Ski jump takeoff performance predictions for a mixed-flow, remote-lift STOVL aircraft

NASA Technical Reports Server (NTRS)

Birckelbaw, Lourdes G.

1992-01-01

A ski jump model was developed to predict ski jump takeoff performance for a short takeoff and vertical landing (STOVL) aircraft. The objective was to verify the model with results from a piloted simulation of a mixed flow, remote lift STOVL aircraft. The prediction model is discussed. The predicted results are compared with the piloted simulation results. The ski jump model can be utilized for basic research of other thrust vectoring STOVL aircraft performing a ski jump takeoff.

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.

Advanced Performance Modeling with Combined Passive and Active Monitoring

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

Dovrolis, Constantine; Sim, Alex

2015-04-15

To improve the efficiency of resource utilization and scheduling of scientific data transfers on high-speed networks, the "Advanced Performance Modeling with combined passive and active monitoring" (APM) project investigates and models a general-purpose, reusable and expandable network performance estimation framework. The predictive estimation model and the framework will be helpful in optimizing the performance and utilization of networks as well as sharing resources with predictable performance for scientific collaborations, especially in data intensive applications. Our prediction model utilizes historical network performance information from various network activity logs as well as live streaming measurements from network peering devices. Historical network performancemore » information is used without putting extra load on the resources by active measurement collection. Performance measurements collected by active probing is used judiciously for improving the accuracy of predictions.« less

Validating models of target acquisition performance in the dismounted soldier context

NASA Astrophysics Data System (ADS)

Glaholt, Mackenzie G.; Wong, Rachel K.; Hollands, Justin G.

2018-04-01

The problem of predicting real-world operator performance with digital imaging devices is of great interest within the military and commercial domains. There are several approaches to this problem, including: field trials with imaging devices, laboratory experiments using imagery captured from these devices, and models that predict human performance based on imaging device parameters. The modeling approach is desirable, as both field trials and laboratory experiments are costly and time-consuming. However, the data from these experiments is required for model validation. Here we considered this problem in the context of dismounted soldiering, for which detection and identification of human targets are essential tasks. Human performance data were obtained for two-alternative detection and identification decisions in a laboratory experiment in which photographs of human targets were presented on a computer monitor and the images were digitally magnified to simulate range-to-target. We then compared the predictions of different performance models within the NV-IPM software package: Targeting Task Performance (TTP) metric model and the Johnson model. We also introduced a modification to the TTP metric computation that incorporates an additional correction for target angular size. We examined model predictions using NV-IPM default values for a critical model constant, V50, and we also considered predictions when this value was optimized to fit the behavioral data. When using default values, certain model versions produced a reasonably close fit to the human performance data in the detection task, while for the identification task all models substantially overestimated performance. When using fitted V50 values the models produced improved predictions, though the slopes of the performance functions were still shallow compared to the behavioral data. These findings are discussed in relation to the models' designs and parameters, and the characteristics of the behavioral paradigm.

The development of performance prediction models for Virginia's interstate highway system.

DOT National Transportation Integrated Search

1995-01-01

Performance prediction models are a key component of any well-designed pavement management system. In this study, data compiled from the condition surveys conducted annually on Virginia's pavement network were used to develop prediction models for mo...

External validation of a prediction model for surgical site infection after thoracolumbar spine surgery in a Western European cohort.

PubMed

Janssen, Daniël M C; van Kuijk, Sander M J; d'Aumerie, Boudewijn B; Willems, Paul C

2018-05-16

A prediction model for surgical site infection (SSI) after spine surgery was developed in 2014 by Lee et al. This model was developed to compute an individual estimate of the probability of SSI after spine surgery based on the patient's comorbidity profile and invasiveness of surgery. Before any prediction model can be validly implemented in daily medical practice, it should be externally validated to assess how the prediction model performs in patients sampled independently from the derivation cohort. We included 898 consecutive patients who underwent instrumented thoracolumbar spine surgery. To quantify overall performance using Nagelkerke's R 2 statistic, the discriminative ability was quantified as the area under the receiver operating characteristic curve (AUC). We computed the calibration slope of the calibration plot, to judge prediction accuracy. Sixty patients developed an SSI. The overall performance of the prediction model in our population was poor: Nagelkerke's R 2 was 0.01. The AUC was 0.61 (95% confidence interval (CI) 0.54-0.68). The estimated slope of the calibration plot was 0.52. The previously published prediction model showed poor performance in our academic external validation cohort. To predict SSI after instrumented thoracolumbar spine surgery for the present population, a better fitting prediction model should be developed.

A Public-Private Partnership Develops and Externally Validates a 30-Day Hospital Readmission Risk Prediction Model

PubMed Central

Choudhry, Shahid A.; Li, Jing; Davis, Darcy; Erdmann, Cole; Sikka, Rishi; Sutariya, Bharat

2013-01-01

Introduction: Preventing the occurrence of hospital readmissions is needed to improve quality of care and foster population health across the care continuum. Hospitals are being held accountable for improving transitions of care to avert unnecessary readmissions. Advocate Health Care in Chicago and Cerner (ACC) collaborated to develop all-cause, 30-day hospital readmission risk prediction models to identify patients that need interventional resources. Ideally, prediction models should encompass several qualities: they should have high predictive ability; use reliable and clinically relevant data; use vigorous performance metrics to assess the models; be validated in populations where they are applied; and be scalable in heterogeneous populations. However, a systematic review of prediction models for hospital readmission risk determined that most performed poorly (average C-statistic of 0.66) and efforts to improve their performance are needed for widespread usage. Methods: The ACC team incorporated electronic health record data, utilized a mixed-method approach to evaluate risk factors, and externally validated their prediction models for generalizability. Inclusion and exclusion criteria were applied on the patient cohort and then split for derivation and internal validation. Stepwise logistic regression was performed to develop two predictive models: one for admission and one for discharge. The prediction models were assessed for discrimination ability, calibration, overall performance, and then externally validated. Results: The ACC Admission and Discharge Models demonstrated modest discrimination ability during derivation, internal and external validation post-recalibration (C-statistic of 0.76 and 0.78, respectively), and reasonable model fit during external validation for utility in heterogeneous populations. Conclusions: The ACC Admission and Discharge Models embody the design qualities of ideal prediction models. The ACC plans to continue its partnership to further improve and develop valuable clinical models. PMID:24224068

Analytic Guided-Search Model of Human Performance Accuracy in Target- Localization Search Tasks

NASA Technical Reports Server (NTRS)

Eckstein, Miguel P.; Beutter, Brent R.; Stone, Leland S.

2000-01-01

Current models of human visual search have extended the traditional serial/parallel search dichotomy. Two successful models for predicting human visual search are the Guided Search model and the Signal Detection Theory model. Although these models are inherently different, it has been difficult to compare them because the Guided Search model is designed to predict response time, while Signal Detection Theory models are designed to predict performance accuracy. Moreover, current implementations of the Guided Search model require the use of Monte-Carlo simulations, a method that makes fitting the model's performance quantitatively to human data more computationally time consuming. We have extended the Guided Search model to predict human accuracy in target-localization search tasks. We have also developed analytic expressions that simplify simulation of the model to the evaluation of a small set of equations using only three free parameters. This new implementation and extension of the Guided Search model will enable direct quantitative comparisons with human performance in target-localization search experiments and with the predictions of Signal Detection Theory and other search accuracy models.

Characterizing Decision-Analysis Performances of Risk Prediction Models Using ADAPT Curves.

PubMed

Lee, Wen-Chung; Wu, Yun-Chun

2016-01-01

The area under the receiver operating characteristic curve is a widely used index to characterize the performance of diagnostic tests and prediction models. However, the index does not explicitly acknowledge the utilities of risk predictions. Moreover, for most clinical settings, what counts is whether a prediction model can guide therapeutic decisions in a way that improves patient outcomes, rather than to simply update probabilities.Based on decision theory, the authors propose an alternative index, the "average deviation about the probability threshold" (ADAPT).An ADAPT curve (a plot of ADAPT value against the probability threshold) neatly characterizes the decision-analysis performances of a risk prediction model.Several prediction models can be compared for their ADAPT values at a chosen probability threshold, for a range of plausible threshold values, or for the whole ADAPT curves. This should greatly facilitate the selection of diagnostic tests and prediction models.

A Unified Model of Performance: Validation of its Predictions across Different Sleep/Wake Schedules.

PubMed

Ramakrishnan, Sridhar; Wesensten, Nancy J; Balkin, Thomas J; Reifman, Jaques

2016-01-01

Historically, mathematical models of human neurobehavioral performance developed on data from one sleep study were limited to predicting performance in similar studies, restricting their practical utility. We recently developed a unified model of performance (UMP) to predict the effects of the continuum of sleep loss-from chronic sleep restriction (CSR) to total sleep deprivation (TSD) challenges-and validated it using data from two studies of one laboratory. Here, we significantly extended this effort by validating the UMP predictions across a wide range of sleep/wake schedules from different studies and laboratories. We developed the UMP on psychomotor vigilance task (PVT) lapse data from one study encompassing four different CSR conditions (7 d of 3, 5, 7, and 9 h of sleep/night), and predicted performance in five other studies (from four laboratories), including different combinations of TSD (40 to 88 h), CSR (2 to 6 h of sleep/night), control (8 to 10 h of sleep/night), and nap (nocturnal and diurnal) schedules. The UMP accurately predicted PVT performance trends across 14 different sleep/wake conditions, yielding average prediction errors between 7% and 36%, with the predictions lying within 2 standard errors of the measured data 87% of the time. In addition, the UMP accurately predicted performance impairment (average error of 15%) for schedules (TSD and naps) not used in model development. The unified model of performance can be used as a tool to help design sleep/wake schedules to optimize the extent and duration of neurobehavioral performance and to accelerate recovery after sleep loss. © 2016 Associated Professional Sleep Societies, LLC.

Predicting BRCA1 and BRCA2 gene mutation carriers: comparison of LAMBDA, BRCAPRO, Myriad II, and modified Couch models.

PubMed

Lindor, Noralane M; Lindor, Rachel A; Apicella, Carmel; Dowty, James G; Ashley, Amanda; Hunt, Katherine; Mincey, Betty A; Wilson, Marcia; Smith, M Cathie; Hopper, John L

2007-01-01

Models have been developed to predict the probability that a person carries a detectable germline mutation in the BRCA1 or BRCA2 genes. Their relative performance in a clinical setting is unclear. To compare the performance characteristics of four BRCA1/BRCA2 gene mutation prediction models: LAMBDA, based on a checklist and scores developed from data on Ashkenazi Jewish (AJ) women; BRCAPRO, a Bayesian computer program; modified Couch tables based on regression analyses; and Myriad II tables collated by Myriad Genetics Laboratories. Family cancer history data were analyzed from 200 probands from the Mayo Clinic Familial Cancer Program, in a multispecialty tertiary care group practice. All probands had clinical testing for BRCA1 and BRCA2 mutations conducted in a single laboratory. For each model, performance was assessed by the area under the receiver operator characteristic curve (ROC) and by tests of accuracy and dispersion. Cases "missed" by one or more models (model predicted less than 10% probability of mutation when a mutation was actually found) were compared across models. All models gave similar areas under the ROC curve of 0.71 to 0.76. All models except LAMBDA substantially under-predicted the numbers of carriers. All models were too dispersed. In terms of ranking, all prediction models performed reasonably well with similar performance characteristics. Model predictions were widely discrepant for some families. Review of cancer family histories by an experienced clinician continues to be vital to ensure that critical elements are not missed and that the most appropriate risk prediction figures are provided.

Predictor characteristics necessary for building a clinically useful risk prediction model: a simulation study.

PubMed

Schummers, Laura; Himes, Katherine P; Bodnar, Lisa M; Hutcheon, Jennifer A

2016-09-21

Compelled by the intuitive appeal of predicting each individual patient's risk of an outcome, there is a growing interest in risk prediction models. While the statistical methods used to build prediction models are increasingly well understood, the literature offers little insight to researchers seeking to gauge a priori whether a prediction model is likely to perform well for their particular research question. The objective of this study was to inform the development of new risk prediction models by evaluating model performance under a wide range of predictor characteristics. Data from all births to overweight or obese women in British Columbia, Canada from 2004 to 2012 (n = 75,225) were used to build a risk prediction model for preeclampsia. The data were then augmented with simulated predictors of the outcome with pre-set prevalence values and univariable odds ratios. We built 120 risk prediction models that included known demographic and clinical predictors, and one, three, or five of the simulated variables. Finally, we evaluated standard model performance criteria (discrimination, risk stratification capacity, calibration, and Nagelkerke's r 2 ) for each model. Findings from our models built with simulated predictors demonstrated the predictor characteristics required for a risk prediction model to adequately discriminate cases from non-cases and to adequately classify patients into clinically distinct risk groups. Several predictor characteristics can yield well performing risk prediction models; however, these characteristics are not typical of predictor-outcome relationships in many population-based or clinical data sets. Novel predictors must be both strongly associated with the outcome and prevalent in the population to be useful for clinical prediction modeling (e.g., one predictor with prevalence ≥20 % and odds ratio ≥8, or 3 predictors with prevalence ≥10 % and odds ratios ≥4). Area under the receiver operating characteristic curve values of >0.8 were necessary to achieve reasonable risk stratification capacity. Our findings provide a guide for researchers to estimate the expected performance of a prediction model before a model has been built based on the characteristics of available predictors.

The Motivational Determinants of Task Performance in a Non-Industrial Milieu: A Modification and Extension of Vroom's Model.

ERIC Educational Resources Information Center

Mendel, Raymond M.; Dickinson, Terry L.

Vroom's cognitive model, which proposes to both explain and predict an individual's level of work productivity by drawing on the construct motivation, is discussed and three hypotheses generated: (1) that Vroom's model does predict performance in a non-industrial setting; (2) that it predicts self-perceived performance better than measures…

Use of model calibration to achieve high accuracy in analysis of computer networks

DOEpatents

Frogner, Bjorn; Guarro, Sergio; Scharf, Guy

2004-05-11

A system and method are provided for creating a network performance prediction model, and calibrating the prediction model, through application of network load statistical analyses. The method includes characterizing the measured load on the network, which may include background load data obtained over time, and may further include directed load data representative of a transaction-level event. Probabilistic representations of load data are derived to characterize the statistical persistence of the network performance variability and to determine delays throughout the network. The probabilistic representations are applied to the network performance prediction model to adapt the model for accurate prediction of network performance. Certain embodiments of the method and system may be used for analysis of the performance of a distributed application characterized as data packet streams.

Integrated Modeling Activities for the James Webb Space Telescope: Structural-Thermal-Optical Analysis

NASA Technical Reports Server (NTRS)

Johnston, John D.; Howard, Joseph M.; Mosier, Gary E.; Parrish, Keith A.; McGinnis, Mark A.; Bluth, Marcel; Kim, Kevin; Ha, Kong Q.

2004-01-01

The James Web Space Telescope (JWST) is a large, infrared-optimized space telescope scheduled for launch in 2011. This is a continuation of a series of papers on modeling activities for JWST. The structural-thermal-optical, often referred to as STOP, analysis process is used to predict the effect of thermal distortion on optical performance. The benchmark STOP analysis for JWST assesses the effect of an observatory slew on wavefront error. Temperatures predicted using geometric and thermal math models are mapped to a structural finite element model in order to predict thermally induced deformations. Motions and deformations at optical surfaces are then input to optical models, and optical performance is predicted using either an optical ray trace or a linear optical analysis tool. In addition to baseline performance predictions, a process for performing sensitivity studies to assess modeling uncertainties is described.

Learning Instance-Specific Predictive Models

PubMed Central

Visweswaran, Shyam; Cooper, Gregory F.

2013-01-01

This paper introduces a Bayesian algorithm for constructing predictive models from data that are optimized to predict a target variable well for a particular instance. This algorithm learns Markov blanket models, carries out Bayesian model averaging over a set of models to predict a target variable of the instance at hand, and employs an instance-specific heuristic to locate a set of suitable models to average over. We call this method the instance-specific Markov blanket (ISMB) algorithm. The ISMB algorithm was evaluated on 21 UCI data sets using five different performance measures and its performance was compared to that of several commonly used predictive algorithms, including nave Bayes, C4.5 decision tree, logistic regression, neural networks, k-Nearest Neighbor, Lazy Bayesian Rules, and AdaBoost. Over all the data sets, the ISMB algorithm performed better on average on all performance measures against all the comparison algorithms. PMID:25045325

Predicting Student Academic Performance in an Engineering Dynamics Course: A Comparison of Four Types of Predictive Mathematical Models

ERIC Educational Resources Information Center

Huang, Shaobo; Fang, Ning

2013-01-01

Predicting student academic performance has long been an important research topic in many academic disciplines. The present study is the first study that develops and compares four types of mathematical models to predict student academic performance in engineering dynamics--a high-enrollment, high-impact, and core course that many engineering…

Charge-coupled-device X-ray detector performance model

NASA Technical Reports Server (NTRS)

Bautz, M. W.; Berman, G. E.; Doty, J. P.; Ricker, G. R.

