows greater flexibility compared to the traditional linear space-time interaction. The mixture component allows the accommodation of global space-time interaction as well as the departures from the overall spatial and temporal risk patterns. This study performed a comprehensive assessment of mixture models based on the diverse criteria pertaining to goodness-of-fit, cross-validation and evaluation based on in-sample data for predictive accuracy of crash estimates. The assessment of model performance in terms of goodness-of-fit clearly established the superiority of the time-adjacency specification which was evidently more complex due to the addition of information borrowed from neighboring years, but this addition of parameters allowed significant advantage at posterior deviance which subsequently benefited overall fit to crash data. The Base models were also developed to study the comparison between the proposed mixture and traditional space-time components for each temporal model. The mixture models consistently outperformed the corresponding Base models due to the advantages of much lower deviance. For cross-validation comparison of predictive accuracy, linear time trend model was adjudged the best as it recorded the highest value of log pseudo marginal likelihood (LPML). Four other evaluation criteria were considered for typical validation using the same data for model development. Under each criterion, observed crash counts were compared with three types of data containing Bayesian estimated, normal predicted, and model replicated ones. The linear model again performed the best in most scenarios except one case of using model replicated data and two cases involving prediction without including random effects. These phenomena indicated the mediocre performance of linear trend when random effects were excluded for evaluation. This might be due to the flexible mixture space-time interaction which can efficiently absorb the residual variability escaping from the predictable part of the model. The comparison of Base and mixture models in terms of prediction accuracy further bolstered the superiority of the mixture models as the mixture ones generated more precise estimated crash counts across all four models, suggesting that the advantages associated with mixture component at model fit were transferable to prediction accuracy. Finally, the residual analysis demonstrated the consistently superior performance of random effect models which validates the importance of incorporating the correlation structures to account for unobserved heterogeneity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Impact of QTL minor allele frequency on genomic evaluation using real genotype data and simulated phenotypes in Japanese Black cattle.

PubMed

Uemoto, Yoshinobu; Sasaki, Shinji; Kojima, Takatoshi; Sugimoto, Yoshikazu; Watanabe, Toshio

2015-11-19

Genetic variance that is not captured by single nucleotide polymorphisms (SNPs) is due to imperfect linkage disequilibrium (LD) between SNPs and quantitative trait loci (QTLs), and the extent of LD between SNPs and QTLs depends on different minor allele frequencies (MAF) between them. To evaluate the impact of MAF of QTLs on genomic evaluation, we performed a simulation study using real cattle genotype data. In total, 1368 Japanese Black cattle and 592,034 SNPs (Illumina BovineHD BeadChip) were used. We simulated phenotypes using real genotypes under different scenarios, varying the MAF categories, QTL heritability, number of QTLs, and distribution of QTL effect. After generating true breeding values and phenotypes, QTL heritability was estimated and the prediction accuracy of genomic estimated breeding value (GEBV) was assessed under different SNP densities, prediction models, and population size by a reference-test validation design. The extent of LD between SNPs and QTLs in this population was higher in the QTLs with high MAF than in those with low MAF. The effect of MAF of QTLs depended on the genetic architecture, evaluation strategy, and population size in genomic evaluation. In genetic architecture, genomic evaluation was affected by the MAF of QTLs combined with the QTL heritability and the distribution of QTL effect. The number of QTL was not affected on genomic evaluation if the number of QTL was more than 50. In the evaluation strategy, we showed that different SNP densities and prediction models affect the heritability estimation and genomic prediction and that this depends on the MAF of QTLs. In addition, accurate QTL heritability and GEBV were obtained using denser SNP information and the prediction model accounted for the SNPs with low and high MAFs. In population size, a large sample size is needed to increase the accuracy of GEBV. The MAF of QTL had an impact on heritability estimation and prediction accuracy. Most genetic variance can be captured using denser SNPs and the prediction model accounted for MAF, but a large sample size is needed to increase the accuracy of GEBV under all QTL MAF categories.

A Systematic Approach to Predicting Spring Force for Sagittal Craniosynostosis Surgery.

PubMed

Zhang, Guangming; Tan, Hua; Qian, Xiaohua; Zhang, Jian; Li, King; David, Lisa R; Zhou, Xiaobo

2016-05-01

Spring-assisted surgery (SAS) can effectively treat scaphocephaly by reshaping crania with the appropriate spring force. However, it is difficult to accurately estimate spring force without considering biomechanical properties of tissues. This study presents and validates a reliable system to accurately predict the spring force for sagittal craniosynostosis surgery. The authors randomly chose 23 patients who underwent SAS and had been followed for at least 2 years. An elastic model was designed to characterize the biomechanical behavior of calvarial bone tissue for each individual. After simulating the contact force on accurate position of the skull strip with the springs, the finite element method was applied to calculating the stress of each tissue node based on the elastic model. A support vector regression approach was then used to model the relationships between biomechanical properties generated from spring force, bone thickness, and the change of cephalic index after surgery. Therefore, for a new patient, the optimal spring force can be predicted based on the learned model with virtual spring simulation and dynamic programming approach prior to SAS. Leave-one-out cross-validation was implemented to assess the accuracy of our prediction. As a result, the mean prediction accuracy of this model was 93.35%, demonstrating the great potential of this model as a useful adjunct for preoperative planning tool.

Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model.

PubMed

Qiu, Mingyue; Song, Yu

2016-01-01

In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders' expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day's price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately.

Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model

PubMed Central

Qiu, Mingyue; Song, Yu

2016-01-01

In the business sector, it has always been a difficult task to predict the exact daily price of the stock market index; hence, there is a great deal of research being conducted regarding the prediction of the direction of stock price index movement. Many factors such as political events, general economic conditions, and traders’ expectations may have an influence on the stock market index. There are numerous research studies that use similar indicators to forecast the direction of the stock market index. In this study, we compare two basic types of input variables to predict the direction of the daily stock market index. The main contribution of this study is the ability to predict the direction of the next day’s price of the Japanese stock market index by using an optimized artificial neural network (ANN) model. To improve the prediction accuracy of the trend of the stock market index in the future, we optimize the ANN model using genetic algorithms (GA). We demonstrate and verify the predictability of stock price direction by using the hybrid GA-ANN model and then compare the performance with prior studies. Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately. PMID:27196055

Meta-analysis of diagnostic accuracy studies accounting for disease prevalence: alternative parameterizations and model selection.

PubMed

Chu, Haitao; Nie, Lei; Cole, Stephen R; Poole, Charles

2009-08-15

In a meta-analysis of diagnostic accuracy studies, the sensitivities and specificities of a diagnostic test may depend on the disease prevalence since the severity and definition of disease may differ from study to study due to the design and the population considered. In this paper, we extend the bivariate nonlinear random effects model on sensitivities and specificities to jointly model the disease prevalence, sensitivities and specificities using trivariate nonlinear random-effects models. Furthermore, as an alternative parameterization, we also propose jointly modeling the test prevalence and the predictive values, which reflect the clinical utility of a diagnostic test. These models allow investigators to study the complex relationship among the disease prevalence, sensitivities and specificities; or among test prevalence and the predictive values, which can reveal hidden information about test performance. We illustrate the proposed two approaches by reanalyzing the data from a meta-analysis of radiological evaluation of lymph node metastases in patients with cervical cancer and a simulation study. The latter illustrates the importance of carefully choosing an appropriate normality assumption for the disease prevalence, sensitivities and specificities, or the test prevalence and the predictive values. In practice, it is recommended to use model selection techniques to identify a best-fitting model for making statistical inference. In summary, the proposed trivariate random effects models are novel and can be very useful in practice for meta-analysis of diagnostic accuracy studies. Copyright 2009 John Wiley & Sons, Ltd.

Identifying a predictive model for response to atypical antipsychotic monotherapy treatment in south Indian schizophrenia patients.

PubMed

Gupta, Meenal; Moily, Nagaraj S; Kaur, Harpreet; Jajodia, Ajay; Jain, Sanjeev; Kukreti, Ritushree

2013-08-01

Atypical antipsychotic (AAP) drugs are the preferred choice of treatment for schizophrenia patients. Patients who do not show favorable response to AAP monotherapy are subjected to random prolonged therapeutic treatment with AAP multitherapy, typical antipsychotics or a combination of both. Therefore, prior identification of patients' response to drugs can be an important step in providing efficacious and safe therapeutic treatment. We thus attempted to elucidate a genetic signature which could predict patients' response to AAP monotherapy. Our logistic regression analyses indicated the probability that 76% patients carrying combination of four SNPs will not show favorable response to AAP therapy. The robustness of this prediction model was assessed using repeated 10-fold cross validation method, and the results across n-fold cross-validations (mean accuracy=71.91%; 95%CI=71.47-72.35) suggest high accuracy and reliability of the prediction model. Further validations of these results in large sample sets are likely to establish their clinical applicability. Copyright © 2013 Elsevier Inc. All rights reserved.

Examining speed versus selection in connectivity models using elk migration as an example

USGS Publications Warehouse

Brennan, Angela; Hanks, EM; Merkle, JA; Cole, EK; Dewey, SR; Courtemanch, AB; Cross, Paul C.

2018-01-01

Context: Landscape resistance is vital to connectivity modeling and frequently derived from resource selection functions (RSFs). RSFs estimate relative probability of use and tend to focus on understanding habitat preferences during slow, routine animal movements (e.g., foraging). Dispersal and migration, however, can produce rarer, faster movements, in which case models of movement speed rather than resource selection may be more realistic for identifying habitats that facilitate connectivity. Objective: To compare two connectivity modeling approaches applied to resistance estimated from models of movement rate and resource selection. Methods: Using movement data from migrating elk, we evaluated continuous time Markov chain (CTMC) and movement-based RSF models (i.e., step selection functions [SSFs]). We applied circuit theory and shortest random path (SRP) algorithms to CTMC, SSF and null (i.e., flat) resistance surfaces to predict corridors between elk seasonal ranges. We evaluated prediction accuracy by comparing model predictions to empirical elk movements. Results: All models predicted elk movements well, but models applied to CTMC resistance were more accurate than models applied to SSF and null resistance. Circuit theory models were more accurate on average than SRP algorithms. Conclusions: CTMC can be more realistic than SSFs for estimating resistance for fast movements, though SSFs may demonstrate some predictive ability when animals also move slowly through corridors (e.g., stopover use during migration). High null model accuracy suggests seasonal range data may also be critical for predicting direct migration routes. For animals that migrate or disperse across large landscapes, we recommend incorporating CTMC into the connectivity modeling toolkit.

