Adaptive correction of ensemble forecasts

NASA Astrophysics Data System (ADS)

Pelosi, Anna; Battista Chirico, Giovanni; Van den Bergh, Joris; Vannitsem, Stephane

2017-04-01

Forecasts from numerical weather prediction (NWP) models often suffer from both systematic and non-systematic errors. These are present in both deterministic and ensemble forecasts, and originate from various sources such as model error and subgrid variability. Statistical post-processing techniques can partly remove such errors, which is particularly important when NWP outputs concerning surface weather variables are employed for site specific applications. Many different post-processing techniques have been developed. For deterministic forecasts, adaptive methods such as the Kalman filter are often used, which sequentially post-process the forecasts by continuously updating the correction parameters as new ground observations become available. These methods are especially valuable when long training data sets do not exist. For ensemble forecasts, well-known techniques are ensemble model output statistics (EMOS), and so-called "member-by-member" approaches (MBM). Here, we introduce a new adaptive post-processing technique for ensemble predictions. The proposed method is a sequential Kalman filtering technique that fully exploits the information content of the ensemble. One correction equation is retrieved and applied to all members, however the parameters of the regression equations are retrieved by exploiting the second order statistics of the forecast ensemble. We compare our new method with two other techniques: a simple method that makes use of a running bias correction of the ensemble mean, and an MBM post-processing approach that rescales the ensemble mean and spread, based on minimization of the Continuous Ranked Probability Score (CRPS). We perform a verification study for the region of Campania in southern Italy. We use two years (2014-2015) of daily meteorological observations of 2-meter temperature and 10-meter wind speed from 18 ground-based automatic weather stations distributed across the region, comparing them with the corresponding COSMO-LEPS ensemble forecasts. Deterministic verification scores (e.g., mean absolute error, bias) and probabilistic scores (e.g., CRPS) are used to evaluate the post-processing techniques. We conclude that the new adaptive method outperforms the simpler running bias-correction. The proposed adaptive method often outperforms the MBM method in removing bias. The MBM method has the advantage of correcting the ensemble spread, although it needs more training data.

A target recognition method for maritime surveillance radars based on hybrid ensemble selection

NASA Astrophysics Data System (ADS)

Fan, Xueman; Hu, Shengliang; He, Jingbo

2017-11-01

In order to improve the generalisation ability of the maritime surveillance radar, a novel ensemble selection technique, termed Optimisation and Dynamic Selection (ODS), is proposed. During the optimisation phase, the non-dominated sorting genetic algorithm II for multi-objective optimisation is used to find the Pareto front, i.e. a set of ensembles of classifiers representing different tradeoffs between the classification error and diversity. During the dynamic selection phase, the meta-learning method is used to predict whether a candidate ensemble is competent enough to classify a query instance based on three different aspects, namely, feature space, decision space and the extent of consensus. The classification performance and time complexity of ODS are compared against nine other ensemble methods using a self-built full polarimetric high resolution range profile data-set. The experimental results clearly show the effectiveness of ODS. In addition, the influence of the selection of diversity measures is studied concurrently.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification

PubMed Central

Haque, Mohammad Nazmul; Noman, Nasimul; Berretta, Regina; Moscato, Pablo

2016-01-01

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases. PMID:26764911

EnsembleGraph: Interactive Visual Analysis of Spatial-Temporal Behavior for Ensemble Simulation Data

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

Shu, Qingya; Guo, Hanqi; Che, Limei

We present a novel visualization framework—EnsembleGraph— for analyzing ensemble simulation data, in order to help scientists understand behavior similarities between ensemble members over space and time. A graph-based representation is used to visualize individual spatiotemporal regions with similar behaviors, which are extracted by hierarchical clustering algorithms. A user interface with multiple-linked views is provided, which enables users to explore, locate, and compare regions that have similar behaviors between and then users can investigate and analyze the selected regions in detail. The driving application of this paper is the studies on regional emission influences over tropospheric ozone, which is based onmore » ensemble simulations conducted with different anthropogenic emission absences using the MOZART-4 (model of ozone and related tracers, version 4) model. We demonstrate the effectiveness of our method by visualizing the MOZART-4 ensemble simulation data and evaluating the relative regional emission influences on tropospheric ozone concentrations. Positive feedbacks from domain experts and two case studies prove efficiency of our method.« less

SVM and SVM Ensembles in Breast Cancer Prediction.

PubMed

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

SVM and SVM Ensembles in Breast Cancer Prediction

PubMed Central

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers. PMID:28060807

Ensemble Methods for MiRNA Target Prediction from Expression Data.

PubMed

Le, Thuc Duy; Zhang, Junpeng; Liu, Lin; Li, Jiuyong

2015-01-01

microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory. In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials.

Ensemble Methods for MiRNA Target Prediction from Expression Data

PubMed Central

Le, Thuc Duy; Zhang, Junpeng; Liu, Lin; Li, Jiuyong

2015-01-01

Background microRNAs (miRNAs) are short regulatory RNAs that are involved in several diseases, including cancers. Identifying miRNA functions is very important in understanding disease mechanisms and determining the efficacy of drugs. An increasing number of computational methods have been developed to explore miRNA functions by inferring the miRNA-mRNA regulatory relationships from data. Each of the methods is developed based on some assumptions and constraints, for instance, assuming linear relationships between variables. For such reasons, computational methods are often subject to the problem of inconsistent performance across different datasets. On the other hand, ensemble methods integrate the results from individual methods and have been proved to outperform each of their individual component methods in theory. Results In this paper, we investigate the performance of some ensemble methods over the commonly used miRNA target prediction methods. We apply eight different popular miRNA target prediction methods to three cancer datasets, and compare their performance with the ensemble methods which integrate the results from each combination of the individual methods. The validation results using experimentally confirmed databases show that the results of the ensemble methods complement those obtained by the individual methods and the ensemble methods perform better than the individual methods across different datasets. The ensemble method, Pearson+IDA+Lasso, which combines methods in different approaches, including a correlation method, a causal inference method, and a regression method, is the best performed ensemble method in this study. Further analysis of the results of this ensemble method shows that the ensemble method can obtain more targets which could not be found by any of the single methods, and the discovered targets are more statistically significant and functionally enriched. The source codes, datasets, miRNA target predictions by all methods, and the ground truth for validation are available in the Supplementary materials. PMID:26114448

Sequential ensemble-based optimal design for parameter estimation: SEQUENTIAL ENSEMBLE-BASED OPTIMAL DESIGN

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

Man, Jun; Zhang, Jiangjiang; Li, Weixuan

2016-10-01

The ensemble Kalman filter (EnKF) has been widely used in parameter estimation for hydrological models. The focus of most previous studies was to develop more efficient analysis (estimation) algorithms. On the other hand, it is intuitively understandable that a well-designed sampling (data-collection) strategy should provide more informative measurements and subsequently improve the parameter estimation. In this work, a Sequential Ensemble-based Optimal Design (SEOD) method, coupled with EnKF, information theory and sequential optimal design, is proposed to improve the performance of parameter estimation. Based on the first-order and second-order statistics, different information metrics including the Shannon entropy difference (SD), degrees ofmore » freedom for signal (DFS) and relative entropy (RE) are used to design the optimal sampling strategy, respectively. The effectiveness of the proposed method is illustrated by synthetic one-dimensional and two-dimensional unsaturated flow case studies. It is shown that the designed sampling strategies can provide more accurate parameter estimation and state prediction compared with conventional sampling strategies. Optimal sampling designs based on various information metrics perform similarly in our cases. The effect of ensemble size on the optimal design is also investigated. Overall, larger ensemble size improves the parameter estimation and convergence of optimal sampling strategy. Although the proposed method is applied to unsaturated flow problems in this study, it can be equally applied in any other hydrological problems.« less

Assessing the impact of land use change on hydrology by ensemble modeling (LUCHEM) III: Scenario analysis

USGS Publications Warehouse

Huisman, J.A.; Breuer, L.; Bormann, H.; Bronstert, A.; Croke, B.F.W.; Frede, H.-G.; Graff, T.; Hubrechts, L.; Jakeman, A.J.; Kite, G.; Lanini, J.; Leavesley, G.; Lettenmaier, D.P.; Lindstrom, G.; Seibert, J.; Sivapalan, M.; Viney, N.R.; Willems, P.

2009-01-01

An ensemble of 10 hydrological models was applied to the same set of land use change scenarios. There was general agreement about the direction of changes in the mean annual discharge and 90% discharge percentile predicted by the ensemble members, although a considerable range in the magnitude of predictions for the scenarios and catchments under consideration was obvious. Differences in the magnitude of the increase were attributed to the different mean annual actual evapotranspiration rates for each land use type. The ensemble of model runs was further analyzed with deterministic and probabilistic ensemble methods. The deterministic ensemble method based on a trimmed mean resulted in a single somewhat more reliable scenario prediction. The probabilistic reliability ensemble averaging (REA) method allowed a quantification of the model structure uncertainty in the scenario predictions. It was concluded that the use of a model ensemble has greatly increased our confidence in the reliability of the model predictions. ?? 2008 Elsevier Ltd.

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.

A deep learning-based multi-model ensemble method for cancer prediction.

PubMed

Xiao, Yawen; Wu, Jun; Lin, Zongli; Zhao, Xiaodong

2018-01-01

Cancer is a complex worldwide health problem associated with high mortality. With the rapid development of the high-throughput sequencing technology and the application of various machine learning methods that have emerged in recent years, progress in cancer prediction has been increasingly made based on gene expression, providing insight into effective and accurate treatment decision making. Thus, developing machine learning methods, which can successfully distinguish cancer patients from healthy persons, is of great current interest. However, among the classification methods applied to cancer prediction so far, no one method outperforms all the others. In this paper, we demonstrate a new strategy, which applies deep learning to an ensemble approach that incorporates multiple different machine learning models. We supply informative gene data selected by differential gene expression analysis to five different classification models. Then, a deep learning method is employed to ensemble the outputs of the five classifiers. The proposed deep learning-based multi-model ensemble method was tested on three public RNA-seq data sets of three kinds of cancers, Lung Adenocarcinoma, Stomach Adenocarcinoma and Breast Invasive Carcinoma. The test results indicate that it increases the prediction accuracy of cancer for all the tested RNA-seq data sets as compared to using a single classifier or the majority voting algorithm. By taking full advantage of different classifiers, the proposed deep learning-based multi-model ensemble method is shown to be accurate and effective for cancer prediction. Copyright © 2017 Elsevier B.V. All rights reserved.

Overlapped Partitioning for Ensemble Classifiers of P300-Based Brain-Computer Interfaces

PubMed Central

Onishi, Akinari; Natsume, Kiyohisa

2014-01-01

A P300-based brain-computer interface (BCI) enables a wide range of people to control devices that improve their quality of life. Ensemble classifiers with naive partitioning were recently applied to the P300-based BCI and these classification performances were assessed. However, they were usually trained on a large amount of training data (e.g., 15300). In this study, we evaluated ensemble linear discriminant analysis (LDA) classifiers with a newly proposed overlapped partitioning method using 900 training data. In addition, the classification performances of the ensemble classifier with naive partitioning and a single LDA classifier were compared. One of three conditions for dimension reduction was applied: the stepwise method, principal component analysis (PCA), or none. The results show that an ensemble stepwise LDA (SWLDA) classifier with overlapped partitioning achieved a better performance than the commonly used single SWLDA classifier and an ensemble SWLDA classifier with naive partitioning. This result implies that the performance of the SWLDA is improved by overlapped partitioning and the ensemble classifier with overlapped partitioning requires less training data than that with naive partitioning. This study contributes towards reducing the required amount of training data and achieving better classification performance. PMID:24695550

Overlapped partitioning for ensemble classifiers of P300-based brain-computer interfaces.

PubMed

Onishi, Akinari; Natsume, Kiyohisa

2014-01-01

A P300-based brain-computer interface (BCI) enables a wide range of people to control devices that improve their quality of life. Ensemble classifiers with naive partitioning were recently applied to the P300-based BCI and these classification performances were assessed. However, they were usually trained on a large amount of training data (e.g., 15300). In this study, we evaluated ensemble linear discriminant analysis (LDA) classifiers with a newly proposed overlapped partitioning method using 900 training data. In addition, the classification performances of the ensemble classifier with naive partitioning and a single LDA classifier were compared. One of three conditions for dimension reduction was applied: the stepwise method, principal component analysis (PCA), or none. The results show that an ensemble stepwise LDA (SWLDA) classifier with overlapped partitioning achieved a better performance than the commonly used single SWLDA classifier and an ensemble SWLDA classifier with naive partitioning. This result implies that the performance of the SWLDA is improved by overlapped partitioning and the ensemble classifier with overlapped partitioning requires less training data than that with naive partitioning. This study contributes towards reducing the required amount of training data and achieving better classification performance.

Minimalist ensemble algorithms for genome-wide protein localization prediction.

PubMed

Lin, Jhih-Rong; Mondal, Ananda Mohan; Liu, Rong; Hu, Jianjun

2012-07-03

Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi.

Minimalist ensemble algorithms for genome-wide protein localization prediction

PubMed Central

2012-01-01

Background Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. Results This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. Conclusions We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi. PMID:22759391

Simulation of weak polyelectrolytes: a comparison between the constant pH and the reaction ensemble method

NASA Astrophysics Data System (ADS)

Landsgesell, Jonas; Holm, Christian; Smiatek, Jens

2017-03-01

The reaction ensemble and the constant pH method are well-known chemical equilibrium approaches to simulate protonation and deprotonation reactions in classical molecular dynamics and Monte Carlo simulations. In this article, we demonstrate the similarity between both methods under certain conditions. We perform molecular dynamics simulations of a weak polyelectrolyte in order to compare the titration curves obtained by both approaches. Our findings reveal a good agreement between the methods when the reaction ensemble is used to sweep the reaction constant. Pronounced differences between the reaction ensemble and the constant pH method can be observed for stronger acids and bases in terms of adaptive pH values. These deviations are due to the presence of explicit protons in the reaction ensemble method which induce a screening of electrostatic interactions between the charged titrable groups of the polyelectrolyte. The outcomes of our simulation hint to a better applicability of the reaction ensemble method for systems in confined geometries and titrable groups in polyelectrolytes with different pKa values.

Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm.

PubMed

Ren, Fulong; Cao, Peng; Li, Wei; Zhao, Dazhe; Zaiane, Osmar

2017-01-01

Diabetic retinopathy (DR) is a progressive disease, and its detection at an early stage is crucial for saving a patient's vision. An automated screening system for DR can help in reduce the chances of complete blindness due to DR along with lowering the work load on ophthalmologists. Among the earliest signs of DR are microaneurysms (MAs). However, current schemes for MA detection appear to report many false positives because detection algorithms have high sensitivity. Inevitably some non-MAs structures are labeled as MAs in the initial MAs identification step. This is a typical "class imbalance problem". Class imbalanced data has detrimental effects on the performance of conventional classifiers. In this work, we propose an ensemble based adaptive over-sampling algorithm for overcoming the class imbalance problem in the false positive reduction, and we use Boosting, Bagging, Random subspace as the ensemble framework to improve microaneurysm detection. The ensemble based over-sampling methods we proposed combine the strength of adaptive over-sampling and ensemble. The objective of the amalgamation of ensemble and adaptive over-sampling is to reduce the induction biases introduced from imbalanced data and to enhance the generalization classification performance of extreme learning machines (ELM). Experimental results show that our ASOBoost method has higher area under the ROC curve (AUC) and G-mean values than many existing class imbalance learning methods. Copyright © 2016 Elsevier Ltd. All rights reserved.

Impact of ensemble learning in the assessment of skeletal maturity.

PubMed

Cunha, Pedro; Moura, Daniel C; Guevara López, Miguel Angel; Guerra, Conceição; Pinto, Daniela; Ramos, Isabel

2014-09-01

The assessment of the bone age, or skeletal maturity, is an important task in pediatrics that measures the degree of maturation of children's bones. Nowadays, there is no standard clinical procedure for assessing bone age and the most widely used approaches are the Greulich and Pyle and the Tanner and Whitehouse methods. Computer methods have been proposed to automatize the process; however, there is a lack of exploration about how to combine the features of the different parts of the hand, and how to take advantage of ensemble techniques for this purpose. This paper presents a study where the use of ensemble techniques for improving bone age assessment is evaluated. A new computer method was developed that extracts descriptors for each joint of each finger, which are then combined using different ensemble schemes for obtaining a final bone age value. Three popular ensemble schemes are explored in this study: bagging, stacking and voting. Best results were achieved by bagging with a rule-based regression (M5P), scoring a mean absolute error of 10.16 months. Results show that ensemble techniques improve the prediction performance of most of the evaluated regression algorithms, always achieving best or comparable to best results. Therefore, the success of the ensemble methods allow us to conclude that their use may improve computer-based bone age assessment, offering a scalable option for utilizing multiple regions of interest and combining their output.

Confidence-based ensemble for GBM brain tumor segmentation

NASA Astrophysics Data System (ADS)

Huo, Jing; van Rikxoort, Eva M.; Okada, Kazunori; Kim, Hyun J.; Pope, Whitney; Goldin, Jonathan; Brown, Matthew

2011-03-01

It is a challenging task to automatically segment glioblastoma multiforme (GBM) brain tumors on T1w post-contrast isotropic MR images. A semi-automated system using fuzzy connectedness has recently been developed for computing the tumor volume that reduces the cost of manual annotation. In this study, we propose a an ensemble method that combines multiple segmentation results into a final ensemble one. The method is evaluated on a dataset of 20 cases from a multi-center pharmaceutical drug trial and compared to the fuzzy connectedness method. Three individual methods were used in the framework: fuzzy connectedness, GrowCut, and voxel classification. The combination method is a confidence map averaging (CMA) method. The CMA method shows an improved ROC curve compared to the fuzzy connectedness method (p < 0.001). The CMA ensemble result is more robust compared to the three individual methods.

A New Method for Determining Structure Ensemble: Application to a RNA Binding Di-Domain Protein.

PubMed

Liu, Wei; Zhang, Jingfeng; Fan, Jing-Song; Tria, Giancarlo; Grüber, Gerhard; Yang, Daiwen

2016-05-10

Structure ensemble determination is the basis of understanding the structure-function relationship of a multidomain protein with weak domain-domain interactions. Paramagnetic relaxation enhancement has been proven a powerful tool in the study of structure ensembles, but there exist a number of challenges such as spin-label flexibility, domain dynamics, and overfitting. Here we propose a new (to our knowledge) method to describe structure ensembles using a minimal number of conformers. In this method, individual domains are considered rigid; the position of each spin-label conformer and the structure of each protein conformer are defined by three and six orthogonal parameters, respectively. First, the spin-label ensemble is determined by optimizing the positions and populations of spin-label conformers against intradomain paramagnetic relaxation enhancements with a genetic algorithm. Subsequently, the protein structure ensemble is optimized using a more efficient genetic algorithm-based approach and an overfitting indicator, both of which were established in this work. The method was validated using a reference ensemble with a set of conformers whose populations and structures are known. This method was also applied to study the structure ensemble of the tandem di-domain of a poly (U) binding protein. The determined ensemble was supported by small-angle x-ray scattering and nuclear magnetic resonance relaxation data. The ensemble obtained suggests an induced fit mechanism for recognition of target RNA by the protein. Copyright © 2016 Biophysical Society. Published by Elsevier Inc. All rights reserved.

Ensemble Deep Learning for Biomedical Time Series Classification

PubMed Central

2016-01-01

Ensemble learning has been proved to improve the generalization ability effectively in both theory and practice. In this paper, we briefly outline the current status of research on it first. Then, a new deep neural network-based ensemble method that integrates filtering views, local views, distorted views, explicit training, implicit training, subview prediction, and Simple Average is proposed for biomedical time series classification. Finally, we validate its effectiveness on the Chinese Cardiovascular Disease Database containing a large number of electrocardiogram recordings. The experimental results show that the proposed method has certain advantages compared to some well-known ensemble methods, such as Bagging and AdaBoost. PMID:27725828

Similarity Measures for Protein Ensembles

PubMed Central

Lindorff-Larsen, Kresten; Ferkinghoff-Borg, Jesper

2009-01-01

Analyses of similarities and changes in protein conformation can provide important information regarding protein function and evolution. Many scores, including the commonly used root mean square deviation, have therefore been developed to quantify the similarities of different protein conformations. However, instead of examining individual conformations it is in many cases more relevant to analyse ensembles of conformations that have been obtained either through experiments or from methods such as molecular dynamics simulations. We here present three approaches that can be used to compare conformational ensembles in the same way as the root mean square deviation is used to compare individual pairs of structures. The methods are based on the estimation of the probability distributions underlying the ensembles and subsequent comparison of these distributions. We first validate the methods using a synthetic example from molecular dynamics simulations. We then apply the algorithms to revisit the problem of ensemble averaging during structure determination of proteins, and find that an ensemble refinement method is able to recover the correct distribution of conformations better than standard single-molecule refinement. PMID:19145244

A Bayesian Ensemble Approach for Epidemiological Projections

PubMed Central

Lindström, Tom; Tildesley, Michael; Webb, Colleen

2015-01-01

Mathematical models are powerful tools for epidemiology and can be used to compare control actions. However, different models and model parameterizations may provide different prediction of outcomes. In other fields of research, ensemble modeling has been used to combine multiple projections. We explore the possibility of applying such methods to epidemiology by adapting Bayesian techniques developed for climate forecasting. We exemplify the implementation with single model ensembles based on different parameterizations of the Warwick model run for the 2001 United Kingdom foot and mouth disease outbreak and compare the efficacy of different control actions. This allows us to investigate the effect that discrepancy among projections based on different modeling assumptions has on the ensemble prediction. A sensitivity analysis showed that the choice of prior can have a pronounced effect on the posterior estimates of quantities of interest, in particular for ensembles with large discrepancy among projections. However, by using a hierarchical extension of the method we show that prior sensitivity can be circumvented. We further extend the method to include a priori beliefs about different modeling assumptions and demonstrate that the effect of this can have different consequences depending on the discrepancy among projections. We propose that the method is a promising analytical tool for ensemble modeling of disease outbreaks. PMID:25927892

Training set extension for SVM ensemble in P300-speller with familiar face paradigm.

PubMed

Li, Qi; Shi, Kaiyang; Gao, Ning; Li, Jian; Bai, Ou

2018-03-27

P300-spellers are brain-computer interface (BCI)-based character input systems. Support vector machine (SVM) ensembles are trained with large-scale training sets and used as classifiers in these systems. However, the required large-scale training data necessitate a prolonged collection time for each subject, which results in data collected toward the end of the period being contaminated by the subject's fatigue. This study aimed to develop a method for acquiring more training data based on a collected small training set. A new method was developed in which two corresponding training datasets in two sequences are superposed and averaged to extend the training set. The proposed method was tested offline on a P300-speller with the familiar face paradigm. The SVM ensemble with extended training set achieved 85% classification accuracy for the averaged results of four sequences, and 100% for 11 sequences in the P300-speller. In contrast, the conventional SVM ensemble with non-extended training set achieved only 65% accuracy for four sequences, and 92% for 11 sequences. The SVM ensemble with extended training set achieves higher classification accuracies than the conventional SVM ensemble, which verifies that the proposed method effectively improves the classification performance of BCI P300-spellers, thus enhancing their practicality.

Wang-Landau Reaction Ensemble Method: Simulation of Weak Polyelectrolytes and General Acid-Base Reactions.

PubMed

Landsgesell, Jonas; Holm, Christian; Smiatek, Jens

2017-02-14

We present a novel method for the study of weak polyelectrolytes and general acid-base reactions in molecular dynamics and Monte Carlo simulations. The approach combines the advantages of the reaction ensemble and the Wang-Landau sampling method. Deprotonation and protonation reactions are simulated explicitly with the help of the reaction ensemble method, while the accurate sampling of the corresponding phase space is achieved by the Wang-Landau approach. The combination of both techniques provides a sufficient statistical accuracy such that meaningful estimates for the density of states and the partition sum can be obtained. With regard to these estimates, several thermodynamic observables like the heat capacity or reaction free energies can be calculated. We demonstrate that the computation times for the calculation of titration curves with a high statistical accuracy can be significantly decreased when compared to the original reaction ensemble method. The applicability of our approach is validated by the study of weak polyelectrolytes and their thermodynamic properties.

Quantum Ensemble Classification: A Sampling-Based Learning Control Approach.

PubMed

Chen, Chunlin; Dong, Daoyi; Qi, Bo; Petersen, Ian R; Rabitz, Herschel

2017-06-01

Quantum ensemble classification (QEC) has significant applications in discrimination of atoms (or molecules), separation of isotopes, and quantum information extraction. However, quantum mechanics forbids deterministic discrimination among nonorthogonal states. The classification of inhomogeneous quantum ensembles is very challenging, since there exist variations in the parameters characterizing the members within different classes. In this paper, we recast QEC as a supervised quantum learning problem. A systematic classification methodology is presented by using a sampling-based learning control (SLC) approach for quantum discrimination. The classification task is accomplished via simultaneously steering members belonging to different classes to their corresponding target states (e.g., mutually orthogonal states). First, a new discrimination method is proposed for two similar quantum systems. Then, an SLC method is presented for QEC. Numerical results demonstrate the effectiveness of the proposed approach for the binary classification of two-level quantum ensembles and the multiclass classification of multilevel quantum ensembles.

Cosolvent-Based Molecular Dynamics for Ensemble Docking: Practical Method for Generating Druggable Protein Conformations.

PubMed

Uehara, Shota; Tanaka, Shigenori

2017-04-24

Protein flexibility is a major hurdle in current structure-based virtual screening (VS). In spite of the recent advances in high-performance computing, protein-ligand docking methods still demand tremendous computational cost to take into account the full degree of protein flexibility. In this context, ensemble docking has proven its utility and efficiency for VS studies, but it still needs a rational and efficient method to select and/or generate multiple protein conformations. Molecular dynamics (MD) simulations are useful to produce distinct protein conformations without abundant experimental structures. In this study, we present a novel strategy that makes use of cosolvent-based molecular dynamics (CMD) simulations for ensemble docking. By mixing small organic molecules into a solvent, CMD can stimulate dynamic protein motions and induce partial conformational changes of binding pocket residues appropriate for the binding of diverse ligands. The present method has been applied to six diverse target proteins and assessed by VS experiments using many actives and decoys of DEKOIS 2.0. The simulation results have revealed that the CMD is beneficial for ensemble docking. Utilizing cosolvent simulation allows the generation of druggable protein conformations, improving the VS performance compared with the use of a single experimental structure or ensemble docking by standard MD with pure water as the solvent.

Assessing an ensemble Kalman filter inference of Manning's n coefficient of an idealized tidal inlet against a polynomial chaos-based MCMC

NASA Astrophysics Data System (ADS)

Siripatana, Adil; Mayo, Talea; Sraj, Ihab; Knio, Omar; Dawson, Clint; Le Maitre, Olivier; Hoteit, Ibrahim

2017-08-01

Bayesian estimation/inversion is commonly used to quantify and reduce modeling uncertainties in coastal ocean model, especially in the framework of parameter estimation. Based on Bayes rule, the posterior probability distribution function (pdf) of the estimated quantities is obtained conditioned on available data. It can be computed either directly, using a Markov chain Monte Carlo (MCMC) approach, or by sequentially processing the data following a data assimilation approach, which is heavily exploited in large dimensional state estimation problems. The advantage of data assimilation schemes over MCMC-type methods arises from the ability to algorithmically accommodate a large number of uncertain quantities without significant increase in the computational requirements. However, only approximate estimates are generally obtained by this approach due to the restricted Gaussian prior and noise assumptions that are generally imposed in these methods. This contribution aims at evaluating the effectiveness of utilizing an ensemble Kalman-based data assimilation method for parameter estimation of a coastal ocean model against an MCMC polynomial chaos (PC)-based scheme. We focus on quantifying the uncertainties of a coastal ocean ADvanced CIRCulation (ADCIRC) model with respect to the Manning's n coefficients. Based on a realistic framework of observation system simulation experiments (OSSEs), we apply an ensemble Kalman filter and the MCMC method employing a surrogate of ADCIRC constructed by a non-intrusive PC expansion for evaluating the likelihood, and test both approaches under identical scenarios. We study the sensitivity of the estimated posteriors with respect to the parameters of the inference methods, including ensemble size, inflation factor, and PC order. A full analysis of both methods, in the context of coastal ocean model, suggests that an ensemble Kalman filter with appropriate ensemble size and well-tuned inflation provides reliable mean estimates and uncertainties of Manning's n coefficients compared to the full posterior distributions inferred by MCMC.

Ensemble stacking mitigates biases in inference of synaptic connectivity.

PubMed

Chambers, Brendan; Levy, Maayan; Dechery, Joseph B; MacLean, Jason N

2018-01-01

A promising alternative to directly measuring the anatomical connections in a neuronal population is inferring the connections from the activity. We employ simulated spiking neuronal networks to compare and contrast commonly used inference methods that identify likely excitatory synaptic connections using statistical regularities in spike timing. We find that simple adjustments to standard algorithms improve inference accuracy: A signing procedure improves the power of unsigned mutual-information-based approaches and a correction that accounts for differences in mean and variance of background timing relationships, such as those expected to be induced by heterogeneous firing rates, increases the sensitivity of frequency-based methods. We also find that different inference methods reveal distinct subsets of the synaptic network and each method exhibits different biases in the accurate detection of reciprocity and local clustering. To correct for errors and biases specific to single inference algorithms, we combine methods into an ensemble. Ensemble predictions, generated as a linear combination of multiple inference algorithms, are more sensitive than the best individual measures alone, and are more faithful to ground-truth statistics of connectivity, mitigating biases specific to single inference methods. These weightings generalize across simulated datasets, emphasizing the potential for the broad utility of ensemble-based approaches.

Sequence Based Prediction of Antioxidant Proteins Using a Classifier Selection Strategy

PubMed Central

Zhang, Lina; Zhang, Chengjin; Gao, Rui; Yang, Runtao; Song, Qing

2016-01-01

Antioxidant proteins perform significant functions in maintaining oxidation/antioxidation balance and have potential therapies for some diseases. Accurate identification of antioxidant proteins could contribute to revealing physiological processes of oxidation/antioxidation balance and developing novel antioxidation-based drugs. In this study, an ensemble method is presented to predict antioxidant proteins with hybrid features, incorporating SSI (Secondary Structure Information), PSSM (Position Specific Scoring Matrix), RSA (Relative Solvent Accessibility), and CTD (Composition, Transition, Distribution). The prediction results of the ensemble predictor are determined by an average of prediction results of multiple base classifiers. Based on a classifier selection strategy, we obtain an optimal ensemble classifier composed of RF (Random Forest), SMO (Sequential Minimal Optimization), NNA (Nearest Neighbor Algorithm), and J48 with an accuracy of 0.925. A Relief combined with IFS (Incremental Feature Selection) method is adopted to obtain optimal features from hybrid features. With the optimal features, the ensemble method achieves improved performance with a sensitivity of 0.95, a specificity of 0.93, an accuracy of 0.94, and an MCC (Matthew’s Correlation Coefficient) of 0.880, far better than the existing method. To evaluate the prediction performance objectively, the proposed method is compared with existing methods on the same independent testing dataset. Encouragingly, our method performs better than previous studies. In addition, our method achieves more balanced performance with a sensitivity of 0.878 and a specificity of 0.860. These results suggest that the proposed ensemble method can be a potential candidate for antioxidant protein prediction. For public access, we develop a user-friendly web server for antioxidant protein identification that is freely accessible at http://antioxidant.weka.cc. PMID:27662651

Ensemble framework based real-time respiratory motion prediction for adaptive radiotherapy applications.

PubMed

Tatinati, Sivanagaraja; Nazarpour, Kianoush; Tech Ang, Wei; Veluvolu, Kalyana C

2016-08-01

Successful treatment of tumors with motion-adaptive radiotherapy requires accurate prediction of respiratory motion, ideally with a prediction horizon larger than the latency in radiotherapy system. Accurate prediction of respiratory motion is however a non-trivial task due to the presence of irregularities and intra-trace variabilities, such as baseline drift and temporal changes in fundamental frequency pattern. In this paper, to enhance the accuracy of the respiratory motion prediction, we propose a stacked regression ensemble framework that integrates heterogeneous respiratory motion prediction algorithms. We further address two crucial issues for developing a successful ensemble framework: (1) selection of appropriate prediction methods to ensemble (level-0 methods) among the best existing prediction methods; and (2) finding a suitable generalization approach that can successfully exploit the relative advantages of the chosen level-0 methods. The efficacy of the developed ensemble framework is assessed with real respiratory motion traces acquired from 31 patients undergoing treatment. Results show that the developed ensemble framework improves the prediction performance significantly compared to the best existing methods. Copyright © 2016 IPEM. Published by Elsevier Ltd. All rights reserved.

Efficient data assimilation algorithm for bathymetry application

NASA Astrophysics Data System (ADS)

Ghorbanidehno, H.; Lee, J. H.; Farthing, M.; Hesser, T.; Kitanidis, P. K.; Darve, E. F.

2017-12-01

Information on the evolving state of the nearshore zone bathymetry is crucial to shoreline management, recreational safety, and naval operations. The high cost and complex logistics of using ship-based surveys for bathymetry estimation have encouraged the use of remote sensing techniques. Data assimilation methods combine the remote sensing data and nearshore hydrodynamic models to estimate the unknown bathymetry and the corresponding uncertainties. In particular, several recent efforts have combined Kalman Filter-based techniques such as ensembled-based Kalman filters with indirect video-based observations to address the bathymetry inversion problem. However, these methods often suffer from ensemble collapse and uncertainty underestimation. Here, the Compressed State Kalman Filter (CSKF) method is used to estimate the bathymetry based on observed wave celerity. In order to demonstrate the accuracy and robustness of the CSKF method, we consider twin tests with synthetic observations of wave celerity, while the bathymetry profiles are chosen based on surveys taken by the U.S. Army Corps of Engineer Field Research Facility (FRF) in Duck, NC. The first test case is a bathymetry estimation problem for a spatially smooth and temporally constant bathymetry profile. The second test case is a bathymetry estimation problem for a temporally evolving bathymetry from a smooth to a non-smooth profile. For both problems, we compare the results of CSKF with those obtained by the local ensemble transform Kalman filter (LETKF), which is a popular ensemble-based Kalman filter method.

Reducing false-positive incidental findings with ensemble genotyping and logistic regression based variant filtering methods.

PubMed

Hwang, Kyu-Baek; Lee, In-Hee; Park, Jin-Ho; Hambuch, Tina; Choe, Yongjoon; Kim, MinHyeok; Lee, Kyungjoon; Song, Taemin; Neu, Matthew B; Gupta, Neha; Kohane, Isaac S; Green, Robert C; Kong, Sek Won

2014-08-01

As whole genome sequencing (WGS) uncovers variants associated with rare and common diseases, an immediate challenge is to minimize false-positive findings due to sequencing and variant calling errors. False positives can be reduced by combining results from orthogonal sequencing methods, but costly. Here, we present variant filtering approaches using logistic regression (LR) and ensemble genotyping to minimize false positives without sacrificing sensitivity. We evaluated the methods using paired WGS datasets of an extended family prepared using two sequencing platforms and a validated set of variants in NA12878. Using LR or ensemble genotyping based filtering, false-negative rates were significantly reduced by 1.1- to 17.8-fold at the same levels of false discovery rates (5.4% for heterozygous and 4.5% for homozygous single nucleotide variants (SNVs); 30.0% for heterozygous and 18.7% for homozygous insertions; 25.2% for heterozygous and 16.6% for homozygous deletions) compared to the filtering based on genotype quality scores. Moreover, ensemble genotyping excluded > 98% (105,080 of 107,167) of false positives while retaining > 95% (897 of 937) of true positives in de novo mutation (DNM) discovery in NA12878, and performed better than a consensus method using two sequencing platforms. Our proposed methods were effective in prioritizing phenotype-associated variants, and an ensemble genotyping would be essential to minimize false-positive DNM candidates. © 2014 WILEY PERIODICALS, INC.

Reducing false positive incidental findings with ensemble genotyping and logistic regression-based variant filtering methods

PubMed Central

Hwang, Kyu-Baek; Lee, In-Hee; Park, Jin-Ho; Hambuch, Tina; Choi, Yongjoon; Kim, MinHyeok; Lee, Kyungjoon; Song, Taemin; Neu, Matthew B.; Gupta, Neha; Kohane, Isaac S.; Green, Robert C.; Kong, Sek Won

2014-01-01

As whole genome sequencing (WGS) uncovers variants associated with rare and common diseases, an immediate challenge is to minimize false positive findings due to sequencing and variant calling errors. False positives can be reduced by combining results from orthogonal sequencing methods, but costly. Here we present variant filtering approaches using logistic regression (LR) and ensemble genotyping to minimize false positives without sacrificing sensitivity. We evaluated the methods using paired WGS datasets of an extended family prepared using two sequencing platforms and a validated set of variants in NA12878. Using LR or ensemble genotyping based filtering, false negative rates were significantly reduced by 1.1- to 17.8-fold at the same levels of false discovery rates (5.4% for heterozygous and 4.5% for homozygous SNVs; 30.0% for heterozygous and 18.7% for homozygous insertions; 25.2% for heterozygous and 16.6% for homozygous deletions) compared to the filtering based on genotype quality scores. Moreover, ensemble genotyping excluded > 98% (105,080 of 107,167) of false positives while retaining > 95% (897 of 937) of true positives in de novo mutation (DNM) discovery, and performed better than a consensus method using two sequencing platforms. Our proposed methods were effective in prioritizing phenotype-associated variants, and ensemble genotyping would be essential to minimize false positive DNM candidates. PMID:24829188

A further step toward an optimal ensemble of classifiers for peptide classification, a case study: HIV protease.

PubMed

Nanni, Loris; Lumini, Alessandra

2009-01-01

The focuses of this work are: to propose a novel method for building an ensemble of classifiers for peptide classification based on substitution matrices; to show the importance to select a proper set of the parameters of the classifiers that build the ensemble of learning systems. The HIV-1 protease cleavage site prediction problem is here studied. The results obtained by a blind testing protocol are reported, the comparison with other state-of-the-art approaches, based on ensemble of classifiers, allows to quantify the performance improvement obtained by the systems proposed in this paper. The simulation based on experimentally determined protease cleavage data has demonstrated the success of these new ensemble algorithms. Particularly interesting it is to note that also if the HIV-1 protease cleavage site prediction problem is considered linearly separable we obtain the best performance using an ensemble of non-linear classifiers.

Application of the maximum entropy principle to determine ensembles of intrinsically disordered proteins from residual dipolar couplings.

PubMed

Sanchez-Martinez, M; Crehuet, R

2014-12-21

We present a method based on the maximum entropy principle that can re-weight an ensemble of protein structures based on data from residual dipolar couplings (RDCs). The RDCs of intrinsically disordered proteins (IDPs) provide information on the secondary structure elements present in an ensemble; however even two sets of RDCs are not enough to fully determine the distribution of conformations, and the force field used to generate the structures has a pervasive influence on the refined ensemble. Two physics-based coarse-grained force fields, Profasi and Campari, are able to predict the secondary structure elements present in an IDP, but even after including the RDC data, the re-weighted ensembles differ between both force fields. Thus the spread of IDP ensembles highlights the need for better force fields. We distribute our algorithm in an open-source Python code.

An adaptive Gaussian process-based iterative ensemble smoother for data assimilation

NASA Astrophysics Data System (ADS)

Ju, Lei; Zhang, Jiangjiang; Meng, Long; Wu, Laosheng; Zeng, Lingzao

2018-05-01

Accurate characterization of subsurface hydraulic conductivity is vital for modeling of subsurface flow and transport. The iterative ensemble smoother (IES) has been proposed to estimate the heterogeneous parameter field. As a Monte Carlo-based method, IES requires a relatively large ensemble size to guarantee its performance. To improve the computational efficiency, we propose an adaptive Gaussian process (GP)-based iterative ensemble smoother (GPIES) in this study. At each iteration, the GP surrogate is adaptively refined by adding a few new base points chosen from the updated parameter realizations. Then the sensitivity information between model parameters and measurements is calculated from a large number of realizations generated by the GP surrogate with virtually no computational cost. Since the original model evaluations are only required for base points, whose number is much smaller than the ensemble size, the computational cost is significantly reduced. The applicability of GPIES in estimating heterogeneous conductivity is evaluated by the saturated and unsaturated flow problems, respectively. Without sacrificing estimation accuracy, GPIES achieves about an order of magnitude of speed-up compared with the standard IES. Although subsurface flow problems are considered in this study, the proposed method can be equally applied to other hydrological models.

Residue-level global and local ensemble-ensemble comparisons of protein domains.

PubMed

Clark, Sarah A; Tronrud, Dale E; Karplus, P Andrew

2015-09-01

Many methods of protein structure generation such as NMR-based solution structure determination and template-based modeling do not produce a single model, but an ensemble of models consistent with the available information. Current strategies for comparing ensembles lose information because they use only a single representative structure. Here, we describe the ENSEMBLATOR and its novel strategy to directly compare two ensembles containing the same atoms to identify significant global and local backbone differences between them on per-atom and per-residue levels, respectively. The ENSEMBLATOR has four components: eePREP (ee for ensemble-ensemble), which selects atoms common to all models; eeCORE, which identifies atoms belonging to a cutoff-distance dependent common core; eeGLOBAL, which globally superimposes all models using the defined core atoms and calculates for each atom the two intraensemble variations, the interensemble variation, and the closest approach of members of the two ensembles; and eeLOCAL, which performs a local overlay of each dipeptide and, using a novel measure of local backbone similarity, reports the same four variations as eeGLOBAL. The combination of eeGLOBAL and eeLOCAL analyses identifies the most significant differences between ensembles. We illustrate the ENSEMBLATOR's capabilities by showing how using it to analyze NMR ensembles and to compare NMR ensembles with crystal structures provides novel insights compared to published studies. One of these studies leads us to suggest that a "consistency check" of NMR-derived ensembles may be a useful analysis step for NMR-based structure determinations in general. The ENSEMBLATOR 1.0 is available as a first generation tool to carry out ensemble-ensemble comparisons. © 2015 The Protein Society.

Residue-level global and local ensemble-ensemble comparisons of protein domains

PubMed Central

Clark, Sarah A; Tronrud, Dale E; Andrew Karplus, P

2015-01-01

Many methods of protein structure generation such as NMR-based solution structure determination and template-based modeling do not produce a single model, but an ensemble of models consistent with the available information. Current strategies for comparing ensembles lose information because they use only a single representative structure. Here, we describe the ENSEMBLATOR and its novel strategy to directly compare two ensembles containing the same atoms to identify significant global and local backbone differences between them on per-atom and per-residue levels, respectively. The ENSEMBLATOR has four components: eePREP (ee for ensemble-ensemble), which selects atoms common to all models; eeCORE, which identifies atoms belonging to a cutoff-distance dependent common core; eeGLOBAL, which globally superimposes all models using the defined core atoms and calculates for each atom the two intraensemble variations, the interensemble variation, and the closest approach of members of the two ensembles; and eeLOCAL, which performs a local overlay of each dipeptide and, using a novel measure of local backbone similarity, reports the same four variations as eeGLOBAL. The combination of eeGLOBAL and eeLOCAL analyses identifies the most significant differences between ensembles. We illustrate the ENSEMBLATOR's capabilities by showing how using it to analyze NMR ensembles and to compare NMR ensembles with crystal structures provides novel insights compared to published studies. One of these studies leads us to suggest that a “consistency check” of NMR-derived ensembles may be a useful analysis step for NMR-based structure determinations in general. The ENSEMBLATOR 1.0 is available as a first generation tool to carry out ensemble-ensemble comparisons. PMID:26032515

Clustering-Based Ensemble Learning for Activity Recognition in Smart Homes

PubMed Central

Jurek, Anna; Nugent, Chris; Bi, Yaxin; Wu, Shengli

2014-01-01

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks. PMID:25014095

Clustering-based ensemble learning for activity recognition in smart homes.

PubMed

Jurek, Anna; Nugent, Chris; Bi, Yaxin; Wu, Shengli

2014-07-10

Application of sensor-based technology within activity monitoring systems is becoming a popular technique within the smart environment paradigm. Nevertheless, the use of such an approach generates complex constructs of data, which subsequently requires the use of intricate activity recognition techniques to automatically infer the underlying activity. This paper explores a cluster-based ensemble method as a new solution for the purposes of activity recognition within smart environments. With this approach activities are modelled as collections of clusters built on different subsets of features. A classification process is performed by assigning a new instance to its closest cluster from each collection. Two different sensor data representations have been investigated, namely numeric and binary. Following the evaluation of the proposed methodology it has been demonstrated that the cluster-based ensemble method can be successfully applied as a viable option for activity recognition. Results following exposure to data collected from a range of activities indicated that the ensemble method had the ability to perform with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers considered as benchmarks.

Village Building Identification Based on Ensemble Convolutional Neural Networks

PubMed Central

Guo, Zhiling; Chen, Qi; Xu, Yongwei; Shibasaki, Ryosuke; Shao, Xiaowei

2017-01-01

In this study, we present the Ensemble Convolutional Neural Network (ECNN), an elaborate CNN frame formulated based on ensembling state-of-the-art CNN models, to identify village buildings from open high-resolution remote sensing (HRRS) images. First, to optimize and mine the capability of CNN for village mapping and to ensure compatibility with our classification targets, a few state-of-the-art models were carefully optimized and enhanced based on a series of rigorous analyses and evaluations. Second, rather than directly implementing building identification by using these models, we exploited most of their advantages by ensembling their feature extractor parts into a stronger model called ECNN based on the multiscale feature learning method. Finally, the generated ECNN was applied to a pixel-level classification frame to implement object identification. The proposed method can serve as a viable tool for village building identification with high accuracy and efficiency. The experimental results obtained from the test area in Savannakhet province, Laos, prove that the proposed ECNN model significantly outperforms existing methods, improving overall accuracy from 96.64% to 99.26%, and kappa from 0.57 to 0.86. PMID:29084154

Improving ensemble decision tree performance using Adaboost and Bagging

NASA Astrophysics Data System (ADS)

Hasan, Md. Rajib; Siraj, Fadzilah; Sainin, Mohd Shamrie

2015-12-01

Ensemble classifier systems are considered as one of the most promising in medical data classification and the performance of deceision tree classifier can be increased by the ensemble method as it is proven to be better than single classifiers. However, in a ensemble settings the performance depends on the selection of suitable base classifier. This research employed two prominent esemble s namely Adaboost and Bagging with base classifiers such as Random Forest, Random Tree, j48, j48grafts and Logistic Model Regression (LMT) that have been selected independently. The empirical study shows that the performance varries when different base classifiers are selected and even some places overfitting issue also been noted. The evidence shows that ensemble decision tree classfiers using Adaboost and Bagging improves the performance of selected medical data sets.

Comparing Planning Hydrologic Ensembles associated with Paleoclimate, Projected Climate, and blended Climate Information Sets

NASA Astrophysics Data System (ADS)

Brekke, L. D.; Prairie, J.; Pruitt, T.; Rajagopalan, B.; Woodhouse, C.

2008-12-01

Water resources adaptation planning under climate change involves making assumptions about probabilistic water supply conditions, which are linked to a given climate context (e.g., instrument records, paleoclimate indicators, projected climate data, or blend of these). Methods have been demonstrated to associate water supply assumptions with any of these climate information types. Additionally, demonstrations have been offered that represent these information types in a scenario-rich (ensemble) planning framework, either via ensembles (e.g., survey of many climate projections) or stochastic modeling (e.g., based on instrument records or paleoclimate indicators). If the planning goal involves using a hydrologic ensemble that jointly reflects paleoclimate (e.g., lower- frequency variations) and projected climate information (e.g., monthly to annual trends), methods are required to guide how these information types might be translated into water supply assumptions. However, even if such a method exists, there is lack of understanding on how such a hydrologic ensemble might differ from ensembles developed relative to paleoclimate or projected climate information alone. This research explores two questions: (1) how might paleoclimate and projected climate information be blended into an planning hydrologic ensemble, and (2) how does a planning hydrologic ensemble differ when associated with the individual climate information types (i.e. instrumental records, paleoclimate, projected climate, or blend of the latter two). Case study basins include the Gunnison River Basin in Colorado and the Missouri River Basin above Toston in Montana. Presentation will highlight ensemble development methods by information type, and comparison of ensemble results.

Input Decimated Ensembles

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Oza, Nikunj C.; Clancy, Daniel (Technical Monitor)

2001-01-01

Using an ensemble of classifiers instead of a single classifier has been shown to improve generalization performance in many pattern recognition problems. However, the extent of such improvement depends greatly on the amount of correlation among the errors of the base classifiers. Therefore, reducing those correlations while keeping the classifiers' performance levels high is an important area of research. In this article, we explore input decimation (ID), a method which selects feature subsets for their ability to discriminate among the classes and uses them to decouple the base classifiers. We provide a summary of the theoretical benefits of correlation reduction, along with results of our method on two underwater sonar data sets, three benchmarks from the Probenl/UCI repositories, and two synthetic data sets. The results indicate that input decimated ensembles (IDEs) outperform ensembles whose base classifiers use all the input features; randomly selected subsets of features; and features created using principal components analysis, on a wide range of domains.

Comparison of Basic and Ensemble Data Mining Methods in Predicting 5-Year Survival of Colorectal Cancer Patients.

PubMed

Pourhoseingholi, Mohamad Amin; Kheirian, Sedigheh; Zali, Mohammad Reza

2017-12-01

Colorectal cancer (CRC) is one of the most common malignancies and cause of cancer mortality worldwide. Given the importance of predicting the survival of CRC patients and the growing use of data mining methods, this study aims to compare the performance of models for predicting 5-year survival of CRC patients using variety of basic and ensemble data mining methods. The CRC dataset from The Shahid Beheshti University of Medical Sciences Research Center for Gastroenterology and Liver Diseases were used for prediction and comparative study of the base and ensemble data mining techniques. Feature selection methods were used to select predictor attributes for classification. The WEKA toolkit and MedCalc software were respectively utilized for creating and comparing the models. The obtained results showed that the predictive performance of developed models was altogether high (all greater than 90%). Overall, the performance of ensemble models was higher than that of basic classifiers and the best result achieved by ensemble voting model in terms of area under the ROC curve (AUC= 0.96). AUC Comparison of models showed that the ensemble voting method significantly outperformed all models except for two methods of Random Forest (RF) and Bayesian Network (BN) considered the overlapping 95% confidence intervals. This result may indicate high predictive power of these two methods along with ensemble voting for predicting 5-year survival of CRC patients.

Sampling-based ensemble segmentation against inter-operator variability

NASA Astrophysics Data System (ADS)

Huo, Jing; Okada, Kazunori; Pope, Whitney; Brown, Matthew

2011-03-01

Inconsistency and a lack of reproducibility are commonly associated with semi-automated segmentation methods. In this study, we developed an ensemble approach to improve reproducibility and applied it to glioblastoma multiforme (GBM) brain tumor segmentation on T1-weigted contrast enhanced MR volumes. The proposed approach combines samplingbased simulations and ensemble segmentation into a single framework; it generates a set of segmentations by perturbing user initialization and user-specified internal parameters, then fuses the set of segmentations into a single consensus result. Three combination algorithms were applied: majority voting, averaging and expectation-maximization (EM). The reproducibility of the proposed framework was evaluated by a controlled experiment on 16 tumor cases from a multicenter drug trial. The ensemble framework had significantly better reproducibility than the individual base Otsu thresholding method (p<.001).

Revealing Risks in Adaptation Planning: expanding Uncertainty Treatment and dealing with Large Projection Ensembles during Planning Scenario development

NASA Astrophysics Data System (ADS)

Brekke, L. D.; Clark, M. P.; Gutmann, E. D.; Wood, A.; Mizukami, N.; Mendoza, P. A.; Rasmussen, R.; Ikeda, K.; Pruitt, T.; Arnold, J. R.; Rajagopalan, B.

2015-12-01

Adaptation planning assessments often rely on single methods for climate projection downscaling and hydrologic analysis, do not reveal uncertainties from associated method choices, and thus likely produce overly confident decision-support information. Recent work by the authors has highlighted this issue by identifying strengths and weaknesses of widely applied methods for downscaling climate projections and assessing hydrologic impacts. This work has shown that many of the methodological choices made can alter the magnitude, and even the sign of the climate change signal. Such results motivate consideration of both sources of method uncertainty within an impacts assessment. Consequently, the authors have pursued development of improved downscaling techniques spanning a range of method classes (quasi-dynamical and circulation-based statistical methods) and developed approaches to better account for hydrologic analysis uncertainty (multi-model; regional parameter estimation under forcing uncertainty). This presentation summarizes progress in the development of these methods, as well as implications of pursuing these developments. First, having access to these methods creates an opportunity to better reveal impacts uncertainty through multi-method ensembles, expanding on present-practice ensembles which are often based only on emissions scenarios and GCM choices. Second, such expansion of uncertainty treatment combined with an ever-expanding wealth of global climate projection information creates a challenge of how to use such a large ensemble for local adaptation planning. To address this challenge, the authors are evaluating methods for ensemble selection (considering the principles of fidelity, diversity and sensitivity) that is compatible with present-practice approaches for abstracting change scenarios from any "ensemble of opportunity". Early examples from this development will also be presented.

Ensemble pharmacophore meets ensemble docking: a novel screening strategy for the identification of RIPK1 inhibitors

NASA Astrophysics Data System (ADS)

Fayaz, S. M.; Rajanikant, G. K.

2014-07-01

Programmed cell death has been a fascinating area of research since it throws new challenges and questions in spite of the tremendous ongoing research in this field. Recently, necroptosis, a programmed form of necrotic cell death, has been implicated in many diseases including neurological disorders. Receptor interacting serine/threonine protein kinase 1 (RIPK1) is an important regulatory protein involved in the necroptosis and inhibition of this protein is essential to stop necroptotic process and eventually cell death. Current structure-based virtual screening methods involve a wide range of strategies and recently, considering the multiple protein structures for pharmacophore extraction has been emphasized as a way to improve the outcome. However, using the pharmacophoric information completely during docking is very important. Further, in such methods, using the appropriate protein structures for docking is desirable. If not, potential compound hits, obtained through pharmacophore-based screening, may not have correct ranks and scores after docking. Therefore, a comprehensive integration of different ensemble methods is essential, which may provide better virtual screening results. In this study, dual ensemble screening, a novel computational strategy was used to identify diverse and potent inhibitors against RIPK1. All the pharmacophore features present in the binding site were captured using both the apo and holo protein structures and an ensemble pharmacophore was built by combining these features. This ensemble pharmacophore was employed in pharmacophore-based screening of ZINC database. The compound hits, thus obtained, were subjected to ensemble docking. The leads acquired through docking were further validated through feature evaluation and molecular dynamics simulation.

Multiclass cancer classification using a feature subset-based ensemble from microRNA expression profiles.

PubMed

Piao, Yongjun; Piao, Minghao; Ryu, Keun Ho

2017-01-01

Cancer classification has been a crucial topic of research in cancer treatment. In the last decade, messenger RNA (mRNA) expression profiles have been widely used to classify different types of cancers. With the discovery of a new class of small non-coding RNAs; known as microRNAs (miRNAs), various studies have shown that the expression patterns of miRNA can also accurately classify human cancers. Therefore, there is a great demand for the development of machine learning approaches to accurately classify various types of cancers using miRNA expression data. In this article, we propose a feature subset-based ensemble method in which each model is learned from a different projection of the original feature space to classify multiple cancers. In our method, the feature relevance and redundancy are considered to generate multiple feature subsets, the base classifiers are learned from each independent miRNA subset, and the average posterior probability is used to combine the base classifiers. To test the performance of our method, we used bead-based and sequence-based miRNA expression datasets and conducted 10-fold and leave-one-out cross validations. The experimental results show that the proposed method yields good results and has higher prediction accuracy than popular ensemble methods. The Java program and source code of the proposed method and the datasets in the experiments are freely available at https://sourceforge.net/projects/mirna-ensemble/. Copyright © 2016 Elsevier Ltd. All rights reserved.

Project FIRES. Volume 1: Program Overview and Summary, Phase 1B

NASA Technical Reports Server (NTRS)

Abeles, F. J.

1980-01-01

Overall performance requirements and evaluation methods for firefighters protective equipment were established and published as the Protective Ensemble Performance Standards (PEPS). Current firefighters protective equipment was tested and evaluated against the PEPS requirements, and the preliminary design of a prototype protective ensemble was performed. In phase 1B, the design of the prototype ensemble was finalized. Prototype ensembles were fabricated and then subjected to a series of qualification tests which were based upon the PEPS requirements. Engineering drawings and purchase specifications were prepared for the new protective ensemble.

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks.

PubMed

Zhang, Cuicui; Liang, Xuefeng; Matsuyama, Takashi

2014-12-08

Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the "small sample size" (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0-1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system.

Generic Learning-Based Ensemble Framework for Small Sample Size Face Recognition in Multi-Camera Networks

PubMed Central

Zhang, Cuicui; Liang, Xuefeng; Matsuyama, Takashi

2014-01-01

Multi-camera networks have gained great interest in video-based surveillance systems for security monitoring, access control, etc. Person re-identification is an essential and challenging task in multi-camera networks, which aims to determine if a given individual has already appeared over the camera network. Individual recognition often uses faces as a trial and requires a large number of samples during the training phrase. This is difficult to fulfill due to the limitation of the camera hardware system and the unconstrained image capturing conditions. Conventional face recognition algorithms often encounter the “small sample size” (SSS) problem arising from the small number of training samples compared to the high dimensionality of the sample space. To overcome this problem, interest in the combination of multiple base classifiers has sparked research efforts in ensemble methods. However, existing ensemble methods still open two questions: (1) how to define diverse base classifiers from the small data; (2) how to avoid the diversity/accuracy dilemma occurring during ensemble. To address these problems, this paper proposes a novel generic learning-based ensemble framework, which augments the small data by generating new samples based on a generic distribution and introduces a tailored 0–1 knapsack algorithm to alleviate the diversity/accuracy dilemma. More diverse base classifiers can be generated from the expanded face space, and more appropriate base classifiers are selected for ensemble. Extensive experimental results on four benchmarks demonstrate the higher ability of our system to cope with the SSS problem compared to the state-of-the-art system. PMID:25494350

A fuzzy integral method based on the ensemble of neural networks to analyze fMRI data for cognitive state classification across multiple subjects.

PubMed

Cacha, L A; Parida, S; Dehuri, S; Cho, S-B; Poznanski, R R

2016-12-01

The huge number of voxels in fMRI over time poses a major challenge to for effective analysis. Fast, accurate, and reliable classifiers are required for estimating the decoding accuracy of brain activities. Although machine-learning classifiers seem promising, individual classifiers have their own limitations. To address this limitation, the present paper proposes a method based on the ensemble of neural networks to analyze fMRI data for cognitive state classification for application across multiple subjects. Similarly, the fuzzy integral (FI) approach has been employed as an efficient tool for combining different classifiers. The FI approach led to the development of a classifiers ensemble technique that performs better than any of the single classifier by reducing the misclassification, the bias, and the variance. The proposed method successfully classified the different cognitive states for multiple subjects with high accuracy of classification. Comparison of the performance improvement, while applying ensemble neural networks method, vs. that of the individual neural network strongly points toward the usefulness of the proposed method.

Discrete post-processing of total cloud cover ensemble forecasts

NASA Astrophysics Data System (ADS)

Hemri, Stephan; Haiden, Thomas; Pappenberger, Florian

2017-04-01

This contribution presents an approach to post-process ensemble forecasts for the discrete and bounded weather variable of total cloud cover. Two methods for discrete statistical post-processing of ensemble predictions are tested. The first approach is based on multinomial logistic regression, the second involves a proportional odds logistic regression model. Applying them to total cloud cover raw ensemble forecasts from the European Centre for Medium-Range Weather Forecasts improves forecast skill significantly. Based on station-wise post-processing of raw ensemble total cloud cover forecasts for a global set of 3330 stations over the period from 2007 to early 2014, the more parsimonious proportional odds logistic regression model proved to slightly outperform the multinomial logistic regression model. Reference Hemri, S., Haiden, T., & Pappenberger, F. (2016). Discrete post-processing of total cloud cover ensemble forecasts. Monthly Weather Review 144, 2565-2577.

A hybrid filtering method based on a novel empirical mode decomposition for friction signals

NASA Astrophysics Data System (ADS)

Li, Chengwei; Zhan, Liwei

2015-12-01

During a measurement, the measured signal usually contains noise. To remove the noise and preserve the important feature of the signal, we introduce a hybrid filtering method that uses a new intrinsic mode function (NIMF) and a modified Hausdorff distance. The NIMF is defined as the difference between the noisy signal and each intrinsic mode function (IMF), which is obtained by empirical mode decomposition (EMD), ensemble EMD, complementary ensemble EMD, or complete ensemble EMD with adaptive noise (CEEMDAN). The relevant mode selecting is based on the similarity between the first NIMF and the rest of the NIMFs. With this filtering method, the EMD and improved versions are used to filter the simulation and friction signals. The friction signal between an airplane tire and the runaway is recorded during a simulated airplane touchdown and features spikes of various amplitudes and noise. The filtering effectiveness of the four hybrid filtering methods are compared and discussed. The results show that the filtering method based on CEEMDAN outperforms other signal filtering methods.

Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble-based methods?

PubMed Central

Austin, Peter C; Lee, Douglas S; Steyerberg, Ewout W; Tu, Jack V

2012-01-01

In biomedical research, the logistic regression model is the most commonly used method for predicting the probability of a binary outcome. While many clinical researchers have expressed an enthusiasm for regression trees, this method may have limited accuracy for predicting health outcomes. We aimed to evaluate the improvement that is achieved by using ensemble-based methods, including bootstrap aggregation (bagging) of regression trees, random forests, and boosted regression trees. We analyzed 30-day mortality in two large cohorts of patients hospitalized with either acute myocardial infarction (N = 16,230) or congestive heart failure (N = 15,848) in two distinct eras (1999–2001 and 2004–2005). We found that both the in-sample and out-of-sample prediction of ensemble methods offered substantial improvement in predicting cardiovascular mortality compared to conventional regression trees. However, conventional logistic regression models that incorporated restricted cubic smoothing splines had even better performance. We conclude that ensemble methods from the data mining and machine learning literature increase the predictive performance of regression trees, but may not lead to clear advantages over conventional logistic regression models for predicting short-term mortality in population-based samples of subjects with cardiovascular disease. PMID:22777999

Numerical weather prediction model tuning via ensemble prediction system

NASA Astrophysics Data System (ADS)

Jarvinen, H.; Laine, M.; Ollinaho, P.; Solonen, A.; Haario, H.

2011-12-01

This paper discusses a novel approach to tune predictive skill of numerical weather prediction (NWP) models. NWP models contain tunable parameters which appear in parameterizations schemes of sub-grid scale physical processes. Currently, numerical values of these parameters are specified manually. In a recent dual manuscript (QJRMS, revised) we developed a new concept and method for on-line estimation of the NWP model parameters. The EPPES ("Ensemble prediction and parameter estimation system") method requires only minimal changes to the existing operational ensemble prediction infra-structure and it seems very cost-effective because practically no new computations are introduced. The approach provides an algorithmic decision making tool for model parameter optimization in operational NWP. In EPPES, statistical inference about the NWP model tunable parameters is made by (i) generating each member of the ensemble of predictions using different model parameter values, drawn from a proposal distribution, and (ii) feeding-back the relative merits of the parameter values to the proposal distribution, based on evaluation of a suitable likelihood function against verifying observations. In the presentation, the method is first illustrated in low-order numerical tests using a stochastic version of the Lorenz-95 model which effectively emulates the principal features of ensemble prediction systems. The EPPES method correctly detects the unknown and wrongly specified parameters values, and leads to an improved forecast skill. Second, results with an atmospheric general circulation model based ensemble prediction system show that the NWP model tuning capacity of EPPES scales up to realistic models and ensemble prediction systems. Finally, a global top-end NWP model tuning exercise with preliminary results is published.

HLPI-Ensemble: Prediction of human lncRNA-protein interactions based on ensemble strategy.

PubMed

Hu, Huan; Zhang, Li; Ai, Haixin; Zhang, Hui; Fan, Yetian; Zhao, Qi; Liu, Hongsheng

2018-03-27

LncRNA plays an important role in many biological and disease progression by binding to related proteins. However, the experimental methods for studying lncRNA-protein interactions are time-consuming and expensive. Although there are a few models designed to predict the interactions of ncRNA-protein, they all have some common drawbacks that limit their predictive performance. In this study, we present a model called HLPI-Ensemble designed specifically for human lncRNA-protein interactions. HLPI-Ensemble adopts the ensemble strategy based on three mainstream machine learning algorithms of Support Vector Machines (SVM), Random Forests (RF) and Extreme Gradient Boosting (XGB) to generate HLPI-SVM Ensemble, HLPI-RF Ensemble and HLPI-XGB Ensemble, respectively. The results of 10-fold cross-validation show that HLPI-SVM Ensemble, HLPI-RF Ensemble and HLPI-XGB Ensemble achieved AUCs of 0.95, 0.96 and 0.96, respectively, in the test dataset. Furthermore, we compared the performance of the HLPI-Ensemble models with the previous models through external validation dataset. The results show that the false positives (FPs) of HLPI-Ensemble models are much lower than that of the previous models, and other evaluation indicators of HLPI-Ensemble models are also higher than those of the previous models. It is further showed that HLPI-Ensemble models are superior in predicting human lncRNA-protein interaction compared with previous models. The HLPI-Ensemble is publicly available at: http://ccsipb.lnu.edu.cn/hlpiensemble/ .

Comparison of numerical weather prediction based deterministic and probabilistic wind resource assessment methods

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

Zhang, Jie; Draxl, Caroline; Hopson, Thomas

Numerical weather prediction (NWP) models have been widely used for wind resource assessment. Model runs with higher spatial resolution are generally more accurate, yet extremely computational expensive. An alternative approach is to use data generated by a low resolution NWP model, in conjunction with statistical methods. In order to analyze the accuracy and computational efficiency of different types of NWP-based wind resource assessment methods, this paper performs a comparison of three deterministic and probabilistic NWP-based wind resource assessment methodologies: (i) a coarse resolution (0.5 degrees x 0.67 degrees) global reanalysis data set, the Modern-Era Retrospective Analysis for Research and Applicationsmore » (MERRA); (ii) an analog ensemble methodology based on the MERRA, which provides both deterministic and probabilistic predictions; and (iii) a fine resolution (2-km) NWP data set, the Wind Integration National Dataset (WIND) Toolkit, based on the Weather Research and Forecasting model. Results show that: (i) as expected, the analog ensemble and WIND Toolkit perform significantly better than MERRA confirming their ability to downscale coarse estimates; (ii) the analog ensemble provides the best estimate of the multi-year wind distribution at seven of the nine sites, while the WIND Toolkit is the best at one site; (iii) the WIND Toolkit is more accurate in estimating the distribution of hourly wind speed differences, which characterizes the wind variability, at five of the available sites, with the analog ensemble being best at the remaining four locations; and (iv) the analog ensemble computational cost is negligible, whereas the WIND Toolkit requires large computational resources. Future efforts could focus on the combination of the analog ensemble with intermediate resolution (e.g., 10-15 km) NWP estimates, to considerably reduce the computational burden, while providing accurate deterministic estimates and reliable probabilistic assessments.« less

An Ensemble-Based Smoother with Retrospectively Updated Weights for Highly Nonlinear Systems

NASA Technical Reports Server (NTRS)

Chin, T. M.; Turmon, M. J.; Jewell, J. B.; Ghil, M.

2006-01-01

Monte Carlo computational methods have been introduced into data assimilation for nonlinear systems in order to alleviate the computational burden of updating and propagating the full probability distribution. By propagating an ensemble of representative states, algorithms like the ensemble Kalman filter (EnKF) and the resampled particle filter (RPF) rely on the existing modeling infrastructure to approximate the distribution based on the evolution of this ensemble. This work presents an ensemble-based smoother that is applicable to the Monte Carlo filtering schemes like EnKF and RPF. At the minor cost of retrospectively updating a set of weights for ensemble members, this smoother has demonstrated superior capabilities in state tracking for two highly nonlinear problems: the double-well potential and trivariate Lorenz systems. The algorithm does not require retrospective adaptation of the ensemble members themselves, and it is thus suited to a streaming operational mode. The accuracy of the proposed backward-update scheme in estimating non-Gaussian distributions is evaluated by comparison to the more accurate estimates provided by a Markov chain Monte Carlo algorithm.

Ligand-biased ensemble receptor docking (LigBEnD): a hybrid ligand/receptor structure-based approach

NASA Astrophysics Data System (ADS)

Lam, Polo C.-H.; Abagyan, Ruben; Totrov, Maxim

2018-01-01

Ligand docking to flexible protein molecules can be efficiently carried out through ensemble docking to multiple protein conformations, either from experimental X-ray structures or from in silico simulations. The success of ensemble docking often requires the careful selection of complementary protein conformations, through docking and scoring of known co-crystallized ligands. False positives, in which a ligand in a wrong pose achieves a better docking score than that of native pose, arise as additional protein conformations are added. In the current study, we developed a new ligand-biased ensemble receptor docking method and composite scoring function which combine the use of ligand-based atomic property field (APF) method with receptor structure-based docking. This method helps us to correctly dock 30 out of 36 ligands presented by the D3R docking challenge. For the six mis-docked ligands, the cognate receptor structures prove to be too different from the 40 available experimental Pocketome conformations used for docking and could be identified only by receptor sampling beyond experimentally explored conformational subspace.

A comparison of ensemble post-processing approaches that preserve correlation structures

NASA Astrophysics Data System (ADS)

Schefzik, Roman; Van Schaeybroeck, Bert; Vannitsem, Stéphane

2016-04-01

Despite the fact that ensemble forecasts address the major sources of uncertainty, they exhibit biases and dispersion errors and therefore are known to improve by calibration or statistical post-processing. For instance the ensemble model output statistics (EMOS) method, also known as non-homogeneous regression approach (Gneiting et al., 2005) is known to strongly improve forecast skill. EMOS is based on fitting and adjusting a parametric probability density function (PDF). However, EMOS and other common post-processing approaches apply to a single weather quantity at a single location for a single look-ahead time. They are therefore unable of taking into account spatial, inter-variable and temporal dependence structures. Recently many research efforts have been invested in designing post-processing methods that resolve this drawback but also in verification methods that enable the detection of dependence structures. New verification methods are applied on two classes of post-processing methods, both generating physically coherent ensembles. A first class uses the ensemble copula coupling (ECC) that starts from EMOS but adjusts the rank structure (Schefzik et al., 2013). The second class is a member-by-member post-processing (MBM) approach that maps each raw ensemble member to a corrected one (Van Schaeybroeck and Vannitsem, 2015). We compare variants of the EMOS-ECC and MBM classes and highlight a specific theoretical connection between them. All post-processing variants are applied in the context of the ensemble system of the European Centre of Weather Forecasts (ECMWF) and compared using multivariate verification tools including the energy score, the variogram score (Scheuerer and Hamill, 2015) and the band depth rank histogram (Thorarinsdottir et al., 2015). Gneiting, Raftery, Westveld, and Goldman, 2005: Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation. Mon. Wea. Rev., {133}, 1098-1118. Scheuerer and Hamill, 2015. Variogram-based proper scoring rules for probabilistic forecasts of multivariate quantities. Mon. Wea. Rev. {143},1321-1334. Schefzik, Thorarinsdottir, Gneiting. Uncertainty quantification in complex simulation models using ensemble copula coupling. Statistical Science {28},616-640, 2013. Thorarinsdottir, M. Scheuerer, and C. Heinz, 2015. Assessing the calibration of high-dimensional ensemble forecasts using rank histograms, arXiv:1310.0236. Van Schaeybroeck and Vannitsem, 2015: Ensemble post-processing using member-by-member approaches: theoretical aspects. Q.J.R. Meteorol. Soc., 141: 807-818.

Skill of Global Raw and Postprocessed Ensemble Predictions of Rainfall over Northern Tropical Africa

NASA Astrophysics Data System (ADS)

Vogel, Peter; Knippertz, Peter; Fink, Andreas H.; Schlueter, Andreas; Gneiting, Tilmann

2018-04-01

Accumulated precipitation forecasts are of high socioeconomic importance for agriculturally dominated societies in northern tropical Africa. In this study, we analyze the performance of nine operational global ensemble prediction systems (EPSs) relative to climatology-based forecasts for 1 to 5-day accumulated precipitation based on the monsoon seasons 2007-2014 for three regions within northern tropical Africa. To assess the full potential of raw ensemble forecasts across spatial scales, we apply state-of-the-art statistical postprocessing methods in form of Bayesian Model Averaging (BMA) and Ensemble Model Output Statistics (EMOS), and verify against station and spatially aggregated, satellite-based gridded observations. Raw ensemble forecasts are uncalibrated, unreliable, and underperform relative to climatology, independently of region, accumulation time, monsoon season, and ensemble. Differences between raw ensemble and climatological forecasts are large, and partly stem from poor prediction for low precipitation amounts. BMA and EMOS postprocessed forecasts are calibrated, reliable, and strongly improve on the raw ensembles, but - somewhat disappointingly - typically do not outperform climatology. Most EPSs exhibit slight improvements over the period 2007-2014, but overall have little added value compared to climatology. We suspect that the parametrization of convection is a potential cause for the sobering lack of ensemble forecast skill in a region dominated by mesoscale convective systems.

Human resource recommendation algorithm based on ensemble learning and Spark

NASA Astrophysics Data System (ADS)

Cong, Zihan; Zhang, Xingming; Wang, Haoxiang; Xu, Hongjie

2017-08-01

Aiming at the problem of “information overload” in the human resources industry, this paper proposes a human resource recommendation algorithm based on Ensemble Learning. The algorithm considers the characteristics and behaviours of both job seeker and job features in the real business circumstance. Firstly, the algorithm uses two ensemble learning methods-Bagging and Boosting. The outputs from both learning methods are then merged to form user interest model. Based on user interest model, job recommendation can be extracted for users. The algorithm is implemented as a parallelized recommendation system on Spark. A set of experiments have been done and analysed. The proposed algorithm achieves significant improvement in accuracy, recall rate and coverage, compared with recommendation algorithms such as UserCF and ItemCF.

Probabilistic precipitation nowcasting based on an extrapolation of radar reflectivity and an ensemble approach

NASA Astrophysics Data System (ADS)

Sokol, Zbyněk; Mejsnar, Jan; Pop, Lukáš; Bližňák, Vojtěch

2017-09-01

A new method for the probabilistic nowcasting of instantaneous rain rates (ENS) based on the ensemble technique and extrapolation along Lagrangian trajectories of current radar reflectivity is presented. Assuming inaccurate forecasts of the trajectories, an ensemble of precipitation forecasts is calculated and used to estimate the probability that rain rates will exceed a given threshold in a given grid point. Although the extrapolation neglects the growth and decay of precipitation, their impact on the probability forecast is taken into account by the calibration of forecasts using the reliability component of the Brier score (BS). ENS forecasts the probability that the rain rates will exceed thresholds of 0.1, 1.0 and 3.0 mm/h in squares of 3 km by 3 km. The lead times were up to 60 min, and the forecast accuracy was measured by the BS. The ENS forecasts were compared with two other methods: combined method (COM) and neighbourhood method (NEI). NEI considered the extrapolated values in the square neighbourhood of 5 by 5 grid points of the point of interest as ensemble members, and the COM ensemble was comprised of united ensemble members of ENS and NEI. The results showed that the calibration technique significantly improves bias of the probability forecasts by including additional uncertainties that correspond to neglected processes during the extrapolation. In addition, the calibration can also be used for finding the limits of maximum lead times for which the forecasting method is useful. We found that ENS is useful for lead times up to 60 min for thresholds of 0.1 and 1 mm/h and approximately 30 to 40 min for a threshold of 3 mm/h. We also found that a reasonable size of the ensemble is 100 members, which provided better scores than ensembles with 10, 25 and 50 members. In terms of the BS, the best results were obtained by ENS and COM, which are comparable. However, ENS is better calibrated and thus preferable.

Efficient Agent-Based Cluster Ensembles

NASA Technical Reports Server (NTRS)

Agogino, Adrian; Tumer, Kagan

2006-01-01

Numerous domains ranging from distributed data acquisition to knowledge reuse need to solve the cluster ensemble problem of combining multiple clusterings into a single unified clustering. Unfortunately current non-agent-based cluster combining methods do not work in a distributed environment, are not robust to corrupted clusterings and require centralized access to all original clusterings. Overcoming these issues will allow cluster ensembles to be used in fundamentally distributed and failure-prone domains such as data acquisition from satellite constellations, in addition to domains demanding confidentiality such as combining clusterings of user profiles. This paper proposes an efficient, distributed, agent-based clustering ensemble method that addresses these issues. In this approach each agent is assigned a small subset of the data and votes on which final cluster its data points should belong to. The final clustering is then evaluated by a global utility, computed in a distributed way. This clustering is also evaluated using an agent-specific utility that is shown to be easier for the agents to maximize. Results show that agents using the agent-specific utility can achieve better performance than traditional non-agent based methods and are effective even when up to 50% of the agents fail.