1987-01-01

A model that predicts the performance characteristics of CCD detectors being developed for use in X-ray imaging is presented. The model accounts for the interactions of both X-rays and charged particles with the CCD and simulates the transport and loss of charge in the detector. Predicted performance parameters include detective and net quantum efficiencies, split-event probability, and a parameter characterizing the effective thickness presented by the detector to cosmic-ray protons. The predicted performance of two CCDs of different epitaxial layer thicknesses is compared. The model predicts that in each device incomplete recovery of the charge liberated by a photon of energy between 0.1 and 10 keV is very likely to be accompanied by charge splitting between adjacent pixels. The implications of the model predictions for CCD data processing algorithms are briefly discussed.

Predicting Jakarta composite index using hybrid of fuzzy time series and support vector regression models

NASA Astrophysics Data System (ADS)

Febrian Umbara, Rian; Tarwidi, Dede; Budi Setiawan, Erwin

2018-03-01

The paper discusses the prediction of Jakarta Composite Index (JCI) in Indonesia Stock Exchange. The study is based on JCI historical data for 1286 days to predict the value of JCI one day ahead. This paper proposes predictions done in two stages., The first stage using Fuzzy Time Series (FTS) to predict values of ten technical indicators, and the second stage using Support Vector Regression (SVR) to predict the value of JCI one day ahead, resulting in a hybrid prediction model FTS-SVR. The performance of this combined prediction model is compared with the performance of the single stage prediction model using SVR only. Ten technical indicators are used as input for each model.

A Free Wake Numerical Simulation for Darrieus Vertical Axis Wind Turbine Performance Prediction

NASA Astrophysics Data System (ADS)

Belu, Radian

2010-11-01

In the last four decades, several aerodynamic prediction models have been formulated for the Darrieus wind turbine performances and characteristics. We can identified two families: stream-tube and vortex. The paper presents a simplified numerical techniques for simulating vertical axis wind turbine flow, based on the lifting line theory and a free vortex wake model, including dynamic stall effects for predicting the performances of a 3-D vertical axis wind turbine. A vortex model is used in which the wake is composed of trailing stream-wise and shedding span-wise vortices, whose strengths are equal to the change in the bound vortex strength as required by the Helmholz and Kelvin theorems. Performance parameters are computed by application of the Biot-Savart law along with the Kutta-Jukowski theorem and a semi-empirical stall model. We tested the developed model with an adaptation of the earlier multiple stream-tube performance prediction model for the Darrieus turbines. Predictions by using our method are shown to compare favorably with existing experimental data and the outputs of other numerical models. The method can predict accurately the local and global performances of a vertical axis wind turbine, and can be used in the design and optimization of wind turbines for built environment applications.

Prediction models for intracranial hemorrhage or major bleeding in patients on antiplatelet therapy: a systematic review and external validation study.

PubMed

Hilkens, N A; Algra, A; Greving, J P

2016-01-01

ESSENTIALS: Prediction models may help to identify patients at high risk of bleeding on antiplatelet therapy. We identified existing prediction models for bleeding and validated them in patients with cerebral ischemia. Five prediction models were identified, all of which had some methodological shortcomings. Performance in patients with cerebral ischemia was poor. Background Antiplatelet therapy is widely used in secondary prevention after a transient ischemic attack (TIA) or ischemic stroke. Bleeding is the main adverse effect of antiplatelet therapy and is potentially life threatening. Identification of patients at increased risk of bleeding may help target antiplatelet therapy. This study sought to identify existing prediction models for intracranial hemorrhage or major bleeding in patients on antiplatelet therapy and evaluate their performance in patients with cerebral ischemia. We systematically searched PubMed and Embase for existing prediction models up to December 2014. The methodological quality of the included studies was assessed with the CHARMS checklist. Prediction models were externally validated in the European Stroke Prevention Study 2, comprising 6602 patients with a TIA or ischemic stroke. We assessed discrimination and calibration of included prediction models. Five prediction models were identified, of which two were developed in patients with previous cerebral ischemia. Three studies assessed major bleeding, one studied intracerebral hemorrhage and one gastrointestinal bleeding. None of the studies met all criteria of good quality. External validation showed poor discriminative performance, with c-statistics ranging from 0.53 to 0.64 and poor calibration. A limited number of prediction models is available that predict intracranial hemorrhage or major bleeding in patients on antiplatelet therapy. The methodological quality of the models varied, but was generally low. Predictive performance in patients with cerebral ischemia was poor. In order to reliably predict the risk of bleeding in patients with cerebral ischemia, development of a prediction model according to current methodological standards is needed. © 2015 International Society on Thrombosis and Haemostasis.

Iowa calibration of MEPDG performance prediction models.

DOT National Transportation Integrated Search

2013-06-01

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

On the use and the performance of software reliability growth models

NASA Technical Reports Server (NTRS)

Keiller, Peter A.; Miller, Douglas R.

1991-01-01

We address the problem of predicting future failures for a piece of software. The number of failures occurring during a finite future time interval is predicted from the number failures observed during an initial period of usage by using software reliability growth models. Two different methods for using the models are considered: straightforward use of individual models, and dynamic selection among models based on goodness-of-fit and quality-of-prediction criteria. Performance is judged by the relative error of the predicted number of failures over future finite time intervals relative to the number of failures eventually observed during the intervals. Six of the former models and eight of the latter are evaluated, based on their performance on twenty data sets. Many open questions remain regarding the use and the performance of software reliability growth models.

Prediction models for successful external cephalic version: a systematic review.

PubMed

Velzel, Joost; de Hundt, Marcella; Mulder, Frederique M; Molkenboer, Jan F M; Van der Post, Joris A M; Mol, Ben W; Kok, Marjolein

2015-12-01

To provide an overview of existing prediction models for successful ECV, and to assess their quality, development and performance. We searched MEDLINE, EMBASE and the Cochrane Library to identify all articles reporting on prediction models for successful ECV published from inception to January 2015. We extracted information on study design, sample size, model-building strategies and validation. We evaluated the phases of model development and summarized their performance in terms of discrimination, calibration and clinical usefulness. We collected different predictor variables together with their defined significance, in order to identify important predictor variables for successful ECV. We identified eight articles reporting on seven prediction models. All models were subjected to internal validation. Only one model was also validated in an external cohort. Two prediction models had a low overall risk of bias, of which only one showed promising predictive performance at internal validation. This model also completed the phase of external validation. For none of the models their impact on clinical practice was evaluated. The most important predictor variables for successful ECV described in the selected articles were parity, placental location, breech engagement and the fetal head being palpable. One model was assessed using discrimination and calibration using internal (AUC 0.71) and external validation (AUC 0.64), while two other models were assessed with discrimination and calibration, respectively. We found one prediction model for breech presentation that was validated in an external cohort and had acceptable predictive performance. This model should be used to council women considering ECV. Copyright © 2015. Published by Elsevier Ireland Ltd.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models.

PubMed

Barkhordari, Mahnaz; Padyab, Mojgan; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-01-01

Prediction is a fundamental part of prevention of cardiovascular diseases (CVD). The development of prediction algorithms based on the multivariate regression models loomed several decades ago. Parallel with predictive models development, biomarker researches emerged in an impressively great scale. The key question is how best to assess and quantify the improvement in risk prediction offered by new biomarkers or more basically how to assess the performance of a risk prediction model. Discrimination, calibration, and added predictive value have been recently suggested to be used while comparing the predictive performances of the predictive models' with and without novel biomarkers. Lack of user-friendly statistical software has restricted implementation of novel model assessment methods while examining novel biomarkers. We intended, thus, to develop a user-friendly software that could be used by researchers with few programming skills. We have written a Stata command that is intended to help researchers obtain cut point-free and cut point-based net reclassification improvement index and (NRI) and relative and absolute Integrated discriminatory improvement index (IDI) for logistic-based regression analyses.We applied the commands to a real data on women participating the Tehran lipid and glucose study (TLGS) to examine if information of a family history of premature CVD, waist circumference, and fasting plasma glucose can improve predictive performance of the Framingham's "general CVD risk" algorithm. The command is addpred for logistic regression models. The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers.

Predicting Energy Performance of a Net-Zero Energy Building: A Statistical Approach

PubMed Central

Kneifel, Joshua; Webb, David

2016-01-01

Performance-based building requirements have become more prevalent because it gives freedom in building design while still maintaining or exceeding the energy performance required by prescriptive-based requirements. In order to determine if building designs reach target energy efficiency improvements, it is necessary to estimate the energy performance of a building using predictive models and different weather conditions. Physics-based whole building energy simulation modeling is the most common approach. However, these physics-based models include underlying assumptions and require significant amounts of information in order to specify the input parameter values. An alternative approach to test the performance of a building is to develop a statistically derived predictive regression model using post-occupancy data that can accurately predict energy consumption and production based on a few common weather-based factors, thus requiring less information than simulation models. A regression model based on measured data should be able to predict energy performance of a building for a given day as long as the weather conditions are similar to those during the data collection time frame. This article uses data from the National Institute of Standards and Technology (NIST) Net-Zero Energy Residential Test Facility (NZERTF) to develop and validate a regression model to predict the energy performance of the NZERTF using two weather variables aggregated to the daily level, applies the model to estimate the energy performance of hypothetical NZERTFs located in different cities in the Mixed-Humid climate zone, and compares these estimates to the results from already existing EnergyPlus whole building energy simulations. This regression model exhibits agreement with EnergyPlus predictive trends in energy production and net consumption, but differs greatly in energy consumption. The model can be used as a framework for alternative and more complex models based on the experimental data collected from the NZERTF. PMID:27956756

Predicting Energy Performance of a Net-Zero Energy Building: A Statistical Approach.

PubMed

Kneifel, Joshua; Webb, David

2016-09-01

Performance-based building requirements have become more prevalent because it gives freedom in building design while still maintaining or exceeding the energy performance required by prescriptive-based requirements. In order to determine if building designs reach target energy efficiency improvements, it is necessary to estimate the energy performance of a building using predictive models and different weather conditions. Physics-based whole building energy simulation modeling is the most common approach. However, these physics-based models include underlying assumptions and require significant amounts of information in order to specify the input parameter values. An alternative approach to test the performance of a building is to develop a statistically derived predictive regression model using post-occupancy data that can accurately predict energy consumption and production based on a few common weather-based factors, thus requiring less information than simulation models. A regression model based on measured data should be able to predict energy performance of a building for a given day as long as the weather conditions are similar to those during the data collection time frame. This article uses data from the National Institute of Standards and Technology (NIST) Net-Zero Energy Residential Test Facility (NZERTF) to develop and validate a regression model to predict the energy performance of the NZERTF using two weather variables aggregated to the daily level, applies the model to estimate the energy performance of hypothetical NZERTFs located in different cities in the Mixed-Humid climate zone, and compares these estimates to the results from already existing EnergyPlus whole building energy simulations. This regression model exhibits agreement with EnergyPlus predictive trends in energy production and net consumption, but differs greatly in energy consumption. The model can be used as a framework for alternative and more complex models based on the experimental data collected from the NZERTF.

Physics-based model for predicting the performance of a miniature wind turbine

NASA Astrophysics Data System (ADS)

Xu, F. J.; Hu, J. Z.; Qiu, Y. P.; Yuan, F. G.

2011-04-01

A comprehensive physics-based model for predicting the performance of the miniature wind turbine (MWT) for power wireless sensor systems was proposed in this paper. An approximation of the power coefficient of the turbine rotor was made after the turbine rotor performance was measured. Incorporation of the approximation with the equivalent circuit model which was proposed according to the principles of the MWT, the overall system performance of the MWT was predicted. To demonstrate the prediction, the MWT system comprised of a 7.6 cm thorgren plastic propeller as turbine rotor and a DC motor as generator was designed and its performance was tested experimentally. The predicted output voltage, power and system efficiency are matched well with the tested results, which imply that this study holds promise in estimating and optimizing the performance of the MWT.

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

PubMed Central

Yang, Chuanlei; Wang, Yinyan; Wang, Hechun

2018-01-01

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

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

PubMed

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

2018-01-01

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

Integrated Modeling Activities for the James Webb Space Telescope (JWST): Structural-Thermal-Optical Analysis

NASA Technical Reports Server (NTRS)

Johnston, John D.; Parrish, Keith; Howard, Joseph M.; Mosier, Gary E.; McGinnis, Mark; Bluth, Marcel; Kim, Kevin; Ha, Hong Q.

2004-01-01

This is a continuation of a series of papers on modeling activities for JWST. The structural-thermal- optical, often referred to as "STOP", analysis process is used to predict the effect of thermal distortion on optical performance. The benchmark STOP analysis for JWST assesses the effect of an observatory slew on wavefront error. The paper begins an overview of multi-disciplinary engineering analysis, or integrated modeling, which is a critical element of the JWST mission. The STOP analysis process is then described. This process consists of the following steps: thermal analysis, structural analysis, and optical analysis. Temperatures predicted using geometric and thermal math models are mapped to the structural finite element model in order to predict thermally-induced deformations. Motions and deformations at optical surfaces are input to optical models and optical performance is predicted using either an optical ray trace or WFE estimation techniques based on prior ray traces or first order optics. Following the discussion of the analysis process, results based on models representing the design at the time of the System Requirements Review. In addition to baseline performance predictions, sensitivity studies are performed to assess modeling uncertainties. Of particular interest is the sensitivity of optical performance to uncertainties in temperature predictions and variations in metal properties. The paper concludes with a discussion of modeling uncertainty as it pertains to STOP analysis.

Multivariate meta-analysis of individual participant data helped externally validate the performance and implementation of a prediction model.

PubMed

Snell, Kym I E; Hua, Harry; Debray, Thomas P A; Ensor, Joie; Look, Maxime P; Moons, Karel G M; Riley, Richard D

2016-01-01

Our aim was to improve meta-analysis methods for summarizing a prediction model's performance when individual participant data are available from multiple studies for external validation. We suggest multivariate meta-analysis for jointly synthesizing calibration and discrimination performance, while accounting for their correlation. The approach estimates a prediction model's average performance, the heterogeneity in performance across populations, and the probability of "good" performance in new populations. This allows different implementation strategies (e.g., recalibration) to be compared. Application is made to a diagnostic model for deep vein thrombosis (DVT) and a prognostic model for breast cancer mortality. In both examples, multivariate meta-analysis reveals that calibration performance is excellent on average but highly heterogeneous across populations unless the model's intercept (baseline hazard) is recalibrated. For the cancer model, the probability of "good" performance (defined by C statistic ≥0.7 and calibration slope between 0.9 and 1.1) in a new population was 0.67 with recalibration but 0.22 without recalibration. For the DVT model, even with recalibration, there was only a 0.03 probability of "good" performance. Multivariate meta-analysis can be used to externally validate a prediction model's calibration and discrimination performance across multiple populations and to evaluate different implementation strategies. Crown Copyright © 2016. Published by Elsevier Inc. All rights reserved.

Comparison of five modelling techniques to predict the spatial distribution and abundance of seabirds

USGS Publications Warehouse

O'Connell, Allan F.; Gardner, Beth; Oppel, Steffen; Meirinho, Ana; Ramírez, Iván; Miller, Peter I.; Louzao, Maite

2012-01-01

Knowledge about the spatial distribution of seabirds at sea is important for conservation. During marine conservation planning, logistical constraints preclude seabird surveys covering the complete area of interest and spatial distribution of seabirds is frequently inferred from predictive statistical models. Increasingly complex models are available to relate the distribution and abundance of pelagic seabirds to environmental variables, but a comparison of their usefulness for delineating protected areas for seabirds is lacking. Here we compare the performance of five modelling techniques (generalised linear models, generalised additive models, Random Forest, boosted regression trees, and maximum entropy) to predict the distribution of Balearic Shearwaters (Puffinus mauretanicus) along the coast of the western Iberian Peninsula. We used ship transect data from 2004 to 2009 and 13 environmental variables to predict occurrence and density, and evaluated predictive performance of all models using spatially segregated test data. Predicted distribution varied among the different models, although predictive performance varied little. An ensemble prediction that combined results from all five techniques was robust and confirmed the existence of marine important bird areas for Balearic Shearwaters in Portugal and Spain. Our predictions suggested additional areas that would be of high priority for conservation and could be proposed as protected areas. Abundance data were extremely difficult to predict, and none of five modelling techniques provided a reliable prediction of spatial patterns. We advocate the use of ensemble modelling that combines the output of several methods to predict the spatial distribution of seabirds, and use these predictions to target separate surveys assessing the abundance of seabirds in areas of regular use.