Improving default risk prediction using Bayesian model uncertainty techniques.

PubMed

Kazemi, Reza; Mosleh, Ali

2012-11-01

Credit risk is the potential exposure of a creditor to an obligor's failure or refusal to repay the debt in principal or interest. The potential of exposure is measured in terms of probability of default. Many models have been developed to estimate credit risk, with rating agencies dating back to the 19th century. They provide their assessment of probability of default and transition probabilities of various firms in their annual reports. Regulatory capital requirements for credit risk outlined by the Basel Committee on Banking Supervision have made it essential for banks and financial institutions to develop sophisticated models in an attempt to measure credit risk with higher accuracy. The Bayesian framework proposed in this article uses the techniques developed in physical sciences and engineering for dealing with model uncertainty and expert accuracy to obtain improved estimates of credit risk and associated uncertainties. The approach uses estimates from one or more rating agencies and incorporates their historical accuracy (past performance data) in estimating future default risk and transition probabilities. Several examples demonstrate that the proposed methodology can assess default probability with accuracy exceeding the estimations of all the individual models. Moreover, the methodology accounts for potentially significant departures from "nominal predictions" due to "upsetting events" such as the 2008 global banking crisis. © 2012 Society for Risk Analysis.

Distress modeling for DARWin-ME : final report.

DOT National Transportation Integrated Search

2013-12-01

Distress prediction models, or transfer functions, are key components of the Pavement M-E Design and relevant analysis. The accuracy of such models depends on a successful process of calibration and subsequent validation of model coefficients in the ...

Prediction of high incidence of dengue in the Philippines.

PubMed

Buczak, Anna L; Baugher, Benjamin; Babin, Steven M; Ramac-Thomas, Liane C; Guven, Erhan; Elbert, Yevgeniy; Koshute, Phillip T; Velasco, John Mark S; Roque, Vito G; Tayag, Enrique A; Yoon, In-Kyu; Lewis, Sheri H

2014-04-01

Accurate prediction of dengue incidence levels weeks in advance of an outbreak may reduce the morbidity and mortality associated with this neglected disease. Therefore, models were developed to predict high and low dengue incidence in order to provide timely forewarnings in the Philippines. Model inputs were chosen based on studies indicating variables that may impact dengue incidence. The method first uses Fuzzy Association Rule Mining techniques to extract association rules from these historical epidemiological, environmental, and socio-economic data, as well as climate data indicating future weather patterns. Selection criteria were used to choose a subset of these rules for a classifier, thereby generating a Prediction Model. The models predicted high or low incidence of dengue in a Philippines province four weeks in advance. The threshold between high and low was determined relative to historical incidence data. Model accuracy is described by Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, and Specificity computed on test data not previously used to develop the model. Selecting a model using the F0.5 measure, which gives PPV more importance than Sensitivity, gave these results: PPV = 0.780, NPV = 0.938, Sensitivity = 0.547, Specificity = 0.978. Using the F3 measure, which gives Sensitivity more importance than PPV, the selected model had PPV = 0.778, NPV = 0.948, Sensitivity = 0.627, Specificity = 0.974. The decision as to which model has greater utility depends on how the predictions will be used in a particular situation. This method builds prediction models for future dengue incidence in the Philippines and is capable of being modified for use in different situations; for diseases other than dengue; and for regions beyond the Philippines. The Philippines dengue prediction models predicted high or low incidence of dengue four weeks in advance of an outbreak with high accuracy, as measured by PPV, NPV, Sensitivity, and Specificity.

Prediction of High Incidence of Dengue in the Philippines

PubMed Central

Buczak, Anna L.; Baugher, Benjamin; Babin, Steven M.; Ramac-Thomas, Liane C.; Guven, Erhan; Elbert, Yevgeniy; Koshute, Phillip T.; Velasco, John Mark S.; Roque, Vito G.; Tayag, Enrique A.; Yoon, In-Kyu; Lewis, Sheri H.

2014-01-01

Background Accurate prediction of dengue incidence levels weeks in advance of an outbreak may reduce the morbidity and mortality associated with this neglected disease. Therefore, models were developed to predict high and low dengue incidence in order to provide timely forewarnings in the Philippines. Methods Model inputs were chosen based on studies indicating variables that may impact dengue incidence. The method first uses Fuzzy Association Rule Mining techniques to extract association rules from these historical epidemiological, environmental, and socio-economic data, as well as climate data indicating future weather patterns. Selection criteria were used to choose a subset of these rules for a classifier, thereby generating a Prediction Model. The models predicted high or low incidence of dengue in a Philippines province four weeks in advance. The threshold between high and low was determined relative to historical incidence data. Principal Findings Model accuracy is described by Positive Predictive Value (PPV), Negative Predictive Value (NPV), Sensitivity, and Specificity computed on test data not previously used to develop the model. Selecting a model using the F0.5 measure, which gives PPV more importance than Sensitivity, gave these results: PPV = 0.780, NPV = 0.938, Sensitivity = 0.547, Specificity = 0.978. Using the F3 measure, which gives Sensitivity more importance than PPV, the selected model had PPV = 0.778, NPV = 0.948, Sensitivity = 0.627, Specificity = 0.974. The decision as to which model has greater utility depends on how the predictions will be used in a particular situation. Conclusions This method builds prediction models for future dengue incidence in the Philippines and is capable of being modified for use in different situations; for diseases other than dengue; and for regions beyond the Philippines. The Philippines dengue prediction models predicted high or low incidence of dengue four weeks in advance of an outbreak with high accuracy, as measured by PPV, NPV, Sensitivity, and Specificity. PMID:24722434

Sub-Model Partial Least Squares for Improved Accuracy in Quantitative Laser Induced Breakdown Spectroscopy

NASA Astrophysics Data System (ADS)

Anderson, R. B.; Clegg, S. M.; Frydenvang, J.