Rain radar measurement error estimation using data assimilation in an advection-based nowcasting system

NASA Astrophysics Data System (ADS)

Merker, Claire; Ament, Felix; Clemens, Marco

2017-04-01

The quantification of measurement uncertainty for rain radar data remains challenging. Radar reflectivity measurements are affected, amongst other things, by calibration errors, noise, blocking and clutter, and attenuation. Their combined impact on measurement accuracy is difficult to quantify due to incomplete process understanding and complex interdependencies. An improved quality assessment of rain radar measurements is of interest for applications both in meteorology and hydrology, for example for precipitation ensemble generation, rainfall runoff simulations, or in data assimilation for numerical weather prediction. Especially a detailed description of the spatial and temporal structure of errors is beneficial in order to make best use of the areal precipitation information provided by radars. Radar precipitation ensembles are one promising approach to represent spatially variable radar measurement errors. We present a method combining ensemble radar precipitation nowcasting with data assimilation to estimate radar measurement uncertainty at each pixel. This combination of ensemble forecast and observation yields a consistent spatial and temporal evolution of the radar error field. We use an advection-based nowcasting method to generate an ensemble reflectivity forecast from initial data of a rain radar network. Subsequently, reflectivity data from single radars is assimilated into the forecast using the Local Ensemble Transform Kalman Filter. The spread of the resulting analysis ensemble provides a flow-dependent, spatially and temporally correlated reflectivity error estimate at each pixel. We will present first case studies that illustrate the method using data from a high-resolution X-band radar network.

Constructing better classifier ensemble based on weighted accuracy and diversity measure.

PubMed

Zeng, Xiaodong; Wong, Derek F; Chao, Lidia S

2014-01-01

A weighted accuracy and diversity (WAD) method is presented, a novel measure used to evaluate the quality of the classifier ensemble, assisting in the ensemble selection task. The proposed measure is motivated by a commonly accepted hypothesis; that is, a robust classifier ensemble should not only be accurate but also different from every other member. In fact, accuracy and diversity are mutual restraint factors; that is, an ensemble with high accuracy may have low diversity, and an overly diverse ensemble may negatively affect accuracy. This study proposes a method to find the balance between accuracy and diversity that enhances the predictive ability of an ensemble for unknown data. The quality assessment for an ensemble is performed such that the final score is achieved by computing the harmonic mean of accuracy and diversity, where two weight parameters are used to balance them. The measure is compared to two representative measures, Kappa-Error and GenDiv, and two threshold measures that consider only accuracy or diversity, with two heuristic search algorithms, genetic algorithm, and forward hill-climbing algorithm, in ensemble selection tasks performed on 15 UCI benchmark datasets. The empirical results demonstrate that the WAD measure is superior to others in most cases.

Constructing Better Classifier Ensemble Based on Weighted Accuracy and Diversity Measure

PubMed Central

Chao, Lidia S.

2014-01-01

A weighted accuracy and diversity (WAD) method is presented, a novel measure used to evaluate the quality of the classifier ensemble, assisting in the ensemble selection task. The proposed measure is motivated by a commonly accepted hypothesis; that is, a robust classifier ensemble should not only be accurate but also different from every other member. In fact, accuracy and diversity are mutual restraint factors; that is, an ensemble with high accuracy may have low diversity, and an overly diverse ensemble may negatively affect accuracy. This study proposes a method to find the balance between accuracy and diversity that enhances the predictive ability of an ensemble for unknown data. The quality assessment for an ensemble is performed such that the final score is achieved by computing the harmonic mean of accuracy and diversity, where two weight parameters are used to balance them. The measure is compared to two representative measures, Kappa-Error and GenDiv, and two threshold measures that consider only accuracy or diversity, with two heuristic search algorithms, genetic algorithm, and forward hill-climbing algorithm, in ensemble selection tasks performed on 15 UCI benchmark datasets. The empirical results demonstrate that the WAD measure is superior to others in most cases. PMID:24672402

Encoding of Spatial Attention by Primate Prefrontal Cortex Neuronal Ensembles

PubMed Central

Treue, Stefan

2018-01-01

Abstract Single neurons in the primate lateral prefrontal cortex (LPFC) encode information about the allocation of visual attention and the features of visual stimuli. However, how this compares to the performance of neuronal ensembles at encoding the same information is poorly understood. Here, we recorded the responses of neuronal ensembles in the LPFC of two macaque monkeys while they performed a task that required attending to one of two moving random dot patterns positioned in different hemifields and ignoring the other pattern. We found single units selective for the location of the attended stimulus as well as for its motion direction. To determine the coding of both variables in the population of recorded units, we used a linear classifier and progressively built neuronal ensembles by iteratively adding units according to their individual performance (best single units), or by iteratively adding units based on their contribution to the ensemble performance (best ensemble). For both methods, ensembles of relatively small sizes (n < 60) yielded substantially higher decoding performance relative to individual single units. However, the decoder reached similar performance using fewer neurons with the best ensemble building method compared with the best single units method. Our results indicate that neuronal ensembles within the LPFC encode more information about the attended spatial and nonspatial features of visual stimuli than individual neurons. They further suggest that efficient coding of attention can be achieved by relatively small neuronal ensembles characterized by a certain relationship between signal and noise correlation structures. PMID:29568798

A Random Forest-based ensemble method for activity recognition.

PubMed

Feng, Zengtao; Mo, Lingfei; Li, Meng

2015-01-01

This paper presents a multi-sensor ensemble approach to human physical activity (PA) recognition, using random forest. We designed an ensemble learning algorithm, which integrates several independent Random Forest classifiers based on different sensor feature sets to build a more stable, more accurate and faster classifier for human activity recognition. To evaluate the algorithm, PA data collected from the PAMAP (Physical Activity Monitoring for Aging People), which is a standard, publicly available database, was utilized to train and test. The experimental results show that the algorithm is able to correctly recognize 19 PA types with an accuracy of 93.44%, while the training is faster than others. The ensemble classifier system based on the RF (Random Forest) algorithm can achieve high recognition accuracy and fast calculation.

Evaluation of medium-range ensemble flood forecasting based on calibration strategies and ensemble methods in Lanjiang Basin, Southeast China

NASA Astrophysics Data System (ADS)

Liu, Li; Gao, Chao; Xuan, Weidong; Xu, Yue-Ping

2017-11-01

Ensemble flood forecasts by hydrological models using numerical weather prediction products as forcing data are becoming more commonly used in operational flood forecasting applications. In this study, a hydrological ensemble flood forecasting system comprised of an automatically calibrated Variable Infiltration Capacity model and quantitative precipitation forecasts from TIGGE dataset is constructed for Lanjiang Basin, Southeast China. The impacts of calibration strategies and ensemble methods on the performance of the system are then evaluated. The hydrological model is optimized by the parallel programmed ε-NSGA II multi-objective algorithm. According to the solutions by ε-NSGA II, two differently parameterized models are determined to simulate daily flows and peak flows at each of the three hydrological stations. Then a simple yet effective modular approach is proposed to combine these daily and peak flows at the same station into one composite series. Five ensemble methods and various evaluation metrics are adopted. The results show that ε-NSGA II can provide an objective determination on parameter estimation, and the parallel program permits a more efficient simulation. It is also demonstrated that the forecasts from ECMWF have more favorable skill scores than other Ensemble Prediction Systems. The multimodel ensembles have advantages over all the single model ensembles and the multimodel methods weighted on members and skill scores outperform other methods. Furthermore, the overall performance at three stations can be satisfactory up to ten days, however the hydrological errors can degrade the skill score by approximately 2 days, and the influence persists until a lead time of 10 days with a weakening trend. With respect to peak flows selected by the Peaks Over Threshold approach, the ensemble means from single models or multimodels are generally underestimated, indicating that the ensemble mean can bring overall improvement in forecasting of flows. For peak values taking flood forecasts from each individual member into account is more appropriate.

NWP model forecast skill optimization via closure parameter variations

NASA Astrophysics Data System (ADS)

Järvinen, H.; Ollinaho, P.; Laine, M.; Solonen, A.; Haario, H.

2012-04-01

We present results of a novel approach to tune predictive skill of numerical weather prediction (NWP) models. These models contain tunable parameters which appear in parameterizations schemes of sub-grid scale physical processes. The current practice is to specify manually the numerical parameter values, based on expert knowledge. We developed recently a concept and method (QJRMS 2011) for on-line estimation of the NWP model parameters via closure parameter variations. The method called EPPES ("Ensemble prediction and parameter estimation system") utilizes ensemble prediction infra-structure for parameter estimation in a very cost-effective way: practically no new computations are introduced. The approach provides an algorithmic decision making tool for model parameter optimization in operational NWP. In EPPES, statistical inference about the NWP model tunable parameters is made by (i) generating an ensemble of predictions so that each member uses different model parameter values, drawn from a proposal distribution, and (ii) feeding-back the relative merits of the parameter values to the proposal distribution, based on evaluation of a suitable likelihood function against verifying observations. In this presentation, the method is first illustrated in low-order numerical tests using a stochastic version of the Lorenz-95 model which effectively emulates the principal features of ensemble prediction systems. The EPPES method correctly detects the unknown and wrongly specified parameters values, and leads to an improved forecast skill. Second, results with an ensemble prediction system emulator, based on the ECHAM5 atmospheric GCM show that the model tuning capability of EPPES scales up to realistic models and ensemble prediction systems. Finally, preliminary results of EPPES in the context of ECMWF forecasting system are presented.

NIMEFI: gene regulatory network inference using multiple ensemble feature importance algorithms.

PubMed

Ruyssinck, Joeri; Huynh-Thu, Vân Anh; Geurts, Pierre; Dhaene, Tom; Demeester, Piet; Saeys, Yvan

2014-01-01

One of the long-standing open challenges in computational systems biology is the topology inference of gene regulatory networks from high-throughput omics data. Recently, two community-wide efforts, DREAM4 and DREAM5, have been established to benchmark network inference techniques using gene expression measurements. In these challenges the overall top performer was the GENIE3 algorithm. This method decomposes the network inference task into separate regression problems for each gene in the network in which the expression values of a particular target gene are predicted using all other genes as possible predictors. Next, using tree-based ensemble methods, an importance measure for each predictor gene is calculated with respect to the target gene and a high feature importance is considered as putative evidence of a regulatory link existing between both genes. The contribution of this work is twofold. First, we generalize the regression decomposition strategy of GENIE3 to other feature importance methods. We compare the performance of support vector regression, the elastic net, random forest regression, symbolic regression and their ensemble variants in this setting to the original GENIE3 algorithm. To create the ensemble variants, we propose a subsampling approach which allows us to cast any feature selection algorithm that produces a feature ranking into an ensemble feature importance algorithm. We demonstrate that the ensemble setting is key to the network inference task, as only ensemble variants achieve top performance. As second contribution, we explore the effect of using rankwise averaged predictions of multiple ensemble algorithms as opposed to only one. We name this approach NIMEFI (Network Inference using Multiple Ensemble Feature Importance algorithms) and show that this approach outperforms all individual methods in general, although on a specific network a single method can perform better. An implementation of NIMEFI has been made publicly available.

AUC-based biomarker ensemble with an application on gene scores predicting low bone mineral density.

PubMed

Zhao, X G; Dai, W; Li, Y; Tian, L

2011-11-01

The area under the receiver operating characteristic (ROC) curve (AUC), long regarded as a 'golden' measure for the predictiveness of a continuous score, has propelled the need to develop AUC-based predictors. However, the AUC-based ensemble methods are rather scant, largely due to the fact that the associated objective function is neither continuous nor concave. Indeed, there is no reliable numerical algorithm identifying optimal combination of a set of biomarkers to maximize the AUC, especially when the number of biomarkers is large. We have proposed a novel AUC-based statistical ensemble methods for combining multiple biomarkers to differentiate a binary response of interest. Specifically, we propose to replace the non-continuous and non-convex AUC objective function by a convex surrogate loss function, whose minimizer can be efficiently identified. With the established framework, the lasso and other regularization techniques enable feature selections. Extensive simulations have demonstrated the superiority of the new methods to the existing methods. The proposal has been applied to a gene expression dataset to construct gene expression scores to differentiate elderly women with low bone mineral density (BMD) and those with normal BMD. The AUCs of the resulting scores in the independent test dataset has been satisfactory. Aiming for directly maximizing AUC, the proposed AUC-based ensemble method provides an efficient means of generating a stable combination of multiple biomarkers, which is especially useful under the high-dimensional settings. lutian@stanford.edu. Supplementary data are available at Bioinformatics online.

Drug-target interaction prediction using ensemble learning and dimensionality reduction.

PubMed

Ezzat, Ali; Wu, Min; Li, Xiao-Li; Kwoh, Chee-Keong

2017-10-01

Experimental prediction of drug-target interactions is expensive, time-consuming and tedious. Fortunately, computational methods help narrow down the search space for interaction candidates to be further examined via wet-lab techniques. Nowadays, the number of attributes/features for drugs and targets, as well as the amount of their interactions, are increasing, making these computational methods inefficient or occasionally prohibitive. This motivates us to derive a reduced feature set for prediction. In addition, since ensemble learning techniques are widely used to improve the classification performance, it is also worthwhile to design an ensemble learning framework to enhance the performance for drug-target interaction prediction. In this paper, we propose a framework for drug-target interaction prediction leveraging both feature dimensionality reduction and ensemble learning. First, we conducted feature subspacing to inject diversity into the classifier ensemble. Second, we applied three different dimensionality reduction methods to the subspaced features. Third, we trained homogeneous base learners with the reduced features and then aggregated their scores to derive the final predictions. For base learners, we selected two classifiers, namely Decision Tree and Kernel Ridge Regression, resulting in two variants of ensemble models, EnsemDT and EnsemKRR, respectively. In our experiments, we utilized AUC (Area under ROC Curve) as an evaluation metric. We compared our proposed methods with various state-of-the-art methods under 5-fold cross validation. Experimental results showed EnsemKRR achieving the highest AUC (94.3%) for predicting drug-target interactions. In addition, dimensionality reduction helped improve the performance of EnsemDT. In conclusion, our proposed methods produced significant improvements for drug-target interaction prediction. Copyright © 2017 Elsevier Inc. All rights reserved.

Cluster ensemble based on Random Forests for genetic data.

PubMed

Alhusain, Luluah; Hafez, Alaaeldin M

2017-01-01

Clustering plays a crucial role in several application domains, such as bioinformatics. In bioinformatics, clustering has been extensively used as an approach for detecting interesting patterns in genetic data. One application is population structure analysis, which aims to group individuals into subpopulations based on shared genetic variations, such as single nucleotide polymorphisms. Advances in DNA sequencing technology have facilitated the obtainment of genetic datasets with exceptional sizes. Genetic data usually contain hundreds of thousands of genetic markers genotyped for thousands of individuals, making an efficient means for handling such data desirable. Random Forests (RFs) has emerged as an efficient algorithm capable of handling high-dimensional data. RFs provides a proximity measure that can capture different levels of co-occurring relationships between variables. RFs has been widely considered a supervised learning method, although it can be converted into an unsupervised learning method. Therefore, RF-derived proximity measure combined with a clustering technique may be well suited for determining the underlying structure of unlabeled data. This paper proposes, RFcluE, a cluster ensemble approach for determining the underlying structure of genetic data based on RFs. The approach comprises a cluster ensemble framework to combine multiple runs of RF clustering. Experiments were conducted on high-dimensional, real genetic dataset to evaluate the proposed approach. The experiments included an examination of the impact of parameter changes, comparing RFcluE performance against other clustering methods, and an assessment of the relationship between the diversity and quality of the ensemble and its effect on RFcluE performance. This paper proposes, RFcluE, a cluster ensemble approach based on RF clustering to address the problem of population structure analysis and demonstrate the effectiveness of the approach. The paper also illustrates that applying a cluster ensemble approach, combining multiple RF clusterings, produces more robust and higher-quality results as a consequence of feeding the ensemble with diverse views of high-dimensional genetic data obtained through bagging and random subspace, the two key features of the RF algorithm.

Towards an improved ensemble precipitation forecast: A probabilistic post-processing approach

NASA Astrophysics Data System (ADS)

Khajehei, Sepideh; Moradkhani, Hamid

2017-03-01

Recently, ensemble post-processing (EPP) has become a commonly used approach for reducing the uncertainty in forcing data and hence hydrologic simulation. The procedure was introduced to build ensemble precipitation forecasts based on the statistical relationship between observations and forecasts. More specifically, the approach relies on a transfer function that is developed based on a bivariate joint distribution between the observations and the simulations in the historical period. The transfer function is used to post-process the forecast. In this study, we propose a Bayesian EPP approach based on copula functions (COP-EPP) to improve the reliability of the precipitation ensemble forecast. Evaluation of the copula-based method is carried out by comparing the performance of the generated ensemble precipitation with the outputs from an existing procedure, i.e. mixed type meta-Gaussian distribution. Monthly precipitation from Climate Forecast System Reanalysis (CFS) and gridded observation from Parameter-Elevation Relationships on Independent Slopes Model (PRISM) have been employed to generate the post-processed ensemble precipitation. Deterministic and probabilistic verification frameworks are utilized in order to evaluate the outputs from the proposed technique. Distribution of seasonal precipitation for the generated ensemble from the copula-based technique is compared to the observation and raw forecasts for three sub-basins located in the Western United States. Results show that both techniques are successful in producing reliable and unbiased ensemble forecast, however, the COP-EPP demonstrates considerable improvement in the ensemble forecast in both deterministic and probabilistic verification, in particular in characterizing the extreme events in wet seasons.

Impacts of calibration strategies and ensemble methods on ensemble flood forecasting over Lanjiang basin, Southeast China

NASA Astrophysics Data System (ADS)

Liu, Li; Xu, Yue-Ping

2017-04-01

Ensemble flood forecasting driven by numerical weather prediction products is becoming more commonly used in operational flood forecasting applications.In this study, a hydrological ensemble flood forecasting system based on Variable Infiltration Capacity (VIC) model and quantitative precipitation forecasts from TIGGE dataset is constructed for Lanjiang Basin, Southeast China. The impacts of calibration strategies and ensemble methods on the performance of the system are then evaluated.The hydrological model is optimized by parallel programmed ɛ-NSGAII multi-objective algorithm and two respectively parameterized models are determined to simulate daily flows and peak flows coupled with a modular approach.The results indicatethat the ɛ-NSGAII algorithm permits more efficient optimization and rational determination on parameter setting.It is demonstrated that the multimodel ensemble streamflow mean have better skills than the best singlemodel ensemble mean (ECMWF) and the multimodel ensembles weighted on members and skill scores outperform other multimodel ensembles. For typical flood event, it is proved that the flood can be predicted 3-4 days in advance, but the flows in rising limb can be captured with only 1-2 days ahead due to the flash feature. With respect to peak flows selected by Peaks Over Threshold approach, the ensemble means from either singlemodel or multimodels are generally underestimated as the extreme values are smoothed out by ensemble process.

A method for determining the weak statistical stationarity of a random process

NASA Technical Reports Server (NTRS)

Sadeh, W. Z.; Koper, C. A., Jr.

1978-01-01

A method for determining the weak statistical stationarity of a random process is presented. The core of this testing procedure consists of generating an equivalent ensemble which approximates a true ensemble. Formation of an equivalent ensemble is accomplished through segmenting a sufficiently long time history of a random process into equal, finite, and statistically independent sample records. The weak statistical stationarity is ascertained based on the time invariance of the equivalent-ensemble averages. Comparison of these averages with their corresponding time averages over a single sample record leads to a heuristic estimate of the ergodicity of a random process. Specific variance tests are introduced for evaluating the statistical independence of the sample records, the time invariance of the equivalent-ensemble autocorrelations, and the ergodicity. Examination and substantiation of these procedures were conducted utilizing turbulent velocity signals.

Designing boosting ensemble of relational fuzzy systems.

PubMed

Scherer, Rafał

2010-10-01

A method frequently used in classification systems for improving classification accuracy is to combine outputs of several classifiers. Among various types of classifiers, fuzzy ones are tempting because of using intelligible fuzzy if-then rules. In the paper we build an AdaBoost ensemble of relational neuro-fuzzy classifiers. Relational fuzzy systems bond input and output fuzzy linguistic values by a binary relation; thus, fuzzy rules have additional, comparing to traditional fuzzy systems, weights - elements of a fuzzy relation matrix. Thanks to this the system is better adjustable to data during learning. In the paper an ensemble of relational fuzzy systems is proposed. The problem is that such an ensemble contains separate rule bases which cannot be directly merged. As systems are separate, we cannot treat fuzzy rules coming from different systems as rules from the same (single) system. In the paper, the problem is addressed by a novel design of fuzzy systems constituting the ensemble, resulting in normalization of individual rule bases during learning. The method described in the paper is tested on several known benchmarks and compared with other machine learning solutions from the literature.

New approach to information fusion for Lipschitz classifiers ensembles: Application in multi-channel C-OTDR-monitoring systems

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

Timofeev, Andrey V.; Egorov, Dmitry V.

This paper presents new results concerning selection of an optimal information fusion formula for an ensemble of Lipschitz classifiers. The goal of information fusion is to create an integral classificatory which could provide better generalization ability of the ensemble while achieving a practically acceptable level of effectiveness. The problem of information fusion is very relevant for data processing in multi-channel C-OTDR-monitoring systems. In this case we have to effectively classify targeted events which appear in the vicinity of the monitored object. Solution of this problem is based on usage of an ensemble of Lipschitz classifiers each of which corresponds tomore » a respective channel. We suggest a brand new method for information fusion in case of ensemble of Lipschitz classifiers. This method is called “The Weighing of Inversely as Lipschitz Constants” (WILC). Results of WILC-method practical usage in multichannel C-OTDR monitoring systems are presented.« less

Automatic Estimation of Osteoporotic Fracture Cases by Using Ensemble Learning Approaches.

PubMed

Kilic, Niyazi; Hosgormez, Erkan

2016-03-01

Ensemble learning methods are one of the most powerful tools for the pattern classification problems. In this paper, the effects of ensemble learning methods and some physical bone densitometry parameters on osteoporotic fracture detection were investigated. Six feature set models were constructed including different physical parameters and they fed into the ensemble classifiers as input features. As ensemble learning techniques, bagging, gradient boosting and random subspace (RSM) were used. Instance based learning (IBk) and random forest (RF) classifiers applied to six feature set models. The patients were classified into three groups such as osteoporosis, osteopenia and control (healthy), using ensemble classifiers. Total classification accuracy and f-measure were also used to evaluate diagnostic performance of the proposed ensemble classification system. The classification accuracy has reached to 98.85 % by the combination of model 6 (five BMD + five T-score values) using RSM-RF classifier. The findings of this paper suggest that the patients will be able to be warned before a bone fracture occurred, by just examining some physical parameters that can easily be measured without invasive operations.

Image Change Detection via Ensemble Learning

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

Martin, Benjamin W; Vatsavai, Raju

2013-01-01

The concept of geographic change detection is relevant in many areas. Changes in geography can reveal much information about a particular location. For example, analysis of changes in geography can identify regions of population growth, change in land use, and potential environmental disturbance. A common way to perform change detection is to use a simple method such as differencing to detect regions of change. Though these techniques are simple, often the application of these techniques is very limited. Recently, use of machine learning methods such as neural networks for change detection has been explored with great success. In this work,more » we explore the use of ensemble learning methodologies for detecting changes in bitemporal synthetic aperture radar (SAR) images. Ensemble learning uses a collection of weak machine learning classifiers to create a stronger classifier which has higher accuracy than the individual classifiers in the ensemble. The strength of the ensemble lies in the fact that the individual classifiers in the ensemble create a mixture of experts in which the final classification made by the ensemble classifier is calculated from the outputs of the individual classifiers. Our methodology leverages this aspect of ensemble learning by training collections of weak decision tree based classifiers to identify regions of change in SAR images collected of a region in the Staten Island, New York area during Hurricane Sandy. Preliminary studies show that the ensemble method has approximately 11.5% higher change detection accuracy than an individual classifier.« less

Large unbalanced credit scoring using Lasso-logistic regression ensemble.

PubMed

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

Post-processing method for wind speed ensemble forecast using wind speed and direction

NASA Astrophysics Data System (ADS)

Sofie Eide, Siri; Bjørnar Bremnes, John; Steinsland, Ingelin

2017-04-01

Statistical methods are widely applied to enhance the quality of both deterministic and ensemble NWP forecasts. In many situations, like wind speed forecasting, most of the predictive information is contained in one variable in the NWP models. However, in statistical calibration of deterministic forecasts it is often seen that including more variables can further improve forecast skill. For ensembles this is rarely taken advantage of, mainly due to that it is generally not straightforward how to include multiple variables. In this study, it is demonstrated how multiple variables can be included in Bayesian model averaging (BMA) by using a flexible regression method for estimating the conditional means. The method is applied to wind speed forecasting at 204 Norwegian stations based on wind speed and direction forecasts from the ECMWF ensemble system. At about 85 % of the sites the ensemble forecasts were improved in terms of CRPS by adding wind direction as predictor compared to only using wind speed. On average the improvements were about 5 %, but mainly for moderate to strong wind situations. For weak wind speeds adding wind direction had more or less neutral impact.

On the incidence of meteorological and hydrological processors: Effect of resolution, sharpness and reliability of hydrological ensemble forecasts

NASA Astrophysics Data System (ADS)

Abaza, Mabrouk; Anctil, François; Fortin, Vincent; Perreault, Luc

2017-12-01

Meteorological and hydrological ensemble prediction systems are imperfect. Their outputs could often be improved through the use of a statistical processor, opening up the question of the necessity of using both processors (meteorological and hydrological), only one of them, or none. This experiment compares the predictive distributions from four hydrological ensemble prediction systems (H-EPS) utilising the Ensemble Kalman filter (EnKF) probabilistic sequential data assimilation scheme. They differ in the inclusion or not of the Distribution Based Scaling (DBS) method for post-processing meteorological forecasts and the ensemble Bayesian Model Averaging (ensemble BMA) method for hydrological forecast post-processing. The experiment is implemented on three large watersheds and relies on the combination of two meteorological reforecast products: the 4-member Canadian reforecasts from the Canadian Centre for Meteorological and Environmental Prediction (CCMEP) and the 10-member American reforecasts from the National Oceanic and Atmospheric Administration (NOAA), leading to 14 members at each time step. Results show that all four tested H-EPS lead to resolution and sharpness values that are quite similar, with an advantage to DBS + EnKF. The ensemble BMA is unable to compensate for any bias left in the precipitation ensemble forecasts. On the other hand, it succeeds in calibrating ensemble members that are otherwise under-dispersed. If reliability is preferred over resolution and sharpness, DBS + EnKF + ensemble BMA performs best, making use of both processors in the H-EPS system. Conversely, for enhanced resolution and sharpness, DBS is the preferred method.

A comparative study of breast cancer diagnosis based on neural network ensemble via improved training algorithms.

PubMed

Azami, Hamed; Escudero, Javier

2015-08-01

Breast cancer is one of the most common types of cancer in women all over the world. Early diagnosis of this kind of cancer can significantly increase the chances of long-term survival. Since diagnosis of breast cancer is a complex problem, neural network (NN) approaches have been used as a promising solution. Considering the low speed of the back-propagation (BP) algorithm to train a feed-forward NN, we consider a number of improved NN trainings for the Wisconsin breast cancer dataset: BP with momentum, BP with adaptive learning rate, BP with adaptive learning rate and momentum, Polak-Ribikre conjugate gradient algorithm (CGA), Fletcher-Reeves CGA, Powell-Beale CGA, scaled CGA, resilient BP (RBP), one-step secant and quasi-Newton methods. An NN ensemble, which is a learning paradigm to combine a number of NN outputs, is used to improve the accuracy of the classification task. Results demonstrate that NN ensemble-based classification methods have better performance than NN-based algorithms. The highest overall average accuracy is 97.68% obtained by NN ensemble trained by RBP for 50%-50% training-test evaluation method.

Insights into the deterministic skill of air quality ensembles ...

EPA Pesticide Factsheets

Simulations from chemical weather models are subject to uncertainties in the input data (e.g. emission inventory, initial and boundary conditions) as well as those intrinsic to the model (e.g. physical parameterization, chemical mechanism). Multi-model ensembles can improve the forecast skill, provided that certain mathematical conditions are fulfilled. In this work, four ensemble methods were applied to two different datasets, and their performance was compared for ozone (O3), nitrogen dioxide (NO2) and particulate matter (PM10). Apart from the unconditional ensemble average, the approach behind the other three methods relies on adding optimum weights to members or constraining the ensemble to those members that meet certain conditions in time or frequency domain. The two different datasets were created for the first and second phase of the Air Quality Model Evaluation International Initiative (AQMEII). The methods are evaluated against ground level observations collected from the EMEP (European Monitoring and Evaluation Programme) and AirBase databases. The goal of the study is to quantify to what extent we can extract predictable signals from an ensemble with superior skill over the single models and the ensemble mean. Verification statistics show that the deterministic models simulate better O3 than NO2 and PM10, linked to different levels of complexity in the represented processes. The unconditional ensemble mean achieves higher skill compared to each stati

Reliable probabilities through statistical post-processing of ensemble predictions

NASA Astrophysics Data System (ADS)

Van Schaeybroeck, Bert; Vannitsem, Stéphane

2013-04-01

We develop post-processing or calibration approaches based on linear regression that make ensemble forecasts more reliable. We enforce climatological reliability in the sense that the total variability of the prediction is equal to the variability of the observations. Second, we impose ensemble reliability such that the spread around the ensemble mean of the observation coincides with the one of the ensemble members. In general the attractors of the model and reality are inhomogeneous. Therefore ensemble spread displays a variability not taken into account in standard post-processing methods. We overcome this by weighting the ensemble by a variable error. The approaches are tested in the context of the Lorenz 96 model (Lorenz 1996). The forecasts become more reliable at short lead times as reflected by a flatter rank histogram. Our best method turns out to be superior to well-established methods like EVMOS (Van Schaeybroeck and Vannitsem, 2011) and Nonhomogeneous Gaussian Regression (Gneiting et al., 2005). References [1] Gneiting, T., Raftery, A. E., Westveld, A., Goldman, T., 2005: Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation. Mon. Weather Rev. 133, 1098-1118. [2] Lorenz, E. N., 1996: Predictability - a problem partly solved. Proceedings, Seminar on Predictability ECMWF. 1, 1-18. [3] Van Schaeybroeck, B., and S. Vannitsem, 2011: Post-processing through linear regression, Nonlin. Processes Geophys., 18, 147.

Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble

PubMed Central

Liu, Hang; Chu, Renzhi; Tang, Zhenan

2015-01-01

Sensor drift is the most challenging problem in gas sensing at present. We propose a novel two-dimensional classifier ensemble strategy to solve the gas discrimination problem, regardless of the gas concentration, with high accuracy over extended periods of time. This strategy is appropriate for multi-class classifiers that consist of combinations of pairwise classifiers, such as support vector machines. We compare the performance of the strategy with those of competing methods in an experiment based on a public dataset that was compiled over a period of three years. The experimental results demonstrate that the two-dimensional ensemble outperforms the other methods considered. Furthermore, we propose a pre-aging process inspired by that applied to the sensors to improve the stability of the classifier ensemble. The experimental results demonstrate that the weight of each multi-class classifier model in the ensemble remains fairly static before and after the addition of new classifier models to the ensemble, when a pre-aging procedure is applied. PMID:25942640

Glyph-based analysis of multimodal directional distributions in vector field ensembles

NASA Astrophysics Data System (ADS)

Jarema, Mihaela; Demir, Ismail; Kehrer, Johannes; Westermann, Rüdiger

2015-04-01

Ensemble simulations are increasingly often performed in the geosciences in order to study the uncertainty and variability of model predictions. Describing ensemble data by mean and standard deviation can be misleading in case of multimodal distributions. We present first results of a glyph-based visualization of multimodal directional distributions in 2D and 3D vector ensemble data. Directional information on the circle/sphere is modeled using mixtures of probability density functions (pdfs), which enables us to characterize the distributions with relatively few parameters. The resulting mixture models are represented by 2D and 3D lobular glyphs showing direction, spread and strength of each principal mode of the distributions. A 3D extension of our approach is realized by means of an efficient GPU rendering technique. We demonstrate our method in the context of ensemble weather simulations.

Design of an Evolutionary Approach for Intrusion Detection

PubMed Central

2013-01-01

A novel evolutionary approach is proposed for effective intrusion detection based on benchmark datasets. The proposed approach can generate a pool of noninferior individual solutions and ensemble solutions thereof. The generated ensembles can be used to detect the intrusions accurately. For intrusion detection problem, the proposed approach could consider conflicting objectives simultaneously like detection rate of each attack class, error rate, accuracy, diversity, and so forth. The proposed approach can generate a pool of noninferior solutions and ensembles thereof having optimized trade-offs values of multiple conflicting objectives. In this paper, a three-phase, approach is proposed to generate solutions to a simple chromosome design in the first phase. In the first phase, a Pareto front of noninferior individual solutions is approximated. In the second phase of the proposed approach, the entire solution set is further refined to determine effective ensemble solutions considering solution interaction. In this phase, another improved Pareto front of ensemble solutions over that of individual solutions is approximated. The ensemble solutions in improved Pareto front reported improved detection results based on benchmark datasets for intrusion detection. In the third phase, a combination method like majority voting method is used to fuse the predictions of individual solutions for determining prediction of ensemble solution. Benchmark datasets, namely, KDD cup 1999 and ISCX 2012 dataset, are used to demonstrate and validate the performance of the proposed approach for intrusion detection. The proposed approach can discover individual solutions and ensemble solutions thereof with a good support and a detection rate from benchmark datasets (in comparison with well-known ensemble methods like bagging and boosting). In addition, the proposed approach is a generalized classification approach that is applicable to the problem of any field having multiple conflicting objectives, and a dataset can be represented in the form of labelled instances in terms of its features. PMID:24376390

Comparison of ensemble post-processing approaches, based on empirical and dynamical error modelisation of rainfall-runoff model forecasts

NASA Astrophysics Data System (ADS)

Chardon, J.; Mathevet, T.; Le Lay, M.; Gailhard, J.

2012-04-01

In the context of a national energy company (EDF : Electricité de France), hydro-meteorological forecasts are necessary to ensure safety and security of installations, meet environmental standards and improve water ressources management and decision making. Hydrological ensemble forecasts allow a better representation of meteorological and hydrological forecasts uncertainties and improve human expertise of hydrological forecasts, which is essential to synthesize available informations, coming from different meteorological and hydrological models and human experience. An operational hydrological ensemble forecasting chain has been developed at EDF since 2008 and is being used since 2010 on more than 30 watersheds in France. This ensemble forecasting chain is characterized ensemble pre-processing (rainfall and temperature) and post-processing (streamflow), where a large human expertise is solicited. The aim of this paper is to compare 2 hydrological ensemble post-processing methods developed at EDF in order improve ensemble forecasts reliability (similar to Monatanari &Brath, 2004; Schaefli et al., 2007). The aim of the post-processing methods is to dress hydrological ensemble forecasts with hydrological model uncertainties, based on perfect forecasts. The first method (called empirical approach) is based on a statistical modelisation of empirical error of perfect forecasts, by streamflow sub-samples of quantile class and lead-time. The second method (called dynamical approach) is based on streamflow sub-samples of quantile class and streamflow variation, and lead-time. On a set of 20 watersheds used for operational forecasts, results show that both approaches are necessary to ensure a good post-processing of hydrological ensemble, allowing a good improvement of reliability, skill and sharpness of ensemble forecasts. The comparison of the empirical and dynamical approaches shows the limits of the empirical approach which is not able to take into account hydrological dynamic and processes, i. e. sample heterogeneity. For a same streamflow range corresponds different processes such as rising limbs or recession, where uncertainties are different. The dynamical approach improves reliability, skills and sharpness of forecasts and globally reduces confidence intervals width. When compared in details, the dynamical approach allows a noticeable reduction of confidence intervals during recessions where uncertainty is relatively lower and a slight increase of confidence intervals during rising limbs or snowmelt where uncertainty is greater. The dynamic approach, validated by forecaster's experience that considered the empirical approach not discriminative enough, improved forecaster's confidence and communication of uncertainties. Montanari, A. and Brath, A., (2004). A stochastic approach for assessing the uncertainty of rainfall-runoff simulations. Water Resources Research, 40, W01106, doi:10.1029/2003WR002540. Schaefli, B., Balin Talamba, D. and Musy, A., (2007). Quantifying hydrological modeling errors through a mixture of normal distributions. Journal of Hydrology, 332, 303-315.

pE-DB: a database of structural ensembles of intrinsically disordered and of unfolded proteins.

PubMed

Varadi, Mihaly; Kosol, Simone; Lebrun, Pierre; Valentini, Erica; Blackledge, Martin; Dunker, A Keith; Felli, Isabella C; Forman-Kay, Julie D; Kriwacki, Richard W; Pierattelli, Roberta; Sussman, Joel; Svergun, Dmitri I; Uversky, Vladimir N; Vendruscolo, Michele; Wishart, David; Wright, Peter E; Tompa, Peter

2014-01-01

The goal of pE-DB (http://pedb.vib.be) is to serve as an openly accessible database for the deposition of structural ensembles of intrinsically disordered proteins (IDPs) and of denatured proteins based on nuclear magnetic resonance spectroscopy, small-angle X-ray scattering and other data measured in solution. Owing to the inherent flexibility of IDPs, solution techniques are particularly appropriate for characterizing their biophysical properties, and structural ensembles in agreement with these data provide a convenient tool for describing the underlying conformational sampling. Database entries consist of (i) primary experimental data with descriptions of the acquisition methods and algorithms used for the ensemble calculations, and (ii) the structural ensembles consistent with these data, provided as a set of models in a Protein Data Bank format. PE-DB is open for submissions from the community, and is intended as a forum for disseminating the structural ensembles and the methodologies used to generate them. While the need to represent the IDP structures is clear, methods for determining and evaluating the structural ensembles are still evolving. The availability of the pE-DB database is expected to promote the development of new modeling methods and leads to a better understanding of how function arises from disordered states.

Representation of photon limited data in emission tomography using origin ensembles

NASA Astrophysics Data System (ADS)

Sitek, A.

2008-06-01

Representation and reconstruction of data obtained by emission tomography scanners are challenging due to high noise levels in the data. Typically, images obtained using tomographic measurements are represented using grids. In this work, we define images as sets of origins of events detected during tomographic measurements; we call these origin ensembles (OEs). A state in the ensemble is characterized by a vector of 3N parameters Y, where the parameters are the coordinates of origins of detected events in a three-dimensional space and N is the number of detected events. The 3N-dimensional probability density function (PDF) for that ensemble is derived, and we present an algorithm for OE image estimation from tomographic measurements. A displayable image (e.g. grid based image) is derived from the OE formulation by calculating ensemble expectations based on the PDF using the Markov chain Monte Carlo method. The approach was applied to computer-simulated 3D list-mode positron emission tomography data. The reconstruction errors for a 10 000 000 event acquisition for simulated ranged from 0.1 to 34.8%, depending on object size and sampling density. The method was also applied to experimental data and the results of the OE method were consistent with those obtained by a standard maximum-likelihood approach. The method is a new approach to representation and reconstruction of data obtained by photon-limited emission tomography measurements.

A two-stage method of quantitative flood risk analysis for reservoir real-time operation using ensemble-based hydrologic forecasts

NASA Astrophysics Data System (ADS)

Liu, P.

2013-12-01

Quantitative analysis of the risk for reservoir real-time operation is a hard task owing to the difficulty of accurate description of inflow uncertainties. The ensemble-based hydrologic forecasts directly depict the inflows not only the marginal distributions but also their persistence via scenarios. This motivates us to analyze the reservoir real-time operating risk with ensemble-based hydrologic forecasts as inputs. A method is developed by using the forecast horizon point to divide the future time into two stages, the forecast lead-time and the unpredicted time. The risk within the forecast lead-time is computed based on counting the failure number of forecast scenarios, and the risk in the unpredicted time is estimated using reservoir routing with the design floods and the reservoir water levels of forecast horizon point. As a result, a two-stage risk analysis method is set up to quantify the entire flood risks by defining the ratio of the number of scenarios that excessive the critical value to the total number of scenarios. The China's Three Gorges Reservoir (TGR) is selected as a case study, where the parameter and precipitation uncertainties are implemented to produce ensemble-based hydrologic forecasts. The Bayesian inference, Markov Chain Monte Carlo, is used to account for the parameter uncertainty. Two reservoir operation schemes, the real operated and scenario optimization, are evaluated for the flood risks and hydropower profits analysis. With the 2010 flood, it is found that the improvement of the hydrologic forecast accuracy is unnecessary to decrease the reservoir real-time operation risk, and most risks are from the forecast lead-time. It is therefore valuable to decrease the avarice of ensemble-based hydrologic forecasts with less bias for a reservoir operational purpose.

Ensemble-Based Parameter Estimation in a Coupled GCM Using the Adaptive Spatial Average Method

DOE PAGES

Liu, Y.; Liu, Z.; Zhang, S.; ...

2014-05-29

Ensemble-based parameter estimation for a climate model is emerging as an important topic in climate research. And for a complex system such as a coupled ocean–atmosphere general circulation model, the sensitivity and response of a model variable to a model parameter could vary spatially and temporally. An adaptive spatial average (ASA) algorithm is proposed to increase the efficiency of parameter estimation. Refined from a previous spatial average method, the ASA uses the ensemble spread as the criterion for selecting “good” values from the spatially varying posterior estimated parameter values; these good values are then averaged to give the final globalmore » uniform posterior parameter. In comparison with existing methods, the ASA parameter estimation has a superior performance: faster convergence and enhanced signal-to-noise ratio.« less

Upgrades to the REA method for producing probabilistic climate change projections

NASA Astrophysics Data System (ADS)

Xu, Ying; Gao, Xuejie; Giorgi, Filippo

2010-05-01

We present an augmented version of the Reliability Ensemble Averaging (REA) method designed to generate probabilistic climate change information from ensembles of climate model simulations. Compared to the original version, the augmented one includes consideration of multiple variables and statistics in the calculation of the performance-based weights. In addition, the model convergence criterion previously employed is removed. The method is applied to the calculation of changes in mean and variability for temperature and precipitation over different sub-regions of East Asia based on the recently completed CMIP3 multi-model ensemble. Comparison of the new and old REA methods, along with the simple averaging procedure, and the use of different combinations of performance metrics shows that at fine sub-regional scales the choice of weighting is relevant. This is mostly because the models show a substantial spread in performance for the simulation of precipitation statistics, a result that supports the use of model weighting as a useful option to account for wide ranges of quality of models. The REA method, and in particular the upgraded one, provides a simple and flexible framework for assessing the uncertainty related to the aggregation of results from ensembles of models in order to produce climate change information at the regional scale. KEY WORDS: REA method, Climate change, CMIP3

Application of new methods based on ECMWF ensemble model for predicting severe convective weather situations

NASA Astrophysics Data System (ADS)

Lazar, Dora; Ihasz, Istvan

2013-04-01

The short and medium range operational forecasts, warning and alarm of the severe weather are one of the most important activities of the Hungarian Meteorological Service. Our study provides comprehensive summary of newly developed methods based on ECMWF ensemble forecasts to assist successful prediction of the convective weather situations. . In the first part of the study a brief overview is given about the components of atmospheric convection, which are the atmospheric lifting force, convergence and vertical wind shear. The atmospheric instability is often used to characterize the so-called instability index; one of the most popular and often used indexes is the convective available potential energy. Heavy convective events, like intensive storms, supercells and tornadoes are needed the vertical instability, adequate moisture and vertical wind shear. As a first step statistical studies of these three parameters are based on nine years time series of 51-member ensemble forecasting model based on convective summer time period, various statistical analyses were performed. Relationship of the rate of the convective and total precipitation and above three parameters was studied by different statistical methods. Four new visualization methods were applied for supporting successful forecasts of severe weathers. Two of the four visualization methods the ensemble meteogram and the ensemble vertical profiles had been available at the beginning of our work. Both methods show probability of the meteorological parameters for the selected location. Additionally two new methods have been developed. First method provides probability map of the event exceeding predefined values, so the incident of the spatial uncertainty is well-defined. The convective weather events are characterized by the incident of space often rhapsodic occurs rather have expected the event area can be selected so that the ensemble forecasts give very good support. Another new visualization tool shows time evolution of predefined multiple thresholds in graphical form for any selected location. With applying this tool degree of the dangerous weather conditions can be well estimated. Besides intensive convective periods are clearly marked during the forecasting period. Developments were done by MAGICS++ software under UNIX operating system. The third part of the study usefulness of these tools is demonstrated in three interesting cases studies of last summer.

Texture Descriptors Ensembles Enable Image-Based Classification of Maturation of Human Stem Cell-Derived Retinal Pigmented Epithelium

PubMed Central

Caetano dos Santos, Florentino Luciano; Skottman, Heli; Juuti-Uusitalo, Kati; Hyttinen, Jari

2016-01-01

Aims A fast, non-invasive and observer-independent method to analyze the homogeneity and maturity of human pluripotent stem cell (hPSC) derived retinal pigment epithelial (RPE) cells is warranted to assess the suitability of hPSC-RPE cells for implantation or in vitro use. The aim of this work was to develop and validate methods to create ensembles of state-of-the-art texture descriptors and to provide a robust classification tool to separate three different maturation stages of RPE cells by using phase contrast microscopy images. The same methods were also validated on a wide variety of biological image classification problems, such as histological or virus image classification. Methods For image classification we used different texture descriptors, descriptor ensembles and preprocessing techniques. Also, three new methods were tested. The first approach was an ensemble of preprocessing methods, to create an additional set of images. The second was the region-based approach, where saliency detection and wavelet decomposition divide each image in two different regions, from which features were extracted through different descriptors. The third method was an ensemble of Binarized Statistical Image Features, based on different sizes and thresholds. A Support Vector Machine (SVM) was trained for each descriptor histogram and the set of SVMs combined by sum rule. The accuracy of the computer vision tool was verified in classifying the hPSC-RPE cell maturation level. Dataset and Results The RPE dataset contains 1862 subwindows from 195 phase contrast images. The final descriptor ensemble outperformed the most recent stand-alone texture descriptors, obtaining, for the RPE dataset, an area under ROC curve (AUC) of 86.49% with the 10-fold cross validation and 91.98% with the leave-one-image-out protocol. The generality of the three proposed approaches was ascertained with 10 more biological image datasets, obtaining an average AUC greater than 97%. Conclusions Here we showed that the developed ensembles of texture descriptors are able to classify the RPE cell maturation stage. Moreover, we proved that preprocessing and region-based decomposition improves many descriptors’ accuracy in biological dataset classification. Finally, we built the first public dataset of stem cell-derived RPE cells, which is publicly available to the scientific community for classification studies. The proposed tool is available at https://www.dei.unipd.it/node/2357 and the RPE dataset at http://www.biomeditech.fi/data/RPE_dataset/. Both are available at https://figshare.com/s/d6fb591f1beb4f8efa6f. PMID:26895509

Fire spread estimation on forest wildfire using ensemble kalman filter

NASA Astrophysics Data System (ADS)

Syarifah, Wardatus; Apriliani, Erna

2018-04-01

Wildfire is one of the most frequent disasters in the world, for example forest wildfire, causing population of forest decrease. Forest wildfire, whether naturally occurring or prescribed, are potential risks for ecosystems and human settlements. These risks can be managed by monitoring the weather, prescribing fires to limit available fuel, and creating firebreaks. With computer simulations we can predict and explore how fires may spread. The model of fire spread on forest wildfire was established to determine the fire properties. The fire spread model is prepared based on the equation of the diffusion reaction model. There are many methods to estimate the spread of fire. The Kalman Filter Ensemble Method is a modified estimation method of the Kalman Filter algorithm that can be used to estimate linear and non-linear system models. In this research will apply Ensemble Kalman Filter (EnKF) method to estimate the spread of fire on forest wildfire. Before applying the EnKF method, the fire spread model will be discreted using finite difference method. At the end, the analysis obtained illustrated by numerical simulation using software. The simulation results show that the Ensemble Kalman Filter method is closer to the system model when the ensemble value is greater, while the covariance value of the system model and the smaller the measurement.

Monte Carlo replica-exchange based ensemble docking of protein conformations.

PubMed

Zhang, Zhe; Ehmann, Uwe; Zacharias, Martin

2017-05-01

A replica-exchange Monte Carlo (REMC) ensemble docking approach has been developed that allows efficient exploration of protein-protein docking geometries. In addition to Monte Carlo steps in translation and orientation of binding partners, possible conformational changes upon binding are included based on Monte Carlo selection of protein conformations stored as ordered pregenerated conformational ensembles. The conformational ensembles of each binding partner protein were generated by three different approaches starting from the unbound partner protein structure with a range spanning a root mean square deviation of 1-2.5 Å with respect to the unbound structure. Because MC sampling is performed to select appropriate partner conformations on the fly the approach is not limited by the number of conformations in the ensemble compared to ensemble docking of each conformer pair in ensemble cross docking. Although only a fraction of generated conformers was in closer agreement with the bound structure the REMC ensemble docking approach achieved improved docking results compared to REMC docking with only the unbound partner structures or using docking energy minimization methods. The approach has significant potential for further improvement in combination with more realistic structural ensembles and better docking scoring functions. Proteins 2017; 85:924-937. © 2016 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

The total probabilities from high-resolution ensemble forecasting of floods

NASA Astrophysics Data System (ADS)

Olav Skøien, Jon; Bogner, Konrad; Salamon, Peter; Smith, Paul; Pappenberger, Florian

2015-04-01

Ensemble forecasting has for a long time been used in meteorological modelling, to give an indication of the uncertainty of the forecasts. As meteorological ensemble forecasts often show some bias and dispersion errors, there is a need for calibration and post-processing of the ensembles. Typical methods for this are Bayesian Model Averaging (Raftery et al., 2005) and Ensemble Model Output Statistics (EMOS) (Gneiting et al., 2005). There are also methods for regionalizing these methods (Berrocal et al., 2007) and for incorporating the correlation between lead times (Hemri et al., 2013). To make optimal predictions of floods along the stream network in hydrology, we can easily use the ensemble members as input to the hydrological models. However, some of the post-processing methods will need modifications when regionalizing the forecasts outside the calibration locations, as done by Hemri et al. (2013). We present a method for spatial regionalization of the post-processed forecasts based on EMOS and top-kriging (Skøien et al., 2006). We will also look into different methods for handling the non-normality of runoff and the effect on forecasts skills in general and for floods in particular. Berrocal, V. J., Raftery, A. E. and Gneiting, T.: Combining Spatial Statistical and Ensemble Information in Probabilistic Weather Forecasts, Mon. Weather Rev., 135(4), 1386-1402, doi:10.1175/MWR3341.1, 2007. Gneiting, T., Raftery, A. E., Westveld, A. H. and Goldman, T.: Calibrated Probabilistic Forecasting Using Ensemble Model Output Statistics and Minimum CRPS Estimation, Mon. Weather Rev., 133(5), 1098-1118, doi:10.1175/MWR2904.1, 2005. Hemri, S., Fundel, F. and Zappa, M.: Simultaneous calibration of ensemble river flow predictions over an entire range of lead times, Water Resour. Res., 49(10), 6744-6755, doi:10.1002/wrcr.20542, 2013. Raftery, A. E., Gneiting, T., Balabdaoui, F. and Polakowski, M.: Using Bayesian Model Averaging to Calibrate Forecast Ensembles, Mon. Weather Rev., 133(5), 1155-1174, doi:10.1175/MWR2906.1, 2005. Skøien, J. O., Merz, R. and Blöschl, G.: Top-kriging - Geostatistics on stream networks, Hydrol. Earth Syst. Sci., 10(2), 277-287, 2006.

Accuracy of the microcanonical Lanczos method to compute real-frequency dynamical spectral functions of quantum models at finite temperatures

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

Okamoto, Satoshi; Alvarez, Gonzalo; Dagotto, Elbio

We examine the accuracy of the microcanonical Lanczos method (MCLM) developed by Long et al. [Phys. Rev. B 68, 235106 (2003)] to compute dynamical spectral functions of interacting quantum models at finite temperatures. The MCLM is based on the microcanonical ensemble, which becomes exact in the thermodynamic limit. To apply the microcanonical ensemble at a fixed temperature, one has to find energy eigenstates with the energy eigenvalue corresponding to the internal energy in the canonical ensemble. Here in this paper, we propose to use thermal pure quantum state methods by Sugiura and Shimizu [Phys. Rev. Lett. 111, 010401 (2013)] tomore » obtain the internal energy. After obtaining the energy eigenstates using the Lanczos diagonalization method, dynamical quantities are computed via a continued fraction expansion, a standard procedure for Lanczos-based numerical methods. Using one-dimensional antiferromagnetic Heisenberg chains with S = 1/2, we demonstrate that the proposed procedure is reasonably accurate, even for relatively small systems.« less

Accuracy of the microcanonical Lanczos method to compute real-frequency dynamical spectral functions of quantum models at finite temperatures

DOE PAGES

Okamoto, Satoshi; Alvarez, Gonzalo; Dagotto, Elbio; ...

2018-04-20

We examine the accuracy of the microcanonical Lanczos method (MCLM) developed by Long et al. [Phys. Rev. B 68, 235106 (2003)] to compute dynamical spectral functions of interacting quantum models at finite temperatures. The MCLM is based on the microcanonical ensemble, which becomes exact in the thermodynamic limit. To apply the microcanonical ensemble at a fixed temperature, one has to find energy eigenstates with the energy eigenvalue corresponding to the internal energy in the canonical ensemble. Here in this paper, we propose to use thermal pure quantum state methods by Sugiura and Shimizu [Phys. Rev. Lett. 111, 010401 (2013)] tomore » obtain the internal energy. After obtaining the energy eigenstates using the Lanczos diagonalization method, dynamical quantities are computed via a continued fraction expansion, a standard procedure for Lanczos-based numerical methods. Using one-dimensional antiferromagnetic Heisenberg chains with S = 1/2, we demonstrate that the proposed procedure is reasonably accurate, even for relatively small systems.« less

Calibration of limited-area ensemble precipitation forecasts for hydrological predictions

NASA Astrophysics Data System (ADS)

Diomede, Tommaso; Marsigli, Chiara; Montani, Andrea; Nerozzi, Fabrizio; Paccagnella, Tiziana

2015-04-01

The main objective of this study is to investigate the impact of calibration for limited-area ensemble precipitation forecasts, to be used for driving discharge predictions up to 5 days in advance. A reforecast dataset, which spans 30 years, based on the Consortium for Small Scale Modeling Limited-Area Ensemble Prediction System (COSMO-LEPS) was used for testing the calibration strategy. Three calibration techniques were applied: quantile-to-quantile mapping, linear regression, and analogs. The performance of these methodologies was evaluated in terms of statistical scores for the precipitation forecasts operationally provided by COSMO-LEPS in the years 2003-2007 over Germany, Switzerland, and the Emilia-Romagna region (northern Italy). The analog-based method seemed to be preferred because of its capability of correct position errors and spread deficiencies. A suitable spatial domain for the analog search can help to handle model spatial errors as systematic errors. However, the performance of the analog-based method may degrade in cases where a limited training dataset is available. A sensitivity test on the length of the training dataset over which to perform the analog search has been performed. The quantile-to-quantile mapping and linear regression methods were less effective, mainly because the forecast-analysis relation was not so strong for the available training dataset. A comparison between the calibration based on the deterministic reforecast and the calibration based on the full operational ensemble used as training dataset has been considered, with the aim to evaluate whether reforecasts are really worthy for calibration, given that their computational cost is remarkable. The verification of the calibration process was then performed by coupling ensemble precipitation forecasts with a distributed rainfall-runoff model. This test was carried out for a medium-sized catchment located in Emilia-Romagna, showing a beneficial impact of the analog-based method on the reduction of missed events for discharge predictions.

Effects of ensemble and summary displays on interpretations of geospatial uncertainty data.

PubMed

Padilla, Lace M; Ruginski, Ian T; Creem-Regehr, Sarah H

2017-01-01

Ensemble and summary displays are two widely used methods to represent visual-spatial uncertainty; however, there is disagreement about which is the most effective technique to communicate uncertainty to the general public. Visualization scientists create ensemble displays by plotting multiple data points on the same Cartesian coordinate plane. Despite their use in scientific practice, it is more common in public presentations to use visualizations of summary displays, which scientists create by plotting statistical parameters of the ensemble members. While prior work has demonstrated that viewers make different decisions when viewing summary and ensemble displays, it is unclear what components of the displays lead to diverging judgments. This study aims to compare the salience of visual features - or visual elements that attract bottom-up attention - as one possible source of diverging judgments made with ensemble and summary displays in the context of hurricane track forecasts. We report that salient visual features of both ensemble and summary displays influence participant judgment. Specifically, we find that salient features of summary displays of geospatial uncertainty can be misunderstood as displaying size information. Further, salient features of ensemble displays evoke judgments that are indicative of accurate interpretations of the underlying probability distribution of the ensemble data. However, when participants use ensemble displays to make point-based judgments, they may overweight individual ensemble members in their decision-making process. We propose that ensemble displays are a promising alternative to summary displays in a geospatial context but that decisions about visualization methods should be informed by the viewer's task.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

PubMed Central

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data. PMID:25706988

Deep learning ensemble with asymptotic techniques for oscillometric blood pressure estimation.

PubMed

Lee, Soojeong; Chang, Joon-Hyuk

2017-11-01

This paper proposes a deep learning based ensemble regression estimator with asymptotic techniques, and offers a method that can decrease uncertainty for oscillometric blood pressure (BP) measurements using the bootstrap and Monte-Carlo approach. While the former is used to estimate SBP and DBP, the latter attempts to determine confidence intervals (CIs) for SBP and DBP based on oscillometric BP measurements. This work originally employs deep belief networks (DBN)-deep neural networks (DNN) to effectively estimate BPs based on oscillometric measurements. However, there are some inherent problems with these methods. First, it is not easy to determine the best DBN-DNN estimator, and worthy information might be omitted when selecting one DBN-DNN estimator and discarding the others. Additionally, our input feature vectors, obtained from only five measurements per subject, represent a very small sample size; this is a critical weakness when using the DBN-DNN technique and can cause overfitting or underfitting, depending on the structure of the algorithm. To address these problems, an ensemble with an asymptotic approach (based on combining the bootstrap with the DBN-DNN technique) is utilized to generate the pseudo features needed to estimate the SBP and DBP. In the first stage, the bootstrap-aggregation technique is used to create ensemble parameters. Afterward, the AdaBoost approach is employed for the second-stage SBP and DBP estimation. We then use the bootstrap and Monte-Carlo techniques in order to determine the CIs based on the target BP estimated using the DBN-DNN ensemble regression estimator with the asymptotic technique in the third stage. The proposed method can mitigate the estimation uncertainty such as large the standard deviation of error (SDE) on comparing the proposed DBN-DNN ensemble regression estimator with the DBN-DNN single regression estimator, we identify that the SDEs of the SBP and DBP are reduced by 0.58 and 0.57  mmHg, respectively. These indicate that the proposed method actually enhances the performance by 9.18% and 10.88% compared with the DBN-DNN single estimator. The proposed methodology improves the accuracy of BP estimation and reduces the uncertainty for BP estimation. Copyright © 2017 Elsevier B.V. All rights reserved.

Ensemble-based flash-flood modelling: Taking into account hydrodynamic parameters and initial soil moisture uncertainties

NASA Astrophysics Data System (ADS)

Edouard, Simon; Vincendon, Béatrice; Ducrocq, Véronique

2018-05-01

Intense precipitation events in the Mediterranean often lead to devastating flash floods (FF). FF modelling is affected by several kinds of uncertainties and Hydrological Ensemble Prediction Systems (HEPS) are designed to take those uncertainties into account. The major source of uncertainty comes from rainfall forcing and convective-scale meteorological ensemble prediction systems can manage it for forecasting purpose. But other sources are related to the hydrological modelling part of the HEPS. This study focuses on the uncertainties arising from the hydrological model parameters and initial soil moisture with aim to design an ensemble-based version of an hydrological model dedicated to Mediterranean fast responding rivers simulations, the ISBA-TOP coupled system. The first step consists in identifying the parameters that have the strongest influence on FF simulations by assuming perfect precipitation. A sensitivity study is carried out first using a synthetic framework and then for several real events and several catchments. Perturbation methods varying the most sensitive parameters as well as initial soil moisture allow designing an ensemble-based version of ISBA-TOP. The first results of this system on some real events are presented. The direct perspective of this work will be to drive this ensemble-based version with the members of a convective-scale meteorological ensemble prediction system to design a complete HEPS for FF forecasting.

Advanced ensemble modelling of flexible macromolecules using X-ray solution scattering.

PubMed

Tria, Giancarlo; Mertens, Haydyn D T; Kachala, Michael; Svergun, Dmitri I

2015-03-01

Dynamic ensembles of macromolecules mediate essential processes in biology. Understanding the mechanisms driving the function and molecular interactions of 'unstructured' and flexible molecules requires alternative approaches to those traditionally employed in structural biology. Small-angle X-ray scattering (SAXS) is an established method for structural characterization of biological macromolecules in solution, and is directly applicable to the study of flexible systems such as intrinsically disordered proteins and multi-domain proteins with unstructured regions. The Ensemble Optimization Method (EOM) [Bernadó et al. (2007 ▶). J. Am. Chem. Soc. 129, 5656-5664] was the first approach introducing the concept of ensemble fitting of the SAXS data from flexible systems. In this approach, a large pool of macromolecules covering the available conformational space is generated and a sub-ensemble of conformers coexisting in solution is selected guided by the fit to the experimental SAXS data. This paper presents a series of new developments and advancements to the method, including significantly enhanced functionality and also quantitative metrics for the characterization of the results. Building on the original concept of ensemble optimization, the algorithms for pool generation have been redesigned to allow for the construction of partially or completely symmetric oligomeric models, and the selection procedure was improved to refine the size of the ensemble. Quantitative measures of the flexibility of the system studied, based on the characteristic integral parameters of the selected ensemble, are introduced. These improvements are implemented in the new EOM version 2.0, and the capabilities as well as inherent limitations of the ensemble approach in SAXS, and of EOM 2.0 in particular, are discussed.

Self-Adaptive Prediction of Cloud Resource Demands Using Ensemble Model and Subtractive-Fuzzy Clustering Based Fuzzy Neural Network

PubMed Central

Chen, Zhijia; Zhu, Yuanchang; Di, Yanqiang; Feng, Shaochong

2015-01-01

In IaaS (infrastructure as a service) cloud environment, users are provisioned with virtual machines (VMs). To allocate resources for users dynamically and effectively, accurate resource demands predicting is essential. For this purpose, this paper proposes a self-adaptive prediction method using ensemble model and subtractive-fuzzy clustering based fuzzy neural network (ESFCFNN). We analyze the characters of user preferences and demands. Then the architecture of the prediction model is constructed. We adopt some base predictors to compose the ensemble model. Then the structure and learning algorithm of fuzzy neural network is researched. To obtain the number of fuzzy rules and the initial value of the premise and consequent parameters, this paper proposes the fuzzy c-means combined with subtractive clustering algorithm, that is, the subtractive-fuzzy clustering. Finally, we adopt different criteria to evaluate the proposed method. The experiment results show that the method is accurate and effective in predicting the resource demands. PMID:25691896

NIMEFI: Gene Regulatory Network Inference using Multiple Ensemble Feature Importance Algorithms

PubMed Central

Ruyssinck, Joeri; Huynh-Thu, Vân Anh; Geurts, Pierre; Dhaene, Tom; Demeester, Piet; Saeys, Yvan

2014-01-01

One of the long-standing open challenges in computational systems biology is the topology inference of gene regulatory networks from high-throughput omics data. Recently, two community-wide efforts, DREAM4 and DREAM5, have been established to benchmark network inference techniques using gene expression measurements. In these challenges the overall top performer was the GENIE3 algorithm. This method decomposes the network inference task into separate regression problems for each gene in the network in which the expression values of a particular target gene are predicted using all other genes as possible predictors. Next, using tree-based ensemble methods, an importance measure for each predictor gene is calculated with respect to the target gene and a high feature importance is considered as putative evidence of a regulatory link existing between both genes. The contribution of this work is twofold. First, we generalize the regression decomposition strategy of GENIE3 to other feature importance methods. We compare the performance of support vector regression, the elastic net, random forest regression, symbolic regression and their ensemble variants in this setting to the original GENIE3 algorithm. To create the ensemble variants, we propose a subsampling approach which allows us to cast any feature selection algorithm that produces a feature ranking into an ensemble feature importance algorithm. We demonstrate that the ensemble setting is key to the network inference task, as only ensemble variants achieve top performance. As second contribution, we explore the effect of using rankwise averaged predictions of multiple ensemble algorithms as opposed to only one. We name this approach NIMEFI (Network Inference using Multiple Ensemble Feature Importance algorithms) and show that this approach outperforms all individual methods in general, although on a specific network a single method can perform better. An implementation of NIMEFI has been made publicly available. PMID:24667482

Developing an approach to effectively use super ensemble experiments for the projection of hydrological extremes under climate change

NASA Astrophysics Data System (ADS)

Watanabe, S.; Kim, H.; Utsumi, N.

2017-12-01

This study aims to develop a new approach which projects hydrology under climate change using super ensemble experiments. The use of multiple ensemble is essential for the estimation of extreme, which is a major issue in the impact assessment of climate change. Hence, the super ensemble experiments are recently conducted by some research programs. While it is necessary to use multiple ensemble, the multiple calculations of hydrological simulation for each output of ensemble simulations needs considerable calculation costs. To effectively use the super ensemble experiments, we adopt a strategy to use runoff projected by climate models directly. The general approach of hydrological projection is to conduct hydrological model simulations which include land-surface and river routing process using atmospheric boundary conditions projected by climate models as inputs. This study, on the other hand, simulates only river routing model using runoff projected by climate models. In general, the climate model output is systematically biased so that a preprocessing which corrects such bias is necessary for impact assessments. Various bias correction methods have been proposed, but, to the best of our knowledge, no method has proposed for variables other than surface meteorology. Here, we newly propose a method for utilizing the projected future runoff directly. The developed method estimates and corrects the bias based on the pseudo-observation which is a result of retrospective offline simulation. We show an application of this approach to the super ensemble experiments conducted under the program of Half a degree Additional warming, Prognosis and Projected Impacts (HAPPI). More than 400 ensemble experiments from multiple climate models are available. The results of the validation using historical simulations by HAPPI indicates that the output of this approach can effectively reproduce retrospective runoff variability. Likewise, the bias of runoff from super ensemble climate projections is corrected, and the impact of climate change on hydrologic extremes is assessed in a cost-efficient way.

A new Method for the Estimation of Initial Condition Uncertainty Structures in Mesoscale Models

NASA Astrophysics Data System (ADS)

Keller, J. D.; Bach, L.; Hense, A.

2012-12-01

The estimation of fast growing error modes of a system is a key interest of ensemble data assimilation when assessing uncertainty in initial conditions. Over the last two decades three methods (and variations of these methods) have evolved for global numerical weather prediction models: ensemble Kalman filter, singular vectors and breeding of growing modes (or now ensemble transform). While the former incorporates a priori model error information and observation error estimates to determine ensemble initial conditions, the latter two techniques directly address the error structures associated with Lyapunov vectors. However, in global models these structures are mainly associated with transient global wave patterns. When assessing initial condition uncertainty in mesoscale limited area models, several problems regarding the aforementioned techniques arise: (a) additional sources of uncertainty on the smaller scales contribute to the error and (b) error structures from the global scale may quickly move through the model domain (depending on the size of the domain). To address the latter problem, perturbation structures from global models are often included in the mesoscale predictions as perturbed boundary conditions. However, the initial perturbations (when used) are often generated with a variant of an ensemble Kalman filter which does not necessarily focus on the large scale error patterns. In the framework of the European regional reanalysis project of the Hans-Ertel-Center for Weather Research we use a mesoscale model with an implemented nudging data assimilation scheme which does not support ensemble data assimilation at all. In preparation of an ensemble-based regional reanalysis and for the estimation of three-dimensional atmospheric covariance structures, we implemented a new method for the assessment of fast growing error modes for mesoscale limited area models. The so-called self-breeding is development based on the breeding of growing modes technique. Initial perturbations are integrated forward for a short time period and then rescaled and added to the initial state again. Iterating this rapid breeding cycle provides estimates for the initial uncertainty structure (or local Lyapunov vectors) given a specific norm. To avoid that all ensemble perturbations converge towards the leading local Lyapunov vector we apply an ensemble transform variant to orthogonalize the perturbations in the sub-space spanned by the ensemble. By choosing different kind of norms to measure perturbation growth, this technique allows for estimating uncertainty patterns targeted at specific sources of errors (e.g. convection, turbulence). With case study experiments we show applications of the self-breeding method for different sources of uncertainty and different horizontal scales.

Evolutionary Ensemble for In Silico Prediction of Ames Test Mutagenicity

NASA Astrophysics Data System (ADS)

Chen, Huanhuan; Yao, Xin

Driven by new regulations and animal welfare, the need to develop in silico models has increased recently as alternative approaches to safety assessment of chemicals without animal testing. This paper describes a novel machine learning ensemble approach to building an in silico model for the prediction of the Ames test mutagenicity, one of a battery of the most commonly used experimental in vitro and in vivo genotoxicity tests for safety evaluation of chemicals. Evolutionary random neural ensemble with negative correlation learning (ERNE) [1] was developed based on neural networks and evolutionary algorithms. ERNE combines the method of bootstrap sampling on training data with the method of random subspace feature selection to ensure diversity in creating individuals within an initial ensemble. Furthermore, while evolving individuals within the ensemble, it makes use of the negative correlation learning, enabling individual NNs to be trained as accurate as possible while still manage to maintain them as diverse as possible. Therefore, the resulting individuals in the final ensemble are capable of cooperating collectively to achieve better generalization of prediction. The empirical experiment suggest that ERNE is an effective ensemble approach for predicting the Ames test mutagenicity of chemicals.

Ensemble approach for differentiation of malignant melanoma

NASA Astrophysics Data System (ADS)

Rastgoo, Mojdeh; Morel, Olivier; Marzani, Franck; Garcia, Rafael

2015-04-01

Melanoma is the deadliest type of skin cancer, yet it is the most treatable kind depending on its early diagnosis. The early prognosis of melanoma is a challenging task for both clinicians and dermatologists. Due to the importance of early diagnosis and in order to assist the dermatologists, we propose an automated framework based on ensemble learning methods and dermoscopy images to differentiate melanoma from dysplastic and benign lesions. The evaluation of our framework on the recent and public dermoscopy benchmark (PH2 dataset) indicates the potential of proposed method. Our evaluation, using only global features, revealed that ensembles such as random forest perform better than single learner. Using random forest ensemble and combination of color and texture features, our framework achieved the highest sensitivity of 94% and specificity of 92%.

Petit and grand ensemble Monte Carlo calculations of the thermodynamics of the lattice gas

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

Murch, G.E.; Thorn, R.J.

1978-11-01

A direct Monte Carlo method for estimating the chemical potential in the petit canonical ensemble was applied to the simple cubic Ising-like lattice gas. The method is based on a simple relationship between the chemical potential and the potential energy distribution in a lattice gas at equilibrium as derived independently by Widom, and Jackson and Klein. Results are presented here for the chemical potential at various compositions and temperatures above and below the zero field ferromagnetic and antiferromagnetic critical points. The same lattice gas model was reconstructed in the form of a restricted grand canonical ensemble and results at severalmore » temperatures were compared with those from the petit canonical ensemble. The agreement was excellent in these cases.« less

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.

Practical implementation of a particle filter data assimilation approach to estimate initial hydrologic conditions and initialize medium-range streamflow forecasts

NASA Astrophysics Data System (ADS)

Clark, E.; Wood, A.; Nijssen, B.; Newman, A. J.; Mendoza, P. A.

2016-12-01

The System for Hydrometeorological Applications, Research and Prediction (SHARP), developed at the National Center for Atmospheric Research (NCAR), University of Washington, U.S. Army Corps of Engineers, and U.S. Bureau of Reclamation, is a fully automated ensemble prediction system for short-term to seasonal applications. It incorporates uncertainty in initial hydrologic conditions (IHCs) and in hydrometeorological predictions. In this implementation, IHC uncertainty is estimated by propagating an ensemble of 100 plausible temperature and precipitation time series through the Sacramento/Snow-17 model. The forcing ensemble explicitly accounts for measurement and interpolation uncertainties in the development of gridded meteorological forcing time series. The resulting ensemble of derived IHCs exhibits a broad range of possible soil moisture and snow water equivalent (SWE) states. To select the IHCs that are most consistent with the observations, we employ a particle filter (PF) that weights IHC ensemble members based on observations of streamflow and SWE. These particles are then used to initialize ensemble precipitation and temperature forecasts downscaled from the Global Ensemble Forecast System (GEFS), generating a streamflow forecast ensemble. We test this method in two basins in the Pacific Northwest that are important for water resources management: 1) the Green River upstream of Howard Hanson Dam, and 2) the South Fork Flathead River upstream of Hungry Horse Dam. The first of these is characterized by mixed snow and rain, while the second is snow-dominated. The PF-based forecasts are compared to forecasts based on a single IHC (corresponding to median streamflow) paired with the full GEFS ensemble, and 2) the full IHC ensemble, without filtering, paired with the full GEFS ensemble. In addition to assessing improvements in the spread of IHCs, we perform a hindcast experiment to evaluate the utility of PF-based data assimilation on streamflow forecasts at 1- to 7-day lead times.

Hierarchical Ensemble Methods for Protein Function Prediction

PubMed Central

2014-01-01

Protein function prediction is a complex multiclass multilabel classification problem, characterized by multiple issues such as the incompleteness of the available annotations, the integration of multiple sources of high dimensional biomolecular data, the unbalance of several functional classes, and the difficulty of univocally determining negative examples. Moreover, the hierarchical relationships between functional classes that characterize both the Gene Ontology and FunCat taxonomies motivate the development of hierarchy-aware prediction methods that showed significantly better performances than hierarchical-unaware “flat” prediction methods. In this paper, we provide a comprehensive review of hierarchical methods for protein function prediction based on ensembles of learning machines. According to this general approach, a separate learning machine is trained to learn a specific functional term and then the resulting predictions are assembled in a “consensus” ensemble decision, taking into account the hierarchical relationships between classes. The main hierarchical ensemble methods proposed in the literature are discussed in the context of existing computational methods for protein function prediction, highlighting their characteristics, advantages, and limitations. Open problems of this exciting research area of computational biology are finally considered, outlining novel perspectives for future research. PMID:25937954

Ensemble kalman filtering to perform data assimilation with soil water content probes and pedotransfer functions in modeling water flow in variably saturated soils

USDA-ARS?s Scientific Manuscript database

Data from modern soil water contents probes can be used for data assimilation in soil water flow modeling, i.e. continual correction of the flow model performance based on observations. The ensemble Kalman filter appears to be an appropriate method for that. The method requires estimates of the unce...

Performance analysis of a Principal Component Analysis ensemble classifier for Emotiv headset P300 spellers.

PubMed

Elsawy, Amr S; Eldawlatly, Seif; Taher, Mohamed; Aly, Gamal M

2014-01-01

The current trend to use Brain-Computer Interfaces (BCIs) with mobile devices mandates the development of efficient EEG data processing methods. In this paper, we demonstrate the performance of a Principal Component Analysis (PCA) ensemble classifier for P300-based spellers. We recorded EEG data from multiple subjects using the Emotiv neuroheadset in the context of a classical oddball P300 speller paradigm. We compare the performance of the proposed ensemble classifier to the performance of traditional feature extraction and classifier methods. Our results demonstrate the capability of the PCA ensemble classifier to classify P300 data recorded using the Emotiv neuroheadset with an average accuracy of 86.29% on cross-validation data. In addition, offline testing of the recorded data reveals an average classification accuracy of 73.3% that is significantly higher than that achieved using traditional methods. Finally, we demonstrate the effect of the parameters of the P300 speller paradigm on the performance of the method.