A Unified Model of Performance for Predicting the Effects of Sleep and Caffeine

PubMed Central

Ramakrishnan, Sridhar; Wesensten, Nancy J.; Kamimori, Gary H.; Moon, James E.; Balkin, Thomas J.; Reifman, Jaques

2016-01-01

Study Objectives: Existing mathematical models of neurobehavioral performance cannot predict the beneficial effects of caffeine across the spectrum of sleep loss conditions, limiting their practical utility. Here, we closed this research gap by integrating a model of caffeine effects with the recently validated unified model of performance (UMP) into a single, unified modeling framework. We then assessed the accuracy of this new UMP in predicting performance across multiple studies. Methods: We hypothesized that the pharmacodynamics of caffeine vary similarly during both wakefulness and sleep, and that caffeine has a multiplicative effect on performance. Accordingly, to represent the effects of caffeine in the UMP, we multiplied a dose-dependent caffeine factor (which accounts for the pharmacokinetics and pharmacodynamics of caffeine) to the performance estimated in the absence of caffeine. We assessed the UMP predictions in 14 distinct laboratory- and field-study conditions, including 7 different sleep-loss schedules (from 5 h of sleep per night to continuous sleep loss for 85 h) and 6 different caffeine doses (from placebo to repeated 200 mg doses to a single dose of 600 mg). Results: The UMP accurately predicted group-average psychomotor vigilance task performance data across the different sleep loss and caffeine conditions (6% < error < 27%), yielding greater accuracy for mild and moderate sleep loss conditions than for more severe cases. Overall, accounting for the effects of caffeine resulted in improved predictions (after caffeine consumption) by up to 70%. Conclusions: The UMP provides the first comprehensive tool for accurate selection of combinations of sleep schedules and caffeine countermeasure strategies to optimize neurobehavioral performance. Citation: Ramakrishnan S, Wesensten NJ, Kamimori GH, Moon JE, Balkin TJ, Reifman J. A unified model of performance for predicting the effects of sleep and caffeine. SLEEP 2016;39(10):1827–1841. PMID:27397562

A predictive model of flight crew performance in automated air traffic control and flight management operations

DOT National Transportation Integrated Search

1995-01-01

Prepared ca. 1995. This paper describes Air-MIDAS, a model of pilot performance in interaction with varied levels of automation in flight management operations. The model was used to predict the performance of a two person flight crew responding to c...

Predicting Document Retrieval System Performance: An Expected Precision Measure.

ERIC Educational Resources Information Center

Losee, Robert M., Jr.

1987-01-01

Describes an expected precision (EP) measure designed to predict document retrieval performance. Highlights include decision theoretic models; precision and recall as measures of system performance; EP graphs; relevance feedback; and computing the retrieval status value of a document for two models, the Binary Independent Model and the Two Poisson…

A Complete Procedure for Predicting and Improving the Performance of HAWT's

NASA Astrophysics Data System (ADS)

Al-Abadi, Ali; Ertunç, Özgür; Sittig, Florian; Delgado, Antonio

2014-06-01

A complete procedure for predicting and improving the performance of the horizontal axis wind turbine (HAWT) has been developed. The first process is predicting the power extracted by the turbine and the derived rotor torque, which should be identical to that of the drive unit. The BEM method and a developed post-stall treatment for resolving stall-regulated HAWT is incorporated in the prediction. For that, a modified stall-regulated prediction model, which can predict the HAWT performance over the operating range of oncoming wind velocity, is derived from existing models. The model involves radius and chord, which has made it more general in applications for predicting the performance of different scales and rotor shapes of HAWTs. The second process is modifying the rotor shape by an optimization process, which can be applied to any existing HAWT, to improve its performance. A gradient- based optimization is used for adjusting the chord and twist angle distribution of the rotor blade to increase the extraction of the power while keeping the drive torque constant, thus the same drive unit can be kept. The final process is testing the modified turbine to predict its enhanced performance. The procedure is applied to NREL phase-VI 10kW as a baseline turbine. The study has proven the applicability of the developed model in predicting the performance of the baseline as well as the optimized turbine. In addition, the optimization method has shown that the power coefficient can be increased while keeping same design rotational speed.

Complex versus simple models: ion-channel cardiac toxicity prediction.

PubMed

Mistry, Hitesh B

2018-01-01

There is growing interest in applying detailed mathematical models of the heart for ion-channel related cardiac toxicity prediction. However, a debate as to whether such complex models are required exists. Here an assessment in the predictive performance between two established large-scale biophysical cardiac models and a simple linear model B net was conducted. Three ion-channel data-sets were extracted from literature. Each compound was designated a cardiac risk category using two different classification schemes based on information within CredibleMeds. The predictive performance of each model within each data-set for each classification scheme was assessed via a leave-one-out cross validation. Overall the B net model performed equally as well as the leading cardiac models in two of the data-sets and outperformed both cardiac models on the latest. These results highlight the importance of benchmarking complex versus simple models but also encourage the development of simple models.

The predictive performance of a path-dependent exotic-option credit risk model in the emerging market

NASA Astrophysics Data System (ADS)

Chen, Dar-Hsin; Chou, Heng-Chih; Wang, David; Zaabar, Rim

2011-06-01

Most empirical research of the path-dependent, exotic-option credit risk model focuses on developed markets. Taking Taiwan as an example, this study investigates the bankruptcy prediction performance of the path-dependent, barrier option model in the emerging market. We adopt Duan's (1994) [11], (2000) [12] transformed-data maximum likelihood estimation (MLE) method to directly estimate the unobserved model parameters, and compare the predictive ability of the barrier option model to the commonly adopted credit risk model, Merton's model. Our empirical findings show that the barrier option model is more powerful than Merton's model in predicting bankruptcy in the emerging market. Moreover, we find that the barrier option model predicts bankruptcy much better for highly-leveraged firms. Finally, our findings indicate that the prediction accuracy of the credit risk model can be improved by higher asset liquidity and greater financial transparency.

Assessing effects of variation in global climate data sets on spatial predictions from climate envelope models

USGS Publications Warehouse

Romañach, Stephanie; Watling, James I.; Fletcher, Robert J.; Speroterra, Carolina; Bucklin, David N.; Brandt, Laura A.; Pearlstine, Leonard G.; Escribano, Yesenia; Mazzotti, Frank J.

2014-01-01

Climate change poses new challenges for natural resource managers. Predictive modeling of species–environment relationships using climate envelope models can enhance our understanding of climate change effects on biodiversity, assist in assessment of invasion risk by exotic organisms, and inform life-history understanding of individual species. While increasing interest has focused on the role of uncertainty in future conditions on model predictions, models also may be sensitive to the initial conditions on which they are trained. Although climate envelope models are usually trained using data on contemporary climate, we lack systematic comparisons of model performance and predictions across alternative climate data sets available for model training. Here, we seek to fill that gap by comparing variability in predictions between two contemporary climate data sets to variability in spatial predictions among three alternative projections of future climate. Overall, correlations between monthly temperature and precipitation variables were very high for both contemporary and future data. Model performance varied across algorithms, but not between two alternative contemporary climate data sets. Spatial predictions varied more among alternative general-circulation models describing future climate conditions than between contemporary climate data sets. However, we did find that climate envelope models with low Cohen's kappa scores made more discrepant spatial predictions between climate data sets for the contemporary period than did models with high Cohen's kappa scores. We suggest conservation planners evaluate multiple performance metrics and be aware of the importance of differences in initial conditions for spatial predictions from climate envelope models.

Scoring annual earthquake predictions in China

NASA Astrophysics Data System (ADS)

Zhuang, Jiancang; Jiang, Changsheng

2012-02-01

The Annual Consultation Meeting on Earthquake Tendency in China is held by the China Earthquake Administration (CEA) in order to provide one-year earthquake predictions over most China. In these predictions, regions of concern are denoted together with the corresponding magnitude range of the largest earthquake expected during the next year. Evaluating the performance of these earthquake predictions is rather difficult, especially for regions that are of no concern, because they are made on arbitrary regions with flexible magnitude ranges. In the present study, the gambling score is used to evaluate the performance of these earthquake predictions. Based on a reference model, this scoring method rewards successful predictions and penalizes failures according to the risk (probability of being failure) that the predictors have taken. Using the Poisson model, which is spatially inhomogeneous and temporally stationary, with the Gutenberg-Richter law for earthquake magnitudes as the reference model, we evaluate the CEA predictions based on 1) a partial score for evaluating whether issuing the alarmed regions is based on information that differs from the reference model (knowledge of average seismicity level) and 2) a complete score that evaluates whether the overall performance of the prediction is better than the reference model. The predictions made by the Annual Consultation Meetings on Earthquake Tendency from 1990 to 2003 are found to include significant precursory information, but the overall performance is close to that of the reference model.

A Prediction Model for Community Colleges Using Graduation Rate as the Performance Indicator

ERIC Educational Resources Information Center

Moosai, Susan

2010-01-01

In this thesis a prediction model using graduation rate as the performance indicator is obtained for community colleges for three cohort years, 2003, 2004, and 2005 in the states of California, Florida, and Michigan. Multiple Regression analysis, using an aggregate of seven predictor variables, was employed in determining this prediction model.…

Risk prediction models of breast cancer: a systematic review of model performances.

PubMed

Anothaisintawee, Thunyarat; Teerawattananon, Yot; Wiratkapun, Chollathip; Kasamesup, Vijj; Thakkinstian, Ammarin

2012-05-01

The number of risk prediction models has been increasingly developed, for estimating about breast cancer in individual women. However, those model performances are questionable. We therefore have conducted a study with the aim to systematically review previous risk prediction models. The results from this review help to identify the most reliable model and indicate the strengths and weaknesses of each model for guiding future model development. We searched MEDLINE (PubMed) from 1949 and EMBASE (Ovid) from 1974 until October 2010. Observational studies which constructed models using regression methods were selected. Information about model development and performance were extracted. Twenty-five out of 453 studies were eligible. Of these, 18 developed prediction models and 7 validated existing prediction models. Up to 13 variables were included in the models and sample sizes for each study ranged from 550 to 2,404,636. Internal validation was performed in four models, while five models had external validation. Gail and Rosner and Colditz models were the significant models which were subsequently modified by other scholars. Calibration performance of most models was fair to good (expected/observe ratio: 0.87-1.12), but discriminatory accuracy was poor to fair both in internal validation (concordance statistics: 0.53-0.66) and in external validation (concordance statistics: 0.56-0.63). Most models yielded relatively poor discrimination in both internal and external validation. This poor discriminatory accuracy of existing models might be because of a lack of knowledge about risk factors, heterogeneous subtypes of breast cancer, and different distributions of risk factors across populations. In addition the concordance statistic itself is insensitive to measure the improvement of discrimination. Therefore, the new method such as net reclassification index should be considered to evaluate the improvement of the performance of a new develop model.

Evaluation of a Pharmacokinetic-Pharmacodynamic Model for Hypouricemic Effects of Febuxostat Using Datasets Obtained from Real-world Patients.

PubMed

Hirai, Toshinori; Itoh, Toshimasa; Kimura, Toshimi; Echizen, Hirotoshi

2018-06-06

Febuxostat is an active xanthine oxidase (XO) inhibitor that is widely used in the hyperuricemia treatment. We aimed to evaluate the predictive performance of a pharmacokinetic-pharmacodynamic (PK-PD) model for hypouricemic effects of febuxostat. Previously, we have formulated a PK--PD model for predicting hypouricemic effects of febuxostat as a function of baseline serum urate levels, body weight, renal function, and drug dose using datasets reported in preapproval studies (Hirai T et al., Biol Pharm Bull 2016; 39: 1013-21). Using an updated model with sensitivity analysis, we examined the predictive performance of the PK-PD model using datasets obtained from the medical records of patients who received febuxostat from March 2011 to December 2015 at Tokyo Women's Medical University Hospital. Multivariate regression analysis was performed to explore clinical variables to improve the predictive performance of the model. A total of 1,199 serum urate data were retrieved from 168 patients (age: 60.5 ±17.7 years, 71.4% males) who received febuxostat as hyperuricemia treatment. There was a significant correlation (r=0.68, p<0.01) between serum urate levels observed and those predicted by the modified PK-PD model. A multivariate regression analysis revealed that the predictive performance of the model may be improved further by considering comorbidities, such as diabetes mellitus, estimated glomerular filtration rate (eGFR), and co-administration of loop diuretics (r = 0.77, p<0.01). The PK-PD model may be useful for predicting individualized maintenance doses of febuxostat in real-world patients. This article is protected by copyright. All rights reserved.

Predicting High-Power Performance in Professional Cyclists.

PubMed

Sanders, Dajo; Heijboer, Mathieu; Akubat, Ibrahim; Meijer, Kenneth; Hesselink, Matthijs K

2017-03-01

To assess if short-duration (5 to ~300 s) high-power performance can accurately be predicted using the anaerobic power reserve (APR) model in professional cyclists. Data from 4 professional cyclists from a World Tour cycling team were used. Using the maximal aerobic power, sprint peak power output, and an exponential constant describing the decrement in power over time, a power-duration relationship was established for each participant. To test the predictive accuracy of the model, several all-out field trials of different durations were performed by each cyclist. The power output achieved during the all-out trials was compared with the predicted power output by the APR model. The power output predicted by the model showed very large to nearly perfect correlations to the actual power output obtained during the all-out trials for each cyclist (r = .88 ± .21, .92 ± .17, .95 ± .13, and .97 ± .09). Power output during the all-out trials remained within an average of 6.6% (53 W) of the predicted power output by the model. This preliminary pilot study presents 4 case studies on the applicability of the APR model in professional cyclists using a field-based approach. The decrement in all-out performance during high-intensity exercise seems to conform to a general relationship with a single exponential-decay model describing the decrement in power vs increasing duration. These results are in line with previous studies using the APR model to predict performance during brief all-out trials. Future research should evaluate the APR model with a larger sample size of elite cyclists.

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

PubMed

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

2014-02-01

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

A multilateral modelling of Youth Soccer Performance Index (YSPI)

NASA Astrophysics Data System (ADS)

Bisyri Husin Musawi Maliki, Ahmad; Razali Abdullah, Mohamad; Juahir, Hafizan; Abdullah, Farhana; Ain Shahirah Abdullah, Nurul; Muazu Musa, Rabiu; Musliha Mat-Rasid, Siti; Adnan, Aleesha; Azura Kosni, Norlaila; Muhamad, Wan Siti Amalina Wan; Afiqah Mohamad Nasir, Nur

2018-04-01

This study aims to identify the most dominant factors that influencing performance of soccer player and to predict group performance for soccer players. A total of 184 of youth soccer players from Malaysia sport school and six soccer academy encompasses as respondence of the study. Exploratory factor analysis (EFA) and Confirmatory factor analysis (CFA) were computed to identify the most dominant factors whereas reducing the initial 26 parameters with recommended >0.5 of factor loading. Meanwhile, prediction of the soccer performance was predicted by regression model. CFA revealed that sit and reach, vertical jump, VO2max, age, weight, height, sitting height, calf circumference (cc), medial upper arm circumference (muac), maturation, bicep, triceps, subscapular, suprailiac, 5M, 10M, and 20M speed were the most dominant factors. Further index analysis forming Youth Soccer Performance Index (YSPI) resulting by categorizing three groups namely, high, moderate, and low. The regression model for this study was significant set as p < 0.001 and R2 is 0.8222 which explained that the model contributed a total of 82% prediction ability to predict the whole set of the variables. The significant parameters in contributing prediction of YSPI are discussed. As a conclusion, the precision of the prediction models by integrating a multilateral factor reflecting for predicting potential soccer player and hopefully can create a competitive soccer games.

Academic motivation, self-concept, engagement, and performance in high school: key processes from a longitudinal perspective.

PubMed

Green, Jasmine; Liem, Gregory Arief D; Martin, Andrew J; Colmar, Susan; Marsh, Herbert W; McInerney, Dennis

2012-10-01

The study tested three theoretically/conceptually hypothesized longitudinal models of academic processes leading to academic performance. Based on a longitudinal sample of 1866 high-school students across two consecutive years of high school (Time 1 and Time 2), the model with the most superior heuristic value demonstrated: (a) academic motivation and self-concept positively predicted attitudes toward school; (b) attitudes toward school positively predicted class participation and homework completion and negatively predicted absenteeism; and (c) class participation and homework completion positively predicted test performance whilst absenteeism negatively predicted test performance. Taken together, these findings provide support for the relevance of the self-system model and, particularly, the importance of examining the dynamic relationships amongst engagement factors of the model. The study highlights implications for educational and psychological theory, measurement, and intervention. Copyright © 2012 The Foundation for Professionals in Services for Adolescents. Published by Elsevier Ltd. All rights reserved.

The RAPIDD ebola forecasting challenge: Synthesis and lessons learnt.

PubMed

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

2018-03-01

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

Pre-operative prediction of surgical morbidity in children: comparison of five statistical models.