2015-12-01

One of the primary challenges faced by the ChemCam instrument on the Curiosity Mars rover is developing a regression model that can accurately predict the composition of the wide range of target types encountered (basalts, calcium sulfate, feldspar, oxides, etc.). The original calibration used 69 rock standards to train a partial least squares (PLS) model for each major element. By expanding the suite of calibration samples to >400 targets spanning a wider range of compositions, the accuracy of the model was improved, but some targets with "extreme" compositions (e.g. pure minerals) were still poorly predicted. We have therefore developed a simple method, referred to as "submodel PLS", to improve the performance of PLS across a wide range of target compositions. In addition to generating a "full" (0-100 wt.%) PLS model for the element of interest, we also generate several overlapping submodels (e.g. for SiO2, we generate "low" (0-50 wt.%), "mid" (30-70 wt.%), and "high" (60-100 wt.%) models). The submodels are generally more accurate than the "full" model for samples within their range because they are able to adjust for matrix effects that are specific to that range. To predict the composition of an unknown target, we first predict the composition with the submodels and the "full" model. Then, based on the predicted composition from the "full" model, the appropriate submodel prediction can be used (e.g. if the full model predicts a low composition, use the "low" model result, which is likely to be more accurate). For samples with "full" predictions that occur in a region of overlap between submodels, the submodel predictions are "blended" using a simple linear weighted sum. The submodel PLS method shows improvements in most of the major elements predicted by ChemCam and reduces the occurrence of negative predictions for low wt.% targets. Submodel PLS is currently being used in conjunction with ICA regression for the major element compositions of ChemCam data.

Precision assessment of some supervised and unsupervised algorithms for genotype discrimination in the genus Pisum using SSR molecular data.

PubMed

Nasiri, Jaber; Naghavi, Mohammad Reza; Kayvanjoo, Amir Hossein; Nasiri, Mojtaba; Ebrahimi, Mansour

2015-03-07

For the first time, prediction accuracies of some supervised and unsupervised algorithms were evaluated in an SSR-based DNA fingerprinting study of a pea collection containing 20 cultivars and 57 wild samples. In general, according to the 10 attribute weighting models, the SSR alleles of PEAPHTAP-2 and PSBLOX13.2-1 were the two most important attributes to generate discrimination among eight different species and subspecies of genus Pisum. In addition, K-Medoids unsupervised clustering run on Chi squared dataset exhibited the best prediction accuracy (83.12%), while the lowest accuracy (25.97%) gained as K-Means model ran on FCdb database. Irrespective of some fluctuations, the overall accuracies of tree induction models were significantly high for many algorithms, and the attributes PSBLOX13.2-3 and PEAPHTAP could successfully detach Pisum fulvum accessions and cultivars from the others when two selected decision trees were taken into account. Meanwhile, the other used supervised algorithms exhibited overall reliable accuracies, even though in some rare cases, they gave us low amounts of accuracies. Our results, altogether, demonstrate promising applications of both supervised and unsupervised algorithms to provide suitable data mining tools regarding accurate fingerprinting of different species and subspecies of genus Pisum, as a fundamental priority task in breeding programs of the crop. Copyright © 2015 Elsevier Ltd. All rights reserved.

Predicting outcomes in patients with perforated gastroduodenal ulcers: artificial neural network modelling indicates a highly complex disease.

PubMed

Søreide, K; Thorsen, K; Søreide, J A

2015-02-01

Mortality prediction models for patients with perforated peptic ulcer (PPU) have not yielded consistent or highly accurate results. Given the complex nature of this disease, which has many non-linear associations with outcomes, we explored artificial neural networks (ANNs) to predict the complex interactions between the risk factors of PPU and death among patients with this condition. ANN modelling using a standard feed-forward, back-propagation neural network with three layers (i.e., an input layer, a hidden layer and an output layer) was used to predict the 30-day mortality of consecutive patients from a population-based cohort undergoing surgery for PPU. A receiver-operating characteristic (ROC) analysis was used to assess model accuracy. Of the 172 patients, 168 had their data included in the model; the data of 117 (70%) were used for the training set, and the data of 51 (39%) were used for the test set. The accuracy, as evaluated by area under the ROC curve (AUC), was best for an inclusive, multifactorial ANN model (AUC 0.90, 95% CIs 0.85-0.95; p < 0.001). This model outperformed standard predictive scores, including Boey and PULP. The importance of each variable decreased as the number of factors included in the ANN model increased. The prediction of death was most accurate when using an ANN model with several univariate influences on the outcome. This finding demonstrates that PPU is a highly complex disease for which clinical prognoses are likely difficult. The incorporation of computerised learning systems might enhance clinical judgments to improve decision making and outcome prediction.