Creating ensembles of decision trees through sampling

DOEpatents

Kamath, Chandrika; Cantu-Paz, Erick

2005-08-30

A system for decision tree ensembles that includes a module to read the data, a module to sort the data, a module to evaluate a potential split of the data according to some criterion using a random sample of the data, a module to split the data, and a module to combine multiple decision trees in ensembles. The decision tree method is based on statistical sampling techniques and includes the steps of reading the data; sorting the data; evaluating a potential split according to some criterion using a random sample of the data, splitting the data, and combining multiple decision trees in ensembles.

Uncertainty Quantification in Alchemical Free Energy Methods.

PubMed

Bhati, Agastya P; Wan, Shunzhou; Hu, Yuan; Sherborne, Brad; Coveney, Peter V

2018-06-12

Alchemical free energy methods have gained much importance recently from several reports of improved ligand-protein binding affinity predictions based on their implementation using molecular dynamics simulations. A large number of variants of such methods implementing different accelerated sampling techniques and free energy estimators are available, each claimed to be better than the others in its own way. However, the key features of reproducibility and quantification of associated uncertainties in such methods have barely been discussed. Here, we apply a systematic protocol for uncertainty quantification to a number of popular alchemical free energy methods, covering both absolute and relative free energy predictions. We show that a reliable measure of error estimation is provided by ensemble simulation-an ensemble of independent MD simulations-which applies irrespective of the free energy method. The need to use ensemble methods is fundamental and holds regardless of the duration of time of the molecular dynamics simulations performed.

Mixture EMOS model for calibrating ensemble forecasts of wind speed.

PubMed

Baran, S; Lerch, S

2016-03-01

Ensemble model output statistics (EMOS) is a statistical tool for post-processing forecast ensembles of weather variables obtained from multiple runs of numerical weather prediction models in order to produce calibrated predictive probability density functions. The EMOS predictive probability density function is given by a parametric distribution with parameters depending on the ensemble forecasts. We propose an EMOS model for calibrating wind speed forecasts based on weighted mixtures of truncated normal (TN) and log-normal (LN) distributions where model parameters and component weights are estimated by optimizing the values of proper scoring rules over a rolling training period. The new model is tested on wind speed forecasts of the 50 member European Centre for Medium-range Weather Forecasts ensemble, the 11 member Aire Limitée Adaptation dynamique Développement International-Hungary Ensemble Prediction System ensemble of the Hungarian Meteorological Service, and the eight-member University of Washington mesoscale ensemble, and its predictive performance is compared with that of various benchmark EMOS models based on single parametric families and combinations thereof. The results indicate improved calibration of probabilistic and accuracy of point forecasts in comparison with the raw ensemble and climatological forecasts. The mixture EMOS model significantly outperforms the TN and LN EMOS methods; moreover, it provides better calibrated forecasts than the TN-LN combination model and offers an increased flexibility while avoiding covariate selection problems. © 2016 The Authors Environmetrics Published by JohnWiley & Sons Ltd.

A New Multivariate Approach in Generating Ensemble Meteorological Forcings for Hydrological Forecasting

NASA Astrophysics Data System (ADS)

Khajehei, Sepideh; Moradkhani, Hamid

2015-04-01

Producing reliable and accurate hydrologic ensemble forecasts are subject to various sources of uncertainty, including meteorological forcing, initial conditions, model structure, and model parameters. Producing reliable and skillful precipitation ensemble forecasts is one approach to reduce the total uncertainty in hydrological applications. Currently, National Weather Prediction (NWP) models are developing ensemble forecasts for various temporal ranges. It is proven that raw products from NWP models are biased in mean and spread. Given the above state, there is a need for methods that are able to generate reliable ensemble forecasts for hydrological applications. One of the common techniques is to apply statistical procedures in order to generate ensemble forecast from NWP-generated single-value forecasts. The procedure is based on the bivariate probability distribution between the observation and single-value precipitation forecast. However, one of the assumptions of the current method is fitting Gaussian distribution to the marginal distributions of observed and modeled climate variable. Here, we have described and evaluated a Bayesian approach based on Copula functions to develop an ensemble precipitation forecast from the conditional distribution of single-value precipitation forecasts. Copula functions are known as the multivariate joint distribution of univariate marginal distributions, which are presented as an alternative procedure in capturing the uncertainties related to meteorological forcing. Copulas are capable of modeling the joint distribution of two variables with any level of correlation and dependency. This study is conducted over a sub-basin in the Columbia River Basin in USA using the monthly precipitation forecasts from Climate Forecast System (CFS) with 0.5x0.5 Deg. spatial resolution to reproduce the observations. The verification is conducted on a different period and the superiority of the procedure is compared with Ensemble Pre-Processor approach currently used by National Weather Service River Forecast Centers in USA.

Ensemble of classifiers for ontology enrichment

NASA Astrophysics Data System (ADS)

Semenova, A. V.; Kureichik, V. M.

2018-05-01

A classifier is a basis of ontology learning systems. Classification of text documents is used in many applications, such as information retrieval, information extraction, definition of spam. A new ensemble of classifiers based on SVM (a method of support vectors), LSTM (neural network) and word embedding are suggested. An experiment was conducted on open data, which allows us to conclude that the proposed classification method is promising. The implementation of the proposed classifier is performed in the Matlab using the functions of the Text Analytics Toolbox. The principal difference between the proposed ensembles of classifiers is the high quality of classification of data at acceptable time costs.

Multi-Optimisation Consensus Clustering

NASA Astrophysics Data System (ADS)

Li, Jian; Swift, Stephen; Liu, Xiaohui

Ensemble Clustering has been developed to provide an alternative way of obtaining more stable and accurate clustering results. It aims to avoid the biases of individual clustering algorithms. However, it is still a challenge to develop an efficient and robust method for Ensemble Clustering. Based on an existing ensemble clustering method, Consensus Clustering (CC), this paper introduces an advanced Consensus Clustering algorithm called Multi-Optimisation Consensus Clustering (MOCC), which utilises an optimised Agreement Separation criterion and a Multi-Optimisation framework to improve the performance of CC. Fifteen different data sets are used for evaluating the performance of MOCC. The results reveal that MOCC can generate more accurate clustering results than the original CC algorithm.

Method of inducing surface ensembles on a metal catalyst

DOEpatents

Miller, Steven S.

1989-01-01

A method of inducing surface ensembles on a transition metal catalyst used in the conversion of a reactant gas or gas mixture, such as carbon monoxide and hydrogen into hydrocarbons (the Fischer-Tropsch reaction) is disclosed which comprises adding a Lewis base to the syngas (CO+H.sub.2) mixture before reaction takes place. The formation of surface ensembles in this manner restricts the number and types of reaction pathways which will be utilized, thus greatly narrowing the product distribution and maximizing the efficiency of the Fischer-Tropsch reaction. Similarly, amines may also be produced by the conversion of reactant gas or gases, such as nitrogen, hydrogen, or hydrocarbon constituents.

Method of inducing surface ensembles on a metal catalyst

DOEpatents

Miller, S.S.

1987-10-02

A method of inducing surface ensembles on a transition metal catalyst used in the conversion of a reactant gas or gas mixture, such as carbon monoxide and hydrogen into hydrocarbons (the Fischer-Tropsch reaction) is disclosed which comprises adding a Lewis base to the syngas (CO + H/sub 2/) mixture before reaction takes place. The formation of surface ensembles in this manner restricts the number and types of reaction pathways which will be utilized, thus greatly narrowing the product distribution and maximizing the efficiency of the Fischer-Tropsch reaction. Similarly, amines may also be produced by the conversion of reactant gas or gases, such as nitrogen, hydrogen, or hydrocarbon constituents.

Simulation of tropical cyclone activity over the western North Pacific based on CMIP5 models

NASA Astrophysics Data System (ADS)

Shen, Haibo; Zhou, Weican; Zhao, Haikun

2017-09-01

Based on the Coupled Model Inter-comparison Project 5 (CMIP5) models, the tropical cyclone (TC) activity in the summers of 1965-2005 over the western North Pacific (WNP) is simulated by a TC dynamically downscaling system. In consideration of diversity among climate models, Bayesian model averaging (BMA) and equal-weighed model averaging (EMA) methods are applied to produce the ensemble large-scale environmental factors of the CMIP5 model outputs. The environmental factors generated by BMA and EMA methods are compared, as well as the corresponding TC simulations by the downscaling system. Results indicate that BMA method shows a significant advantage over the EMA. In addition, impacts of model selections on BMA method are examined. To each factor, ten models with better performance are selected from 30 CMIP5 models and then conduct BMA, respectively. As a consequence, the ensemble environmental factors and simulated TC activity are similar with the results from the 30 models' BMA, which verifies the BMA method can afford corresponding weight for each model in the ensemble based on the model's predictive skill. Thereby, the existence of poor performance models will not particularly affect the BMA effectiveness and the ensemble outcomes are improved. Finally, based upon the BMA method and downscaling system, we analyze the sensitivity of TC activity to three important environmental factors, i.e., sea surface temperature (SST), large-scale steering flow, and vertical wind shear. Among three factors, SST and large-scale steering flow greatly affect TC tracks, while average intensity distribution is sensitive to all three environmental factors. Moreover, SST and vertical wind shear jointly play a critical role in the inter-annual variability of TC lifetime maximum intensity and frequency of intense TCs.

A new approach to human microRNA target prediction using ensemble pruning and rotation forest.

PubMed

Mousavi, Reza; Eftekhari, Mahdi; Haghighi, Mehdi Ghezelbash

2015-12-01

MicroRNAs (miRNAs) are small non-coding RNAs that have important functions in gene regulation. Since finding miRNA target experimentally is costly and needs spending much time, the use of machine learning methods is a growing research area for miRNA target prediction. In this paper, a new approach is proposed by using two popular ensemble strategies, i.e. Ensemble Pruning and Rotation Forest (EP-RTF), to predict human miRNA target. For EP, the approach utilizes Genetic Algorithm (GA). In other words, a subset of classifiers from the heterogeneous ensemble is first selected by GA. Next, the selected classifiers are trained based on the RTF method and then are combined using weighted majority voting. In addition to seeking a better subset of classifiers, the parameter of RTF is also optimized by GA. Findings of the present study confirm that the newly developed EP-RTF outperforms (in terms of classification accuracy, sensitivity, and specificity) the previously applied methods over four datasets in the field of human miRNA target. Diversity-error diagrams reveal that the proposed ensemble approach constructs individual classifiers which are more accurate and usually diverse than the other ensemble approaches. Given these experimental results, we highly recommend EP-RTF for improving the performance of miRNA target prediction.

Comparison of modeling methods to predict the spatial distribution of deep-sea coral and sponge in the Gulf of Alaska

NASA Astrophysics Data System (ADS)

Rooper, Christopher N.; Zimmermann, Mark; Prescott, Megan M.

2017-08-01

Deep-sea coral and sponge ecosystems are widespread throughout most of Alaska's marine waters, and are associated with many different species of fishes and invertebrates. These ecosystems are vulnerable to the effects of commercial fishing activities and climate change. We compared four commonly used species distribution models (general linear models, generalized additive models, boosted regression trees and random forest models) and an ensemble model to predict the presence or absence and abundance of six groups of benthic invertebrate taxa in the Gulf of Alaska. All four model types performed adequately on training data for predicting presence and absence, with regression forest models having the best overall performance measured by the area under the receiver-operating-curve (AUC). The models also performed well on the test data for presence and absence with average AUCs ranging from 0.66 to 0.82. For the test data, ensemble models performed the best. For abundance data, there was an obvious demarcation in performance between the two regression-based methods (general linear models and generalized additive models), and the tree-based models. The boosted regression tree and random forest models out-performed the other models by a wide margin on both the training and testing data. However, there was a significant drop-off in performance for all models of invertebrate abundance ( 50%) when moving from the training data to the testing data. Ensemble model performance was between the tree-based and regression-based methods. The maps of predictions from the models for both presence and abundance agreed very well across model types, with an increase in variability in predictions for the abundance data. We conclude that where data conforms well to the modeled distribution (such as the presence-absence data and binomial distribution in this study), the four types of models will provide similar results, although the regression-type models may be more consistent with biological theory. For data with highly zero-inflated distributions and non-normal distributions such as the abundance data from this study, the tree-based methods performed better. Ensemble models that averaged predictions across the four model types, performed better than the GLM or GAM models but slightly poorer than the tree-based methods, suggesting ensemble models might be more robust to overfitting than tree methods, while mitigating some of the disadvantages in predictive performance of regression methods.

Protein Sequence Classification with Improved Extreme Learning Machine Algorithms

PubMed Central

2014-01-01

Precisely classifying a protein sequence from a large biological protein sequences database plays an important role for developing competitive pharmacological products. Comparing the unseen sequence with all the identified protein sequences and returning the category index with the highest similarity scored protein, conventional methods are usually time-consuming. Therefore, it is urgent and necessary to build an efficient protein sequence classification system. In this paper, we study the performance of protein sequence classification using SLFNs. The recent efficient extreme learning machine (ELM) and its invariants are utilized as the training algorithms. The optimal pruned ELM is first employed for protein sequence classification in this paper. To further enhance the performance, the ensemble based SLFNs structure is constructed where multiple SLFNs with the same number of hidden nodes and the same activation function are used as ensembles. For each ensemble, the same training algorithm is adopted. The final category index is derived using the majority voting method. Two approaches, namely, the basic ELM and the OP-ELM, are adopted for the ensemble based SLFNs. The performance is analyzed and compared with several existing methods using datasets obtained from the Protein Information Resource center. The experimental results show the priority of the proposed algorithms. PMID:24795876

Sampling the isothermal-isobaric ensemble by Langevin dynamics

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

Gao, Xingyu; Institute of Applied Physics and Computational Mathematics, Fenghao East Road 2, Beijing 100094; CAEP Software Center for High Performance Numerical Simulation, Huayuan Road 6, Beijing 100088

2016-03-28

We present a new method of conducting fully flexible-cell molecular dynamics simulation in isothermal-isobaric ensemble based on Langevin equations of motion. The stochastic coupling to all particle and cell degrees of freedoms is introduced in a correct way, in the sense that the stationary configurational distribution is proved to be consistent with that of the isothermal-isobaric ensemble. In order to apply the proposed method in computer simulations, a second order symmetric numerical integration scheme is developed by Trotter’s splitting of the single-step propagator. Moreover, a practical guide of choosing working parameters is suggested for user specified thermo- and baro-coupling timemore » scales. The method and software implementation are carefully validated by a numerical example.« less

Force Sensor Based Tool Condition Monitoring Using a Heterogeneous Ensemble Learning Model

PubMed Central

Wang, Guofeng; Yang, Yinwei; Li, Zhimeng

2014-01-01

Tool condition monitoring (TCM) plays an important role in improving machining efficiency and guaranteeing workpiece quality. In order to realize reliable recognition of the tool condition, a robust classifier needs to be constructed to depict the relationship between tool wear states and sensory information. However, because of the complexity of the machining process and the uncertainty of the tool wear evolution, it is hard for a single classifier to fit all the collected samples without sacrificing generalization ability. In this paper, heterogeneous ensemble learning is proposed to realize tool condition monitoring in which the support vector machine (SVM), hidden Markov model (HMM) and radius basis function (RBF) are selected as base classifiers and a stacking ensemble strategy is further used to reflect the relationship between the outputs of these base classifiers and tool wear states. Based on the heterogeneous ensemble learning classifier, an online monitoring system is constructed in which the harmonic features are extracted from force signals and a minimal redundancy and maximal relevance (mRMR) algorithm is utilized to select the most prominent features. To verify the effectiveness of the proposed method, a titanium alloy milling experiment was carried out and samples with different tool wear states were collected to build the proposed heterogeneous ensemble learning classifier. Moreover, the homogeneous ensemble learning model and majority voting strategy are also adopted to make a comparison. The analysis and comparison results show that the proposed heterogeneous ensemble learning classifier performs better in both classification accuracy and stability. PMID:25405514

Force sensor based tool condition monitoring using a heterogeneous ensemble learning model.

PubMed

Wang, Guofeng; Yang, Yinwei; Li, Zhimeng

2014-11-14

Tool condition monitoring (TCM) plays an important role in improving machining efficiency and guaranteeing workpiece quality. In order to realize reliable recognition of the tool condition, a robust classifier needs to be constructed to depict the relationship between tool wear states and sensory information. However, because of the complexity of the machining process and the uncertainty of the tool wear evolution, it is hard for a single classifier to fit all the collected samples without sacrificing generalization ability. In this paper, heterogeneous ensemble learning is proposed to realize tool condition monitoring in which the support vector machine (SVM), hidden Markov model (HMM) and radius basis function (RBF) are selected as base classifiers and a stacking ensemble strategy is further used to reflect the relationship between the outputs of these base classifiers and tool wear states. Based on the heterogeneous ensemble learning classifier, an online monitoring system is constructed in which the harmonic features are extracted from force signals and a minimal redundancy and maximal relevance (mRMR) algorithm is utilized to select the most prominent features. To verify the effectiveness of the proposed method, a titanium alloy milling experiment was carried out and samples with different tool wear states were collected to build the proposed heterogeneous ensemble learning classifier. Moreover, the homogeneous ensemble learning model and majority voting strategy are also adopted to make a comparison. The analysis and comparison results show that the proposed heterogeneous ensemble learning classifier performs better in both classification accuracy and stability.

Using ensemble of classifiers for predicting HIV protease cleavage sites in proteins.

PubMed

Nanni, Loris; Lumini, Alessandra

2009-03-01

The focus of this work is the use of ensembles of classifiers for predicting HIV protease cleavage sites in proteins. Due to the complex relationships in the biological data, several recent works show that often ensembles of learning algorithms outperform stand-alone methods. We show that the fusion of approaches based on different encoding models can be useful for improving the performance of this classification problem. In particular, in this work four different feature encodings for peptides are described and tested. An extensive evaluation on a large dataset according to a blind testing protocol is reported which demonstrates how different feature extraction methods and classifiers can be combined for obtaining a robust and reliable system. The comparison with other stand-alone approaches allows quantifying the performance improvement obtained by the ensembles proposed in this work.

Multi-model ensembles for assessment of flood losses and associated uncertainty

NASA Astrophysics Data System (ADS)

Figueiredo, Rui; Schröter, Kai; Weiss-Motz, Alexander; Martina, Mario L. V.; Kreibich, Heidi

2018-05-01

Flood loss modelling is a crucial part of risk assessments. However, it is subject to large uncertainty that is often neglected. Most models available in the literature are deterministic, providing only single point estimates of flood loss, and large disparities tend to exist among them. Adopting any one such model in a risk assessment context is likely to lead to inaccurate loss estimates and sub-optimal decision-making. In this paper, we propose the use of multi-model ensembles to address these issues. This approach, which has been applied successfully in other scientific fields, is based on the combination of different model outputs with the aim of improving the skill and usefulness of predictions. We first propose a model rating framework to support ensemble construction, based on a probability tree of model properties, which establishes relative degrees of belief between candidate models. Using 20 flood loss models in two test cases, we then construct numerous multi-model ensembles, based both on the rating framework and on a stochastic method, differing in terms of participating members, ensemble size and model weights. We evaluate the performance of ensemble means, as well as their probabilistic skill and reliability. Our results demonstrate that well-designed multi-model ensembles represent a pragmatic approach to consistently obtain more accurate flood loss estimates and reliable probability distributions of model uncertainty.

Ensemble training to improve recognition using 2D ear

NASA Astrophysics Data System (ADS)

Middendorff, Christopher; Bowyer, Kevin W.

2009-05-01

The ear has gained popularity as a biometric feature due to the robustness of the shape over time and across emotional expression. Popular methods of ear biometrics analyze the ear as a whole, leaving these methods vulnerable to error due to occlusion. Many researchers explore ear recognition using an ensemble, but none present a method for designing the individual parts that comprise the ensemble. In this work, we introduce a method of modifying the ensemble shapes to improve performance. We determine how different properties of an ensemble training system can affect overall performance. We show that ensembles built from small parts will outperform ensembles built with larger parts, and that incorporating a large number of parts improves the performance of the ensemble.

A Novel Bearing Multi-Fault Diagnosis Approach Based on Weighted Permutation Entropy and an Improved SVM Ensemble Classifier.

PubMed

Zhou, Shenghan; Qian, Silin; Chang, Wenbing; Xiao, Yiyong; Cheng, Yang

2018-06-14

Timely and accurate state detection and fault diagnosis of rolling element bearings are very critical to ensuring the reliability of rotating machinery. This paper proposes a novel method of rolling bearing fault diagnosis based on a combination of ensemble empirical mode decomposition (EEMD), weighted permutation entropy (WPE) and an improved support vector machine (SVM) ensemble classifier. A hybrid voting (HV) strategy that combines SVM-based classifiers and cloud similarity measurement (CSM) was employed to improve the classification accuracy. First, the WPE value of the bearing vibration signal was calculated to detect the fault. Secondly, if a bearing fault occurred, the vibration signal was decomposed into a set of intrinsic mode functions (IMFs) by EEMD. The WPE values of the first several IMFs were calculated to form the fault feature vectors. Then, the SVM ensemble classifier was composed of binary SVM and the HV strategy to identify the bearing multi-fault types. Finally, the proposed model was fully evaluated by experiments and comparative studies. The results demonstrate that the proposed method can effectively detect bearing faults and maintain a high accuracy rate of fault recognition when a small number of training samples are available.

Conservative strategy-based ensemble surrogate model for optimal groundwater remediation design at DNAPLs-contaminated sites

NASA Astrophysics Data System (ADS)

Ouyang, Qi; Lu, Wenxi; Lin, Jin; Deng, Wenbing; Cheng, Weiguo

2017-08-01

The surrogate-based simulation-optimization techniques are frequently used for optimal groundwater remediation design. When this technique is used, surrogate errors caused by surrogate-modeling uncertainty may lead to generation of infeasible designs. In this paper, a conservative strategy that pushes the optimal design into the feasible region was used to address surrogate-modeling uncertainty. In addition, chance-constrained programming (CCP) was adopted to compare with the conservative strategy in addressing this uncertainty. Three methods, multi-gene genetic programming (MGGP), Kriging (KRG) and support vector regression (SVR), were used to construct surrogate models for a time-consuming multi-phase flow model. To improve the performance of the surrogate model, ensemble surrogates were constructed based on combinations of different stand-alone surrogate models. The results show that: (1) the surrogate-modeling uncertainty was successfully addressed by the conservative strategy, which means that this method is promising for addressing surrogate-modeling uncertainty. (2) The ensemble surrogate model that combines MGGP with KRG showed the most favorable performance, which indicates that this ensemble surrogate can utilize both stand-alone surrogate models to improve the performance of the surrogate model.

Creating "Intelligent" Ensemble Averages Using a Process-Based Framework

NASA Astrophysics Data System (ADS)

Baker, Noel; Taylor, Patrick

2014-05-01

The CMIP5 archive contains future climate projections from over 50 models provided by dozens of modeling centers from around the world. Individual model projections, however, are subject to biases created by structural model uncertainties. As a result, ensemble averaging of multiple models is used to add value to individual model projections and construct a consensus projection. Previous reports for the IPCC establish climate change projections based on an equal-weighted average of all model projections. However, individual models reproduce certain climate processes better than other models. Should models be weighted based on performance? Unequal ensemble averages have previously been constructed using a variety of mean state metrics. What metrics are most relevant for constraining future climate projections? This project develops a framework for systematically testing metrics in models to identify optimal metrics for unequal weighting multi-model ensembles. The intention is to produce improved ("intelligent") unequal-weight ensemble averages. A unique aspect of this project is the construction and testing of climate process-based model evaluation metrics. A climate process-based metric is defined as a metric based on the relationship between two physically related climate variables—e.g., outgoing longwave radiation and surface temperature. Several climate process metrics are constructed using high-quality Earth radiation budget data from NASA's Clouds and Earth's Radiant Energy System (CERES) instrument in combination with surface temperature data sets. It is found that regional values of tested quantities can vary significantly when comparing the equal-weighted ensemble average and an ensemble weighted using the process-based metric. Additionally, this study investigates the dependence of the metric weighting scheme on the climate state using a combination of model simulations including a non-forced preindustrial control experiment, historical simulations, and several radiative forcing Representative Concentration Pathway (RCP) scenarios. Ultimately, the goal of the framework is to advise better methods for ensemble averaging models and create better climate predictions.

A variational ensemble scheme for noisy image data assimilation

NASA Astrophysics Data System (ADS)

Yang, Yin; Robinson, Cordelia; Heitz, Dominique; Mémin, Etienne

2014-05-01

Data assimilation techniques aim at recovering a system state variables trajectory denoted as X, along time from partially observed noisy measurements of the system denoted as Y. These procedures, which couple dynamics and noisy measurements of the system, fulfill indeed a twofold objective. On one hand, they provide a denoising - or reconstruction - procedure of the data through a given model framework and on the other hand, they provide estimation procedures for unknown parameters of the dynamics. A standard variational data assimilation problem can be formulated as the minimization of the following objective function with respect to the initial discrepancy, η, from the background initial guess: δ« J(η(x)) = 1∥Xb (x) - X (t ,x)∥2 + 1 tf∥H(X (t,x ))- Y (t,x)∥2dt. 2 0 0 B 2 t0 R (1) where the observation operator H links the state variable and the measurements. The cost function can be interpreted as the log likelihood function associated to the a posteriori distribution of the state given the past history of measurements and the background. In this work, we aim at studying ensemble based optimal control strategies for data assimilation. Such formulation nicely combines the ingredients of ensemble Kalman filters and variational data assimilation (4DVar). It is also formulated as the minimization of the objective function (1), but similarly to ensemble filter, it introduces in its objective function an empirical ensemble-based background-error covariance defined as: B ≡ <(Xb - )(Xb - )T>. (2) Thus, it works in an off-line smoothing mode rather than on the fly like sequential filters. Such resulting ensemble variational data assimilation technique corresponds to a relatively new family of methods [1,2,3]. It presents two main advantages: first, it does not require anymore to construct the adjoint of the dynamics tangent linear operator, which is a considerable advantage with respect to the method's implementation, and second, it enables the handling of a flow-dependent background error covariance matrix that can be consistently adjusted to the background error. These nice advantages come however at the cost of a reduced rank modeling of the solution space. The B matrix is at most of rank N - 1 (N is the size of the ensemble) which is considerably lower than the dimension of state space. This rank deficiency may introduce spurious correlation errors, which particularly impact the quality of results associated with a high resolution computing grid. The common strategy to suppress these distant correlations for ensemble Kalman techniques is through localization procedures. In this paper we present key theoretical properties associated to different choices of methods involved in this setup and compare with an incremental 4DVar method experimentally the performances of several variations of an ensemble technique of interest. The comparisons have been led on the basis of a Shallow Water model and have been carried out both with synthetic data and real observations. We particularly addressed the potential pitfalls and advantages of the different methods. The results indicate an advantage in favor of the ensemble technique both in quality and computational cost when dealing with incomplete observations. We highlight as the premise of using ensemble variational assimilation, that the initial perturbation used to build the initial ensemble has to fit the physics of the observed phenomenon . We also apply the method to a stochastic shallow-water model which incorporate an uncertainty expression if the subgrid stress tensor related to the ensemble spread. References [1] A. C. Lorenc, The potential of the ensemble kalman filter for nwp - a comparison with 4d-var, Quart. J. Roy. Meteor. Soc., Vol. 129, pp. 3183-3203, 2003. [2] C. Liu, Q. Xiao, and B. Wang, An Ensemble-Based Four-Dimensional Variational Data Assimilation Scheme. Part I: Technical Formulation and Preliminary Test, Mon. Wea. Rev., Vol. 136(9), pp. 3363-3373, 2008. [3] M. Buehner, Ensemble-derived stationary and flow-dependent background-error covariances: Evaluation in a quasi- operational NWP setting, Quart. J. Roy. Meteor. Soc., Vol. 131(607), pp. 1013-1043, April 2005.

Ocean state and uncertainty forecasts using HYCOM with Local Ensemble Transfer Kalman Filter (LETKF)

NASA Astrophysics Data System (ADS)

Wei, Mozheng; Hogan, Pat; Rowley, Clark; Smedstad, Ole-Martin; Wallcraft, Alan; Penny, Steve

2017-04-01

An ensemble forecast system based on the US Navy's operational HYCOM using Local Ensemble Transfer Kalman Filter (LETKF) technology has been developed for ocean state and uncertainty forecasts. One of the advantages is that the best possible initial analysis states for the HYCOM forecasts are provided by the LETKF which assimilates the operational observations using ensemble method. The background covariance during this assimilation process is supplied with the ensemble, thus it avoids the difficulty of developing tangent linear and adjoint models for 4D-VAR from the complicated hybrid isopycnal vertical coordinate in HYCOM. Another advantage is that the ensemble system provides the valuable uncertainty estimate corresponding to every state forecast from HYCOM. Uncertainty forecasts have been proven to be critical for the downstream users and managers to make more scientifically sound decisions in numerical prediction community. In addition, ensemble mean is generally more accurate and skilful than the single traditional deterministic forecast with the same resolution. We will introduce the ensemble system design and setup, present some results from 30-member ensemble experiment, and discuss scientific, technical and computational issues and challenges, such as covariance localization, inflation, model related uncertainties and sensitivity to the ensemble size.

Device and Method for Gathering Ensemble Data Sets

NASA Technical Reports Server (NTRS)

Racette, Paul E. (Inventor)

2014-01-01

An ensemble detector uses calibrated noise references to produce ensemble sets of data from which properties of non-stationary processes may be extracted. The ensemble detector comprising: a receiver; a switching device coupled to the receiver, the switching device configured to selectively connect each of a plurality of reference noise signals to the receiver; and a gain modulation circuit coupled to the receiver and configured to vary a gain of the receiver based on a forcing signal; whereby the switching device selectively connects each of the plurality of reference noise signals to the receiver to produce an output signal derived from the plurality of reference noise signals and the forcing signal.

Accuracy of the microcanonical Lanczos method to compute real-frequency dynamical spectral functions of quantum models at finite temperatures.

PubMed

Okamoto, Satoshi; Alvarez, Gonzalo; Dagotto, Elbio; Tohyama, Takami

2018-04-01

We examine the accuracy of the microcanonical Lanczos method (MCLM) developed by Long et al. [Phys. Rev. B 68, 235106 (2003)PRBMDO0163-182910.1103/PhysRevB.68.235106] to compute dynamical spectral functions of interacting quantum models at finite temperatures. The MCLM is based on the microcanonical ensemble, which becomes exact in the thermodynamic limit. To apply the microcanonical ensemble at a fixed temperature, one has to find energy eigenstates with the energy eigenvalue corresponding to the internal energy in the canonical ensemble. Here, we propose to use thermal pure quantum state methods by Sugiura and Shimizu [Phys. Rev. Lett. 111, 010401 (2013)PRLTAO0031-900710.1103/PhysRevLett.111.010401] to obtain the internal energy. After obtaining the energy eigenstates using the Lanczos diagonalization method, dynamical quantities are computed via a continued fraction expansion, a standard procedure for Lanczos-based numerical methods. Using one-dimensional antiferromagnetic Heisenberg chains with S=1/2, we demonstrate that the proposed procedure is reasonably accurate, even for relatively small systems.

Accuracy of the microcanonical Lanczos method to compute real-frequency dynamical spectral functions of quantum models at finite temperatures

NASA Astrophysics Data System (ADS)

Okamoto, Satoshi; Alvarez, Gonzalo; Dagotto, Elbio; Tohyama, Takami

2018-04-01

We examine the accuracy of the microcanonical Lanczos method (MCLM) developed by Long et al. [Phys. Rev. B 68, 235106 (2003), 10.1103/PhysRevB.68.235106] to compute dynamical spectral functions of interacting quantum models at finite temperatures. The MCLM is based on the microcanonical ensemble, which becomes exact in the thermodynamic limit. To apply the microcanonical ensemble at a fixed temperature, one has to find energy eigenstates with the energy eigenvalue corresponding to the internal energy in the canonical ensemble. Here, we propose to use thermal pure quantum state methods by Sugiura and Shimizu [Phys. Rev. Lett. 111, 010401 (2013), 10.1103/PhysRevLett.111.010401] to obtain the internal energy. After obtaining the energy eigenstates using the Lanczos diagonalization method, dynamical quantities are computed via a continued fraction expansion, a standard procedure for Lanczos-based numerical methods. Using one-dimensional antiferromagnetic Heisenberg chains with S =1 /2 , we demonstrate that the proposed procedure is reasonably accurate, even for relatively small systems.

An "Ensemble Approach" to Modernizing Extreme Precipitation Estimation for Dam Safety Decision-Making

NASA Astrophysics Data System (ADS)

Cifelli, R.; Mahoney, K. M.; Webb, R. S.; McCormick, B.

2017-12-01

To ensure structural and operational safety of dams and other water management infrastructure, water resources managers and engineers require information about the potential for heavy precipitation. The methods and data used to estimate extreme rainfall amounts for managing risk are based on 40-year-old science and in need of improvement. The need to evaluate new approaches based on the best science available has led the states of Colorado and New Mexico to engage a body of scientists and engineers in an innovative "ensemble approach" to updating extreme precipitation estimates. NOAA is at the forefront of one of three technical approaches that make up the "ensemble study"; the three approaches are conducted concurrently and in collaboration with each other. One approach is the conventional deterministic, "storm-based" method, another is a risk-based regional precipitation frequency estimation tool, and the third is an experimental approach utilizing NOAA's state-of-the-art High Resolution Rapid Refresh (HRRR) physically-based dynamical weather prediction model. The goal of the overall project is to use the individual strengths of these different methods to define an updated and broadly acceptable state of the practice for evaluation and design of dam spillways. This talk will highlight the NOAA research and NOAA's role in the overarching goal to better understand and characterizing extreme precipitation estimation uncertainty. The research led by NOAA explores a novel high-resolution dataset and post-processing techniques using a super-ensemble of hourly forecasts from the HRRR model. We also investigate how this rich dataset may be combined with statistical methods to optimally cast the data in probabilistic frameworks. NOAA expertise in the physical processes that drive extreme precipitation is also employed to develop careful testing and improved understanding of the limitations of older estimation methods and assumptions. The process of decision making in the midst of uncertainty is a major part of this study. We will speak to how the ensemble approach may be used in concert with one another to manage risk and enhance resiliency in the midst of uncertainty. Finally, the presentation will also address the implications of including climate change in future extreme precipitation estimation studies.

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

PubMed Central

Whalen, Sean; Pandey, Om Prakash

2015-01-01

Prediction problems in biomedical sciences, including protein function prediction (PFP), are generally quite difficult. This is due in part to incomplete knowledge of the cellular phenomenon of interest, the appropriateness and data quality of the variables and measurements used for prediction, as well as a lack of consensus regarding the ideal predictor for specific problems. In such scenarios, a powerful approach to improving prediction performance is to construct heterogeneous ensemble predictors that combine the output of diverse individual predictors that capture complementary aspects of the problems and/or datasets. In this paper, we demonstrate the potential of such heterogeneous ensembles, derived from stacking and ensemble selection methods, for addressing PFP and other similar biomedical prediction problems. Deeper analysis of these results shows that the superior predictive ability of these methods, especially stacking, can be attributed to their attention to the following aspects of the ensemble learning process: (i) better balance of diversity and performance, (ii) more effective calibration of outputs and (iii) more robust incorporation of additional base predictors. Finally, to make the effective application of heterogeneous ensembles to large complex datasets (big data) feasible, we present DataSink, a distributed ensemble learning framework, and demonstrate its sound scalability using the examined datasets. DataSink is publicly available from https://github.com/shwhalen/datasink. PMID:26342255

Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level

PubMed Central

Arshad, Sannia; Rho, Seungmin

2014-01-01

We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes. PMID:25295302

Robust framework to combine diverse classifiers assigning distributed confidence to individual classifiers at class level.

PubMed

Khalid, Shehzad; Arshad, Sannia; Jabbar, Sohail; Rho, Seungmin

2014-01-01

We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes.

A method for ensemble wildland fire simulation

Treesearch

Mark A. Finney; Isaac C. Grenfell; Charles W. McHugh; Robert C. Seli; Diane Trethewey; Richard D. Stratton; Stuart Brittain

2011-01-01

An ensemble simulation system that accounts for uncertainty in long-range weather conditions and two-dimensional wildland fire spread is described. Fuel moisture is expressed based on the energy release component, a US fire danger rating index, and its variation throughout the fire season is modeled using time series analysis of historical weather data. This analysis...

A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers

PubMed Central

2012-01-01

Background Biomarker panels derived separately from genomic and proteomic data and with a variety of computational methods have demonstrated promising classification performance in various diseases. An open question is how to create effective proteo-genomic panels. The framework of ensemble classifiers has been applied successfully in various analytical domains to combine classifiers so that the performance of the ensemble exceeds the performance of individual classifiers. Using blood-based diagnosis of acute renal allograft rejection as a case study, we address the following question in this paper: Can acute rejection classification performance be improved by combining individual genomic and proteomic classifiers in an ensemble? Results The first part of the paper presents a computational biomarker development pipeline for genomic and proteomic data. The pipeline begins with data acquisition (e.g., from bio-samples to microarray data), quality control, statistical analysis and mining of the data, and finally various forms of validation. The pipeline ensures that the various classifiers to be combined later in an ensemble are diverse and adequate for clinical use. Five mRNA genomic and five proteomic classifiers were developed independently using single time-point blood samples from 11 acute-rejection and 22 non-rejection renal transplant patients. The second part of the paper examines five ensembles ranging in size from two to 10 individual classifiers. Performance of ensembles is characterized by area under the curve (AUC), sensitivity, and specificity, as derived from the probability of acute rejection for individual classifiers in the ensemble in combination with one of two aggregation methods: (1) Average Probability or (2) Vote Threshold. One ensemble demonstrated superior performance and was able to improve sensitivity and AUC beyond the best values observed for any of the individual classifiers in the ensemble, while staying within the range of observed specificity. The Vote Threshold aggregation method achieved improved sensitivity for all 5 ensembles, but typically at the cost of decreased specificity. Conclusion Proteo-genomic biomarker ensemble classifiers show promise in the diagnosis of acute renal allograft rejection and can improve classification performance beyond that of individual genomic or proteomic classifiers alone. Validation of our results in an international multicenter study is currently underway. PMID:23216969

A computational pipeline for the development of multi-marker bio-signature panels and ensemble classifiers.

PubMed

Günther, Oliver P; Chen, Virginia; Freue, Gabriela Cohen; Balshaw, Robert F; Tebbutt, Scott J; Hollander, Zsuzsanna; Takhar, Mandeep; McMaster, W Robert; McManus, Bruce M; Keown, Paul A; Ng, Raymond T

2012-12-08

Biomarker panels derived separately from genomic and proteomic data and with a variety of computational methods have demonstrated promising classification performance in various diseases. An open question is how to create effective proteo-genomic panels. The framework of ensemble classifiers has been applied successfully in various analytical domains to combine classifiers so that the performance of the ensemble exceeds the performance of individual classifiers. Using blood-based diagnosis of acute renal allograft rejection as a case study, we address the following question in this paper: Can acute rejection classification performance be improved by combining individual genomic and proteomic classifiers in an ensemble? The first part of the paper presents a computational biomarker development pipeline for genomic and proteomic data. The pipeline begins with data acquisition (e.g., from bio-samples to microarray data), quality control, statistical analysis and mining of the data, and finally various forms of validation. The pipeline ensures that the various classifiers to be combined later in an ensemble are diverse and adequate for clinical use. Five mRNA genomic and five proteomic classifiers were developed independently using single time-point blood samples from 11 acute-rejection and 22 non-rejection renal transplant patients. The second part of the paper examines five ensembles ranging in size from two to 10 individual classifiers. Performance of ensembles is characterized by area under the curve (AUC), sensitivity, and specificity, as derived from the probability of acute rejection for individual classifiers in the ensemble in combination with one of two aggregation methods: (1) Average Probability or (2) Vote Threshold. One ensemble demonstrated superior performance and was able to improve sensitivity and AUC beyond the best values observed for any of the individual classifiers in the ensemble, while staying within the range of observed specificity. The Vote Threshold aggregation method achieved improved sensitivity for all 5 ensembles, but typically at the cost of decreased specificity. Proteo-genomic biomarker ensemble classifiers show promise in the diagnosis of acute renal allograft rejection and can improve classification performance beyond that of individual genomic or proteomic classifiers alone. Validation of our results in an international multicenter study is currently underway.

A study of fuzzy logic ensemble system performance on face recognition problem

NASA Astrophysics Data System (ADS)

Polyakova, A.; Lipinskiy, L.

2017-02-01

Some problems are difficult to solve by using a single intelligent information technology (IIT). The ensemble of the various data mining (DM) techniques is a set of models which are able to solve the problem by itself, but the combination of which allows increasing the efficiency of the system as a whole. Using the IIT ensembles can improve the reliability and efficiency of the final decision, since it emphasizes on the diversity of its components. The new method of the intellectual informational technology ensemble design is considered in this paper. It is based on the fuzzy logic and is designed to solve the classification and regression problems. The ensemble consists of several data mining algorithms: artificial neural network, support vector machine and decision trees. These algorithms and their ensemble have been tested by solving the face recognition problems. Principal components analysis (PCA) is used for feature selection.

Ensemble Grouping Strategies for Embedded Stochastic Collocation Methods Applied to Anisotropic Diffusion Problems

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

D'Elia, M.; Edwards, H. C.; Hu, J.

Previous work has demonstrated that propagating groups of samples, called ensembles, together through forward simulations can dramatically reduce the aggregate cost of sampling-based uncertainty propagation methods [E. Phipps, M. D'Elia, H. C. Edwards, M. Hoemmen, J. Hu, and S. Rajamanickam, SIAM J. Sci. Comput., 39 (2017), pp. C162--C193]. However, critical to the success of this approach when applied to challenging problems of scientific interest is the grouping of samples into ensembles to minimize the total computational work. For example, the total number of linear solver iterations for ensemble systems may be strongly influenced by which samples form the ensemble whenmore » applying iterative linear solvers to parameterized and stochastic linear systems. In this paper we explore sample grouping strategies for local adaptive stochastic collocation methods applied to PDEs with uncertain input data, in particular canonical anisotropic diffusion problems where the diffusion coefficient is modeled by truncated Karhunen--Loève expansions. Finally, we demonstrate that a measure of the total anisotropy of the diffusion coefficient is a good surrogate for the number of linear solver iterations for each sample and therefore provides a simple and effective metric for grouping samples.« less

Ensemble Grouping Strategies for Embedded Stochastic Collocation Methods Applied to Anisotropic Diffusion Problems

DOE PAGES

D'Elia, M.; Edwards, H. C.; Hu, J.; ...

2018-01-18

Previous work has demonstrated that propagating groups of samples, called ensembles, together through forward simulations can dramatically reduce the aggregate cost of sampling-based uncertainty propagation methods [E. Phipps, M. D'Elia, H. C. Edwards, M. Hoemmen, J. Hu, and S. Rajamanickam, SIAM J. Sci. Comput., 39 (2017), pp. C162--C193]. However, critical to the success of this approach when applied to challenging problems of scientific interest is the grouping of samples into ensembles to minimize the total computational work. For example, the total number of linear solver iterations for ensemble systems may be strongly influenced by which samples form the ensemble whenmore » applying iterative linear solvers to parameterized and stochastic linear systems. In this paper we explore sample grouping strategies for local adaptive stochastic collocation methods applied to PDEs with uncertain input data, in particular canonical anisotropic diffusion problems where the diffusion coefficient is modeled by truncated Karhunen--Loève expansions. Finally, we demonstrate that a measure of the total anisotropy of the diffusion coefficient is a good surrogate for the number of linear solver iterations for each sample and therefore provides a simple and effective metric for grouping samples.« less

Characterization of coronary plaque regions in intravascular ultrasound images using a hybrid ensemble classifier.

PubMed

Hwang, Yoo Na; Lee, Ju Hwan; Kim, Ga Young; Shin, Eun Seok; Kim, Sung Min

2018-01-01

The purpose of this study was to propose a hybrid ensemble classifier to characterize coronary plaque regions in intravascular ultrasound (IVUS) images. Pixels were allocated to one of four tissues (fibrous tissue (FT), fibro-fatty tissue (FFT), necrotic core (NC), and dense calcium (DC)) through processes of border segmentation, feature extraction, feature selection, and classification. Grayscale IVUS images and their corresponding virtual histology images were acquired from 11 patients with known or suspected coronary artery disease using 20 MHz catheter. A total of 102 hybrid textural features including first order statistics (FOS), gray level co-occurrence matrix (GLCM), extended gray level run-length matrix (GLRLM), Laws, local binary pattern (LBP), intensity, and discrete wavelet features (DWF) were extracted from IVUS images. To select optimal feature sets, genetic algorithm was implemented. A hybrid ensemble classifier based on histogram and texture information was then used for plaque characterization in this study. The optimal feature set was used as input of this ensemble classifier. After tissue characterization, parameters including sensitivity, specificity, and accuracy were calculated to validate the proposed approach. A ten-fold cross validation approach was used to determine the statistical significance of the proposed method. Our experimental results showed that the proposed method had reliable performance for tissue characterization in IVUS images. The hybrid ensemble classification method outperformed other existing methods by achieving characterization accuracy of 81% for FFT and 75% for NC. In addition, this study showed that Laws features (SSV and SAV) were key indicators for coronary tissue characterization. The proposed method had high clinical applicability for image-based tissue characterization. Copyright © 2017 Elsevier B.V. All rights reserved.

An Efficient Local Correlation Matrix Decomposition Approach for the Localization Implementation of Ensemble-Based Assimilation Methods

NASA Astrophysics Data System (ADS)

Zhang, Hongqin; Tian, Xiangjun

2018-04-01

Ensemble-based data assimilation methods often use the so-called localization scheme to improve the representation of the ensemble background error covariance (Be). Extensive research has been undertaken to reduce the computational cost of these methods by using the localized ensemble samples to localize Be by means of a direct decomposition of the local correlation matrix C. However, the computational costs of the direct decomposition of the local correlation matrix C are still extremely high due to its high dimension. In this paper, we propose an efficient local correlation matrix decomposition approach based on the concept of alternating directions. This approach is intended to avoid direct decomposition of the correlation matrix. Instead, we first decompose the correlation matrix into 1-D correlation matrices in the three coordinate directions, then construct their empirical orthogonal function decomposition at low resolution. This procedure is followed by the 1-D spline interpolation process to transform the above decompositions to the high-resolution grid. Finally, an efficient correlation matrix decomposition is achieved by computing the very similar Kronecker product. We conducted a series of comparison experiments to illustrate the validity and accuracy of the proposed local correlation matrix decomposition approach. The effectiveness of the proposed correlation matrix decomposition approach and its efficient localization implementation of the nonlinear least-squares four-dimensional variational assimilation are further demonstrated by several groups of numerical experiments based on the Advanced Research Weather Research and Forecasting model.

Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS

NASA Astrophysics Data System (ADS)

Tehrany, Mahyat Shafapour; Pradhan, Biswajeet; Jebur, Mustafa Neamah

2014-05-01

Flood is one of the most devastating natural disasters that occur frequently in Terengganu, Malaysia. Recently, ensemble based techniques are getting extremely popular in flood modeling. In this paper, weights-of-evidence (WoE) model was utilized first, to assess the impact of classes of each conditioning factor on flooding through bivariate statistical analysis (BSA). Then, these factors were reclassified using the acquired weights and entered into the support vector machine (SVM) model to evaluate the correlation between flood occurrence and each conditioning factor. Through this integration, the weak point of WoE can be solved and the performance of the SVM will be enhanced. The spatial database included flood inventory, slope, stream power index (SPI), topographic wetness index (TWI), altitude, curvature, distance from the river, geology, rainfall, land use/cover (LULC), and soil type. Four kernel types of SVM (linear kernel (LN), polynomial kernel (PL), radial basis function kernel (RBF), and sigmoid kernel (SIG)) were used to investigate the performance of each kernel type. The efficiency of the new ensemble WoE and SVM method was tested using area under curve (AUC) which measured the prediction and success rates. The validation results proved the strength and efficiency of the ensemble method over the individual methods. The best results were obtained from RBF kernel when compared with the other kernel types. Success rate and prediction rate for ensemble WoE and RBF-SVM method were 96.48% and 95.67% respectively. The proposed ensemble flood susceptibility mapping method could assist researchers and local governments in flood mitigation strategies.

Complete ensemble local mean decomposition with adaptive noise and its application to fault diagnosis for rolling bearings

NASA Astrophysics Data System (ADS)

Wang, Lei; Liu, Zhiwen; Miao, Qiang; Zhang, Xin

2018-06-01

Mode mixing resulting from intermittent signals is an annoying problem associated with the local mean decomposition (LMD) method. Based on noise-assisted approach, ensemble local mean decomposition (ELMD) method alleviates the mode mixing issue of LMD to some degree. However, the product functions (PFs) produced by ELMD often contain considerable residual noise, and thus a relatively large number of ensemble trials are required to eliminate the residual noise. Furthermore, since different realizations of Gaussian white noise are added to the original signal, different trials may generate different number of PFs, making it difficult to take ensemble mean. In this paper, a novel method is proposed called complete ensemble local mean decomposition with adaptive noise (CELMDAN) to solve these two problems. The method adds a particular and adaptive noise at every decomposition stage for each trial. Moreover, a unique residue is obtained after separating each PF, and the obtained residue is used as input for the next stage. Two simulated signals are analyzed to illustrate the advantages of CELMDAN in comparison to ELMD and CEEMDAN. To further demonstrate the efficiency of CELMDAN, the method is applied to diagnose faults for rolling bearings in an experimental case and an engineering case. The diagnosis results indicate that CELMDAN can extract more fault characteristic information with less interference than ELMD.

An Improved Ensemble Learning Method for Classifying High-Dimensional and Imbalanced Biomedicine Data.

PubMed

Yu, Hualong; Ni, Jun

2014-01-01

Training classifiers on skewed data can be technically challenging tasks, especially if the data is high-dimensional simultaneously, the tasks can become more difficult. In biomedicine field, skewed data type often appears. In this study, we try to deal with this problem by combining asymmetric bagging ensemble classifier (asBagging) that has been presented in previous work and an improved random subspace (RS) generation strategy that is called feature subspace (FSS). Specifically, FSS is a novel method to promote the balance level between accuracy and diversity of base classifiers in asBagging. In view of the strong generalization capability of support vector machine (SVM), we adopt it to be base classifier. Extensive experiments on four benchmark biomedicine data sets indicate that the proposed ensemble learning method outperforms many baseline approaches in terms of Accuracy, F-measure, G-mean and AUC evaluation criterions, thus it can be regarded as an effective and efficient tool to deal with high-dimensional and imbalanced biomedical data.

Creating "Intelligent" Climate Model Ensemble Averages Using a Process-Based Framework

NASA Astrophysics Data System (ADS)

Baker, N. C.; Taylor, P. C.

2014-12-01

The CMIP5 archive contains future climate projections from over 50 models provided by dozens of modeling centers from around the world. Individual model projections, however, are subject to biases created by structural model uncertainties. As a result, ensemble averaging of multiple models is often used to add value to model projections: consensus projections have been shown to consistently outperform individual models. Previous reports for the IPCC establish climate change projections based on an equal-weighted average of all model projections. However, certain models reproduce climate processes better than other models. Should models be weighted based on performance? Unequal ensemble averages have previously been constructed using a variety of mean state metrics. What metrics are most relevant for constraining future climate projections? This project develops a framework for systematically testing metrics in models to identify optimal metrics for unequal weighting multi-model ensembles. A unique aspect of this project is the construction and testing of climate process-based model evaluation metrics. A climate process-based metric is defined as a metric based on the relationship between two physically related climate variables—e.g., outgoing longwave radiation and surface temperature. Metrics are constructed using high-quality Earth radiation budget data from NASA's Clouds and Earth's Radiant Energy System (CERES) instrument and surface temperature data sets. It is found that regional values of tested quantities can vary significantly when comparing weighted and unweighted model ensembles. For example, one tested metric weights the ensemble by how well models reproduce the time-series probability distribution of the cloud forcing component of reflected shortwave radiation. The weighted ensemble for this metric indicates lower simulated precipitation (up to .7 mm/day) in tropical regions than the unweighted ensemble: since CMIP5 models have been shown to overproduce precipitation, this result could indicate that the metric is effective in identifying models which simulate more realistic precipitation. Ultimately, the goal of the framework is to identify performance metrics for advising better methods for ensemble averaging models and create better climate predictions.

Nonmechanistic forecasts of seasonal influenza with iterative one-week-ahead distributions.

PubMed

Brooks, Logan C; Farrow, David C; Hyun, Sangwon; Tibshirani, Ryan J; Rosenfeld, Roni

2018-06-15

Accurate and reliable forecasts of seasonal epidemics of infectious disease can assist in the design of countermeasures and increase public awareness and preparedness. This article describes two main contributions we made recently toward this goal: a novel approach to probabilistic modeling of surveillance time series based on "delta densities", and an optimization scheme for combining output from multiple forecasting methods into an adaptively weighted ensemble. Delta densities describe the probability distribution of the change between one observation and the next, conditioned on available data; chaining together nonparametric estimates of these distributions yields a model for an entire trajectory. Corresponding distributional forecasts cover more observed events than alternatives that treat the whole season as a unit, and improve upon multiple evaluation metrics when extracting key targets of interest to public health officials. Adaptively weighted ensembles integrate the results of multiple forecasting methods, such as delta density, using weights that can change from situation to situation. We treat selection of optimal weightings across forecasting methods as a separate estimation task, and describe an estimation procedure based on optimizing cross-validation performance. We consider some details of the data generation process, including data revisions and holiday effects, both in the construction of these forecasting methods and when performing retrospective evaluation. The delta density method and an adaptively weighted ensemble of other forecasting methods each improve significantly on the next best ensemble component when applied separately, and achieve even better cross-validated performance when used in conjunction. We submitted real-time forecasts based on these contributions as part of CDC's 2015/2016 FluSight Collaborative Comparison. Among the fourteen submissions that season, this system was ranked by CDC as the most accurate.

A Fuzzy Integral Ensemble Method in Visual P300 Brain-Computer Interface.

PubMed

Cavrini, Francesco; Bianchi, Luigi; Quitadamo, Lucia Rita; Saggio, Giovanni

2016-01-01

We evaluate the possibility of application of combination of classifiers using fuzzy measures and integrals to Brain-Computer Interface (BCI) based on electroencephalography. In particular, we present an ensemble method that can be applied to a variety of systems and evaluate it in the context of a visual P300-based BCI. Offline analysis of data relative to 5 subjects lets us argue that the proposed classification strategy is suitable for BCI. Indeed, the achieved performance is significantly greater than the average of the base classifiers and, broadly speaking, similar to that of the best one. Thus the proposed methodology allows realizing systems that can be used by different subjects without the need for a preliminary configuration phase in which the best classifier for each user has to be identified. Moreover, the ensemble is often capable of detecting uncertain situations and turning them from misclassifications into abstentions, thereby improving the level of safety in BCI for environmental or device control.

A new strategy for snow-cover mapping using remote sensing data and ensemble based systems techniques

NASA Astrophysics Data System (ADS)

Roberge, S.; Chokmani, K.; De Sève, D.

2012-04-01

The snow cover plays an important role in the hydrological cycle of Quebec (Eastern Canada). Consequently, evaluating its spatial extent interests the authorities responsible for the management of water resources, especially hydropower companies. The main objective of this study is the development of a snow-cover mapping strategy using remote sensing data and ensemble based systems techniques. Planned to be tested in a near real-time operational mode, this snow-cover mapping strategy has the advantage to provide the probability of a pixel to be snow covered and its uncertainty. Ensemble systems are made of two key components. First, a method is needed to build an ensemble of classifiers that is diverse as much as possible. Second, an approach is required to combine the outputs of individual classifiers that make up the ensemble in such a way that correct decisions are amplified, and incorrect ones are cancelled out. In this study, we demonstrate the potential of ensemble systems to snow-cover mapping using remote sensing data. The chosen classifier is a sequential thresholds algorithm using NOAA-AVHRR data adapted to conditions over Eastern Canada. Its special feature is the use of a combination of six sequential thresholds varying according to the day in the winter season. Two versions of the snow-cover mapping algorithm have been developed: one is specific for autumn (from October 1st to December 31st) and the other for spring (from March 16th to May 31st). In order to build the ensemble based system, different versions of the algorithm are created by varying randomly its parameters. One hundred of the versions are included in the ensemble. The probability of a pixel to be snow, no-snow or cloud covered corresponds to the amount of votes the pixel has been classified as such by all classifiers. The overall performance of ensemble based mapping is compared to the overall performance of the chosen classifier, and also with ground observations at meteorological stations.

Intelligent ensemble T-S fuzzy neural networks with RCDPSO_DM optimization for effective handling of complex clinical pathway variances.

PubMed

Du, Gang; Jiang, Zhibin; Diao, Xiaodi; Yao, Yang

2013-07-01

Takagi-Sugeno (T-S) fuzzy neural networks (FNNs) can be used to handle complex, fuzzy, uncertain clinical pathway (CP) variances. However, there are many drawbacks, such as slow training rate, propensity to become trapped in a local minimum and poor ability to perform a global search. In order to improve overall performance of variance handling by T-S FNNs, a new CP variance handling method is proposed in this study. It is based on random cooperative decomposing particle swarm optimization with double mutation mechanism (RCDPSO_DM) for T-S FNNs. Moreover, the proposed integrated learning algorithm, combining the RCDPSO_DM algorithm with a Kalman filtering algorithm, is applied to optimize antecedent and consequent parameters of constructed T-S FNNs. Then, a multi-swarm cooperative immigrating particle swarm algorithm ensemble method is used for intelligent ensemble T-S FNNs with RCDPSO_DM optimization to further improve stability and accuracy of CP variance handling. Finally, two case studies on liver and kidney poisoning variances in osteosarcoma preoperative chemotherapy are used to validate the proposed method. The result demonstrates that intelligent ensemble T-S FNNs based on the RCDPSO_DM achieves superior performances, in terms of stability, efficiency, precision and generalizability, over PSO ensemble of all T-S FNNs with RCDPSO_DM optimization, single T-S FNNs with RCDPSO_DM optimization, standard T-S FNNs, standard Mamdani FNNs and T-S FNNs based on other algorithms (cooperative particle swarm optimization and particle swarm optimization) for CP variance handling. Therefore, it makes CP variance handling more effective. Copyright © 2013 Elsevier Ltd. All rights reserved.

Recognition of medication information from discharge summaries using ensembles of classifiers.

PubMed

Doan, Son; Collier, Nigel; Xu, Hua; Pham, Hoang Duy; Tu, Minh Phuong

2012-05-07

Extraction of clinical information such as medications or problems from clinical text is an important task of clinical natural language processing (NLP). Rule-based methods are often used in clinical NLP systems because they are easy to adapt and customize. Recently, supervised machine learning methods have proven to be effective in clinical NLP as well. However, combining different classifiers to further improve the performance of clinical entity recognition systems has not been investigated extensively. Combining classifiers into an ensemble classifier presents both challenges and opportunities to improve performance in such NLP tasks. We investigated ensemble classifiers that used different voting strategies to combine outputs from three individual classifiers: a rule-based system, a support vector machine (SVM) based system, and a conditional random field (CRF) based system. Three voting methods were proposed and evaluated using the annotated data sets from the 2009 i2b2 NLP challenge: simple majority, local SVM-based voting, and local CRF-based voting. Evaluation on 268 manually annotated discharge summaries from the i2b2 challenge showed that the local CRF-based voting method achieved the best F-score of 90.84% (94.11% Precision, 87.81% Recall) for 10-fold cross-validation. We then compared our systems with the first-ranked system in the challenge by using the same training and test sets. Our system based on majority voting achieved a better F-score of 89.65% (93.91% Precision, 85.76% Recall) than the previously reported F-score of 89.19% (93.78% Precision, 85.03% Recall) by the first-ranked system in the challenge. Our experimental results using the 2009 i2b2 challenge datasets showed that ensemble classifiers that combine individual classifiers into a voting system could achieve better performance than a single classifier in recognizing medication information from clinical text. It suggests that simple strategies that can be easily implemented such as majority voting could have the potential to significantly improve clinical entity recognition.

Comparison of surface freshwater fluxes from different climate forecasts produced through different ensemble generation schemes.

NASA Astrophysics Data System (ADS)

Romanova, Vanya; Hense, Andreas; Wahl, Sabrina; Brune, Sebastian; Baehr, Johanna

2016-04-01

The decadal variability and its predictability of the surface net freshwater fluxes is compared in a set of retrospective predictions, all using the same model setup, and only differing in the implemented ocean initialisation method and ensemble generation method. The basic aim is to deduce the differences between the initialization/ensemble generation methods in view of the uncertainty of the verifying observational data sets. The analysis will give an approximation of the uncertainties of the net freshwater fluxes, which up to now appear to be one of the most uncertain products in observational data and model outputs. All ensemble generation methods are implemented into the MPI-ESM earth system model in the framework of the ongoing MiKlip project (www.fona-miklip.de). Hindcast experiments are initialised annually between 2000-2004, and from each start year 10 ensemble members are initialized for 5 years each. Four different ensemble generation methods are compared: (i) a method based on the Anomaly Transform method (Romanova and Hense, 2015) in which the initial oceanic perturbations represent orthogonal and balanced anomaly structures in space and time and between the variables taken from a control run, (ii) one-day-lagged ocean states from the MPI-ESM-LR baseline system (iii) one-day-lagged of ocean and atmospheric states with preceding full-field nudging to re-analysis in both the atmospheric and the oceanic component of the system - the baseline one MPI-ESM-LR system, (iv) an Ensemble Kalman Filter (EnKF) implemented into oceanic part of MPI-ESM (Brune et al. 2015), assimilating monthly subsurface oceanic temperature and salinity (EN3) using the Parallel Data Assimilation Framework (PDAF). The hindcasts are evaluated probabilistically using fresh water flux data sets from four different reanalysis data sets: MERRA, NCEP-R1, GFDL ocean reanalysis and GECCO2. The assessments show no clear differences in the evaluations scores on regional scales. However, on the global scale the physically motivated methods (i) and (iv) provide probabilistic hindcasts with a consistently higher reliability than the lagged initialization methods (ii)/(iii) despite the large uncertainties in the verifying observations and in the simulations.

An Ensemble Approach in Converging Contents of LMS and KMS

ERIC Educational Resources Information Center

Sabitha, A. Sai; Mehrotra, Deepti; Bansal, Abhay

2017-01-01

Currently the challenges in e-Learning are converging the learning content from various sources and managing them within e-learning practices. Data mining learning algorithms can be used and the contents can be converged based on the Metadata of the objects. Ensemble methods use multiple learning algorithms and it can be used to converge the…

Uncertainty analysis of neural network based flood forecasting models: An ensemble based approach for constructing prediction interval

NASA Astrophysics Data System (ADS)

Kasiviswanathan, K.; Sudheer, K.

2013-05-01

Artificial neural network (ANN) based hydrologic models have gained lot of attention among water resources engineers and scientists, owing to their potential for accurate prediction of flood flows as compared to conceptual or physics based hydrologic models. The ANN approximates the non-linear functional relationship between the complex hydrologic variables in arriving at the river flow forecast values. Despite a large number of applications, there is still some criticism that ANN's point prediction lacks in reliability since the uncertainty of predictions are not quantified, and it limits its use in practical applications. A major concern in application of traditional uncertainty analysis techniques on neural network framework is its parallel computing architecture with large degrees of freedom, which makes the uncertainty assessment a challenging task. Very limited studies have considered assessment of predictive uncertainty of ANN based hydrologic models. In this study, a novel method is proposed that help construct the prediction interval of ANN flood forecasting model during calibration itself. The method is designed to have two stages of optimization during calibration: at stage 1, the ANN model is trained with genetic algorithm (GA) to obtain optimal set of weights and biases vector, and during stage 2, the optimal variability of ANN parameters (obtained in stage 1) is identified so as to create an ensemble of predictions. During the 2nd stage, the optimization is performed with multiple objectives, (i) minimum residual variance for the ensemble mean, (ii) maximum measured data points to fall within the estimated prediction interval and (iii) minimum width of prediction interval. The method is illustrated using a real world case study of an Indian basin. The method was able to produce an ensemble that has an average prediction interval width of 23.03 m3/s, with 97.17% of the total validation data points (measured) lying within the interval. The derived prediction interval for a selected hydrograph in the validation data set is presented in Fig 1. It is noted that most of the observed flows lie within the constructed prediction interval, and therefore provides information about the uncertainty of the prediction. One specific advantage of the method is that when ensemble mean value is considered as a forecast, the peak flows are predicted with improved accuracy by this method compared to traditional single point forecasted ANNs. Fig. 1 Prediction Interval for selected hydrograph

A benchmark for reaction coordinates in the transition path ensemble

PubMed Central

2016-01-01

The molecular mechanism of a reaction is embedded in its transition path ensemble, the complete collection of reactive trajectories. Utilizing the information in the transition path ensemble alone, we developed a novel metric, which we termed the emergent potential energy, for distinguishing reaction coordinates from the bath modes. The emergent potential energy can be understood as the average energy cost for making a displacement of a coordinate in the transition path ensemble. Where displacing a bath mode invokes essentially no cost, it costs significantly to move the reaction coordinate. Based on some general assumptions of the behaviors of reaction and bath coordinates in the transition path ensemble, we proved theoretically with statistical mechanics that the emergent potential energy could serve as a benchmark of reaction coordinates and demonstrated its effectiveness by applying it to a prototypical system of biomolecular dynamics. Using the emergent potential energy as guidance, we developed a committor-free and intuition-independent method for identifying reaction coordinates in complex systems. We expect this method to be applicable to a wide range of reaction processes in complex biomolecular systems. PMID:27059559

A Canonical Ensemble Correlation Prediction Model for Seasonal Precipitation Anomaly

NASA Technical Reports Server (NTRS)

Shen, Samuel S. P.; Lau, William K. M.; Kim, Kyu-Myong; Li, Guilong

2001-01-01

This report describes an optimal ensemble forecasting model for seasonal precipitation and its error estimation. Each individual forecast is based on the canonical correlation analysis (CCA) in the spectral spaces whose bases are empirical orthogonal functions (EOF). The optimal weights in the ensemble forecasting crucially depend on the mean square error of each individual forecast. An estimate of the mean square error of a CCA prediction is made also using the spectral method. The error is decomposed onto EOFs of the predictand and decreases linearly according to the correlation between the predictor and predictand. This new CCA model includes the following features: (1) the use of area-factor, (2) the estimation of prediction error, and (3) the optimal ensemble of multiple forecasts. The new CCA model is applied to the seasonal forecasting of the United States precipitation field. The predictor is the sea surface temperature.

Practical implementation of a particle filter data assimilation approach to estimate initial hydrologic conditions and initialize medium-range streamflow forecasts

NASA Astrophysics Data System (ADS)

Clark, Elizabeth; Wood, Andy; Nijssen, Bart; Mendoza, Pablo; Newman, Andy; Nowak, Kenneth; Arnold, Jeffrey

2017-04-01

In an automated forecast system, hydrologic data assimilation (DA) performs the valuable function of correcting raw simulated watershed model states to better represent external observations, including measurements of streamflow, snow, soil moisture, and the like. Yet the incorporation of automated DA into operational forecasting systems has been a long-standing challenge due to the complexities of the hydrologic system, which include numerous lags between state and output variations. To help demonstrate that such methods can succeed in operational automated implementations, we present results from the real-time application of an ensemble particle filter (PF) for short-range (7 day lead) ensemble flow forecasts in western US river basins. We use the System for Hydromet Applications, Research and Prediction (SHARP), developed by the National Center for Atmospheric Research (NCAR) in collaboration with the University of Washington, U.S. Army Corps of Engineers, and U.S. Bureau of Reclamation. SHARP is a fully automated platform for short-term to seasonal hydrologic forecasting applications, incorporating uncertainty in initial hydrologic conditions (IHCs) and in hydrometeorological predictions through ensemble methods. In this implementation, IHC uncertainty is estimated by propagating an ensemble of 100 temperature and precipitation time series through conceptual and physically-oriented models. The resulting ensemble of derived IHCs exhibits a broad range of possible soil moisture and snow water equivalent (SWE) states. The PF selects and/or weights and resamples the IHCs that are most consistent with external streamflow observations, and uses the particles to initialize a streamflow forecast ensemble driven by ensemble precipitation and temperature forecasts downscaled from the Global Ensemble Forecast System (GEFS). We apply this method in real-time for several basins in the western US that are important for water resources management, and perform a hindcast experiment to evaluate the utility of PF-based data assimilation on streamflow forecasts skill. This presentation describes findings, including a comparison of sequential and non-sequential particle weighting methods.

Reproducing multi-model ensemble average with Ensemble-averaged Reconstructed Forcings (ERF) in regional climate modeling

NASA Astrophysics Data System (ADS)

Erfanian, A.; Fomenko, L.; Wang, G.

2016-12-01

Multi-model ensemble (MME) average is considered the most reliable for simulating both present-day and future climates. It has been a primary reference for making conclusions in major coordinated studies i.e. IPCC Assessment Reports and CORDEX. The biases of individual models cancel out each other in MME average, enabling the ensemble mean to outperform individual members in simulating the mean climate. This enhancement however comes with tremendous computational cost, which is especially inhibiting for regional climate modeling as model uncertainties can originate from both RCMs and the driving GCMs. Here we propose the Ensemble-based Reconstructed Forcings (ERF) approach to regional climate modeling that achieves a similar level of bias reduction at a fraction of cost compared with the conventional MME approach. The new method constructs a single set of initial and boundary conditions (IBCs) by averaging the IBCs of multiple GCMs, and drives the RCM with this ensemble average of IBCs to conduct a single run. Using a regional climate model (RegCM4.3.4-CLM4.5), we tested the method over West Africa for multiple combination of (up to six) GCMs. Our results indicate that the performance of the ERF method is comparable to that of the MME average in simulating the mean climate. The bias reduction seen in ERF simulations is achieved by using more realistic IBCs in solving the system of equations underlying the RCM physics and dynamics. This endows the new method with a theoretical advantage in addition to reducing computational cost. The ERF output is an unaltered solution of the RCM as opposed to a climate state that might not be physically plausible due to the averaging of multiple solutions with the conventional MME approach. The ERF approach should be considered for use in major international efforts such as CORDEX. Key words: Multi-model ensemble, ensemble analysis, ERF, regional climate modeling

Ensemble empirical mode decomposition based fluorescence spectral noise reduction for low concentration PAHs

NASA Astrophysics Data System (ADS)

Wang, Shu-tao; Yang, Xue-ying; Kong, De-ming; Wang, Yu-tian

2017-11-01

A new noise reduction method based on ensemble empirical mode decomposition (EEMD) is proposed to improve the detection effect for fluorescence spectra. Polycyclic aromatic hydrocarbons (PAHs) pollutants, as a kind of important current environmental pollution source, are highly oncogenic. Using the fluorescence spectroscopy method, the PAHs pollutants can be detected. However, instrument will produce noise in the experiment. Weak fluorescent signals can be affected by noise, so we propose a way to denoise and improve the detection effect. Firstly, we use fluorescence spectrometer to detect PAHs to obtain fluorescence spectra. Subsequently, noises are reduced by EEMD algorithm. Finally, the experiment results show the proposed method is feasible.

Ensemble Methods

NASA Astrophysics Data System (ADS)

Re, Matteo; Valentini, Giorgio

2012-03-01

Ensemble methods are statistical and computational learning procedures reminiscent of the human social learning behavior of seeking several opinions before making any crucial decision. The idea of combining the opinions of different "experts" to obtain an overall “ensemble” decision is rooted in our culture at least from the classical age of ancient Greece, and it has been formalized during the Enlightenment with the Condorcet Jury Theorem[45]), which proved that the judgment of a committee is superior to those of individuals, provided the individuals have reasonable competence. Ensembles are sets of learning machines that combine in some way their decisions, or their learning algorithms, or different views of data, or other specific characteristics to obtain more reliable and more accurate predictions in supervised and unsupervised learning problems [48,116]. A simple example is represented by the majority vote ensemble, by which the decisions of different learning machines are combined, and the class that receives the majority of “votes” (i.e., the class predicted by the majority of the learning machines) is the class predicted by the overall ensemble [158]. In the literature, a plethora of terms other than ensembles has been used, such as fusion, combination, aggregation, and committee, to indicate sets of learning machines that work together to solve a machine learning problem [19,40,56,66,99,108,123], but in this chapter we maintain the term ensemble in its widest meaning, in order to include the whole range of combination methods. Nowadays, ensemble methods represent one of the main current research lines in machine learning [48,116], and the interest of the research community on ensemble methods is witnessed by conferences and workshops specifically devoted to ensembles, first of all the multiple classifier systems (MCS) conference organized by Roli, Kittler, Windeatt, and other researchers of this area [14,62,85,149,173]. Several theories have been proposed to explain the characteristics and the successful application of ensembles to different application domains. For instance, Allwein, Schapire, and Singer interpreted the improved generalization capabilities of ensembles of learning machines in the framework of large margin classifiers [4,177], Kleinberg in the context of stochastic discrimination theory [112], and Breiman and Friedman in the light of the bias-variance analysis borrowed from classical statistics [21,70]. Empirical studies showed that both in classification and regression problems, ensembles improve on single learning machines, and moreover large experimental studies compared the effectiveness of different ensemble methods on benchmark data sets [10,11,49,188]. The interest in this research area is motivated also by the availability of very fast computers and networks of workstations at a relatively low cost that allow the implementation and the experimentation of complex ensemble methods using off-the-shelf computer platforms. However, as explained in Section 26.2 there are deeper reasons to use ensembles of learning machines, motivated by the intrinsic characteristics of the ensemble methods. The main aim of this chapter is to introduce ensemble methods and to provide an overview and a bibliography of the main areas of research, without pretending to be exhaustive or to explain the detailed characteristics of each ensemble method. The paper is organized as follows. In the next section, the main theoretical and practical reasons for combining multiple learners are introduced. Section 26.3 depicts the main taxonomies on ensemble methods proposed in the literature. In Section 26.4 and 26.5, we present an overview of the main supervised ensemble methods reported in the literature, adopting a simple taxonomy, originally proposed in Ref. [201]. Applications of ensemble methods are only marginally considered, but a specific section on some relevant applications of ensemble methods in astronomy and astrophysics has been added (Section 26.6). The conclusion (Section 26.7) ends this paper and lists some issues not covered in this work.

Self-consistent implementation of ensemble density functional theory method for multiple strongly correlated electron pairs

DOE PAGES

Filatov, Michael; Liu, Fang; Kim, Kwang S.; ...

2016-12-22

Here, the spin-restricted ensemble-referenced Kohn-Sham (REKS) method is based on an ensemble representation of the density and is capable of correctly describing the non-dynamic electron correlation stemming from (near-)degeneracy of several electronic configurations. The existing REKS methodology describes systems with two electrons in two fractionally occupied orbitals. In this work, the REKS methodology is extended to treat systems with four fractionally occupied orbitals accommodating four electrons and self-consistent implementation of the REKS(4,4) method with simultaneous optimization of the orbitals and their fractional occupation numbers is reported. The new method is applied to a number of molecular systems where simultaneous dissociationmore » of several chemical bonds takes place, as well as to the singlet ground states of organic tetraradicals 2,4-didehydrometaxylylene and 1,4,6,9-spiro[4.4]nonatetrayl.« less

MATLAB algorithm to implement soil water data assimilation with the Ensemble Kalman Filter using HYDRUS.

PubMed

Valdes-Abellan, Javier; Pachepsky, Yakov; Martinez, Gonzalo

2018-01-01

Data assimilation is becoming a promising technique in hydrologic modelling to update not only model states but also to infer model parameters, specifically to infer soil hydraulic properties in Richard-equation-based soil water models. The Ensemble Kalman Filter method is one of the most widely employed method among the different data assimilation alternatives. In this study the complete Matlab© code used to study soil data assimilation efficiency under different soil and climatic conditions is shown. The code shows the method how data assimilation through EnKF was implemented. Richards equation was solved by the used of Hydrus-1D software which was run from Matlab. •MATLAB routines are released to be used/modified without restrictions for other researchers•Data assimilation Ensemble Kalman Filter method code.•Soil water Richard equation flow solved by Hydrus-1D.

Quantifying rapid changes in cardiovascular state with a moving ensemble average.