PubMed

Cooper, Jennifer N; Wei, Lai; Fernandez, Soledad A; Minneci, Peter C; Deans, Katherine J

2015-02-01

The accurate prediction of surgical risk is important to patients and physicians. Logistic regression (LR) models are typically used to estimate these risks. However, in the fields of data mining and machine-learning, many alternative classification and prediction algorithms have been developed. This study aimed to compare the performance of LR to several data mining algorithms for predicting 30-day surgical morbidity in children. We used the 2012 National Surgical Quality Improvement Program-Pediatric dataset to compare the performance of (1) a LR model that assumed linearity and additivity (simple LR model) (2) a LR model incorporating restricted cubic splines and interactions (flexible LR model) (3) a support vector machine, (4) a random forest and (5) boosted classification trees for predicting surgical morbidity. The ensemble-based methods showed significantly higher accuracy, sensitivity, specificity, PPV, and NPV than the simple LR model. However, none of the models performed better than the flexible LR model in terms of the aforementioned measures or in model calibration or discrimination. Support vector machines, random forests, and boosted classification trees do not show better performance than LR for predicting pediatric surgical morbidity. After further validation, the flexible LR model derived in this study could be used to assist with clinical decision-making based on patient-specific surgical risks. Copyright © 2014 Elsevier Ltd. All rights reserved.

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

NASA Astrophysics Data System (ADS)

Ko, P.; Kurosawa, S.

2014-03-01

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

Object detection in natural backgrounds predicted by discrimination performance and models

NASA Technical Reports Server (NTRS)

Rohaly, A. M.; Ahumada, A. J. Jr; Watson, A. B.

1997-01-01

Many models of visual performance predict image discriminability, the visibility of the difference between a pair of images. We compared the ability of three image discrimination models to predict the detectability of objects embedded in natural backgrounds. The three models were: a multiple channel Cortex transform model with within-channel masking; a single channel contrast sensitivity filter model; and a digital image difference metric. Each model used a Minkowski distance metric (generalized vector magnitude) to summate absolute differences between the background and object plus background images. For each model, this summation was implemented with three different exponents: 2, 4 and infinity. In addition, each combination of model and summation exponent was implemented with and without a simple contrast gain factor. The model outputs were compared to measures of object detectability obtained from 19 observers. Among the models without the contrast gain factor, the multiple channel model with a summation exponent of 4 performed best, predicting the pattern of observer d's with an RMS error of 2.3 dB. The contrast gain factor improved the predictions of all three models for all three exponents. With the factor, the best exponent was 4 for all three models, and their prediction errors were near 1 dB. These results demonstrate that image discrimination models can predict the relative detectability of objects in natural scenes.

A Case Study on a Combination NDVI Forecasting Model Based on the Entropy Weight Method

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

Huang, Shengzhi; Ming, Bo; Huang, Qiang

It is critically meaningful to accurately predict NDVI (Normalized Difference Vegetation Index), which helps guide regional ecological remediation and environmental managements. In this study, a combination forecasting model (CFM) was proposed to improve the performance of NDVI predictions in the Yellow River Basin (YRB) based on three individual forecasting models, i.e., the Multiple Linear Regression (MLR), Artificial Neural Network (ANN), and Support Vector Machine (SVM) models. The entropy weight method was employed to determine the weight coefficient for each individual model depending on its predictive performance. Results showed that: (1) ANN exhibits the highest fitting capability among the four orecastingmore » models in the calibration period, whilst its generalization ability becomes weak in the validation period; MLR has a poor performance in both calibration and validation periods; the predicted results of CFM in the calibration period have the highest stability; (2) CFM generally outperforms all individual models in the validation period, and can improve the reliability and stability of predicted results through combining the strengths while reducing the weaknesses of individual models; (3) the performances of all forecasting models are better in dense vegetation areas than in sparse vegetation areas.« less

Temporal and geographical external validation study and extension of the Mayo Clinic prediction model to predict eGFR in the younger population of Swiss ADPKD patients.

PubMed

Girardat-Rotar, Laura; Braun, Julia; Puhan, Milo A; Abraham, Alison G; Serra, Andreas L

2017-07-17

Prediction models in autosomal dominant polycystic kidney disease (ADPKD) are useful in clinical settings to identify patients with greater risk of a rapid disease progression in whom a treatment may have more benefits than harms. Mayo Clinic investigators developed a risk prediction tool for ADPKD patients using a single kidney value. Our aim was to perform an independent geographical and temporal external validation as well as evaluate the potential for improving the predictive performance by including additional information on total kidney volume. We used data from the on-going Swiss ADPKD study from 2006 to 2016. The main analysis included a sample size of 214 patients with Typical ADPKD (Class 1). We evaluated the Mayo Clinic model performance calibration and discrimination in our external sample and assessed whether predictive performance could be improved through the addition of subsequent kidney volume measurements beyond the baseline assessment. The calibration of both versions of the Mayo Clinic prediction model using continuous Height adjusted total kidney volume (HtTKV) and using risk subclasses was good, with R 2 of 78% and 70%, respectively. Accuracy was also good with 91.5% and 88.7% of the predicted within 30% of the observed, respectively. Additional information regarding kidney volume did not substantially improve the model performance. The Mayo Clinic prediction models are generalizable to other clinical settings and provide an accurate tool based on available predictors to identify patients at high risk for rapid disease progression.

Opportunities of probabilistic flood loss models

NASA Astrophysics Data System (ADS)

Schröter, Kai; Kreibich, Heidi; Lüdtke, Stefan; Vogel, Kristin; Merz, Bruno

2016-04-01

Oftentimes, traditional uni-variate damage models as for instance depth-damage curves fail to reproduce the variability of observed flood damage. However, reliable flood damage models are a prerequisite for the practical usefulness of the model results. Innovative multi-variate probabilistic modelling approaches are promising to capture and quantify the uncertainty involved and thus to improve the basis for decision making. In this study we compare the predictive capability of two probabilistic modelling approaches, namely Bagging Decision Trees and Bayesian Networks and traditional stage damage functions. For model evaluation we use empirical damage data which are available from computer aided telephone interviews that were respectively compiled after the floods in 2002, 2005, 2006 and 2013 in the Elbe and Danube catchments in Germany. We carry out a split sample test by sub-setting the damage records. One sub-set is used to derive the models and the remaining records are used to evaluate the predictive performance of the model. Further we stratify the sample according to catchments which allows studying model performance in a spatial transfer context. Flood damage estimation is carried out on the scale of the individual buildings in terms of relative damage. The predictive performance of the models is assessed in terms of systematic deviations (mean bias), precision (mean absolute error) as well as in terms of sharpness of the predictions the reliability which is represented by the proportion of the number of observations that fall within the 95-quantile and 5-quantile predictive interval. The comparison of the uni-variable Stage damage function and the multivariable model approach emphasises the importance to quantify predictive uncertainty. With each explanatory variable, the multi-variable model reveals an additional source of uncertainty. However, the predictive performance in terms of precision (mbe), accuracy (mae) and reliability (HR) is clearly improved in comparison to uni-variable Stage damage function. Overall, Probabilistic models provide quantitative information about prediction uncertainty which is crucial to assess the reliability of model predictions and improves the usefulness of model results.

A Bayesian Performance Prediction Model for Mathematics Education: A Prototypical Approach for Effective Group Composition

ERIC Educational Resources Information Center

Bekele, Rahel; McPherson, Maggie

2011-01-01

This research work presents a Bayesian Performance Prediction Model that was created in order to determine the strength of personality traits in predicting the level of mathematics performance of high school students in Addis Ababa. It is an automated tool that can be used to collect information from students for the purpose of effective group…

Do repeated assessments of performance status improve predictions for risk of death among patients with cancer? A population-based cohort study.

PubMed

Su, Jiandong; Barbera, Lisa; Sutradhar, Rinku

2015-06-01

Prior work has utilized longitudinal information on performance status to demonstrate its association with risk of death among cancer patients; however, no study has assessed whether such longitudinal information improves the predictions for risk of death. To examine whether the use of repeated performance status assessments improve predictions for risk of death compared to using only performance status assessment at the time of cancer diagnosis. This was a population-based longitudinal study of adult outpatients who had a cancer diagnosis and had at least one assessment of performance status. To account for each patient's changing performance status over time, we implemented a Cox model with a time-varying covariate for performance status. This model was compared to a Cox model using only a time-fixed (baseline) covariate for performance status. The regression coefficients of each model were derived based on a randomly selected 60% of patients, and then, the predictive ability of each model was assessed via concordance probabilities when applied to the remaining 40% of patients. Our study consisted of 15,487 cancer patients with over 53,000 performance status assessments. The utilization of repeated performance status assessments improved predictions for risk of death compared to using only the performance status assessment taken at diagnosis. When studying the hazard of death among patients with cancer, if available, researchers should incorporate changing information on performance status scores, instead of simply baseline information on performance status. © The Author(s) 2015.

Analysis of high vacuum systems using SINDA'85

NASA Technical Reports Server (NTRS)

Spivey, R. A.; Clanton, S. E.; Moore, J. D.

1993-01-01

The theory, algorithms, and test data correlation analysis of a math model developed to predict performance of the Space Station Freedom Vacuum Exhaust System are presented. The theory used to predict the flow characteristics of viscous, transition, and molecular flow is presented in detail. Development of user subroutines which predict the flow characteristics in conjunction with the SINDA'85/FLUINT analysis software are discussed. The resistance-capacitance network approach with application to vacuum system analysis is demonstrated and results from the model are correlated with test data. The model was developed to predict the performance of the Space Station Freedom Vacuum Exhaust System. However, the unique use of the user subroutines developed in this model and written into the SINDA'85/FLUINT thermal analysis model provides a powerful tool that can be used to predict the transient performance of vacuum systems and gas flow in tubes of virtually any geometry. This can be accomplished using a resistance-capacitance (R-C) method very similar to the methods used to perform thermal analyses.

A review of statistical updating methods for clinical prediction models.

PubMed

Su, Ting-Li; Jaki, Thomas; Hickey, Graeme L; Buchan, Iain; Sperrin, Matthew

2018-01-01

A clinical prediction model is a tool for predicting healthcare outcomes, usually within a specific population and context. A common approach is to develop a new clinical prediction model for each population and context; however, this wastes potentially useful historical information. A better approach is to update or incorporate the existing clinical prediction models already developed for use in similar contexts or populations. In addition, clinical prediction models commonly become miscalibrated over time, and need replacing or updating. In this article, we review a range of approaches for re-using and updating clinical prediction models; these fall in into three main categories: simple coefficient updating, combining multiple previous clinical prediction models in a meta-model and dynamic updating of models. We evaluated the performance (discrimination and calibration) of the different strategies using data on mortality following cardiac surgery in the United Kingdom: We found that no single strategy performed sufficiently well to be used to the exclusion of the others. In conclusion, useful tools exist for updating existing clinical prediction models to a new population or context, and these should be implemented rather than developing a new clinical prediction model from scratch, using a breadth of complementary statistical methods.

Personalized Modeling for Prediction with Decision-Path Models

PubMed Central

Visweswaran, Shyam; Ferreira, Antonio; Ribeiro, Guilherme A.; Oliveira, Alexandre C.; Cooper, Gregory F.

2015-01-01

Deriving predictive models in medicine typically relies on a population approach where a single model is developed from a dataset of individuals. In this paper we describe and evaluate a personalized approach in which we construct a new type of decision tree model called decision-path model that takes advantage of the particular features of a given person of interest. We introduce three personalized methods that derive personalized decision-path models. We compared the performance of these methods to that of Classification And Regression Tree (CART) that is a population decision tree to predict seven different outcomes in five medical datasets. Two of the three personalized methods performed statistically significantly better on area under the ROC curve (AUC) and Brier skill score compared to CART. The personalized approach of learning decision path models is a new approach for predictive modeling that can perform better than a population approach. PMID:26098570

Final Technical Report: Increasing Prediction Accuracy.

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

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

2015-12-01

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

A comprehensive mechanistic model for upward two-phase flow in wellbores

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

Sylvester, N.D.; Sarica, C.; Shoham, O.

1994-05-01

A comprehensive model is formulated to predict the flow behavior for upward two-phase flow. This model is composed of a model for flow-pattern prediction and a set of independent mechanistic models for predicting such flow characteristics as holdup and pressure drop in bubble, slug, and annular flow. The comprehensive model is evaluated by using a well data bank made up of 1,712 well cases covering a wide variety of field data. Model performance is also compared with six commonly used empirical correlations and the Hasan-Kabir mechanistic model. Overall model performance is in good agreement with the data. In comparison withmore » other methods, the comprehensive model performed the best.« less

Modeling and Prediction of Solvent Effect on Human Skin Permeability using Support Vector Regression and Random Forest.

PubMed

Baba, Hiromi; Takahara, Jun-ichi; Yamashita, Fumiyoshi; Hashida, Mitsuru

2015-11-01

The solvent effect on skin permeability is important for assessing the effectiveness and toxicological risk of new dermatological formulations in pharmaceuticals and cosmetics development. The solvent effect occurs by diverse mechanisms, which could be elucidated by efficient and reliable prediction models. However, such prediction models have been hampered by the small variety of permeants and mixture components archived in databases and by low predictive performance. Here, we propose a solution to both problems. We first compiled a novel large database of 412 samples from 261 structurally diverse permeants and 31 solvents reported in the literature. The data were carefully screened to ensure their collection under consistent experimental conditions. To construct a high-performance predictive model, we then applied support vector regression (SVR) and random forest (RF) with greedy stepwise descriptor selection to our database. The models were internally and externally validated. The SVR achieved higher performance statistics than RF. The (externally validated) determination coefficient, root mean square error, and mean absolute error of SVR were 0.899, 0.351, and 0.268, respectively. Moreover, because all descriptors are fully computational, our method can predict as-yet unsynthesized compounds. Our high-performance prediction model offers an attractive alternative to permeability experiments for pharmaceutical and cosmetic candidate screening and optimizing skin-permeable topical formulations.

Genomic models with genotype × environment interaction for predicting hybrid performance: an application in maize hybrids.

PubMed

Acosta-Pech, Rocío; Crossa, José; de Los Campos, Gustavo; Teyssèdre, Simon; Claustres, Bruno; Pérez-Elizalde, Sergio; Pérez-Rodríguez, Paulino

2017-07-01

A new genomic model that incorporates genotype × environment interaction gave increased prediction accuracy of untested hybrid response for traits such as percent starch content, percent dry matter content and silage yield of maize hybrids. The prediction of hybrid performance (HP) is very important in agricultural breeding programs. In plant breeding, multi-environment trials play an important role in the selection of important traits, such as stability across environments, grain yield and pest resistance. Environmental conditions modulate gene expression causing genotype × environment interaction (G × E), such that the estimated genetic correlations of the performance of individual lines across environments summarize the joint action of genes and environmental conditions. This article proposes a genomic statistical model that incorporates G × E for general and specific combining ability for predicting the performance of hybrids in environments. The proposed model can also be applied to any other hybrid species with distinct parental pools. In this study, we evaluated the predictive ability of two HP prediction models using a cross-validation approach applied in extensive maize hybrid data, comprising 2724 hybrids derived from 507 dent lines and 24 flint lines, which were evaluated for three traits in 58 environments over 12 years; analyses were performed for each year. On average, genomic models that include the interaction of general and specific combining ability with environments have greater predictive ability than genomic models without interaction with environments (ranging from 12 to 22%, depending on the trait). We concluded that including G × E in the prediction of untested maize hybrids increases the accuracy of genomic models.

A predictive pilot model for STOL aircraft landing

NASA Technical Reports Server (NTRS)

Kleinman, D. L.; Killingsworth, W. R.

1974-01-01

An optimal control approach has been used to model pilot performance during STOL flare and landing. The model is used to predict pilot landing performance for three STOL configurations, each having a different level of automatic control augmentation. Model predictions are compared with flight simulator data. It is concluded that the model can be effective design tool for studying analytically the effects of display modifications, different stability augmentation systems, and proposed changes in the landing area geometry.

Stata Modules for Calculating Novel Predictive Performance Indices for Logistic Models

PubMed Central

Barkhordari, Mahnaz; Padyab, Mojgan; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-01-01

Background Prediction is a fundamental part of prevention of cardiovascular diseases (CVD). The development of prediction algorithms based on the multivariate regression models loomed several decades ago. Parallel with predictive models development, biomarker researches emerged in an impressively great scale. The key question is how best to assess and quantify the improvement in risk prediction offered by new biomarkers or more basically how to assess the performance of a risk prediction model. Discrimination, calibration, and added predictive value have been recently suggested to be used while comparing the predictive performances of the predictive models’ with and without novel biomarkers. Objectives Lack of user-friendly statistical software has restricted implementation of novel model assessment methods while examining novel biomarkers. We intended, thus, to develop a user-friendly software that could be used by researchers with few programming skills. Materials and Methods We have written a Stata command that is intended to help researchers obtain cut point-free and cut point-based net reclassification improvement index and (NRI) and relative and absolute Integrated discriminatory improvement index (IDI) for logistic-based regression analyses.We applied the commands to a real data on women participating the Tehran lipid and glucose study (TLGS) to examine if information of a family history of premature CVD, waist circumference, and fasting plasma glucose can improve predictive performance of the Framingham’s “general CVD risk” algorithm. Results The command is addpred for logistic regression models. Conclusions The Stata package provided herein can encourage the use of novel methods in examining predictive capacity of ever-emerging plethora of novel biomarkers. PMID:27279830

Dual Pathways from Reactive Aggression to Depressive Symptoms in Children: Further Examination of the Failure Model.