Development of Validated Computer-based Preoperative Predictive Model for Proximal Junction Failure (PJF) or Clinically Significant PJK With 86% Accuracy Based on 510 ASD Patients With 2-year Follow-up.

PubMed

Scheer, Justin K; Osorio, Joseph A; Smith, Justin S; Schwab, Frank; Lafage, Virginie; Hart, Robert A; Bess, Shay; Line, Breton; Diebo, Bassel G; Protopsaltis, Themistocles S; Jain, Amit; Ailon, Tamir; Burton, Douglas C; Shaffrey, Christopher I; Klineberg, Eric; Ames, Christopher P

2016-11-15

A retrospective review of large, multicenter adult spinal deformity (ASD) database. The aim of this study was to build a model based on baseline demographic, radiographic, and surgical factors that can predict clinically significant proximal junctional kyphosis (PJK) and proximal junctional failure (PJF). PJF and PJK are significant complications and it remains unclear what are the specific drivers behind the development of either. There exists no predictive model that could potentially aid in the clinical decision making for adult patients undergoing deformity correction. Inclusion criteria: age ≥18 years, ASD, at least four levels fused. Variables included in the model were demographics, primary/revision, use of three-column osteotomy, upper-most instrumented vertebra (UIV)/lower-most instrumented vertebra (LIV) levels and UIV implant type (screw, hooks), number of levels fused, and baseline sagittal radiographs [pelvic tilt (PT), pelvic incidence and lumbar lordosis (PI-LL), thoracic kyphosis (TK), and sagittal vertical axis (SVA)]. PJK was defined as an increase from baseline of proximal junctional angle ≥20° with concomitant deterioration of at least one SRS-Schwab sagittal modifier grade from 6 weeks postop. PJF was defined as requiring revision for PJK. An ensemble of decision trees were constructed using the C5.0 algorithm with five different bootstrapped models, and internally validated via a 70 : 30 data split for training and testing. Accuracy and the area under a receiver operator characteristic curve (AUC) were calculated. Five hundred ten patients were included, with 357 for model training and 153 as testing targets (PJF: 37, PJK: 102). The overall model accuracy was 86.3% with an AUC of 0.89 indicating a good model fit. The seven strongest (importance ≥0.95) predictors were age, LIV, pre-operative SVA, UIV implant type, UIV, pre-operative PT, and pre-operative PI-LL. A successful model (86% accuracy, 0.89 AUC) was built predicting either PJF or clinically significant PJK. This model can set the groundwork for preop point of care decision making, risk stratification, and need for prophylactic strategies for patients undergoing ASD surgery. 3.

A Probabilistic Strategy for Understanding Action Selection

PubMed Central

Kim, Byounghoon; Basso, Michele A.

2010-01-01

Brain regions involved in transforming sensory signals into movement commands are the likely sites where decisions are formed. Once formed, a decision must be read-out from the activity of populations of neurons to produce a choice of action. How this occurs remains unresolved. We recorded from four superior colliculus (SC) neurons simultaneously while monkeys performed a target selection task. We implemented three models to gain insight into the computational principles underlying population coding of action selection. We compared the population vector average (PVA), winner-takes-all (WTA) and a Bayesian model, maximum a posteriori estimate (MAP) to determine which predicted choices most often. The probabilistic model predicted more trials correctly than both the WTA and the PVA. The MAP model predicted 81.88% whereas WTA predicted 71.11% and PVA/OLE predicted the least number of trials at 55.71 and 69.47%. Recovering MAP estimates using simulated, non-uniform priors that correlated with monkeys’ choice performance, improved the accuracy of the model by 2.88%. A dynamic analysis revealed that the MAP estimate evolved over time and the posterior probability of the saccade choice reached a maximum at the time of the saccade. MAP estimates also scaled with choice performance accuracy. Although there was overlap in the prediction abilities of all the models, we conclude that movement choice from populations of neurons may be best understood by considering frameworks based on probability. PMID:20147560

A New Scheme to Characterize and Identify Protein Ubiquitination Sites.

PubMed

Nguyen, Van-Nui; Huang, Kai-Yao; Huang, Chien-Hsun; Lai, K Robert; Lee, Tzong-Yi

2017-01-01

Protein ubiquitination, involving the conjugation of ubiquitin on lysine residue, serves as an important modulator of many cellular functions in eukaryotes. Recent advancements in proteomic technology have stimulated increasing interest in identifying ubiquitination sites. However, most computational tools for predicting ubiquitination sites are focused on small-scale data. With an increasing number of experimentally verified ubiquitination sites, we were motivated to design a predictive model for identifying lysine ubiquitination sites for large-scale proteome dataset. This work assessed not only single features, such as amino acid composition (AAC), amino acid pair composition (AAPC) and evolutionary information, but also the effectiveness of incorporating two or more features into a hybrid approach to model construction. The support vector machine (SVM) was applied to generate the prediction models for ubiquitination site identification. Evaluation by five-fold cross-validation showed that the SVM models learned from the combination of hybrid features delivered a better prediction performance. Additionally, a motif discovery tool, MDDLogo, was adopted to characterize the potential substrate motifs of ubiquitination sites. The SVM models integrating the MDDLogo-identified substrate motifs could yield an average accuracy of 68.70 percent. Furthermore, the independent testing result showed that the MDDLogo-clustered SVM models could provide a promising accuracy (78.50 percent) and perform better than other prediction tools. Two cases have demonstrated the effective prediction of ubiquitination sites with corresponding substrate motifs.