PubMed

Cieslak, Matthew; Ryan, William S; Babenko, Viktoriya; Erro, Hannah; Rathbun, Zoe M; Meiring, Wendy; Kelsey, Robert M; Blascovich, Jim; Grafton, Scott T

2018-04-01

MEAP, the moving ensemble analysis pipeline, is a new open-source tool designed to perform multisubject preprocessing and analysis of cardiovascular data, including electrocardiogram (ECG), impedance cardiogram (ICG), and continuous blood pressure (BP). In addition to traditional ensemble averaging, MEAP implements a moving ensemble averaging method that allows for the continuous estimation of indices related to cardiovascular state, including cardiac output, preejection period, heart rate variability, and total peripheral resistance, among others. Here, we define the moving ensemble technique mathematically, highlighting its differences from fixed-window ensemble averaging. We describe MEAP's interface and features for signal processing, artifact correction, and cardiovascular-based fMRI analysis. We demonstrate the accuracy of MEAP's novel B point detection algorithm on a large collection of hand-labeled ICG waveforms. As a proof of concept, two subjects completed a series of four physical and cognitive tasks (cold pressor, Valsalva maneuver, video game, random dot kinetogram) on 3 separate days while ECG, ICG, and BP were recorded. Critically, the moving ensemble method reliably captures the rapid cyclical cardiovascular changes related to the baroreflex during the Valsalva maneuver and the classic cold pressor response. Cardiovascular measures were seen to vary considerably within repetitions of the same cognitive task for each individual, suggesting that a carefully designed paradigm could be used to capture fast-acting event-related changes in cardiovascular state. © 2017 Society for Psychophysiological Research.

A simple plug-in bagging ensemble based on threshold-moving for classifying binary and multiclass imbalanced data.

PubMed

Collell, Guillem; Prelec, Drazen; Patil, Kaustubh R

2018-01-31

Class imbalance presents a major hurdle in the application of classification methods. A commonly taken approach is to learn ensembles of classifiers using rebalanced data. Examples include bootstrap averaging (bagging) combined with either undersampling or oversampling of the minority class examples. However, rebalancing methods entail asymmetric changes to the examples of different classes, which in turn can introduce their own biases. Furthermore, these methods often require specifying the performance measure of interest a priori, i.e., before learning. An alternative is to employ the threshold moving technique, which applies a threshold to the continuous output of a model, offering the possibility to adapt to a performance measure a posteriori , i.e., a plug-in method. Surprisingly, little attention has been paid to this combination of a bagging ensemble and threshold-moving. In this paper, we study this combination and demonstrate its competitiveness. Contrary to the other resampling methods, we preserve the natural class distribution of the data resulting in well-calibrated posterior probabilities. Additionally, we extend the proposed method to handle multiclass data. We validated our method on binary and multiclass benchmark data sets by using both, decision trees and neural networks as base classifiers. We perform analyses that provide insights into the proposed method.

Simulating large-scale crop yield by using perturbed-parameter ensemble method

NASA Astrophysics Data System (ADS)

Iizumi, T.; Yokozawa, M.; Sakurai, G.; Nishimori, M.

2010-12-01

Toshichika Iizumi, Masayuki Yokozawa, Gen Sakurai, Motoki Nishimori Agro-Meteorology Division, National Institute for Agro-Environmental Sciences, Japan Abstract One of concerning issues of food security under changing climate is to predict the inter-annual variation of crop production induced by climate extremes and modulated climate. To secure food supply for growing world population, methodology that can accurately predict crop yield on a large scale is needed. However, for developing a process-based large-scale crop model with a scale of general circulation models (GCMs), 100 km in latitude and longitude, researchers encounter the difficulties in spatial heterogeneity of available information on crop production such as cultivated cultivars and management. This study proposed an ensemble-based simulation method that uses a process-based crop model and systematic parameter perturbation procedure, taking maize in U.S., China, and Brazil as examples. The crop model was developed modifying the fundamental structure of the Soil and Water Assessment Tool (SWAT) to incorporate the effect of heat stress on yield. We called the new model PRYSBI: the Process-based Regional-scale Yield Simulator with Bayesian Inference. The posterior probability density function (PDF) of 17 parameters, which represents the crop- and grid-specific features of the crop and its uncertainty under given data, was estimated by the Bayesian inversion analysis. We then take 1500 ensemble members of simulated yield values based on the parameter sets sampled from the posterior PDF to describe yearly changes of the yield, i.e. perturbed-parameter ensemble method. The ensemble median for 27 years (1980-2006) was compared with the data aggregated from the county yield. On a country scale, the ensemble median of the simulated yield showed a good correspondence with the reported yield: the Pearson’s correlation coefficient is over 0.6 for all countries. In contrast, on a grid scale, the correspondence is still high in most grids regardless of the countries. However, the model showed comparatively low reproducibility in the slope areas, such as around the Rocky Mountains in South Dakota, around the Great Xing'anling Mountains in Heilongjiang, and around the Brazilian Plateau. As there is a wide-ranging local climate conditions in the complex terrain, such as the slope of mountain, the GCM grid-scale weather inputs is likely one of major sources of error. The results of this study highlight the benefits of the perturbed-parameter ensemble method in simulating crop yield on a GCM grid scale: (1) the posterior PDF of parameter could quantify the uncertainty of parameter value of the crop model associated with the local crop production aspects; (2) the method can explicitly account for the uncertainty of parameter value in the crop model simulations; (3) the method achieve a Monte Carlo approximation of probability of sub-grid scale yield, accounting for the nonlinear response of crop yield to weather and management; (4) the method is therefore appropriate to aggregate the simulated sub-grid scale yields to a grid-scale yield and it may be a reason for high performance of the model in capturing inter-annual variation of yield.

Multi-objective optimization for generating a weighted multi-model ensemble

NASA Astrophysics Data System (ADS)

Lee, H.

2017-12-01

Many studies have demonstrated that multi-model ensembles generally show better skill than each ensemble member. When generating weighted multi-model ensembles, the first step is measuring the performance of individual model simulations using observations. There is a consensus on the assignment of weighting factors based on a single evaluation metric. When considering only one evaluation metric, the weighting factor for each model is proportional to a performance score or inversely proportional to an error for the model. While this conventional approach can provide appropriate combinations of multiple models, the approach confronts a big challenge when there are multiple metrics under consideration. When considering multiple evaluation metrics, it is obvious that a simple averaging of multiple performance scores or model ranks does not address the trade-off problem between conflicting metrics. So far, there seems to be no best method to generate weighted multi-model ensembles based on multiple performance metrics. The current study applies the multi-objective optimization, a mathematical process that provides a set of optimal trade-off solutions based on a range of evaluation metrics, to combining multiple performance metrics for the global climate models and their dynamically downscaled regional climate simulations over North America and generating a weighted multi-model ensemble. NASA satellite data and the Regional Climate Model Evaluation System (RCMES) software toolkit are used for assessment of the climate simulations. Overall, the performance of each model differs markedly with strong seasonal dependence. Because of the considerable variability across the climate simulations, it is important to evaluate models systematically and make future projections by assigning optimized weighting factors to the models with relatively good performance. Our results indicate that the optimally weighted multi-model ensemble always shows better performance than an arithmetic ensemble mean and may provide reliable future projections.

An Integrated Scenario Ensemble-Based Framework for Hurricane Evacuation Modeling: Part 2-Hazard Modeling.

PubMed

Blanton, Brian; Dresback, Kendra; Colle, Brian; Kolar, Randy; Vergara, Humberto; Hong, Yang; Leonardo, Nicholas; Davidson, Rachel; Nozick, Linda; Wachtendorf, Tricia

2018-04-25

Hurricane track and intensity can change rapidly in unexpected ways, thus making predictions of hurricanes and related hazards uncertain. This inherent uncertainty often translates into suboptimal decision-making outcomes, such as unnecessary evacuation. Representing this uncertainty is thus critical in evacuation planning and related activities. We describe a physics-based hazard modeling approach that (1) dynamically accounts for the physical interactions among hazard components and (2) captures hurricane evolution uncertainty using an ensemble method. This loosely coupled model system provides a framework for probabilistic water inundation and wind speed levels for a new, risk-based approach to evacuation modeling, described in a companion article in this issue. It combines the Weather Research and Forecasting (WRF) meteorological model, the Coupled Routing and Excess STorage (CREST) hydrologic model, and the ADvanced CIRCulation (ADCIRC) storm surge, tide, and wind-wave model to compute inundation levels and wind speeds for an ensemble of hurricane predictions. Perturbations to WRF's initial and boundary conditions and different model physics/parameterizations generate an ensemble of storm solutions, which are then used to drive the coupled hydrologic + hydrodynamic models. Hurricane Isabel (2003) is used as a case study to illustrate the ensemble-based approach. The inundation, river runoff, and wind hazard results are strongly dependent on the accuracy of the mesoscale meteorological simulations, which improves with decreasing lead time to hurricane landfall. The ensemble envelope brackets the observed behavior while providing "best-case" and "worst-case" scenarios for the subsequent risk-based evacuation model. © 2018 Society for Risk Analysis.

An optimized ensemble local mean decomposition method for fault detection of mechanical components

NASA Astrophysics Data System (ADS)

Zhang, Chao; Li, Zhixiong; Hu, Chao; Chen, Shuai; Wang, Jianguo; Zhang, Xiaogang

2017-03-01

Mechanical transmission systems have been widely adopted in most of industrial applications, and issues related to the maintenance of these systems have attracted considerable attention in the past few decades. The recently developed ensemble local mean decomposition (ELMD) method shows satisfactory performance in fault detection of mechanical components for preventing catastrophic failures and reducing maintenance costs. However, the performance of ELMD often heavily depends on proper selection of its model parameters. To this end, this paper proposes an optimized ensemble local mean decomposition (OELMD) method to determinate an optimum set of ELMD parameters for vibration signal analysis. In OELMD, an error index termed the relative root-mean-square error (Relative RMSE) is used to evaluate the decomposition performance of ELMD with a certain amplitude of the added white noise. Once a maximum Relative RMSE, corresponding to an optimal noise amplitude, is determined, OELMD then identifies optimal noise bandwidth and ensemble number based on the Relative RMSE and signal-to-noise ratio (SNR), respectively. Thus, all three critical parameters of ELMD (i.e. noise amplitude and bandwidth, and ensemble number) are optimized by OELMD. The effectiveness of OELMD was evaluated using experimental vibration signals measured from three different mechanical components (i.e. the rolling bearing, gear and diesel engine) under faulty operation conditions.

Clustering algorithms for identifying core atom sets and for assessing the precision of protein structure ensembles.

PubMed

Snyder, David A; Montelione, Gaetano T

2005-06-01

An important open question in the field of NMR-based biomolecular structure determination is how best to characterize the precision of the resulting ensemble of structures. Typically, the RMSD, as minimized in superimposing the ensemble of structures, is the preferred measure of precision. However, the presence of poorly determined atomic coordinates and multiple "RMSD-stable domains"--locally well-defined regions that are not aligned in global superimpositions--complicate RMSD calculations. In this paper, we present a method, based on a novel, structurally defined order parameter, for identifying a set of core atoms to use in determining superimpositions for RMSD calculations. In addition we present a method for deciding whether to partition that core atom set into "RMSD-stable domains" and, if so, how to determine partitioning of the core atom set. We demonstrate our algorithm and its application in calculating statistically sound RMSD values by applying it to a set of NMR-derived structural ensembles, superimposing each RMSD-stable domain (or the entire core atom set, where appropriate) found in each protein structure under consideration. A parameter calculated by our algorithm using a novel, kurtosis-based criterion, the epsilon-value, is a measure of precision of the superimposition that complements the RMSD. In addition, we compare our algorithm with previously described algorithms for determining core atom sets. The methods presented in this paper for biomolecular structure superimposition are quite general, and have application in many areas of structural bioinformatics and structural biology.

Development of Gridded Ensemble Precipitation and Temperature Datasets for the Contiguous United States Plus Hawai'i and Alaska

NASA Astrophysics Data System (ADS)

Newman, A. J.; Clark, M. P.; Nijssen, B.; Wood, A.; Gutmann, E. D.; Mizukami, N.; Longman, R. J.; Giambelluca, T. W.; Cherry, J.; Nowak, K.; Arnold, J.; Prein, A. F.

2016-12-01

Gridded precipitation and temperature products are inherently uncertain due to myriad factors. These include interpolation from a sparse observation network, measurement representativeness, and measurement errors. Despite this inherent uncertainty, uncertainty is typically not included, or is a specific addition to each dataset without much general applicability across different datasets. A lack of quantitative uncertainty estimates for hydrometeorological forcing fields limits their utility to support land surface and hydrologic modeling techniques such as data assimilation, probabilistic forecasting and verification. To address this gap, we have developed a first of its kind gridded, observation-based ensemble of precipitation and temperature at a daily increment for the period 1980-2012 over the United States (including Alaska and Hawaii). A longer, higher resolution version (1970-present, 1/16th degree) has also been implemented to support real-time hydrologic- monitoring and prediction in several regional US domains. We will present the development and evaluation of the dataset, along with initial applications of the dataset for ensemble data assimilation and probabilistic evaluation of high resolution regional climate model simulations. We will also present results on the new high resolution products for Alaska and Hawaii (2 km and 250 m respectively), to complete the first ensemble observation based product suite for the entire 50 states. Finally, we will present plans to improve the ensemble dataset, focusing on efforts to improve the methods used for station interpolation and ensemble generation, as well as methods to fuse station data with numerical weather prediction model output.

Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry.

PubMed

Chowdhury, Alok Kumar; Tjondronegoro, Dian; Chandran, Vinod; Trost, Stewart G

2017-09-01

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.

Predicting drug-induced liver injury using ensemble learning methods and molecular fingerprints.

PubMed

Ai, Haixin; Chen, Wen; Zhang, Li; Huang, Liangchao; Yin, Zimo; Hu, Huan; Zhao, Qi; Zhao, Jian; Liu, Hongsheng

2018-05-21

Drug-induced liver injury (DILI) is a major safety concern in the drug-development process, and various methods have been proposed to predict the hepatotoxicity of compounds during the early stages of drug trials. In this study, we developed an ensemble model using three machine learning algorithms and 12 molecular fingerprints from a dataset containing 1,241 diverse compounds. The ensemble model achieved an average accuracy of 71.1±2.6%, sensitivity of 79.9±3.6%, specificity of 60.3±4.8%, and area under the receiver operating characteristic curve (AUC) of 0.764±0.026 in five-fold cross-validation and an accuracy of 84.3%, sensitivity of 86.9%, specificity of 75.4%, and AUC of 0.904 in an external validation dataset of 286 compounds collected from the Liver Toxicity Knowledge Base (LTKB). Compared with previous methods, the ensemble model achieved relatively high accuracy and sensitivity. We also identified several substructures related to DILI. In addition, we provide a web server offering access to our models (http://ccsipb.lnu.edu.cn/toxicity/HepatoPred-EL/).

Uncovering representations of sleep-associated hippocampal ensemble spike activity

NASA Astrophysics Data System (ADS)

Chen, Zhe; Grosmark, Andres D.; Penagos, Hector; Wilson, Matthew A.

2016-08-01

Pyramidal neurons in the rodent hippocampus exhibit spatial tuning during spatial navigation, and they are reactivated in specific temporal order during sharp-wave ripples observed in quiet wakefulness or slow wave sleep. However, analyzing representations of sleep-associated hippocampal ensemble spike activity remains a great challenge. In contrast to wake, during sleep there is a complete absence of animal behavior, and the ensemble spike activity is sparse (low occurrence) and fragmental in time. To examine important issues encountered in sleep data analysis, we constructed synthetic sleep-like hippocampal spike data (short epochs, sparse and sporadic firing, compressed timescale) for detailed investigations. Based upon two Bayesian population-decoding methods (one receptive field-based, and the other not), we systematically investigated their representation power and detection reliability. Notably, the receptive-field-free decoding method was found to be well-tuned for hippocampal ensemble spike data in slow wave sleep (SWS), even in the absence of prior behavioral measure or ground truth. Our results showed that in addition to the sample length, bin size, and firing rate, number of active hippocampal pyramidal neurons are critical for reliable representation of the space as well as for detection of spatiotemporal reactivated patterns in SWS or quiet wakefulness.

Multi-Model Ensemble Wake Vortex Prediction

NASA Technical Reports Server (NTRS)

Koerner, Stephan; Holzaepfel, Frank; Ahmad, Nash'at N.

2015-01-01

Several multi-model ensemble methods are investigated for predicting wake vortex transport and decay. This study is a joint effort between National Aeronautics and Space Administration and Deutsches Zentrum fuer Luft- und Raumfahrt to develop a multi-model ensemble capability using their wake models. An overview of different multi-model ensemble methods and their feasibility for wake applications is presented. The methods include Reliability Ensemble Averaging, Bayesian Model Averaging, and Monte Carlo Simulations. The methodologies are evaluated using data from wake vortex field experiments.

Girsanov reweighting for path ensembles and Markov state models

NASA Astrophysics Data System (ADS)

Donati, L.; Hartmann, C.; Keller, B. G.

2017-06-01

The sensitivity of molecular dynamics on changes in the potential energy function plays an important role in understanding the dynamics and function of complex molecules. We present a method to obtain path ensemble averages of a perturbed dynamics from a set of paths generated by a reference dynamics. It is based on the concept of path probability measure and the Girsanov theorem, a result from stochastic analysis to estimate a change of measure of a path ensemble. Since Markov state models (MSMs) of the molecular dynamics can be formulated as a combined phase-space and path ensemble average, the method can be extended to reweight MSMs by combining it with a reweighting of the Boltzmann distribution. We demonstrate how to efficiently implement the Girsanov reweighting in a molecular dynamics simulation program by calculating parts of the reweighting factor "on the fly" during the simulation, and we benchmark the method on test systems ranging from a two-dimensional diffusion process and an artificial many-body system to alanine dipeptide and valine dipeptide in implicit and explicit water. The method can be used to study the sensitivity of molecular dynamics on external perturbations as well as to reweight trajectories generated by enhanced sampling schemes to the original dynamics.

A mutual information-Dempster-Shafer based decision ensemble system for land cover classification of hyperspectral data

NASA Astrophysics Data System (ADS)

Pahlavani, Parham; Bigdeli, Behnaz

2017-12-01

Hyperspectral images contain extremely rich spectral information that offer great potential to discriminate between various land cover classes. However, these images are usually composed of tens or hundreds of spectrally close bands, which result in high redundancy and great amount of computation time in hyperspectral classification. Furthermore, in the presence of mixed coverage pixels, crisp classifiers produced errors, omission and commission. This paper presents a mutual information-Dempster-Shafer system through an ensemble classification approach for classification of hyperspectral data. First, mutual information is applied to split data into a few independent partitions to overcome high dimensionality. Then, a fuzzy maximum likelihood classifies each band subset. Finally, Dempster-Shafer is applied to fuse the results of the fuzzy classifiers. In order to assess the proposed method, a crisp ensemble system based on a support vector machine as the crisp classifier and weighted majority voting as the crisp fusion method are applied on hyperspectral data. Furthermore, a dimension reduction system is utilized to assess the effectiveness of mutual information band splitting of the proposed method. The proposed methodology provides interesting conclusions on the effectiveness and potentiality of mutual information-Dempster-Shafer based classification of hyperspectral data.

Paleoclimate reconstruction through Bayesian data assimilation

NASA Astrophysics Data System (ADS)

Fer, I.; Raiho, A.; Rollinson, C.; Dietze, M.

2017-12-01

Methods of paleoclimate reconstruction from plant-based proxy data rely on assumptions of static vegetation-climate link which is often established between modern climate and vegetation. This approach might result in biased climate constructions as it does not account for vegetation dynamics. Predictive tools such as process-based dynamic vegetation models (DVM) and their Bayesian inversion could be used to construct the link between plant-based proxy data and palaeoclimate more realistically. In other words, given the proxy data, it is possible to infer the climate that could result in that particular vegetation composition, by comparing the DVM outputs to the proxy data within a Bayesian state data assimilation framework. In this study, using fossil pollen data from five sites across the northern hardwood region of the US, we assimilate fractional composition and aboveground biomass into dynamic vegetation models, LINKAGES, LPJ-GUESS and ED2. To do this, starting from 4 Global Climate Model outputs, we generate an ensemble of downscaled meteorological drivers for the period 850-2015. Then, as a first pass, we weigh these ensembles based on their fidelity with independent paleoclimate proxies. Next, we run the models with this ensemble of drivers, and comparing the ensemble model output to the vegetation data, adjust the model state estimates towards the data. At each iteration, we also reweight the climate values that make the model and data consistent, producing a reconstructed climate time-series dataset. We validated the method using present-day datasets, as well as a synthetic dataset, and then assessed the consistency of results across ecosystem models. Our method allows the combination of multiple data types to reconstruct the paleoclimate, with associated uncertainty estimates, based on ecophysiological and ecological processes rather than phenomenological correlations with proxy data.

Modality-Driven Classification and Visualization of Ensemble Variance

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

Bensema, Kevin; Gosink, Luke; Obermaier, Harald

Advances in computational power now enable domain scientists to address conceptual and parametric uncertainty by running simulations multiple times in order to sufficiently sample the uncertain input space. While this approach helps address conceptual and parametric uncertainties, the ensemble datasets produced by this technique present a special challenge to visualization researchers as the ensemble dataset records a distribution of possible values for each location in the domain. Contemporary visualization approaches that rely solely on summary statistics (e.g., mean and variance) cannot convey the detailed information encoded in ensemble distributions that are paramount to ensemble analysis; summary statistics provide no informationmore » about modality classification and modality persistence. To address this problem, we propose a novel technique that classifies high-variance locations based on the modality of the distribution of ensemble predictions. Additionally, we develop a set of confidence metrics to inform the end-user of the quality of fit between the distribution at a given location and its assigned class. We apply a similar method to time-varying ensembles to illustrate the relationship between peak variance and bimodal or multimodal behavior. These classification schemes enable a deeper understanding of the behavior of the ensemble members by distinguishing between distributions that can be described by a single tendency and distributions which reflect divergent trends in the ensemble.« less

Method and apparatus for quantum information processing using entangled neutral-atom qubits

DOEpatents

Jau, Yuan Yu; Biedermann, Grant; Deutsch, Ivan

2018-04-03

A method for preparing an entangled quantum state of an atomic ensemble is provided. The method includes loading each atom of the atomic ensemble into a respective optical trap; placing each atom of the atomic ensemble into a same first atomic quantum state by impingement of pump radiation; approaching the atoms of the atomic ensemble to within a dipole-dipole interaction length of each other; Rydberg-dressing the atomic ensemble; during the Rydberg-dressing operation, exciting the atomic ensemble with a Raman pulse tuned to stimulate a ground-state hyperfine transition from the first atomic quantum state to a second atomic quantum state; and separating the atoms of the atomic ensemble by more than a dipole-dipole interaction length.

Impacts of snow cover fraction data assimilation on modeled energy and moisture budgets

NASA Astrophysics Data System (ADS)

Arsenault, Kristi R.; Houser, Paul R.; De Lannoy, Gabriëlle J. M.; Dirmeyer, Paul A.

2013-07-01

Two data assimilation (DA) methods, a simple rule-based direct insertion (DI) approach and a one-dimensional ensemble Kalman filter (EnKF) method, are evaluated by assimilating snow cover fraction observations into the Community Land surface Model. The ensemble perturbation needed for the EnKF resulted in negative snowpack biases. Therefore, a correction is made to the ensemble bias using an approach that constrains the ensemble forecasts with a single unperturbed deterministic LSM run. This is shown to improve the final snow state analyses. The EnKF method produces slightly better results in higher elevation locations, whereas results indicate that the DI method has a performance advantage in lower elevation regions. In addition, the two DA methods are evaluated in terms of their overall impacts on the other land surface state variables (e.g., soil moisture) and fluxes (e.g., latent heat flux). The EnKF method is shown to have less impact overall than the DI method and causes less distortion of the hydrological budget. However, the land surface model adjusts more slowly to the smaller EnKF increments, which leads to smaller but slightly more persistent moisture budget errors than found with the DI updates. The DI method can remove almost instantly much of the modeled snowpack, but this also allows the model system to quickly revert to hydrological balance for nonsnowpack conditions.

Evaluating statistical consistency in the ocean model component of the Community Earth System Model (pyCECT v2.0)

NASA Astrophysics Data System (ADS)

Baker, Allison H.; Hu, Yong; Hammerling, Dorit M.; Tseng, Yu-heng; Xu, Haiying; Huang, Xiaomeng; Bryan, Frank O.; Yang, Guangwen

2016-07-01

The Parallel Ocean Program (POP), the ocean model component of the Community Earth System Model (CESM), is widely used in climate research. Most current work in CESM-POP focuses on improving the model's efficiency or accuracy, such as improving numerical methods, advancing parameterization, porting to new architectures, or increasing parallelism. Since ocean dynamics are chaotic in nature, achieving bit-for-bit (BFB) identical results in ocean solutions cannot be guaranteed for even tiny code modifications, and determining whether modifications are admissible (i.e., statistically consistent with the original results) is non-trivial. In recent work, an ensemble-based statistical approach was shown to work well for software verification (i.e., quality assurance) on atmospheric model data. The general idea of the ensemble-based statistical consistency testing is to use a qualitative measurement of the variability of the ensemble of simulations as a metric with which to compare future simulations and make a determination of statistical distinguishability. The capability to determine consistency without BFB results boosts model confidence and provides the flexibility needed, for example, for more aggressive code optimizations and the use of heterogeneous execution environments. Since ocean and atmosphere models have differing characteristics in term of dynamics, spatial variability, and timescales, we present a new statistical method to evaluate ocean model simulation data that requires the evaluation of ensemble means and deviations in a spatial manner. In particular, the statistical distribution from an ensemble of CESM-POP simulations is used to determine the standard score of any new model solution at each grid point. Then the percentage of points that have scores greater than a specified threshold indicates whether the new model simulation is statistically distinguishable from the ensemble simulations. Both ensemble size and composition are important. Our experiments indicate that the new POP ensemble consistency test (POP-ECT) tool is capable of distinguishing cases that should be statistically consistent with the ensemble and those that should not, as well as providing a simple, subjective and systematic way to detect errors in CESM-POP due to the hardware or software stack, positively contributing to quality assurance for the CESM-POP code.

A framework of multitemplate ensemble for fingerprint verification

NASA Astrophysics Data System (ADS)

Yin, Yilong; Ning, Yanbin; Ren, Chunxiao; Liu, Li

2012-12-01

How to improve performance of an automatic fingerprint verification system (AFVS) is always a big challenge in biometric verification field. Recently, it becomes popular to improve the performance of AFVS using ensemble learning approach to fuse related information of fingerprints. In this article, we propose a novel framework of fingerprint verification which is based on the multitemplate ensemble method. This framework is consisted of three stages. In the first stage, enrollment stage, we adopt an effective template selection method to select those fingerprints which best represent a finger, and then, a polyhedron is created by the matching results of multiple template fingerprints and a virtual centroid of the polyhedron is given. In the second stage, verification stage, we measure the distance between the centroid of the polyhedron and a query image. In the final stage, a fusion rule is used to choose a proper distance from a distance set. The experimental results on the FVC2004 database prove the improvement on the effectiveness of the new framework in fingerprint verification. With a minutiae-based matching method, the average EER of four databases in FVC2004 drops from 10.85 to 0.88, and with a ridge-based matching method, the average EER of these four databases also decreases from 14.58 to 2.51.

AUC-Maximizing Ensembles through Metalearning.

PubMed

LeDell, Erin; van der Laan, Mark J; Petersen, Maya

2016-05-01

Area Under the ROC Curve (AUC) is often used to measure the performance of an estimator in binary classification problems. An AUC-maximizing classifier can have significant advantages in cases where ranking correctness is valued or if the outcome is rare. In a Super Learner ensemble, maximization of the AUC can be achieved by the use of an AUC-maximining metalearning algorithm. We discuss an implementation of an AUC-maximization technique that is formulated as a nonlinear optimization problem. We also evaluate the effectiveness of a large number of different nonlinear optimization algorithms to maximize the cross-validated AUC of the ensemble fit. The results provide evidence that AUC-maximizing metalearners can, and often do, out-perform non-AUC-maximizing metalearning methods, with respect to ensemble AUC. The results also demonstrate that as the level of imbalance in the training data increases, the Super Learner ensemble outperforms the top base algorithm by a larger degree.

AUC-Maximizing Ensembles through Metalearning

PubMed Central

LeDell, Erin; van der Laan, Mark J.; Peterson, Maya

2016-01-01

Area Under the ROC Curve (AUC) is often used to measure the performance of an estimator in binary classification problems. An AUC-maximizing classifier can have significant advantages in cases where ranking correctness is valued or if the outcome is rare. In a Super Learner ensemble, maximization of the AUC can be achieved by the use of an AUC-maximining metalearning algorithm. We discuss an implementation of an AUC-maximization technique that is formulated as a nonlinear optimization problem. We also evaluate the effectiveness of a large number of different nonlinear optimization algorithms to maximize the cross-validated AUC of the ensemble fit. The results provide evidence that AUC-maximizing metalearners can, and often do, out-perform non-AUC-maximizing metalearning methods, with respect to ensemble AUC. The results also demonstrate that as the level of imbalance in the training data increases, the Super Learner ensemble outperforms the top base algorithm by a larger degree. PMID:27227721

Ensemble Pruning for Glaucoma Detection in an Unbalanced Data Set.

PubMed

Adler, Werner; Gefeller, Olaf; Gul, Asma; Horn, Folkert K; Khan, Zardad; Lausen, Berthold

2016-12-07

Random forests are successful classifier ensemble methods consisting of typically 100 to 1000 classification trees. Ensemble pruning techniques reduce the computational cost, especially the memory demand, of random forests by reducing the number of trees without relevant loss of performance or even with increased performance of the sub-ensemble. The application to the problem of an early detection of glaucoma, a severe eye disease with low prevalence, based on topographical measurements of the eye background faces specific challenges. We examine the performance of ensemble pruning strategies for glaucoma detection in an unbalanced data situation. The data set consists of 102 topographical features of the eye background of 254 healthy controls and 55 glaucoma patients. We compare the area under the receiver operating characteristic curve (AUC), and the Brier score on the total data set, in the majority class, and in the minority class of pruned random forest ensembles obtained with strategies based on the prediction accuracy of greedily grown sub-ensembles, the uncertainty weighted accuracy, and the similarity between single trees. To validate the findings and to examine the influence of the prevalence of glaucoma in the data set, we additionally perform a simulation study with lower prevalences of glaucoma. In glaucoma classification all three pruning strategies lead to improved AUC and smaller Brier scores on the total data set with sub-ensembles as small as 30 to 80 trees compared to the classification results obtained with the full ensemble consisting of 1000 trees. In the simulation study, we were able to show that the prevalence of glaucoma is a critical factor and lower prevalence decreases the performance of our pruning strategies. The memory demand for glaucoma classification in an unbalanced data situation based on random forests could effectively be reduced by the application of pruning strategies without loss of performance in a population with increased risk of glaucoma.

Predicting miRNA targets for head and neck squamous cell carcinoma using an ensemble method.

PubMed

Gao, Hong; Jin, Hui; Li, Guijun

2018-01-01

This study aimed to uncover potential microRNA (miRNA) targets in head and neck squamous cell carcinoma (HNSCC) using an ensemble method which combined 3 different methods: Pearson's correlation coefficient (PCC), Lasso and a causal inference method (i.e., intervention calculus when the directed acyclic graph (DAG) is absent [IDA]), based on Borda count election. The Borda count election method was used to integrate the top 100 predicted targets of each miRNA generated by individual methods. Afterwards, to validate the performance ability of our method, we checked the TarBase v6.0, miRecords v2013, miRWalk v2.0 and miRTarBase v4.5 databases to validate predictions for miRNAs. Pathway enrichment analysis of target genes in the top 1,000 miRNA-messenger RNA (mRNA) interactions was conducted to focus on significant KEGG pathways. Finally, we extracted target genes based on occurrence frequency ≥3. Based on an absolute value of PCC >0.7, we found 33 miRNAs and 288 mRNAs for further analysis. We extracted 10 target genes with predicted frequencies not less than 3. The target gene MYO5C possessed the highest frequency, which was predicted by 7 different miRNAs. Significantly, a total of 8 pathways were identified; the pathways of cytokine-cytokine receptor interaction and chemokine signaling pathway were the most significant. We successfully predicted target genes and pathways for HNSCC relying on miRNA expression data, mRNA expression profile, an ensemble method and pathway information. Our results may offer new information for the diagnosis and estimation of the prognosis of HNSCC.

An adaptive incremental approach to constructing ensemble classifiers: application in an information-theoretic computer-aided decision system for detection of masses in mammograms.

PubMed

Mazurowski, Maciej A; Zurada, Jacek M; Tourassi, Georgia D

2009-07-01

Ensemble classifiers have been shown efficient in multiple applications. In this article, the authors explore the effectiveness of ensemble classifiers in a case-based computer-aided diagnosis system for detection of masses in mammograms. They evaluate two general ways of constructing subclassifiers by resampling of the available development dataset: Random division and random selection. Furthermore, they discuss the problem of selecting the ensemble size and propose two adaptive incremental techniques that automatically select the size for the problem at hand. All the techniques are evaluated with respect to a previously proposed information-theoretic CAD system (IT-CAD). The experimental results show that the examined ensemble techniques provide a statistically significant improvement (AUC = 0.905 +/- 0.024) in performance as compared to the original IT-CAD system (AUC = 0.865 +/- 0.029). Some of the techniques allow for a notable reduction in the total number of examples stored in the case base (to 1.3% of the original size), which, in turn, results in lower storage requirements and a shorter response time of the system. Among the methods examined in this article, the two proposed adaptive techniques are by far the most effective for this purpose. Furthermore, the authors provide some discussion and guidance for choosing the ensemble parameters.

Multiscale Macromolecular Simulation: Role of Evolving Ensembles

PubMed Central

Singharoy, A.; Joshi, H.; Ortoleva, P.J.

2013-01-01

Multiscale analysis provides an algorithm for the efficient simulation of macromolecular assemblies. This algorithm involves the coevolution of a quasiequilibrium probability density of atomic configurations and the Langevin dynamics of spatial coarse-grained variables denoted order parameters (OPs) characterizing nanoscale system features. In practice, implementation of the probability density involves the generation of constant OP ensembles of atomic configurations. Such ensembles are used to construct thermal forces and diffusion factors that mediate the stochastic OP dynamics. Generation of all-atom ensembles at every Langevin timestep is computationally expensive. Here, multiscale computation for macromolecular systems is made more efficient by a method that self-consistently folds in ensembles of all-atom configurations constructed in an earlier step, history, of the Langevin evolution. This procedure accounts for the temporal evolution of these ensembles, accurately providing thermal forces and diffusions. It is shown that efficiency and accuracy of the OP-based simulations is increased via the integration of this historical information. Accuracy improves with the square root of the number of historical timesteps included in the calculation. As a result, CPU usage can be decreased by a factor of 3-8 without loss of accuracy. The algorithm is implemented into our existing force-field based multiscale simulation platform and demonstrated via the structural dynamics of viral capsomers. PMID:22978601

[Computer aided diagnosis model for lung tumor based on ensemble convolutional neural network].

PubMed

Wang, Yuanyuan; Zhou, Tao; Lu, Huiling; Wu, Cuiying; Yang, Pengfei

2017-08-01

The convolutional neural network (CNN) could be used on computer-aided diagnosis of lung tumor with positron emission tomography (PET)/computed tomography (CT), which can provide accurate quantitative analysis to compensate for visual inertia and defects in gray-scale sensitivity, and help doctors diagnose accurately. Firstly, parameter migration method is used to build three CNNs (CT-CNN, PET-CNN, and PET/CT-CNN) for lung tumor recognition in CT, PET, and PET/CT image, respectively. Then, we aimed at CT-CNN to obtain the appropriate model parameters for CNN training through analysis the influence of model parameters such as epochs, batchsize and image scale on recognition rate and training time. Finally, three single CNNs are used to construct ensemble CNN, and then lung tumor PET/CT recognition was completed through relative majority vote method and the performance between ensemble CNN and single CNN was compared. The experiment results show that the ensemble CNN is better than single CNN on computer-aided diagnosis of lung tumor.

Soft sensor modeling based on variable partition ensemble method for nonlinear batch processes

NASA Astrophysics Data System (ADS)

Wang, Li; Chen, Xiangguang; Yang, Kai; Jin, Huaiping

2017-01-01

Batch processes are always characterized by nonlinear and system uncertain properties, therefore, the conventional single model may be ill-suited. A local learning strategy soft sensor based on variable partition ensemble method is developed for the quality prediction of nonlinear and non-Gaussian batch processes. A set of input variable sets are obtained by bootstrapping and PMI criterion. Then, multiple local GPR models are developed based on each local input variable set. When a new test data is coming, the posterior probability of each best performance local model is estimated based on Bayesian inference and used to combine these local GPR models to get the final prediction result. The proposed soft sensor is demonstrated by applying to an industrial fed-batch chlortetracycline fermentation process.

Protein binding hot spots prediction from sequence only by a new ensemble learning method.

PubMed

Hu, Shan-Shan; Chen, Peng; Wang, Bing; Li, Jinyan

2017-10-01

Hot spots are interfacial core areas of binding proteins, which have been applied as targets in drug design. Experimental methods are costly in both time and expense to locate hot spot areas. Recently, in-silicon computational methods have been widely used for hot spot prediction through sequence or structure characterization. As the structural information of proteins is not always solved, and thus hot spot identification from amino acid sequences only is more useful for real-life applications. This work proposes a new sequence-based model that combines physicochemical features with the relative accessible surface area of amino acid sequences for hot spot prediction. The model consists of 83 classifiers involving the IBk (Instance-based k means) algorithm, where instances are encoded by important properties extracted from a total of 544 properties in the AAindex1 (Amino Acid Index) database. Then top-performance classifiers are selected to form an ensemble by a majority voting technique. The ensemble classifier outperforms the state-of-the-art computational methods, yielding an F1 score of 0.80 on the benchmark binding interface database (BID) test set. http://www2.ahu.edu.cn/pchen/web/HotspotEC.htm .

Ensemble learning for spatial interpolation of soil potassium content based on environmental information.

PubMed

Liu, Wei; Du, Peijun; Wang, Dongchen

2015-01-01

One important method to obtain the continuous surfaces of soil properties from point samples is spatial interpolation. In this paper, we propose a method that combines ensemble learning with ancillary environmental information for improved interpolation of soil properties (hereafter, EL-SP). First, we calculated the trend value for soil potassium contents at the Qinghai Lake region in China based on measured values. Then, based on soil types, geology types, land use types, and slope data, the remaining residual was simulated with the ensemble learning model. Next, the EL-SP method was applied to interpolate soil potassium contents at the study site. To evaluate the utility of the EL-SP method, we compared its performance with other interpolation methods including universal kriging, inverse distance weighting, ordinary kriging, and ordinary kriging combined geographic information. Results show that EL-SP had a lower mean absolute error and root mean square error than the data produced by the other models tested in this paper. Notably, the EL-SP maps can describe more locally detailed information and more accurate spatial patterns for soil potassium content than the other methods because of the combined use of different types of environmental information; these maps are capable of showing abrupt boundary information for soil potassium content. Furthermore, the EL-SP method not only reduces prediction errors, but it also compliments other environmental information, which makes the spatial interpolation of soil potassium content more reasonable and useful.

Exploiting ensemble learning for automatic cataract detection and grading.

PubMed

Yang, Ji-Jiang; Li, Jianqiang; Shen, Ruifang; Zeng, Yang; He, Jian; Bi, Jing; Li, Yong; Zhang, Qinyan; Peng, Lihui; Wang, Qing

2016-02-01

Cataract is defined as a lenticular opacity presenting usually with poor visual acuity. It is one of the most common causes of visual impairment worldwide. Early diagnosis demands the expertise of trained healthcare professionals, which may present a barrier to early intervention due to underlying costs. To date, studies reported in the literature utilize a single learning model for retinal image classification in grading cataract severity. We present an ensemble learning based approach as a means to improving diagnostic accuracy. Three independent feature sets, i.e., wavelet-, sketch-, and texture-based features, are extracted from each fundus image. For each feature set, two base learning models, i.e., Support Vector Machine and Back Propagation Neural Network, are built. Then, the ensemble methods, majority voting and stacking, are investigated to combine the multiple base learning models for final fundus image classification. Empirical experiments are conducted for cataract detection (two-class task, i.e., cataract or non-cataractous) and cataract grading (four-class task, i.e., non-cataractous, mild, moderate or severe) tasks. The best performance of the ensemble classifier is 93.2% and 84.5% in terms of the correct classification rates for cataract detection and grading tasks, respectively. The results demonstrate that the ensemble classifier outperforms the single learning model significantly, which also illustrates the effectiveness of the proposed approach. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Multimodel Ensemble Methods for Prediction of Wake-Vortex Transport and Decay Originating NASA

NASA Technical Reports Server (NTRS)

Korner, Stephan; Ahmad, Nashat N.; Holzapfel, Frank; VanValkenburg, Randal L.

2017-01-01

Several multimodel ensemble methods are selected and further developed to improve the deterministic and probabilistic prediction skills of individual wake-vortex transport and decay models. The different multimodel ensemble methods are introduced, and their suitability for wake applications is demonstrated. The selected methods include direct ensemble averaging, Bayesian model averaging, and Monte Carlo simulation. The different methodologies are evaluated employing data from wake-vortex field measurement campaigns conducted in the United States and Germany.

A Proposed Methodology to Classify Frontier Capital Markets

DTIC Science & Technology

2011-07-31

but because it is the surest route to our common good.” -Inaugural Speech by President Barack Obama, Jan 2009 This project involves basic...machine learning. The algorithm consists of a unique binary classifier mechanism that combines three methods: k-Nearest Neighbors ( kNN ), ensemble...Through kNN Ensemble Classification Techniques E. Capital Market Classification Based on Capital Flows and Trading Architecture F. Horizontal

Polynomial Chaos Based Acoustic Uncertainty Predictions from Ocean Forecast Ensembles

NASA Astrophysics Data System (ADS)

Dennis, S.

2016-02-01

Most significant ocean acoustic propagation occurs at tens of kilometers, at scales small compared basin and to most fine scale ocean modeling. To address the increased emphasis on uncertainty quantification, for example transmission loss (TL) probability density functions (PDF) within some radius, a polynomial chaos (PC) based method is utilized. In order to capture uncertainty in ocean modeling, Navy Coastal Ocean Model (NCOM) now includes ensembles distributed to reflect the ocean analysis statistics. Since the ensembles are included in the data assimilation for the new forecast ensembles, the acoustic modeling uses the ensemble predictions in a similar fashion for creating sound speed distribution over an acoustically relevant domain. Within an acoustic domain, singular value decomposition over the combined time-space structure of the sound speeds can be used to create Karhunen-Loève expansions of sound speed, subject to multivariate normality testing. These sound speed expansions serve as a basis for Hermite polynomial chaos expansions of derived quantities, in particular TL. The PC expansion coefficients result from so-called non-intrusive methods, involving evaluation of TL at multi-dimensional Gauss-Hermite quadrature collocation points. Traditional TL calculation from standard acoustic propagation modeling could be prohibitively time consuming at all multi-dimensional collocation points. This method employs Smolyak order and gridding methods to allow adaptive sub-sampling of the collocation points to determine only the most significant PC expansion coefficients to within a preset tolerance. Practically, the Smolyak order and grid sizes grow only polynomially in the number of Karhunen-Loève terms, alleviating the curse of dimensionality. The resulting TL PC coefficients allow the determination of TL PDF normality and its mean and standard deviation. In the non-normal case, PC Monte Carlo methods are used to rapidly establish the PDF. This work was sponsored by the Office of Naval Research

Transient Calibration of a Variably-Saturated Groundwater Flow Model By Iterative Ensemble Smoothering: Synthetic Case and Application to the Flow Induced During Shaft Excavation and Operation of the Bure Underground Research Laboratory

NASA Astrophysics Data System (ADS)

Lam, D. T.; Kerrou, J.; Benabderrahmane, H.; Perrochet, P.

2017-12-01

The calibration of groundwater flow models in transient state can be motivated by the expected improved characterization of the aquifer hydraulic properties, especially when supported by a rich transient dataset. In the prospect of setting up a calibration strategy for a variably-saturated transient groundwater flow model of the area around the ANDRA's Bure Underground Research Laboratory, we wish to take advantage of the long hydraulic head and flowrate time series collected near and at the access shafts in order to help inform the model hydraulic parameters. A promising inverse approach for such high-dimensional nonlinear model, and which applicability has been illustrated more extensively in other scientific fields, could be an iterative ensemble smoother algorithm initially developed for a reservoir engineering problem. Furthermore, the ensemble-based stochastic framework will allow to address to some extent the uncertainty of the calibration for a subsequent analysis of a flow process dependent prediction. By assimilating the available data in one single step, this method iteratively updates each member of an initial ensemble of stochastic realizations of parameters until the minimization of an objective function. However, as it is well known for ensemble-based Kalman methods, this correction computed from approximations of covariance matrices is most efficient when the ensemble realizations are multi-Gaussian. As shown by the comparison of the updated ensemble mean obtained for our simplified synthetic model of 2D vertical flow by using either multi-Gaussian or multipoint simulations of parameters, the ensemble smoother fails to preserve the initial connectivity of the facies and the parameter bimodal distribution. Given the geological structures depicted by the multi-layered geological model built for the real case, our goal is to find how to still best leverage the performance of the ensemble smoother while using an initial ensemble of conditional multi-Gaussian simulations or multipoint simulations as conceptually consistent as possible. Performance of the algorithm including additional steps to help mitigate the effects of non-Gaussian patterns, such as Gaussian anamorphosis, or resampling of facies from the training image using updated local probability constraints will be assessed.

SQUEEZE-E: The Optimal Solution for Molecular Simulations with Periodic Boundary Conditions.

PubMed

Wassenaar, Tsjerk A; de Vries, Sjoerd; Bonvin, Alexandre M J J; Bekker, Henk

2012-10-09

In molecular simulations of macromolecules, it is desirable to limit the amount of solvent in the system to avoid spending computational resources on uninteresting solvent-solvent interactions. As a consequence, periodic boundary conditions are commonly used, with a simulation box chosen as small as possible, for a given minimal distance between images. Here, we describe how such a simulation cell can be set up for ensembles, taking into account a priori available or estimable information regarding conformational flexibility. Doing so ensures that any conformation present in the input ensemble will satisfy the distance criterion during the simulation. This helps avoid periodicity artifacts due to conformational changes. The method introduces three new approaches in computational geometry: (1) The first is the derivation of an optimal packing of ensembles, for which the mathematical framework is described. (2) A new method for approximating the α-hull and the contact body for single bodies and ensembles is presented, which is orders of magnitude faster than existing routines, allowing the calculation of packings of large ensembles and/or large bodies. 3. A routine is described for searching a combination of three vectors on a discretized contact body forming a reduced base for a lattice with minimal cell volume. The new algorithms reduce the time required to calculate packings of single bodies from minutes or hours to seconds. The use and efficacy of the method is demonstrated for ensembles obtained from NMR, MD simulations, and elastic network modeling. An implementation of the method has been made available online at http://haddock.chem.uu.nl/services/SQUEEZE/ and has been made available as an option for running simulations through the weNMR GRID MD server at http://haddock.science.uu.nl/enmr/services/GROMACS/main.php .

Ensemble positive unlabeled learning for disease gene identification.

PubMed

Yang, Peng; Li, Xiaoli; Chua, Hon-Nian; Kwoh, Chee-Keong; Ng, See-Kiong

2014-01-01

An increasing number of genes have been experimentally confirmed in recent years as causative genes to various human diseases. The newly available knowledge can be exploited by machine learning methods to discover additional unknown genes that are likely to be associated with diseases. In particular, positive unlabeled learning (PU learning) methods, which require only a positive training set P (confirmed disease genes) and an unlabeled set U (the unknown candidate genes) instead of a negative training set N, have been shown to be effective in uncovering new disease genes in the current scenario. Using only a single source of data for prediction can be susceptible to bias due to incompleteness and noise in the genomic data and a single machine learning predictor prone to bias caused by inherent limitations of individual methods. In this paper, we propose an effective PU learning framework that integrates multiple biological data sources and an ensemble of powerful machine learning classifiers for disease gene identification. Our proposed method integrates data from multiple biological sources for training PU learning classifiers. A novel ensemble-based PU learning method EPU is then used to integrate multiple PU learning classifiers to achieve accurate and robust disease gene predictions. Our evaluation experiments across six disease groups showed that EPU achieved significantly better results compared with various state-of-the-art prediction methods as well as ensemble learning classifiers. Through integrating multiple biological data sources for training and the outputs of an ensemble of PU learning classifiers for prediction, we are able to minimize the potential bias and errors in individual data sources and machine learning algorithms to achieve more accurate and robust disease gene predictions. In the future, our EPU method provides an effective framework to integrate the additional biological and computational resources for better disease gene predictions.

A new adaptive estimation method of spacecraft thermal mathematical model with an ensemble Kalman filter

NASA Astrophysics Data System (ADS)

Akita, T.; Takaki, R.; Shima, E.

2012-04-01

An adaptive estimation method of spacecraft thermal mathematical model is presented. The method is based on the ensemble Kalman filter, which can effectively handle the nonlinearities contained in the thermal model. The state space equations of the thermal mathematical model is derived, where both temperature and uncertain thermal characteristic parameters are considered as the state variables. In the method, the thermal characteristic parameters are automatically estimated as the outputs of the filtered state variables, whereas, in the usual thermal model correlation, they are manually identified by experienced engineers using trial-and-error approach. A numerical experiment of a simple small satellite is provided to verify the effectiveness of the presented method.

EFS: an ensemble feature selection tool implemented as R-package and web-application.

PubMed

Neumann, Ursula; Genze, Nikita; Heider, Dominik

2017-01-01

Feature selection methods aim at identifying a subset of features that improve the prediction performance of subsequent classification models and thereby also simplify their interpretability. Preceding studies demonstrated that single feature selection methods can have specific biases, whereas an ensemble feature selection has the advantage to alleviate and compensate for these biases. The software EFS (Ensemble Feature Selection) makes use of multiple feature selection methods and combines their normalized outputs to a quantitative ensemble importance. Currently, eight different feature selection methods have been integrated in EFS, which can be used separately or combined in an ensemble. EFS identifies relevant features while compensating specific biases of single methods due to an ensemble approach. Thereby, EFS can improve the prediction accuracy and interpretability in subsequent binary classification models. EFS can be downloaded as an R-package from CRAN or used via a web application at http://EFS.heiderlab.de.

A Machine Learning Ensemble Classifier for Early Prediction of Diabetic Retinopathy.

PubMed

S K, Somasundaram; P, Alli

2017-11-09

The main complication of diabetes is Diabetic retinopathy (DR), retinal vascular disease and it leads to the blindness. Regular screening for early DR disease detection is considered as an intensive labor and resource oriented task. Therefore, automatic detection of DR diseases is performed only by using the computational technique is the great solution. An automatic method is more reliable to determine the presence of an abnormality in Fundus images (FI) but, the classification process is poorly performed. Recently, few research works have been designed for analyzing texture discrimination capacity in FI to distinguish the healthy images. However, the feature extraction (FE) process was not performed well, due to the high dimensionality. Therefore, to identify retinal features for DR disease diagnosis and early detection using Machine Learning and Ensemble Classification method, called, Machine Learning Bagging Ensemble Classifier (ML-BEC) is designed. The ML-BEC method comprises of two stages. The first stage in ML-BEC method comprises extraction of the candidate objects from Retinal Images (RI). The candidate objects or the features for DR disease diagnosis include blood vessels, optic nerve, neural tissue, neuroretinal rim, optic disc size, thickness and variance. These features are initially extracted by applying Machine Learning technique called, t-distributed Stochastic Neighbor Embedding (t-SNE). Besides, t-SNE generates a probability distribution across high-dimensional images where the images are separated into similar and dissimilar pairs. Then, t-SNE describes a similar probability distribution across the points in the low-dimensional map. This lessens the Kullback-Leibler divergence among two distributions regarding the locations of the points on the map. The second stage comprises of application of ensemble classifiers to the extracted features for providing accurate analysis of digital FI using machine learning. In this stage, an automatic detection of DR screening system using Bagging Ensemble Classifier (BEC) is investigated. With the help of voting the process in ML-BEC, bagging minimizes the error due to variance of the base classifier. With the publicly available retinal image databases, our classifier is trained with 25% of RI. Results show that the ensemble classifier can achieve better classification accuracy (CA) than single classification models. Empirical experiments suggest that the machine learning-based ensemble classifier is efficient for further reducing DR classification time (CT).

Multivariate localization methods for ensemble Kalman filtering

NASA Astrophysics Data System (ADS)

Roh, S.; Jun, M.; Szunyogh, I.; Genton, M. G.

2015-05-01

In ensemble Kalman filtering (EnKF), the small number of ensemble members that is feasible to use in a practical data assimilation application leads to sampling variability of the estimates of the background error covariances. The standard approach to reducing the effects of this sampling variability, which has also been found to be highly efficient in improving the performance of EnKF, is the localization of the estimates of the covariances. One family of localization techniques is based on taking the Schur (entry-wise) product of the ensemble-based sample covariance matrix and a correlation matrix whose entries are obtained by the discretization of a distance-dependent correlation function. While the proper definition of the localization function for a single state variable has been extensively investigated, a rigorous definition of the localization function for multiple state variables has been seldom considered. This paper introduces two strategies for the construction of localization functions for multiple state variables. The proposed localization functions are tested by assimilating simulated observations experiments into the bivariate Lorenz 95 model with their help.

Ensemble based on static classifier selection for automated diagnosis of Mild Cognitive Impairment.

PubMed

Nanni, Loris; Lumini, Alessandra; Zaffonato, Nicolò

2018-05-15

Alzheimer's disease (AD) is the most common cause of neurodegenerative dementia in the elderly population. Scientific research is very active in the challenge of designing automated approaches to achieve an early and certain diagnosis. Recently an international competition among AD predictors has been organized: "A Machine learning neuroimaging challenge for automated diagnosis of Mild Cognitive Impairment" (MLNeCh). This competition is based on pre-processed sets of T1-weighted Magnetic Resonance Images (MRI) to be classified in four categories: stable AD, individuals with MCI who converted to AD, individuals with MCI who did not convert to AD and healthy controls. In this work, we propose a method to perform early diagnosis of AD, which is evaluated on MLNeCh dataset. Since the automatic classification of AD is based on the use of feature vectors of high dimensionality, different techniques of feature selection/reduction are compared in order to avoid the curse-of-dimensionality problem, then the classification method is obtained as the combination of Support Vector Machines trained using different clusters of data extracted from the whole training set. The multi-classifier approach proposed in this work outperforms all the stand-alone method tested in our experiments. The final ensemble is based on a set of classifiers, each trained on a different cluster of the training data. The proposed ensemble has the great advantage of performing well using a very reduced version of the data (the reduction factor is more than 90%). The MATLAB code for the ensemble of classifiers will be publicly available 1 to other researchers for future comparisons. Copyright © 2017 Elsevier B.V. All rights reserved.

Path planning in uncertain flow fields using ensemble method

NASA Astrophysics Data System (ADS)

Wang, Tong; Le Maître, Olivier P.; Hoteit, Ibrahim; Knio, Omar M.

2016-10-01

An ensemble-based approach is developed to conduct optimal path planning in unsteady ocean currents under uncertainty. We focus our attention on two-dimensional steady and unsteady uncertain flows, and adopt a sampling methodology that is well suited to operational forecasts, where an ensemble of deterministic predictions is used to model and quantify uncertainty. In an operational setting, much about dynamics, topography, and forcing of the ocean environment is uncertain. To address this uncertainty, the flow field is parametrized using a finite number of independent canonical random variables with known densities, and the ensemble is generated by sampling these variables. For each of the resulting realizations of the uncertain current field, we predict the path that minimizes the travel time by solving a boundary value problem (BVP), based on the Pontryagin maximum principle. A family of backward-in-time trajectories starting at the end position is used to generate suitable initial values for the BVP solver. This allows us to examine and analyze the performance of the sampling strategy and to develop insight into extensions dealing with general circulation ocean models. In particular, the ensemble method enables us to perform a statistical analysis of travel times and consequently develop a path planning approach that accounts for these statistics. The proposed methodology is tested for a number of scenarios. We first validate our algorithms by reproducing simple canonical solutions, and then demonstrate our approach in more complex flow fields, including idealized, steady and unsteady double-gyre flows.

Quasi-static ensemble variational data assimilation: a theoretical and numerical study with the iterative ensemble Kalman smoother

NASA Astrophysics Data System (ADS)

Fillion, Anthony; Bocquet, Marc; Gratton, Serge

2018-04-01

The analysis in nonlinear variational data assimilation is the solution of a non-quadratic minimization. Thus, the analysis efficiency relies on its ability to locate a global minimum of the cost function. If this minimization uses a Gauss-Newton (GN) method, it is critical for the starting point to be in the attraction basin of a global minimum. Otherwise the method may converge to a local extremum, which degrades the analysis. With chaotic models, the number of local extrema often increases with the temporal extent of the data assimilation window, making the former condition harder to satisfy. This is unfortunate because the assimilation performance also increases with this temporal extent. However, a quasi-static (QS) minimization may overcome these local extrema. It accomplishes this by gradually injecting the observations in the cost function. This method was introduced by Pires et al. (1996) in a 4D-Var context. We generalize this approach to four-dimensional strong-constraint nonlinear ensemble variational (EnVar) methods, which are based on both a nonlinear variational analysis and the propagation of dynamical error statistics via an ensemble. This forces one to consider the cost function minimizations in the broader context of cycled data assimilation algorithms. We adapt this QS approach to the iterative ensemble Kalman smoother (IEnKS), an exemplar of nonlinear deterministic four-dimensional EnVar methods. Using low-order models, we quantify the positive impact of the QS approach on the IEnKS, especially for long data assimilation windows. We also examine the computational cost of QS implementations and suggest cheaper algorithms.

A Solar Time-Based Analog Ensemble Method for Regional Solar Power Forecasting

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

Hodge, Brian S; Zhang, Xinmin; Li, Yuan

This paper presents a new analog ensemble method for day-ahead regional photovoltaic (PV) power forecasting with hourly resolution. By utilizing open weather forecast and power measurement data, this prediction method is processed within a set of historical data with similar meteorological data (temperature and irradiance), and astronomical date (solar time and earth declination angle). Further, clustering and blending strategies are applied to improve its accuracy in regional PV forecasting. The robustness of the proposed method is demonstrated with three different numerical weather prediction models, the North American Mesoscale Forecast System, the Global Forecast System, and the Short-Range Ensemble Forecast, formore » both region level and single site level PV forecasts. Using real measured data, the new forecasting approach is applied to the load zone in Southeastern Massachusetts as a case study. The normalized root mean square error (NRMSE) has been reduced by 13.80%-61.21% when compared with three tested baselines.« less

Enhanced Assimilation of InSAR Displacement and Well Data for Groundwater Monitoring

NASA Astrophysics Data System (ADS)

Abdullin, A.; Jonsson, S.

2016-12-01

Ground deformation related to aquifer exploitation can cause damage to buildings and infrastructure leading to major economic losses and sometimes even loss of human lives. Understanding reservoir behavior helps in assessing possible future ground movement and water depletion hazard of a region under study. We have developed an InSAR-based data assimilation framework for groundwater reservoirs that efficiently incorporates InSAR data for improved reservoir management and forecasts. InSAR displacement data are integrated with the groundwater modeling software MODFLOW using ensemble-based assimilation approaches. We have examined several Ensemble Methods for updating model parameters such as hydraulic conductivity and model variables like pressure head while simultaneously providing an estimate of the uncertainty. A realistic three-dimensional aquifer model was built to demonstrate the capability of the Ensemble Methods incorporating InSAR-derived displacement measurements. We find from these numerical tests that including both ground deformation and well water level data as observations improves the RMSE of the hydraulic conductivity estimate by up to 20% comparing to using only one type of observations. The RMSE estimation of this property after the final time step is similar for Ensemble Kalman Filter (EnKF), Ensemble Smoother (ES) and ES with multiple data assimilation (ES-MDA) methods. The results suggest that the high spatial and temporal resolution subsidence observations from InSAR are very helpful for accurately quantifying hydraulic parameters. We have tested the framework on several different examples and have found good performance in improving aquifer properties estimation, which should prove useful for groundwater management. Our ongoing work focuses on assimilating real InSAR-derived time series and hydraulic head data for calibrating and predicting aquifer properties of basin-wide groundwater systems.

Ensemble Feature Learning of Genomic Data Using Support Vector Machine

PubMed Central

Anaissi, Ali; Goyal, Madhu; Catchpoole, Daniel R.; Braytee, Ali; Kennedy, Paul J.

2016-01-01

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data. PMID:27304923

Improving database enrichment through ensemble docking

NASA Astrophysics Data System (ADS)

Rao, Shashidhar; Sanschagrin, Paul C.; Greenwood, Jeremy R.; Repasky, Matthew P.; Sherman, Woody; Farid, Ramy

2008-09-01

While it may seem intuitive that using an ensemble of multiple conformations of a receptor in structure-based virtual screening experiments would necessarily yield improved enrichment of actives relative to using just a single receptor, it turns out that at least in the p38 MAP kinase model system studied here, a very large majority of all possible ensembles do not yield improved enrichment of actives. However, there are combinations of receptor structures that do lead to improved enrichment results. We present here a method to select the ensembles that produce the best enrichments that does not rely on knowledge of active compounds or sophisticated analyses of the 3D receptor structures. In the system studied here, the small fraction of ensembles of up to 3 receptors that do yield good enrichments of actives were identified by selecting ensembles that have the best mean GlideScore for the top 1% of the docked ligands in a database screen of actives and drug-like "decoy" ligands. Ensembles of two receptors identified using this mean GlideScore metric generally outperform single receptors, while ensembles of three receptors identified using this metric consistently give optimal enrichment factors in which, for example, 40% of the known actives outrank all the other ligands in the database.

Effects of ensembles on methane hydrate nucleation kinetics.

PubMed

Zhang, Zhengcai; Liu, Chan-Juan; Walsh, Matthew R; Guo, Guang-Jun

2016-06-21

By performing molecular dynamics simulations to form a hydrate with a methane nano-bubble in liquid water at 250 K and 50 MPa, we report how different ensembles, such as the NPT, NVT, and NVE ensembles, affect the nucleation kinetics of the methane hydrate. The nucleation trajectories are monitored using the face-saturated incomplete cage analysis (FSICA) and the mutually coordinated guest (MCG) order parameter (OP). The nucleation rate and the critical nucleus are obtained using the mean first-passage time (MFPT) method based on the FS cages and the MCG-1 OPs, respectively. The fitting results of MFPT show that hydrate nucleation and growth are coupled together, consistent with the cage adsorption hypothesis which emphasizes that the cage adsorption of methane is a mechanism for both hydrate nucleation and growth. For the three different ensembles, the hydrate nucleation rate is quantitatively ordered as follows: NPT > NVT > NVE, while the sequence of hydrate crystallinity is exactly reversed. However, the largest size of the critical nucleus appears in the NVT ensemble, rather than in the NVE ensemble. These results are helpful for choosing a suitable ensemble when to study hydrate formation via computer simulations, and emphasize the importance of the order degree of the critical nucleus.

Data-driven reverse engineering of signaling pathways using ensembles of dynamic models.

PubMed

Henriques, David; Villaverde, Alejandro F; Rocha, Miguel; Saez-Rodriguez, Julio; Banga, Julio R

2017-02-01

Despite significant efforts and remarkable progress, the inference of signaling networks from experimental data remains very challenging. The problem is particularly difficult when the objective is to obtain a dynamic model capable of predicting the effect of novel perturbations not considered during model training. The problem is ill-posed due to the nonlinear nature of these systems, the fact that only a fraction of the involved proteins and their post-translational modifications can be measured, and limitations on the technologies used for growing cells in vitro, perturbing them, and measuring their variations. As a consequence, there is a pervasive lack of identifiability. To overcome these issues, we present a methodology called SELDOM (enSEmbLe of Dynamic lOgic-based Models), which builds an ensemble of logic-based dynamic models, trains them to experimental data, and combines their individual simulations into an ensemble prediction. It also includes a model reduction step to prune spurious interactions and mitigate overfitting. SELDOM is a data-driven method, in the sense that it does not require any prior knowledge of the system: the interaction networks that act as scaffolds for the dynamic models are inferred from data using mutual information. We have tested SELDOM on a number of experimental and in silico signal transduction case-studies, including the recent HPN-DREAM breast cancer challenge. We found that its performance is highly competitive compared to state-of-the-art methods for the purpose of recovering network topology. More importantly, the utility of SELDOM goes beyond basic network inference (i.e. uncovering static interaction networks): it builds dynamic (based on ordinary differential equation) models, which can be used for mechanistic interpretations and reliable dynamic predictions in new experimental conditions (i.e. not used in the training). For this task, SELDOM's ensemble prediction is not only consistently better than predictions from individual models, but also often outperforms the state of the art represented by the methods used in the HPN-DREAM challenge.

Data-driven reverse engineering of signaling pathways using ensembles of dynamic models

PubMed Central

Henriques, David; Villaverde, Alejandro F.; Banga, Julio R.

2017-01-01

Despite significant efforts and remarkable progress, the inference of signaling networks from experimental data remains very challenging. The problem is particularly difficult when the objective is to obtain a dynamic model capable of predicting the effect of novel perturbations not considered during model training. The problem is ill-posed due to the nonlinear nature of these systems, the fact that only a fraction of the involved proteins and their post-translational modifications can be measured, and limitations on the technologies used for growing cells in vitro, perturbing them, and measuring their variations. As a consequence, there is a pervasive lack of identifiability. To overcome these issues, we present a methodology called SELDOM (enSEmbLe of Dynamic lOgic-based Models), which builds an ensemble of logic-based dynamic models, trains them to experimental data, and combines their individual simulations into an ensemble prediction. It also includes a model reduction step to prune spurious interactions and mitigate overfitting. SELDOM is a data-driven method, in the sense that it does not require any prior knowledge of the system: the interaction networks that act as scaffolds for the dynamic models are inferred from data using mutual information. We have tested SELDOM on a number of experimental and in silico signal transduction case-studies, including the recent HPN-DREAM breast cancer challenge. We found that its performance is highly competitive compared to state-of-the-art methods for the purpose of recovering network topology. More importantly, the utility of SELDOM goes beyond basic network inference (i.e. uncovering static interaction networks): it builds dynamic (based on ordinary differential equation) models, which can be used for mechanistic interpretations and reliable dynamic predictions in new experimental conditions (i.e. not used in the training). For this task, SELDOM’s ensemble prediction is not only consistently better than predictions from individual models, but also often outperforms the state of the art represented by the methods used in the HPN-DREAM challenge. PMID:28166222

Quasi-most unstable modes: a window to 'À la carte' ensemble diversity?

NASA Astrophysics Data System (ADS)

Homar Santaner, Victor; Stensrud, David J.

2010-05-01

The atmospheric scientific community is nowadays facing the ambitious challenge of providing useful forecasts of atmospheric events that produce high societal impact. The low level of social resilience to false alarms creates tremendous pressure on forecasting offices to issue accurate, timely and reliable warnings.Currently, no operational numerical forecasting system is able to respond to the societal demand for high-resolution (in time and space) predictions in the 12-72h time span. The main reasons for such deficiencies are the lack of adequate observations and the high non-linearity of the numerical models that are currently used. The whole weather forecasting problem is intrinsically probabilistic and current methods aim at coping with the various sources of uncertainties and the error propagation throughout the forecasting system. This probabilistic perspective is often created by generating ensembles of deterministic predictions that are aimed at sampling the most important sources of uncertainty in the forecasting system. The ensemble generation/sampling strategy is a crucial aspect of their performance and various methods have been proposed. Although global forecasting offices have been using ensembles of perturbed initial conditions for medium-range operational forecasts since 1994, no consensus exists regarding the optimum sampling strategy for high resolution short-range ensemble forecasts. Bred vectors, however, have been hypothesized to better capture the growing modes in the highly nonlinear mesoscale dynamics of severe episodes than singular vectors or observation perturbations. Yet even this technique is not able to produce enough diversity in the ensembles to accurately and routinely predict extreme phenomena such as severe weather. Thus, we propose a new method to generate ensembles of initial conditions perturbations that is based on the breeding technique. Given a standard bred mode, a set of customized perturbations is derived with specified amplitudes and horizontal scales. This allows the ensemble to excite growing modes across a wider range of scales. Results show that this approach produces significantly more spread in the ensemble prediction than standard bred modes alone. Several examples that illustrate the benefits from this approach for severe weather forecasts will be provided.

Ensemble Linear Neighborhood Propagation for Predicting Subchloroplast Localization of Multi-Location Proteins.

PubMed

Wan, Shibiao; Mak, Man-Wai; Kung, Sun-Yuan

2016-12-02

In the postgenomic era, the number of unreviewed protein sequences is remarkably larger and grows tremendously faster than that of reviewed ones. However, existing methods for protein subchloroplast localization often ignore the information from these unlabeled proteins. This paper proposes a multi-label predictor based on ensemble linear neighborhood propagation (LNP), namely, LNP-Chlo, which leverages hybrid sequence-based feature information from both labeled and unlabeled proteins for predicting localization of both single- and multi-label chloroplast proteins. Experimental results on a stringent benchmark dataset and a novel independent dataset suggest that LNP-Chlo performs at least 6% (absolute) better than state-of-the-art predictors. This paper also demonstrates that ensemble LNP significantly outperforms LNP based on individual features. For readers' convenience, the online Web server LNP-Chlo is freely available at http://bioinfo.eie.polyu.edu.hk/LNPChloServer/ .

The Cross-Entropy Based Multi-Filter Ensemble Method for Gene Selection.

PubMed

Sun, Yingqiang; Lu, Chengbo; Li, Xiaobo

2018-05-17

The gene expression profile has the characteristics of a high dimension, low sample, and continuous type, and it is a great challenge to use gene expression profile data for the classification of tumor samples. This paper proposes a cross-entropy based multi-filter ensemble (CEMFE) method for microarray data classification. Firstly, multiple filters are used to select the microarray data in order to obtain a plurality of the pre-selected feature subsets with a different classification ability. The top N genes with the highest rank of each subset are integrated so as to form a new data set. Secondly, the cross-entropy algorithm is used to remove the redundant data in the data set. Finally, the wrapper method, which is based on forward feature selection, is used to select the best feature subset. The experimental results show that the proposed method is more efficient than other gene selection methods and that it can achieve a higher classification accuracy under fewer characteristic genes.

Improved method for predicting protein fold patterns with ensemble classifiers.

PubMed

Chen, W; Liu, X; Huang, Y; Jiang, Y; Zou, Q; Lin, C

2012-01-27

Protein folding is recognized as a critical problem in the field of biophysics in the 21st century. Predicting protein-folding patterns is challenging due to the complex structure of proteins. In an attempt to solve this problem, we employed ensemble classifiers to improve prediction accuracy. In our experiments, 188-dimensional features were extracted based on the composition and physical-chemical property of proteins and 20-dimensional features were selected using a coupled position-specific scoring matrix. Compared with traditional prediction methods, these methods were superior in terms of prediction accuracy. The 188-dimensional feature-based method achieved 71.2% accuracy in five cross-validations. The accuracy rose to 77% when we used a 20-dimensional feature vector. These methods were used on recent data, with 54.2% accuracy. Source codes and dataset, together with web server and software tools for prediction, are available at: http://datamining.xmu.edu.cn/main/~cwc/ProteinPredict.html.

Analysis of Vibration and Noise of Construction Machinery Based on Ensemble Empirical Mode Decomposition and Spectral Correlation Analysis Method

NASA Astrophysics Data System (ADS)

Chen, Yuebiao; Zhou, Yiqi; Yu, Gang; Lu, Dan

In order to analyze the effect of engine vibration on cab noise of construction machinery in multi-frequency bands, a new method based on ensemble empirical mode decomposition (EEMD) and spectral correlation analysis is proposed. Firstly, the intrinsic mode functions (IMFs) of vibration and noise signals were obtained by EEMD method, and then the IMFs which have the same frequency bands were selected. Secondly, we calculated the spectral correlation coefficients between the selected IMFs, getting the main frequency bands in which engine vibration has significant impact on cab noise. Thirdly, the dominated frequencies were picked out and analyzed by spectral analysis method. The study result shows that the main frequency bands and dominated frequencies in which engine vibration have serious impact on cab noise can be identified effectively by the proposed method, which provides effective guidance to noise reduction of construction machinery.

Large ensemble modeling of the last deglacial retreat of the West Antarctic Ice Sheet: comparison of simple and advanced statistical techniques

NASA Astrophysics Data System (ADS)

Pollard, David; Chang, Won; Haran, Murali; Applegate, Patrick; DeConto, Robert

2016-05-01

A 3-D hybrid ice-sheet model is applied to the last deglacial retreat of the West Antarctic Ice Sheet over the last ˜ 20 000 yr. A large ensemble of 625 model runs is used to calibrate the model to modern and geologic data, including reconstructed grounding lines, relative sea-level records, elevation-age data and uplift rates, with an aggregate score computed for each run that measures overall model-data misfit. Two types of statistical methods are used to analyze the large-ensemble results: simple averaging weighted by the aggregate score, and more advanced Bayesian techniques involving Gaussian process-based emulation and calibration, and Markov chain Monte Carlo. The analyses provide sea-level-rise envelopes with well-defined parametric uncertainty bounds, but the simple averaging method only provides robust results with full-factorial parameter sampling in the large ensemble. Results for best-fit parameter ranges and envelopes of equivalent sea-level rise with the simple averaging method agree well with the more advanced techniques. Best-fit parameter ranges confirm earlier values expected from prior model tuning, including large basal sliding coefficients on modern ocean beds.

A novel approach for baseline correction in 1H-MRS signals based on ensemble empirical mode decomposition.

PubMed

Parto Dezfouli, Mohammad Ali; Dezfouli, Mohsen Parto; Rad, Hamidreza Saligheh

2014-01-01

Proton magnetic resonance spectroscopy ((1)H-MRS) is a non-invasive diagnostic tool for measuring biochemical changes in the human body. Acquired (1)H-MRS signals may be corrupted due to a wideband baseline signal generated by macromolecules. Recently, several methods have been developed for the correction of such baseline signals, however most of them are not able to estimate baseline in complex overlapped signal. In this study, a novel automatic baseline correction method is proposed for (1)H-MRS spectra based on ensemble empirical mode decomposition (EEMD). This investigation was applied on both the simulated data and the in-vivo (1)H-MRS of human brain signals. Results justify the efficiency of the proposed method to remove the baseline from (1)H-MRS signals.

Total probabilities of ensemble runoff forecasts

NASA Astrophysics Data System (ADS)

Olav Skøien, Jon; Bogner, Konrad; Salamon, Peter; Smith, Paul; Pappenberger, Florian

2017-04-01

Ensemble forecasting has a long history from meteorological modelling, as an indication of the uncertainty of the forecasts. However, it is necessary to calibrate and post-process the ensembles as the they often exhibit both bias and dispersion errors. Two of the most common methods for this are Bayesian Model Averaging (Raftery et al., 2005) and Ensemble Model Output Statistics (EMOS) (Gneiting et al., 2005). There are also methods for regionalizing these methods (Berrocal et al., 2007) and for incorporating the correlation between lead times (Hemri et al., 2013). Engeland and Steinsland Engeland and Steinsland (2014) developed a framework which can estimate post-processing parameters varying in space and time, while giving a spatially and temporally consistent output. However, their method is computationally complex for our larger number of stations, which makes it unsuitable for our purpose. Our post-processing method of the ensembles is developed in the framework of the European Flood Awareness System (EFAS - http://www.efas.eu), where we are making forecasts for whole Europe, and based on observations from around 700 catchments. As the target is flood forecasting, we are also more interested in improving the forecast skill for high-flows rather than in a good prediction of the entire flow regime. EFAS uses a combination of ensemble forecasts and deterministic forecasts from different meteorological forecasters to force a distributed hydrologic model and to compute runoff ensembles for each river pixel within the model domain. Instead of showing the mean and the variability of each forecast ensemble individually, we will now post-process all model outputs to estimate the total probability, the post-processed mean and uncertainty of all ensembles. The post-processing parameters are first calibrated for each calibration location, but we are adding a spatial penalty in the calibration process to force a spatial correlation of the parameters. The penalty takes distance, stream-connectivity and size of the catchment areas into account. This can in some cases have a slight negative impact on the calibration error, but avoids large differences between parameters of nearby locations, whether stream connected or not. The spatial calibration also makes it easier to interpolate the post-processing parameters to uncalibrated locations. We also look into different methods for handling the non-normal distributions of runoff data and the effect of different data transformations on forecasts skills in general and for floods in particular. Berrocal, V. J., Raftery, A. E. and Gneiting, T.: Combining Spatial Statistical and Ensemble Information in Probabilistic Weather Forecasts, Mon. Weather Rev., 135(4), 1386-1402, doi:10.1175/MWR3341.1, 2007. Engeland, K. and Steinsland, I.: Probabilistic postprocessing models for flow forecasts for a system of catchments and several lead times, Water Resour. Res., 50(1), 182-197, doi:10.1002/2012WR012757, 2014. Gneiting, T., Raftery, A. E., Westveld, A. H. and Goldman, T.: Calibrated Probabilistic Forecasting Using Ensemble Model Output Statistics and Minimum CRPS Estimation, Mon. Weather Rev., 133(5), 1098-1118, doi:10.1175/MWR2904.1, 2005. Hemri, S., Fundel, F. and Zappa, M.: Simultaneous calibration of ensemble river flow predictions over an entire range of lead times, Water Resour. Res., 49(10), 6744-6755, doi:10.1002/wrcr.20542, 2013. Raftery, A. E., Gneiting, T., Balabdaoui, F. and Polakowski, M.: Using Bayesian Model Averaging to Calibrate Forecast Ensembles, Mon. Weather Rev., 133(5), 1155-1174, doi:10.1175/MWR2906.1, 2005.