PubMed

Evans, Spencer C; Fite, Paula J

2018-04-13

The failure model posits that peer rejection and poor academic performance are dual pathways in the association between early aggressive behavior and subsequent depressive symptoms. We examined this model using an accelerated longitudinal design while also incorporating proactive and reactive aggression and gender moderation. Children in 1st, 3rd, and 5th grades (n = 912; ages 6-12; 48% female) were rated three times annually by their primary teachers on measures of proactive and reactive aggression, peer rejection, academic performance, and depressive symptoms. Using Bayesian cross-classified estimation to account for nested and planned-missing data, path models were estimated to examine whether early reactive aggression predicted subsequent peer rejection and academic performance, and whether these, in turn, predicted subsequent depressive symptoms. From 1st to 3rd grade, reactive aggression predicted peer rejection (not academic performance), proactive aggression predicted academic performance (not peer rejection), and academic performance and peer rejection both predicted depressive symptoms. From 3rd to 5th grade, however, neither peer rejection nor academic performance predicted subsequent depressive symptoms. Results were not moderated by gender. Overall, these findings provide mixed and limited support for the failure model among school-age children. Early reactive aggression may be a key risk factor for social problems, whereas proactive aggression may be linked to improved academic functioning. The "dual pathways" of peer rejection and academic performance may operate during early but not later elementary school. Limitations and implications are discussed.

Construction of a model for predicting creatinine clearance in Japanese patients treated with Cisplatin therapy.

PubMed

Yajima, Airi; Uesawa, Yoshihiro; Ogawa, Chiaki; Yatabe, Megumi; Kondo, Naoki; Saito, Shinichiro; Suzuki, Yoshihiko; Atsuda, Kouichiro; Kagaya, Hajime

2015-05-01

There exist various useful predictive models, such as the Cockcroft-Gault model, for estimating creatinine clearance (CLcr). However, the prediction of renal function is difficult in patients with cancer treated with cisplatin. Therefore, we attempted to construct a new model for predicting CLcr in such patients. Japanese patients with head and neck cancer who had received cisplatin-based chemotherapy were used as subjects. A multiple regression equation was constructed as a model for predicting CLcr values based on background and laboratory data. A model for predicting CLcr, which included body surface area, serum creatinine and albumin, was constructed. The model exhibited good performance prior to cisplatin therapy. In addition, it performed better than previously reported models after cisplatin therapy. The predictive model constructed in the present study displayed excellent potential and was useful for estimating the renal function of patients treated with cisplatin therapy. Copyright© 2015 International Institute of Anticancer Research (Dr. John G. Delinassios), All rights reserved.

Long-term particulate matter modeling for health effects studies in California - Part 1: Model performance on temporal and spatial variations

NASA Astrophysics Data System (ADS)

Hu, J.; Zhang, H.; Ying, Q.; Chen, S.-H.; Vandenberghe, F.; Kleeman, M. J.

2014-08-01

For the first time, a decadal (9 years from 2000 to 2008) air quality model simulation with 4 km horizontal resolution and daily time resolution has been conducted in California to provide air quality data for health effects studies. Model predictions are compared to measurements to evaluate the accuracy of the simulation with an emphasis on spatial and temporal variations that could be used in epidemiology studies. Better model performance is found at longer averaging times, suggesting that model results with averaging times ≥ 1 month should be the first to be considered in epidemiological studies. The UCD/CIT model predicts spatial and temporal variations in the concentrations of O3, PM2.5, EC, OC, nitrate, and ammonium that meet standard modeling performance criteria when compared to monthly-averaged measurements. Predicted sulfate concentrations do not meet target performance metrics due to missing sulfur sources in the emissions. Predicted seasonal and annual variations of PM2.5, EC, OC, nitrate, and ammonium have mean fractional biases that meet the model performance criteria in 95%, 100%, 71%, 73%, and 92% of the simulated months, respectively. The base dataset provides an improvement for predicted population exposure to PM concentrations in California compared to exposures estimated by central site monitors operated one day out of every 3 days at a few urban locations. Uncertainties in the model predictions arise from several issues. Incomplete understanding of secondary organic aerosol formation mechanisms leads to OC bias in the model results in summertime but does not affect OC predictions in winter when concentrations are typically highest. The CO and NO (species dominated by mobile emissions) results reveal temporal and spatial uncertainties associated with the mobile emissions generated by the EMFAC 2007 model. The WRF model tends to over-predict wind speed during stagnation events, leading to under-predictions of high PM concentrations, usually in winter months. The WRF model also generally under-predicts relative humidity, resulting in less particulate nitrate formation especially during winter months. These issues will be improved in future studies. All model results included in the current manuscript can be downloaded free of charge at http://faculty.engineering.ucdavis.edu/kleeman/.

Benchmarking hydrological model predictive capability for UK River flows and flood peaks.

NASA Astrophysics Data System (ADS)

Lane, Rosanna; Coxon, Gemma; Freer, Jim; Wagener, Thorsten

2017-04-01

Data and hydrological models are now available for national hydrological analyses. However, hydrological model performance varies between catchments, and lumped, conceptual models are not able to produce adequate simulations everywhere. This study aims to benchmark hydrological model performance for catchments across the United Kingdom within an uncertainty analysis framework. We have applied four hydrological models from the FUSE framework to 1128 catchments across the UK. These models are all lumped models and run at a daily timestep, but differ in the model structural architecture and process parameterisations, therefore producing different but equally plausible simulations. We apply FUSE over a 20 year period from 1988-2008, within a GLUE Monte Carlo uncertainty analyses framework. Model performance was evaluated for each catchment, model structure and parameter set using standard performance metrics. These were calculated both for the whole time series and to assess seasonal differences in model performance. The GLUE uncertainty analysis framework was then applied to produce simulated 5th and 95th percentile uncertainty bounds for the daily flow time-series and additionally the annual maximum prediction bounds for each catchment. The results show that the model performance varies significantly in space and time depending on catchment characteristics including climate, geology and human impact. We identify regions where models are systematically failing to produce good results, and present reasons why this could be the case. We also identify regions or catchment characteristics where one model performs better than others, and have explored what structural component or parameterisation enables certain models to produce better simulations in these catchments. Model predictive capability was assessed for each catchment, through looking at the ability of the models to produce discharge prediction bounds which successfully bound the observed discharge. These results improve our understanding of the predictive capability of simple conceptual hydrological models across the UK and help us to identify where further effort is needed to develop modelling approaches to better represent different catchment and climate typologies.

Long short-term memory neural network for air pollutant concentration predictions: Method development and evaluation.

PubMed

Li, Xiang; Peng, Ling; Yao, Xiaojing; Cui, Shaolong; Hu, Yuan; You, Chengzeng; Chi, Tianhe

2017-12-01

Air pollutant concentration forecasting is an effective method of protecting public health by providing an early warning against harmful air pollutants. However, existing methods of air pollutant concentration prediction fail to effectively model long-term dependencies, and most neglect spatial correlations. In this paper, a novel long short-term memory neural network extended (LSTME) model that inherently considers spatiotemporal correlations is proposed for air pollutant concentration prediction. Long short-term memory (LSTM) layers were used to automatically extract inherent useful features from historical air pollutant data, and auxiliary data, including meteorological data and time stamp data, were merged into the proposed model to enhance the performance. Hourly PM 2.5 (particulate matter with an aerodynamic diameter less than or equal to 2.5 μm) concentration data collected at 12 air quality monitoring stations in Beijing City from Jan/01/2014 to May/28/2016 were used to validate the effectiveness of the proposed LSTME model. Experiments were performed using the spatiotemporal deep learning (STDL) model, the time delay neural network (TDNN) model, the autoregressive moving average (ARMA) model, the support vector regression (SVR) model, and the traditional LSTM NN model, and a comparison of the results demonstrated that the LSTME model is superior to the other statistics-based models. Additionally, the use of auxiliary data improved model performance. For the one-hour prediction tasks, the proposed model performed well and exhibited a mean absolute percentage error (MAPE) of 11.93%. In addition, we conducted multiscale predictions over different time spans and achieved satisfactory performance, even for 13-24 h prediction tasks (MAPE = 31.47%). Copyright © 2017 Elsevier Ltd. All rights reserved.

Paradigm of pretest risk stratification before coronary computed tomography.

PubMed

Jensen, Jesper Møller; Ovrehus, Kristian A; Nielsen, Lene H; Jensen, Jesper K; Larsen, Henrik M; Nørgaard, Bjarne L

2009-01-01

The optimal method of determining the pretest risk of coronary artery disease as a patient selection tool before coronary multidetector computed tomography (MDCT) is unknown. We investigated the ability of 3 different clinical risk scores to predict the outcome of coronary MDCT. This was a retrospective study of 551 patients consecutively referred for coronary MDCT on a suspicion of coronary artery disease. Diamond-Forrester, Duke, and Morise risk models were used to predict coronary artery stenosis (>50%) as assessed by coronary MDCT. The models were compared by receiver operating characteristic analysis. The distribution of low-, intermediate-, and high-risk persons, respectively, was established and compared for each of the 3 risk models. Overall, all risk prediction models performed equally well. However, the Duke risk model classified the low-risk patients more correctly than did the other models (P < 0.01). In patients without coronary artery calcification (CAC), the predictive value of the Duke risk model was superior to the other risk models (P < 0.05). Currently available risk prediction models seem to perform better in patients without CAC. Between the risk prediction models, there was a significant discrepancy in the distribution of patients at low, intermediate, or high risk (P < 0.01). The 3 risk prediction models perform equally well, although the Duke risk score may have advantages in subsets of patients. The choice of risk prediction model affects the referral pattern to MDCT. Copyright (c) 2009 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.

Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis.

PubMed

Xie, Yuanchang; Lord, Dominique; Zhang, Yunlong

2007-09-01

Statistical models have frequently been used in highway safety studies. They can be utilized for various purposes, including establishing relationships between variables, screening covariates and predicting values. Generalized linear models (GLM) and hierarchical Bayes models (HBM) have been the most common types of model favored by transportation safety analysts. Over the last few years, researchers have proposed the back-propagation neural network (BPNN) model for modeling the phenomenon under study. Compared to GLMs and HBMs, BPNNs have received much less attention in highway safety modeling. The reasons are attributed to the complexity for estimating this kind of model as well as the problem related to "over-fitting" the data. To circumvent the latter problem, some statisticians have proposed the use of Bayesian neural network (BNN) models. These models have been shown to perform better than BPNN models while at the same time reducing the difficulty associated with over-fitting the data. The objective of this study is to evaluate the application of BNN models for predicting motor vehicle crashes. To accomplish this objective, a series of models was estimated using data collected on rural frontage roads in Texas. Three types of models were compared: BPNN, BNN and the negative binomial (NB) regression models. The results of this study show that in general both types of neural network models perform better than the NB regression model in terms of data prediction. Although the BPNN model can occasionally provide better or approximately equivalent prediction performance compared to the BNN model, in most cases its prediction performance is worse than the BNN model. In addition, the data fitting performance of the BPNN model is consistently worse than the BNN model, which suggests that the BNN model has better generalization abilities than the BPNN model and can effectively alleviate the over-fitting problem without significantly compromising the nonlinear approximation ability. The results also show that BNNs could be used for other useful analyses in highway safety, including the development of accident modification factors and for improving the prediction capabilities for evaluating different highway design alternatives.

A new framework to enhance the interpretation of external validation studies of clinical prediction models.

PubMed

Debray, Thomas P A; Vergouwe, Yvonne; Koffijberg, Hendrik; Nieboer, Daan; Steyerberg, Ewout W; Moons, Karel G M

2015-03-01

It is widely acknowledged that the performance of diagnostic and prognostic prediction models should be assessed in external validation studies with independent data from "different but related" samples as compared with that of the development sample. We developed a framework of methodological steps and statistical methods for analyzing and enhancing the interpretation of results from external validation studies of prediction models. We propose to quantify the degree of relatedness between development and validation samples on a scale ranging from reproducibility to transportability by evaluating their corresponding case-mix differences. We subsequently assess the models' performance in the validation sample and interpret the performance in view of the case-mix differences. Finally, we may adjust the model to the validation setting. We illustrate this three-step framework with a prediction model for diagnosing deep venous thrombosis using three validation samples with varying case mix. While one external validation sample merely assessed the model's reproducibility, two other samples rather assessed model transportability. The performance in all validation samples was adequate, and the model did not require extensive updating to correct for miscalibration or poor fit to the validation settings. The proposed framework enhances the interpretation of findings at external validation of prediction models. Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.

Thermal and structural analysis of the GOES scan mirror's on orbit performance

NASA Technical Reports Server (NTRS)

Zurmehly, G. E.; Hookman, R. A.

1991-01-01

The on-orbit performance of the GOES satellite's scan mirror has been predicted by means of thermal, structural, and optical models. A simpler-than-conventional thermal model was used to reduce the time required to obtain orbital predictions, and the structural model was used to predict on-earth gravity sag and on-orbit distortions. The transfer of data from the thermal model to the structural model was automated for a given set of thermal nodes and structural grids.

Predicting survival across chronic interstitial lung disease: the ILD-GAP model.

PubMed

Ryerson, Christopher J; Vittinghoff, Eric; Ley, Brett; Lee, Joyce S; Mooney, Joshua J; Jones, Kirk D; Elicker, Brett M; Wolters, Paul J; Koth, Laura L; King, Talmadge E; Collard, Harold R

2014-04-01

Risk prediction is challenging in chronic interstitial lung disease (ILD) because of heterogeneity in disease-specific and patient-specific variables. Our objective was to determine whether mortality is accurately predicted in patients with chronic ILD using the GAP model, a clinical prediction model based on sex, age, and lung physiology, that was previously validated in patients with idiopathic pulmonary fibrosis. Patients with idiopathic pulmonary fibrosis (n=307), chronic hypersensitivity pneumonitis (n=206), connective tissue disease-associated ILD (n=281), idiopathic nonspecific interstitial pneumonia (n=45), or unclassifiable ILD (n=173) were selected from an ongoing database (N=1,012). Performance of the previously validated GAP model was compared with novel prediction models in each ILD subtype and the combined cohort. Patients with follow-up pulmonary function data were used for longitudinal model validation. The GAP model had good performance in all ILD subtypes (c-index, 74.6 in the combined cohort), which was maintained at all stages of disease severity and during follow-up evaluation. The GAP model had similar performance compared with alternative prediction models. A modified ILD-GAP Index was developed for application across all ILD subtypes to provide disease-specific survival estimates using a single risk prediction model. This was done by adding a disease subtype variable that accounted for better adjusted survival in connective tissue disease-associated ILD, chronic hypersensitivity pneumonitis, and idiopathic nonspecific interstitial pneumonia. The GAP model accurately predicts risk of death in chronic ILD. The ILD-GAP model accurately predicts mortality in major chronic ILD subtypes and at all stages of disease.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Som, Sukhamoy; Stoughton, John W.; Mielke, Roland R.

1990-01-01

Performance modeling and performance enhancement for periodic execution of large-grain, decision-free algorithms in data flow architectures are discussed. Applications include real-time implementation of control and signal processing algorithms where performance is required to be highly predictable. The mapping of algorithms onto the specified class of data flow architectures is realized by a marked graph model called algorithm to architecture mapping model (ATAMM). Performance measures and bounds are established. Algorithm transformation techniques are identified for performance enhancement and reduction of resource (computing element) requirements. A systematic design procedure is described for generating operating conditions for predictable performance both with and without resource constraints. An ATAMM simulator is used to test and validate the performance prediction by the design procedure. Experiments on a three resource testbed provide verification of the ATAMM model and the design procedure.

Aqua/Aura Updated Inclination Adjust Maneuver Performance Prediction Model

NASA Technical Reports Server (NTRS)

Boone, Spencer

2017-01-01

This presentation will discuss the updated Inclination Adjust Maneuver (IAM) performance prediction model that was developed for Aqua and Aura following the 2017 IAM series. This updated model uses statistical regression methods to identify potential long-term trends in maneuver parameters, yielding improved predictions when re-planning past maneuvers. The presentation has been reviewed and approved by Eric Moyer, ESMO Deputy Project Manager.

Varying execution discipline to increase performance

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

Campbell, P.L.; Maccabe, A.B.