ASME V\\&V challenge problem: Surrogate-based V&V

DOE Office of Scientific and Technical Information (OSTI.GOV)

Beghini, Lauren L.; Hough, Patricia D.

2015-12-18

The process of verification and validation can be resource intensive. From the computational model perspective, the resource demand typically arises from long simulation run times on multiple cores coupled with the need to characterize and propagate uncertainties. In addition, predictive computations performed for safety and reliability analyses have similar resource requirements. For this reason, there is a tradeoff between the time required to complete the requisite studies and the fidelity or accuracy of the results that can be obtained. At a high level, our approach is cast within a validation hierarchy that provides a framework in which we perform sensitivitymore » analysis, model calibration, model validation, and prediction. The evidence gathered as part of these activities is mapped into the Predictive Capability Maturity Model to assess credibility of the model used for the reliability predictions. With regard to specific technical aspects of our analysis, we employ surrogate-based methods, primarily based on polynomial chaos expansions and Gaussian processes, for model calibration, sensitivity analysis, and uncertainty quantification in order to reduce the number of simulations that must be done. The goal is to tip the tradeoff balance to improving accuracy without increasing the computational demands.« less

Predicting Depression among Patients with Diabetes Using Longitudinal Data. A Multilevel Regression Model.

PubMed

Jin, H; Wu, S; Vidyanti, I; Di Capua, P; Wu, B

2015-01-01

This article is part of the Focus Theme of Methods of Information in Medicine on "Big Data and Analytics in Healthcare". Depression is a common and often undiagnosed condition for patients with diabetes. It is also a condition that significantly impacts healthcare outcomes, use, and cost as well as elevating suicide risk. Therefore, a model to predict depression among diabetes patients is a promising and valuable tool for providers to proactively assess depressive symptoms and identify those with depression. This study seeks to develop a generalized multilevel regression model, using a longitudinal data set from a recent large-scale clinical trial, to predict depression severity and presence of major depression among patients with diabetes. Severity of depression was measured by the Patient Health Questionnaire PHQ-9 score. Predictors were selected from 29 candidate factors to develop a 2-level Poisson regression model that can make population-average predictions for all patients and subject-specific predictions for individual patients with historical records. Newly obtained patient records can be incorporated with historical records to update the prediction model. Root-mean-square errors (RMSE) were used to evaluate predictive accuracy of PHQ-9 scores. The study also evaluated the classification ability of using the predicted PHQ-9 scores to classify patients as having major depression. Two time-invariant and 10 time-varying predictors were selected for the model. Incorporating historical records and using them to update the model may improve both predictive accuracy of PHQ-9 scores and classification ability of the predicted scores. Subject-specific predictions (for individual patients with historical records) achieved RMSE about 4 and areas under the receiver operating characteristic (ROC) curve about 0.9 and are better than population-average predictions. The study developed a generalized multilevel regression model to predict depression and demonstrated that using generalized multilevel regression based on longitudinal patient records can achieve high predictive ability.

A fingertip force prediction model for grasp patterns characterised from the chaotic behaviour of EEG.

PubMed

Roy, Rinku; Sikdar, Debdeep; Mahadevappa, Manjunatha; Kumar, C S

2018-05-19

A stable grasp is attained through appropriate hand preshaping and precise fingertip forces. Here, we have proposed a method to decode grasp patterns from motor imagery and subsequent fingertip force estimation model with a slippage avoidance strategy. We have developed a feature-based classification of electroencephalography (EEG) associated with imagination of the grasping postures. Chaotic behaviour of EEG for different grasping patterns has been utilised to capture the dynamics of associated motor activities. We have computed correlation dimension (CD) as the feature and classified with "one against one" multiclass support vector machine (SVM) to discriminate between different grasping patterns. The result of the analysis showed varying classification accuracies at different subband levels. Broad categories of grasping patterns, namely, power grasp and precision grasp, were classified at a 96.0% accuracy rate in the alpha subband. Furthermore, power grasp subtypes were classified with an accuracy of 97.2% in the upper beta subband, whereas precision grasp subtypes showed relatively lower 75.0% accuracy in the alpha subband. Following assessment of fingertip force distributions while grasping, a nonlinear autoregressive (NAR) model with proper prediction of fingertip forces was proposed for each grasp pattern. A slippage detection strategy has been incorporated with automatic recalibration of the regripping force. Intention of each grasp pattern associated with corresponding fingertip force model was virtualised in this work. This integrated system can be utilised as the control strategy for prosthetic hand in the future. The model to virtualise motor imagery based fingertip force prediction with inherent slippage correction for different grasp types ᅟ.

Scoring and staging systems using cox linear regression modeling and recursive partitioning.