Using simulation to interpret experimental data in terms of protein conformational ensembles.

PubMed

Allison, Jane R

2017-04-01

In their biological environment, proteins are dynamic molecules, necessitating an ensemble structural description. Molecular dynamics simulations and solution-state experiments provide complimentary information in the form of atomically detailed coordinates and averaged or distributions of structural properties or related quantities. Recently, increases in the temporal and spatial scale of conformational sampling and comparison of the more diverse conformational ensembles thus generated have revealed the importance of sampling rare events. Excitingly, new methods based on maximum entropy and Bayesian inference are promising to provide a statistically sound mechanism for combining experimental data with molecular dynamics simulations. Copyright © 2016 Elsevier Ltd. All rights reserved.

Assessing the predictive capability of randomized tree-based ensembles in streamflow modelling

NASA Astrophysics Data System (ADS)

Galelli, S.; Castelletti, A.

2013-02-01

Combining randomization methods with ensemble prediction is emerging as an effective option to balance accuracy and computational efficiency in data-driven modeling. In this paper we investigate the prediction capability of extremely randomized trees (Extra-Trees), in terms of accuracy, explanation ability and computational efficiency, in a streamflow modeling exercise. Extra-Trees are a totally randomized tree-based ensemble method that (i) alleviates the poor generalization property and tendency to overfitting of traditional standalone decision trees (e.g. CART); (ii) is computationally very efficient; and, (iii) allows to infer the relative importance of the input variables, which might help in the ex-post physical interpretation of the model. The Extra-Trees potential is analyzed on two real-world case studies (Marina catchment (Singapore) and Canning River (Western Australia)) representing two different morphoclimatic contexts comparatively with other tree-based methods (CART and M5) and parametric data-driven approaches (ANNs and multiple linear regression). Results show that Extra-Trees perform comparatively well to the best of the benchmarks (i.e. M5) in both the watersheds, while outperforming the other approaches in terms of computational requirement when adopted on large datasets. In addition, the ranking of the input variable provided can be given a physically meaningful interpretation.

Assessing the predictive capability of randomized tree-based ensembles in streamflow modelling

NASA Astrophysics Data System (ADS)

Galelli, S.; Castelletti, A.

2013-07-01

Combining randomization methods with ensemble prediction is emerging as an effective option to balance accuracy and computational efficiency in data-driven modelling. In this paper, we investigate the prediction capability of extremely randomized trees (Extra-Trees), in terms of accuracy, explanation ability and computational efficiency, in a streamflow modelling exercise. Extra-Trees are a totally randomized tree-based ensemble method that (i) alleviates the poor generalisation property and tendency to overfitting of traditional standalone decision trees (e.g. CART); (ii) is computationally efficient; and, (iii) allows to infer the relative importance of the input variables, which might help in the ex-post physical interpretation of the model. The Extra-Trees potential is analysed on two real-world case studies - Marina catchment (Singapore) and Canning River (Western Australia) - representing two different morphoclimatic contexts. The evaluation is performed against other tree-based methods (CART and M5) and parametric data-driven approaches (ANNs and multiple linear regression). Results show that Extra-Trees perform comparatively well to the best of the benchmarks (i.e. M5) in both the watersheds, while outperforming the other approaches in terms of computational requirement when adopted on large datasets. In addition, the ranking of the input variable provided can be given a physically meaningful interpretation.

Exploring the calibration of a wind forecast ensemble for energy applications

NASA Astrophysics Data System (ADS)

Heppelmann, Tobias; Ben Bouallegue, Zied; Theis, Susanne

2015-04-01

In the German research project EWeLiNE, Deutscher Wetterdienst (DWD) and Fraunhofer Institute for Wind Energy and Energy System Technology (IWES) are collaborating with three German Transmission System Operators (TSO) in order to provide the TSOs with improved probabilistic power forecasts. Probabilistic power forecasts are derived from probabilistic weather forecasts, themselves derived from ensemble prediction systems (EPS). Since the considered raw ensemble wind forecasts suffer from underdispersiveness and bias, calibration methods are developed for the correction of the model bias and the ensemble spread bias. The overall aim is to improve the ensemble forecasts such that the uncertainty of the possible weather deployment is depicted by the ensemble spread from the first forecast hours. Additionally, the ensemble members after calibration should remain physically consistent scenarios. We focus on probabilistic hourly wind forecasts with horizon of 21 h delivered by the convection permitting high-resolution ensemble system COSMO-DE-EPS which has become operational in 2012 at DWD. The ensemble consists of 20 ensemble members driven by four different global models. The model area includes whole Germany and parts of Central Europe with a horizontal resolution of 2.8 km and a vertical resolution of 50 model levels. For verification we use wind mast measurements around 100 m height that corresponds to the hub height of wind energy plants that belong to wind farms within the model area. Calibration of the ensemble forecasts can be performed by different statistical methods applied to the raw ensemble output. Here, we explore local bivariate Ensemble Model Output Statistics at individual sites and quantile regression with different predictors. Applying different methods, we already show an improvement of ensemble wind forecasts from COSMO-DE-EPS for energy applications. In addition, an ensemble copula coupling approach transfers the time-dependencies of the raw ensemble to the calibrated ensemble. The calibrated wind forecasts are evaluated first with univariate probabilistic scores and additionally with diagnostics of wind ramps in order to assess the time-consistency of the calibrated ensemble members.

Reconstruction of ensembles of coupled time-delay systems from time series.

PubMed

Sysoev, I V; Prokhorov, M D; Ponomarenko, V I; Bezruchko, B P

2014-06-01

We propose a method to recover from time series the parameters of coupled time-delay systems and the architecture of couplings between them. The method is based on a reconstruction of model delay-differential equations and estimation of statistical significance of couplings. It can be applied to networks composed of nonidentical nodes with an arbitrary number of unidirectional and bidirectional couplings. We test our method on chaotic and periodic time series produced by model equations of ensembles of diffusively coupled time-delay systems in the presence of noise, and apply it to experimental time series obtained from electronic oscillators with delayed feedback coupled by resistors.

Selecting climate simulations for impact studies based on multivariate patterns of climate change.

PubMed

Mendlik, Thomas; Gobiet, Andreas

In climate change impact research it is crucial to carefully select the meteorological input for impact models. We present a method for model selection that enables the user to shrink the ensemble to a few representative members, conserving the model spread and accounting for model similarity. This is done in three steps: First, using principal component analysis for a multitude of meteorological parameters, to find common patterns of climate change within the multi-model ensemble. Second, detecting model similarities with regard to these multivariate patterns using cluster analysis. And third, sampling models from each cluster, to generate a subset of representative simulations. We present an application based on the ENSEMBLES regional multi-model ensemble with the aim to provide input for a variety of climate impact studies. We find that the two most dominant patterns of climate change relate to temperature and humidity patterns. The ensemble can be reduced from 25 to 5 simulations while still maintaining its essential characteristics. Having such a representative subset of simulations reduces computational costs for climate impact modeling and enhances the quality of the ensemble at the same time, as it prevents double-counting of dependent simulations that would lead to biased statistics. The online version of this article (doi:10.1007/s10584-015-1582-0) contains supplementary material, which is available to authorized users.

An adaptive incremental approach to constructing ensemble classifiers: Application in an information-theoretic computer-aided decision system for detection of masses in mammograms

PubMed Central

Mazurowski, Maciej A.; Zurada, Jacek M.; Tourassi, Georgia D.

2009-01-01

Ensemble classifiers have been shown efficient in multiple applications. In this article, the authors explore the effectiveness of ensemble classifiers in a case-based computer-aided diagnosis system for detection of masses in mammograms. They evaluate two general ways of constructing subclassifiers by resampling of the available development dataset: Random division and random selection. Furthermore, they discuss the problem of selecting the ensemble size and propose two adaptive incremental techniques that automatically select the size for the problem at hand. All the techniques are evaluated with respect to a previously proposed information-theoretic CAD system (IT-CAD). The experimental results show that the examined ensemble techniques provide a statistically significant improvement (AUC=0.905±0.024) in performance as compared to the original IT-CAD system (AUC=0.865±0.029). Some of the techniques allow for a notable reduction in the total number of examples stored in the case base (to 1.3% of the original size), which, in turn, results in lower storage requirements and a shorter response time of the system. Among the methods examined in this article, the two proposed adaptive techniques are by far the most effective for this purpose. Furthermore, the authors provide some discussion and guidance for choosing the ensemble parameters. PMID:19673196

Simultaneous escaping of explicit and hidden free energy barriers: application of the orthogonal space random walk strategy in generalized ensemble based conformational sampling.

PubMed

Zheng, Lianqing; Chen, Mengen; Yang, Wei

2009-06-21

To overcome the pseudoergodicity problem, conformational sampling can be accelerated via generalized ensemble methods, e.g., through the realization of random walks along prechosen collective variables, such as spatial order parameters, energy scaling parameters, or even system temperatures or pressures, etc. As usually observed, in generalized ensemble simulations, hidden barriers are likely to exist in the space perpendicular to the collective variable direction and these residual free energy barriers could greatly abolish the sampling efficiency. This sampling issue is particularly severe when the collective variable is defined in a low-dimension subset of the target system; then the "Hamiltonian lagging" problem, which reveals the fact that necessary structural relaxation falls behind the move of the collective variable, may be likely to occur. To overcome this problem in equilibrium conformational sampling, we adopted the orthogonal space random walk (OSRW) strategy, which was originally developed in the context of free energy simulation [L. Zheng, M. Chen, and W. Yang, Proc. Natl. Acad. Sci. U.S.A. 105, 20227 (2008)]. Thereby, generalized ensemble simulations can simultaneously escape both the explicit barriers along the collective variable direction and the hidden barriers that are strongly coupled with the collective variable move. As demonstrated in our model studies, the present OSRW based generalized ensemble treatments show improved sampling capability over the corresponding classical generalized ensemble treatments.

Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data

NASA Technical Reports Server (NTRS)

Rebbapragada, Umaa; Wagstaff, Kiri L.

2011-01-01

This paper seeks to improve low-cost labeling in terms of training set reliability (the fraction of correctly labeled training items) and test set performance for multi-view learning methods. Co-training is a popular multiview learning method that combines high-confidence example selection with low-cost (self) labeling. However, co-training with certain base learning algorithms significantly reduces training set reliability, causing an associated drop in prediction accuracy. We propose the use of ensemble labeling to improve reliability in such cases. We also discuss and show promising results on combining low-cost ensemble labeling with active (low-confidence) example selection. We unify these example selection and labeling strategies under collaborative learning, a family of techniques for multi-view learning that we are developing for distributed, sensor-network environments.

Generalized Ensemble Sampling of Enzyme Reaction Free Energy Pathways

PubMed Central

Wu, Dongsheng; Fajer, Mikolai I.; Cao, Liaoran; Cheng, Xiaolin; Yang, Wei

2016-01-01

Free energy path sampling plays an essential role in computational understanding of chemical reactions, particularly those occurring in enzymatic environments. Among a variety of molecular dynamics simulation approaches, the generalized ensemble sampling strategy is uniquely attractive for the fact that it not only can enhance the sampling of rare chemical events but also can naturally ensure consistent exploration of environmental degrees of freedom. In this review, we plan to provide a tutorial-like tour on an emerging topic: generalized ensemble sampling of enzyme reaction free energy path. The discussion is largely focused on our own studies, particularly ones based on the metadynamics free energy sampling method and the on-the-path random walk path sampling method. We hope that this mini presentation will provide interested practitioners some meaningful guidance for future algorithm formulation and application study. PMID:27498634

Encoding qubits into oscillators with atomic ensembles and squeezed light

NASA Astrophysics Data System (ADS)

Motes, Keith R.; Baragiola, Ben Q.; Gilchrist, Alexei; Menicucci, Nicolas C.

2017-05-01

The Gottesman-Kitaev-Preskill (GKP) encoding of a qubit within an oscillator provides a number of advantages when used in a fault-tolerant architecture for quantum computing, most notably that Gaussian operations suffice to implement all single- and two-qubit Clifford gates. The main drawback of the encoding is that the logical states themselves are challenging to produce. Here we present a method for generating optical GKP-encoded qubits by coupling an atomic ensemble to a squeezed state of light. Particular outcomes of a subsequent spin measurement of the ensemble herald successful generation of the resource state in the optical mode. We analyze the method in terms of the resources required (total spin and amount of squeezing) and the probability of success. We propose a physical implementation using a Faraday-based quantum nondemolition interaction.

Ensemble Data Mining Methods

NASA Technical Reports Server (NTRS)

Oza, Nikunj C.

2004-01-01

Ensemble Data Mining Methods, also known as Committee Methods or Model Combiners, are machine learning methods that leverage the power of multiple models to achieve better prediction accuracy than any of the individual models could on their own. The basic goal when designing an ensemble is the same as when establishing a committee of people: each member of the committee should be as competent as possible, but the members should be complementary to one another. If the members are not complementary, Le., if they always agree, then the committee is unnecessary---any one member is sufficient. If the members are complementary, then when one or a few members make an error, the probability is high that the remaining members can correct this error. Research in ensemble methods has largely revolved around designing ensembles consisting of competent yet complementary models.

A comparison between EDA-EnVar and ETKF-EnVar data assimilation techniques using radar observations at convective scales through a case study of Hurricane Ike (2008)

NASA Astrophysics Data System (ADS)

Shen, Feifei; Xu, Dongmei; Xue, Ming; Min, Jinzhong

2017-07-01

This study examines the impacts of assimilating radar radial velocity (Vr) data for the simulation of hurricane Ike (2008) with two different ensemble generation techniques in the framework of the hybrid ensemble-variational (EnVar) data assimilation system of Weather Research and Forecasting model. For the generation of ensemble perturbations we apply two techniques, the ensemble transform Kalman filter (ETKF) and the ensemble of data assimilation (EDA). For the ETKF-EnVar, the forecast ensemble perturbations are updated by the ETKF, while for the EDA-EnVar, the hybrid is employed to update each ensemble member with perturbed observations. The ensemble mean is analyzed by the hybrid method with flow-dependent ensemble covariance for both EnVar. The sensitivity of analyses and forecasts to the two applied ensemble generation techniques is investigated in our current study. It is found that the EnVar system is rather stable with different ensemble update techniques in terms of its skill on improving the analyses and forecasts. The EDA-EnVar-based ensemble perturbations are likely to include slightly less organized spatial structures than those in ETKF-EnVar, and the perturbations of the latter are constructed more dynamically. Detailed diagnostics reveal that both of the EnVar schemes not only produce positive temperature increments around the hurricane center but also systematically adjust the hurricane location with the hurricane-specific error covariance. On average, the analysis and forecast from the ETKF-EnVar have slightly smaller errors than that from the EDA-EnVar in terms of track, intensity, and precipitation forecast. Moreover, ETKF-EnVar yields better forecasts when verified against conventional observations.

Ensemble gene function prediction database reveals genes important for complex I formation in Arabidopsis thaliana.

PubMed

Hansen, Bjoern Oest; Meyer, Etienne H; Ferrari, Camilla; Vaid, Neha; Movahedi, Sara; Vandepoele, Klaas; Nikoloski, Zoran; Mutwil, Marek

2018-03-01

Recent advances in gene function prediction rely on ensemble approaches that integrate results from multiple inference methods to produce superior predictions. Yet, these developments remain largely unexplored in plants. We have explored and compared two methods to integrate 10 gene co-function networks for Arabidopsis thaliana and demonstrate how the integration of these networks produces more accurate gene function predictions for a larger fraction of genes with unknown function. These predictions were used to identify genes involved in mitochondrial complex I formation, and for five of them, we confirmed the predictions experimentally. The ensemble predictions are provided as a user-friendly online database, EnsembleNet. The methods presented here demonstrate that ensemble gene function prediction is a powerful method to boost prediction performance, whereas the EnsembleNet database provides a cutting-edge community tool to guide experimentalists. © 2017 The Authors. New Phytologist © 2017 New Phytologist Trust.

MULTI-K: accurate classification of microarray subtypes using ensemble k-means clustering

PubMed Central

Kim, Eun-Youn; Kim, Seon-Young; Ashlock, Daniel; Nam, Dougu

2009-01-01

Background Uncovering subtypes of disease from microarray samples has important clinical implications such as survival time and sensitivity of individual patients to specific therapies. Unsupervised clustering methods have been used to classify this type of data. However, most existing methods focus on clusters with compact shapes and do not reflect the geometric complexity of the high dimensional microarray clusters, which limits their performance. Results We present a cluster-number-based ensemble clustering algorithm, called MULTI-K, for microarray sample classification, which demonstrates remarkable accuracy. The method amalgamates multiple k-means runs by varying the number of clusters and identifies clusters that manifest the most robust co-memberships of elements. In addition to the original algorithm, we newly devised the entropy-plot to control the separation of singletons or small clusters. MULTI-K, unlike the simple k-means or other widely used methods, was able to capture clusters with complex and high-dimensional structures accurately. MULTI-K outperformed other methods including a recently developed ensemble clustering algorithm in tests with five simulated and eight real gene-expression data sets. Conclusion The geometric complexity of clusters should be taken into account for accurate classification of microarray data, and ensemble clustering applied to the number of clusters tackles the problem very well. The C++ code and the data sets tested are available from the authors. PMID:19698124

On the predictability of outliers in ensemble forecasts

NASA Astrophysics Data System (ADS)

Siegert, S.; Bröcker, J.; Kantz, H.

2012-03-01

In numerical weather prediction, ensembles are used to retrieve probabilistic forecasts of future weather conditions. We consider events where the verification is smaller than the smallest, or larger than the largest ensemble member of a scalar ensemble forecast. These events are called outliers. In a statistically consistent K-member ensemble, outliers should occur with a base rate of 2/(K+1). In operational ensembles this base rate tends to be higher. We study the predictability of outlier events in terms of the Brier Skill Score and find that forecast probabilities can be calculated which are more skillful than the unconditional base rate. This is shown analytically for statistically consistent ensembles. Using logistic regression, forecast probabilities for outlier events in an operational ensemble are calculated. These probabilities exhibit positive skill which is quantitatively similar to the analytical results. Possible causes of these results as well as their consequences for ensemble interpretation are discussed.

A mesoscale hybrid data assimilation system based on the JMA nonhydrostatic model

NASA Astrophysics Data System (ADS)

Ito, K.; Kunii, M.; Kawabata, T. T.; Saito, K. K.; Duc, L. L.

2015-12-01

This work evaluates the potential of a hybrid ensemble Kalman filter and four-dimensional variational (4D-Var) data assimilation system for predicting severe weather events from a deterministic point of view. This hybrid system is an adjoint-based 4D-Var system using a background error covariance matrix constructed from the mixture of a so-called NMC method and perturbations in a local ensemble transform Kalman filter data assimilation system, both of which are based on the Japan Meteorological Agency nonhydrostatic model. To construct the background error covariance matrix, we investigated two types of schemes. One is a spatial localization scheme and the other is neighboring ensemble approach, which regards the result at a horizontally spatially shifted point in each ensemble member as that obtained from a different realization of ensemble simulation. An assimilation of a pseudo single-observation located to the north of a tropical cyclone (TC) yielded an analysis increment of wind and temperature physically consistent with what is expected for a mature TC in both hybrid systems, whereas an analysis increment in a 4D-Var system using a static background error covariance distorted a structure of the mature TC. Real data assimilation experiments applied to 4 TCs and 3 local heavy rainfall events showed that hybrid systems and EnKF provided better initial conditions than the NMC-based 4D-Var, both for predicting the intensity and track forecast of TCs and for the location and amount of local heavy rainfall events.

A Novel Data-Driven Learning Method for Radar Target Detection in Nonstationary Environments

DTIC Science & Technology

2016-05-01

Classifier ensembles for changing environments,” in Multiple Classifier Systems, vol. 3077, F. Roli, J. Kittler and T. Windeatt, Eds. New York, NY...Dec. 2006, pp. 1113–1118. [21] J. Z. Kolter and M. A. Maloof, “Dynamic weighted majority: An ensemble method for drifting concepts,” J. Mach. Learn...Trans. Neural Netw., vol. 22, no. 10, pp. 1517–1531, Oct. 2011. [23] R. Polikar, “ Ensemble learning,” in Ensemble Machine Learning: Methods and

Ensemble-based docking: From hit discovery to metabolism and toxicity predictions

DOE PAGES

Evangelista, Wilfredo; Weir, Rebecca; Ellingson, Sally; ...

2016-07-29

The use of ensemble-based docking for the exploration of biochemical pathways and toxicity prediction of drug candidates is described. We describe the computational engineering work necessary to enable large ensemble docking campaigns on supercomputers. We show examples where ensemble-based docking has significantly increased the number and the diversity of validated drug candidates. Finally, we illustrate how ensemble-based docking can be extended beyond hit discovery and toward providing a structural basis for the prediction of metabolism and off-target binding relevant to pre-clinical and clinical trials.

Identifying Optimal Measurement Subspace for the Ensemble Kalman Filter

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

Zhou, Ning; Huang, Zhenyu; Welch, Greg

2012-05-24

To reduce the computational load of the ensemble Kalman filter while maintaining its efficacy, an optimization algorithm based on the generalized eigenvalue decomposition method is proposed for identifying the most informative measurement subspace. When the number of measurements is large, the proposed algorithm can be used to make an effective tradeoff between computational complexity and estimation accuracy. This algorithm also can be extended to other Kalman filters for measurement subspace selection.

Operating Spin Echo in the Quantum Regime for an Atomic-Ensemble Quantum Memory

NASA Astrophysics Data System (ADS)

Rui, Jun; Jiang, Yan; Yang, Sheng-Jun; Zhao, Bo; Bao, Xiao-Hui; Pan, Jian-Wei

2015-09-01

Spin echo is a powerful technique to extend atomic or nuclear coherence times by overcoming the dephasing due to inhomogeneous broadenings. However, there are disputes about the feasibility of applying this technique to an ensemble-based quantum memory at the single-quanta level. In this experimental study, we find that noise due to imperfections of the rephasing pulses has both intense superradiant and weak isotropic parts. By properly arranging the beam directions and optimizing the pulse fidelities, we successfully manage to operate the spin echo technique in the quantum regime by observing nonclassical photon-photon correlations as well as the quantum behavior of retrieved photons. Our work for the first time demonstrates the feasibility of harnessing the spin echo method to extend the lifetime of ensemble-based quantum memories at the single-quanta level.

A Global Carbon Assimilation System using a modified EnKF assimilation method

NASA Astrophysics Data System (ADS)

Zhang, S.; Zheng, X.; Chen, Z.; Dan, B.; Chen, J. M.; Yi, X.; Wang, L.; Wu, G.

2014-10-01

A Global Carbon Assimilation System based on Ensemble Kalman filter (GCAS-EK) is developed for assimilating atmospheric CO2 abundance data into an ecosystem model to simultaneously estimate the surface carbon fluxes and atmospheric CO2 distribution. This assimilation approach is based on the ensemble Kalman filter (EnKF), but with several new developments, including using analysis states to iteratively estimate ensemble forecast errors, and a maximum likelihood estimation of the inflation factors of the forecast and observation errors. The proposed assimilation approach is tested in observing system simulation experiments and then used to estimate the terrestrial ecosystem carbon fluxes and atmospheric CO2 distributions from 2002 to 2008. The results showed that this assimilation approach can effectively reduce the biases and uncertainties of the carbon fluxes simulated by the ecosystem model.

Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples.

PubMed

Zhang, He-Hua; Yang, Liuyang; Liu, Yuchuan; Wang, Pin; Yin, Jun; Li, Yongming; Qiu, Mingguo; Zhu, Xueru; Yan, Fang

2016-11-16

The use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined. In this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation. Experimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms. This study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.

Simulation's Ensemble is Better Than Ensemble Simulation

NASA Astrophysics Data System (ADS)

Yan, X.

2017-12-01

Simulation's ensemble is better than ensemble simulation Yan Xiaodong State Key Laboratory of Earth Surface Processes and Resource Ecology (ESPRE) Beijing Normal University,19 Xinjiekouwai Street, Haidian District, Beijing 100875, China Email: yxd@bnu.edu.cnDynamical system is simulated from initial state. However initial state data is of great uncertainty, which leads to uncertainty of simulation. Therefore, multiple possible initial states based simulation has been used widely in atmospheric science, which has indeed been proved to be able to lower the uncertainty, that was named simulation's ensemble because multiple simulation results would be fused . In ecological field, individual based model simulation (forest gap models for example) can be regarded as simulation's ensemble compared with community based simulation (most ecosystem models). In this talk, we will address the advantage of individual based simulation and even their ensembles.

A Single Column Model Ensemble Approach Applied to the TWP-ICE Experiment

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

Davies, Laura; Jakob, Christian; Cheung, K.

2013-06-27

Single column models (SCM) are useful testbeds for investigating the parameterisation schemes of numerical weather prediction and climate models. The usefulness of SCM simulations are limited, however, by the accuracy of the best-estimate large-scale data prescribed. One method to address this uncertainty is to perform ensemble simulations of the SCM. This study first derives an ensemble of large-scale data for the Tropical Warm Pool International Cloud Experiment (TWP-ICE) based on an estimate of a possible source of error in the best-estimate product. This data is then used to carry out simulations with 11 SCM and 2 cloud-resolving models (CRM). Best-estimatemore » simulations are also performed. All models show that moisture related variables are close to observations and there are limited differences between the best-estimate and ensemble mean values. The models, however, show different sensitivities to changes in the forcing particularly when weakly forced. The ensemble simulations highlight important differences in the moisture budget between the SCM and CRM. Systematic differences are also apparent in the ensemble mean vertical structure of cloud variables. The ensemble is further used to investigate relations between cloud variables and precipitation identifying large differences between CRM and SCM. This study highlights that additional information can be gained by performing ensemble simulations enhancing the information derived from models using the more traditional single best-estimate simulation.« less

A Noise-Assisted Data Analysis Method for Automatic EOG-Based Sleep Stage Classification Using Ensemble Learning.

PubMed

Olesen, Alexander Neergaard; Christensen, Julie A E; Sorensen, Helge B D; Jennum, Poul J

2016-08-01

Reducing the number of recording modalities for sleep staging research can benefit both researchers and patients, under the condition that they provide as accurate results as conventional systems. This paper investigates the possibility of exploiting the multisource nature of the electrooculography (EOG) signals by presenting a method for automatic sleep staging using the complete ensemble empirical mode decomposition with adaptive noise algorithm, and a random forest classifier. It achieves a high overall accuracy of 82% and a Cohen's kappa of 0.74 indicating substantial agreement between automatic and manual scoring.

The ensemble switch method for computing interfacial tensions

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

Schmitz, Fabian; Virnau, Peter

2015-04-14

We present a systematic thermodynamic integration approach to compute interfacial tensions for solid-liquid interfaces, which is based on the ensemble switch method. Applying Monte Carlo simulations and finite-size scaling techniques, we obtain results for hard spheres, which are in agreement with previous computations. The case of solid-liquid interfaces in a variant of the effective Asakura-Oosawa model and of liquid-vapor interfaces in the Lennard-Jones model are discussed as well. We demonstrate that a thorough finite-size analysis of the simulation data is required to obtain precise results for the interfacial tension.

A four-stage hybrid model for hydrological time series forecasting.

PubMed

Di, Chongli; Yang, Xiaohua; Wang, Xiaochao

2014-01-01

Hydrological time series forecasting remains a difficult task due to its complicated nonlinear, non-stationary and multi-scale characteristics. To solve this difficulty and improve the prediction accuracy, a novel four-stage hybrid model is proposed for hydrological time series forecasting based on the principle of 'denoising, decomposition and ensemble'. The proposed model has four stages, i.e., denoising, decomposition, components prediction and ensemble. In the denoising stage, the empirical mode decomposition (EMD) method is utilized to reduce the noises in the hydrological time series. Then, an improved method of EMD, the ensemble empirical mode decomposition (EEMD), is applied to decompose the denoised series into a number of intrinsic mode function (IMF) components and one residual component. Next, the radial basis function neural network (RBFNN) is adopted to predict the trend of all of the components obtained in the decomposition stage. In the final ensemble prediction stage, the forecasting results of all of the IMF and residual components obtained in the third stage are combined to generate the final prediction results, using a linear neural network (LNN) model. For illustration and verification, six hydrological cases with different characteristics are used to test the effectiveness of the proposed model. The proposed hybrid model performs better than conventional single models, the hybrid models without denoising or decomposition and the hybrid models based on other methods, such as the wavelet analysis (WA)-based hybrid models. In addition, the denoising and decomposition strategies decrease the complexity of the series and reduce the difficulties of the forecasting. With its effective denoising and accurate decomposition ability, high prediction precision and wide applicability, the new model is very promising for complex time series forecasting. This new forecast model is an extension of nonlinear prediction models.

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.

"Intelligent Ensemble" Projections of Precipitation and Surface Radiation in Support of Agricultural Climate Change Adaptation

NASA Technical Reports Server (NTRS)

Taylor, Patrick C.; Baker, Noel C.

2015-01-01

Earth's climate is changing and will continue to change into the foreseeable future. Expected changes in the climatological distribution of precipitation, surface temperature, and surface solar radiation will significantly impact agriculture. Adaptation strategies are, therefore, required to reduce the agricultural impacts of climate change. Climate change projections of precipitation, surface temperature, and surface solar radiation distributions are necessary input for adaption planning studies. These projections are conventionally constructed from an ensemble of climate model simulations (e.g., the Coupled Model Intercomparison Project 5 (CMIP5)) as an equal weighted average, one model one vote. Each climate model, however, represents the array of climate-relevant physical processes with varying degrees of fidelity influencing the projection of individual climate variables differently. Presented here is a new approach, termed the "Intelligent Ensemble, that constructs climate variable projections by weighting each model according to its ability to represent key physical processes, e.g., precipitation probability distribution. This approach provides added value over the equal weighted average method. Physical process metrics applied in the "Intelligent Ensemble" method are created using a combination of NASA and NOAA satellite and surface-based cloud, radiation, temperature, and precipitation data sets. The "Intelligent Ensemble" method is applied to the RCP4.5 and RCP8.5 anthropogenic climate forcing simulations within the CMIP5 archive to develop a set of climate change scenarios for precipitation, temperature, and surface solar radiation in each USDA Farm Resource Region for use in climate change adaptation studies.

Identifying Outliers of Non-Gaussian Groundwater State Data Based on Ensemble Estimation for Long-Term Trends

NASA Astrophysics Data System (ADS)

Park, E.; Jeong, J.; Choi, J.; Han, W. S.; Yun, S. T.

2016-12-01

Three modified outlier identification methods: the three sigma rule (3s), inter quantile range (IQR) and median absolute deviation (MAD), which take advantage of the ensemble regression method are proposed. For validation purposes, the performance of the methods is compared using simulated and actual groundwater data with a few hypothetical conditions. In the validations using simulated data, all of the proposed methods reasonably identify outliers at a 5% outlier level; whereas, only the IQR method performs well for identifying outliers at a 30% outlier level. When applying the methods to real groundwater data, the outlier identification performance of the IQR method is found to be superior to the other two methods. However, the IQR method is found to have a limitation in the false identification of excessive outliers, which may be supplemented by joint applications with the other methods (i.e., the 3s rule and MAD methods). The proposed methods can be also applied as a potential tool for future anomaly detection by model training based on currently available data.

Multivariate localization methods for ensemble Kalman filtering

NASA Astrophysics Data System (ADS)

Roh, S.; Jun, M.; Szunyogh, I.; Genton, M. G.

2015-12-01

In ensemble Kalman filtering (EnKF), the small number of ensemble members that is feasible to use in a practical data assimilation application leads to sampling variability of the estimates of the background error covariances. The standard approach to reducing the effects of this sampling variability, which has also been found to be highly efficient in improving the performance of EnKF, is the localization of the estimates of the covariances. One family of localization techniques is based on taking the Schur (element-wise) product of the ensemble-based sample covariance matrix and a correlation matrix whose entries are obtained by the discretization of a distance-dependent correlation function. While the proper definition of the localization function for a single state variable has been extensively investigated, a rigorous definition of the localization function for multiple state variables that exist at the same locations has been seldom considered. This paper introduces two strategies for the construction of localization functions for multiple state variables. The proposed localization functions are tested by assimilating simulated observations experiments into the bivariate Lorenz 95 model with their help.

iACP-GAEnsC: Evolutionary genetic algorithm based ensemble classification of anticancer peptides by utilizing hybrid feature space.

PubMed

Akbar, Shahid; Hayat, Maqsood; Iqbal, Muhammad; Jan, Mian Ahmad

2017-06-01

Cancer is a fatal disease, responsible for one-quarter of all deaths in developed countries. Traditional anticancer therapies such as, chemotherapy and radiation, are highly expensive, susceptible to errors and ineffective techniques. These conventional techniques induce severe side-effects on human cells. Due to perilous impact of cancer, the development of an accurate and highly efficient intelligent computational model is desirable for identification of anticancer peptides. In this paper, evolutionary intelligent genetic algorithm-based ensemble model, 'iACP-GAEnsC', is proposed for the identification of anticancer peptides. In this model, the protein sequences are formulated, using three different discrete feature representation methods, i.e., amphiphilic Pseudo amino acid composition, g-Gap dipeptide composition, and Reduce amino acid alphabet composition. The performance of the extracted feature spaces are investigated separately and then merged to exhibit the significance of hybridization. In addition, the predicted results of individual classifiers are combined together, using optimized genetic algorithm and simple majority technique in order to enhance the true classification rate. It is observed that genetic algorithm-based ensemble classification outperforms than individual classifiers as well as simple majority voting base ensemble. The performance of genetic algorithm-based ensemble classification is highly reported on hybrid feature space, with an accuracy of 96.45%. In comparison to the existing techniques, 'iACP-GAEnsC' model has achieved remarkable improvement in terms of various performance metrics. Based on the simulation results, it is observed that 'iACP-GAEnsC' model might be a leading tool in the field of drug design and proteomics for researchers. Copyright © 2017 Elsevier B.V. All rights reserved.

From climate model ensembles to climate change impacts and adaptation: A case study of water resource management in the southwest of England

NASA Astrophysics Data System (ADS)

Lopez, Ana; Fung, Fai; New, Mark; Watts, Glenn; Weston, Alan; Wilby, Robert L.

2009-08-01

The majority of climate change impacts and adaptation studies so far have been based on at most a few deterministic realizations of future climate, usually representing different emissions scenarios. Large ensembles of climate models are increasingly available either as ensembles of opportunity or perturbed physics ensembles, providing a wealth of additional data that is potentially useful for improving adaptation strategies to climate change. Because of the novelty of this ensemble information, there is little previous experience of practical applications or of the added value of this information for impacts and adaptation decision making. This paper evaluates the value of perturbed physics ensembles of climate models for understanding and planning public water supply under climate change. We deliberately select water resource models that are already used by water supply companies and regulators on the assumption that uptake of information from large ensembles of climate models will be more likely if it does not involve significant investment in new modeling tools and methods. We illustrate the methods with a case study on the Wimbleball water resource zone in the southwest of England. This zone is sufficiently simple to demonstrate the utility of the approach but with enough complexity to allow a variety of different decisions to be made. Our research shows that the additional information contained in the climate model ensemble provides a better understanding of the possible ranges of future conditions, compared to the use of single-model scenarios. Furthermore, with careful presentation, decision makers will find the results from large ensembles of models more accessible and be able to more easily compare the merits of different management options and the timing of different adaptation. The overhead in additional time and expertise for carrying out the impacts analysis will be justified by the increased quality of the decision-making process. We remark that even though we have focused our study on a water resource system in the United Kingdom, our conclusions about the added value of climate model ensembles in guiding adaptation decisions can be generalized to other sectors and geographical regions.

Laser transit anemometer software development program

NASA Technical Reports Server (NTRS)

Abbiss, John B.

1989-01-01

Algorithms were developed for the extraction of two components of mean velocity, standard deviation, and the associated correlation coefficient from laser transit anemometry (LTA) data ensembles. The solution method is based on an assumed two-dimensional Gaussian probability density function (PDF) model of the flow field under investigation. The procedure consists of transforming the data ensembles from the data acquisition domain (consisting of time and angle information) to the velocity space domain (consisting of velocity component information). The mean velocity results are obtained from the data ensemble centroid. Through a least squares fitting of the transformed data to an ellipse representing the intersection of a plane with the PDF, the standard deviations and correlation coefficient are obtained. A data set simulation method is presented to test the data reduction process. Results of using the simulation system with a limited test matrix of input values is also given.

The wisdom of the commons: ensemble tree classifiers for prostate cancer prognosis.

PubMed

Koziol, James A; Feng, Anne C; Jia, Zhenyu; Wang, Yipeng; Goodison, Seven; McClelland, Michael; Mercola, Dan

2009-01-01

Classification and regression trees have long been used for cancer diagnosis and prognosis. Nevertheless, instability and variable selection bias, as well as overfitting, are well-known problems of tree-based methods. In this article, we investigate whether ensemble tree classifiers can ameliorate these difficulties, using data from two recent studies of radical prostatectomy in prostate cancer. Using time to progression following prostatectomy as the relevant clinical endpoint, we found that ensemble tree classifiers robustly and reproducibly identified three subgroups of patients in the two clinical datasets: non-progressors, early progressors and late progressors. Moreover, the consensus classifications were independent predictors of time to progression compared to known clinical prognostic factors.

Filter Bank Regularized Common Spatial Pattern Ensemble for Small Sample Motor Imagery Classification.

PubMed

Park, Sang-Hoon; Lee, David; Lee, Sang-Goog

2018-02-01

For the last few years, many feature extraction methods have been proposed based on biological signals. Among these, the brain signals have the advantage that they can be obtained, even by people with peripheral nervous system damage. Motor imagery electroencephalograms (EEG) are inexpensive to measure, offer a high temporal resolution, and are intuitive. Therefore, these have received a significant amount of attention in various fields, including signal processing, cognitive science, and medicine. The common spatial pattern (CSP) algorithm is a useful method for feature extraction from motor imagery EEG. However, performance degradation occurs in a small-sample setting (SSS), because the CSP depends on sample-based covariance. Since the active frequency range is different for each subject, it is also inconvenient to set the frequency range to be different every time. In this paper, we propose the feature extraction method based on a filter bank to solve these problems. The proposed method consists of five steps. First, motor imagery EEG is divided by a using filter bank. Second, the regularized CSP (R-CSP) is applied to the divided EEG. Third, we select the features according to mutual information based on the individual feature algorithm. Fourth, parameter sets are selected for the ensemble. Finally, we classify using ensemble based on features. The brain-computer interface competition III data set IVa is used to evaluate the performance of the proposed method. The proposed method improves the mean classification accuracy by 12.34%, 11.57%, 9%, 4.95%, and 4.47% compared with CSP, SR-CSP, R-CSP, filter bank CSP (FBCSP), and SR-FBCSP. Compared with the filter bank R-CSP ( , ), which is a parameter selection version of the proposed method, the classification accuracy is improved by 3.49%. In particular, the proposed method shows a large improvement in performance in the SSS.

Fault detection of the connection of lithium-ion power batteries based on entropy for electric vehicles

NASA Astrophysics Data System (ADS)

Yao, Lei; Wang, Zhenpo; Ma, Jun

2015-10-01

This paper proposes a method of fault detection of the connection of Lithium-Ion batteries based on entropy for electric vehicle. In electric vehicle operation process, some factors, such as road conditions, driving habits, vehicle performance, always affect batteries by vibration, which easily cause loosing or virtual connection between batteries. Through the simulation of the battery charging and discharging experiment under vibration environment, the data of voltage fluctuation can be obtained. Meanwhile, an optimal filtering method is adopted using discrete cosine filter method to analyze the characteristics of system noise, based on the voltage set when batteries are working under different vibration frequency. Experimental data processed by filtering is analyzed based on local Shannon entropy, ensemble Shannon entropy and sample entropy. And the best way to find a method of fault detection of the connection of lithium-ion batteries based on entropy is presented for electric vehicle. The experimental data shows that ensemble Shannon entropy can predict the accurate time and the location of battery connection failure in real time. Besides electric-vehicle industry, this method can also be used in other areas in complex vibration environment.

A Statistical Description of Neural Ensemble Dynamics

PubMed Central

Long, John D.; Carmena, Jose M.

2011-01-01

The growing use of multi-channel neural recording techniques in behaving animals has produced rich datasets that hold immense potential for advancing our understanding of how the brain mediates behavior. One limitation of these techniques is they do not provide important information about the underlying anatomical connections among the recorded neurons within an ensemble. Inferring these connections is often intractable because the set of possible interactions grows exponentially with ensemble size. This is a fundamental challenge one confronts when interpreting these data. Unfortunately, the combination of expert knowledge and ensemble data is often insufficient for selecting a unique model of these interactions. Our approach shifts away from modeling the network diagram of the ensemble toward analyzing changes in the dynamics of the ensemble as they relate to behavior. Our contribution consists of adapting techniques from signal processing and Bayesian statistics to track the dynamics of ensemble data on time-scales comparable with behavior. We employ a Bayesian estimator to weigh prior information against the available ensemble data, and use an adaptive quantization technique to aggregate poorly estimated regions of the ensemble data space. Importantly, our method is capable of detecting changes in both the magnitude and structure of correlations among neurons missed by firing rate metrics. We show that this method is scalable across a wide range of time-scales and ensemble sizes. Lastly, the performance of this method on both simulated and real ensemble data is used to demonstrate its utility. PMID:22319486

The Upper and Lower Bounds of the Prediction Accuracies of Ensemble Methods for Binary Classification

PubMed Central

Wang, Xueyi; Davidson, Nicholas J.

2011-01-01

Ensemble methods have been widely used to improve prediction accuracy over individual classifiers. In this paper, we achieve a few results about the prediction accuracies of ensemble methods for binary classification that are missed or misinterpreted in previous literature. First we show the upper and lower bounds of the prediction accuracies (i.e. the best and worst possible prediction accuracies) of ensemble methods. Next we show that an ensemble method can achieve > 0.5 prediction accuracy, while individual classifiers have < 0.5 prediction accuracies. Furthermore, for individual classifiers with different prediction accuracies, the average of the individual accuracies determines the upper and lower bounds. We perform two experiments to verify the results and show that it is hard to achieve the upper and lower bounds accuracies by random individual classifiers and better algorithms need to be developed. PMID:21853162

Training in cortical control of neuroprosthetic devices improves signal extraction from small neuronal ensembles.

PubMed

Helms Tillery, S I; Taylor, D M; Schwartz, A B

2003-01-01

We have recently developed a closed-loop environment in which we can test the ability of primates to control the motion of a virtual device using ensembles of simultaneously recorded neurons /29/. Here we use a maximum likelihood method to assess the information about task performance contained in the neuronal ensemble. We trained two animals to control the motion of a computer cursor in three dimensions. Initially the animals controlled cursor motion using arm movements, but eventually they learned to drive the cursor directly from cortical activity. Using a population vector (PV) based upon the relation between cortical activity and arm motion, the animals were able to control the cursor directly from the brain in a closed-loop environment, but with difficulty. We added a supervised learning method that modified the parameters of the PV according to task performance (adaptive PV), and found that animals were able to exert much finer control over the cursor motion from brain signals. Here we describe a maximum likelihood method (ML) to assess the information about target contained in neuronal ensemble activity. Using this method, we compared the information about target contained in the ensemble during arm control, during brain control early in the adaptive PV, and during brain control after the adaptive PV had settled and the animal could drive the cursor reliably and with fine gradations. During the arm-control task, the ML was able to determine the target of the movement in as few as 10% of the trials, and as many as 75% of the trials, with an average of 65%. This average dropped when the animals used a population vector to control motion of the cursor. On average we could determine the target in around 35% of the trials. This low percentage was also reflected in poor control of the cursor, so that the animal was unable to reach the target in a large percentage of trials. Supervised adjustment of the population vector parameters produced new weighting coefficients and directional tuning parameters for many neurons. This produced a much better performance of the brain-controlled cursor motion. It was also reflected in the maximum likelihood measure of cell activity, producing the correct target based only on neuronal activity in over 80% of the trials on average. The changes in maximum likelihood estimates of target location based on ensemble firing show that an animal's ability to regulate the motion of a cortically controlled device is not crucially dependent on the experimenter's ability to estimate intention from neuronal activity.

A Probabilistic Collocation Based Iterative Kalman Filter for Landfill Data Assimilation

NASA Astrophysics Data System (ADS)

Qiang, Z.; Zeng, L.; Wu, L.

2016-12-01

Due to the strong spatial heterogeneity of landfill, uncertainty is ubiquitous in gas transport process in landfill. To accurately characterize the landfill properties, the ensemble Kalman filter (EnKF) has been employed to assimilate the measurements, e.g., the gas pressure. As a Monte Carlo (MC) based method, the EnKF usually requires a large ensemble size, which poses a high computational cost for large scale problems. In this work, we propose a probabilistic collocation based iterative Kalman filter (PCIKF) to estimate permeability in a liquid-gas coupling model. This method employs polynomial chaos expansion (PCE) to represent and propagate the uncertainties of model parameters and states, and an iterative form of Kalman filter to assimilate the current gas pressure data. To further reduce the computation cost, the functional ANOVA (analysis of variance) decomposition is conducted, and only the first order ANOVA components are remained for PCE. Illustrated with numerical case studies, this proposed method shows significant superiority in computation efficiency compared with the traditional MC based iterative EnKF. The developed method has promising potential in reliable prediction and management of landfill gas production.

Artificial neural networks for efficient clustering of conformational ensembles and their potential for medicinal chemistry.

PubMed

Pandini, Alessandro; Fraccalvieri, Domenico; Bonati, Laura

2013-01-01

The biological function of proteins is strictly related to their molecular flexibility and dynamics: enzymatic activity, protein-protein interactions, ligand binding and allosteric regulation are important mechanisms involving protein motions. Computational approaches, such as Molecular Dynamics (MD) simulations, are now routinely used to study the intrinsic dynamics of target proteins as well as to complement molecular docking approaches. These methods have also successfully supported the process of rational design and discovery of new drugs. Identification of functionally relevant conformations is a key step in these studies. This is generally done by cluster analysis of the ensemble of structures in the MD trajectory. Recently Artificial Neural Network (ANN) approaches, in particular methods based on Self-Organising Maps (SOMs), have been reported performing more accurately and providing more consistent results than traditional clustering algorithms in various data-mining problems. In the specific case of conformational analysis, SOMs have been successfully used to compare multiple ensembles of protein conformations demonstrating a potential in efficiently detecting the dynamic signatures central to biological function. Moreover, examples of the use of SOMs to address problems relevant to other stages of the drug-design process, including clustering of docking poses, have been reported. In this contribution we review recent applications of ANN algorithms in analysing conformational and structural ensembles and we discuss their potential in computer-based approaches for medicinal chemistry.

Representing radar rainfall uncertainty with ensembles based on a time-variant geostatistical error modelling approach

NASA Astrophysics Data System (ADS)

Cecinati, Francesca; Rico-Ramirez, Miguel Angel; Heuvelink, Gerard B. M.; Han, Dawei

2017-05-01

The application of radar quantitative precipitation estimation (QPE) to hydrology and water quality models can be preferred to interpolated rainfall point measurements because of the wide coverage that radars can provide, together with a good spatio-temporal resolutions. Nonetheless, it is often limited by the proneness of radar QPE to a multitude of errors. Although radar errors have been widely studied and techniques have been developed to correct most of them, residual errors are still intrinsic in radar QPE. An estimation of uncertainty of radar QPE and an assessment of uncertainty propagation in modelling applications is important to quantify the relative importance of the uncertainty associated to radar rainfall input in the overall modelling uncertainty. A suitable tool for this purpose is the generation of radar rainfall ensembles. An ensemble is the representation of the rainfall field and its uncertainty through a collection of possible alternative rainfall fields, produced according to the observed errors, their spatial characteristics, and their probability distribution. The errors are derived from a comparison between radar QPE and ground point measurements. The novelty of the proposed ensemble generator is that it is based on a geostatistical approach that assures a fast and robust generation of synthetic error fields, based on the time-variant characteristics of errors. The method is developed to meet the requirement of operational applications to large datasets. The method is applied to a case study in Northern England, using the UK Met Office NIMROD radar composites at 1 km resolution and at 1 h accumulation on an area of 180 km by 180 km. The errors are estimated using a network of 199 tipping bucket rain gauges from the Environment Agency. 183 of the rain gauges are used for the error modelling, while 16 are kept apart for validation. The validation is done by comparing the radar rainfall ensemble with the values recorded by the validation rain gauges. The validated ensemble is then tested on a hydrological case study, to show the advantage of probabilistic rainfall for uncertainty propagation. The ensemble spread only partially captures the mismatch between the modelled and the observed flow. The residual uncertainty can be attributed to other sources of uncertainty, in particular to model structural uncertainty, parameter identification uncertainty, uncertainty in other inputs, and uncertainty in the observed flow.

Significance of model credibility in estimating climate projection distributions for regional hydroclimatological risk assessments

USGS Publications Warehouse

Brekke, L.D.; Dettinger, M.D.; Maurer, E.P.; Anderson, M.

2008-01-01

Ensembles of historical climate simulations and climate projections from the World Climate Research Programme's (WCRP's) Coupled Model Intercomparison Project phase 3 (CMIP3) multi-model dataset were investigated to determine how model credibility affects apparent relative scenario likelihoods in regional risk assessments. Methods were developed and applied in a Northern California case study. An ensemble of 59 twentieth century climate simulations from 17 WCRP CMIP3 models was analyzed to evaluate relative model credibility associated with a 75-member projection ensemble from the same 17 models. Credibility was assessed based on how models realistically reproduced selected statistics of historical climate relevant to California climatology. Metrics of this credibility were used to derive relative model weights leading to weight-threshold culling of models contributing to the projection ensemble. Density functions were then estimated for two projected quantities (temperature and precipitation), with and without considering credibility-based ensemble reductions. An analysis for Northern California showed that, while some models seem more capable at recreating limited aspects twentieth century climate, the overall tendency is for comparable model performance when several credibility measures are combined. Use of these metrics to decide which models to include in density function development led to local adjustments to function shapes, but led to limited affect on breadth and central tendency, which were found to be more influenced by 'completeness' of the original ensemble in terms of models and emissions pathways. ?? 2007 Springer Science+Business Media B.V.

An 'Observational Large Ensemble' to compare observed and modeled temperature trend uncertainty due to internal variability.

NASA Astrophysics Data System (ADS)

Poppick, A. N.; McKinnon, K. A.; Dunn-Sigouin, E.; Deser, C.

2017-12-01

Initial condition climate model ensembles suggest that regional temperature trends can be highly variable on decadal timescales due to characteristics of internal climate variability. Accounting for trend uncertainty due to internal variability is therefore necessary to contextualize recent observed temperature changes. However, while the variability of trends in a climate model ensemble can be evaluated directly (as the spread across ensemble members), internal variability simulated by a climate model may be inconsistent with observations. Observation-based methods for assessing the role of internal variability on trend uncertainty are therefore required. Here, we use a statistical resampling approach to assess trend uncertainty due to internal variability in historical 50-year (1966-2015) winter near-surface air temperature trends over North America. We compare this estimate of trend uncertainty to simulated trend variability in the NCAR CESM1 Large Ensemble (LENS), finding that uncertainty in wintertime temperature trends over North America due to internal variability is largely overestimated by CESM1, on average by a factor of 32%. Our observation-based resampling approach is combined with the forced signal from LENS to produce an 'Observational Large Ensemble' (OLENS). The members of OLENS indicate a range of spatially coherent fields of temperature trends resulting from different sequences of internal variability consistent with observations. The smaller trend variability in OLENS suggests that uncertainty in the historical climate change signal in observations due to internal variability is less than suggested by LENS.

Scalable and balanced dynamic hybrid data assimilation

NASA Astrophysics Data System (ADS)

Kauranne, Tuomo; Amour, Idrissa; Gunia, Martin; Kallio, Kari; Lepistö, Ahti; Koponen, Sampsa

2017-04-01

Scalability of complex weather forecasting suites is dependent on the technical tools available for implementing highly parallel computational kernels, but to an equally large extent also on the dependence patterns between various components of the suite, such as observation processing, data assimilation and the forecast model. Scalability is a particular challenge for 4D variational assimilation methods that necessarily couple the forecast model into the assimilation process and subject this combination to an inherently serial quasi-Newton minimization process. Ensemble based assimilation methods are naturally more parallel, but large models force ensemble sizes to be small and that results in poor assimilation accuracy, somewhat akin to shooting with a shotgun in a million-dimensional space. The Variational Ensemble Kalman Filter (VEnKF) is an ensemble method that can attain the accuracy of 4D variational data assimilation with a small ensemble size. It achieves this by processing a Gaussian approximation of the current error covariance distribution, instead of a set of ensemble members, analogously to the Extended Kalman Filter EKF. Ensemble members are re-sampled every time a new set of observations is processed from a new approximation of that Gaussian distribution which makes VEnKF a dynamic assimilation method. After this a smoothing step is applied that turns VEnKF into a dynamic Variational Ensemble Kalman Smoother VEnKS. In this smoothing step, the same process is iterated with frequent re-sampling of the ensemble but now using past iterations as surrogate observations until the end result is a smooth and balanced model trajectory. In principle, VEnKF could suffer from similar scalability issues as 4D-Var. However, this can be avoided by isolating the forecast model completely from the minimization process by implementing the latter as a wrapper code whose only link to the model is calling for many parallel and totally independent model runs, all of them implemented as parallel model runs themselves. The only bottleneck in the process is the gathering and scattering of initial and final model state snapshots before and after the parallel runs which requires a very efficient and low-latency communication network. However, the volume of data communicated is small and the intervening minimization steps are only 3D-Var, which means their computational load is negligible compared with the fully parallel model runs. We present example results of scalable VEnKF with the 4D lake and shallow sea model COHERENS, assimilating simultaneously continuous in situ measurements in a single point and infrequent satellite images that cover a whole lake, with the fully scalable VEnKF.

Ideas for a pattern-oriented approach towards a VERA analysis ensemble

NASA Astrophysics Data System (ADS)

Gorgas, T.; Dorninger, M.

2010-09-01

Ideas for a pattern-oriented approach towards a VERA analysis ensemble For many applications in meteorology and especially for verification purposes it is important to have some information about the uncertainties of observation and analysis data. A high quality of these "reference data" is an absolute necessity as the uncertainties are reflected in verification measures. The VERA (Vienna Enhanced Resolution Analysis) scheme includes a sophisticated quality control tool which accounts for the correction of observational data and provides an estimation of the observation uncertainty. It is crucial for meteorologically and physically reliable analysis fields. VERA is based on a variational principle and does not need any first guess fields. It is therefore NWP model independent and can also be used as an unbiased reference for real time model verification. For downscaling purposes VERA uses an a priori knowledge on small-scale physical processes over complex terrain, the so called "fingerprint technique", which transfers information from rich to data sparse regions. The enhanced Joint D-PHASE and COPS data set forms the data base for the analysis ensemble study. For the WWRP projects D-PHASE and COPS a joint activity has been started to collect GTS and non-GTS data from the national and regional meteorological services in Central Europe for 2007. Data from more than 11.000 stations are available for high resolution analyses. The usage of random numbers as perturbations for ensemble experiments is a common approach in meteorology. In most implementations, like for NWP-model ensemble systems, the focus lies on error growth and propagation on the spatial and temporal scale. When defining errors in analysis fields we have to consider the fact that analyses are not time dependent and that no perturbation method aimed at temporal evolution is possible. Further, the method applied should respect two major sources of analysis errors: Observation errors AND analysis or interpolation errors. With the concept of an analysis ensemble we hope to get a more detailed sight on both sources of analysis errors. For the computation of the VERA ensemble members a sample of Gaussian random perturbations is produced for each station and parameter. The deviation of perturbations is based on the correction proposals by the VERA QC scheme to provide some "natural" limits for the ensemble. In order to put more emphasis on the weather situation we aim to integrate the main synoptic field structures as weighting factors for the perturbations. Two widely approved approaches are used for the definition of these main field structures: The Principal Component Analysis and a 2D-Discrete Wavelet Transform. The results of tests concerning the implementation of this pattern-supported analysis ensemble system and a comparison of the different approaches are given in the presentation.

Concrete ensemble Kalman filters with rigorous catastrophic filter divergence

PubMed Central

Kelly, David; Majda, Andrew J.; Tong, Xin T.

2015-01-01

The ensemble Kalman filter and ensemble square root filters are data assimilation methods used to combine high-dimensional, nonlinear dynamical models with observed data. Ensemble methods are indispensable tools in science and engineering and have enjoyed great success in geophysical sciences, because they allow for computationally cheap low-ensemble-state approximation for extremely high-dimensional turbulent forecast models. From a theoretical perspective, the dynamical properties of these methods are poorly understood. One of the central mysteries is the numerical phenomenon known as catastrophic filter divergence, whereby ensemble-state estimates explode to machine infinity, despite the true state remaining in a bounded region. In this article we provide a breakthrough insight into the phenomenon, by introducing a simple and natural forecast model that transparently exhibits catastrophic filter divergence under all ensemble methods and a large set of initializations. For this model, catastrophic filter divergence is not an artifact of numerical instability, but rather a true dynamical property of the filter. The divergence is not only validated numerically but also proven rigorously. The model cleanly illustrates mechanisms that give rise to catastrophic divergence and confirms intuitive accounts of the phenomena given in past literature. PMID:26261335

Concrete ensemble Kalman filters with rigorous catastrophic filter divergence.

PubMed

Kelly, David; Majda, Andrew J; Tong, Xin T

2015-08-25

The ensemble Kalman filter and ensemble square root filters are data assimilation methods used to combine high-dimensional, nonlinear dynamical models with observed data. Ensemble methods are indispensable tools in science and engineering and have enjoyed great success in geophysical sciences, because they allow for computationally cheap low-ensemble-state approximation for extremely high-dimensional turbulent forecast models. From a theoretical perspective, the dynamical properties of these methods are poorly understood. One of the central mysteries is the numerical phenomenon known as catastrophic filter divergence, whereby ensemble-state estimates explode to machine infinity, despite the true state remaining in a bounded region. In this article we provide a breakthrough insight into the phenomenon, by introducing a simple and natural forecast model that transparently exhibits catastrophic filter divergence under all ensemble methods and a large set of initializations. For this model, catastrophic filter divergence is not an artifact of numerical instability, but rather a true dynamical property of the filter. The divergence is not only validated numerically but also proven rigorously. The model cleanly illustrates mechanisms that give rise to catastrophic divergence and confirms intuitive accounts of the phenomena given in past literature.

Long-term ensemble forecast of snowmelt inflow into the Cheboksary Reservoir under two different weather scenarios

NASA Astrophysics Data System (ADS)

Gelfan, Alexander; Moreydo, Vsevolod; Motovilov, Yury; Solomatine, Dimitri P.

2018-04-01

A long-term forecasting ensemble methodology, applied to water inflows into the Cheboksary Reservoir (Russia), is presented. The methodology is based on a version of the semi-distributed hydrological model ECOMAG (ECOlogical Model for Applied Geophysics) that allows for the calculation of an ensemble of inflow hydrographs using two different sets of weather ensembles for the lead time period: observed weather data, constructed on the basis of the Ensemble Streamflow Prediction methodology (ESP-based forecast), and synthetic weather data, simulated by a multi-site weather generator (WG-based forecast). We have studied the following: (1) whether there is any advantage of the developed ensemble forecasts in comparison with the currently issued operational forecasts of water inflow into the Cheboksary Reservoir, and (2) whether there is any noticeable improvement in probabilistic forecasts when using the WG-simulated ensemble compared to the ESP-based ensemble. We have found that for a 35-year period beginning from the reservoir filling in 1982, both continuous and binary model-based ensemble forecasts (issued in the deterministic form) outperform the operational forecasts of the April-June inflow volume actually used and, additionally, provide acceptable forecasts of additional water regime characteristics besides the inflow volume. We have also demonstrated that the model performance measures (in the verification period) obtained from the WG-based probabilistic forecasts, which are based on a large number of possible weather scenarios, appeared to be more statistically reliable than the corresponding measures calculated from the ESP-based forecasts based on the observed weather scenarios.

Ensemble-based prediction of RNA secondary structures.

PubMed

Aghaeepour, Nima; Hoos, Holger H

2013-04-24

Accurate structure prediction methods play an important role for the understanding of RNA function. Energy-based, pseudoknot-free secondary structure prediction is one of the most widely used and versatile approaches, and improved methods for this task have received much attention over the past five years. Despite the impressive progress that as been achieved in this area, existing evaluations of the prediction accuracy achieved by various algorithms do not provide a comprehensive, statistically sound assessment. Furthermore, while there is increasing evidence that no prediction algorithm consistently outperforms all others, no work has been done to exploit the complementary strengths of multiple approaches. In this work, we present two contributions to the area of RNA secondary structure prediction. Firstly, we use state-of-the-art, resampling-based statistical methods together with a previously published and increasingly widely used dataset of high-quality RNA structures to conduct a comprehensive evaluation of existing RNA secondary structure prediction procedures. The results from this evaluation clarify the performance relationship between ten well-known existing energy-based pseudoknot-free RNA secondary structure prediction methods and clearly demonstrate the progress that has been achieved in recent years. Secondly, we introduce AveRNA, a generic and powerful method for combining a set of existing secondary structure prediction procedures into an ensemble-based method that achieves significantly higher prediction accuracies than obtained from any of its component procedures. Our new, ensemble-based method, AveRNA, improves the state of the art for energy-based, pseudoknot-free RNA secondary structure prediction by exploiting the complementary strengths of multiple existing prediction procedures, as demonstrated using a state-of-the-art statistical resampling approach. In addition, AveRNA allows an intuitive and effective control of the trade-off between false negative and false positive base pair predictions. Finally, AveRNA can make use of arbitrary sets of secondary structure prediction procedures and can therefore be used to leverage improvements in prediction accuracy offered by algorithms and energy models developed in the future. Our data, MATLAB software and a web-based version of AveRNA are publicly available at http://www.cs.ubc.ca/labs/beta/Software/AveRNA.

Weaving colloidal webs around droplets: spontaneous assembly of extended colloidal networks encasing microfluidic droplet ensembles.

PubMed

Zheng, Lu; Ho, Leon Yoon; Khan, Saif A

2016-10-26

The ability to form transient, self-assembling solid networks that 'cocoon' emulsion droplets on-demand allows new possibilities in the rapidly expanding area of microfluidic droplet-based materials science. In this communication, we demonstrate the spontaneous formation of extended colloidal networks that encase large microfluidic droplet ensembles, thus completely arresting droplet motion and effectively isolating each droplet from others in the ensemble. To do this, we employ molecular inclusion complexes of β-cyclodextrin, which spontaneously form and assemble into colloidal solids at the droplet interface and beyond, via the outward diffusion of a guest molecule (dichloromethane) from the droplets. We illustrate the advantage of such transient network-based droplet stabilization in the area of pharmaceutical crystallization, where we are able to fabricate monodisperse spherical crystalline microgranules of 5-methyl-2-[(2-nitrophenyl)amino]-3-thiophenecarbonitrile (ROY), a model hydrophobic drug, with a dramatic enhancement of particle properties compared to conventional methods.

Verification of ECMWF System 4 for seasonal hydrological forecasting in a northern climate

NASA Astrophysics Data System (ADS)

Bazile, Rachel; Boucher, Marie-Amélie; Perreault, Luc; Leconte, Robert

2017-11-01

Hydropower production requires optimal dam and reservoir management to prevent flooding damage and avoid operation losses. In a northern climate, where spring freshet constitutes the main inflow volume, seasonal forecasts can help to establish a yearly strategy. Long-term hydrological forecasts often rely on past observations of streamflow or meteorological data. Another alternative is to use ensemble meteorological forecasts produced by climate models. In this paper, those produced by the ECMWF (European Centre for Medium-Range Forecast) System 4 are examined and bias is characterized. Bias correction, through the linear scaling method, improves the performance of the raw ensemble meteorological forecasts in terms of continuous ranked probability score (CRPS). Then, three seasonal ensemble hydrological forecasting systems are compared: (1) the climatology of simulated streamflow, (2) the ensemble hydrological forecasts based on climatology (ESP) and (3) the hydrological forecasts based on bias-corrected ensemble meteorological forecasts from System 4 (corr-DSP). Simulated streamflow computed using observed meteorological data is used as benchmark. Accounting for initial conditions is valuable even for long-term forecasts. ESP and corr-DSP both outperform the climatology of simulated streamflow for lead times from 1 to 5 months depending on the season and watershed. Integrating information about future meteorological conditions also improves monthly volume forecasts. For the 1-month lead time, a gain exists for almost all watersheds during winter, summer and fall. However, volume forecasts performance for spring varies from one watershed to another. For most of them, the performance is close to the performance of ESP. For longer lead times, the CRPS skill score is mostly in favour of ESP, even if for many watersheds, ESP and corr-DSP have comparable skill. Corr-DSP appears quite reliable but, in some cases, under-dispersion or bias is observed. A more complex bias-correction method should be further investigated to remedy this weakness and take more advantage of the ensemble forecasts produced by the climate model. Overall, in this study, bias-corrected ensemble meteorological forecasts appear to be an interesting source of information for hydrological forecasting for lead times up to 1 month. They could also complement ESP for longer lead times.

Predicting diabetes mellitus using SMOTE and ensemble machine learning approach: The Henry Ford ExercIse Testing (FIT) project.

PubMed

Alghamdi, Manal; Al-Mallah, Mouaz; Keteyian, Steven; Brawner, Clinton; Ehrman, Jonathan; Sakr, Sherif

2017-01-01

Machine learning is becoming a popular and important approach in the field of medical research. In this study, we investigate the relative performance of various machine learning methods such as Decision Tree, Naïve Bayes, Logistic Regression, Logistic Model Tree and Random Forests for predicting incident diabetes using medical records of cardiorespiratory fitness. In addition, we apply different techniques to uncover potential predictors of diabetes. This FIT project study used data of 32,555 patients who are free of any known coronary artery disease or heart failure who underwent clinician-referred exercise treadmill stress testing at Henry Ford Health Systems between 1991 and 2009 and had a complete 5-year follow-up. At the completion of the fifth year, 5,099 of those patients have developed diabetes. The dataset contained 62 attributes classified into four categories: demographic characteristics, disease history, medication use history, and stress test vital signs. We developed an Ensembling-based predictive model using 13 attributes that were selected based on their clinical importance, Multiple Linear Regression, and Information Gain Ranking methods. The negative effect of the imbalance class of the constructed model was handled by Synthetic Minority Oversampling Technique (SMOTE). The overall performance of the predictive model classifier was improved by the Ensemble machine learning approach using the Vote method with three Decision Trees (Naïve Bayes Tree, Random Forest, and Logistic Model Tree) and achieved high accuracy of prediction (AUC = 0.92). The study shows the potential of ensembling and SMOTE approaches for predicting incident diabetes using cardiorespiratory fitness data.

Ensemble flare forecasting: using numerical weather prediction techniques to improve space weather operations

NASA Astrophysics Data System (ADS)

Murray, S.; Guerra, J. A.

2017-12-01

One essential component of operational space weather forecasting is the prediction of solar flares. Early flare forecasting work focused on statistical methods based on historical flaring rates, but more complex machine learning methods have been developed in recent years. A multitude of flare forecasting methods are now available, however it is still unclear which of these methods performs best, and none are substantially better than climatological forecasts. Current operational space weather centres cannot rely on automated methods, and generally use statistical forecasts with a little human intervention. Space weather researchers are increasingly looking towards methods used in terrestrial weather to improve current forecasting techniques. Ensemble forecasting has been used in numerical weather prediction for many years as a way to combine different predictions in order to obtain a more accurate result. It has proved useful in areas such as magnetospheric modelling and coronal mass ejection arrival analysis, however has not yet been implemented in operational flare forecasting. Here we construct ensemble forecasts for major solar flares by linearly combining the full-disk probabilistic forecasts from a group of operational forecasting methods (ASSA, ASAP, MAG4, MOSWOC, NOAA, and Solar Monitor). Forecasts from each method are weighted by a factor that accounts for the method's ability to predict previous events, and several performance metrics (both probabilistic and categorical) are considered. The results provide space weather forecasters with a set of parameters (combination weights, thresholds) that allow them to select the most appropriate values for constructing the 'best' ensemble forecast probability value, according to the performance metric of their choice. In this way different forecasts can be made to fit different end-user needs.

Behavior of Filters and Smoothers for Strongly Nonlinear Dynamics

NASA Technical Reports Server (NTRS)

Zhu, Yanqui; Cohn, Stephen E.; Todling, Ricardo

1999-01-01

The Kalman filter is the optimal filter in the presence of known gaussian error statistics and linear dynamics. Filter extension to nonlinear dynamics is non trivial in the sense of appropriately representing high order moments of the statistics. Monte Carlo, ensemble-based, methods have been advocated as the methodology for representing high order moments without any questionable closure assumptions. Investigation along these lines has been conducted for highly idealized dynamics such as the strongly nonlinear Lorenz model as well as more realistic models of the means and atmosphere. A few relevant issues in this context are related to the necessary number of ensemble members to properly represent the error statistics and, the necessary modifications in the usual filter situations to allow for correct update of the ensemble members. The ensemble technique has also been applied to the problem of smoothing for which similar questions apply. Ensemble smoother examples, however, seem to be quite puzzling in that results state estimates are worse than for their filter analogue. In this study, we use concepts in probability theory to revisit the ensemble methodology for filtering and smoothing in data assimilation. We use the Lorenz model to test and compare the behavior of a variety of implementations of ensemble filters. We also implement ensemble smoothers that are able to perform better than their filter counterparts. A discussion of feasibility of these techniques to large data assimilation problems will be given at the time of the conference.

Improving the accuracy of flood forecasting with transpositions of ensemble NWP rainfall fields considering orographic effects

NASA Astrophysics Data System (ADS)

Yu, Wansik; Nakakita, Eiichi; Kim, Sunmin; Yamaguchi, Kosei

2016-08-01

The use of meteorological ensembles to produce sets of hydrological predictions increased the capability to issue flood warnings. However, space scale of the hydrological domain is still much finer than meteorological model, and NWP models have challenges with displacement. The main objective of this study to enhance the transposition method proposed in Yu et al. (2014) and to suggest the post-processing ensemble flood forecasting method for the real-time updating and the accuracy improvement of flood forecasts that considers the separation of the orographic rainfall and the correction of misplaced rain distributions using additional ensemble information through the transposition of rain distributions. In the first step of the proposed method, ensemble forecast rainfalls from a numerical weather prediction (NWP) model are separated into orographic and non-orographic rainfall fields using atmospheric variables and the extraction of topographic effect. Then the non-orographic rainfall fields are examined by the transposition scheme to produce additional ensemble information and new ensemble NWP rainfall fields are calculated by recombining the transposition results of non-orographic rain fields with separated orographic rainfall fields for a generation of place-corrected ensemble information. Then, the additional ensemble information is applied into a hydrologic model for post-flood forecasting with a 6-h interval. The newly proposed method has a clear advantage to improve the accuracy of mean value of ensemble flood forecasting. Our study is carried out and verified using the largest flood event by typhoon 'Talas' of 2011 over the two catchments, which are Futatsuno (356.1 km2) and Nanairo (182.1 km2) dam catchments of Shingu river basin (2360 km2), which is located in the Kii peninsula, Japan.

Precision bounds for gradient magnetometry with atomic ensembles

NASA Astrophysics Data System (ADS)

Apellaniz, Iagoba; Urizar-Lanz, Iñigo; Zimborás, Zoltán; Hyllus, Philipp; Tóth, Géza

2018-05-01

We study gradient magnetometry with an ensemble of atoms with arbitrary spin. We calculate precision bounds for estimating the gradient of the magnetic field based on the quantum Fisher information. For quantum states that are invariant under homogeneous magnetic fields, we need to measure a single observable to estimate the gradient. On the other hand, for states that are sensitive to homogeneous fields, a simultaneous measurement is needed, as the homogeneous field must also be estimated. We prove that for the cases studied in this paper, such a measurement is feasible. We present a method to calculate precision bounds for gradient estimation with a chain of atoms or with two spatially separated atomic ensembles. We also consider a single atomic ensemble with an arbitrary density profile, where the atoms cannot be addressed individually, and which is a very relevant case for experiments. Our model can take into account even correlations between particle positions. While in most of the discussion we consider an ensemble of localized particles that are classical with respect to their spatial degree of freedom, we also discuss the case of gradient metrology with a single Bose-Einstein condensate.

Proposed hybrid-classifier ensemble algorithm to map snow cover area

NASA Astrophysics Data System (ADS)

Nijhawan, Rahul; Raman, Balasubramanian; Das, Josodhir

2018-01-01

Metaclassification ensemble approach is known to improve the prediction performance of snow-covered area. The methodology adopted in this case is based on neural network along with four state-of-art machine learning algorithms: support vector machine, artificial neural networks, spectral angle mapper, K-mean clustering, and a snow index: normalized difference snow index. An AdaBoost ensemble algorithm related to decision tree for snow-cover mapping is also proposed. According to available literature, these methods have been rarely used for snow-cover mapping. Employing the above techniques, a study was conducted for Raktavarn and Chaturangi Bamak glaciers, Uttarakhand, Himalaya using multispectral Landsat 7 ETM+ (enhanced thematic mapper) image. The study also compares the results with those obtained from statistical combination methods (majority rule and belief functions) and accuracies of individual classifiers. Accuracy assessment is performed by computing the quantity and allocation disagreement, analyzing statistic measures (accuracy, precision, specificity, AUC, and sensitivity) and receiver operating characteristic curves. A total of 225 combinations of parameters for individual classifiers were trained and tested on the dataset and results were compared with the proposed approach. It was observed that the proposed methodology produced the highest classification accuracy (95.21%), close to (94.01%) that was produced by the proposed AdaBoost ensemble algorithm. From the sets of observations, it was concluded that the ensemble of classifiers produced better results compared to individual classifiers.

An Ensemble Approach for Drug Side Effect Prediction

PubMed Central

Jahid, Md Jamiul; Ruan, Jianhua

2014-01-01

In silico prediction of drug side-effects in early stage of drug development is becoming more popular now days, which not only reduces the time for drug design but also reduces the drug development costs. In this article we propose an ensemble approach to predict drug side-effects of drug molecules based on their chemical structure. Our idea originates from the observation that similar drugs have similar side-effects. Based on this observation we design an ensemble approach that combine the results from different classification models where each model is generated by a different set of similar drugs. We applied our approach to 1385 side-effects in the SIDER database for 888 drugs. Results show that our approach outperformed previously published approaches and standard classifiers. Furthermore, we applied our method to a number of uncharacterized drug molecules in DrugBank database and predict their side-effect profiles for future usage. Results from various sources confirm that our method is able to predict the side-effects for uncharacterized drugs and more importantly able to predict rare side-effects which are often ignored by other approaches. The method described in this article can be useful to predict side-effects in drug design in an early stage to reduce experimental cost and time. PMID:25327524

Ensemble Data Assimilation Without Ensembles: Methodology and Application to Ocean Data Assimilation

NASA Technical Reports Server (NTRS)

Keppenne, Christian L.; Rienecker, Michele M.; Kovach, Robin M.; Vernieres, Guillaume

2013-01-01

Two methods to estimate background error covariances for data assimilation are introduced. While both share properties with the ensemble Kalman filter (EnKF), they differ from it in that they do not require the integration of multiple model trajectories. Instead, all the necessary covariance information is obtained from a single model integration. The first method is referred-to as SAFE (Space Adaptive Forecast error Estimation) because it estimates error covariances from the spatial distribution of model variables within a single state vector. It can thus be thought of as sampling an ensemble in space. The second method, named FAST (Flow Adaptive error Statistics from a Time series), constructs an ensemble sampled from a moving window along a model trajectory. The underlying assumption in these methods is that forecast errors in data assimilation are primarily phase errors in space and/or time.