1993-12-22

This research investigates the relationship between execution discipline and performance. The hypothesis has two parts: 1. Different execution disciplines exhibit different performance for different computations, and 2. These differences can be effectively predicted by heuristics. A machine model is developed that can vary its execution discipline. That is, the model can execute a given program using either the control-driven, data-driven or demand-driven execution discipline. This model is referred to as a ``variable-execution-discipline`` machine. The instruction set for the model is the Program Dependence Web (PDW). The first part of the hypothesis will be tested by simulating the execution of themore » machine model on a suite of computations, based on the Livermore Fortran Kernel (LFK) Test (a.k.a. the Livermore Loops), using all three execution disciplines. Heuristics are developed to predict relative performance. These heuristics predict (a) the execution time under each discipline for one iteration of each loop and (b) the number of iterations taken by that loop; then the heuristics use those predictions to develop a prediction for the execution of the entire loop. Similar calculations are performed for branch statements. The second part of the hypothesis will be tested by comparing the results of the simulated execution with the predictions produced by the heuristics. If the hypothesis is supported, then the door is open for the development of machines that can vary execution discipline to increase performance.« less

Improving Computational Efficiency of Prediction in Model-Based Prognostics Using the Unscented Transform

NASA Technical Reports Server (NTRS)

Daigle, Matthew John; Goebel, Kai Frank

2010-01-01

Model-based prognostics captures system knowledge in the form of physics-based models of components, and how they fail, in order to obtain accurate predictions of end of life (EOL). EOL is predicted based on the estimated current state distribution of a component and expected profiles of future usage. In general, this requires simulations of the component using the underlying models. In this paper, we develop a simulation-based prediction methodology that achieves computational efficiency by performing only the minimal number of simulations needed in order to accurately approximate the mean and variance of the complete EOL distribution. This is performed through the use of the unscented transform, which predicts the means and covariances of a distribution passed through a nonlinear transformation. In this case, the EOL simulation acts as that nonlinear transformation. In this paper, we review the unscented transform, and describe how this concept is applied to efficient EOL prediction. As a case study, we develop a physics-based model of a solenoid valve, and perform simulation experiments to demonstrate improved computational efficiency without sacrificing prediction accuracy.

Personalized long-term prediction of cognitive function: Using sequential assessments to improve model performance.

PubMed

Chi, Chih-Lin; Zeng, Wenjun; Oh, Wonsuk; Borson, Soo; Lenskaia, Tatiana; Shen, Xinpeng; Tonellato, Peter J

2017-12-01

Prediction of onset and progression of cognitive decline and dementia is important both for understanding the underlying disease processes and for planning health care for populations at risk. Predictors identified in research studies are typically accessed at one point in time. In this manuscript, we argue that an accurate model for predicting cognitive status over relatively long periods requires inclusion of time-varying components that are sequentially assessed at multiple time points (e.g., in multiple follow-up visits). We developed a pilot model to test the feasibility of using either estimated or observed risk factors to predict cognitive status. We developed two models, the first using a sequential estimation of risk factors originally obtained from 8 years prior, then improved by optimization. This model can predict how cognition will change over relatively long time periods. The second model uses observed rather than estimated time-varying risk factors and, as expected, results in better prediction. This model can predict when newly observed data are acquired in a follow-up visit. Performances of both models that are evaluated in10-fold cross-validation and various patient subgroups show supporting evidence for these pilot models. Each model consists of multiple base prediction units (BPUs), which were trained using the same set of data. The difference in usage and function between the two models is the source of input data: either estimated or observed data. In the next step of model refinement, we plan to integrate the two types of data together to flexibly predict dementia status and changes over time, when some time-varying predictors are measured only once and others are measured repeatedly. Computationally, both data provide upper and lower bounds for predictive performance. Copyright © 2017 Elsevier Inc. All rights reserved.

A systematic review of breast cancer incidence risk prediction models with meta-analysis of their performance.

PubMed

Meads, Catherine; Ahmed, Ikhlaaq; Riley, Richard D

2012-04-01

A risk prediction model is a statistical tool for estimating the probability that a currently healthy individual with specific risk factors will develop a condition in the future such as breast cancer. Reliably accurate prediction models can inform future disease burdens, health policies and individual decisions. Breast cancer prediction models containing modifiable risk factors, such as alcohol consumption, BMI or weight, condom use, exogenous hormone use and physical activity, are of particular interest to women who might be considering how to reduce their risk of breast cancer and clinicians developing health policies to reduce population incidence rates. We performed a systematic review to identify and evaluate the performance of prediction models for breast cancer that contain modifiable factors. A protocol was developed and a sensitive search in databases including MEDLINE and EMBASE was conducted in June 2010. Extensive use was made of reference lists. Included were any articles proposing or validating a breast cancer prediction model in a general female population, with no language restrictions. Duplicate data extraction and quality assessment were conducted. Results were summarised qualitatively, and where possible meta-analysis of model performance statistics was undertaken. The systematic review found 17 breast cancer models, each containing a different but often overlapping set of modifiable and other risk factors, combined with an estimated baseline risk that was also often different. Quality of reporting was generally poor, with characteristics of included participants and fitted model results often missing. Only four models received independent validation in external data, most notably the 'Gail 2' model with 12 validations. None of the models demonstrated consistently outstanding ability to accurately discriminate between those who did and those who did not develop breast cancer. For example, random-effects meta-analyses of the performance of the 'Gail 2' model showed the average C statistic was 0.63 (95% CI 0.59-0.67), and the expected/observed ratio of events varied considerably across studies (95% prediction interval for E/O ratio when the model was applied in practice was 0.75-1.19). There is a need for models with better predictive performance but, given the large amount of work already conducted, further improvement of existing models based on conventional risk factors is perhaps unlikely. Research to identify new risk factors with large additionally predictive ability is therefore needed, alongside clearer reporting and continual validation of new models as they develop.

Evaluation in Appalachian pasture systems of the 1996 (update 2000) National Research Council model for weaning cattle.

PubMed

Whetsell, M S; Rayburn, E B; Osborne, P I

2006-05-01

This study was conducted to evaluate the accuracy of the National Research Council's (2000) Nutrient Requirements of Beef Cattle computer model when used to predict calf performance during on-farm pasture or dry-lot weaning and backgrounding. Calf performance was measured on 22 farms in 2002 and 8 farms in 2003 that participated in West Virginia Beef Quality Assurance Sale marketing pools. Calves were weaned on pasture (25 farms) or dry-lot (5 farms) and fed supplemental hay, haylage, ground shell corn, soybean hulls, or a commercial concentrate. Concentrates were fed at a rate of 0.0 to 1.5% of BW. The National Research Council (2000) model was used to predict ADG of each group of calves observed on each farm. The model error was measured by calculating residuals (the difference between predicted ADG minus observed ADG). Predicted animal performance was determined using level 1 of the model. Results show that, when using normal on-farm pasture sampling and forage analysis methods, the model error for ADG is high and did not accurately predict the performance of steers or heifers fed high-forage pasture-based diets; the predicted ADG was lower (P < 0.05) than the observed ADG. The estimated intake of low-producing animals was similar to the expected DMI, but for the greater-producing animals it was not. The NRC (2000) beef model may more accurately predict on-farm animal performance in pastured situations if feed analysis values reflect the energy value of the feed, account for selective grazing, and relate empty BW and shrunk BW to NDF.

Assessment of Geometry and In-Flow Effects on Contra-Rotating Open Rotor Broadband Noise Predictions

NASA Technical Reports Server (NTRS)

Zawodny, Nikolas S.; Nark, Douglas M.; Boyd, D. Douglas, Jr.

2015-01-01

Application of previously formulated semi-analytical models for the prediction of broadband noise due to turbulent rotor wake interactions and rotor blade trailing edges is performed on the historical baseline F31/A31 contra-rotating open rotor configuration. Simplified two-dimensional blade element analysis is performed on cambered NACA 4-digit airfoil profiles, which are meant to serve as substitutes for the actual rotor blade sectional geometries. Rotor in-flow effects such as induced axial and tangential velocities are incorporated into the noise prediction models based on supporting computational fluid dynamics (CFD) results and simplified in-flow velocity models. Emphasis is placed on the development of simplified rotor in-flow models for the purpose of performing accurate noise predictions independent of CFD information. The broadband predictions are found to compare favorably with experimental acoustic results.

Comparison of RNA-seq and microarray-based models for clinical endpoint prediction.

PubMed

Zhang, Wenqian; Yu, Ying; Hertwig, Falk; Thierry-Mieg, Jean; Zhang, Wenwei; Thierry-Mieg, Danielle; Wang, Jian; Furlanello, Cesare; Devanarayan, Viswanath; Cheng, Jie; Deng, Youping; Hero, Barbara; Hong, Huixiao; Jia, Meiwen; Li, Li; Lin, Simon M; Nikolsky, Yuri; Oberthuer, André; Qing, Tao; Su, Zhenqiang; Volland, Ruth; Wang, Charles; Wang, May D; Ai, Junmei; Albanese, Davide; Asgharzadeh, Shahab; Avigad, Smadar; Bao, Wenjun; Bessarabova, Marina; Brilliant, Murray H; Brors, Benedikt; Chierici, Marco; Chu, Tzu-Ming; Zhang, Jibin; Grundy, Richard G; He, Min Max; Hebbring, Scott; Kaufman, Howard L; Lababidi, Samir; Lancashire, Lee J; Li, Yan; Lu, Xin X; Luo, Heng; Ma, Xiwen; Ning, Baitang; Noguera, Rosa; Peifer, Martin; Phan, John H; Roels, Frederik; Rosswog, Carolina; Shao, Susan; Shen, Jie; Theissen, Jessica; Tonini, Gian Paolo; Vandesompele, Jo; Wu, Po-Yen; Xiao, Wenzhong; Xu, Joshua; Xu, Weihong; Xuan, Jiekun; Yang, Yong; Ye, Zhan; Dong, Zirui; Zhang, Ke K; Yin, Ye; Zhao, Chen; Zheng, Yuanting; Wolfinger, Russell D; Shi, Tieliu; Malkas, Linda H; Berthold, Frank; Wang, Jun; Tong, Weida; Shi, Leming; Peng, Zhiyu; Fischer, Matthias

2015-06-25

Gene expression profiling is being widely applied in cancer research to identify biomarkers for clinical endpoint prediction. Since RNA-seq provides a powerful tool for transcriptome-based applications beyond the limitations of microarrays, we sought to systematically evaluate the performance of RNA-seq-based and microarray-based classifiers in this MAQC-III/SEQC study for clinical endpoint prediction using neuroblastoma as a model. We generate gene expression profiles from 498 primary neuroblastomas using both RNA-seq and 44 k microarrays. Characterization of the neuroblastoma transcriptome by RNA-seq reveals that more than 48,000 genes and 200,000 transcripts are being expressed in this malignancy. We also find that RNA-seq provides much more detailed information on specific transcript expression patterns in clinico-genetic neuroblastoma subgroups than microarrays. To systematically compare the power of RNA-seq and microarray-based models in predicting clinical endpoints, we divide the cohort randomly into training and validation sets and develop 360 predictive models on six clinical endpoints of varying predictability. Evaluation of factors potentially affecting model performances reveals that prediction accuracies are most strongly influenced by the nature of the clinical endpoint, whereas technological platforms (RNA-seq vs. microarrays), RNA-seq data analysis pipelines, and feature levels (gene vs. transcript vs. exon-junction level) do not significantly affect performances of the models. We demonstrate that RNA-seq outperforms microarrays in determining the transcriptomic characteristics of cancer, while RNA-seq and microarray-based models perform similarly in clinical endpoint prediction. Our findings may be valuable to guide future studies on the development of gene expression-based predictive models and their implementation in clinical practice.

Accounting for Slipping and Other False Negatives in Logistic Models of Student Learning

ERIC Educational Resources Information Center

MacLellan, Christopher J.; Liu, Ran; Koedinger, Kenneth R.

2015-01-01

Additive Factors Model (AFM) and Performance Factors Analysis (PFA) are two popular models of student learning that employ logistic regression to estimate parameters and predict performance. This is in contrast to Bayesian Knowledge Tracing (BKT) which uses a Hidden Markov Model formalism. While all three models tend to make similar predictions,…

Optimizing Blasting’s Air Overpressure Prediction Model using Swarm Intelligence

NASA Astrophysics Data System (ADS)

Nur Asmawisham Alel, Mohd; Ruben Anak Upom, Mark; Asnida Abdullah, Rini; Hazreek Zainal Abidin, Mohd

2018-04-01

Air overpressure (AOp) resulting from blasting can cause damage and nuisance to nearby civilians. Thus, it is important to be able to predict AOp accurately. In this study, 8 different Artificial Neural Network (ANN) were developed for the purpose of prediction of AOp. The ANN models were trained using different variants of Particle Swarm Optimization (PSO) algorithm. AOp predictions were also made using an empirical equation, as suggested by United States Bureau of Mines (USBM), to serve as a benchmark. In order to develop the models, 76 blasting operations in Hulu Langat were investigated. All the ANN models were found to outperform the USBM equation in three performance metrics; root mean square error (RMSE), mean absolute percentage error (MAPE) and coefficient of determination (R2). Using a performance ranking method, MSO-Rand-Mut was determined to be the best prediction model for AOp with a performance metric of RMSE=2.18, MAPE=1.73% and R2=0.97. The result shows that ANN models trained using PSO are capable of predicting AOp with great accuracy.

Predicting stillbirth in a low resource setting.

PubMed

Kayode, Gbenga A; Grobbee, Diederick E; Amoakoh-Coleman, Mary; Adeleke, Ibrahim Taiwo; Ansah, Evelyn; de Groot, Joris A H; Klipstein-Grobusch, Kerstin

2016-09-20

Stillbirth is a major contributor to perinatal mortality and it is particularly common in low- and middle-income countries, where annually about three million stillbirths occur in the third trimester. This study aims to develop a prediction model for early detection of pregnancies at high risk of stillbirth. This retrospective cohort study examined 6,573 pregnant women who delivered at Federal Medical Centre Bida, a tertiary level of healthcare in Nigeria from January 2010 to December 2013. Descriptive statistics were performed and missing data imputed. Multivariable logistic regression was applied to examine the associations between selected candidate predictors and stillbirth. Discrimination and calibration were used to assess the model's performance. The prediction model was validated internally and over-optimism was corrected. We developed a prediction model for stillbirth that comprised maternal comorbidity, place of residence, maternal occupation, parity, bleeding in pregnancy, and fetal presentation. As a secondary analysis, we extended the model by including fetal growth rate as a predictor, to examine how beneficial ultrasound parameters would be for the predictive performance of the model. After internal validation, both calibration and discriminative performance of both the basic and extended model were excellent (i.e. C-statistic basic model = 0.80 (95 % CI 0.78-0.83) and extended model = 0.82 (95 % CI 0.80-0.83)). We developed a simple but informative prediction model for early detection of pregnancies with a high risk of stillbirth for early intervention in a low resource setting. Future research should focus on external validation of the performance of this promising model.

Predicting adsorptive removal of chlorophenol from aqueous solution using artificial intelligence based modeling approaches.

PubMed

Singh, Kunwar P; Gupta, Shikha; Ojha, Priyanka; Rai, Premanjali

2013-04-01

The research aims to develop artificial intelligence (AI)-based model to predict the adsorptive removal of 2-chlorophenol (CP) in aqueous solution by coconut shell carbon (CSC) using four operational variables (pH of solution, adsorbate concentration, temperature, and contact time), and to investigate their effects on the adsorption process. Accordingly, based on a factorial design, 640 batch experiments were conducted. Nonlinearities in experimental data were checked using Brock-Dechert-Scheimkman (BDS) statistics. Five nonlinear models were constructed to predict the adsorptive removal of CP in aqueous solution by CSC using four variables as input. Performances of the constructed models were evaluated and compared using statistical criteria. BDS statistics revealed strong nonlinearity in experimental data. Performance of all the models constructed here was satisfactory. Radial basis function network (RBFN) and multilayer perceptron network (MLPN) models performed better than generalized regression neural network, support vector machines, and gene expression programming models. Sensitivity analysis revealed that the contact time had highest effect on adsorption followed by the solution pH, temperature, and CP concentration. The study concluded that all the models constructed here were capable of capturing the nonlinearity in data. A better generalization and predictive performance of RBFN and MLPN models suggested that these can be used to predict the adsorption of CP in aqueous solution using CSC.

Statistical Modeling and Prediction for Tourism Economy Using Dendritic Neural Network

PubMed Central

Yu, Ying; Wang, Yirui; Tang, Zheng

2017-01-01

With the impact of global internationalization, tourism economy has also been a rapid development. The increasing interest aroused by more advanced forecasting methods leads us to innovate forecasting methods. In this paper, the seasonal trend autoregressive integrated moving averages with dendritic neural network model (SA-D model) is proposed to perform the tourism demand forecasting. First, we use the seasonal trend autoregressive integrated moving averages model (SARIMA model) to exclude the long-term linear trend and then train the residual data by the dendritic neural network model and make a short-term prediction. As the result showed in this paper, the SA-D model can achieve considerably better predictive performances. In order to demonstrate the effectiveness of the SA-D model, we also use the data that other authors used in the other models and compare the results. It also proved that the SA-D model achieved good predictive performances in terms of the normalized mean square error, absolute percentage of error, and correlation coefficient. PMID:28246527

Statistical Modeling and Prediction for Tourism Economy Using Dendritic Neural Network.