PubMed

Lee, J W; Um, S H; Lee, J B; Mun, J; Cho, H

2006-01-01

Scoring and staging systems are used to determine the order and class of data according to predictors. Systems used for medical data, such as the Child-Turcotte-Pugh scoring and staging systems for ordering and classifying patients with liver disease, are often derived strictly from physicians' experience and intuition. We construct objective and data-based scoring/staging systems using statistical methods. We consider Cox linear regression modeling and recursive partitioning techniques for censored survival data. In particular, to obtain a target number of stages we propose cross-validation and amalgamation algorithms. We also propose an algorithm for constructing scoring and staging systems by integrating local Cox linear regression models into recursive partitioning, so that we can retain the merits of both methods such as superior predictive accuracy, ease of use, and detection of interactions between predictors. The staging system construction algorithms are compared by cross-validation evaluation of real data. The data-based cross-validation comparison shows that Cox linear regression modeling is somewhat better than recursive partitioning when there are only continuous predictors, while recursive partitioning is better when there are significant categorical predictors. The proposed local Cox linear recursive partitioning has better predictive accuracy than Cox linear modeling and simple recursive partitioning. This study indicates that integrating local linear modeling into recursive partitioning can significantly improve prediction accuracy in constructing scoring and staging systems.

Haplotype-Based Genome-Wide Prediction Models Exploit Local Epistatic Interactions Among Markers

PubMed Central

Jiang, Yong; Schmidt, Renate H.; Reif, Jochen C.

2018-01-01

Genome-wide prediction approaches represent versatile tools for the analysis and prediction of complex traits. Mostly they rely on marker-based information, but scenarios have been reported in which models capitalizing on closely-linked markers that were combined into haplotypes outperformed marker-based models. Detailed comparisons were undertaken to reveal under which circumstances haplotype-based genome-wide prediction models are superior to marker-based models. Specifically, it was of interest to analyze whether and how haplotype-based models may take local epistatic effects between markers into account. Assuming that populations consisted of fully homozygous individuals, a marker-based model in which local epistatic effects inside haplotype blocks were exploited (LEGBLUP) was linearly transformable into a haplotype-based model (HGBLUP). This theoretical derivation formally revealed that haplotype-based genome-wide prediction models capitalize on local epistatic effects among markers. Simulation studies corroborated this finding. Due to its computational efficiency the HGBLUP model promises to be an interesting tool for studies in which ultra-high-density SNP data sets are studied. Applying the HGBLUP model to empirical data sets revealed higher prediction accuracies than for marker-based models for both traits studied using a mouse panel. In contrast, only a small subset of the traits analyzed in crop populations showed such a benefit. Cases in which higher prediction accuracies are observed for HGBLUP than for marker-based models are expected to be of immediate relevance for breeders, due to the tight linkage a beneficial haplotype will be preserved for many generations. In this respect the inheritance of local epistatic effects very much resembles the one of additive effects. PMID:29549092

Haplotype-Based Genome-Wide Prediction Models Exploit Local Epistatic Interactions Among Markers.

PubMed

Jiang, Yong; Schmidt, Renate H; Reif, Jochen C

2018-05-04

Genome-wide prediction approaches represent versatile tools for the analysis and prediction of complex traits. Mostly they rely on marker-based information, but scenarios have been reported in which models capitalizing on closely-linked markers that were combined into haplotypes outperformed marker-based models. Detailed comparisons were undertaken to reveal under which circumstances haplotype-based genome-wide prediction models are superior to marker-based models. Specifically, it was of interest to analyze whether and how haplotype-based models may take local epistatic effects between markers into account. Assuming that populations consisted of fully homozygous individuals, a marker-based model in which local epistatic effects inside haplotype blocks were exploited (LEGBLUP) was linearly transformable into a haplotype-based model (HGBLUP). This theoretical derivation formally revealed that haplotype-based genome-wide prediction models capitalize on local epistatic effects among markers. Simulation studies corroborated this finding. Due to its computational efficiency the HGBLUP model promises to be an interesting tool for studies in which ultra-high-density SNP data sets are studied. Applying the HGBLUP model to empirical data sets revealed higher prediction accuracies than for marker-based models for both traits studied using a mouse panel. In contrast, only a small subset of the traits analyzed in crop populations showed such a benefit. Cases in which higher prediction accuracies are observed for HGBLUP than for marker-based models are expected to be of immediate relevance for breeders, due to the tight linkage a beneficial haplotype will be preserved for many generations. In this respect the inheritance of local epistatic effects very much resembles the one of additive effects. Copyright © 2018 Jiang et al.

An Experimental Study in Determining Energy Expenditure from Treadmill Walking using Hip-Worn Inertial Sensors

PubMed Central

Vathsangam, Harshvardhan; Emken, Adar; Schroeder, E. Todd; Spruijt-Metz, Donna; Sukhatme, Gaurav S.