On the statistical equivalence of restrained-ensemble simulations with the maximum entropy method

PubMed Central

Roux, Benoît; Weare, Jonathan

2013-01-01

An issue of general interest in computer simulations is to incorporate information from experiments into a structural model. An important caveat in pursuing this goal is to avoid corrupting the resulting model with spurious and arbitrary biases. While the problem of biasing thermodynamic ensembles can be formulated rigorously using the maximum entropy method introduced by Jaynes, the approach can be cumbersome in practical applications with the need to determine multiple unknown coefficients iteratively. A popular alternative strategy to incorporate the information from experiments is to rely on restrained-ensemble molecular dynamics simulations. However, the fundamental validity of this computational strategy remains in question. Here, it is demonstrated that the statistical distribution produced by restrained-ensemble simulations is formally consistent with the maximum entropy method of Jaynes. This clarifies the underlying conditions under which restrained-ensemble simulations will yield results that are consistent with the maximum entropy method. PMID:23464140

Genetic programming based ensemble system for microarray data classification.

PubMed

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved.

Genetic Programming Based Ensemble System for Microarray Data Classification

PubMed Central

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved. PMID:25810748

An Effective Antifreeze Protein Predictor with Ensemble Classifiers and Comprehensive Sequence Descriptors.

PubMed

Yang, Runtao; Zhang, Chengjin; Gao, Rui; Zhang, Lina

2015-09-07

Antifreeze proteins (AFPs) play a pivotal role in the antifreeze effect of overwintering organisms. They have a wide range of applications in numerous fields, such as improving the production of crops and the quality of frozen foods. Accurate identification of AFPs may provide important clues to decipher the underlying mechanisms of AFPs in ice-binding and to facilitate the selection of the most appropriate AFPs for several applications. Based on an ensemble learning technique, this study proposes an AFP identification system called AFP-Ensemble. In this system, random forest classifiers are trained by different training subsets and then aggregated into a consensus classifier by majority voting. The resulting predictor yields a sensitivity of 0.892, a specificity of 0.940, an accuracy of 0.938 and a balanced accuracy of 0.916 on an independent dataset, which are far better than the results obtained by previous methods. These results reveal that AFP-Ensemble is an effective and promising predictor for large-scale determination of AFPs. The detailed feature analysis in this study may give useful insights into the molecular mechanisms of AFP-ice interactions and provide guidance for the related experimental validation. A web server has been designed to implement the proposed method.

How Accurate Are Transition States from Simulations of Enzymatic Reactions?

PubMed Central

2015-01-01

The rate expression of traditional transition state theory (TST) assumes no recrossing of the transition state (TS) and thermal quasi-equilibrium between the ground state and the TS. Currently, it is not well understood to what extent these assumptions influence the nature of the activated complex obtained in traditional TST-based simulations of processes in the condensed phase in general and in enzymes in particular. Here we scrutinize these assumptions by characterizing the TSs for hydride transfer catalyzed by the enzyme Escherichia coli dihydrofolate reductase obtained using various simulation approaches. Specifically, we compare the TSs obtained with common TST-based methods and a dynamics-based method. Using a recently developed accurate hybrid quantum mechanics/molecular mechanics potential, we find that the TST-based and dynamics-based methods give considerably different TS ensembles. This discrepancy, which could be due equilibrium solvation effects and the nature of the reaction coordinate employed and its motion, raises major questions about how to interpret the TSs determined by common simulation methods. We conclude that further investigation is needed to characterize the impact of various TST assumptions on the TS phase-space ensemble and on the reaction kinetics. PMID:24860275

75 FR 27736 - Availability for Non-Exclusive, Exclusive, or Partially Exclusive Licensing of U.S. Provisional...

Federal Register 2010, 2011, 2012, 2013, 2014

2010-05-18

... Cooling Method for Protective Clothing Ensembles AGENCY: Department of the Army, DoD. ACTION: Notice... Protective Clothing Ensembles,'' filed March 30, 2010. The United States Government, as represented by the... to a two- stage evaporative cooling method for use in protective clothing ensembles. Brenda S. Bowen...

The wisdom of the commons: ensemble tree classifiers for prostate cancer prognosis

PubMed Central

Koziol, James A.; Feng, Anne C.; Jia, Zhenyu; Wang, Yipeng; Goodison, Seven; McClelland, Michael; Mercola, Dan

2009-01-01

Motivation: Classification and regression trees have long been used for cancer diagnosis and prognosis. Nevertheless, instability and variable selection bias, as well as overfitting, are well-known problems of tree-based methods. In this article, we investigate whether ensemble tree classifiers can ameliorate these difficulties, using data from two recent studies of radical prostatectomy in prostate cancer. Results: Using time to progression following prostatectomy as the relevant clinical endpoint, we found that ensemble tree classifiers robustly and reproducibly identified three subgroups of patients in the two clinical datasets: non-progressors, early progressors and late progressors. Moreover, the consensus classifications were independent predictors of time to progression compared to known clinical prognostic factors. Contact: dmercola@uci.edu PMID:18628288

Gibbs Ensembles for Nearly Compatible and Incompatible Conditional Models

PubMed Central

Chen, Shyh-Huei; Wang, Yuchung J.

2010-01-01

Gibbs sampler has been used exclusively for compatible conditionals that converge to a unique invariant joint distribution. However, conditional models are not always compatible. In this paper, a Gibbs sampling-based approach — Gibbs ensemble —is proposed to search for a joint distribution that deviates least from a prescribed set of conditional distributions. The algorithm can be easily scalable such that it can handle large data sets of high dimensionality. Using simulated data, we show that the proposed approach provides joint distributions that are less discrepant from the incompatible conditionals than those obtained by other methods discussed in the literature. The ensemble approach is also applied to a data set regarding geno-polymorphism and response to chemotherapy in patients with metastatic colorectal PMID:21286232

Grand canonical ensemble Monte Carlo simulation of the dCpG/proflavine crystal hydrate.

PubMed

Resat, H; Mezei, M

1996-09-01

The grand canonical ensemble Monte Carlo molecular simulation method is used to investigate hydration patterns in the crystal hydrate structure of the dCpG/proflavine intercalated complex. The objective of this study is to show by example that the recently advocated grand canonical ensemble simulation is a computationally efficient method for determining the positions of the hydrating water molecules in protein and nucleic acid structures. A detailed molecular simulation convergence analysis and an analogous comparison of the theoretical results with experiments clearly show that the grand ensemble simulations can be far more advantageous than the comparable canonical ensemble simulations.

A method to encapsulate model structural uncertainty in ensemble projections of future climate: EPIC v1.0

NASA Astrophysics Data System (ADS)

Lewis, Jared; Bodeker, Greg E.; Kremser, Stefanie; Tait, Andrew

2017-12-01

A method, based on climate pattern scaling, has been developed to expand a small number of projections of fields of a selected climate variable (X) into an ensemble that encapsulates a wide range of indicative model structural uncertainties. The method described in this paper is referred to as the Ensemble Projections Incorporating Climate model uncertainty (EPIC) method. Each ensemble member is constructed by adding contributions from (1) a climatology derived from observations that represents the time-invariant part of the signal; (2) a contribution from forced changes in X, where those changes can be statistically related to changes in global mean surface temperature (Tglobal); and (3) a contribution from unforced variability that is generated by a stochastic weather generator. The patterns of unforced variability are also allowed to respond to changes in Tglobal. The statistical relationships between changes in X (and its patterns of variability) and Tglobal are obtained in a training phase. Then, in an implementation phase, 190 simulations of Tglobal are generated using a simple climate model tuned to emulate 19 different global climate models (GCMs) and 10 different carbon cycle models. Using the generated Tglobal time series and the correlation between the forced changes in X and Tglobal, obtained in the training phase, the forced change in the X field can be generated many times using Monte Carlo analysis. A stochastic weather generator is used to generate realistic representations of weather which include spatial coherence. Because GCMs and regional climate models (RCMs) are less likely to correctly represent unforced variability compared to observations, the stochastic weather generator takes as input measures of variability derived from observations, but also responds to forced changes in climate in a way that is consistent with the RCM projections. This approach to generating a large ensemble of projections is many orders of magnitude more computationally efficient than running multiple GCM or RCM simulations. Such a large ensemble of projections permits a description of a probability density function (PDF) of future climate states rather than a small number of individual story lines within that PDF, which may not be representative of the PDF as a whole; the EPIC method largely corrects for such potential sampling biases. The method is useful for providing projections of changes in climate to users wishing to investigate the impacts and implications of climate change in a probabilistic way. A web-based tool, using the EPIC method to provide probabilistic projections of changes in daily maximum and minimum temperatures for New Zealand, has been developed and is described in this paper.

Stabilizing canonical-ensemble calculations in the auxiliary-field Monte Carlo method

NASA Astrophysics Data System (ADS)

Gilbreth, C. N.; Alhassid, Y.

2015-03-01

Quantum Monte Carlo methods are powerful techniques for studying strongly interacting Fermi systems. However, implementing these methods on computers with finite-precision arithmetic requires careful attention to numerical stability. In the auxiliary-field Monte Carlo (AFMC) method, low-temperature or large-model-space calculations require numerically stabilized matrix multiplication. When adapting methods used in the grand-canonical ensemble to the canonical ensemble of fixed particle number, the numerical stabilization increases the number of required floating-point operations for computing observables by a factor of the size of the single-particle model space, and thus can greatly limit the systems that can be studied. We describe an improved method for stabilizing canonical-ensemble calculations in AFMC that exhibits better scaling, and present numerical tests that demonstrate the accuracy and improved performance of the method.

Ensemble-based evaluation of extreme water levels for the eastern Baltic Sea

NASA Astrophysics Data System (ADS)

Eelsalu, Maris; Soomere, Tarmo

2016-04-01

The risks and damages associated with coastal flooding that are naturally associated with an increase in the magnitude of extreme storm surges are one of the largest concerns of countries with extensive low-lying nearshore areas. The relevant risks are even more contrast for semi-enclosed water bodies such as the Baltic Sea where subtidal (weekly-scale) variations in the water volume of the sea substantially contribute to the water level and lead to large spreading of projections of future extreme water levels. We explore the options for using large ensembles of projections to more reliably evaluate return periods of extreme water levels. Single projections of the ensemble are constructed by means of fitting several sets of block maxima with various extreme value distributions. The ensemble is based on two simulated data sets produced in the Swedish Meteorological and Hydrological Institute. A hindcast by the Rossby Centre Ocean model is sampled with a resolution of 6 h and a similar hindcast by the circulation model NEMO with a resolution of 1 h. As the annual maxima of water levels in the Baltic Sea are not always uncorrelated, we employ maxima for calendar years and for stormy seasons. As the shape parameter of the Generalised Extreme Value distribution changes its sign and substantially varies in magnitude along the eastern coast of the Baltic Sea, the use of a single distribution for the entire coast is inappropriate. The ensemble involves projections based on the Generalised Extreme Value, Gumbel and Weibull distributions. The parameters of these distributions are evaluated using three different ways: maximum likelihood method and method of moments based on both biased and unbiased estimates. The total number of projections in the ensemble is 40. As some of the resulting estimates contain limited additional information, the members of pairs of projections that are highly correlated are assigned weights 0.6. A comparison of the ensemble-based projection of extreme water levels and their return periods with similar estimates derived from local observations reveals an interesting pattern of match and mismatch. The match is almost perfect in measurement sites where local effects (e.g., wave-induced set-up or local surge in very shallow areas that are not resolved by circulation models) do not contribute to the observed values of water level. There is, however, substantial mismatch between projected and observed extreme values for most of the Estonian coast. The mismatch is largest for sections that are open to high waves and for several bays that are deeply cut into mainland but open for predominant strong wind directions. Detailed quantification of this mismatch eventually makes it possible to develop substantially improved estimates of extreme water levels in sections where local effects considerably contribute into the total water level.

Post-processing of multi-model ensemble river discharge forecasts using censored EMOS

NASA Astrophysics Data System (ADS)

Hemri, Stephan; Lisniak, Dmytro; Klein, Bastian

2014-05-01

When forecasting water levels and river discharge, ensemble weather forecasts are used as meteorological input to hydrologic process models. As hydrologic models are imperfect and the input ensembles tend to be biased and underdispersed, the output ensemble forecasts for river runoff typically are biased and underdispersed, too. Thus, statistical post-processing is required in order to achieve calibrated and sharp predictions. Standard post-processing methods such as Ensemble Model Output Statistics (EMOS) that have their origins in meteorological forecasting are now increasingly being used in hydrologic applications. Here we consider two sub-catchments of River Rhine, for which the forecasting system of the Federal Institute of Hydrology (BfG) uses runoff data that are censored below predefined thresholds. To address this methodological challenge, we develop a censored EMOS method that is tailored to such data. The censored EMOS forecast distribution can be understood as a mixture of a point mass at the censoring threshold and a continuous part based on a truncated normal distribution. Parameter estimates of the censored EMOS model are obtained by minimizing the Continuous Ranked Probability Score (CRPS) over the training dataset. Model fitting on Box-Cox transformed data allows us to take account of the positive skewness of river discharge distributions. In order to achieve realistic forecast scenarios over an entire range of lead-times, there is a need for multivariate extensions. To this end, we smooth the marginal parameter estimates over lead-times. In order to obtain realistic scenarios of discharge evolution over time, the marginal distributions have to be linked with each other. To this end, the multivariate dependence structure can either be adopted from the raw ensemble like in Ensemble Copula Coupling (ECC), or be estimated from observations in a training period. The censored EMOS model has been applied to multi-model ensemble forecasts issued on a daily basis over a period of three years. For the two catchments considered, this resulted in well calibrated and sharp forecast distributions over all lead-times from 1 to 114 h. Training observations tended to be better indicators for the dependence structure than the raw ensemble.

Combined Monte Carlo/torsion-angle molecular dynamics for ensemble modeling of proteins, nucleic acids and carbohydrates.

PubMed

Zhang, Weihong; Howell, Steven C; Wright, David W; Heindel, Andrew; Qiu, Xiangyun; Chen, Jianhan; Curtis, Joseph E

2017-05-01

We describe a general method to use Monte Carlo simulation followed by torsion-angle molecular dynamics simulations to create ensembles of structures to model a wide variety of soft-matter biological systems. Our particular emphasis is focused on modeling low-resolution small-angle scattering and reflectivity structural data. We provide examples of this method applied to HIV-1 Gag protein and derived fragment proteins, TraI protein, linear B-DNA, a nucleosome core particle, and a glycosylated monoclonal antibody. This procedure will enable a large community of researchers to model low-resolution experimental data with greater accuracy by using robust physics based simulation and sampling methods which are a significant improvement over traditional methods used to interpret such data. Published by Elsevier Inc.

The FLAME-slab method for electromagnetic wave scattering in aperiodic slabs

NASA Astrophysics Data System (ADS)

Mansha, Shampy; Tsukerman, Igor; Chong, Y. D.

2017-12-01

The proposed numerical method, "FLAME-slab," solves electromagnetic wave scattering problems for aperiodic slab structures by exploiting short-range regularities in these structures. The computational procedure involves special difference schemes with high accuracy even on coarse grids. These schemes are based on Trefftz approximations, utilizing functions that locally satisfy the governing differential equations, as is done in the Flexible Local Approximation Method (FLAME). Radiation boundary conditions are implemented via Fourier expansions in the air surrounding the slab. When applied to ensembles of slab structures with identical short-range features, such as amorphous or quasicrystalline lattices, the method is significantly more efficient, both in runtime and in memory consumption, than traditional approaches. This efficiency is due to the fact that the Trefftz functions need to be computed only once for the whole ensemble.

Accelerated iterative beam angle selection in IMRT

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

Bangert, Mark, E-mail: m.bangert@dkfz.de; Unkelbach, Jan

2016-03-15

Purpose: Iterative methods for beam angle selection (BAS) for intensity-modulated radiation therapy (IMRT) planning sequentially construct a beneficial ensemble of beam directions. In a naïve implementation, the nth beam is selected by adding beam orientations one-by-one from a discrete set of candidates to an existing ensemble of (n − 1) beams. The best beam orientation is identified in a time consuming process by solving the fluence map optimization (FMO) problem for every candidate beam and selecting the beam that yields the largest improvement to the objective function value. This paper evaluates two alternative methods to accelerate iterative BAS based onmore » surrogates for the FMO objective function value. Methods: We suggest to select candidate beams not based on the FMO objective function value after convergence but (1) based on the objective function value after five FMO iterations of a gradient based algorithm and (2) based on a projected gradient of the FMO problem in the first iteration. The performance of the objective function surrogates is evaluated based on the resulting objective function values and dose statistics in a treatment planning study comprising three intracranial, three pancreas, and three prostate cases. Furthermore, iterative BAS is evaluated for an application in which a small number of noncoplanar beams complement a set of coplanar beam orientations. This scenario is of practical interest as noncoplanar setups may require additional attention of the treatment personnel for every couch rotation. Results: Iterative BAS relying on objective function surrogates yields similar results compared to naïve BAS with regard to the objective function values and dose statistics. At the same time, early stopping of the FMO and using the projected gradient during the first iteration enable reductions in computation time by approximately one to two orders of magnitude. With regard to the clinical delivery of noncoplanar IMRT treatments, we could show that optimized beam ensembles using only a few noncoplanar beam orientations often approach the plan quality of fully noncoplanar ensembles. Conclusions: We conclude that iterative BAS in combination with objective function surrogates can be a viable option to implement automated BAS at clinically acceptable computation times.« less

Ensemble-based docking: From hit discovery to metabolism and toxicity predictions.

PubMed

Evangelista, Wilfredo; Weir, Rebecca L; Ellingson, Sally R; Harris, Jason B; Kapoor, Karan; Smith, Jeremy C; Baudry, Jerome

2016-10-15

This paper describes and illustrates the use of ensemble-based docking, i.e., using a collection of protein structures in docking calculations for hit discovery, the exploration of biochemical pathways and toxicity prediction of drug candidates. We describe the computational engineering work necessary to enable large ensemble docking campaigns on supercomputers. We show examples where ensemble-based docking has significantly increased the number and the diversity of validated drug candidates. Finally, we illustrate how ensemble-based docking can be extended beyond hit discovery and toward providing a structural basis for the prediction of metabolism and off-target binding relevant to pre-clinical and clinical trials. Copyright © 2016 Elsevier Ltd. All rights reserved.

Observing system simulation experiments with multiple methods

NASA Astrophysics Data System (ADS)

Ishibashi, Toshiyuki

2014-11-01

An observing System Simulation Experiment (OSSE) is a method to evaluate impacts of hypothetical observing systems on analysis and forecast accuracy in numerical weather prediction (NWP) systems. Since OSSE requires simulations of hypothetical observations, uncertainty of OSSE results is generally larger than that of observing system experiments (OSEs). To reduce such uncertainty, OSSEs for existing observing systems are often carried out as calibration of the OSSE system. The purpose of this study is to achieve reliable OSSE results based on results of OSSEs with multiple methods. There are three types of OSSE methods. The first one is the sensitivity observing system experiment (SOSE) based OSSE (SOSEOSSE). The second one is the ensemble of data assimilation cycles (ENDA) based OSSE (ENDA-OSSE). The third one is the nature-run (NR) based OSSE (NR-OSSE). These three OSSE methods have very different properties. The NROSSE evaluates hypothetical observations in a virtual (hypothetical) world, NR. The ENDA-OSSE is very simple method but has a sampling error problem due to a small size ensemble. The SOSE-OSSE requires a very highly accurate analysis field as a pseudo truth of the real atmosphere. We construct these three types of OSSE methods in the Japan meteorological Agency (JMA) global 4D-Var experimental system. In the conference, we will present initial results of these OSSE systems and their comparisons.

Combining Rosetta with molecular dynamics (MD): A benchmark of the MD-based ensemble protein design.

PubMed

Ludwiczak, Jan; Jarmula, Adam; Dunin-Horkawicz, Stanislaw

2018-07-01

Computational protein design is a set of procedures for computing amino acid sequences that will fold into a specified structure. Rosetta Design, a commonly used software for protein design, allows for the effective identification of sequences compatible with a given backbone structure, while molecular dynamics (MD) simulations can thoroughly sample near-native conformations. We benchmarked a procedure in which Rosetta design is started on MD-derived structural ensembles and showed that such a combined approach generates 20-30% more diverse sequences than currently available methods with only a slight increase in computation time. Importantly, the increase in diversity is achieved without a loss in the quality of the designed sequences assessed by their resemblance to natural sequences. We demonstrate that the MD-based procedure is also applicable to de novo design tasks started from backbone structures without any sequence information. In addition, we implemented a protocol that can be used to assess the stability of designed models and to select the best candidates for experimental validation. In sum our results demonstrate that the MD ensemble-based flexible backbone design can be a viable method for protein design, especially for tasks that require a large pool of diverse sequences. Copyright © 2018 Elsevier Inc. All rights reserved.

Ensemble Generation and the Influence of Protein Flexibility on Geometric Tunnel Prediction in Cytochrome P450 Enzymes

PubMed Central

Kingsley, Laura J.; Lill, Markus A.

2014-01-01

Computational prediction of ligand entry and egress paths in proteins has become an emerging topic in computational biology and has proven useful in fields such as protein engineering and drug design. Geometric tunnel prediction programs, such as Caver3.0 and MolAxis, are computationally efficient methods to identify potential ligand entry and egress routes in proteins. Although many geometric tunnel programs are designed to accommodate a single input structure, the increasingly recognized importance of protein flexibility in tunnel formation and behavior has led to the more widespread use of protein ensembles in tunnel prediction. However, there has not yet been an attempt to directly investigate the influence of ensemble size and composition on geometric tunnel prediction. In this study, we compared tunnels found in a single crystal structure to ensembles of various sizes generated using different methods on both the apo and holo forms of cytochrome P450 enzymes CYP119, CYP2C9, and CYP3A4. Several protein structure clustering methods were tested in an attempt to generate smaller ensembles that were capable of reproducing the data from larger ensembles. Ultimately, we found that by including members from both the apo and holo data sets, we could produce ensembles containing less than 15 members that were comparable to apo or holo ensembles containing over 100 members. Furthermore, we found that, in the absence of either apo or holo crystal structure data, pseudo-apo or –holo ensembles (e.g. adding ligand to apo protein throughout MD simulations) could be used to resemble the structural ensembles of the corresponding apo and holo ensembles, respectively. Our findings not only further highlight the importance of including protein flexibility in geometric tunnel prediction, but also suggest that smaller ensembles can be as capable as larger ensembles at capturing many of the protein motions important for tunnel prediction at a lower computational cost. PMID:24956479

Statistical hadronization and microcanonical ensemble

DOE PAGES

Becattini, F.; Ferroni, L.

2004-01-01

We present a Monte Carlo calculation of the microcanonical ensemble of the of the ideal hadron-resonance gas including all known states up to a mass of 1. 8 GeV, taking into account quantum statistics. The computing method is a development of a previous one based on a Metropolis Monte Carlo algorithm, with a the grand-canonical limit of the multi-species multiplicity distribution as proposal matrix. The microcanonical average multiplicities of the various hadron species are found to converge to the canonical ones for moderately low values of the total energy. This algorithm opens the way for event generators based for themore » statistical hadronization model.« less

A Hyper-Heuristic Ensemble Method for Static Job-Shop Scheduling.

PubMed

Hart, Emma; Sim, Kevin

2016-01-01

We describe a new hyper-heuristic method NELLI-GP for solving job-shop scheduling problems (JSSP) that evolves an ensemble of heuristics. The ensemble adopts a divide-and-conquer approach in which each heuristic solves a unique subset of the instance set considered. NELLI-GP extends an existing ensemble method called NELLI by introducing a novel heuristic generator that evolves heuristics composed of linear sequences of dispatching rules: each rule is represented using a tree structure and is itself evolved. Following a training period, the ensemble is shown to outperform both existing dispatching rules and a standard genetic programming algorithm on a large set of new test instances. In addition, it obtains superior results on a set of 210 benchmark problems from the literature when compared to two state-of-the-art hyper-heuristic approaches. Further analysis of the relationship between heuristics in the evolved ensemble and the instances each solves provides new insights into features that might describe similar instances.

Perceptron ensemble of graph-based positive-unlabeled learning for disease gene identification.

PubMed

Jowkar, Gholam-Hossein; Mansoori, Eghbal G

2016-10-01

Identification of disease genes, using computational methods, is an important issue in biomedical and bioinformatics research. According to observations that diseases with the same or similar phenotype have the same biological characteristics, researchers have tried to identify genes by using machine learning tools. In recent attempts, some semi-supervised learning methods, called positive-unlabeled learning, is used for disease gene identification. In this paper, we present a Perceptron ensemble of graph-based positive-unlabeled learning (PEGPUL) on three types of biological attributes: gene ontologies, protein domains and protein-protein interaction networks. In our method, a reliable set of positive and negative genes are extracted using co-training schema. Then, the similarity graph of genes is built using metric learning by concentrating on multi-rank-walk method to perform inference from labeled genes. At last, a Perceptron ensemble is learned from three weighted classifiers: multilevel support vector machine, k-nearest neighbor and decision tree. The main contributions of this paper are: (i) incorporating the statistical properties of gene data through choosing proper metrics, (ii) statistical evaluation of biological features, and (iii) noise robustness characteristic of PEGPUL via using multilevel schema. In order to assess PEGPUL, we have applied it on 12950 disease genes with 949 positive genes from six class of diseases and 12001 unlabeled genes. Compared with some popular disease gene identification methods, the experimental results show that PEGPUL has reasonable performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Implementation of unsteady sampling procedures for the parallel direct simulation Monte Carlo method

NASA Astrophysics Data System (ADS)

Cave, H. M.; Tseng, K.-C.; Wu, J.-S.; Jermy, M. C.; Huang, J.-C.; Krumdieck, S. P.

2008-06-01

An unsteady sampling routine for a general parallel direct simulation Monte Carlo method called PDSC is introduced, allowing the simulation of time-dependent flow problems in the near continuum range. A post-processing procedure called DSMC rapid ensemble averaging method (DREAM) is developed to improve the statistical scatter in the results while minimising both memory and simulation time. This method builds an ensemble average of repeated runs over small number of sampling intervals prior to the sampling point of interest by restarting the flow using either a Maxwellian distribution based on macroscopic properties for near equilibrium flows (DREAM-I) or output instantaneous particle data obtained by the original unsteady sampling of PDSC for strongly non-equilibrium flows (DREAM-II). The method is validated by simulating shock tube flow and the development of simple Couette flow. Unsteady PDSC is found to accurately predict the flow field in both cases with significantly reduced run-times over single processor code and DREAM greatly reduces the statistical scatter in the results while maintaining accurate particle velocity distributions. Simulations are then conducted of two applications involving the interaction of shocks over wedges. The results of these simulations are compared to experimental data and simulations from the literature where there these are available. In general, it was found that 10 ensembled runs of DREAM processing could reduce the statistical uncertainty in the raw PDSC data by 2.5-3.3 times, based on the limited number of cases in the present study.

A Compound Fault Diagnosis for Rolling Bearings Method Based on Blind Source Separation and Ensemble Empirical Mode Decomposition

PubMed Central

Wang, Huaqing; Li, Ruitong; Tang, Gang; Yuan, Hongfang; Zhao, Qingliang; Cao, Xi

2014-01-01

A Compound fault signal usually contains multiple characteristic signals and strong confusion noise, which makes it difficult to separate week fault signals from them through conventional ways, such as FFT-based envelope detection, wavelet transform or empirical mode decomposition individually. In order to improve the compound faults diagnose of rolling bearings via signals’ separation, the present paper proposes a new method to identify compound faults from measured mixed-signals, which is based on ensemble empirical mode decomposition (EEMD) method and independent component analysis (ICA) technique. With the approach, a vibration signal is firstly decomposed into intrinsic mode functions (IMF) by EEMD method to obtain multichannel signals. Then, according to a cross correlation criterion, the corresponding IMF is selected as the input matrix of ICA. Finally, the compound faults can be separated effectively by executing ICA method, which makes the fault features more easily extracted and more clearly identified. Experimental results validate the effectiveness of the proposed method in compound fault separating, which works not only for the outer race defect, but also for the rollers defect and the unbalance fault of the experimental system. PMID:25289644

No-Reference Image Quality Assessment by Wide-Perceptual-Domain Scorer Ensemble Method.

PubMed

Liu, Tsung-Jung; Liu, Kuan-Hsien

2018-03-01

A no-reference (NR) learning-based approach to assess image quality is presented in this paper. The devised features are extracted from wide perceptual domains, including brightness, contrast, color, distortion, and texture. These features are used to train a model (scorer) which can predict scores. The scorer selection algorithms are utilized to help simplify the proposed system. In the final stage, the ensemble method is used to combine the prediction results from selected scorers. Two multiple-scale versions of the proposed approach are also presented along with the single-scale one. They turn out to have better performances than the original single-scale method. Because of having features from five different domains at multiple image scales and using the outputs (scores) from selected score prediction models as features for multi-scale or cross-scale fusion (i.e., ensemble), the proposed NR image quality assessment models are robust with respect to more than 24 image distortion types. They also can be used on the evaluation of images with authentic distortions. The extensive experiments on three well-known and representative databases confirm the performance robustness of our proposed model.

Direct Extraction of Tumor Response Based on Ensemble Empirical Mode Decomposition for Image Reconstruction of Early Breast Cancer Detection by UWB.

PubMed

Li, Qinwei; Xiao, Xia; Wang, Liang; Song, Hang; Kono, Hayato; Liu, Peifang; Lu, Hong; Kikkawa, Takamaro

2015-10-01

A direct extraction method of tumor response based on ensemble empirical mode decomposition (EEMD) is proposed for early breast cancer detection by ultra-wide band (UWB) microwave imaging. With this approach, the image reconstruction for the tumor detection can be realized with only extracted signals from as-detected waveforms. The calibration process executed in the previous research for obtaining reference waveforms which stand for signals detected from the tumor-free model is not required. The correctness of the method is testified by successfully detecting a 4 mm tumor located inside the glandular region in one breast model and by the model located at the interface between the gland and the fat, respectively. The reliability of the method is checked by distinguishing a tumor buried in the glandular tissue whose dielectric constant is 35. The feasibility of the method is confirmed by showing the correct tumor information in both simulation results and experimental results for the realistic 3-D printed breast phantom.

Identifying outliers of non-Gaussian groundwater state data based on ensemble estimation for long-term trends

NASA Astrophysics Data System (ADS)

Jeong, Jina; Park, Eungyu; Han, Weon Shik; Kim, Kueyoung; Choung, Sungwook; Chung, Il Moon

2017-05-01

A hydrogeological dataset often includes substantial deviations that need to be inspected. In the present study, three outlier identification methods - the three sigma rule (3σ), inter quantile range (IQR), and median absolute deviation (MAD) - that take advantage of the ensemble regression method are proposed by considering non-Gaussian characteristics of groundwater data. For validation purposes, the performance of the methods is compared using simulated and actual groundwater data with a few hypothetical conditions. In the validations using simulated data, all of the proposed methods reasonably identify outliers at a 5% outlier level; whereas, only the IQR method performs well for identifying outliers at a 30% outlier level. When applying the methods to real groundwater data, the outlier identification performance of the IQR method is found to be superior to the other two methods. However, the IQR method shows limitation by identifying excessive false outliers, which may be overcome by its joint application with other methods (for example, the 3σ rule and MAD methods). The proposed methods can be also applied as potential tools for the detection of future anomalies by model training based on currently available data.

MSEBAG: a dynamic classifier ensemble generation based on `minimum-sufficient ensemble' and bagging

NASA Astrophysics Data System (ADS)

Chen, Lei; Kamel, Mohamed S.

2016-01-01

In this paper, we propose a dynamic classifier system, MSEBAG, which is characterised by searching for the 'minimum-sufficient ensemble' and bagging at the ensemble level. It adopts an 'over-generation and selection' strategy and aims to achieve a good bias-variance trade-off. In the training phase, MSEBAG first searches for the 'minimum-sufficient ensemble', which maximises the in-sample fitness with the minimal number of base classifiers. Then, starting from the 'minimum-sufficient ensemble', a backward stepwise algorithm is employed to generate a collection of ensembles. The objective is to create a collection of ensembles with a descending fitness on the data, as well as a descending complexity in the structure. MSEBAG dynamically selects the ensembles from the collection for the decision aggregation. The extended adaptive aggregation (EAA) approach, a bagging-style algorithm performed at the ensemble level, is employed for this task. EAA searches for the competent ensembles using a score function, which takes into consideration both the in-sample fitness and the confidence of the statistical inference, and averages the decisions of the selected ensembles to label the test pattern. The experimental results show that the proposed MSEBAG outperforms the benchmarks on average.

An ensemble framework for identifying essential proteins.

PubMed

Zhang, Xue; Xiao, Wangxin; Acencio, Marcio Luis; Lemke, Ney; Wang, Xujing

2016-08-25

Many centrality measures have been proposed to mine and characterize the correlations between network topological properties and protein essentiality. However, most of them show limited prediction accuracy, and the number of common predicted essential proteins by different methods is very small. In this paper, an ensemble framework is proposed which integrates gene expression data and protein-protein interaction networks (PINs). It aims to improve the prediction accuracy of basic centrality measures. The idea behind this ensemble framework is that different protein-protein interactions (PPIs) may show different contributions to protein essentiality. Five standard centrality measures (degree centrality, betweenness centrality, closeness centrality, eigenvector centrality, and subgraph centrality) are integrated into the ensemble framework respectively. We evaluated the performance of the proposed ensemble framework using yeast PINs and gene expression data. The results show that it can considerably improve the prediction accuracy of the five centrality measures individually. It can also remarkably increase the number of common predicted essential proteins among those predicted by each centrality measure individually and enable each centrality measure to find more low-degree essential proteins. This paper demonstrates that it is valuable to differentiate the contributions of different PPIs for identifying essential proteins based on network topological characteristics. The proposed ensemble framework is a successful paradigm to this end.

A combination of feature extraction methods with an ensemble of different classifiers for protein structural class prediction problem.

PubMed

Dehzangi, Abdollah; Paliwal, Kuldip; Sharma, Alok; Dehzangi, Omid; Sattar, Abdul

2013-01-01

Better understanding of structural class of a given protein reveals important information about its overall folding type and its domain. It can also be directly used to provide critical information on general tertiary structure of a protein which has a profound impact on protein function determination and drug design. Despite tremendous enhancements made by pattern recognition-based approaches to solve this problem, it still remains as an unsolved issue for bioinformatics that demands more attention and exploration. In this study, we propose a novel feature extraction model that incorporates physicochemical and evolutionary-based information simultaneously. We also propose overlapped segmented distribution and autocorrelation-based feature extraction methods to provide more local and global discriminatory information. The proposed feature extraction methods are explored for 15 most promising attributes that are selected from a wide range of physicochemical-based attributes. Finally, by applying an ensemble of different classifiers namely, Adaboost.M1, LogitBoost, naive Bayes, multilayer perceptron (MLP), and support vector machine (SVM) we show enhancement of the protein structural class prediction accuracy for four popular benchmarks.

Early sinkhole detection using a drone-based thermal camera and image processing

NASA Astrophysics Data System (ADS)

Lee, Eun Ju; Shin, Sang Young; Ko, Byoung Chul; Chang, Chunho

2016-09-01

Accurate advance detection of the sinkholes that are occurring more frequently now is an important way of preventing human fatalities and property damage. Unlike naturally occurring sinkholes, human-induced ones in urban areas are typically due to groundwater disturbances and leaks of water and sewage caused by large-scale construction. Although many sinkhole detection methods have been developed, it is still difficult to predict sinkholes that occur in depth areas. In addition, conventional methods are inappropriate for scanning a large area because of their high cost. Therefore, this paper uses a drone combined with a thermal far-infrared (FIR) camera to detect potential sinkholes over a large area based on computer vision and pattern classification techniques. To make a standard dataset, we dug eight holes of depths 0.5-2 m in increments of 0.5 m and with a maximum width of 1 m. We filmed these using the drone-based FIR camera at a height of 50 m. We first detect candidate regions by analysing cold spots in the thermal images based on the fact that a sinkhole typically has a lower thermal energy than its background. Then, these regions are classified into sinkhole and non-sinkhole classes using a pattern classifier. In this study, we ensemble the classification results based on a light convolutional neural network (CNN) and those based on a Boosted Random Forest (BRF) with handcrafted features. We apply the proposed ensemble method successfully to sinkhole data for various sizes and depths in different environments, and prove that the CNN ensemble and the BRF one with handcrafted features are better at detecting sinkholes than other classifiers or standalone CNN.

Project fires. Volume 2: Protective ensemble performance standards, phase 1B

NASA Astrophysics Data System (ADS)

Abeles, F. J.

1980-05-01

The design of the prototype protective ensemble was finalized. Prototype ensembles were fabricated and then subjected to a series of qualification tests which were based upon the protective ensemble performance standards PEPS requirements. Engineering drawings and purchase specifications were prepared for the new protective ensemble.

A Single-column Model Ensemble Approach Applied to the TWP-ICE Experiment

NASA Technical Reports Server (NTRS)

Davies, L.; Jakob, C.; Cheung, K.; DelGenio, A.; Hill, A.; Hume, T.; Keane, R. J.; Komori, T.; Larson, V. E.; Lin, Y.;

Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines

NASA Astrophysics Data System (ADS)

Zheng, Jinde; Pan, Haiyang; Cheng, Junsheng

2017-02-01

To timely detect the incipient failure of rolling bearing and find out the accurate fault location, a novel rolling bearing fault diagnosis method is proposed based on the composite multiscale fuzzy entropy (CMFE) and ensemble support vector machines (ESVMs). Fuzzy entropy (FuzzyEn), as an improvement of sample entropy (SampEn), is a new nonlinear method for measuring the complexity of time series. Since FuzzyEn (or SampEn) in single scale can not reflect the complexity effectively, multiscale fuzzy entropy (MFE) is developed by defining the FuzzyEns of coarse-grained time series, which represents the system dynamics in different scales. However, the MFE values will be affected by the data length, especially when the data are not long enough. By combining information of multiple coarse-grained time series in the same scale, the CMFE algorithm is proposed in this paper to enhance MFE, as well as FuzzyEn. Compared with MFE, with the increasing of scale factor, CMFE obtains much more stable and consistent values for a short-term time series. In this paper CMFE is employed to measure the complexity of vibration signals of rolling bearings and is applied to extract the nonlinear features hidden in the vibration signals. Also the physically meanings of CMFE being suitable for rolling bearing fault diagnosis are explored. Based on these, to fulfill an automatic fault diagnosis, the ensemble SVMs based multi-classifier is constructed for the intelligent classification of fault features. Finally, the proposed fault diagnosis method of rolling bearing is applied to experimental data analysis and the results indicate that the proposed method could effectively distinguish different fault categories and severities of rolling bearings.

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

Prediction of dosage-based parameters from the puff dispersion of airborne materials in urban environments using the CFD-RANS methodology

NASA Astrophysics Data System (ADS)

Efthimiou, G. C.; Andronopoulos, S.; Bartzis, J. G.

2018-02-01

One of the key issues of recent research on the dispersion inside complex urban environments is the ability to predict dosage-based parameters from the puff release of an airborne material from a point source in the atmospheric boundary layer inside the built-up area. The present work addresses the question of whether the computational fluid dynamics (CFD)-Reynolds-averaged Navier-Stokes (RANS) methodology can be used to predict ensemble-average dosage-based parameters that are related with the puff dispersion. RANS simulations with the ADREA-HF code were, therefore, performed, where a single puff was released in each case. The present method is validated against the data sets from two wind-tunnel experiments. In each experiment, more than 200 puffs were released from which ensemble-averaged dosage-based parameters were calculated and compared to the model's predictions. The performance of the model was evaluated using scatter plots and three validation metrics: fractional bias, normalized mean square error, and factor of two. The model presented a better performance for the temporal parameters (i.e., ensemble-average times of puff arrival, peak, leaving, duration, ascent, and descent) than for the ensemble-average dosage and peak concentration. The majority of the obtained values of validation metrics were inside established acceptance limits. Based on the obtained model performance indices, the CFD-RANS methodology as implemented in the code ADREA-HF is able to predict the ensemble-average temporal quantities related to transient emissions of airborne material in urban areas within the range of the model performance acceptance criteria established in the literature. The CFD-RANS methodology as implemented in the code ADREA-HF is also able to predict the ensemble-average dosage, but the dosage results should be treated with some caution; as in one case, the observed ensemble-average dosage was under-estimated slightly more than the acceptance criteria. Ensemble-average peak concentration was systematically underpredicted by the model to a degree higher than the allowable by the acceptance criteria, in 1 of the 2 wind-tunnel experiments. The model performance depended on the positions of the examined sensors in relation to the emission source and the buildings configuration. The work presented in this paper was carried out (partly) within the scope of COST Action ES1006 "Evaluation, improvement, and guidance for the use of local-scale emergency prediction and response tools for airborne hazards in built environments".

Bayesian ensemble refinement by replica simulations and reweighting.

PubMed

Hummer, Gerhard; Köfinger, Jürgen

2015-12-28

We describe different Bayesian ensemble refinement methods, examine their interrelation, and discuss their practical application. With ensemble refinement, the properties of dynamic and partially disordered (bio)molecular structures can be characterized by integrating a wide range of experimental data, including measurements of ensemble-averaged observables. We start from a Bayesian formulation in which the posterior is a functional that ranks different configuration space distributions. By maximizing this posterior, we derive an optimal Bayesian ensemble distribution. For discrete configurations, this optimal distribution is identical to that obtained by the maximum entropy "ensemble refinement of SAXS" (EROS) formulation. Bayesian replica ensemble refinement enhances the sampling of relevant configurations by imposing restraints on averages of observables in coupled replica molecular dynamics simulations. We show that the strength of the restraints should scale linearly with the number of replicas to ensure convergence to the optimal Bayesian result in the limit of infinitely many replicas. In the "Bayesian inference of ensembles" method, we combine the replica and EROS approaches to accelerate the convergence. An adaptive algorithm can be used to sample directly from the optimal ensemble, without replicas. We discuss the incorporation of single-molecule measurements and dynamic observables such as relaxation parameters. The theoretical analysis of different Bayesian ensemble refinement approaches provides a basis for practical applications and a starting point for further investigations.

Bayesian ensemble refinement by replica simulations and reweighting

NASA Astrophysics Data System (ADS)

Hummer, Gerhard; Köfinger, Jürgen

2015-12-01

We describe different Bayesian ensemble refinement methods, examine their interrelation, and discuss their practical application. With ensemble refinement, the properties of dynamic and partially disordered (bio)molecular structures can be characterized by integrating a wide range of experimental data, including measurements of ensemble-averaged observables. We start from a Bayesian formulation in which the posterior is a functional that ranks different configuration space distributions. By maximizing this posterior, we derive an optimal Bayesian ensemble distribution. For discrete configurations, this optimal distribution is identical to that obtained by the maximum entropy "ensemble refinement of SAXS" (EROS) formulation. Bayesian replica ensemble refinement enhances the sampling of relevant configurations by imposing restraints on averages of observables in coupled replica molecular dynamics simulations. We show that the strength of the restraints should scale linearly with the number of replicas to ensure convergence to the optimal Bayesian result in the limit of infinitely many replicas. In the "Bayesian inference of ensembles" method, we combine the replica and EROS approaches to accelerate the convergence. An adaptive algorithm can be used to sample directly from the optimal ensemble, without replicas. We discuss the incorporation of single-molecule measurements and dynamic observables such as relaxation parameters. The theoretical analysis of different Bayesian ensemble refinement approaches provides a basis for practical applications and a starting point for further investigations.

Streamflow hindcasting in European river basins via multi-parametric ensemble of the mesoscale hydrologic model (mHM)

NASA Astrophysics Data System (ADS)

Noh, Seong Jin; Rakovec, Oldrich; Kumar, Rohini; Samaniego, Luis

2016-04-01

There have been tremendous improvements in distributed hydrologic modeling (DHM) which made a process-based simulation with a high spatiotemporal resolution applicable on a large spatial scale. Despite of increasing information on heterogeneous property of a catchment, DHM is still subject to uncertainties inherently coming from model structure, parameters and input forcing. Sequential data assimilation (DA) may facilitate improved streamflow prediction via DHM using real-time observations to correct internal model states. In conventional DA methods such as state updating, parametric uncertainty is, however, often ignored mainly due to practical limitations of methodology to specify modeling uncertainty with limited ensemble members. If parametric uncertainty related with routing and runoff components is not incorporated properly, predictive uncertainty by DHM may be insufficient to capture dynamics of observations, which may deteriorate predictability. Recently, a multi-scale parameter regionalization (MPR) method was proposed to make hydrologic predictions at different scales using a same set of model parameters without losing much of the model performance. The MPR method incorporated within the mesoscale hydrologic model (mHM, http://www.ufz.de/mhm) could effectively represent and control uncertainty of high-dimensional parameters in a distributed model using global parameters. In this study, we present a global multi-parametric ensemble approach to incorporate parametric uncertainty of DHM in DA to improve streamflow predictions. To effectively represent and control uncertainty of high-dimensional parameters with limited number of ensemble, MPR method is incorporated with DA. Lagged particle filtering is utilized to consider the response times and non-Gaussian characteristics of internal hydrologic processes. The hindcasting experiments are implemented to evaluate impacts of the proposed DA method on streamflow predictions in multiple European river basins having different climate and catchment characteristics. Because augmentation of parameters is not required within an assimilation window, the approach could be stable with limited ensemble members and viable for practical uses.

Grand canonical ensemble Monte Carlo simulation of the dCpG/proflavine crystal hydrate.

PubMed Central

Resat, H; Mezei, M

1996-01-01

The grand canonical ensemble Monte Carlo molecular simulation method is used to investigate hydration patterns in the crystal hydrate structure of the dCpG/proflavine intercalated complex. The objective of this study is to show by example that the recently advocated grand canonical ensemble simulation is a computationally efficient method for determining the positions of the hydrating water molecules in protein and nucleic acid structures. A detailed molecular simulation convergence analysis and an analogous comparison of the theoretical results with experiments clearly show that the grand ensemble simulations can be far more advantageous than the comparable canonical ensemble simulations. Images FIGURE 5 FIGURE 7 PMID:8873992

The Behavior of Filters and Smoothers for Strongly Nonlinear Dynamics

NASA Technical Reports Server (NTRS)

Zhu, Yanqiu; Cohn, Stephen E.; Todling, Ricardo

1999-01-01

The Kalman filter is the optimal filter in the presence of known Gaussian error statistics and linear dynamics. Filter extension to nonlinear dynamics is non trivial in the sense of appropriately representing high order moments of the statistics. Monte Carlo, ensemble-based, methods have been advocated as the methodology for representing high order moments without any questionable closure assumptions (e.g., Miller 1994). Investigation along these lines has been conducted for highly idealized dynamics such as the strongly nonlinear Lorenz (1963) model as well as more realistic models of the oceans (Evensen and van Leeuwen 1996) and atmosphere (Houtekamer and Mitchell 1998). A few relevant issues in this context are related to the necessary number of ensemble members to properly represent the error statistics and, the necessary modifications in the usual filter equations to allow for correct update of the ensemble members (Burgers 1998). The ensemble technique has also been applied to the problem of smoothing for which similar questions apply. Ensemble smoother examples, however, seem to quite puzzling in that results of state estimate are worse than for their filter analogue (Evensen 1997). In this study, we use concepts in probability theory to revisit the ensemble methodology for filtering and smoothing in data assimilation. We use Lorenz (1963) model to test and compare the behavior of a variety implementations of ensemble filters. We also implement ensemble smoothers that are able to perform better than their filter counterparts. A discussion of feasibility of these techniques to large data assimilation problems will be given at the time of the conference.

Moving beyond the cost-loss ratio: economic assessment of streamflow forecasts for a risk-averse decision maker

NASA Astrophysics Data System (ADS)

Matte, Simon; Boucher, Marie-Amélie; Boucher, Vincent; Fortier Filion, Thomas-Charles

2017-06-01

A large effort has been made over the past 10 years to promote the operational use of probabilistic or ensemble streamflow forecasts. Numerous studies have shown that ensemble forecasts are of higher quality than deterministic ones. Many studies also conclude that decisions based on ensemble rather than deterministic forecasts lead to better decisions in the context of flood mitigation. Hence, it is believed that ensemble forecasts possess a greater economic and social value for both decision makers and the general population. However, the vast majority of, if not all, existing hydro-economic studies rely on a cost-loss ratio framework that assumes a risk-neutral decision maker. To overcome this important flaw, this study borrows from economics and evaluates the economic value of early warning flood systems using the well-known Constant Absolute Risk Aversion (CARA) utility function, which explicitly accounts for the level of risk aversion of the decision maker. This new framework allows for the full exploitation of the information related to a forecasts' uncertainty, making it especially suited for the economic assessment of ensemble or probabilistic forecasts. Rather than comparing deterministic and ensemble forecasts, this study focuses on comparing different types of ensemble forecasts. There are multiple ways of assessing and representing forecast uncertainty. Consequently, there exist many different means of building an ensemble forecasting system for future streamflow. One such possibility is to dress deterministic forecasts using the statistics of past error forecasts. Such dressing methods are popular among operational agencies because of their simplicity and intuitiveness. Another approach is the use of ensemble meteorological forecasts for precipitation and temperature, which are then provided as inputs to one or many hydrological model(s). In this study, three concurrent ensemble streamflow forecasting systems are compared: simple statistically dressed deterministic forecasts, forecasts based on meteorological ensembles, and a variant of the latter that also includes an estimation of state variable uncertainty. This comparison takes place for the Montmorency River, a small flood-prone watershed in southern central Quebec, Canada. The assessment of forecasts is performed for lead times of 1 to 5 days, both in terms of forecasts' quality (relative to the corresponding record of observations) and in terms of economic value, using the new proposed framework based on the CARA utility function. It is found that the economic value of a forecast for a risk-averse decision maker is closely linked to the forecast reliability in predicting the upper tail of the streamflow distribution. Hence, post-processing forecasts to avoid over-forecasting could help improve both the quality and the value of forecasts.

Unbiased Rare Event Sampling in Spatial Stochastic Systems Biology Models Using a Weighted Ensemble of Trajectories

PubMed Central

Donovan, Rory M.; Tapia, Jose-Juan; Sullivan, Devin P.; Faeder, James R.; Murphy, Robert F.; Dittrich, Markus; Zuckerman, Daniel M.

2016-01-01

The long-term goal of connecting scales in biological simulation can be facilitated by scale-agnostic methods. We demonstrate that the weighted ensemble (WE) strategy, initially developed for molecular simulations, applies effectively to spatially resolved cell-scale simulations. The WE approach runs an ensemble of parallel trajectories with assigned weights and uses a statistical resampling strategy of replicating and pruning trajectories to focus computational effort on difficult-to-sample regions. The method can also generate unbiased estimates of non-equilibrium and equilibrium observables, sometimes with significantly less aggregate computing time than would be possible using standard parallelization. Here, we use WE to orchestrate particle-based kinetic Monte Carlo simulations, which include spatial geometry (e.g., of organelles, plasma membrane) and biochemical interactions among mobile molecular species. We study a series of models exhibiting spatial, temporal and biochemical complexity and show that although WE has important limitations, it can achieve performance significantly exceeding standard parallel simulation—by orders of magnitude for some observables. PMID:26845334

Method for exploratory cluster analysis and visualisation of single-trial ERP ensembles.

PubMed

Williams, N J; Nasuto, S J; Saddy, J D

2015-07-30

The validity of ensemble averaging on event-related potential (ERP) data has been questioned, due to its assumption that the ERP is identical across trials. Thus, there is a need for preliminary testing for cluster structure in the data. We propose a complete pipeline for the cluster analysis of ERP data. To increase the signal-to-noise (SNR) ratio of the raw single-trials, we used a denoising method based on Empirical Mode Decomposition (EMD). Next, we used a bootstrap-based method to determine the number of clusters, through a measure called the Stability Index (SI). We then used a clustering algorithm based on a Genetic Algorithm (GA) to define initial cluster centroids for subsequent k-means clustering. Finally, we visualised the clustering results through a scheme based on Principal Component Analysis (PCA). After validating the pipeline on simulated data, we tested it on data from two experiments - a P300 speller paradigm on a single subject and a language processing study on 25 subjects. Results revealed evidence for the existence of 6 clusters in one experimental condition from the language processing study. Further, a two-way chi-square test revealed an influence of subject on cluster membership. Our analysis operates on denoised single-trials, the number of clusters are determined in a principled manner and the results are presented through an intuitive visualisation. Given the cluster structure in some experimental conditions, we suggest application of cluster analysis as a preliminary step before ensemble averaging. Copyright © 2015 Elsevier B.V. All rights reserved.

Robust electroencephalogram phase estimation with applications in brain-computer interface systems.

PubMed

Seraj, Esmaeil; Sameni, Reza

2017-03-01

In this study, a robust method is developed for frequency-specific electroencephalogram (EEG) phase extraction using the analytic representation of the EEG. Based on recent theoretical findings in this area, it is shown that some of the phase variations-previously associated to the brain response-are systematic side-effects of the methods used for EEG phase calculation, especially during low analytical amplitude segments of the EEG. With this insight, the proposed method generates randomized ensembles of the EEG phase using minor perturbations in the zero-pole loci of narrow-band filters, followed by phase estimation using the signal's analytical form and ensemble averaging over the randomized ensembles to obtain a robust EEG phase and frequency. This Monte Carlo estimation method is shown to be very robust to noise and minor changes of the filter parameters and reduces the effect of fake EEG phase jumps, which do not have a cerebral origin. As proof of concept, the proposed method is used for extracting EEG phase features for a brain computer interface (BCI) application. The results show significant improvement in classification rates using rather simple phase-related features and a standard K-nearest neighbors and random forest classifiers, over a standard BCI dataset. The average performance was improved between 4-7% (in absence of additive noise) and 8-12% (in presence of additive noise). The significance of these improvements was statistically confirmed by a paired sample t-test, with 0.01 and 0.03 p-values, respectively. The proposed method for EEG phase calculation is very generic and may be applied to other EEG phase-based studies.

Project FIRES [Firefighters' Integrated Response Equipment System]. Volume 2: Protective Ensemble Performance Standards, Phase 1B

NASA Technical Reports Server (NTRS)

Abeles, F. J.

1980-01-01

The design of the prototype protective ensemble was finalized. Prototype ensembles were fabricated and then subjected to a series of qualification tests which were based upon the protective ensemble performance standards PEPS requirements. Engineering drawings and purchase specifications were prepared for the new protective ensemble.

Vibration and acoustic frequency spectra for industrial process modeling using selective fusion multi-condition samples and multi-source features

NASA Astrophysics Data System (ADS)

Tang, Jian; Qiao, Junfei; Wu, ZhiWei; Chai, Tianyou; Zhang, Jian; Yu, Wen

2018-01-01

Frequency spectral data of mechanical vibration and acoustic signals relate to difficult-to-measure production quality and quantity parameters of complex industrial processes. A selective ensemble (SEN) algorithm can be used to build a soft sensor model of these process parameters by fusing valued information selectively from different perspectives. However, a combination of several optimized ensemble sub-models with SEN cannot guarantee the best prediction model. In this study, we use several techniques to construct mechanical vibration and acoustic frequency spectra of a data-driven industrial process parameter model based on selective fusion multi-condition samples and multi-source features. Multi-layer SEN (MLSEN) strategy is used to simulate the domain expert cognitive process. Genetic algorithm and kernel partial least squares are used to construct the inside-layer SEN sub-model based on each mechanical vibration and acoustic frequency spectral feature subset. Branch-and-bound and adaptive weighted fusion algorithms are integrated to select and combine outputs of the inside-layer SEN sub-models. Then, the outside-layer SEN is constructed. Thus, "sub-sampling training examples"-based and "manipulating input features"-based ensemble construction methods are integrated, thereby realizing the selective information fusion process based on multi-condition history samples and multi-source input features. This novel approach is applied to a laboratory-scale ball mill grinding process. A comparison with other methods indicates that the proposed MLSEN approach effectively models mechanical vibration and acoustic signals.

Growth of Errors and Uncertainties in Medium Range Ensemble Forecasts of U.S. East Coast Cool Season Extratropical Cyclones

NASA Astrophysics Data System (ADS)

Zheng, Minghua

Cool-season extratropical cyclones near the U.S. East Coast often have significant impacts on the safety, health, environment and economy of this most densely populated region. Hence it is of vital importance to forecast these high-impact winter storm events as accurately as possible by numerical weather prediction (NWP), including in the medium-range. Ensemble forecasts are appealing to operational forecasters when forecasting such events because they can provide an envelope of likely solutions to serve user communities. However, it is generally accepted that ensemble outputs are not used efficiently in NWS operations mainly due to the lack of simple and quantitative tools to communicate forecast uncertainties and ensemble verification to assess model errors and biases. Ensemble sensitivity analysis (ESA), which employs a linear correlation and regression between a chosen forecast metric and the forecast state vector, can be used to analyze the forecast uncertainty development for both short- and medium-range forecasts. The application of ESA to a high-impact winter storm in December 2010 demonstrated that the sensitivity signals based on different forecast metrics are robust. In particular, the ESA based on the leading two EOF PCs can separate sensitive regions associated with cyclone amplitude and intensity uncertainties, respectively. The sensitivity signals were verified using the leave-one-out cross validation (LOOCV) method based on a multi-model ensemble from CMC, ECMWF, and NCEP. The climatology of ensemble sensitivities for the leading two EOF PCs based on 3-day and 6-day forecasts of historical cyclone cases was presented. It was found that the EOF1 pattern often represents the intensity variations while the EOF2 pattern represents the track variations along west-southwest and east-northeast direction. For PC1, the upper-level trough associated with the East Coast cyclone and its downstream ridge are important to the forecast uncertainty in cyclone strength. The initial differences in forecasting the ridge along the west coast of North America impact the EOF1 pattern most. For PC2, it was shown that the shift of the tri-polar structure is most significantly related to the cyclone track forecasts. The EOF/fuzzy clustering tool was applied to diagnose the scenarios in operational ensemble forecast of East Coast winter storms. It was shown that the clustering method could efficiently separate the forecast scenarios associated with East Coast storms based on the 90-member multi-model ensemble. A scenario-based ensemble verification method has been proposed and applied it to examine the capability of different EPSs in capturing the analysis scenarios for historical East Coast cyclone cases at lead times of 1-9 days. The results suggest that the NCEP model performs better in short-range forecasts in capturing the analysis scenario although it is under-dispersed. The ECMWF ensemble shows the best performance in the medium range. The CMC model is found to show the smallest percentage of members in the analysis group and a relatively high missing rate, suggesting that it is less reliable regarding capturing the analysis scenario when compared with the other two EPSs. A combination of NCEP and CMC models has been found to reduce the missing rate and improve the error-spread skill in medium- to extended-range forecasts. Based on the orthogonal features of the EOF patterns, the model errors for 1-6-day forecasts have been decomposed for the leading two EOF patterns. The results for error decomposition show that the NCEP model tends to better represent both EOF1 and EOF2 patterns by showing less intensity and displacement errors during 1-3 days. The ECMWF model is found to have the smallest errors in both EOF1 and EOF2 patterns during 4-6 days. We have also found that East Coast cyclones in the ECMWF forecast tend to be towards the southwest of the other two models in representing the EOF2 pattern, which is associated with the southwest-northeast shifting of the cyclone. This result suggests that ECMWF model may have a tendency to show a closer-to-shore solution in forecasting East Coast winter storms. The downstream impacts of Rossby wave packets (RWPs) on the predictability of winter storms are investigated to explore the source of ensemble uncertainties. The composited RWPA anomalies show that there are enhanced RWPs propagating across the Pacific in both large-error and large-spread cases over the verification regions. There are also indications that the errors might propagate with a speed comparable with the group velocity of RWPs. Based on the composite results as well as our observations of the operation daily RWPA, a conceptual model of errors/uncertainty development associated with RWPs has been proposed to serve as a practical tool to understand the evolution of forecast errors and uncertainties associated with the coherent RWPs originating from upstream as far as western Pacific. (Abstract shortened by ProQuest.).

High density nitrogen-vacancy sensing surface created via He{sup +} ion implantation of {sup 12}C diamond

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

Kleinsasser, Ed E., E-mail: edklein@uw.edu; Stanfield, Matthew M.; Banks, Jannel K. Q.

2016-05-16

We present a promising method for creating high-density ensembles of nitrogen-vacancy centers with narrow spin-resonances for high-sensitivity magnetic imaging. Practically, narrow spin-resonance linewidths substantially reduce the optical and RF power requirements for ensemble-based sensing. The method combines isotope purified diamond growth, in situ nitrogen doping, and helium ion implantation to realize a 100 nm-thick sensing surface. The obtained 10{sup 17 }cm{sup −3} nitrogen-vacancy density is only a factor of 10 less than the highest densities reported to date, with an observed 200 kHz spin resonance linewidth over 10 times narrower.

Uncertainty in projected point precipitation extremes for hydrological impact analysis of climate change

NASA Astrophysics Data System (ADS)

Van Uytven, Els; Willems, Patrick

2017-04-01

Current trends in the hydro-meteorological variables indicate the potential impact of climate change on hydrological extremes. Therefore, they trigger an increased importance climate adaptation strategies in water management. The impact of climate change on hydro-meteorological and hydrological extremes is, however, highly uncertain. This is due to uncertainties introduced by the climate models, the internal variability inherent to the climate system, the greenhouse gas scenarios and the statistical downscaling methods. In view of the need to define sustainable climate adaptation strategies, there is a need to assess these uncertainties. This is commonly done by means of ensemble approaches. Because more and more climate models and statistical downscaling methods become available, there is a need to facilitate the climate impact and uncertainty analysis. A Climate Perturbation Tool has been developed for that purpose, which combines a set of statistical downscaling methods including weather typing, weather generator, transfer function and advanced perturbation based approaches. By use of an interactive interface, climate impact modelers can apply these statistical downscaling methods in a semi-automatic way to an ensemble of climate model runs. The tool is applicable to any region, but has been demonstrated so far to cases in Belgium, Suriname, Vietnam and Bangladesh. Time series representing future local-scale precipitation, temperature and potential evapotranspiration (PET) conditions were obtained, starting from time series of historical observations. Uncertainties on the future meteorological conditions are represented in two different ways: through an ensemble of time series, and a reduced set of synthetic scenarios. The both aim to span the full uncertainty range as assessed from the ensemble of climate model runs and downscaling methods. For Belgium, for instance, use was made of 100-year time series of 10-minutes precipitation observations and daily temperature and PET observations at Uccle and a large ensemble of 160 global climate model runs (CMIP5). They cover all four representative concentration pathway based greenhouse gas scenarios. While evaluating the downscaled meteorological series, particular attention was given to the performance of extreme value metrics (e.g. for precipitation, by means of intensity-duration-frequency statistics). Moreover, the total uncertainty was decomposed in the fractional uncertainties for each of the uncertainty sources considered. Research assessing the additional uncertainty due to parameter and structural uncertainties of the hydrological impact model is ongoing.

First Assessment of Itaipu Dam Ensemble Inflow Forecasting System

NASA Astrophysics Data System (ADS)

Mainardi Fan, Fernando; Machado Vieira Lisboa, Auder; Gomes Villa Trinidad, Giovanni; Rógenes Monteiro Pontes, Paulo; Collischonn, Walter; Tucci, Carlos; Costa Buarque, Diogo

2017-04-01

Inflow forecasting for Hydropower Plants (HPP) Dams is one of the prominent uses for hydrological forecasts. A very important HPP in terms of energy generation for South America is the Itaipu Dam, located in the Paraná River, between Brazil and Paraguay countries, with a drainage area of 820.000km2. In this work, we present the development of an ensemble forecasting system for Itaipu, operational since November 2015. The system is based in the MGB-IPH hydrological model, includes hydrodynamics simulations of the main river, and is run every day morning forced by seven different rainfall forecasts: (i) CPTEC-ETA 15km; (ii) CPTEC-BRAMS 5km; (iii) SIMEPAR WRF Ferrier; (iv) SIMEPAR WRF Lin; (v) SIMEPAR WRF Morrison; (vi) SIMEPAR WRF WDM6; (vii) SIMEPAR MEDIAN. The last one (vii) corresponds to the median value of SIMEPAR WRF model versions (iii to vi) rainfall forecasts. Besides the developed system, the "traditional" method for inflow forecasting generation for the Itaipu Dam is also run every day. This traditional method consists in the approximation of the future inflow based on the discharge tendency of upstream telemetric gauges. Nowadays, after all the forecasts are run, the hydrology team of Itaipu develop a consensus forecast, based on all obtained results, which is the one used for the Itaipu HPP Dam operation. After one year of operation a first evaluation of the Ensemble Forecasting System was conducted. Results show that the system performs satisfactory for rising flows up to five days lead time. However, some false alarms were also issued by most ensemble members in some cases. And not in all cases the system performed better than the traditional method, especially during hydrograph recessions. In terms of meteorological forecasts, some members usage are being discontinued. In terms of the hydrodynamics representation, it seems that a better information of rivers cross section could improve hydrographs recession curves forecasts. Those opportunities for improvements are currently being addressed in the system next update.

Statistical Methods in Ai: Rare Event Learning Using Associative Rules and Higher-Order Statistics

NASA Astrophysics Data System (ADS)

Iyer, V.; Shetty, S.; Iyengar, S. S.

2015-07-01

Rare event learning has not been actively researched since lately due to the unavailability of algorithms which deal with big samples. The research addresses spatio-temporal streams from multi-resolution sensors to find actionable items from a perspective of real-time algorithms. This computing framework is independent of the number of input samples, application domain, labelled or label-less streams. A sampling overlap algorithm such as Brooks-Iyengar is used for dealing with noisy sensor streams. We extend the existing noise pre-processing algorithms using Data-Cleaning trees. Pre-processing using ensemble of trees using bagging and multi-target regression showed robustness to random noise and missing data. As spatio-temporal streams are highly statistically correlated, we prove that a temporal window based sampling from sensor data streams converges after n samples using Hoeffding bounds. Which can be used for fast prediction of new samples in real-time. The Data-cleaning tree model uses a nonparametric node splitting technique, which can be learned in an iterative way which scales linearly in memory consumption for any size input stream. The improved task based ensemble extraction is compared with non-linear computation models using various SVM kernels for speed and accuracy. We show using empirical datasets the explicit rule learning computation is linear in time and is only dependent on the number of leafs present in the tree ensemble. The use of unpruned trees (t) in our proposed ensemble always yields minimum number (m) of leafs keeping pre-processing computation to n × t log m compared to N2 for Gram Matrix. We also show that the task based feature induction yields higher Qualify of Data (QoD) in the feature space compared to kernel methods using Gram Matrix.

Estimation of sum-to-one constrained parameters with non-Gaussian extensions of ensemble-based Kalman filters: application to a 1D ocean biogeochemical model

NASA Astrophysics Data System (ADS)

Simon, E.; Bertino, L.; Samuelsen, A.

2011-12-01

Combined state-parameter estimation in ocean biogeochemical models with ensemble-based Kalman filters is a challenging task due to the non-linearity of the models, the constraints of positiveness that apply to the variables and parameters, and the non-Gaussian distribution of the variables in which they result. Furthermore, these models are sensitive to numerous parameters that are poorly known. Previous works [1] demonstrated that the Gaussian anamorphosis extensions of ensemble-based Kalman filters were relevant tools to perform combined state-parameter estimation in such non-Gaussian framework. In this study, we focus on the estimation of the grazing preferences parameters of zooplankton species. These parameters are introduced to model the diet of zooplankton species among phytoplankton species and detritus. They are positive values and their sum is equal to one. Because the sum-to-one constraint cannot be handled by ensemble-based Kalman filters, a reformulation of the parameterization is proposed. We investigate two types of changes of variables for the estimation of sum-to-one constrained parameters. The first one is based on Gelman [2] and leads to the estimation of normal distributed parameters. The second one is based on the representation of the unit sphere in spherical coordinates and leads to the estimation of parameters with bounded distributions (triangular or uniform). These formulations are illustrated and discussed in the framework of twin experiments realized in the 1D coupled model GOTM-NORWECOM with Gaussian anamorphosis extensions of the deterministic ensemble Kalman filter (DEnKF). [1] Simon E., Bertino L. : Gaussian anamorphosis extension of the DEnKF for combined state and parameter estimation : application to a 1D ocean ecosystem model. Journal of Marine Systems, 2011. doi :10.1016/j.jmarsys.2011.07.007 [2] Gelman A. : Method of Moments Using Monte Carlo Simulation. Journal of Computational and Graphical Statistics, 4, 1, 36-54, 1995.

Kalman filter data assimilation: targeting observations and parameter estimation.

PubMed

Bellsky, Thomas; Kostelich, Eric J; Mahalov, Alex

2014-06-01

This paper studies the effect of targeted observations on state and parameter estimates determined with Kalman filter data assimilation (DA) techniques. We first provide an analytical result demonstrating that targeting observations within the Kalman filter for a linear model can significantly reduce state estimation error as opposed to fixed or randomly located observations. We next conduct observing system simulation experiments for a chaotic model of meteorological interest, where we demonstrate that the local ensemble transform Kalman filter (LETKF) with targeted observations based on largest ensemble variance is skillful in providing more accurate state estimates than the LETKF with randomly located observations. Additionally, we find that a hybrid ensemble Kalman filter parameter estimation method accurately updates model parameters within the targeted observation context to further improve state estimation.

Optical ensemble analysis of intraocular lens performance through a simulated clinical trial with ZEMAX.

PubMed

Zhao, Huawei

2009-01-01

A ZEMAX model was constructed to simulate a clinical trial of intraocular lenses (IOLs) based on a clinically oriented Monte Carlo ensemble analysis using postoperative ocular parameters. The purpose of this model is to test the feasibility of streamlining and optimizing both the design process and the clinical testing of IOLs. This optical ensemble analysis (OEA) is also validated. Simulated pseudophakic eyes were generated by using the tolerancing and programming features of ZEMAX optical design software. OEA methodology was verified by demonstrating that the results of clinical performance simulations were consistent with previously published clinical performance data using the same types of IOLs. From these results we conclude that the OEA method can objectively simulate the potential clinical trial performance of IOLs.

Multi-model ensemble hydrological simulation using a BP Neural Network for the upper Yalongjiang River Basin, China

NASA Astrophysics Data System (ADS)

Li, Zhanjie; Yu, Jingshan; Xu, Xinyi; Sun, Wenchao; Pang, Bo; Yue, Jiajia

2018-06-01

Hydrological models are important and effective tools for detecting complex hydrological processes. Different models have different strengths when capturing the various aspects of hydrological processes. Relying on a single model usually leads to simulation uncertainties. Ensemble approaches, based on multi-model hydrological simulations, can improve application performance over single models. In this study, the upper Yalongjiang River Basin was selected for a case study. Three commonly used hydrological models (SWAT, VIC, and BTOPMC) were selected and used for independent simulations with the same input and initial values. Then, the BP neural network method was employed to combine the results from the three models. The results show that the accuracy of BP ensemble simulation is better than that of the single models.

Kalman filter data assimilation: Targeting observations and parameter estimation

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

Bellsky, Thomas, E-mail: bellskyt@asu.edu; Kostelich, Eric J.; Mahalov, Alex

2014-06-15

This paper studies the effect of targeted observations on state and parameter estimates determined with Kalman filter data assimilation (DA) techniques. We first provide an analytical result demonstrating that targeting observations within the Kalman filter for a linear model can significantly reduce state estimation error as opposed to fixed or randomly located observations. We next conduct observing system simulation experiments for a chaotic model of meteorological interest, where we demonstrate that the local ensemble transform Kalman filter (LETKF) with targeted observations based on largest ensemble variance is skillful in providing more accurate state estimates than the LETKF with randomly locatedmore » observations. Additionally, we find that a hybrid ensemble Kalman filter parameter estimation method accurately updates model parameters within the targeted observation context to further improve state estimation.« less

Rapid sampling of local minima in protein energy surface and effective reduction through a multi-objective filter

PubMed Central

2013-01-01

Background Many problems in protein modeling require obtaining a discrete representation of the protein conformational space as an ensemble of conformations. In ab-initio structure prediction, in particular, where the goal is to predict the native structure of a protein chain given its amino-acid sequence, the ensemble needs to satisfy energetic constraints. Given the thermodynamic hypothesis, an effective ensemble contains low-energy conformations which are similar to the native structure. The high-dimensionality of the conformational space and the ruggedness of the underlying energy surface currently make it very difficult to obtain such an ensemble. Recent studies have proposed that Basin Hopping is a promising probabilistic search framework to obtain a discrete representation of the protein energy surface in terms of local minima. Basin Hopping performs a series of structural perturbations followed by energy minimizations with the goal of hopping between nearby energy minima. This approach has been shown to be effective in obtaining conformations near the native structure for small systems. Recent work by us has extended this framework to larger systems through employment of the molecular fragment replacement technique, resulting in rapid sampling of large ensembles. Methods This paper investigates the algorithmic components in Basin Hopping to both understand and control their effect on the sampling of near-native minima. Realizing that such an ensemble is reduced before further refinement in full ab-initio protocols, we take an additional step and analyze the quality of the ensemble retained by ensemble reduction techniques. We propose a novel multi-objective technique based on the Pareto front to filter the ensemble of sampled local minima. Results and conclusions We show that controlling the magnitude of the perturbation allows directly controlling the distance between consecutively-sampled local minima and, in turn, steering the exploration towards conformations near the native structure. For the minimization step, we show that the addition of Metropolis Monte Carlo-based minimization is no more effective than a simple greedy search. Finally, we show that the size of the ensemble of sampled local minima can be effectively and efficiently reduced by a multi-objective filter to obtain a simpler representation of the probed energy surface. PMID:24564970

Ensemble forecasting of short-term system scale irrigation demands using real-time flow data and numerical weather predictions

NASA Astrophysics Data System (ADS)

Perera, Kushan C.; Western, Andrew W.; Robertson, David E.; George, Biju; Nawarathna, Bandara

2016-06-01

Irrigation demands fluctuate in response to weather variations and a range of irrigation management decisions, which creates challenges for water supply system operators. This paper develops a method for real-time ensemble forecasting of irrigation demand and applies it to irrigation command areas of various sizes for lead times of 1 to 5 days. The ensemble forecasts are based on a deterministic time series model coupled with ensemble representations of the various inputs to that model. Forecast inputs include past flow, precipitation, and potential evapotranspiration. These inputs are variously derived from flow observations from a modernized irrigation delivery system; short-term weather forecasts derived from numerical weather prediction models and observed weather data available from automatic weather stations. The predictive performance for the ensemble spread of irrigation demand was quantified using rank histograms, the mean continuous rank probability score (CRPS), the mean CRPS reliability and the temporal mean of the ensemble root mean squared error (MRMSE). The mean forecast was evaluated using root mean squared error (RMSE), Nash-Sutcliffe model efficiency (NSE) and bias. The NSE values for evaluation periods ranged between 0.96 (1 day lead time, whole study area) and 0.42 (5 days lead time, smallest command area). Rank histograms and comparison of MRMSE, mean CRPS, mean CRPS reliability and RMSE indicated that the ensemble spread is generally a reliable representation of the forecast uncertainty for short lead times but underestimates the uncertainty for long lead times.

Lysine acetylation sites prediction using an ensemble of support vector machine classifiers.

PubMed

Xu, Yan; Wang, Xiao-Bo; Ding, Jun; Wu, Ling-Yun; Deng, Nai-Yang

2010-05-07

Lysine acetylation is an essentially reversible and high regulated post-translational modification which regulates diverse protein properties. Experimental identification of acetylation sites is laborious and expensive. Hence, there is significant interest in the development of computational methods for reliable prediction of acetylation sites from amino acid sequences. In this paper we use an ensemble of support vector machine classifiers to perform this work. The experimentally determined acetylation lysine sites are extracted from Swiss-Prot database and scientific literatures. Experiment results show that an ensemble of support vector machine classifiers outperforms single support vector machine classifier and other computational methods such as PAIL and LysAcet on the problem of predicting acetylation lysine sites. The resulting method has been implemented in EnsemblePail, a web server for lysine acetylation sites prediction available at http://www.aporc.org/EnsemblePail/. Copyright (c) 2010 Elsevier Ltd. All rights reserved.