PubMed

Yu, Ying; Wang, Yirui; Gao, Shangce; Tang, Zheng

2017-01-01

With the impact of global internationalization, tourism economy has also been a rapid development. The increasing interest aroused by more advanced forecasting methods leads us to innovate forecasting methods. In this paper, the seasonal trend autoregressive integrated moving averages with dendritic neural network model (SA-D model) is proposed to perform the tourism demand forecasting. First, we use the seasonal trend autoregressive integrated moving averages model (SARIMA model) to exclude the long-term linear trend and then train the residual data by the dendritic neural network model and make a short-term prediction. As the result showed in this paper, the SA-D model can achieve considerably better predictive performances. In order to demonstrate the effectiveness of the SA-D model, we also use the data that other authors used in the other models and compare the results. It also proved that the SA-D model achieved good predictive performances in terms of the normalized mean square error, absolute percentage of error, and correlation coefficient.

Bayesian Maximum Entropy Integration of Ozone Observations and Model Predictions: A National Application.

PubMed

Xu, Yadong; Serre, Marc L; Reyes, Jeanette; Vizuete, William

2016-04-19

To improve ozone exposure estimates for ambient concentrations at a national scale, we introduce our novel Regionalized Air Quality Model Performance (RAMP) approach to integrate chemical transport model (CTM) predictions with the available ozone observations using the Bayesian Maximum Entropy (BME) framework. The framework models the nonlinear and nonhomoscedastic relation between air pollution observations and CTM predictions and for the first time accounts for variability in CTM model performance. A validation analysis using only noncollocated data outside of a validation radius rv was performed and the R(2) between observations and re-estimated values for two daily metrics, the daily maximum 8-h average (DM8A) and the daily 24-h average (D24A) ozone concentrations, were obtained with the OBS scenario using ozone observations only in contrast with the RAMP and a Constant Air Quality Model Performance (CAMP) scenarios. We show that, by accounting for the spatial and temporal variability in model performance, our novel RAMP approach is able to extract more information in terms of R(2) increase percentage, with over 12 times for the DM8A and over 3.5 times for the D24A ozone concentrations, from CTM predictions than the CAMP approach assuming that model performance does not change across space and time.

A statistical model for predicting muscle performance

NASA Astrophysics Data System (ADS)

Byerly, Diane Leslie De Caix

The objective of these studies was to develop a capability for predicting muscle performance and fatigue to be utilized for both space- and ground-based applications. To develop this predictive model, healthy test subjects performed a defined, repetitive dynamic exercise to failure using a Lordex spinal machine. Throughout the exercise, surface electromyography (SEMG) data were collected from the erector spinae using a Mega Electronics ME3000 muscle tester and surface electrodes placed on both sides of the back muscle. These data were analyzed using a 5th order Autoregressive (AR) model and statistical regression analysis. It was determined that an AR derived parameter, the mean average magnitude of AR poles, significantly correlated with the maximum number of repetitions (designated Rmax) that a test subject was able to perform. Using the mean average magnitude of AR poles, a test subject's performance to failure could be predicted as early as the sixth repetition of the exercise. This predictive model has the potential to provide a basis for improving post-space flight recovery, monitoring muscle atrophy in astronauts and assessing the effectiveness of countermeasures, monitoring astronaut performance and fatigue during Extravehicular Activity (EVA) operations, providing pre-flight assessment of the ability of an EVA crewmember to perform a given task, improving the design of training protocols and simulations for strenuous International Space Station assembly EVA, and enabling EVA work task sequences to be planned enhancing astronaut performance and safety. Potential ground-based, medical applications of the predictive model include monitoring muscle deterioration and performance resulting from illness, establishing safety guidelines in the industry for repetitive tasks, monitoring the stages of rehabilitation for muscle-related injuries sustained in sports and accidents, and enhancing athletic performance through improved training protocols while reducing injury.

Validation of International Space Station Electrical Performance Model via On-orbit Telemetry

NASA Technical Reports Server (NTRS)

Jannette, Anthony G.; Hojnicki, Jeffrey S.; McKissock, David B.; Fincannon, James; Kerslake, Thomas W.; Rodriguez, Carlos D.

2002-01-01

The first U.S. power module on International Space Station (ISS) was activated in December 2000. Comprised of solar arrays, nickel-hydrogen (NiH2) batteries, and a direct current power management and distribution (PMAD) system, the electric power system (EPS) supplies power to housekeeping and user electrical loads. Modeling EPS performance is needed for several reasons, but primarily to assess near-term planned and off-nominal operations and because the EPS configuration changes over the life of the ISS. The System Power Analysis for Capability Evaluation (SPACE) computer code is used to assess the ISS EPS performance. This paper describes the process of validating the SPACE EPS model via ISS on-orbit telemetry. To accomplish this goal, telemetry was first used to correct assumptions and component models in SPACE. Then on-orbit data was directly input to SPACE to facilitate comparing model predictions to telemetry. It will be shown that SPACE accurately predicts on-orbit component and system performance. For example, battery state-of-charge was predicted to within 0.6 percentage points over a 0 to 100 percent scale and solar array current was predicted to within a root mean square (RMS) error of 5.1 Amps out of a typical maximum of 220 Amps. First, SPACE model predictions are compared to telemetry for the ISS EPS components: solar arrays, NiH2 batteries, and the PMAD system. Second, SPACE predictions for the overall performance of the ISS EPS are compared to telemetry and again demonstrate model accuracy.

Why did the bear cross the road? Comparing the performance of multiple resistance surfaces and connectivity modeling methods

Treesearch

Samuel A. Cushman; Jesse S. Lewis; Erin L. Landguth

2014-01-01

There have been few assessments of the performance of alternative resistance surfaces, and little is known about how connectivity modeling approaches differ in their ability to predict organism movements. In this paper, we evaluate the performance of four connectivity modeling approaches applied to two resistance surfaces in predicting the locations of highway...

Predicting space telerobotic operator training performance from human spatial ability assessment

NASA Astrophysics Data System (ADS)

Liu, Andrew M.; Oman, Charles M.; Galvan, Raquel; Natapoff, Alan

2013-11-01

Our goal was to determine whether existing tests of spatial ability can predict an astronaut's qualification test performance after robotic training. Because training astronauts to be qualified robotics operators is so long and expensive, NASA is interested in tools that can predict robotics performance before training begins. Currently, the Astronaut Office does not have a validated tool to predict robotics ability as part of its astronaut selection or training process. Commonly used tests of human spatial ability may provide such a tool to predict robotics ability. We tested the spatial ability of 50 active astronauts who had completed at least one robotics training course, then used logistic regression models to analyze the correlation between spatial ability test scores and the astronauts' performance in their evaluation test at the end of the training course. The fit of the logistic function to our data is statistically significant for several spatial tests. However, the prediction performance of the logistic model depends on the criterion threshold assumed. To clarify the critical selection issues, we show how the probability of correct classification vs. misclassification varies as a function of the mental rotation test criterion level. Since the costs of misclassification are low, the logistic models of spatial ability and robotic performance are reliable enough only to be used to customize regular and remedial training. We suggest several changes in tracking performance throughout robotics training that could improve the range and reliability of predictive models.

Models of Marine Fish Biodiversity: Assessing Predictors from Three Habitat Classification Schemes.

PubMed

Yates, Katherine L; Mellin, Camille; Caley, M Julian; Radford, Ben T; Meeuwig, Jessica J

2016-01-01

Prioritising biodiversity conservation requires knowledge of where biodiversity occurs. Such knowledge, however, is often lacking. New technologies for collecting biological and physical data coupled with advances in modelling techniques could help address these gaps and facilitate improved management outcomes. Here we examined the utility of environmental data, obtained using different methods, for developing models of both uni- and multivariate biodiversity metrics. We tested which biodiversity metrics could be predicted best and evaluated the performance of predictor variables generated from three types of habitat data: acoustic multibeam sonar imagery, predicted habitat classification, and direct observer habitat classification. We used boosted regression trees (BRT) to model metrics of fish species richness, abundance and biomass, and multivariate regression trees (MRT) to model biomass and abundance of fish functional groups. We compared model performance using different sets of predictors and estimated the relative influence of individual predictors. Models of total species richness and total abundance performed best; those developed for endemic species performed worst. Abundance models performed substantially better than corresponding biomass models. In general, BRT and MRTs developed using predicted habitat classifications performed less well than those using multibeam data. The most influential individual predictor was the abiotic categorical variable from direct observer habitat classification and models that incorporated predictors from direct observer habitat classification consistently outperformed those that did not. Our results show that while remotely sensed data can offer considerable utility for predictive modelling, the addition of direct observer habitat classification data can substantially improve model performance. Thus it appears that there are aspects of marine habitats that are important for modelling metrics of fish biodiversity that are not fully captured by remotely sensed data. As such, the use of remotely sensed data to model biodiversity represents a compromise between model performance and data availability.

Models of Marine Fish Biodiversity: Assessing Predictors from Three Habitat Classification Schemes

PubMed Central

Yates, Katherine L.; Mellin, Camille; Caley, M. Julian; Radford, Ben T.; Meeuwig, Jessica J.

2016-01-01

Prioritising biodiversity conservation requires knowledge of where biodiversity occurs. Such knowledge, however, is often lacking. New technologies for collecting biological and physical data coupled with advances in modelling techniques could help address these gaps and facilitate improved management outcomes. Here we examined the utility of environmental data, obtained using different methods, for developing models of both uni- and multivariate biodiversity metrics. We tested which biodiversity metrics could be predicted best and evaluated the performance of predictor variables generated from three types of habitat data: acoustic multibeam sonar imagery, predicted habitat classification, and direct observer habitat classification. We used boosted regression trees (BRT) to model metrics of fish species richness, abundance and biomass, and multivariate regression trees (MRT) to model biomass and abundance of fish functional groups. We compared model performance using different sets of predictors and estimated the relative influence of individual predictors. Models of total species richness and total abundance performed best; those developed for endemic species performed worst. Abundance models performed substantially better than corresponding biomass models. In general, BRT and MRTs developed using predicted habitat classifications performed less well than those using multibeam data. The most influential individual predictor was the abiotic categorical variable from direct observer habitat classification and models that incorporated predictors from direct observer habitat classification consistently outperformed those that did not. Our results show that while remotely sensed data can offer considerable utility for predictive modelling, the addition of direct observer habitat classification data can substantially improve model performance. Thus it appears that there are aspects of marine habitats that are important for modelling metrics of fish biodiversity that are not fully captured by remotely sensed data. As such, the use of remotely sensed data to model biodiversity represents a compromise between model performance and data availability. PMID:27333202

Markovian prediction of future values for food grains in the economic survey

NASA Astrophysics Data System (ADS)

Sathish, S.; Khadar Babu, S. K.

2017-11-01

Now-a-days prediction and forecasting are plays a vital role in research. For prediction, regression is useful to predict the future value and current value on production process. In this paper, we assume food grain production exhibit Markov chain dependency and time homogeneity. The economic generative performance evaluation the balance time artificial fertilization different level in Estrusdetection using a daily Markov chain model. Finally, Markov process prediction gives better performance compare with Regression model.

A Unified Model of Performance for Predicting the Effects of Sleep and Caffeine.

PubMed

Ramakrishnan, Sridhar; Wesensten, Nancy J; Kamimori, Gary H; Moon, James E; Balkin, Thomas J; Reifman, Jaques

2016-10-01

Existing mathematical models of neurobehavioral performance cannot predict the beneficial effects of caffeine across the spectrum of sleep loss conditions, limiting their practical utility. Here, we closed this research gap by integrating a model of caffeine effects with the recently validated unified model of performance (UMP) into a single, unified modeling framework. We then assessed the accuracy of this new UMP in predicting performance across multiple studies. We hypothesized that the pharmacodynamics of caffeine vary similarly during both wakefulness and sleep, and that caffeine has a multiplicative effect on performance. Accordingly, to represent the effects of caffeine in the UMP, we multiplied a dose-dependent caffeine factor (which accounts for the pharmacokinetics and pharmacodynamics of caffeine) to the performance estimated in the absence of caffeine. We assessed the UMP predictions in 14 distinct laboratory- and field-study conditions, including 7 different sleep-loss schedules (from 5 h of sleep per night to continuous sleep loss for 85 h) and 6 different caffeine doses (from placebo to repeated 200 mg doses to a single dose of 600 mg). The UMP accurately predicted group-average psychomotor vigilance task performance data across the different sleep loss and caffeine conditions (6% < error < 27%), yielding greater accuracy for mild and moderate sleep loss conditions than for more severe cases. Overall, accounting for the effects of caffeine resulted in improved predictions (after caffeine consumption) by up to 70%. The UMP provides the first comprehensive tool for accurate selection of combinations of sleep schedules and caffeine countermeasure strategies to optimize neurobehavioral performance. © 2016 Associated Professional Sleep Societies, LLC.

Confronting uncertainty in flood damage predictions

NASA Astrophysics Data System (ADS)

Schröter, Kai; Kreibich, Heidi; Vogel, Kristin; Merz, Bruno

2015-04-01

Reliable flood damage models are a prerequisite for the practical usefulness of the model results. Oftentimes, traditional uni-variate damage models as for instance depth-damage curves fail to reproduce the variability of observed flood damage. Innovative multi-variate probabilistic modelling approaches are promising to capture and quantify the uncertainty involved and thus to improve the basis for decision making. In this study we compare the predictive capability of two probabilistic modelling approaches, namely Bagging Decision Trees and Bayesian Networks. For model evaluation we use empirical damage data which are available from computer aided telephone interviews that were respectively compiled after the floods in 2002, 2005 and 2006, in the Elbe and Danube catchments in Germany. We carry out a split sample test by sub-setting the damage records. One sub-set is used to derive the models and the remaining records are used to evaluate the predictive performance of the model. Further we stratify the sample according to catchments which allows studying model performance in a spatial transfer context. Flood damage estimation is carried out on the scale of the individual buildings in terms of relative damage. The predictive performance of the models is assessed in terms of systematic deviations (mean bias), precision (mean absolute error) as well as in terms of reliability which is represented by the proportion of the number of observations that fall within the 95-quantile and 5-quantile predictive interval. The reliability of the probabilistic predictions within validation runs decreases only slightly and achieves a very good coverage of observations within the predictive interval. Probabilistic models provide quantitative information about prediction uncertainty which is crucial to assess the reliability of model predictions and improves the usefulness of model results.

Predictive Behavior of a Computational Foot/Ankle Model through Artificial Neural Networks.

PubMed

Chande, Ruchi D; Hargraves, Rosalyn Hobson; Ortiz-Robinson, Norma; Wayne, Jennifer S

2017-01-01

Computational models are useful tools to study the biomechanics of human joints. Their predictive performance is heavily dependent on bony anatomy and soft tissue properties. Imaging data provides anatomical requirements while approximate tissue properties are implemented from literature data, when available. We sought to improve the predictive capability of a computational foot/ankle model by optimizing its ligament stiffness inputs using feedforward and radial basis function neural networks. While the former demonstrated better performance than the latter per mean square error, both networks provided reasonable stiffness predictions for implementation into the computational model.

Designing and benchmarking the MULTICOM protein structure prediction system

PubMed Central

2013-01-01

Background Predicting protein structure from sequence is one of the most significant and challenging problems in bioinformatics. Numerous bioinformatics techniques and tools have been developed to tackle almost every aspect of protein structure prediction ranging from structural feature prediction, template identification and query-template alignment to structure sampling, model quality assessment, and model refinement. How to synergistically select, integrate and improve the strengths of the complementary techniques at each prediction stage and build a high-performance system is becoming a critical issue for constructing a successful, competitive protein structure predictor. Results Over the past several years, we have constructed a standalone protein structure prediction system MULTICOM that combines multiple sources of information and complementary methods at all five stages of the protein structure prediction process including template identification, template combination, model generation, model assessment, and model refinement. The system was blindly tested during the ninth Critical Assessment of Techniques for Protein Structure Prediction (CASP9) in 2010 and yielded very good performance. In addition to studying the overall performance on the CASP9 benchmark, we thoroughly investigated the performance and contributions of each component at each stage of prediction. Conclusions Our comprehensive and comparative study not only provides useful and practical insights about how to select, improve, and integrate complementary methods to build a cutting-edge protein structure prediction system but also identifies a few new sources of information that may help improve the design of a protein structure prediction system. Several components used in the MULTICOM system are available at: http://sysbio.rnet.missouri.edu/multicom_toolbox/. PMID:23442819

Cold formability prediction by the modified maximum force criterion with a non-associated Hill48 model accounting for anisotropic hardening

NASA Astrophysics Data System (ADS)

Lian, J.; Ahn, D. C.; Chae, D. C.; Münstermann, S.; Bleck, W.