2011-01-01

This paper describes an experimental study in estimating energy expenditure from treadmill walking using a single hip-mounted triaxial inertial sensor comprised of a triaxial accelerometer and a triaxial gyroscope. Typical physical activity characterization using accelerometer generated counts suffers from two drawbacks - imprecison (due to proprietary counts) and incompleteness (due to incomplete movement description). We address these problems in the context of steady state walking by directly estimating energy expenditure with data from a hip-mounted inertial sensor. We represent the cyclic nature of walking with a Fourier transform of sensor streams and show how one can map this representation to energy expenditure (as measured by V O2 consumption, mL/min) using three regression techniques - Least Squares Regression (LSR), Bayesian Linear Regression (BLR) and Gaussian Process Regression (GPR). We perform a comparative analysis of the accuracy of sensor streams in predicting energy expenditure (measured by RMS prediction accuracy). Triaxial information is more accurate than uniaxial information. LSR based approaches are prone to outlier sensitivity and overfitting. Gyroscopic information showed equivalent if not better prediction accuracy as compared to accelerometers. Combining accelerometer and gyroscopic information provided better accuracy than using either sensor alone. We also analyze the best algorithmic approach among linear and nonlinear methods as measured by RMS prediction accuracy and run time. Nonlinear regression methods showed better prediction accuracy but required an order of magnitude of run time. This paper emphasizes the role of probabilistic techniques in conjunction with joint modeling of triaxial accelerations and rotational rates to improve energy expenditure prediction for steady-state treadmill walking. PMID:21690001

[Prediction of regional soil quality based on mutual information theory integrated with decision tree algorithm].

PubMed

Lin, Fen-Fang; Wang, Ke; Yang, Ning; Yan, Shi-Guang; Zheng, Xin-Yu

2012-02-01

In this paper, some main factors such as soil type, land use pattern, lithology type, topography, road, and industry type that affect soil quality were used to precisely obtain the spatial distribution characteristics of regional soil quality, mutual information theory was adopted to select the main environmental factors, and decision tree algorithm See 5.0 was applied to predict the grade of regional soil quality. The main factors affecting regional soil quality were soil type, land use, lithology type, distance to town, distance to water area, altitude, distance to road, and distance to industrial land. The prediction accuracy of the decision tree model with the variables selected by mutual information was obviously higher than that of the model with all variables, and, for the former model, whether of decision tree or of decision rule, its prediction accuracy was all higher than 80%. Based on the continuous and categorical data, the method of mutual information theory integrated with decision tree could not only reduce the number of input parameters for decision tree algorithm, but also predict and assess regional soil quality effectively.

Structure-Activity Relationship Models for Rat Carcinogenesis and Assessing the Role Mutagens Play in Model Predictivity

PubMed Central

Carrasquer, C. Alex; Batey, Kaylind; Qamar, Shahid; Cunningham, Albert R.; Cunningham, Suzanne L.

2016-01-01

We previously demonstrated that fragment based cat-SAR carcinogenesis models consisting solely of mutagenic or non-mutagenic carcinogens varied greatly in terms of their predictive accuracy. This led us to investigate how well the rat cancer cat-SAR model predicted mutagens and non-mutagens in their learning set. Four rat cancer cat-SAR models were developed: Complete Rat, Transgender Rat, Male Rat, and Female Rat, with leave-one-out (LOO) validation concordance values of 69%, 74%, 67%, and 73%, respectively. The mutagenic carcinogens produced concordance values in the range of 69–76% as compared to only 47–53% for non-mutagenic carcinogens. As a surrogate for mutagenicity comparisons between single site and multiple site carcinogen SAR models was analyzed. The LOO concordance values for models consisting of 1-site, 2-site, and 4+-site carcinogens were 66%, 71%, and 79%, respectively. As expected, the proportion of mutagens to non-mutagens also increased, rising from 54% for 1-site to 80% for 4+-site carcinogens. This study demonstrates that mutagenic chemicals, in both SAR learning sets and test sets, are influential in assessing model accuracy. This suggests that SAR models for carcinogens may require a two-step process in which mutagenicity is first determined before carcinogenicity can be accurately predicted. PMID:24697549

Accuracy of topographic index models at identifying ephemeral gully trajectories on agricultural fields

NASA Astrophysics Data System (ADS)

Sheshukov, Aleksey Y.; Sekaluvu, Lawrence; Hutchinson, Stacy L.

2018-04-01

Topographic index (TI) models have been widely used to predict trajectories and initiation points of ephemeral gullies (EGs) in agricultural landscapes. Prediction of EGs strongly relies on the selected value of critical TI threshold, and the accuracy depends on topographic features, agricultural management, and datasets of observed EGs. This study statistically evaluated the predictions by TI models in two paired watersheds in Central Kansas that had different levels of structural disturbances due to implemented conservation practices. Four TI models with sole dependency on topographic factors of slope, contributing area, and planform curvature were used in this study. The observed EGs were obtained by field reconnaissance and through the process of hydrological reconditioning of digital elevation models (DEMs). The Kernel Density Estimation analysis was used to evaluate TI distribution within a 10-m buffer of the observed EG trajectories. The EG occurrence within catchments was analyzed using kappa statistics of the error matrix approach, while the lengths of predicted EGs were compared with the observed dataset using the Nash-Sutcliffe Efficiency (NSE) statistics. The TI frequency analysis produced bi-modal distribution of topographic indexes with the pixels within the EG trajectory having a higher peak. The graphs of kappa and NSE versus critical TI threshold showed similar profile for all four TI models and both watersheds with the maximum value representing the best comparison with the observed data. The Compound Topographic Index (CTI) model presented the overall best accuracy with NSE of 0.55 and kappa of 0.32. The statistics for the disturbed watershed showed higher best critical TI threshold values than for the undisturbed watershed. Structural conservation practices implemented in the disturbed watershed reduced ephemeral channels in headwater catchments, thus producing less variability in catchments with EGs. The variation in critical thresholds for all TI models suggested that TI models tend to predict EG occurrence and length over a range of thresholds rather than find a single best value.