Accurate FRET Measurements within Single Diffusing Biomolecules Using Alternating-Laser Excitation

PubMed Central

Lee, Nam Ki; Kapanidis, Achillefs N.; Wang, You; Michalet, Xavier; Mukhopadhyay, Jayanta; Ebright, Richard H.; Weiss, Shimon

2005-01-01

Fluorescence resonance energy transfer (FRET) between a donor (D) and an acceptor (A) at the single-molecule level currently provides qualitative information about distance, and quantitative information about kinetics of distance changes. Here, we used the sorting ability of confocal microscopy equipped with alternating-laser excitation (ALEX) to measure accurate FRET efficiencies and distances from single molecules, using corrections that account for cross-talk terms that contaminate the FRET-induced signal, and for differences in the detection efficiency and quantum yield of the probes. ALEX yields accurate FRET independent of instrumental factors, such as excitation intensity or detector alignment. Using DNA fragments, we showed that ALEX-based distances agree well with predictions from a cylindrical model of DNA; ALEX-based distances fit better to theory than distances obtained at the ensemble level. Distance measurements within transcription complexes agreed well with ensemble-FRET measurements, and with structural models based on ensemble-FRET and x-ray crystallography. ALEX can benefit structural analysis of biomolecules, especially when such molecules are inaccessible to conventional structural methods due to heterogeneity or transient nature. PMID:15653725

Online Cross-Validation-Based Ensemble Learning

PubMed Central

Benkeser, David; Ju, Cheng; Lendle, Sam; van der Laan, Mark

2017-01-01

Online estimators update a current estimate with a new incoming batch of data without having to revisit past data thereby providing streaming estimates that are scalable to big data. We develop flexible, ensemble-based online estimators of an infinite-dimensional target parameter, such as a regression function, in the setting where data are generated sequentially by a common conditional data distribution given summary measures of the past. This setting encompasses a wide range of time-series models and as special case, models for independent and identically distributed data. Our estimator considers a large library of candidate online estimators and uses online cross-validation to identify the algorithm with the best performance. We show that by basing estimates on the cross-validation-selected algorithm, we are asymptotically guaranteed to perform as well as the true, unknown best-performing algorithm. We provide extensions of this approach including online estimation of the optimal ensemble of candidate online estimators. We illustrate excellent performance of our methods using simulations and a real data example where we make streaming predictions of infectious disease incidence using data from a large database. PMID:28474419

QMEANclust: estimation of protein model quality by combining a composite scoring function with structural density information.

PubMed

Benkert, Pascal; Schwede, Torsten; Tosatto, Silvio Ce

2009-05-20

The selection of the most accurate protein model from a set of alternatives is a crucial step in protein structure prediction both in template-based and ab initio approaches. Scoring functions have been developed which can either return a quality estimate for a single model or derive a score from the information contained in the ensemble of models for a given sequence. Local structural features occurring more frequently in the ensemble have a greater probability of being correct. Within the context of the CASP experiment, these so called consensus methods have been shown to perform considerably better in selecting good candidate models, but tend to fail if the best models are far from the dominant structural cluster. In this paper we show that model selection can be improved if both approaches are combined by pre-filtering the models used during the calculation of the structural consensus. Our recently published QMEAN composite scoring function has been improved by including an all-atom interaction potential term. The preliminary model ranking based on the new QMEAN score is used to select a subset of reliable models against which the structural consensus score is calculated. This scoring function called QMEANclust achieves a correlation coefficient of predicted quality score and GDT_TS of 0.9 averaged over the 98 CASP7 targets and perform significantly better in selecting good models from the ensemble of server models than any other groups participating in the quality estimation category of CASP7. Both scoring functions are also benchmarked on the MOULDER test set consisting of 20 target proteins each with 300 alternatives models generated by MODELLER. QMEAN outperforms all other tested scoring functions operating on individual models, while the consensus method QMEANclust only works properly on decoy sets containing a certain fraction of near-native conformations. We also present a local version of QMEAN for the per-residue estimation of model quality (QMEANlocal) and compare it to a new local consensus-based approach. Improved model selection is obtained by using a composite scoring function operating on single models in order to enrich higher quality models which are subsequently used to calculate the structural consensus. The performance of consensus-based methods such as QMEANclust highly depends on the composition and quality of the model ensemble to be analysed. Therefore, performance estimates for consensus methods based on large meta-datasets (e.g. CASP) might overrate their applicability in more realistic modelling situations with smaller sets of models based on individual methods.

Curve Boxplot: Generalization of Boxplot for Ensembles of Curves.

PubMed

Mirzargar, Mahsa; Whitaker, Ross T; Kirby, Robert M

2014-12-01

In simulation science, computational scientists often study the behavior of their simulations by repeated solutions with variations in parameters and/or boundary values or initial conditions. Through such simulation ensembles, one can try to understand or quantify the variability or uncertainty in a solution as a function of the various inputs or model assumptions. In response to a growing interest in simulation ensembles, the visualization community has developed a suite of methods for allowing users to observe and understand the properties of these ensembles in an efficient and effective manner. An important aspect of visualizing simulations is the analysis of derived features, often represented as points, surfaces, or curves. In this paper, we present a novel, nonparametric method for summarizing ensembles of 2D and 3D curves. We propose an extension of a method from descriptive statistics, data depth, to curves. We also demonstrate a set of rendering and visualization strategies for showing rank statistics of an ensemble of curves, which is a generalization of traditional whisker plots or boxplots to multidimensional curves. Results are presented for applications in neuroimaging, hurricane forecasting and fluid dynamics.

Desynchronization in an ensemble of globally coupled chaotic bursting neuronal oscillators by dynamic delayed feedback control

NASA Astrophysics Data System (ADS)

Che, Yanqiu; Yang, Tingting; Li, Ruixue; Li, Huiyan; Han, Chunxiao; Wang, Jiang; Wei, Xile

2015-09-01

In this paper, we propose a dynamic delayed feedback control approach or desynchronization of chaotic-bursting synchronous activities in an ensemble of globally coupled neuronal oscillators. We demonstrate that the difference signal between an ensemble's mean field and its time delayed state, filtered and fed back to the ensemble, can suppress the self-synchronization in the ensemble. These individual units are decoupled and stabilized at the desired desynchronized states while the stimulation signal reduces to the noise level. The effectiveness of the method is illustrated by examples of two different populations of globally coupled chaotic-bursting neurons. The proposed method has potential for mild, effective and demand-controlled therapy of neurological diseases characterized by pathological synchronization.

Using beta binomials to estimate classification uncertainty for ensemble models.

PubMed

Clark, Robert D; Liang, Wenkel; Lee, Adam C; Lawless, Michael S; Fraczkiewicz, Robert; Waldman, Marvin

2014-01-01

Quantitative structure-activity (QSAR) models have enormous potential for reducing drug discovery and development costs as well as the need for animal testing. Great strides have been made in estimating their overall reliability, but to fully realize that potential, researchers and regulators need to know how confident they can be in individual predictions. Submodels in an ensemble model which have been trained on different subsets of a shared training pool represent multiple samples of the model space, and the degree of agreement among them contains information on the reliability of ensemble predictions. For artificial neural network ensembles (ANNEs) using two different methods for determining ensemble classification - one using vote tallies and the other averaging individual network outputs - we have found that the distribution of predictions across positive vote tallies can be reasonably well-modeled as a beta binomial distribution, as can the distribution of errors. Together, these two distributions can be used to estimate the probability that a given predictive classification will be in error. Large data sets comprised of logP, Ames mutagenicity, and CYP2D6 inhibition data are used to illustrate and validate the method. The distributions of predictions and errors for the training pool accurately predicted the distribution of predictions and errors for large external validation sets, even when the number of positive and negative examples in the training pool were not balanced. Moreover, the likelihood of a given compound being prospectively misclassified as a function of the degree of consensus between networks in the ensemble could in most cases be estimated accurately from the fitted beta binomial distributions for the training pool. Confidence in an individual predictive classification by an ensemble model can be accurately assessed by examining the distributions of predictions and errors as a function of the degree of agreement among the constituent submodels. Further, ensemble uncertainty estimation can often be improved by adjusting the voting or classification threshold based on the parameters of the error distribution. Finally, the profiles for models whose predictive uncertainty estimates are not reliable provide clues to that effect without the need for comparison to an external test set.

Development and application of an atmospheric-hydrologic-hydraulic flood forecasting model driven by TIGGE ensemble forecasts

NASA Astrophysics Data System (ADS)

Bao, Hongjun; Zhao, Linna

2012-02-01

A coupled atmospheric-hydrologic-hydraulic ensemble flood forecasting model, driven by The Observing System Research and Predictability Experiment (THORPEX) Interactive Grand Global Ensemble (TIGGE) data, has been developed for flood forecasting over the Huaihe River. The incorporation of numerical weather prediction (NWP) information into flood forecasting systems may increase forecast lead time from a few hours to a few days. A single NWP model forecast from a single forecast center, however, is insufficient as it involves considerable non-predictable uncertainties and leads to a high number of false alarms. The availability of global ensemble NWP systems through TIGGE offers a new opportunity for flood forecast. The Xinanjiang model used for hydrological rainfall-runoff modeling and the one-dimensional unsteady flow model applied to channel flood routing are coupled with ensemble weather predictions based on the TIGGE data from the Canadian Meteorological Centre (CMC), the European Centre for Medium-Range Weather Forecasts (ECMWF), the UK Met Office (UKMO), and the US National Centers for Environmental Prediction (NCEP). The developed ensemble flood forecasting model is applied to flood forecasting of the 2007 flood season as a test case. The test case is chosen over the upper reaches of the Huaihe River above Lutaizi station with flood diversion and retarding areas. The input flood discharge hydrograph from the main channel to the flood diversion area is estimated with the fixed split ratio of the main channel discharge. The flood flow inside the flood retarding area is calculated as a reservoir with the water balance method. The Muskingum method is used for flood routing in the flood diversion area. A probabilistic discharge and flood inundation forecast is provided as the end product to study the potential benefits of using the TIGGE ensemble forecasts. The results demonstrate satisfactory flood forecasting with clear signals of probability of floods up to a few days in advance, and show that TIGGE ensemble forecast data are a promising tool for forecasting of flood inundation, comparable with that driven by raingauge observations.

Various Approaches for Targeting Quasar Candidates

NASA Astrophysics Data System (ADS)

Zhang, Y.; Zhao, Y.

2015-09-01

With the establishment and development of space-based and ground-based observational facilities, the improvement of scientific output of high-cost facilities is still a hot issue for astronomers. The discovery of new and rare quasars attracts much attention. Different methods to select quasar candidates are in bloom. Among them, some are based on color cuts, some are from multiwavelength data, some rely on variability of quasars, some are based on data mining, and some depend on ensemble methods.

Signal enhancement based on complex curvelet transform and complementary ensemble empirical mode decomposition

NASA Astrophysics Data System (ADS)

Dong, Lieqian; Wang, Deying; Zhang, Yimeng; Zhou, Datong

2017-09-01

Signal enhancement is a necessary step in seismic data processing. In this paper we utilize the complementary ensemble empirical mode decomposition (CEEMD) and complex curvelet transform (CCT) methods to separate signal from random noise further to improve the signal to noise (S/N) ratio. Firstly, the original data with noise is decomposed into a series of intrinsic mode function (IMF) profiles with the aid of CEEMD. Then the IMFs with noise are transformed into CCT domain. By choosing different thresholds which are based on the noise level difference of each IMF profile, the noise in original data can be suppressed. Finally, we illustrate the effectiveness of the approach by simulated and field datasets.

The Role of Scale and Model Bias in ADAPT's Photospheric Eatimation

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

Godinez Vazquez, Humberto C.; Hickmann, Kyle Scott; Arge, Charles Nicholas

2015-05-20

The Air Force Assimilative Photospheric flux Transport model (ADAPT), is a magnetic flux propagation based on Worden-Harvey (WH) model. ADAPT would be used to provide a global photospheric map of the Earth. A data assimilation method based on the Ensemble Kalman Filter (EnKF), a method of Monte Carlo approximation tied with Kalman filtering, is used in calculating the ADAPT models.

Quantification of uncertainty in first-principles predicted mechanical properties of solids: Application to solid ion conductors

NASA Astrophysics Data System (ADS)

Ahmad, Zeeshan; Viswanathan, Venkatasubramanian

2016-08-01

Computationally-guided material discovery is being increasingly employed using a descriptor-based screening through the calculation of a few properties of interest. A precise understanding of the uncertainty associated with first-principles density functional theory calculated property values is important for the success of descriptor-based screening. The Bayesian error estimation approach has been built in to several recently developed exchange-correlation functionals, which allows an estimate of the uncertainty associated with properties related to the ground state energy, for example, adsorption energies. Here, we propose a robust and computationally efficient method for quantifying uncertainty in mechanical properties, which depend on the derivatives of the energy. The procedure involves calculating energies around the equilibrium cell volume with different strains and fitting the obtained energies to the corresponding energy-strain relationship. At each strain, we use instead of a single energy, an ensemble of energies, giving us an ensemble of fits and thereby, an ensemble of mechanical properties associated with each fit, whose spread can be used to quantify its uncertainty. The generation of ensemble of energies is only a post-processing step involving a perturbation of parameters of the exchange-correlation functional and solving for the energy non-self-consistently. The proposed method is computationally efficient and provides a more robust uncertainty estimate compared to the approach of self-consistent calculations employing several different exchange-correlation functionals. We demonstrate the method by calculating the uncertainty bounds for several materials belonging to different classes and having different structures using the developed method. We show that the calculated uncertainty bounds the property values obtained using three different GGA functionals: PBE, PBEsol, and RPBE. Finally, we apply the approach to calculate the uncertainty associated with the DFT-calculated elastic properties of solid state Li-ion and Na-ion conductors.

Using Chou's pseudo amino acid composition based on approximate entropy and an ensemble of AdaBoost classifiers to predict protein subnuclear location.

PubMed

Jiang, Xiaoying; Wei, Rong; Zhao, Yanjun; Zhang, Tongliang

2008-05-01

The knowledge of subnuclear localization in eukaryotic cells is essential for understanding the life function of nucleus. Developing prediction methods and tools for proteins subnuclear localization become important research fields in protein science for special characteristics in cell nuclear. In this study, a novel approach has been proposed to predict protein subnuclear localization. Sample of protein is represented by Pseudo Amino Acid (PseAA) composition based on approximate entropy (ApEn) concept, which reflects the complexity of time series. A novel ensemble classifier is designed incorporating three AdaBoost classifiers. The base classifier algorithms in three AdaBoost are decision stumps, fuzzy K nearest neighbors classifier, and radial basis-support vector machines, respectively. Different PseAA compositions are used as input data of different AdaBoost classifier in ensemble. Genetic algorithm is used to optimize the dimension and weight factor of PseAA composition. Two datasets often used in published works are used to validate the performance of the proposed approach. The obtained results of Jackknife cross-validation test are higher and more balance than them of other methods on same datasets. The promising results indicate that the proposed approach is effective and practical. It might become a useful tool in protein subnuclear localization. The software in Matlab and supplementary materials are available freely by contacting the corresponding author.

Segmentation of Image Ensembles via Latent Atlases

PubMed Central

Van Leemput, Koen; Menze, Bjoern H.; Wells, William M.; Golland, Polina

2010-01-01

Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented. PMID:20580305

A hybrid approach to generating search subspaces in dynamically constrained 4-dimensional data assimilation

NASA Astrophysics Data System (ADS)

Yaremchuk, Max; Martin, Paul; Beattie, Christopher

2017-09-01

Development and maintenance of the linearized and adjoint code for advanced circulation models is a challenging issue, requiring a significant proportion of total effort in operational data assimilation (DA). The ensemble-based DA techniques provide a derivative-free alternative, which appears to be competitive with variational methods in many practical applications. This article proposes a hybrid scheme for generating the search subspaces in the adjoint-free 4-dimensional DA method (a4dVar) that does not use a predefined ensemble. The method resembles 4dVar in that the optimal solution is strongly constrained by model dynamics and search directions are supplied iteratively using information from the current and previous model trajectories generated in the process of optimization. In contrast to 4dVar, which produces a single search direction from exact gradient information, a4dVar employs an ensemble of directions to form a subspace in order to proceed. In the earlier versions of a4dVar, search subspaces were built using the leading EOFs of either the model trajectory or the projections of the model-data misfits onto the range of the background error covariance (BEC) matrix at the current iteration. In the present study, we blend both approaches and explore a hybrid scheme of ensemble generation in order to improve the performance and flexibility of the algorithm. In addition, we introduce balance constraints into the BEC structure and periodically augment the search ensemble with BEC eigenvectors to avoid repeating minimization over already explored subspaces. Performance of the proposed hybrid a4dVar (ha4dVar) method is compared with that of standard 4dVar in a realistic regional configuration assimilating real data into the Navy Coastal Ocean Model (NCOM). It is shown that the ha4dVar converges faster than a4dVar and can be potentially competitive with 4dvar both in terms of the required computational time and the forecast skill.

An Ensemble Method for Classifying Regional Disease Patterns of Diffuse Interstitial Lung Disease Using HRCT Images from Different Vendors.

PubMed

Jun, Sanghoon; Kim, Namkug; Seo, Joon Beom; Lee, Young Kyung; Lynch, David A

2017-12-01

We propose the use of ensemble classifiers to overcome inter-scanner variations in the differentiation of regional disease patterns in high-resolution computed tomography (HRCT) images of diffuse interstitial lung disease patients obtained from different scanners. A total of 600 rectangular 20 × 20-pixel regions of interest (ROIs) on HRCT images obtained from two different scanners (GE and Siemens) and the whole lung area of 92 HRCT images were classified as one of six regional pulmonary disease patterns by two expert radiologists. Textual and shape features were extracted from each ROI and the whole lung parenchyma. For automatic classification, individual and ensemble classifiers were trained and tested with the ROI dataset. We designed the following three experimental sets: an intra-scanner study in which the training and test sets were from the same scanner, an integrated scanner study in which the data from the two scanners were merged, and an inter-scanner study in which the training and test sets were acquired from different scanners. In the ROI-based classification, the ensemble classifiers showed better (p < 0.001) accuracy (89.73%, SD = 0.43) than the individual classifiers (88.38%, SD = 0.31) in the integrated scanner test. The ensemble classifiers also showed partial improvements in the intra- and inter-scanner tests. In the whole lung classification experiment, the quantification accuracies of the ensemble classifiers with integrated training (49.57%) were higher (p < 0.001) than the individual classifiers (48.19%). Furthermore, the ensemble classifiers also showed better performance in both the intra- and inter-scanner experiments. We concluded that the ensemble classifiers provide better performance when using integrated scanner images.

Extreme Value Analysis of hydro meteorological extremes in the ClimEx Large-Ensemble

NASA Astrophysics Data System (ADS)

Wood, R. R.; Martel, J. L.; Willkofer, F.; von Trentini, F.; Schmid, F. J.; Leduc, M.; Frigon, A.; Ludwig, R.

2017-12-01

Many studies show an increase in the magnitude and frequency of hydrological extreme events in the course of climate change. However the contribution of natural variability to the magnitude and frequency of hydrological extreme events is not yet settled. A reliable estimate of extreme events is from great interest for water management and public safety. In the course of the ClimEx Project (www.climex-project.org) a new single-model large-ensemble was created by dynamically downscaling the CanESM2 large-ensemble with the Canadian Regional Climate Model version 5 (CRCM5) for an European Domain and a Northeastern North-American domain. By utilizing the ClimEx 50-Member Large-Ensemble (CRCM5 driven by CanESM2 Large-Ensemble) a thorough analysis of natural variability in extreme events is possible. Are the current extreme value statistical methods able to account for natural variability? How large is the natural variability for e.g. a 1/100 year return period derived from a 50-Member Large-Ensemble for Europe and Northeastern North-America? These questions should be answered by applying various generalized extreme value distributions (GEV) to the ClimEx Large-Ensemble. Hereby various return levels (5-, 10-, 20-, 30-, 60- and 100-years) based on various lengths of time series (20-, 30-, 50-, 100- and 1500-years) should be analyzed for the maximum one day precipitation (RX1d), the maximum three hourly precipitation (RX3h) and the streamflow for selected catchments in Europe. The long time series of the ClimEx Ensemble (7500 years) allows us to give a first reliable estimate of the magnitude and frequency of certain extreme events.

A Feature and Algorithm Selection Method for Improving the Prediction of Protein Structural Class.

PubMed

Ni, Qianwu; Chen, Lei

2017-01-01

Correct prediction of protein structural class is beneficial to investigation on protein functions, regulations and interactions. In recent years, several computational methods have been proposed in this regard. However, based on various features, it is still a great challenge to select proper classification algorithm and extract essential features to participate in classification. In this study, a feature and algorithm selection method was presented for improving the accuracy of protein structural class prediction. The amino acid compositions and physiochemical features were adopted to represent features and thirty-eight machine learning algorithms collected in Weka were employed. All features were first analyzed by a feature selection method, minimum redundancy maximum relevance (mRMR), producing a feature list. Then, several feature sets were constructed by adding features in the list one by one. For each feature set, thirtyeight algorithms were executed on a dataset, in which proteins were represented by features in the set. The predicted classes yielded by these algorithms and true class of each protein were collected to construct a dataset, which were analyzed by mRMR method, yielding an algorithm list. From the algorithm list, the algorithm was taken one by one to build an ensemble prediction model. Finally, we selected the ensemble prediction model with the best performance as the optimal ensemble prediction model. Experimental results indicate that the constructed model is much superior to models using single algorithm and other models that only adopt feature selection procedure or algorithm selection procedure. The feature selection procedure or algorithm selection procedure are really helpful for building an ensemble prediction model that can yield a better performance. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis.

PubMed

Ozçift, Akin

2011-05-01

Supervised classification algorithms are commonly used in the designing of computer-aided diagnosis systems. In this study, we present a resampling strategy based Random Forests (RF) ensemble classifier to improve diagnosis of cardiac arrhythmia. Random forests is an ensemble classifier that consists of many decision trees and outputs the class that is the mode of the class's output by individual trees. In this way, an RF ensemble classifier performs better than a single tree from classification performance point of view. In general, multiclass datasets having unbalanced distribution of sample sizes are difficult to analyze in terms of class discrimination. Cardiac arrhythmia is such a dataset that has multiple classes with small sample sizes and it is therefore adequate to test our resampling based training strategy. The dataset contains 452 samples in fourteen types of arrhythmias and eleven of these classes have sample sizes less than 15. Our diagnosis strategy consists of two parts: (i) a correlation based feature selection algorithm is used to select relevant features from cardiac arrhythmia dataset. (ii) RF machine learning algorithm is used to evaluate the performance of selected features with and without simple random sampling to evaluate the efficiency of proposed training strategy. The resultant accuracy of the classifier is found to be 90.0% and this is a quite high diagnosis performance for cardiac arrhythmia. Furthermore, three case studies, i.e., thyroid, cardiotocography and audiology, are used to benchmark the effectiveness of the proposed method. The results of experiments demonstrated the efficiency of random sampling strategy in training RF ensemble classification algorithm. Copyright © 2011 Elsevier Ltd. All rights reserved.

Evaluation of annual, global seismicity forecasts, including ensemble models

NASA Astrophysics Data System (ADS)

Taroni, Matteo; Zechar, Jeremy; Marzocchi, Warner

2013-04-01

In 2009, the Collaboratory for the Study of the Earthquake Predictability (CSEP) initiated a prototype global earthquake forecast experiment. Three models participated in this experiment for 2009, 2010 and 2011—each model forecast the number of earthquakes above magnitude 6 in 1x1 degree cells that span the globe. Here we use likelihood-based metrics to evaluate the consistency of the forecasts with the observed seismicity. We compare model performance with statistical tests and a new method based on the peer-to-peer gambling score. The results of the comparisons are used to build ensemble models that are a weighted combination of the individual models. Notably, in these experiments the ensemble model always performs significantly better than the single best-performing model. Our results indicate the following: i) time-varying forecasts, if not updated after each major shock, may not provide significant advantages with respect to time-invariant models in 1-year forecast experiments; ii) the spatial distribution seems to be the most important feature to characterize the different forecasting performances of the models; iii) the interpretation of consistency tests may be misleading because some good models may be rejected while trivial models may pass consistency tests; iv) a proper ensemble modeling seems to be a valuable procedure to get the best performing model for practical purposes.

A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method.

PubMed

Liu, Xiao; Wang, Xiaoli; Su, Qiang; Zhang, Mo; Zhu, Yanhong; Wang, Qiugen; Wang, Qian

2017-01-01

Heart disease is one of the most common diseases in the world. The objective of this study is to aid the diagnosis of heart disease using a hybrid classification system based on the ReliefF and Rough Set (RFRS) method. The proposed system contains two subsystems: the RFRS feature selection system and a classification system with an ensemble classifier. The first system includes three stages: (i) data discretization, (ii) feature extraction using the ReliefF algorithm, and (iii) feature reduction using the heuristic Rough Set reduction algorithm that we developed. In the second system, an ensemble classifier is proposed based on the C4.5 classifier. The Statlog (Heart) dataset, obtained from the UCI database, was used for experiments. A maximum classification accuracy of 92.59% was achieved according to a jackknife cross-validation scheme. The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques.

Semantic labeling of high-resolution aerial images using an ensemble of fully convolutional networks

NASA Astrophysics Data System (ADS)

Sun, Xiaofeng; Shen, Shuhan; Lin, Xiangguo; Hu, Zhanyi

2017-10-01

High-resolution remote sensing data classification has been a challenging and promising research topic in the community of remote sensing. In recent years, with the rapid advances of deep learning, remarkable progress has been made in this field, which facilitates a transition from hand-crafted features designing to an automatic end-to-end learning. A deep fully convolutional networks (FCNs) based ensemble learning method is proposed to label the high-resolution aerial images. To fully tap the potentials of FCNs, both the Visual Geometry Group network and a deeper residual network, ResNet, are employed. Furthermore, to enlarge training samples with diversity and gain better generalization, in addition to the commonly used data augmentation methods (e.g., rotation, multiscale, and aspect ratio) in the literature, aerial images from other datasets are also collected for cross-scene learning. Finally, we combine these learned models to form an effective FCN ensemble and refine the results using a fully connected conditional random field graph model. Experiments on the ISPRS 2-D Semantic Labeling Contest dataset show that our proposed end-to-end classification method achieves an overall accuracy of 90.7%, a state-of-the-art in the field.

An Ensemble of Neural Networks for Stock Trading Decision Making

NASA Astrophysics Data System (ADS)

Chang, Pei-Chann; Liu, Chen-Hao; Fan, Chin-Yuan; Lin, Jun-Lin; Lai, Chih-Ming

Stock turning signals detection are very interesting subject arising in numerous financial and economic planning problems. In this paper, Ensemble Neural Network system with Intelligent Piecewise Linear Representation for stock turning points detection is presented. The Intelligent piecewise linear representation method is able to generate numerous stocks turning signals from the historic data base, then Ensemble Neural Network system will be applied to train the pattern and retrieve similar stock price patterns from historic data for training. These turning signals represent short-term and long-term trading signals for selling or buying stocks from the market which are applied to forecast the future turning points from the set of test data. Experimental results demonstrate that the hybrid system can make a significant and constant amount of profit when compared with other approaches using stock data available in the market.

Representing Color Ensembles.

PubMed

Chetverikov, Andrey; Campana, Gianluca; Kristjánsson, Árni

2017-10-01

Colors are rarely uniform, yet little is known about how people represent color distributions. We introduce a new method for studying color ensembles based on intertrial learning in visual search. Participants looked for an oddly colored diamond among diamonds with colors taken from either uniform or Gaussian color distributions. On test trials, the targets had various distances in feature space from the mean of the preceding distractor color distribution. Targets on test trials therefore served as probes into probabilistic representations of distractor colors. Test-trial response times revealed a striking similarity between the physical distribution of colors and their internal representations. The results demonstrate that the visual system represents color ensembles in a more detailed way than previously thought, coding not only mean and variance but, most surprisingly, the actual shape (uniform or Gaussian) of the distribution of colors in the environment.

IDM-PhyChm-Ens: intelligent decision-making ensemble methodology for classification of human breast cancer using physicochemical properties of amino acids.

PubMed

Ali, Safdar; Majid, Abdul; Khan, Asifullah

2014-04-01

Development of an accurate and reliable intelligent decision-making method for the construction of cancer diagnosis system is one of the fast growing research areas of health sciences. Such decision-making system can provide adequate information for cancer diagnosis and drug discovery. Descriptors derived from physicochemical properties of protein sequences are very useful for classifying cancerous proteins. Recently, several interesting research studies have been reported on breast cancer classification. To this end, we propose the exploitation of the physicochemical properties of amino acids in protein primary sequences such as hydrophobicity (Hd) and hydrophilicity (Hb) for breast cancer classification. Hd and Hb properties of amino acids, in recent literature, are reported to be quite effective in characterizing the constituent amino acids and are used to study protein foldings, interactions, structures, and sequence-order effects. Especially, using these physicochemical properties, we observed that proline, serine, tyrosine, cysteine, arginine, and asparagine amino acids offer high discrimination between cancerous and healthy proteins. In addition, unlike traditional ensemble classification approaches, the proposed 'IDM-PhyChm-Ens' method was developed by combining the decision spaces of a specific classifier trained on different feature spaces. The different feature spaces used were amino acid composition, split amino acid composition, and pseudo amino acid composition. Consequently, we have exploited different feature spaces using Hd and Hb properties of amino acids to develop an accurate method for classification of cancerous protein sequences. We developed ensemble classifiers using diverse learning algorithms such as random forest (RF), support vector machines (SVM), and K-nearest neighbor (KNN) trained on different feature spaces. We observed that ensemble-RF, in case of cancer classification, performed better than ensemble-SVM and ensemble-KNN. Our analysis demonstrates that ensemble-RF, ensemble-SVM and ensemble-KNN are more effective than their individual counterparts. The proposed 'IDM-PhyChm-Ens' method has shown improved performance compared to existing techniques.

Avoiding the ensemble decorrelation problem using member-by-member post-processing

NASA Astrophysics Data System (ADS)

Van Schaeybroeck, Bert; Vannitsem, Stéphane

2014-05-01

Forecast calibration or post-processing has become a standard tool in atmospheric and climatological science due to the presence of systematic initial condition and model errors. For ensemble forecasts the most competitive methods derive from the assumption of a fixed ensemble distribution. However, when independently applying such 'statistical' methods at different locations, lead times or for multiple variables the correlation structure for individual ensemble members is destroyed. Instead of reastablishing the correlation structure as in Schefzik et al. (2013) we instead propose a calibration method that avoids such problem by correcting each ensemble member individually. Moreover, we analyse the fundamental mechanisms by which the probabilistic ensemble skill can be enhanced. In terms of continuous ranked probability score, our member-by-member approach amounts to skill gain that extends for lead times far beyond the error doubling time and which is as good as the one of the most competitive statistical approach, non-homogeneous Gaussian regression (Gneiting et al. 2005). Besides the conservation of correlation structure, additional benefits arise including the fact that higher-order ensemble moments like kurtosis and skewness are inherited from the uncorrected forecasts. Our detailed analysis is performed in the context of the Kuramoto-Sivashinsky equation and different simple models but the results extent succesfully to the ensemble forecast of the European Centre for Medium-Range Weather Forecasts (Van Schaeybroeck and Vannitsem, 2013, 2014) . References [1] Gneiting, T., Raftery, A. E., Westveld, A., Goldman, T., 2005: Calibrated probabilistic forecasting using ensemble model output statistics and minimum CRPS estimation. Mon. Weather Rev. 133, 1098-1118. [2] Schefzik, R., T.L. Thorarinsdottir, and T. Gneiting, 2013: Uncertainty Quantification in Complex Simulation Models Using Ensemble Copula Coupling. To appear in Statistical Science 28. [3] Van Schaeybroeck, B., and S. Vannitsem, 2013: Reliable probabilities through statistical post-processing of ensemble forecasts. Proceedings of the European Conference on Complex Systems 2012, Springer proceedings on complexity, XVI, p. 347-352. [4] Van Schaeybroeck, B., and S. Vannitsem, 2014: Ensemble post-processing using member-by-member approaches: theoretical aspects, under review.

Estimating uncertainty of Full Waveform Inversion with Ensemble-based methods

NASA Astrophysics Data System (ADS)

Thurin, J.; Brossier, R.; Métivier, L.

2017-12-01

Uncertainty estimation is one key feature of tomographic applications for robust interpretation. However, this information is often missing in the frame of large scale linearized inversions, and only the results at convergence are shown, despite the ill-posed nature of the problem. This issue is common in the Full Waveform Inversion community.While few methodologies have already been proposed in the literature, standard FWI workflows do not include any systematic uncertainty quantifications methods yet, but often try to assess the result's quality through cross-comparison with other results from seismic or comparison with other geophysical data. With the development of large seismic networks/surveys, the increase in computational power and the more and more systematic application of FWI, it is crucial to tackle this problem and to propose robust and affordable workflows, in order to address the uncertainty quantification problem faced for near surface targets, crustal exploration, as well as regional and global scales.In this work (Thurin et al., 2017a,b), we propose an approach which takes advantage of the Ensemble Transform Kalman Filter (ETKF) proposed by Bishop et al., (2001), in order to estimate a low-rank approximation of the posterior covariance matrix of the FWI problem, allowing us to evaluate some uncertainty information of the solution. Instead of solving the FWI problem through a Bayesian inversion with the ETKF, we chose to combine a conventional FWI, based on local optimization, and the ETKF strategies. This scheme allows combining the efficiency of local optimization for solving large scale inverse problems and make the sampling of the local solution space possible thanks to its embarrassingly parallel property. References:Bishop, C. H., Etherton, B. J. and Majumdar, S. J., 2001. Adaptive sampling with the ensemble transform Kalman filter. Part I: Theoretical aspects. Monthly weather review, 129(3), 420-436.Thurin, J., Brossier, R. and Métivier, L. 2017,a.: Ensemble-Based Uncertainty Estimation in Full Waveform Inversion. 79th EAGE Conference and Exhibition 2017, (12 - 15 June, 2017)Thurin, J., Brossier, R. and Métivier, L. 2017,b.: An Ensemble-Transform Kalman Filter - Full Waveform Inversion scheme for Uncertainty estimation; SEG Technical Program Expanded Abstracts 2012

Reinforce: An Ensemble Approach for Inferring PPI Network from AP-MS Data.

PubMed

Tian, Bo; Duan, Qiong; Zhao, Can; Teng, Ben; He, Zengyou

2017-05-17

Affinity Purification-Mass Spectrometry (AP-MS) is one of the most important technologies for constructing protein-protein interaction (PPI) networks. In this paper, we propose an ensemble method, Reinforce, for inferring PPI network from AP-MS data set. The new algorithm named Reinforce is based on rank aggregation and false discovery rate control. Under the null hypothesis that the interaction scores from different scoring methods are randomly generated, Reinforce follows three steps to integrate multiple ranking results from different algorithms or different data sets. The experimental results show that Reinforce can get more stable and accurate inference results than existing algorithms. The source codes of Reinforce and data sets used in the experiments are available at: https://sourceforge.net/projects/reinforce/.

Inferring Pre-shock Acoustic Field From Post-shock Pitot Pressure Measurement

NASA Astrophysics Data System (ADS)

Wang, Jian-Xun; Zhang, Chao; Duan, Lian; Xiao, Heng; Virginia Tech Team; Missouri Univ of Sci; Tech Team

2017-11-01

Linear interaction analysis (LIA) and iterative ensemble Kalman method are used to convert post-shock Pitot pressure fluctuations to static pressure fluctuations in front of the shock. The LIA is used as the forward model for the transfer function associated with a homogeneous field of acoustic waves passing through a nominally normal shock wave. The iterative ensemble Kalman method is then employed to infer the spectrum of upstream acoustic waves based on the post-shock Pitot pressure measured at a single point. Several test cases with synthetic and real measurement data are used to demonstrate the merits of the proposed inference scheme. The study provides the basis for measuring tunnel freestream noise with intrusive probes in noisy supersonic wind tunnels.

Parameterizations for ensemble Kalman inversion

NASA Astrophysics Data System (ADS)

Chada, Neil K.; Iglesias, Marco A.; Roininen, Lassi; Stuart, Andrew M.

2018-05-01

The use of ensemble methods to solve inverse problems is attractive because it is a derivative-free methodology which is also well-adapted to parallelization. In its basic iterative form the method produces an ensemble of solutions which lie in the linear span of the initial ensemble. Choice of the parameterization of the unknown field is thus a key component of the success of the method. We demonstrate how both geometric ideas and hierarchical ideas can be used to design effective parameterizations for a number of applied inverse problems arising in electrical impedance tomography, groundwater flow and source inversion. In particular we show how geometric ideas, including the level set method, can be used to reconstruct piecewise continuous fields, and we show how hierarchical methods can be used to learn key parameters in continuous fields, such as length-scales, resulting in improved reconstructions. Geometric and hierarchical ideas are combined in the level set method to find piecewise constant reconstructions with interfaces of unknown topology.

Advanced Atmospheric Ensemble Modeling Techniques

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

Buckley, R.; Chiswell, S.; Kurzeja, R.

Ensemble modeling (EM), the creation of multiple atmospheric simulations for a given time period, has become an essential tool for characterizing uncertainties in model predictions. We explore two novel ensemble modeling techniques: (1) perturbation of model parameters (Adaptive Programming, AP), and (2) data assimilation (Ensemble Kalman Filter, EnKF). The current research is an extension to work from last year and examines transport on a small spatial scale (<100 km) in complex terrain, for more rigorous testing of the ensemble technique. Two different release cases were studied, a coastal release (SF6) and an inland release (Freon) which consisted of two releasemore » times. Observations of tracer concentration and meteorology are used to judge the ensemble results. In addition, adaptive grid techniques have been developed to reduce required computing resources for transport calculations. Using a 20- member ensemble, the standard approach generated downwind transport that was quantitatively good for both releases; however, the EnKF method produced additional improvement for the coastal release where the spatial and temporal differences due to interior valley heating lead to the inland movement of the plume. The AP technique showed improvements for both release cases, with more improvement shown in the inland release. This research demonstrated that transport accuracy can be improved when models are adapted to a particular location/time or when important local data is assimilated into the simulation and enhances SRNL’s capability in atmospheric transport modeling in support of its current customer base and local site missions, as well as our ability to attract new customers within the intelligence community.« less

Building Diversified Multiple Trees for classification in high dimensional noisy biomedical data.

PubMed

Li, Jiuyong; Liu, Lin; Liu, Jixue; Green, Ryan

2017-12-01

It is common that a trained classification model is applied to the operating data that is deviated from the training data because of noise. This paper will test an ensemble method, Diversified Multiple Tree (DMT), on its capability for classifying instances in a new laboratory using the classifier built on the instances of another laboratory. DMT is tested on three real world biomedical data sets from different laboratories in comparison with four benchmark ensemble methods, AdaBoost, Bagging, Random Forests, and Random Trees. Experiments have also been conducted on studying the limitation of DMT and its possible variations. Experimental results show that DMT is significantly more accurate than other benchmark ensemble classifiers on classifying new instances of a different laboratory from the laboratory where instances are used to build the classifier. This paper demonstrates that an ensemble classifier, DMT, is more robust in classifying noisy data than other widely used ensemble methods. DMT works on the data set that supports multiple simple trees.

Probabilistic Climate Scenario Information for Risk Assessment

NASA Astrophysics Data System (ADS)

Dairaku, K.; Ueno, G.; Takayabu, I.

2014-12-01

Climate information and services for Impacts, Adaptation and Vulnerability (IAV) Assessments are of great concern. In order to develop probabilistic regional climate information that represents the uncertainty in climate scenario experiments in Japan, we compared the physics ensemble experiments using the 60km global atmospheric model of the Meteorological Research Institute (MRI-AGCM) with multi-model ensemble experiments with global atmospheric-ocean coupled models (CMIP3) of SRES A1b scenario experiments. The MRI-AGCM shows relatively good skills particularly in tropics for temperature and geopotential height. Variability in surface air temperature of physical ensemble experiments with MRI-AGCM was within the range of one standard deviation of the CMIP3 model in the Asia region. On the other hand, the variability of precipitation was relatively well represented compared with the variation of the CMIP3 models. Models which show the similar reproducibility in the present climate shows different future climate change. We couldn't find clear relationships between present climate and future climate change in temperature and precipitation. We develop a new method to produce probabilistic information of climate change scenarios by weighting model ensemble experiments based on a regression model (Krishnamurti et al., Science, 1999). The method can be easily applicable to other regions and other physical quantities, and also to downscale to finer-scale dependent on availability of observation dataset. The prototype of probabilistic information in Japan represents the quantified structural uncertainties of multi-model ensemble experiments of climate change scenarios. Acknowledgments: This study was supported by the SOUSEI Program, funded by Ministry of Education, Culture, Sports, Science and Technology, Government of Japan.

An Ensemble Successive Project Algorithm for Liquor Detection Using Near Infrared Sensor.

PubMed

Qu, Fangfang; Ren, Dong; Wang, Jihua; Zhang, Zhong; Lu, Na; Meng, Lei

2016-01-11

Spectral analysis technique based on near infrared (NIR) sensor is a powerful tool for complex information processing and high precision recognition, and it has been widely applied to quality analysis and online inspection of agricultural products. This paper proposes a new method to address the instability of small sample sizes in the successive projections algorithm (SPA) as well as the lack of association between selected variables and the analyte. The proposed method is an evaluated bootstrap ensemble SPA method (EBSPA) based on a variable evaluation index (EI) for variable selection, and is applied to the quantitative prediction of alcohol concentrations in liquor using NIR sensor. In the experiment, the proposed EBSPA with three kinds of modeling methods are established to test their performance. In addition, the proposed EBSPA combined with partial least square is compared with other state-of-the-art variable selection methods. The results show that the proposed method can solve the defects of SPA and it has the best generalization performance and stability. Furthermore, the physical meaning of the selected variables from the near infrared sensor data is clear, which can effectively reduce the variables and improve their prediction accuracy.

Skin lesion computational diagnosis of dermoscopic images: Ensemble models based on input feature manipulation.

PubMed

Oliveira, Roberta B; Pereira, Aledir S; Tavares, João Manuel R S

2017-10-01

The number of deaths worldwide due to melanoma has risen in recent times, in part because melanoma is the most aggressive type of skin cancer. Computational systems have been developed to assist dermatologists in early diagnosis of skin cancer, or even to monitor skin lesions. However, there still remains a challenge to improve classifiers for the diagnosis of such skin lesions. The main objective of this article is to evaluate different ensemble classification models based on input feature manipulation to diagnose skin lesions. Input feature manipulation processes are based on feature subset selections from shape properties, colour variation and texture analysis to generate diversity for the ensemble models. Three subset selection models are presented here: (1) a subset selection model based on specific feature groups, (2) a correlation-based subset selection model, and (3) a subset selection model based on feature selection algorithms. Each ensemble classification model is generated using an optimum-path forest classifier and integrated with a majority voting strategy. The proposed models were applied on a set of 1104 dermoscopic images using a cross-validation procedure. The best results were obtained by the first ensemble classification model that generates a feature subset ensemble based on specific feature groups. The skin lesion diagnosis computational system achieved 94.3% accuracy, 91.8% sensitivity and 96.7% specificity. The input feature manipulation process based on specific feature subsets generated the greatest diversity for the ensemble classification model with very promising results. Copyright © 2017 Elsevier B.V. All rights reserved.

New technique for ensemble dressing combining Multimodel SuperEnsemble and precipitation PDF

NASA Astrophysics Data System (ADS)

Cane, D.; Milelli, M.

2009-09-01

The Multimodel SuperEnsemble technique (Krishnamurti et al., Science 285, 1548-1550, 1999) is a postprocessing method for the estimation of weather forecast parameters reducing direct model output errors. It differs from other ensemble analysis techniques by the use of an adequate weighting of the input forecast models to obtain a combined estimation of meteorological parameters. Weights are calculated by least-square minimization of the difference between the model and the observed field during a so-called training period. Although it can be applied successfully on the continuous parameters like temperature, humidity, wind speed and mean sea level pressure (Cane and Milelli, Meteorologische Zeitschrift, 15, 2, 2006), the Multimodel SuperEnsemble gives good results also when applied on the precipitation, a parameter quite difficult to handle with standard post-processing methods. Here we present our methodology for the Multimodel precipitation forecasts applied on a wide spectrum of results over Piemonte very dense non-GTS weather station network. We will focus particularly on an accurate statistical method for bias correction and on the ensemble dressing in agreement with the observed precipitation forecast-conditioned PDF. Acknowledgement: this work is supported by the Italian Civil Defence Department.

Ensemble Classifier Strategy Based on Transient Feature Fusion in Electronic Nose

NASA Astrophysics Data System (ADS)

Bagheri, Mohammad Ali; Montazer, Gholam Ali

2011-09-01

In this paper, we test the performance of several ensembles of classifiers and each base learner has been trained on different types of extracted features. Experimental results show the potential benefits introduced by the usage of simple ensemble classification systems for the integration of different types of transient features.

Shallow cumuli ensemble statistics for development of a stochastic parameterization

NASA Astrophysics Data System (ADS)

Sakradzija, Mirjana; Seifert, Axel; Heus, Thijs

2014-05-01

According to a conventional deterministic approach to the parameterization of moist convection in numerical atmospheric models, a given large scale forcing produces an unique response from the unresolved convective processes. This representation leaves out the small-scale variability of convection, as it is known from the empirical studies of deep and shallow convective cloud ensembles, there is a whole distribution of sub-grid states corresponding to the given large scale forcing. Moreover, this distribution gets broader with the increasing model resolution. This behavior is also consistent with our theoretical understanding of a coarse-grained nonlinear system. We propose an approach to represent the variability of the unresolved shallow-convective states, including the dependence of the sub-grid states distribution spread and shape on the model horizontal resolution. Starting from the Gibbs canonical ensemble theory, Craig and Cohen (2006) developed a theory for the fluctuations in a deep convective ensemble. The micro-states of a deep convective cloud ensemble are characterized by the cloud-base mass flux, which, according to the theory, is exponentially distributed (Boltzmann distribution). Following their work, we study the shallow cumulus ensemble statistics and the distribution of the cloud-base mass flux. We employ a Large-Eddy Simulation model (LES) and a cloud tracking algorithm, followed by a conditional sampling of clouds at the cloud base level, to retrieve the information about the individual cloud life cycles and the cloud ensemble as a whole. In the case of shallow cumulus cloud ensemble, the distribution of micro-states is a generalized exponential distribution. Based on the empirical and theoretical findings, a stochastic model has been developed to simulate the shallow convective cloud ensemble and to test the convective ensemble theory. Stochastic model simulates a compound random process, with the number of convective elements drawn from a Poisson distribution, and cloud properties sub-sampled from a generalized ensemble distribution. We study the role of the different cloud subtypes in a shallow convective ensemble and how the diverse cloud properties and cloud lifetimes affect the system macro-state. To what extent does the cloud-base mass flux distribution deviate from the simple Boltzmann distribution and how does it affect the results from the stochastic model? Is the memory, provided by the finite lifetime of individual clouds, of importance for the ensemble statistics? We also test for the minimal information given as an input to the stochastic model, able to reproduce the ensemble mean statistics and the variability in a convective ensemble. An important property of the resulting distribution of the sub-grid convective states is its scale-adaptivity - the smaller the grid-size, the broader the compound distribution of the sub-grid states.

Ensemble variant interpretation methods to predict enzyme activity and assign pathogenicity in the CAGI4 NAGLU (Human N-acetyl-glucosaminidase) and UBE2I (Human SUMO-ligase) challenges.

PubMed

Yin, Yizhou; Kundu, Kunal; Pal, Lipika R; Moult, John

2017-09-01

CAGI (Critical Assessment of Genome Interpretation) conducts community experiments to determine the state of the art in relating genotype to phenotype. Here, we report results obtained using newly developed ensemble methods to address two CAGI4 challenges: enzyme activity for population missense variants found in NAGLU (Human N-acetyl-glucosaminidase) and random missense mutations in Human UBE2I (Human SUMO E2 ligase), assayed in a high-throughput competitive yeast complementation procedure. The ensemble methods are effective, ranked second for SUMO-ligase and third for NAGLU, according to the CAGI independent assessors. However, in common with other methods used in CAGI, there are large discrepancies between predicted and experimental activities for a subset of variants. Analysis of the structural context provides some insight into these. Post-challenge analysis shows that the ensemble methods are also effective at assigning pathogenicity for the NAGLU variants. In the clinic, providing an estimate of the reliability of pathogenic assignments is the key. We have also used the NAGLU dataset to show that ensemble methods have considerable potential for this task, and are already reliable enough for use with a subset of mutations. © 2017 Wiley Periodicals, Inc.

Gridded Calibration of Ensemble Wind Vector Forecasts Using Ensemble Model Output Statistics

NASA Astrophysics Data System (ADS)

Lazarus, S. M.; Holman, B. P.; Splitt, M. E.

2017-12-01

A computationally efficient method is developed that performs gridded post processing of ensemble wind vector forecasts. An expansive set of idealized WRF model simulations are generated to provide physically consistent high resolution winds over a coastal domain characterized by an intricate land / water mask. Ensemble model output statistics (EMOS) is used to calibrate the ensemble wind vector forecasts at observation locations. The local EMOS predictive parameters (mean and variance) are then spread throughout the grid utilizing flow-dependent statistical relationships extracted from the downscaled WRF winds. Using data withdrawal and 28 east central Florida stations, the method is applied to one year of 24 h wind forecasts from the Global Ensemble Forecast System (GEFS). Compared to the raw GEFS, the approach improves both the deterministic and probabilistic forecast skill. Analysis of multivariate rank histograms indicate the post processed forecasts are calibrated. Two downscaling case studies are presented, a quiescent easterly flow event and a frontal passage. Strengths and weaknesses of the approach are presented and discussed.

Pairwise Classifier Ensemble with Adaptive Sub-Classifiers for fMRI Pattern Analysis.

PubMed

Kim, Eunwoo; Park, HyunWook

2017-02-01

The multi-voxel pattern analysis technique is applied to fMRI data for classification of high-level brain functions using pattern information distributed over multiple voxels. In this paper, we propose a classifier ensemble for multiclass classification in fMRI analysis, exploiting the fact that specific neighboring voxels can contain spatial pattern information. The proposed method converts the multiclass classification to a pairwise classifier ensemble, and each pairwise classifier consists of multiple sub-classifiers using an adaptive feature set for each class-pair. Simulated and real fMRI data were used to verify the proposed method. Intra- and inter-subject analyses were performed to compare the proposed method with several well-known classifiers, including single and ensemble classifiers. The comparison results showed that the proposed method can be generally applied to multiclass classification in both simulations and real fMRI analyses.

Modified complementary ensemble empirical mode decomposition and intrinsic mode functions evaluation index for high-speed train gearbox fault diagnosis

NASA Astrophysics Data System (ADS)

Chen, Dongyue; Lin, Jianhui; Li, Yanping

2018-06-01

Complementary ensemble empirical mode decomposition (CEEMD) has been developed for the mode-mixing problem in Empirical Mode Decomposition (EMD) method. Compared to the ensemble empirical mode decomposition (EEMD), the CEEMD method reduces residue noise in the signal reconstruction. Both CEEMD and EEMD need enough ensemble number to reduce the residue noise, and hence it would be too much computation cost. Moreover, the selection of intrinsic mode functions (IMFs) for further analysis usually depends on experience. A modified CEEMD method and IMFs evaluation index are proposed with the aim of reducing the computational cost and select IMFs automatically. A simulated signal and in-service high-speed train gearbox vibration signals are employed to validate the proposed method in this paper. The results demonstrate that the modified CEEMD can decompose the signal efficiently with less computation cost, and the IMFs evaluation index can select the meaningful IMFs automatically.

Improving Classification Performance through an Advanced Ensemble Based Heterogeneous Extreme Learning Machines.

PubMed

Abuassba, Adnan O M; Zhang, Dezheng; Luo, Xiong; Shaheryar, Ahmad; Ali, Hazrat

2017-01-01

Extreme Learning Machine (ELM) is a fast-learning algorithm for a single-hidden layer feedforward neural network (SLFN). It often has good generalization performance. However, there are chances that it might overfit the training data due to having more hidden nodes than needed. To address the generalization performance, we use a heterogeneous ensemble approach. We propose an Advanced ELM Ensemble (AELME) for classification, which includes Regularized-ELM, L 2 -norm-optimized ELM (ELML2), and Kernel-ELM. The ensemble is constructed by training a randomly chosen ELM classifier on a subset of training data selected through random resampling. The proposed AELM-Ensemble is evolved by employing an objective function of increasing diversity and accuracy among the final ensemble. Finally, the class label of unseen data is predicted using majority vote approach. Splitting the training data into subsets and incorporation of heterogeneous ELM classifiers result in higher prediction accuracy, better generalization, and a lower number of base classifiers, as compared to other models (Adaboost, Bagging, Dynamic ELM ensemble, data splitting ELM ensemble, and ELM ensemble). The validity of AELME is confirmed through classification on several real-world benchmark datasets.

Improving Classification Performance through an Advanced Ensemble Based Heterogeneous Extreme Learning Machines

PubMed Central

Abuassba, Adnan O. M.; Ali, Hazrat

2017-01-01

Extreme Learning Machine (ELM) is a fast-learning algorithm for a single-hidden layer feedforward neural network (SLFN). It often has good generalization performance. However, there are chances that it might overfit the training data due to having more hidden nodes than needed. To address the generalization performance, we use a heterogeneous ensemble approach. We propose an Advanced ELM Ensemble (AELME) for classification, which includes Regularized-ELM, L2-norm-optimized ELM (ELML2), and Kernel-ELM. The ensemble is constructed by training a randomly chosen ELM classifier on a subset of training data selected through random resampling. The proposed AELM-Ensemble is evolved by employing an objective function of increasing diversity and accuracy among the final ensemble. Finally, the class label of unseen data is predicted using majority vote approach. Splitting the training data into subsets and incorporation of heterogeneous ELM classifiers result in higher prediction accuracy, better generalization, and a lower number of base classifiers, as compared to other models (Adaboost, Bagging, Dynamic ELM ensemble, data splitting ELM ensemble, and ELM ensemble). The validity of AELME is confirmed through classification on several real-world benchmark datasets. PMID:28546808

Monthly ENSO Forecast Skill and Lagged Ensemble Size

PubMed Central

DelSole, T.; Tippett, M.K.; Pegion, K.

2018-01-01

Abstract The mean square error (MSE) of a lagged ensemble of monthly forecasts of the Niño 3.4 index from the Climate Forecast System (CFSv2) is examined with respect to ensemble size and configuration. Although the real‐time forecast is initialized 4 times per day, it is possible to infer the MSE for arbitrary initialization frequency and for burst ensembles by fitting error covariances to a parametric model and then extrapolating to arbitrary ensemble size and initialization frequency. Applying this method to real‐time forecasts, we find that the MSE consistently reaches a minimum for a lagged ensemble size between one and eight days, when four initializations per day are included. This ensemble size is consistent with the 8–10 day lagged ensemble configuration used operationally. Interestingly, the skill of both ensemble configurations is close to the estimated skill of the infinite ensemble. The skill of the weighted, lagged, and burst ensembles are found to be comparable. Certain unphysical features of the estimated error growth were tracked down to problems with the climatology and data discontinuities. PMID:29937973

Monthly ENSO Forecast Skill and Lagged Ensemble Size

NASA Astrophysics Data System (ADS)

Trenary, L.; DelSole, T.; Tippett, M. K.; Pegion, K.

2018-04-01

The mean square error (MSE) of a lagged ensemble of monthly forecasts of the Niño 3.4 index from the Climate Forecast System (CFSv2) is examined with respect to ensemble size and configuration. Although the real-time forecast is initialized 4 times per day, it is possible to infer the MSE for arbitrary initialization frequency and for burst ensembles by fitting error covariances to a parametric model and then extrapolating to arbitrary ensemble size and initialization frequency. Applying this method to real-time forecasts, we find that the MSE consistently reaches a minimum for a lagged ensemble size between one and eight days, when four initializations per day are included. This ensemble size is consistent with the 8-10 day lagged ensemble configuration used operationally. Interestingly, the skill of both ensemble configurations is close to the estimated skill of the infinite ensemble. The skill of the weighted, lagged, and burst ensembles are found to be comparable. Certain unphysical features of the estimated error growth were tracked down to problems with the climatology and data discontinuities.

An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines.

PubMed

Amozegar, M; Khorasani, K

2016-04-01

In this paper, a new approach for Fault Detection and Isolation (FDI) of gas turbine engines is proposed by developing an ensemble of dynamic neural network identifiers. For health monitoring of the gas turbine engine, its dynamics is first identified by constructing three separate or individual dynamic neural network architectures. Specifically, a dynamic multi-layer perceptron (MLP), a dynamic radial-basis function (RBF) neural network, and a dynamic support vector machine (SVM) are trained to individually identify and represent the gas turbine engine dynamics. Next, three ensemble-based techniques are developed to represent the gas turbine engine dynamics, namely, two heterogeneous ensemble models and one homogeneous ensemble model. It is first shown that all ensemble approaches do significantly improve the overall performance and accuracy of the developed system identification scheme when compared to each of the stand-alone solutions. The best selected stand-alone model (i.e., the dynamic RBF network) and the best selected ensemble architecture (i.e., the heterogeneous ensemble) in terms of their performances in achieving an accurate system identification are then selected for solving the FDI task. The required residual signals are generated by using both a single model-based solution and an ensemble-based solution under various gas turbine engine health conditions. Our extensive simulation studies demonstrate that the fault detection and isolation task achieved by using the residuals that are obtained from the dynamic ensemble scheme results in a significantly more accurate and reliable performance as illustrated through detailed quantitative confusion matrix analysis and comparative studies. Copyright © 2016 Elsevier Ltd. All rights reserved.

Nonlinear problems in data-assimilation : Can synchronization help?

NASA Astrophysics Data System (ADS)

Tribbia, J. J.; Duane, G. S.

2009-12-01

Over the past several years, operational weather centers have initiated ensemble prediction and assimilation techniques to estimate the error covariance of forecasts in the short and the medium range. The ensemble techniques used are based on linear methods. The theory This technique s been shown to be a useful indicator of skill in the linear range where forecast errors are small relative to climatological variance. While this advance has been impressive, there are still ad hoc aspects of its use in practice, like the need for covariance inflation which are troubling. Furthermore, to be of utility in the nonlinear range an ensemble assimilation and prediction method must be capable of giving probabilistic information for the situation where a probability density forecast becomes multi-modal. A prototypical, simplest example of such a situation is the planetary-wave regime transition where the pdf is bimodal. Our recent research show how the inconsistencies and extensions of linear methodology can be consistently treated using the paradigm of synchronization which views the problems of assimilation and forecasting as that of optimizing the forecast model state with respect to the future evolution of the atmosphere.

Multiensemble Markov models of molecular thermodynamics and kinetics.

PubMed

Wu, Hao; Paul, Fabian; Wehmeyer, Christoph; Noé, Frank

2016-06-07

We introduce the general transition-based reweighting analysis method (TRAM), a statistically optimal approach to integrate both unbiased and biased molecular dynamics simulations, such as umbrella sampling or replica exchange. TRAM estimates a multiensemble Markov model (MEMM) with full thermodynamic and kinetic information at all ensembles. The approach combines the benefits of Markov state models-clustering of high-dimensional spaces and modeling of complex many-state systems-with those of the multistate Bennett acceptance ratio of exploiting biased or high-temperature ensembles to accelerate rare-event sampling. TRAM does not depend on any rate model in addition to the widely used Markov state model approximation, but uses only fundamental relations such as detailed balance and binless reweighting of configurations between ensembles. Previous methods, including the multistate Bennett acceptance ratio, discrete TRAM, and Markov state models are special cases and can be derived from the TRAM equations. TRAM is demonstrated by efficiently computing MEMMs in cases where other estimators break down, including the full thermodynamics and rare-event kinetics from high-dimensional simulation data of an all-atom protein-ligand binding model.

Multiensemble Markov models of molecular thermodynamics and kinetics

PubMed Central

Wu, Hao; Paul, Fabian; Noé, Frank

2016-01-01

We introduce the general transition-based reweighting analysis method (TRAM), a statistically optimal approach to integrate both unbiased and biased molecular dynamics simulations, such as umbrella sampling or replica exchange. TRAM estimates a multiensemble Markov model (MEMM) with full thermodynamic and kinetic information at all ensembles. The approach combines the benefits of Markov state models—clustering of high-dimensional spaces and modeling of complex many-state systems—with those of the multistate Bennett acceptance ratio of exploiting biased or high-temperature ensembles to accelerate rare-event sampling. TRAM does not depend on any rate model in addition to the widely used Markov state model approximation, but uses only fundamental relations such as detailed balance and binless reweighting of configurations between ensembles. Previous methods, including the multistate Bennett acceptance ratio, discrete TRAM, and Markov state models are special cases and can be derived from the TRAM equations. TRAM is demonstrated by efficiently computing MEMMs in cases where other estimators break down, including the full thermodynamics and rare-event kinetics from high-dimensional simulation data of an all-atom protein–ligand binding model. PMID:27226302

Development of full-field optical spatial coherence tomography system for automated identification of malaria using the multilevel ensemble classifier.

PubMed

Singla, Neeru; Srivastava, Vishal; Mehta, Dalip Singh

2018-05-01

Malaria is a life-threatening infectious blood disease affecting humans and other animals caused by parasitic protozoans belonging to the Plasmodium type especially in developing countries. The gold standard method for the detection of malaria is through the microscopic method of chemically treated blood smears. We developed an automated optical spatial coherence tomographic system using a machine learning approach for a fast identification of malaria cells. In this study, 28 samples (15 healthy, 13 malaria infected stages of red blood cells) were imaged by the developed system and 13 features were extracted. We designed a multilevel ensemble-based classifier for the quantitative prediction of different stages of the malaria cells. The proposed classifier was used by repeating k-fold cross validation dataset and achieve a high-average accuracy of 97.9% for identifying malaria infected late trophozoite stage of cells. Overall, our proposed system and multilevel ensemble model has a substantial quantifiable potential to detect the different stages of malaria infection without staining or expert. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Accelerated iterative beam angle selection in IMRT.

PubMed

Bangert, Mark; Unkelbach, Jan

2016-03-01

Iterative methods for beam angle selection (BAS) for intensity-modulated radiation therapy (IMRT) planning sequentially construct a beneficial ensemble of beam directions. In a naïve implementation, the nth beam is selected by adding beam orientations one-by-one from a discrete set of candidates to an existing ensemble of (n - 1) beams. The best beam orientation is identified in a time consuming process by solving the fluence map optimization (FMO) problem for every candidate beam and selecting the beam that yields the largest improvement to the objective function value. This paper evaluates two alternative methods to accelerate iterative BAS based on surrogates for the FMO objective function value. We suggest to select candidate beams not based on the FMO objective function value after convergence but (1) based on the objective function value after five FMO iterations of a gradient based algorithm and (2) based on a projected gradient of the FMO problem in the first iteration. The performance of the objective function surrogates is evaluated based on the resulting objective function values and dose statistics in a treatment planning study comprising three intracranial, three pancreas, and three prostate cases. Furthermore, iterative BAS is evaluated for an application in which a small number of noncoplanar beams complement a set of coplanar beam orientations. This scenario is of practical interest as noncoplanar setups may require additional attention of the treatment personnel for every couch rotation. Iterative BAS relying on objective function surrogates yields similar results compared to naïve BAS with regard to the objective function values and dose statistics. At the same time, early stopping of the FMO and using the projected gradient during the first iteration enable reductions in computation time by approximately one to two orders of magnitude. With regard to the clinical delivery of noncoplanar IMRT treatments, we could show that optimized beam ensembles using only a few noncoplanar beam orientations often approach the plan quality of fully noncoplanar ensembles. We conclude that iterative BAS in combination with objective function surrogates can be a viable option to implement automated BAS at clinically acceptable computation times.

Dimensionality Reduction Through Classifier Ensembles

NASA Technical Reports Server (NTRS)

Oza, Nikunj C.; Tumer, Kagan; Norwig, Peter (Technical Monitor)

1999-01-01

In data mining, one often needs to analyze datasets with a very large number of attributes. Performing machine learning directly on such data sets is often impractical because of extensive run times, excessive complexity of the fitted model (often leading to overfitting), and the well-known "curse of dimensionality." In practice, to avoid such problems, feature selection and/or extraction are often used to reduce data dimensionality prior to the learning step. However, existing feature selection/extraction algorithms either evaluate features by their effectiveness across the entire data set or simply disregard class information altogether (e.g., principal component analysis). Furthermore, feature extraction algorithms such as principal components analysis create new features that are often meaningless to human users. In this article, we present input decimation, a method that provides "feature subsets" that are selected for their ability to discriminate among the classes. These features are subsequently used in ensembles of classifiers, yielding results superior to single classifiers, ensembles that use the full set of features, and ensembles based on principal component analysis on both real and synthetic datasets.

A New Ensemble Canonical Correlation Prediction Scheme for Seasonal Precipitation

NASA Technical Reports Server (NTRS)

Kim, Kyu-Myong; Lau, William K. M.; Li, Guilong; Shen, Samuel S. P.; Lau, William K. M. (Technical Monitor)

2001-01-01

Department of Mathematical Sciences, University of Alberta, Edmonton, Canada This paper describes the fundamental theory of the ensemble canonical correlation (ECC) algorithm for the seasonal climate forecasting. The algorithm is a statistical regression sch eme based on maximal correlation between the predictor and predictand. The prediction error is estimated by a spectral method using the basis of empirical orthogonal functions. The ECC algorithm treats the predictors and predictands as continuous fields and is an improvement from the traditional canonical correlation prediction. The improvements include the use of area-factor, estimation of prediction error, and the optimal ensemble of multiple forecasts. The ECC is applied to the seasonal forecasting over various parts of the world. The example presented here is for the North America precipitation. The predictor is the sea surface temperature (SST) from different ocean basins. The Climate Prediction Center's reconstructed SST (1951-1999) is used as the predictor's historical data. The optimally interpolated global monthly precipitation is used as the predictand?s historical data. Our forecast experiments show that the ECC algorithm renders very high skill and the optimal ensemble is very important to the high value.

New technologies for examining the role of neuronal ensembles in drug addiction and fear.

PubMed

Cruz, Fabio C; Koya, Eisuke; Guez-Barber, Danielle H; Bossert, Jennifer M; Lupica, Carl R; Shaham, Yavin; Hope, Bruce T

2013-11-01

Correlational data suggest that learned associations are encoded within neuronal ensembles. However, it has been difficult to prove that neuronal ensembles mediate learned behaviours because traditional pharmacological and lesion methods, and even newer cell type-specific methods, affect both activated and non-activated neurons. In addition, previous studies on synaptic and molecular alterations induced by learning did not distinguish between behaviourally activated and non-activated neurons. Here, we describe three new approaches--Daun02 inactivation, FACS sorting of activated neurons and Fos-GFP transgenic rats--that have been used to selectively target and study activated neuronal ensembles in models of conditioned drug effects and relapse. We also describe two new tools--Fos-tTA transgenic mice and inactivation of CREB-overexpressing neurons--that have been used to study the role of neuronal ensembles in conditioned fear.

Ensemble Semi-supervised Frame-work for Brain Magnetic Resonance Imaging Tissue Segmentation.

PubMed

Azmi, Reza; Pishgoo, Boshra; Norozi, Narges; Yeganeh, Samira

2013-04-01

Brain magnetic resonance images (MRIs) tissue segmentation is one of the most important parts of the clinical diagnostic tools. Pixel classification methods have been frequently used in the image segmentation with two supervised and unsupervised approaches up to now. Supervised segmentation methods lead to high accuracy, but they need a large amount of labeled data, which is hard, expensive, and slow to obtain. Moreover, they cannot use unlabeled data to train classifiers. On the other hand, unsupervised segmentation methods have no prior knowledge and lead to low level of performance. However, semi-supervised learning which uses a few labeled data together with a large amount of unlabeled data causes higher accuracy with less trouble. In this paper, we propose an ensemble semi-supervised frame-work for segmenting of brain magnetic resonance imaging (MRI) tissues that it has been used results of several semi-supervised classifiers simultaneously. Selecting appropriate classifiers has a significant role in the performance of this frame-work. Hence, in this paper, we present two semi-supervised algorithms expectation filtering maximization and MCo_Training that are improved versions of semi-supervised methods expectation maximization and Co_Training and increase segmentation accuracy. Afterward, we use these improved classifiers together with graph-based semi-supervised classifier as components of the ensemble frame-work. Experimental results show that performance of segmentation in this approach is higher than both supervised methods and the individual semi-supervised classifiers.

[Prediction of the efficacy of the non-medicamental treatment with the use of the ensemble of classifiers].

PubMed

Zaĭtsev, A A; Khodashinskiĭ, I A; Plotnikov, O O

2011-01-01

The importance to have the most efficacious tools and methods for the prevention and treatment of various diseases and rehabilitation of the patients dictates the necessity of search for new means of optimal correction of individual reserves of the organism. One of the approaches to addressing this problem is simulation of prognostication of curative effects of non-medicamental therapy. It is proposed to choose the therapeutic program using an ensemble of classifiers. Two types of them are considered, one based on the solution trees, the other based on the fuzzy rule basis. The software was developed that ensures high accuracy of th e prognosis of the efficiency of the two programs of the spa and resort treatment.

EMPIRE and pyenda: Two ensemble-based data assimilation systems written in Fortran and Python

NASA Astrophysics Data System (ADS)

Geppert, Gernot; Browne, Phil; van Leeuwen, Peter Jan; Merker, Claire

2017-04-01

We present and compare the features of two ensemble-based data assimilation frameworks, EMPIRE and pyenda. Both frameworks allow to couple models to the assimilation codes using the Message Passing Interface (MPI), leading to extremely efficient and fast coupling between models and the data-assimilation codes. The Fortran-based system EMPIRE (Employing Message Passing Interface for Researching Ensembles) is optimized for parallel, high-performance computing. It currently includes a suite of data assimilation algorithms including variants of the ensemble Kalman and several the particle filters. EMPIRE is targeted at models of all kinds of complexity and has been coupled to several geoscience models, eg. the Lorenz-63 model, a barotropic vorticity model, the general circulation model HadCM3, the ocean model NEMO, and the land-surface model JULES. The Python-based system pyenda (Python Ensemble Data Assimilation) allows Fortran- and Python-based models to be used for data assimilation. Models can be coupled either using MPI or by using a Python interface. Using Python allows quick prototyping and pyenda is aimed at small to medium scale models. pyenda currently includes variants of the ensemble Kalman filter and has been coupled to the Lorenz-63 model, an advection-based precipitation nowcasting scheme, and the dynamic global vegetation model JSBACH.

Determination of the conformational ensemble of the TAR RNA by X-ray scattering interferometry

PubMed Central

Walker, Peter

2017-01-01

Abstract The conformational ensembles of structured RNA's are crucial for biological function, but they remain difficult to elucidate experimentally. We demonstrate with HIV-1 TAR RNA that X-ray scattering interferometry (XSI) can be used to determine RNA conformational ensembles. X-ray scattering interferometry (XSI) is based on site-specifically labeling RNA with pairs of heavy atom probes, and precisely measuring the distribution of inter-probe distances that arise from a heterogeneous mixture of RNA solution structures. We show that the XSI-based model of the TAR RNA ensemble closely resembles an independent model derived from NMR-RDC data. Further, we show how the TAR RNA ensemble changes shape at different salt concentrations. Finally, we demonstrate that a single hybrid model of the TAR RNA ensemble simultaneously fits both the XSI and NMR-RDC data set and show that XSI can be combined with NMR-RDC to further improve the quality of the determined ensemble. The results suggest that XSI-RNA will be a powerful approach for characterizing the solution conformational ensembles of RNAs and RNA-protein complexes under diverse solution conditions. PMID:28108663

Subsurface characterization with localized ensemble Kalman filter employing adaptive thresholding

NASA Astrophysics Data System (ADS)

Delijani, Ebrahim Biniaz; Pishvaie, Mahmoud Reza; Boozarjomehry, Ramin Bozorgmehry

2014-07-01

Ensemble Kalman filter, EnKF, as a Monte Carlo sequential data assimilation method has emerged promisingly for subsurface media characterization during past decade. Due to high computational cost of large ensemble size, EnKF is limited to small ensemble set in practice. This results in appearance of spurious correlation in covariance structure leading to incorrect or probable divergence of updated realizations. In this paper, a universal/adaptive thresholding method is presented to remove and/or mitigate spurious correlation problem in the forecast covariance matrix. This method is, then, extended to regularize Kalman gain directly. Four different thresholding functions have been considered to threshold forecast covariance and gain matrices. These include hard, soft, lasso and Smoothly Clipped Absolute Deviation (SCAD) functions. Three benchmarks are used to evaluate the performances of these methods. These benchmarks include a small 1D linear model and two 2D water flooding (in petroleum reservoirs) cases whose levels of heterogeneity/nonlinearity are different. It should be noted that beside the adaptive thresholding, the standard distance dependant localization and bootstrap Kalman gain are also implemented for comparison purposes. We assessed each setup with different ensemble sets to investigate the sensitivity of each method on ensemble size. The results indicate that thresholding of forecast covariance yields more reliable performance than Kalman gain. Among thresholding function, SCAD is more robust for both covariance and gain estimation. Our analyses emphasize that not all assimilation cycles do require thresholding and it should be performed wisely during the early assimilation cycles. The proposed scheme of adaptive thresholding outperforms other methods for subsurface characterization of underlying benchmarks.

Fine-Tuning Your Ensemble's Jazz Style.

ERIC Educational Resources Information Center

Garcia, Antonio J.

1991-01-01

Proposes instructional strategies for directors of jazz groups, including guidelines for developing of skills necessary for good performance. Includes effective methods for positive changes in ensemble style. Addresses jazz group problems such as beat, tempo, staying in tune, wind power, and solo/ensemble lines. Discusses percussionists, bassists,…

Probabilistic regional climate projection in Japan using a regression model with CMIP5 multi-model ensemble experiments

NASA Astrophysics Data System (ADS)

Ishizaki, N. N.; Dairaku, K.; Ueno, G.

2016-12-01

We have developed a statistical downscaling method for estimating probabilistic climate projection using CMIP5 multi general circulation models (GCMs). A regression model was established so that the combination of weights of GCMs reflects the characteristics of the variation of observations at each grid point. Cross validations were conducted to select GCMs and to evaluate the regression model to avoid multicollinearity. By using spatially high resolution observation system, we conducted statistically downscaled probabilistic climate projections with 20-km horizontal grid spacing. Root mean squared errors for monthly mean air surface temperature and precipitation estimated by the regression method were the smallest compared with the results derived from a simple ensemble mean of GCMs and a cumulative distribution function based bias correction method. Projected changes in the mean temperature and precipitation were basically similar to those of the simple ensemble mean of GCMs. Mean precipitation was generally projected to increase associated with increased temperature and consequent increased moisture content in the air. Weakening of the winter monsoon may affect precipitation decrease in some areas. Temperature increase in excess of 4 K was expected in most areas of Japan in the end of 21st century under RCP8.5 scenario. The estimated probability of monthly precipitation exceeding 300 mm would increase around the Pacific side during the summer and the Japan Sea side during the winter season. This probabilistic climate projection based on the statistical method can be expected to bring useful information to the impact studies and risk assessments.

Quantum Gibbs ensemble Monte Carlo

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

Fantoni, Riccardo, E-mail: rfantoni@ts.infn.it; Moroni, Saverio, E-mail: moroni@democritos.it

We present a path integral Monte Carlo method which is the full quantum analogue of the Gibbs ensemble Monte Carlo method of Panagiotopoulos to study the gas-liquid coexistence line of a classical fluid. Unlike previous extensions of Gibbs ensemble Monte Carlo to include quantum effects, our scheme is viable even for systems with strong quantum delocalization in the degenerate regime of temperature. This is demonstrated by an illustrative application to the gas-superfluid transition of {sup 4}He in two dimensions.

Spatial Ensemble Postprocessing of Precipitation Forecasts Using High Resolution Analyses

NASA Astrophysics Data System (ADS)

Lang, Moritz N.; Schicker, Irene; Kann, Alexander; Wang, Yong

2017-04-01

Ensemble prediction systems are designed to account for errors or uncertainties in the initial and boundary conditions, imperfect parameterizations, etc. However, due to sampling errors and underestimation of the model errors, these ensemble forecasts tend to be underdispersive, and to lack both reliability and sharpness. To overcome such limitations, statistical postprocessing methods are commonly applied to these forecasts. In this study, a full-distributional spatial post-processing method is applied to short-range precipitation forecasts over Austria using Standardized Anomaly Model Output Statistics (SAMOS). Following Stauffer et al. (2016), observation and forecast fields are transformed into standardized anomalies by subtracting a site-specific climatological mean and dividing by the climatological standard deviation. Due to the need of fitting only a single regression model for the whole domain, the SAMOS framework provides a computationally inexpensive method to create operationally calibrated probabilistic forecasts for any arbitrary location or for all grid points in the domain simultaneously. Taking advantage of the INCA system (Integrated Nowcasting through Comprehensive Analysis), high resolution analyses are used for the computation of the observed climatology and for model training. The INCA system operationally combines station measurements and remote sensing data into real-time objective analysis fields at 1 km-horizontal resolution and 1 h-temporal resolution. The precipitation forecast used in this study is obtained from a limited area model ensemble prediction system also operated by ZAMG. The so called ALADIN-LAEF provides, by applying a multi-physics approach, a 17-member forecast at a horizontal resolution of 10.9 km and a temporal resolution of 1 hour. The performed SAMOS approach statistically combines the in-house developed high resolution analysis and ensemble prediction system. The station-based validation of 6 hour precipitation sums shows a mean improvement of more than 40% in CRPS when compared to bilinearly interpolated uncalibrated ensemble forecasts. The validation on randomly selected grid points, representing the true height distribution over Austria, still indicates a mean improvement of 35%. The applied statistical model is currently set up for 6-hourly and daily accumulation periods, but will be extended to a temporal resolution of 1-3 hours within a new probabilistic nowcasting system operated by ZAMG.

The role of ensemble post-processing for modeling the ensemble tail

NASA Astrophysics Data System (ADS)

Van De Vyver, Hans; Van Schaeybroeck, Bert; Vannitsem, Stéphane

2016-04-01

The past decades the numerical weather prediction community has witnessed a paradigm shift from deterministic to probabilistic forecast and state estimation (Buizza and Leutbecher, 2015; Buizza et al., 2008), in an attempt to quantify the uncertainties associated with initial-condition and model errors. An important benefit of a probabilistic framework is the improved prediction of extreme events. However, one may ask to what extent such model estimates contain information on the occurrence probability of extreme events and how this information can be optimally extracted. Different approaches have been proposed and applied on real-world systems which, based on extreme value theory, allow the estimation of extreme-event probabilities conditional on forecasts and state estimates (Ferro, 2007; Friederichs, 2010). Using ensemble predictions generated with a model of low dimensionality, a thorough investigation is presented quantifying the change of predictability of extreme events associated with ensemble post-processing and other influencing factors including the finite ensemble size, lead time and model assumption and the use of different covariates (ensemble mean, maximum, spread...) for modeling the tail distribution. Tail modeling is performed by deriving extreme-quantile estimates using peak-over-threshold representation (generalized Pareto distribution) or quantile regression. Common ensemble post-processing methods aim to improve mostly the ensemble mean and spread of a raw forecast (Van Schaeybroeck and Vannitsem, 2015). Conditional tail modeling, on the other hand, is a post-processing in itself, focusing on the tails only. Therefore, it is unclear how applying ensemble post-processing prior to conditional tail modeling impacts the skill of extreme-event predictions. This work is investigating this question in details. Buizza, Leutbecher, and Isaksen, 2008: Potential use of an ensemble of analyses in the ECMWF Ensemble Prediction System, Q. J. R. Meteorol. Soc. 134: 2051-2066.Buizza and Leutbecher, 2015: The forecast skill horizon, Q. J. R. Meteorol. Soc. 141: 3366-3382.Ferro, 2007: A probability model for verifying deterministic forecasts of extreme events. Weather and Forecasting 22 (5), 1089-1100.Friederichs, 2010: Statistical downscaling of extreme precipitation events using extreme value theory. Extremes 13, 109-132.Van Schaeybroeck and Vannitsem, 2015: Ensemble post-processing using member-by-member approaches: theoretical aspects. Q.J.R. Meteorol. Soc., 141: 807-818.

Online cross-validation-based ensemble learning.

PubMed

Benkeser, David; Ju, Cheng; Lendle, Sam; van der Laan, Mark

2018-01-30

Online estimators update a current estimate with a new incoming batch of data without having to revisit past data thereby providing streaming estimates that are scalable to big data. We develop flexible, ensemble-based online estimators of an infinite-dimensional target parameter, such as a regression function, in the setting where data are generated sequentially by a common conditional data distribution given summary measures of the past. This setting encompasses a wide range of time-series models and, as special case, models for independent and identically distributed data. Our estimator considers a large library of candidate online estimators and uses online cross-validation to identify the algorithm with the best performance. We show that by basing estimates on the cross-validation-selected algorithm, we are asymptotically guaranteed to perform as well as the true, unknown best-performing algorithm. We provide extensions of this approach including online estimation of the optimal ensemble of candidate online estimators. We illustrate excellent performance of our methods using simulations and a real data example where we make streaming predictions of infectious disease incidence using data from a large database. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Automated use of mutagenesis data in structure prediction.

PubMed

Nanda, Vikas; DeGrado, William F

2005-05-15

In the absence of experimental structural determination, numerous methods are available to indirectly predict or probe the structure of a target molecule. Genetic modification of a protein sequence is a powerful tool for identifying key residues involved in binding reactions or protein stability. Mutagenesis data is usually incorporated into the modeling process either through manual inspection of model compatibility with empirical data, or through the generation of geometric constraints linking sensitive residues to a binding interface. We present an approach derived from statistical studies of lattice models for introducing mutation information directly into the fitness score. The approach takes into account the phenotype of mutation (neutral or disruptive) and calculates the energy for a given structure over an ensemble of sequences. The structure prediction procedure searches for the optimal conformation where neutral sequences either have no impact or improve stability and disruptive sequences reduce stability relative to wild type. We examine three types of sequence ensembles: information from saturation mutagenesis, scanning mutagenesis, and homologous proteins. Incorporating multiple sequences into a statistical ensemble serves to energetically separate the native state and misfolded structures. As a result, the prediction of structure with a poor force field is sufficiently enhanced by mutational information to improve accuracy. Furthermore, by separating misfolded conformations from the target score, the ensemble energy serves to speed up conformational search algorithms such as Monte Carlo-based methods. Copyright 2005 Wiley-Liss, Inc.

Large ensemble modeling of last deglacial retreat of the West Antarctic Ice Sheet: comparison of simple and advanced statistical techniques

NASA Astrophysics Data System (ADS)

Pollard, D.; Chang, W.; Haran, M.; Applegate, P.; DeConto, R.

2015-11-01

A 3-D hybrid ice-sheet model is applied to the last deglacial retreat of the West Antarctic Ice Sheet over the last ~ 20 000 years. A large ensemble of 625 model runs is used to calibrate the model to modern and geologic data, including reconstructed grounding lines, relative sea-level records, elevation-age data and uplift rates, with an aggregate score computed for each run that measures overall model-data misfit. Two types of statistical methods are used to analyze the large-ensemble results: simple averaging weighted by the aggregate score, and more advanced Bayesian techniques involving Gaussian process-based emulation and calibration, and Markov chain Monte Carlo. Results for best-fit parameter ranges and envelopes of equivalent sea-level rise with the simple averaging method agree quite well with the more advanced techniques, but only for a large ensemble with full factorial parameter sampling. Best-fit parameter ranges confirm earlier values expected from prior model tuning, including large basal sliding coefficients on modern ocean beds. Each run is extended 5000 years into the "future" with idealized ramped climate warming. In the majority of runs with reasonable scores, this produces grounding-line retreat deep into the West Antarctic interior, and the analysis provides sea-level-rise envelopes with well defined parametric uncertainty bounds.

High resolution probabilistic precipitation forecast over Spain combining the statistical downscaling tool PROMETEO and the AEMET short range EPS system (AEMET/SREPS)

NASA Astrophysics Data System (ADS)

Cofino, A. S.; Santos, C.; Garcia-Moya, J. A.; Gutierrez, J. M.; Orfila, B.

2009-04-01

The Short-Range Ensemble Prediction System (SREPS) is a multi-LAM (UM, HIRLAM, MM5, LM and HRM) multi analysis/boundary conditions (ECMWF, UKMetOffice, DWD and GFS) run twice a day by AEMET (72 hours lead time) over a European domain, with a total of 5 (LAMs) x 4 (GCMs) = 20 members. One of the main goals of this project is analyzing the impact of models and boundary conditions in the short-range high-resolution forecasted precipitation. A previous validation of this method has been done considering a set of climate networks in Spain, France and Germany, by interpolating the prediction to the gauge locations (SREPS, 2008). In this work we compare these results with those obtained by using a statistical downscaling method to post-process the global predictions, obtaining an "advanced interpolation" for the local precipitation using climate network precipitation observations. In particular, we apply the PROMETEO downscaling system based on analogs and compare the SREPS ensemble of 20 members with the PROMETEO statistical ensemble of 5 (analog ensemble) x 4 (GCMs) = 20 members. Moreover, we will also compare the performance of a combined approach post-processing the SREPS outputs using the PROMETEO system. References: SREPS 2008. 2008 EWGLAM-SRNWP Meeting (http://www.aemet.es/documentos/va/divulgacion/conferencias/prediccion/Ewglam/PRED_CSantos.pdf)

Bayesian network ensemble as a multivariate strategy to predict radiation pneumonitis risk

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

Lee, Sangkyu, E-mail: sangkyu.lee@mail.mcgill.ca; Ybarra, Norma; Jeyaseelan, Krishinima

2015-05-15

Purpose: Prediction of radiation pneumonitis (RP) has been shown to be challenging due to the involvement of a variety of factors including dose–volume metrics and radiosensitivity biomarkers. Some of these factors are highly correlated and might affect prediction results when combined. Bayesian network (BN) provides a probabilistic framework to represent variable dependencies in a directed acyclic graph. The aim of this study is to integrate the BN framework and a systems’ biology approach to detect possible interactions among RP risk factors and exploit these relationships to enhance both the understanding and prediction of RP. Methods: The authors studied 54 nonsmall-cellmore » lung cancer patients who received curative 3D-conformal radiotherapy. Nineteen RP events were observed (common toxicity criteria for adverse events grade 2 or higher). Serum concentration of the following four candidate biomarkers were measured at baseline and midtreatment: alpha-2-macroglobulin, angiotensin converting enzyme (ACE), transforming growth factor, interleukin-6. Dose-volumetric and clinical parameters were also included as covariates. Feature selection was performed using a Markov blanket approach based on the Koller–Sahami filter. The Markov chain Monte Carlo technique estimated the posterior distribution of BN graphs built from the observed data of the selected variables and causality constraints. RP probability was estimated using a limited number of high posterior graphs (ensemble) and was averaged for the final RP estimate using Bayes’ rule. A resampling method based on bootstrapping was applied to model training and validation in order to control under- and overfit pitfalls. Results: RP prediction power of the BN ensemble approach reached its optimum at a size of 200. The optimized performance of the BN model recorded an area under the receiver operating characteristic curve (AUC) of 0.83, which was significantly higher than multivariate logistic regression (0.77), mean heart dose (0.69), and a pre-to-midtreatment change in ACE (0.66). When RP prediction was made only with pretreatment information, the AUC ranged from 0.76 to 0.81 depending on the ensemble size. Bootstrap validation of graph features in the ensemble quantified confidence of association between variables in the graphs where ten interactions were statistically significant. Conclusions: The presented BN methodology provides the flexibility to model hierarchical interactions between RP covariates, which is applied to probabilistic inference on RP. The authors’ preliminary results demonstrate that such framework combined with an ensemble method can possibly improve prediction of RP under real-life clinical circumstances such as missing data or treatment plan adaptation.« less

Entanglement in a solid-state spin ensemble.

PubMed

Simmons, Stephanie; Brown, Richard M; Riemann, Helge; Abrosimov, Nikolai V; Becker, Peter; Pohl, Hans-Joachim; Thewalt, Mike L W; Itoh, Kohei M; Morton, John J L

2011-02-03

Entanglement is the quintessential quantum phenomenon. It is a necessary ingredient in most emerging quantum technologies, including quantum repeaters, quantum information processing and the strongest forms of quantum cryptography. Spin ensembles, such as those used in liquid-state nuclear magnetic resonance, have been important for the development of quantum control methods. However, these demonstrations contain no entanglement and ultimately constitute classical simulations of quantum algorithms. Here we report the on-demand generation of entanglement between an ensemble of electron and nuclear spins in isotopically engineered, phosphorus-doped silicon. We combined high-field (3.4 T), low-temperature (2.9 K) electron spin resonance with hyperpolarization of the (31)P nuclear spin to obtain an initial state of sufficient purity to create a non-classical, inseparable state. The state was verified using density matrix tomography based on geometric phase gates, and had a fidelity of 98% relative to the ideal state at this field and temperature. The entanglement operation was performed simultaneously, with high fidelity, on 10(10) spin pairs; this fulfils one of the essential requirements for a silicon-based quantum information processor.

An ensemble of SVM classifiers based on gene pairs.

PubMed

Tong, Muchenxuan; Liu, Kun-Hong; Xu, Chungui; Ju, Wenbin

2013-07-01

In this paper, a genetic algorithm (GA) based ensemble support vector machine (SVM) classifier built on gene pairs (GA-ESP) is proposed. The SVMs (base classifiers of the ensemble system) are trained on different informative gene pairs. These gene pairs are selected by the top scoring pair (TSP) criterion. Each of these pairs projects the original microarray expression onto a 2-D space. Extensive permutation of gene pairs may reveal more useful information and potentially lead to an ensemble classifier with satisfactory accuracy and interpretability. GA is further applied to select an optimized combination of base classifiers. The effectiveness of the GA-ESP classifier is evaluated on both binary-class and multi-class datasets. Copyright © 2013 Elsevier Ltd. All rights reserved.

MUSE: MUlti-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters, and locally optimal atlas selection

PubMed Central

Ou, Yangming; Resnick, Susan M.; Gur, Ruben C.; Gur, Raquel E.; Satterthwaite, Theodore D.; Furth, Susan; Davatzikos, Christos

2016-01-01

Atlas-based automated anatomical labeling is a fundamental tool in medical image segmentation, as it defines regions of interest for subsequent analysis of structural and functional image data. The extensive investigation of multi-atlas warping and fusion techniques over the past 5 or more years has clearly demonstrated the advantages of consensus-based segmentation. However, the common approach is to use multiple atlases with a single registration method and parameter set, which is not necessarily optimal for every individual scan, anatomical region, and problem/data-type. Different registration criteria and parameter sets yield different solutions, each providing complementary information. Herein, we present a consensus labeling framework that generates a broad ensemble of labeled atlases in target image space via the use of several warping algorithms, regularization parameters, and atlases. The label fusion integrates two complementary sources of information: a local similarity ranking to select locally optimal atlases and a boundary modulation term to refine the segmentation consistently with the target image's intensity profile. The ensemble approach consistently outperforms segmentations using individual warping methods alone, achieving high accuracy on several benchmark datasets. The MUSE methodology has been used for processing thousands of scans from various datasets, producing robust and consistent results. MUSE is publicly available both as a downloadable software package, and as an application that can be run on the CBICA Image Processing Portal (https://ipp.cbica.upenn.edu), a web based platform for remote processing of medical images. PMID:26679328

Crossover ensembles of random matrices and skew-orthogonal polynomials

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

Kumar, Santosh, E-mail: skumar.physics@gmail.com; Pandey, Akhilesh, E-mail: ap0700@mail.jnu.ac.in

2011-08-15

Highlights: > We study crossover ensembles of Jacobi family of random matrices. > We consider correlations for orthogonal-unitary and symplectic-unitary crossovers. > We use the method of skew-orthogonal polynomials and quaternion determinants. > We prove universality of spectral correlations in crossover ensembles. > We discuss applications to quantum conductance and communication theory problems. - Abstract: In a recent paper (S. Kumar, A. Pandey, Phys. Rev. E, 79, 2009, p. 026211) we considered Jacobi family (including Laguerre and Gaussian cases) of random matrix ensembles and reported exact solutions of crossover problems involving time-reversal symmetry breaking. In the present paper we givemore » details of the work. We start with Dyson's Brownian motion description of random matrix ensembles and obtain universal hierarchic relations among the unfolded correlation functions. For arbitrary dimensions we derive the joint probability density (jpd) of eigenvalues for all transitions leading to unitary ensembles as equilibrium ensembles. We focus on the orthogonal-unitary and symplectic-unitary crossovers and give generic expressions for jpd of eigenvalues, two-point kernels and n-level correlation functions. This involves generalization of the theory of skew-orthogonal polynomials to crossover ensembles. We also consider crossovers in the circular ensembles to show the generality of our method. In the large dimensionality limit, correlations in spectra with arbitrary initial density are shown to be universal when expressed in terms of a rescaled symmetry breaking parameter. Applications of our crossover results to communication theory and quantum conductance problems are also briefly discussed.« less

A Novel Multi-Class Ensemble Model for Classifying Imbalanced Biomedical Datasets

NASA Astrophysics Data System (ADS)

Bikku, Thulasi; Sambasiva Rao, N., Dr; Rao, Akepogu Ananda, Dr

2017-08-01

This paper mainly focuseson developing aHadoop based framework for feature selection and classification models to classify high dimensionality data in heterogeneous biomedical databases. Wide research has been performing in the fields of Machine learning, Big data and Data mining for identifying patterns. The main challenge is extracting useful features generated from diverse biological systems. The proposed model can be used for predicting diseases in various applications and identifying the features relevant to particular diseases. There is an exponential growth of biomedical repositories such as PubMed and Medline, an accurate predictive model is essential for knowledge discovery in Hadoop environment. Extracting key features from unstructured documents often lead to uncertain results due to outliers and missing values. In this paper, we proposed a two phase map-reduce framework with text preprocessor and classification model. In the first phase, mapper based preprocessing method was designed to eliminate irrelevant features, missing values and outliers from the biomedical data. In the second phase, a Map-Reduce based multi-class ensemble decision tree model was designed and implemented in the preprocessed mapper data to improve the true positive rate and computational time. The experimental results on the complex biomedical datasets show that the performance of our proposed Hadoop based multi-class ensemble model significantly outperforms state-of-the-art baselines.

Accurate RNA 5-methylcytosine site prediction based on heuristic physical-chemical properties reduction and classifier ensemble.

PubMed

Zhang, Ming; Xu, Yan; Li, Lei; Liu, Zi; Yang, Xibei; Yu, Dong-Jun

2018-06-01

RNA 5-methylcytosine (m 5 C) is an important post-transcriptional modification that plays an indispensable role in biological processes. The accurate identification of m 5 C sites from primary RNA sequences is especially useful for deeply understanding the mechanisms and functions of m 5 C. Due to the difficulty and expensive costs of identifying m 5 C sites with wet-lab techniques, developing fast and accurate machine-learning-based prediction methods is urgently needed. In this study, we proposed a new m 5 C site predictor, called M5C-HPCR, by introducing a novel heuristic nucleotide physicochemical property reduction (HPCR) algorithm and classifier ensemble. HPCR extracts multiple reducts of physical-chemical properties for encoding discriminative features, while the classifier ensemble is applied to integrate multiple base predictors, each of which is trained based on a separate reduct of the physical-chemical properties obtained from HPCR. Rigorous jackknife tests on two benchmark datasets demonstrate that M5C-HPCR outperforms state-of-the-art m 5 C site predictors, with the highest values of MCC (0.859) and AUC (0.962). We also implemented the webserver of M5C-HPCR, which is freely available at http://cslab.just.edu.cn:8080/M5C-HPCR/. Copyright © 2018 Elsevier Inc. All rights reserved.

The potential of radar-based ensemble forecasts for flash-flood early warning in the southern Swiss Alps

NASA Astrophysics Data System (ADS)

Liechti, K.; Panziera, L.; Germann, U.; Zappa, M.

2013-10-01

This study explores the limits of radar-based forecasting for hydrological runoff prediction. Two novel radar-based ensemble forecasting chains for flash-flood early warning are investigated in three catchments in the southern Swiss Alps and set in relation to deterministic discharge forecasts for the same catchments. The first radar-based ensemble forecasting chain is driven by NORA (Nowcasting of Orographic Rainfall by means of Analogues), an analogue-based heuristic nowcasting system to predict orographic rainfall for the following eight hours. The second ensemble forecasting system evaluated is REAL-C2, where the numerical weather prediction COSMO-2 is initialised with 25 different initial conditions derived from a four-day nowcast with the radar ensemble REAL. Additionally, three deterministic forecasting chains were analysed. The performance of these five flash-flood forecasting systems was analysed for 1389 h between June 2007 and December 2010 for which NORA forecasts were issued, due to the presence of orographic forcing. A clear preference was found for the ensemble approach. Discharge forecasts perform better when forced by NORA and REAL-C2 rather then by deterministic weather radar data. Moreover, it was observed that using an ensemble of initial conditions at the forecast initialisation, as in REAL-C2, significantly improved the forecast skill. These forecasts also perform better then forecasts forced by ensemble rainfall forecasts (NORA) initialised form a single initial condition of the hydrological model. Thus the best results were obtained with the REAL-C2 forecasting chain. However, for regions where REAL cannot be produced, NORA might be an option for forecasting events triggered by orographic precipitation.

CMIP5 ensemble-based spatial rainfall projection over homogeneous zones of India

NASA Astrophysics Data System (ADS)

Akhter, Javed; Das, Lalu; Deb, Argha

2017-09-01

Performances of the state-of-the-art CMIP5 models in reproducing the spatial rainfall patterns over seven homogeneous rainfall zones of India viz. North Mountainous India (NMI), Northwest India (NWI), North Central India (NCI), Northeast India (NEI), West Peninsular India (WPI), East Peninsular India (EPI) and South Peninsular India (SPI) have been assessed using different conventional performance metrics namely spatial correlation (R), index of agreement (d-index), Nash-Sutcliffe efficiency (NSE), Ratio of RMSE to the standard deviation of the observations (RSR) and mean bias (MB). The results based on these indices revealed that majority of the models are unable to reproduce finer-scaled spatial patterns over most of the zones. Thereafter, four bias correction methods i.e. Scaling, Standardized Reconstruction, Empirical Quantile Mapping and Gamma Quantile Mapping have been applied on GCM simulations to enhance the skills of the GCM projections. It has been found that scaling method compared to other three methods shown its better skill in capturing mean spatial patterns. Multi-model ensemble (MME) comprising 25 numbers of better performing bias corrected (Scaled) GCMs, have been considered for developing future rainfall patterns over seven zones. Models' spread from ensemble mean (uncertainty) has been found to be larger in RCP 8.5 than RCP4.5 ensemble. In general, future rainfall projections from RCP 4.5 and RCP 8.5 revealed an increasing rainfall over seven zones during 2020s, 2050s, and 2080s. The maximum increase has been found over southwestern part of NWI (12-30%), northwestern part of WPI (3-30%), southeastern part of NEI (5-18%) and northern and eastern part of SPI (6-24%). However, the contiguous region comprising by the southeastern part of NCI and northeastern part of EPI, may experience slight decreasing rainfall (about 3%) during 2020s whereas the western part of NMI may also receive around 3% reduction in rainfall during both 2050s and 2080s.

Dynamics Under Location Uncertainty: Model Derivation, Modified Transport and Uncertainty Quantification

NASA Astrophysics Data System (ADS)

Resseguier, V.; Memin, E.; Chapron, B.; Fox-Kemper, B.

2017-12-01

In order to better observe and predict geophysical flows, ensemble-based data assimilation methods are of high importance. In such methods, an ensemble of random realizations represents the variety of the simulated flow's likely behaviors. For this purpose, randomness needs to be introduced in a suitable way and physically-based stochastic subgrid parametrizations are promising paths. This talk will propose a new kind of such a parametrization referred to as modeling under location uncertainty. The fluid velocity is decomposed into a resolved large-scale component and an aliased small-scale one. The first component is possibly random but time-correlated whereas the second is white-in-time but spatially-correlated and possibly inhomogeneous and anisotropic. With such a velocity, the material derivative of any - possibly active - tracer is modified. Three new terms appear: a correction of the large-scale advection, a multiplicative noise and a possibly heterogeneous and anisotropic diffusion. This parameterization naturally ensures attractive properties such as energy conservation for each realization. Additionally, this stochastic material derivative and the associated Reynolds' transport theorem offer a systematic method to derive stochastic models. In particular, we will discuss the consequences of the Quasi-Geostrophic assumptions in our framework. Depending on the turbulence amount, different models with different physical behaviors are obtained. Under strong turbulence assumptions, a simplified diagnosis of frontolysis and frontogenesis at the surface of the ocean is possible in this framework. A Surface Quasi-Geostrophic (SQG) model with a weaker noise influence has also been simulated. A single realization better represents small scales than a deterministic SQG model at the same resolution. Moreover, an ensemble accurately predicts extreme events, bifurcations as well as the amplitudes and the positions of the simulation errors. Figure 1 highlights this last result and compares it to the strong error underestimation of an ensemble simulated from the deterministic dynamic with random initial conditions.

Time delayed Ensemble Nudging Method

NASA Astrophysics Data System (ADS)

An, Zhe; Abarbanel, Henry

Optimal nudging method based on time delayed embedding theory has shows potentials on analyzing and data assimilation in previous literatures. To extend the application and promote the practical implementation, new nudging assimilation method based on the time delayed embedding space is presented and the connection with other standard assimilation methods are studied. Results shows the incorporating information from the time series of data can reduce the sufficient observation needed to preserve the quality of numerical prediction, making it a potential alternative in the field of data assimilation of large geophysical models.

Characterizing sources of uncertainty from global climate models and downscaling techniques

USGS Publications Warehouse

Wootten, Adrienne; Terando, Adam; Reich, Brian J.; Boyles, Ryan; Semazzi, Fred

2017-01-01

In recent years climate model experiments have been increasingly oriented towards providing information that can support local and regional adaptation to the expected impacts of anthropogenic climate change. This shift has magnified the importance of downscaling as a means to translate coarse-scale global climate model (GCM) output to a finer scale that more closely matches the scale of interest. Applying this technique, however, introduces a new source of uncertainty into any resulting climate model ensemble. Here we present a method, based on a previously established variance decomposition method, to partition and quantify the uncertainty in climate model ensembles that is attributable to downscaling. We apply the method to the Southeast U.S. using five downscaled datasets that represent both statistical and dynamical downscaling techniques. The combined ensemble is highly fragmented, in that only a small portion of the complete set of downscaled GCMs and emission scenarios are typically available. The results indicate that the uncertainty attributable to downscaling approaches ~20% for large areas of the Southeast U.S. for precipitation and ~30% for extreme heat days (> 35°C) in the Appalachian Mountains. However, attributable quantities are significantly lower for time periods when the full ensemble is considered but only a sub-sample of all models are available, suggesting that overconfidence could be a serious problem in studies that employ a single set of downscaled GCMs. We conclude with recommendations to advance the design of climate model experiments so that the uncertainty that accrues when downscaling is employed is more fully and systematically considered.

Reliability ensemble averaging of 21st century projections of terrestrial net primary productivity reduces global and regional uncertainties

NASA Astrophysics Data System (ADS)

Exbrayat, Jean-François; Bloom, A. Anthony; Falloon, Pete; Ito, Akihiko; Smallman, T. Luke; Williams, Mathew

2018-02-01

Multi-model averaging techniques provide opportunities to extract additional information from large ensembles of simulations. In particular, present-day model skill can be used to evaluate their potential performance in future climate simulations. Multi-model averaging methods have been used extensively in climate and hydrological sciences, but they have not been used to constrain projected plant productivity responses to climate change, which is a major uncertainty in Earth system modelling. Here, we use three global observationally orientated estimates of current net primary productivity (NPP) to perform a reliability ensemble averaging (REA) method using 30 global simulations of the 21st century change in NPP based on the Inter-Sectoral Impact Model Intercomparison Project (ISIMIP) business as usual emissions scenario. We find that the three REA methods support an increase in global NPP by the end of the 21st century (2095-2099) compared to 2001-2005, which is 2-3 % stronger than the ensemble ISIMIP mean value of 24.2 Pg C y-1. Using REA also leads to a 45-68 % reduction in the global uncertainty of 21st century NPP projection, which strengthens confidence in the resilience of the CO2 fertilization effect to climate change. This reduction in uncertainty is especially clear for boreal ecosystems although it may be an artefact due to the lack of representation of nutrient limitations on NPP in most models. Conversely, the large uncertainty that remains on the sign of the response of NPP in semi-arid regions points to the need for better observations and model development in these regions.

How well the Reliable Ensemble Averaging Method (REA) for 15 CMIP5 GCMs simulations works for Mexico?

NASA Astrophysics Data System (ADS)

Colorado, G.; Salinas, J. A.; Cavazos, T.; de Grau, P.

2013-05-01

15 CMIP5 GCMs precipitation simulations were combined in a weighted ensemble using the Reliable Ensemble Averaging (REA) method, obtaining the weight of each model. This was done for a historical period (1961-2000) and for the future emissions based on low (RCP4.5) and high (RCP8.5) radiating forcing for the period 2075-2099. The annual cycle of simple ensemble of the historical GCMs simulations, the historical REA average and the Climate Research Unit (CRU TS3.1) database was compared in four zones of México. In the case of precipitation we can see the improvements by using the REA method, especially in the two northern zones of México where the REA average is more close to the observations (CRU) that the simple average. However in the southern zones although there is an improvement it is not as good as it is in the north, particularly in the southeast where instead of the REA average is able to reproduce qualitatively good the annual cycle with the mid-summer drought it was greatly underestimated. The main reason is because the precipitation is underestimated for all the models and the mid-summer drought do not even exists in some models. In the REA average of the future scenarios, as we can expected, the most drastic decrease in precipitation was simulated using the RCP8.5 especially in the monsoon area and in the south of Mexico in summer and in winter. In the center and southern of Mexico however, the same scenario in autumn simulates an increase of precipitation.

New technologies for examining neuronal ensembles in drug addiction and fear

PubMed Central

Cruz, Fabio C.; Koya, Eisuke; Guez-Barber, Danielle H.; Bossert, Jennifer M.; Lupica, Carl R.; Shaham, Yavin; Hope, Bruce T.

2015-01-01

Correlational data suggest that learned associations are encoded within neuronal ensembles. However, it has been difficult to prove that neuronal ensembles mediate learned behaviours because traditional pharmacological and lesion methods, and even newer cell type-specific methods, affect both activated and non-activated neurons. Additionally, previous studies on synaptic and molecular alterations induced by learning did not distinguish between behaviourally activated and non-activated neurons. Here, we describe three new approaches—Daun02 inactivation, FACS sorting of activated neurons and c-fos-GFP transgenic rats — that have been used to selectively target and study activated neuronal ensembles in models of conditioned drug effects and relapse. We also describe two new tools — c-fos-tTA mice and inactivation of CREB-overexpressing neurons — that have been used to study the role of neuronal ensembles in conditioned fear. PMID:24088811

Prediction of Weather Impacted Airport Capacity using Ensemble Learning

NASA Technical Reports Server (NTRS)

Wang, Yao Xun

2011-01-01

Ensemble learning with the Bagging Decision Tree (BDT) model was used to assess the impact of weather on airport capacities at selected high-demand airports in the United States. The ensemble bagging decision tree models were developed and validated using the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) data and weather forecast at these airports. The study examines the performance of BDT, along with traditional single Support Vector Machines (SVM), for airport runway configuration selection and airport arrival rates (AAR) prediction during weather impacts. Testing of these models was accomplished using observed weather, weather forecast, and airport operation information at the chosen airports. The experimental results show that ensemble methods are more accurate than a single SVM classifier. The airport capacity ensemble method presented here can be used as a decision support model that supports air traffic flow management to meet the weather impacted airport capacity in order to reduce costs and increase safety.

The role of ensemble-based statistics in variational assimilation of cloud-affected observations from infrared imagers

NASA Astrophysics Data System (ADS)

Hacker, Joshua; Vandenberghe, Francois; Jung, Byoung-Jo; Snyder, Chris

2017-04-01

Effective assimilation of cloud-affected radiance observations from space-borne imagers, with the aim of improving cloud analysis and forecasting, has proven to be difficult. Large observation biases, nonlinear observation operators, and non-Gaussian innovation statistics present many challenges. Ensemble-variational data assimilation (EnVar) systems offer the benefits of flow-dependent background error statistics from an ensemble, and the ability of variational minimization to handle nonlinearity. The specific benefits of ensemble statistics, relative to static background errors more commonly used in variational systems, have not been quantified for the problem of assimilating cloudy radiances. A simple experiment framework is constructed with a regional NWP model and operational variational data assimilation system, to provide the basis understanding the importance of ensemble statistics in cloudy radiance assimilation. Restricting the observations to those corresponding to clouds in the background forecast leads to innovations that are more Gaussian. The number of large innovations is reduced compared to the more general case of all observations, but not eliminated. The Huber norm is investigated to handle the fat tails of the distributions, and allow more observations to be assimilated without the need for strict background checks that eliminate them. Comparing assimilation using only ensemble background error statistics with assimilation using only static background error statistics elucidates the importance of the ensemble statistics. Although the cost functions in both experiments converge to similar values after sufficient outer-loop iterations, the resulting cloud water, ice, and snow content are greater in the ensemble-based analysis. The subsequent forecasts from the ensemble-based analysis also retain more condensed water species, indicating that the local environment is more supportive of clouds. In this presentation we provide details that explain the apparent benefit from using ensembles for cloudy radiance assimilation in an EnVar context.

WE-E-BRE-05: Ensemble of Graphical Models for Predicting Radiation Pneumontis Risk

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

Lee, S; Ybarra, N; Jeyaseelan, K

Purpose: We propose a prior knowledge-based approach to construct an interaction graph of biological and dosimetric radiation pneumontis (RP) covariates for the purpose of developing a RP risk classifier. Methods: We recruited 59 NSCLC patients who received curative radiotherapy with minimum 6 month follow-up. 16 RP events was observed (CTCAE grade ≥2). Blood serum was collected from every patient before (pre-RT) and during RT (mid-RT). From each sample the concentration of the following five candidate biomarkers were taken as covariates: alpha-2-macroglobulin (α2M), angiotensin converting enzyme (ACE), transforming growth factor β (TGF-β), interleukin-6 (IL-6), and osteopontin (OPN). Dose-volumetric parameters were alsomore » included as covariates. The number of biological and dosimetric covariates was reduced by a variable selection scheme implemented by L1-regularized logistic regression (LASSO). Posterior probability distribution of interaction graphs between the selected variables was estimated from the data under the literature-based prior knowledge to weight more heavily the graphs that contain the expected associations. A graph ensemble was formed by averaging the most probable graphs weighted by their posterior, creating a Bayesian Network (BN)-based RP risk classifier. Results: The LASSO selected the following 7 RP covariates: (1) pre-RT concentration level of α2M, (2) α2M level mid- RT/pre-RT, (3) pre-RT IL6 level, (4) IL6 level mid-RT/pre-RT, (5) ACE mid-RT/pre-RT, (6) PTV volume, and (7) mean lung dose (MLD). The ensemble BN model achieved the maximum sensitivity/specificity of 81%/84% and outperformed univariate dosimetric predictors as shown by larger AUC values (0.78∼0.81) compared with MLD (0.61), V20 (0.65) and V30 (0.70). The ensembles obtained by incorporating the prior knowledge improved classification performance for the ensemble size 5∼50. Conclusion: We demonstrated a probabilistic ensemble method to detect robust associations between RP covariates and its potential to improve RP prediction accuracy. Our Bayesian approach to incorporate prior knowledge can enhance efficiency in searching of such associations from data. The authors acknowledge partial support by: 1) CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290) and 2) The Terry Fox Foundation Strategic Training Initiative for Excellence in Radiation Research for the 21st Century (EIRR21)« less

Network-induced chaos in integrate-and-fire neuronal ensembles.

PubMed

Zhou, Douglas; Rangan, Aaditya V; Sun, Yi; Cai, David

2009-09-01

It has been shown that a single standard linear integrate-and-fire (IF) neuron under a general time-dependent stimulus cannot possess chaotic dynamics despite the firing-reset discontinuity. Here we address the issue of whether conductance-based, pulsed-coupled network interactions can induce chaos in an IF neuronal ensemble. Using numerical methods, we demonstrate that all-to-all, homogeneously pulse-coupled IF neuronal networks can indeed give rise to chaotic dynamics under an external periodic current drive. We also provide a precise characterization of the largest Lyapunov exponent for these high dimensional nonsmooth dynamical systems. In addition, we present a stable and accurate numerical algorithm for evaluating the largest Lyapunov exponent, which can overcome difficulties encountered by traditional methods for these nonsmooth dynamical systems with degeneracy induced by, e.g., refractoriness of neurons.

Skill of Ensemble Seasonal Probability Forecasts

NASA Astrophysics Data System (ADS)

Smith, Leonard A.; Binter, Roman; Du, Hailiang; Niehoerster, Falk

2010-05-01

In operational forecasting, the computational complexity of large simulation models is, ideally, justified by enhanced performance over simpler models. We will consider probability forecasts and contrast the skill of ENSEMBLES-based seasonal probability forecasts of interest to the finance sector (specifically temperature forecasts for Nino 3.4 and the Atlantic Main Development Region (MDR)). The ENSEMBLES model simulations will be contrasted against forecasts from statistical models based on the observations (climatological distributions) and empirical dynamics based on the observations but conditioned on the current state (dynamical climatology). For some start dates, individual ENSEMBLES models yield significant skill even at a lead-time of 14 months. The nature of this skill is discussed, and chances of application are noted. Questions surrounding the interpretation of probability forecasts based on these multi-model ensemble simulations are then considered; the distributions considered are formed by kernel dressing the ensemble and blending with the climatology. The sources of apparent (RMS) skill in distributions based on multi-model simulations is discussed, and it is demonstrated that the inclusion of "zero-skill" models in the long range can improve Root-Mean-Square-Error scores, casting some doubt on the common justification for the claim that all models should be included in forming an operational probability forecast. It is argued that the rational response varies with lead time.

One-day-ahead streamflow forecasting via super-ensembles of several neural network architectures based on the Multi-Level Diversity Model

NASA Astrophysics Data System (ADS)

Brochero, Darwin; Hajji, Islem; Pina, Jasson; Plana, Queralt; Sylvain, Jean-Daniel; Vergeynst, Jenna; Anctil, Francois

2015-04-01

Theories about generalization error with ensembles are mainly based on the diversity concept, which promotes resorting to many members of different properties to support mutually agreeable decisions. Kuncheva (2004) proposed the Multi Level Diversity Model (MLDM) to promote diversity in model ensembles, combining different data subsets, input subsets, models, parameters, and including a combiner level in order to optimize the final ensemble. This work tests the hypothesis about the minimisation of the generalization error with ensembles of Neural Network (NN) structures. We used the MLDM to evaluate two different scenarios: (i) ensembles from a same NN architecture, and (ii) a super-ensemble built by a combination of sub-ensembles of many NN architectures. The time series used correspond to the 12 basins of the MOdel Parameter Estimation eXperiment (MOPEX) project that were used by Duan et al. (2006) and Vos (2013) as benchmark. Six architectures are evaluated: FeedForward NN (FFNN) trained with the Levenberg Marquardt algorithm (Hagan et al., 1996), FFNN trained with SCE (Duan et al., 1993), Recurrent NN trained with a complex method (Weins et al., 2008), Dynamic NARX NN (Leontaritis and Billings, 1985), Echo State Network (ESN), and leak integrator neuron (L-ESN) (Lukosevicius and Jaeger, 2009). Each architecture performs separately an Input Variable Selection (IVS) according to a forward stepwise selection (Anctil et al., 2009) using mean square error as objective function. Post-processing by Predictor Stepwise Selection (PSS) of the super-ensemble has been done following the method proposed by Brochero et al. (2011). IVS results showed that the lagged stream flow, lagged precipitation, and Standardized Precipitation Index (SPI) (McKee et al., 1993) were the most relevant variables. They were respectively selected as one of the firsts three selected variables in 66, 45, and 28 of the 72 scenarios. A relationship between aridity index (Arora, 2002) and NN performance showed that wet basins are more easily modelled than dry basins. Nash-Sutcliffe (NS) Efficiency criterion was used to evaluate the performance of the models. Test results showed that in 9 of the 12 basins, the mean sub-ensembles performance was better than the one presented by Vos (2013). Furthermore, in 55 of 72 cases (6 NN structures x 12 basins) the mean sub-ensemble performance was better than the best individual performance, and in 10 basins the performance of the mean super-ensemble was better than the best individual super-ensemble member. As well, it was identified that members of ESN and L-ESN sub-ensembles have very similar and good performance values. Regarding the mean super-ensemble performance, we obtained an average gain in performance of 17%, and found that PSS preserves sub-ensemble members from different NN structures, indicating the pertinence of diversity in the super-ensemble. Moreover, it was demonstrated that around 100 predictors from the different structures are enough to optimize the super-ensemble. Although sub-ensembles of FFNN-SCE showed unstable performances, FFNN-SCE members were picked-up several times in the final predictor selection. References Anctil, F., M. Filion, and J. Tournebize (2009). "A neural network experiment on the simulation of daily nitrate-nitrogen and suspended sediment fluxes from a small agricultural catchment". In: Ecol. Model. 220.6, pp. 879-887. Arora, V. K. (2002). "The use of the aridity index to assess climate change effect on annual runoff". In: J. Hydrol. 265.164, pp. 164 -177 . Brochero, D., F. Anctil, and C. Gagn'e (2011). "Simplifying a hydrological ensemble prediction system with a backward greedy selection of members Part 1: Optimization criteria". In: Hydrol. Earth Syst. Sci. 15.11, pp. 3307-3325. Duan, Q., J. Schaake, V. Andr'eassian, S. Franks, G. Goteti, H. Gupta, Y. Gusev, F. Habets, A. Hall, L. Hay, T. Hogue, M. Huang, G. Leavesley, X. Liang, O. Nasonova, J. Noilhan, L. Oudin, S. Sorooshian, T. Wagener, and E. Wood (2006). "Model Parameter Estimation Experiment (MOPEX): An overview of science strategy and major results from the second and third workshops". In: J. Hydrol. 320.12, pp. 3-17. Duan, Q., V. Gupta, and S. Sorooshian (1993). "Shuffled complex evolution approach for effective and efficient global minimization". In: J. Optimiz. Theory App. 76.3, pp. 501-521. Hagan, M. T., H. B. Demuth, and M. Beale (1996). Neural network design . 1st ed. PWS Publishing Co., p. 730. Kuncheva, L. I. (2004). Combining Pattern Classifiers: Methods and Algorithms . Wiley-Interscience, p. 350. Leontaritis, I. and S. Billings (1985). "Input-output parametric models for non-linear systems Part I: deterministic non-linear systems". In: International Journal of Control 41.2, pp. 303-328. Lukosevicius, M. and H. Jaeger (2009). "Reservoir computing approaches to recurrent neural network training". In: Computer Science Review 3.3, pp. 127-149. McKee, T., N. Doesken, and J. Kleist (1993). The Relationship of Drought Frequency and Duration to Time Scales . In: Eighth Conference on Applied Climatology. Vos, N. J. de (2013). "Echo state networks as an alternative to traditional artificial neural networks in rainfall-runoff modelling". In: Hydrol. Earth Syst. Sci. 17.1, pp. 253-267. Weins, T., R. Burton, G. Schoenau, and D. Bitner (2008). Recursive Generalized Neural Networks (RGNN) for the Modeling of a Load Sensing Pump. In: ASME Joint Conference on Fluid Power, Transmission and Control.

An Optimal Estimation Method to Obtain Surface Layer Turbulent Fluxes from Profile Measurements

NASA Astrophysics Data System (ADS)

Kang, D.

2015-12-01

In the absence of direct turbulence measurements, the turbulence characteristics of the atmospheric surface layer are often derived from measurements of the surface layer mean properties based on Monin-Obukhov Similarity Theory (MOST). This approach requires two levels of the ensemble mean wind, temperature, and water vapor, from which the fluxes of momentum, sensible heat, and water vapor can be obtained. When only one measurement level is available, the roughness heights and the assumed properties of the corresponding variables at the respective roughness heights are used. In practice, the temporal mean with large number of samples are used in place of the ensemble mean. However, in many situations the samples of data are taken from multiple levels. It is thus desirable to derive the boundary layer flux properties using all measurements. In this study, we used an optimal estimation approach to derive surface layer properties based on all available measurements. This approach assumes that the samples are taken from a population whose ensemble mean profile follows the MOST. An optimized estimate is obtained when the results yield a minimum cost function defined as a weighted summation of all error variance at each sample altitude. The weights are based one sample data variance and the altitude of the measurements. This method was applied to measurements in the marine atmospheric surface layer from a small boat using radiosonde on a tethered balloon where temperature and relative humidity profiles in the lowest 50 m were made repeatedly in about 30 minutes. We will present the resultant fluxes and the derived MOST mean profiles using different sets of measurements. The advantage of this method over the 'traditional' methods will be illustrated. Some limitations of this optimization method will also be discussed. Its application to quantify the effects of marine surface layer environment on radar and communication signal propagation will be shown as well.

A Kolmogorov-Smirnov test for the molecular clock based on Bayesian ensembles of phylogenies

PubMed Central

Antoneli, Fernando; Passos, Fernando M.; Lopes, Luciano R.

2018-01-01

Divergence date estimates are central to understand evolutionary processes and depend, in the case of molecular phylogenies, on tests of molecular clocks. Here we propose two non-parametric tests of strict and relaxed molecular clocks built upon a framework that uses the empirical cumulative distribution (ECD) of branch lengths obtained from an ensemble of Bayesian trees and well known non-parametric (one-sample and two-sample) Kolmogorov-Smirnov (KS) goodness-of-fit test. In the strict clock case, the method consists in using the one-sample Kolmogorov-Smirnov (KS) test to directly test if the phylogeny is clock-like, in other words, if it follows a Poisson law. The ECD is computed from the discretized branch lengths and the parameter λ of the expected Poisson distribution is calculated as the average branch length over the ensemble of trees. To compensate for the auto-correlation in the ensemble of trees and pseudo-replication we take advantage of thinning and effective sample size, two features provided by Bayesian inference MCMC samplers. Finally, it is observed that tree topologies with very long or very short branches lead to Poisson mixtures and in this case we propose the use of the two-sample KS test with samples from two continuous branch length distributions, one obtained from an ensemble of clock-constrained trees and the other from an ensemble of unconstrained trees. Moreover, in this second form the test can also be applied to test for relaxed clock models. The use of a statistically equivalent ensemble of phylogenies to obtain the branch lengths ECD, instead of one consensus tree, yields considerable reduction of the effects of small sample size and provides a gain of power. PMID:29300759

A common fallacy in climate model evaluation

NASA Astrophysics Data System (ADS)

Annan, J. D.; Hargreaves, J. C.; Tachiiri, K.

2012-04-01

We discuss the assessment of model ensembles such as that arising from the CMIP3 coordinated multi-model experiments. An important aspect of this is not merely the closeness of the models to observations in absolute terms but also the reliability of the ensemble spread as an indication of uncertainty. In this context, it has been widely argued that the multi-model ensemble of opportunity is insufficiently broad to adequately represent uncertainties regarding future climate change. For example, the IPCC AR4 summarises the consensus with the sentence: "Those studies also suggest that the current AOGCMs may not cover the full range of uncertainty for climate sensitivity." Similar claims have been made in the literature for other properties of the climate system, including the transient climate response and efficiency of ocean heat uptake. Comparison of model outputs with observations of the climate system forms an essential component of model assessment and is crucial for building our confidence in model predictions. However, methods for undertaking this comparison are not always clearly justified and understood. Here we show that the popular approach which forms the basis for the above claims, of comparing the ensemble spread to a so-called "observationally-constrained pdf", can be highly misleading. Such a comparison will almost certainly result in disagreement, but in reality tells us little about the performance of the ensemble. We present an alternative approach based on an assessment of the predictive performance of the ensemble, and show how it may lead to very different, and rather more encouraging, conclusions. We additionally outline some necessary conditions for an ensemble (or more generally, a probabilistic prediction) to be challenged by an observation.

A Cutting Pattern Recognition Method for Shearers Based on Improved Ensemble Empirical Mode Decomposition and a Probabilistic Neural Network

PubMed Central

Xu, Jing; Wang, Zhongbin; Tan, Chao; Si, Lei; Liu, Xinhua

2015-01-01

In order to guarantee the stable operation of shearers and promote construction of an automatic coal mining working face, an online cutting pattern recognition method with high accuracy and speed based on Improved Ensemble Empirical Mode Decomposition (IEEMD) and Probabilistic Neural Network (PNN) is proposed. An industrial microphone is installed on the shearer and the cutting sound is collected as the recognition criterion to overcome the disadvantages of giant size, contact measurement and low identification rate of traditional detectors. To avoid end-point effects and get rid of undesirable intrinsic mode function (IMF) components in the initial signal, IEEMD is conducted on the sound. The end-point continuation based on the practical storage data is performed first to overcome the end-point effect. Next the average correlation coefficient, which is calculated by the correlation of the first IMF with others, is introduced to select essential IMFs. Then the energy and standard deviation of the reminder IMFs are extracted as features and PNN is applied to classify the cutting patterns. Finally, a simulation example, with an accuracy of 92.67%, and an industrial application prove the efficiency and correctness of the proposed method. PMID:26528985

A Sequential Ensemble Prediction System at Convection Permitting Scales

NASA Astrophysics Data System (ADS)

Milan, M.; Simmer, C.

2012-04-01

A Sequential Assimilation Method (SAM) following some aspects of particle filtering with resampling, also called SIR (Sequential Importance Resampling), is introduced and applied in the framework of an Ensemble Prediction System (EPS) for weather forecasting on convection permitting scales, with focus to precipitation forecast. At this scale and beyond, the atmosphere increasingly exhibits chaotic behaviour and non linear state space evolution due to convectively driven processes. One way to take full account of non linear state developments are particle filter methods, their basic idea is the representation of the model probability density function by a number of ensemble members weighted by their likelihood with the observations. In particular particle filter with resampling abandons ensemble members (particles) with low weights restoring the original number of particles adding multiple copies of the members with high weights. In our SIR-like implementation we substitute the likelihood way to define weights and introduce a metric which quantifies the "distance" between the observed atmospheric state and the states simulated by the ensemble members. We also introduce a methodology to counteract filter degeneracy, i.e. the collapse of the simulated state space. To this goal we propose a combination of resampling taking account of simulated state space clustering and nudging. By keeping cluster representatives during resampling and filtering, the method maintains the potential for non linear system state development. We assume that a particle cluster with initially low likelihood may evolve in a state space with higher likelihood in a subsequent filter time thus mimicking non linear system state developments (e.g. sudden convection initiation) and remedies timing errors for convection due to model errors and/or imperfect initial condition. We apply a simplified version of the resampling, the particles with highest weights in each cluster are duplicated; for the model evolution for each particle pair one particle evolves using the forward model; the second particle, however, is nudged to the radar and satellite observation during its evolution based on the forward model.

Application of Enhanced Sampling Monte Carlo Methods for High-Resolution Protein-Protein Docking in Rosetta

PubMed Central

Zhang, Zhe; Schindler, Christina E. M.; Lange, Oliver F.; Zacharias, Martin

2015-01-01

The high-resolution refinement of docked protein-protein complexes can provide valuable structural and mechanistic insight into protein complex formation complementing experiment. Monte Carlo (MC) based approaches are frequently applied to sample putative interaction geometries of proteins including also possible conformational changes of the binding partners. In order to explore efficiency improvements of the MC sampling, several enhanced sampling techniques, including temperature or Hamiltonian replica exchange and well-tempered ensemble approaches, have been combined with the MC method and were evaluated on 20 protein complexes using unbound partner structures. The well-tempered ensemble method combined with a 2-dimensional temperature and Hamiltonian replica exchange scheme (WTE-H-REMC) was identified as the most efficient search strategy. Comparison with prolonged MC searches indicates that the WTE-H-REMC approach requires approximately 5 times fewer MC steps to identify near native docking geometries compared to conventional MC searches. PMID:26053419

Dynamic State Estimation and Parameter Calibration of DFIG based on Ensemble Kalman Filter

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

Fan, Rui; Huang, Zhenyu; Wang, Shaobu

2015-07-30

With the growing interest in the application of wind energy, doubly fed induction generator (DFIG) plays an essential role in the industry nowadays. To deal with the increasing stochastic variations introduced by intermittent wind resource and responsive loads, dynamic state estimation (DSE) are introduced in any power system associated with DFIGs. However, sometimes this dynamic analysis canould not work because the parameters of DFIGs are not accurate enough. To solve the problem, an ensemble Kalman filter (EnKF) method is proposed for the state estimation and parameter calibration tasks. In this paper, a DFIG is modeled and implemented with the EnKFmore » method. Sensitivity analysis is demonstrated regarding the measurement noise, initial state errors and parameter errors. The results indicate this EnKF method has a robust performance on the state estimation and parameter calibration of DFIGs.« less

Towards estimation of respiratory muscle effort with respiratory inductance plethysmography signals and complementary ensemble empirical mode decomposition.

PubMed

Chen, Ya-Chen; Hsiao, Tzu-Chien

2018-07-01

Respiratory inductance plethysmography (RIP) sensor is an inexpensive, non-invasive, easy-to-use transducer for collecting respiratory movement data. Studies have reported that the RIP signal's amplitude and frequency can be used to discriminate respiratory diseases. However, with the conventional approach of RIP data analysis, respiratory muscle effort cannot be estimated. In this paper, the estimation of the respiratory muscle effort through RIP signal was proposed. A complementary ensemble empirical mode decomposition method was used, to extract hidden signals from the RIP signals based on the frequency bands of the activities of different respiratory muscles. To validate the proposed method, an experiment to collect subjects' RIP signal under thoracic breathing (TB) and abdominal breathing (AB) was conducted. The experimental results for both the TB and AB indicate that the proposed method can be used to loosely estimate the activities of thoracic muscles, abdominal muscles, and diaphragm. Graphical abstract ᅟ.

Multi-dimensional coherent optical spectroscopy of semiconductor nanostructures: Collinear and non-collinear approaches

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

Nardin, Gaël; Li, Hebin; Autry, Travis M.

2015-03-21

We review our recent work on multi-dimensional coherent optical spectroscopy (MDCS) of semiconductor nanostructures. Two approaches, appropriate for the study of semiconductor materials, are presented and compared. A first method is based on a non-collinear geometry, where the Four-Wave-Mixing (FWM) signal is detected in the form of a radiated optical field. This approach works for samples with translational symmetry, such as Quantum Wells (QWs) or large and dense ensembles of Quantum Dots (QDs). A second method detects the FWM in the form of a photocurrent in a collinear geometry. This second approach extends the horizon of MDCS to sub-diffraction nanostructures,more » such as single QDs, nanowires, or nanotubes, and small ensembles thereof. Examples of experimental results obtained on semiconductor QW structures are given for each method. In particular, it is shown how MDCS can assess coupling between excitons confined in separated QWs.« less

New Aspects of Probabilistic Forecast Verification Using Information Theory

NASA Astrophysics Data System (ADS)

Tödter, Julian; Ahrens, Bodo

2013-04-01

This work deals with information-theoretical methods in probabilistic forecast verification, particularly concerning ensemble forecasts. Recent findings concerning the "Ignorance Score" are shortly reviewed, then a consistent generalization to continuous forecasts is motivated. For ensemble-generated forecasts, the presented measures can be calculated exactly. The Brier Score (BS) and its generalizations to the multi-categorical Ranked Probability Score (RPS) and to the Continuous Ranked Probability Score (CRPS) are prominent verification measures for probabilistic forecasts. Particularly, their decompositions into measures quantifying the reliability, resolution and uncertainty of the forecasts are attractive. Information theory sets up a natural framework for forecast verification. Recently, it has been shown that the BS is a second-order approximation of the information-based Ignorance Score (IGN), which also contains easily interpretable components and can also be generalized to a ranked version (RIGN). Here, the IGN, its generalizations and decompositions are systematically discussed in analogy to the variants of the BS. Additionally, a Continuous Ranked IGN (CRIGN) is introduced in analogy to the CRPS. The useful properties of the conceptually appealing CRIGN are illustrated, together with an algorithm to evaluate its components reliability, resolution, and uncertainty for ensemble-generated forecasts. This algorithm can also be used to calculate the decomposition of the more traditional CRPS exactly. The applicability of the "new" measures is demonstrated in a small evaluation study of ensemble-based precipitation forecasts.

Ensemble urban flood simulation in comparison with laboratory-scale experiments: Impact of interaction models for manhole, sewer pipe, and surface flow

NASA Astrophysics Data System (ADS)

Noh, Seong Jin; Lee, Seungsoo; An, Hyunuk; Kawaike, Kenji; Nakagawa, Hajime

2016-11-01

An urban flood is an integrated phenomenon that is affected by various uncertainty sources such as input forcing, model parameters, complex geometry, and exchanges of flow among different domains in surfaces and subsurfaces. Despite considerable advances in urban flood modeling techniques, limited knowledge is currently available with regard to the impact of dynamic interaction among different flow domains on urban floods. In this paper, an ensemble method for urban flood modeling is presented to consider the parameter uncertainty of interaction models among a manhole, a sewer pipe, and surface flow. Laboratory-scale experiments on urban flood and inundation are performed under various flow conditions to investigate the parameter uncertainty of interaction models. The results show that ensemble simulation using interaction models based on weir and orifice formulas reproduces experimental data with high accuracy and detects the identifiability of model parameters. Among interaction-related parameters, the parameters of the sewer-manhole interaction show lower uncertainty than those of the sewer-surface interaction. Experimental data obtained under unsteady-state conditions are more informative than those obtained under steady-state conditions to assess the parameter uncertainty of interaction models. Although the optimal parameters vary according to the flow conditions, the difference is marginal. Simulation results also confirm the capability of the interaction models and the potential of the ensemble-based approaches to facilitate urban flood simulation.

Coherent Spin Control at the Quantum Level in an Ensemble-Based Optical Memory.

PubMed

Jobez, Pierre; Laplane, Cyril; Timoney, Nuala; Gisin, Nicolas; Ferrier, Alban; Goldner, Philippe; Afzelius, Mikael

2015-06-12

Long-lived quantum memories are essential components of a long-standing goal of remote distribution of entanglement in quantum networks. These can be realized by storing the quantum states of light as single-spin excitations in atomic ensembles. However, spin states are often subjected to different dephasing processes that limit the storage time, which in principle could be overcome using spin-echo techniques. Theoretical studies suggest this to be challenging due to unavoidable spontaneous emission noise in ensemble-based quantum memories. Here, we demonstrate spin-echo manipulation of a mean spin excitation of 1 in a large solid-state ensemble, generated through storage of a weak optical pulse. After a storage time of about 1 ms we optically read-out the spin excitation with a high signal-to-noise ratio. Our results pave the way for long-duration optical quantum storage using spin-echo techniques for any ensemble-based memory.

A second-order unconstrained optimization method for canonical-ensemble density-functional methods

NASA Astrophysics Data System (ADS)

Nygaard, Cecilie R.; Olsen, Jeppe

2013-03-01

A second order converging method of ensemble optimization (SOEO) in the framework of Kohn-Sham Density-Functional Theory is presented, where the energy is minimized with respect to an ensemble density matrix. It is general in the sense that the number of fractionally occupied orbitals is not predefined, but rather it is optimized by the algorithm. SOEO is a second order Newton-Raphson method of optimization, where both the form of the orbitals and the occupation numbers are optimized simultaneously. To keep the occupation numbers between zero and two, a set of occupation angles is defined, from which the occupation numbers are expressed as trigonometric functions. The total number of electrons is controlled by a built-in second order restriction of the Newton-Raphson equations, which can be deactivated in the case of a grand-canonical ensemble (where the total number of electrons is allowed to change). To test the optimization method, dissociation curves for diatomic carbon are produced using different functionals for the exchange-correlation energy. These curves show that SOEO favors symmetry broken pure-state solutions when using functionals with exact exchange such as Hartree-Fock and Becke three-parameter Lee-Yang-Parr. This is explained by an unphysical contribution to the exact exchange energy from interactions between fractional occupations. For functionals without exact exchange, such as local density approximation or Becke Lee-Yang-Parr, ensemble solutions are favored at interatomic distances larger than the equilibrium distance. Calculations on the chromium dimer are also discussed. They show that SOEO is able to converge to ensemble solutions for systems that are more complicated than diatomic carbon.

A Four-Stage Hybrid Model for Hydrological Time Series Forecasting

PubMed Central

Di, Chongli; Yang, Xiaohua; Wang, Xiaochao

2014-01-01

Hydrological time series forecasting remains a difficult task due to its complicated nonlinear, non-stationary and multi-scale characteristics. To solve this difficulty and improve the prediction accuracy, a novel four-stage hybrid model is proposed for hydrological time series forecasting based on the principle of ‘denoising, decomposition and ensemble’. The proposed model has four stages, i.e., denoising, decomposition, components prediction and ensemble. In the denoising stage, the empirical mode decomposition (EMD) method is utilized to reduce the noises in the hydrological time series. Then, an improved method of EMD, the ensemble empirical mode decomposition (EEMD), is applied to decompose the denoised series into a number of intrinsic mode function (IMF) components and one residual component. Next, the radial basis function neural network (RBFNN) is adopted to predict the trend of all of the components obtained in the decomposition stage. In the final ensemble prediction stage, the forecasting results of all of the IMF and residual components obtained in the third stage are combined to generate the final prediction results, using a linear neural network (LNN) model. For illustration and verification, six hydrological cases with different characteristics are used to test the effectiveness of the proposed model. The proposed hybrid model performs better than conventional single models, the hybrid models without denoising or decomposition and the hybrid models based on other methods, such as the wavelet analysis (WA)-based hybrid models. In addition, the denoising and decomposition strategies decrease the complexity of the series and reduce the difficulties of the forecasting. With its effective denoising and accurate decomposition ability, high prediction precision and wide applicability, the new model is very promising for complex time series forecasting. This new forecast model is an extension of nonlinear prediction models. PMID:25111782

Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation

ERIC Educational Resources Information Center

Austin, Peter C.

2012-01-01

Researchers are increasingly using observational or nonrandomized data to estimate causal treatment effects. Essential to the production of high-quality evidence is the ability to reduce or minimize the confounding that frequently occurs in observational studies. When using the potential outcome framework to define causal treatment effects, one…

Deep multi-spectral ensemble learning for electronic cleansing in dual-energy CT colonography

NASA Astrophysics Data System (ADS)

Tachibana, Rie; Näppi, Janne J.; Hironaka, Toru; Kim, Se Hyung; Yoshida, Hiroyuki

2017-03-01

We developed a novel electronic cleansing (EC) method for dual-energy CT colonography (DE-CTC) based on an ensemble deep convolution neural network (DCNN) and multi-spectral multi-slice image patches. In the method, an ensemble DCNN is used to classify each voxel of a DE-CTC image volume into five classes: luminal air, soft tissue, tagged fecal materials, and partial-volume boundaries between air and tagging and those between soft tissue and tagging. Each DCNN acts as a voxel classifier, where an input image patch centered at the voxel is generated as input to the DCNNs. An image patch has three channels that are mapped from a region-of-interest containing the image plane of the voxel and the two adjacent image planes. Six different types of spectral input image datasets were derived using two dual-energy CT images, two virtual monochromatic images, and two material images. An ensemble DCNN was constructed by use of a meta-classifier that combines the output of multiple DCNNs, each of which was trained with a different type of multi-spectral image patches. The electronically cleansed CTC images were calculated by removal of regions classified as other than soft tissue, followed by a colon surface reconstruction. For pilot evaluation, 359 volumes of interest (VOIs) representing sources of subtraction artifacts observed in current EC schemes were sampled from 30 clinical CTC cases. Preliminary results showed that the ensemble DCNN can yield high accuracy in labeling of the VOIs, indicating that deep learning of multi-spectral EC with multi-slice imaging could accurately remove residual fecal materials from CTC images without generating major EC artifacts.

DrugE-Rank: improving drug–target interaction prediction of new candidate drugs or targets by ensemble learning to rank

PubMed Central

Yuan, Qingjun; Gao, Junning; Wu, Dongliang; Zhang, Shihua; Mamitsuka, Hiroshi; Zhu, Shanfeng

2016-01-01

Motivation: Identifying drug–target interactions is an important task in drug discovery. To reduce heavy time and financial cost in experimental way, many computational approaches have been proposed. Although these approaches have used many different principles, their performance is far from satisfactory, especially in predicting drug–target interactions of new candidate drugs or targets. Methods: Approaches based on machine learning for this problem can be divided into two types: feature-based and similarity-based methods. Learning to rank is the most powerful technique in the feature-based methods. Similarity-based methods are well accepted, due to their idea of connecting the chemical and genomic spaces, represented by drug and target similarities, respectively. We propose a new method, DrugE-Rank, to improve the prediction performance by nicely combining the advantages of the two different types of methods. That is, DrugE-Rank uses LTR, for which multiple well-known similarity-based methods can be used as components of ensemble learning. Results: The performance of DrugE-Rank is thoroughly examined by three main experiments using data from DrugBank: (i) cross-validation on FDA (US Food and Drug Administration) approved drugs before March 2014; (ii) independent test on FDA approved drugs after March 2014; and (iii) independent test on FDA experimental drugs. Experimental results show that DrugE-Rank outperforms competing methods significantly, especially achieving more than 30% improvement in Area under Prediction Recall curve for FDA approved new drugs and FDA experimental drugs. Availability: http://datamining-iip.fudan.edu.cn/service/DrugE-Rank Contact: zhusf@fudan.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307615

Determination of the conformational ensemble of the TAR RNA by X-ray scattering interferometry.

PubMed

Shi, Xuesong; Walker, Peter; Harbury, Pehr B; Herschlag, Daniel

2017-05-05

The conformational ensembles of structured RNA's are crucial for biological function, but they remain difficult to elucidate experimentally. We demonstrate with HIV-1 TAR RNA that X-ray scattering interferometry (XSI) can be used to determine RNA conformational ensembles. X-ray scattering interferometry (XSI) is based on site-specifically labeling RNA with pairs of heavy atom probes, and precisely measuring the distribution of inter-probe distances that arise from a heterogeneous mixture of RNA solution structures. We show that the XSI-based model of the TAR RNA ensemble closely resembles an independent model derived from NMR-RDC data. Further, we show how the TAR RNA ensemble changes shape at different salt concentrations. Finally, we demonstrate that a single hybrid model of the TAR RNA ensemble simultaneously fits both the XSI and NMR-RDC data set and show that XSI can be combined with NMR-RDC to further improve the quality of the determined ensemble. The results suggest that XSI-RNA will be a powerful approach for characterizing the solution conformational ensembles of RNAs and RNA-protein complexes under diverse solution conditions. © The Author(s) 2017. Published by Oxford University Press on behalf of Nucleic Acids Research.

Extended Range Prediction of Indian Summer Monsoon: Current status

NASA Astrophysics Data System (ADS)

Sahai, A. K.; Abhilash, S.; Borah, N.; Joseph, S.; Chattopadhyay, R.; S, S.; Rajeevan, M.; Mandal, R.; Dey, A.

2014-12-01

The main focus of this study is to develop forecast consensus in the extended range prediction (ERP) of monsoon Intraseasonal oscillations using a suit of different variants of Climate Forecast system (CFS) model. In this CFS based Grand MME prediction system (CGMME), the ensemble members are generated by perturbing the initial condition and using different configurations of CFSv2. This is to address the role of different physical mechanisms known to have control on the error growth in the ERP in the 15-20 day time scale. The final formulation of CGMME is based on 21 ensembles of the standalone Global Forecast System (GFS) forced with bias corrected forecasted SST from CFS, 11 low resolution CFST126 and 11 high resolution CFST382. Thus, we develop the multi-model consensus forecast for the ERP of Indian summer monsoon (ISM) using a suite of different variants of CFS model. This coordinated international effort lead towards the development of specific tailor made regional forecast products over Indian region. Skill of deterministic and probabilistic categorical rainfall forecast as well the verification of large-scale low frequency monsoon intraseasonal oscillations has been carried out using hindcast from 2001-2012 during the monsoon season in which all models are initialized at every five days starting from 16May to 28 September. The skill of deterministic forecast from CGMME is better than the best participating single model ensemble configuration (SME). The CGMME approach is believed to quantify the uncertainty in both initial conditions and model formulation. Main improvement is attained in probabilistic forecast which is because of an increase in the ensemble spread, thereby reducing the error due to over-confident ensembles in a single model configuration. For probabilistic forecast, three tercile ranges are determined by ranking method based on the percentage of ensemble members from all the participating models falls in those three categories. CGMME further added value to both deterministic and probability forecast compared to raw SME's and this better skill is probably flows from large spread and improved spread-error relationship. CGMME system is currently capable of generating ER prediction in real time and successfully delivering its experimental operational ER forecast of ISM for the last few years.

An ensemble method for extracting adverse drug events from social media.

PubMed

Liu, Jing; Zhao, Songzheng; Zhang, Xiaodi

2016-06-01

Because adverse drug events (ADEs) are a serious health problem and a leading cause of death, it is of vital importance to identify them correctly and in a timely manner. With the development of Web 2.0, social media has become a large data source for information on ADEs. The objective of this study is to develop a relation extraction system that uses natural language processing techniques to effectively distinguish between ADEs and non-ADEs in informal text on social media. We develop a feature-based approach that utilizes various lexical, syntactic, and semantic features. Information-gain-based feature selection is performed to address high-dimensional features. Then, we evaluate the effectiveness of four well-known kernel-based approaches (i.e., subset tree kernel, tree kernel, shortest dependency path kernel, and all-paths graph kernel) and several ensembles that are generated by adopting different combination methods (i.e., majority voting, weighted averaging, and stacked generalization). All of the approaches are tested using three data sets: two health-related discussion forums and one general social networking site (i.e., Twitter). When investigating the contribution of each feature subset, the feature-based approach attains the best area under the receiver operating characteristics curve (AUC) values, which are 78.6%, 72.2%, and 79.2% on the three data sets. When individual methods are used, we attain the best AUC values of 82.1%, 73.2%, and 77.0% using the subset tree kernel, shortest dependency path kernel, and feature-based approach on the three data sets, respectively. When using classifier ensembles, we achieve the best AUC values of 84.5%, 77.3%, and 84.5% on the three data sets, outperforming the baselines. Our experimental results indicate that ADE extraction from social media can benefit from feature selection. With respect to the effectiveness of different feature subsets, lexical features and semantic features can enhance the ADE extraction capability. Kernel-based approaches, which can stay away from the feature sparsity issue, are qualified to address the ADE extraction problem. Combining different individual classifiers using suitable combination methods can further enhance the ADE extraction effectiveness. Copyright © 2016 Elsevier B.V. All rights reserved.

Geometric analysis characterizes molecular rigidity in generic and non-generic protein configurations

PubMed Central

Budday, Dominik; Leyendecker, Sigrid; van den Bedem, Henry

2015-01-01

Proteins operate and interact with partners by dynamically exchanging between functional substates of a conformational ensemble on a rugged free energy landscape. Understanding how these substates are linked by coordinated, collective motions requires exploring a high-dimensional space, which remains a tremendous challenge. While molecular dynamics simulations can provide atomically detailed insight into the dynamics, computational demands to adequately sample conformational ensembles of large biomolecules and their complexes often require tremendous resources. Kinematic models can provide high-level insights into conformational ensembles and molecular rigidity beyond the reach of molecular dynamics by reducing the dimensionality of the search space. Here, we model a protein as a kinematic linkage and present a new geometric method to characterize molecular rigidity from the constraint manifold Q and its tangent space Q at the current configuration q. In contrast to methods based on combinatorial constraint counting, our method is valid for both generic and non-generic, e.g., singular configurations. Importantly, our geometric approach provides an explicit basis for collective motions along floppy modes, resulting in an efficient procedure to probe conformational space. An atomically detailed structural characterization of coordinated, collective motions would allow us to engineer or allosterically modulate biomolecules by selectively stabilizing conformations that enhance or inhibit function with broad implications for human health. PMID:26213417

Geometric analysis characterizes molecular rigidity in generic and non-generic protein configurations

NASA Astrophysics Data System (ADS)

Budday, Dominik; Leyendecker, Sigrid; van den Bedem, Henry

2015-10-01

Proteins operate and interact with partners by dynamically exchanging between functional substates of a conformational ensemble on a rugged free energy landscape. Understanding how these substates are linked by coordinated, collective motions requires exploring a high-dimensional space, which remains a tremendous challenge. While molecular dynamics simulations can provide atomically detailed insight into the dynamics, computational demands to adequately sample conformational ensembles of large biomolecules and their complexes often require tremendous resources. Kinematic models can provide high-level insights into conformational ensembles and molecular rigidity beyond the reach of molecular dynamics by reducing the dimensionality of the search space. Here, we model a protein as a kinematic linkage and present a new geometric method to characterize molecular rigidity from the constraint manifold Q and its tangent space Tq Q at the current configuration q. In contrast to methods based on combinatorial constraint counting, our method is valid for both generic and non-generic, e.g., singular configurations. Importantly, our geometric approach provides an explicit basis for collective motions along floppy modes, resulting in an efficient procedure to probe conformational space. An atomically detailed structural characterization of coordinated, collective motions would allow us to engineer or allosterically modulate biomolecules by selectively stabilizing conformations that enhance or inhibit function with broad implications for human health.

Addressing model uncertainty through stochastic parameter perturbations within the High Resolution Rapid Refresh (HRRR) ensemble

NASA Astrophysics Data System (ADS)

Wolff, J.; Jankov, I.; Beck, J.; Carson, L.; Frimel, J.; Harrold, M.; Jiang, H.

2016-12-01

It is well known that global and regional numerical weather prediction ensemble systems are under-dispersive, producing unreliable and overconfident ensemble forecasts. Typical approaches to alleviate this problem include the use of multiple dynamic cores, multiple physics suite configurations, or a combination of the two. While these approaches may produce desirable results, they have practical and theoretical deficiencies and are more difficult and costly to maintain. An active area of research that promotes a more unified and sustainable system for addressing the deficiencies in ensemble modeling is the use of stochastic physics to represent model-related uncertainty. Stochastic approaches include Stochastic Parameter Perturbations (SPP), Stochastic Kinetic Energy Backscatter (SKEB), Stochastic Perturbation of Physics Tendencies (SPPT), or some combination of all three. The focus of this study is to assess the model performance within a convection-permitting ensemble at 3-km grid spacing across the Contiguous United States (CONUS) when using stochastic approaches. For this purpose, the test utilized a single physics suite configuration based on the operational High-Resolution Rapid Refresh (HRRR) model, with ensemble members produced by employing stochastic methods. Parameter perturbations were employed in the Rapid Update Cycle (RUC) land surface model and Mellor-Yamada-Nakanishi-Niino (MYNN) planetary boundary layer scheme. Results will be presented in terms of bias, error, spread, skill, accuracy, reliability, and sharpness using the Model Evaluation Tools (MET) verification package. Due to the high level of complexity of running a frequently updating (hourly), high spatial resolution (3 km), large domain (CONUS) ensemble system, extensive high performance computing (HPC) resources were needed to meet this objective. Supercomputing resources were provided through the National Center for Atmospheric Research (NCAR) Strategic Capability (NSC) project support, allowing for a more extensive set of tests over multiple seasons, consequently leading to more robust results. Through the use of these stochastic innovations and powerful supercomputing at NCAR, further insights and advancements in ensemble forecasting at convection-permitting scales will be possible.

Regression approach to non-invasive determination of bilirubin in neonatal blood

NASA Astrophysics Data System (ADS)

Lysenko, S. A.; Kugeiko, M. M.

2012-07-01

A statistical ensemble of structural and biophysical parameters of neonatal skin was modeled based on experimental data. Diffuse scattering coefficients of the skin in the visible and infrared regions were calculated by applying a Monte-Carlo method to each realization of the ensemble. The potential accuracy of recovering the bilirubin concentration in dermis (which correlates closely with that in blood) was estimated from spatially resolved spectrometric measurements of diffuse scattering. The possibility to determine noninvasively the bilirubin concentration was shown by measurements of diffuse scattering at λ = 460, 500, and 660 nm at three source-detector separations under conditions of total variability of the skin biophysical parameters.

CABS-flex: server for fast simulation of protein structure fluctuations

PubMed Central

Jamroz, Michal; Kolinski, Andrzej; Kmiecik, Sebastian

2013-01-01

The CABS-flex server (http://biocomp.chem.uw.edu.pl/CABSflex) implements CABS-model–based protocol for the fast simulations of near-native dynamics of globular proteins. In this application, the CABS model was shown to be a computationally efficient alternative to all-atom molecular dynamics—a classical simulation approach. The simulation method has been validated on a large set of molecular dynamics simulation data. Using a single input (user-provided file in PDB format), the CABS-flex server outputs an ensemble of protein models (in all-atom PDB format) reflecting the flexibility of the input structure, together with the accompanying analysis (residue mean-square-fluctuation profile and others). The ensemble of predicted models can be used in structure-based studies of protein functions and interactions. PMID:23658222