2016-08-01

Experimental and numerical investigations on the characterisation and prediction of cold formability of a ferritic steel sheet are performed in this study. Tensile tests and Nakajima tests were performed for the plasticity characterisation and the forming limit diagram determination. In the numerical prediction, the modified maximum force criterion is selected as the localisation criterion. For the plasticity model, a non-associated formulation of the Hill48 model is employed. With the non-associated flow rule, the model can result in a similar predictive capability of stress and r-value directionality to the advanced non-quadratic associated models. To accurately characterise the anisotropy evolution during hardening, the anisotropic hardening is also calibrated and implemented into the model for the prediction of the formability.

Strategies for concurrent processing of complex algorithms in data driven architectures

NASA Technical Reports Server (NTRS)

Stoughton, John W.; Mielke, Roland R.; Som, Sukhamony

1990-01-01

The performance modeling and enhancement for periodic execution of large-grain, decision-free algorithms in data flow architectures is examined. Applications include real-time implementation of control and signal processing algorithms where performance is required to be highly predictable. The mapping of algorithms onto the specified class of data flow architectures is realized by a marked graph model called ATAMM (Algorithm To Architecture Mapping Model). Performance measures and bounds are established. Algorithm transformation techniques are identified for performance enhancement and reduction of resource (computing element) requirements. A systematic design procedure is described for generating operating conditions for predictable performance both with and without resource constraints. An ATAMM simulator is used to test and validate the performance prediction by the design procedure. Experiments on a three resource testbed provide verification of the ATAMM model and the design procedure.

Do bioclimate variables improve performance of climate envelope models?

USGS Publications Warehouse

Watling, James I.; Romañach, Stephanie S.; Bucklin, David N.; Speroterra, Carolina; Brandt, Laura A.; Pearlstine, Leonard G.; Mazzotti, Frank J.

2012-01-01

Climate envelope models are widely used to forecast potential effects of climate change on species distributions. A key issue in climate envelope modeling is the selection of predictor variables that most directly influence species. To determine whether model performance and spatial predictions were related to the selection of predictor variables, we compared models using bioclimate variables with models constructed from monthly climate data for twelve terrestrial vertebrate species in the southeastern USA using two different algorithms (random forests or generalized linear models), and two model selection techniques (using uncorrelated predictors or a subset of user-defined biologically relevant predictor variables). There were no differences in performance between models created with bioclimate or monthly variables, but one metric of model performance was significantly greater using the random forest algorithm compared with generalized linear models. Spatial predictions between maps using bioclimate and monthly variables were very consistent using the random forest algorithm with uncorrelated predictors, whereas we observed greater variability in predictions using generalized linear models.

Can air temperature be used to project influences of climate change on stream temperature?

USGS Publications Warehouse

Arismendi, Ivan; Safeeq, Mohammad; Dunham, Jason B.; Johnson, Sherri L.

2014-01-01

Worldwide, lack of data on stream temperature has motivated the use of regression-based statistical models to predict stream temperatures based on more widely available data on air temperatures. Such models have been widely applied to project responses of stream temperatures under climate change, but the performance of these models has not been fully evaluated. To address this knowledge gap, we examined the performance of two widely used linear and nonlinear regression models that predict stream temperatures based on air temperatures. We evaluated model performance and temporal stability of model parameters in a suite of regulated and unregulated streams with 11–44 years of stream temperature data. Although such models may have validity when predicting stream temperatures within the span of time that corresponds to the data used to develop them, model predictions did not transfer well to other time periods. Validation of model predictions of most recent stream temperatures, based on air temperature–stream temperature relationships from previous time periods often showed poor performance when compared with observed stream temperatures. Overall, model predictions were less robust in regulated streams and they frequently failed in detecting the coldest and warmest temperatures within all sites. In many cases, the magnitude of errors in these predictions falls within a range that equals or exceeds the magnitude of future projections of climate-related changes in stream temperatures reported for the region we studied (between 0.5 and 3.0 °C by 2080). The limited ability of regression-based statistical models to accurately project stream temperatures over time likely stems from the fact that underlying processes at play, namely the heat budgets of air and water, are distinctive in each medium and vary among localities and through time.

Geographic and temporal validity of prediction models: Different approaches were useful to examine model performance

PubMed Central

Austin, Peter C.; van Klaveren, David; Vergouwe, Yvonne; Nieboer, Daan; Lee, Douglas S.; Steyerberg, Ewout W.

2017-01-01

Objective Validation of clinical prediction models traditionally refers to the assessment of model performance in new patients. We studied different approaches to geographic and temporal validation in the setting of multicenter data from two time periods. Study Design and Setting We illustrated different analytic methods for validation using a sample of 14,857 patients hospitalized with heart failure at 90 hospitals in two distinct time periods. Bootstrap resampling was used to assess internal validity. Meta-analytic methods were used to assess geographic transportability. Each hospital was used once as a validation sample, with the remaining hospitals used for model derivation. Hospital-specific estimates of discrimination (c-statistic) and calibration (calibration intercepts and slopes) were pooled using random effects meta-analysis methods. I2 statistics and prediction interval width quantified geographic transportability. Temporal transportability was assessed using patients from the earlier period for model derivation and patients from the later period for model validation. Results Estimates of reproducibility, pooled hospital-specific performance, and temporal transportability were on average very similar, with c-statistics of 0.75. Between-hospital variation was moderate according to I2 statistics and prediction intervals for c-statistics. Conclusion This study illustrates how performance of prediction models can be assessed in settings with multicenter data at different time periods. PMID:27262237

Modeling daily discharge responses of a large karstic aquifer using soft computing methods: Artificial neural network and neuro-fuzzy

NASA Astrophysics Data System (ADS)

Kurtulus, Bedri; Razack, Moumtaz

2010-02-01

SummaryThis paper compares two methods for modeling karst aquifers, which are heterogeneous, highly non-linear, and hierarchical systems. There is a clear need to model these systems given the crucial role they play in water supply in many countries. In recent years, the main components of soft computing (fuzzy logic (FL), and Artificial Neural Networks, (ANNs)) have come to prevail in the modeling of complex non-linear systems in different scientific and technologic disciplines. In this study, Artificial Neural Networks and Adaptive Neuro-Fuzzy Interface System (ANFIS) methods were used for the prediction of daily discharge of karstic aquifers and their capability was compared. The approach was applied to 7 years of daily data of La Rochefoucauld karst system in south-western France. In order to predict the karst daily discharges, single-input (rainfall, piezometric level) vs. multiple-input (rainfall and piezometric level) series were used. In addition to these inputs, all models used measured or simulated discharges from the previous days with a specified delay. The models were designed in a Matlab™ environment. An automatic procedure was used to select the best calibrated models. Daily discharge predictions were then performed using the calibrated models. Comparing predicted and observed hydrographs indicates that both models (ANN and ANFIS) provide close predictions of the karst daily discharges. The summary statistics of both series (observed and predicted daily discharges) are comparable. The performance of both models is improved when the number of inputs is increased from one to two. The root mean square error between the observed and predicted series reaches a minimum for two-input models. However, the ANFIS model demonstrates a better performance than the ANN model to predict peak flow. The ANFIS approach demonstrates a better generalization capability and slightly higher performance than the ANN, especially for peak discharges.

Prediction of Coronary Artery Disease Risk Based on Multiple Longitudinal Biomarkers

PubMed Central

Yang, Lili; Yu, Menggang; Gao, Sujuan

2016-01-01

In the last decade, few topics in the area of cardiovascular disease (CVD) research have received as much attention as risk prediction. One of the well documented risk factors for CVD is high blood pressure (BP). Traditional CVD risk prediction models consider BP levels measured at a single time and such models form the basis for current clinical guidelines for CVD prevention. However, in clinical practice, BP levels are often observed and recorded in a longitudinal fashion. Information on BP trajectories can be powerful predictors for CVD events. We consider joint modeling of time to coronary artery disease and individual longitudinal measures of systolic and diastolic BPs in a primary care cohort with up to 20 years of follow-up. We applied novel prediction metrics to assess the predictive performance of joint models. Predictive performances of proposed joint models and other models were assessed via simulations and illustrated using the primary care cohort. PMID:26439685

Implementation of new pavement performance prediction models in PMIS : report

DOT National Transportation Integrated Search

2012-08-01

Pavement performance prediction models and maintenance and rehabilitation (M&R) optimization processes : enable managers and engineers to plan and prioritize pavement M&R activities in a cost-effective manner. : This report describes TxDOTs effort...

Validity of Treadmill-Derived Critical Speed on Predicting 5000-Meter Track-Running Performance.

PubMed

Nimmerichter, Alfred; Novak, Nina; Triska, Christoph; Prinz, Bernhard; Breese, Brynmor C

2017-03-01

Nimmerichter, A, Novak, N, Triska, C, Prinz, B, and Breese, BC. Validity of treadmill-derived critical speed on predicting 5,000-meter track-running performance. J Strength Cond Res 31(3): 706-714, 2017-To evaluate 3 models of critical speed (CS) for the prediction of 5,000-m running performance, 16 trained athletes completed an incremental test on a treadmill to determine maximal aerobic speed (MAS) and 3 randomly ordered runs to exhaustion at the [INCREMENT]70% intensity, at 110% and 98% of MAS. Critical speed and the distance covered above CS (D') were calculated using the hyperbolic speed-time (HYP), the linear distance-time (LIN), and the linear speed inverse-time model (INV). Five thousand meter performance was determined on a 400-m running track. Individual predictions of 5,000-m running time (t = [5,000-D']/CS) and speed (s = D'/t + CS) were calculated across the 3 models in addition to multiple regression analyses. Prediction accuracy was assessed with the standard error of estimate (SEE) from linear regression analysis and the mean difference expressed in units of measurement and coefficient of variation (%). Five thousand meter running performance (speed: 4.29 ± 0.39 m·s; time: 1,176 ± 117 seconds) was significantly better than the predictions from all 3 models (p < 0.0001). The mean difference was 65-105 seconds (5.7-9.4%) for time and -0.22 to -0.34 m·s (-5.0 to -7.5%) for speed. Predictions from multiple regression analyses with CS and D' as predictor variables were not significantly different from actual running performance (-1.0 to 1.1%). The SEE across all models and predictions was approximately 65 seconds or 0.20 m·s and is therefore considered as moderate. The results of this study have shown the importance of aerobic and anaerobic energy system contribution to predict 5,000-m running performance. Using estimates of CS and D' is valuable for predicting performance over race distances of 5,000 m.

Dengue forecasting in São Paulo city with generalized additive models, artificial neural networks and seasonal autoregressive integrated moving average models.

PubMed

Baquero, Oswaldo Santos; Santana, Lidia Maria Reis; Chiaravalloti-Neto, Francisco

2018-01-01

Globally, the number of dengue cases has been on the increase since 1990 and this trend has also been found in Brazil and its most populated city-São Paulo. Surveillance systems based on predictions allow for timely decision making processes, and in turn, timely and efficient interventions to reduce the burden of the disease. We conducted a comparative study of dengue predictions in São Paulo city to test the performance of trained seasonal autoregressive integrated moving average models, generalized additive models and artificial neural networks. We also used a naïve model as a benchmark. A generalized additive model with lags of the number of cases and meteorological variables had the best performance, predicted epidemics of unprecedented magnitude and its performance was 3.16 times higher than the benchmark and 1.47 higher that the next best performing model. The predictive models captured the seasonal patterns but differed in their capacity to anticipate large epidemics and all outperformed the benchmark. In addition to be able to predict epidemics of unprecedented magnitude, the best model had computational advantages, since its training and tuning was straightforward and required seconds or at most few minutes. These are desired characteristics to provide timely results for decision makers. However, it should be noted that predictions are made just one month ahead and this is a limitation that future studies could try to reduce.

Comparison of the Predictive Performance and Interpretability of Random Forest and Linear Models on Benchmark Data Sets.

PubMed

Marchese Robinson, Richard L; Palczewska, Anna; Palczewski, Jan; Kidley, Nathan

2017-08-28

The ability to interpret the predictions made by quantitative structure-activity relationships (QSARs) offers a number of advantages. While QSARs built using nonlinear modeling approaches, such as the popular Random Forest algorithm, might sometimes be more predictive than those built using linear modeling approaches, their predictions have been perceived as difficult to interpret. However, a growing number of approaches have been proposed for interpreting nonlinear QSAR models in general and Random Forest in particular. In the current work, we compare the performance of Random Forest to those of two widely used linear modeling approaches: linear Support Vector Machines (SVMs) (or Support Vector Regression (SVR)) and partial least-squares (PLS). We compare their performance in terms of their predictivity as well as the chemical interpretability of the predictions using novel scoring schemes for assessing heat map images of substructural contributions. We critically assess different approaches for interpreting Random Forest models as well as for obtaining predictions from the forest. We assess the models on a large number of widely employed public-domain benchmark data sets corresponding to regression and binary classification problems of relevance to hit identification and toxicology. We conclude that Random Forest typically yields comparable or possibly better predictive performance than the linear modeling approaches and that its predictions may also be interpreted in a chemically and biologically meaningful way. In contrast to earlier work looking at interpretation of nonlinear QSAR models, we directly compare two methodologically distinct approaches for interpreting Random Forest models. The approaches for interpreting Random Forest assessed in our article were implemented using open-source programs that we have made available to the community. These programs are the rfFC package ( https://r-forge.r-project.org/R/?group_id=1725 ) for the R statistical programming language and the Python program HeatMapWrapper [ https://doi.org/10.5281/zenodo.495163 ] for heat map generation.

Effect of experimental design on the prediction performance of calibration models based on near-infrared spectroscopy for pharmaceutical applications.

PubMed

Bondi, Robert W; Igne, Benoît; Drennen, James K; Anderson, Carl A

2012-12-01

Near-infrared spectroscopy (NIRS) is a valuable tool in the pharmaceutical industry, presenting opportunities for online analyses to achieve real-time assessment of intermediates and finished dosage forms. The purpose of this work was to investigate the effect of experimental designs on prediction performance of quantitative models based on NIRS using a five-component formulation as a model system. The following experimental designs were evaluated: five-level, full factorial (5-L FF); three-level, full factorial (3-L FF); central composite; I-optimal; and D-optimal. The factors for all designs were acetaminophen content and the ratio of microcrystalline cellulose to lactose monohydrate. Other constituents included croscarmellose sodium and magnesium stearate (content remained constant). Partial least squares-based models were generated using data from individual experimental designs that related acetaminophen content to spectral data. The effect of each experimental design was evaluated by determining the statistical significance of the difference in bias and standard error of the prediction for that model's prediction performance. The calibration model derived from the I-optimal design had similar prediction performance as did the model derived from the 5-L FF design, despite containing 16 fewer design points. It also outperformed all other models estimated from designs with similar or fewer numbers of samples. This suggested that experimental-design selection for calibration-model development is critical, and optimum performance can be achieved with efficient experimental designs (i.e., optimal designs).

Incorporating groundwater flow into the WEPP model

Treesearch

William Elliot; Erin Brooks; Tim Link; Sue Miller

2010-01-01

The water erosion prediction project (WEPP) model is a physically-based hydrology and erosion model. In recent years, the hydrology prediction within the model has been improved for forest watershed modeling by incorporating shallow lateral flow into watershed runoff prediction. This has greatly improved WEPP's hydrologic performance on small watersheds with...

Assessing deep and shallow learning methods for quantitative prediction of acute chemical toxicity.

PubMed

Liu, Ruifeng; Madore, Michael; Glover, Kyle P; Feasel, Michael G; Wallqvist, Anders

2018-05-02

Animal-based methods for assessing chemical toxicity are struggling to meet testing demands. In silico approaches, including machine-learning methods, are promising alternatives. Recently, deep neural networks (DNNs) were evaluated and reported to outperform other machine-learning methods for quantitative structure-activity relationship modeling of molecular properties. However, most of the reported performance evaluations relied on global performance metrics, such as the root mean squared error (RMSE) between the predicted and experimental values of all samples, without considering the impact of sample distribution across the activity spectrum. Here, we carried out an in-depth analysis of DNN performance for quantitative prediction of acute chemical toxicity using several datasets. We found that the overall performance of DNN models on datasets of up to 30,000 compounds was similar to that of random forest (RF) models, as measured by the RMSE and correlation coefficients between the predicted and experimental results. However, our detailed analyses demonstrated that global performance metrics are inappropriate for datasets with a highly uneven sample distribution, because they show a strong bias for the most populous compounds along the toxicity spectrum. For highly toxic compounds, DNN and RF models trained on all samples performed much worse than the global performance metrics indicated. Surprisingly, our variable nearest neighbor method, which utilizes only structurally similar compounds to make predictions, performed reasonably well, suggesting that information of close near neighbors in the training sets is a key determinant of acute toxicity predictions.

Genomic Prediction Accounting for Genotype by Environment Interaction Offers an Effective Framework for Breeding Simultaneously for Adaptation to an Abiotic Stress and Performance Under Normal Cropping Conditions in Rice.

PubMed

Ben Hassen, Manel; Bartholomé, Jérôme; Valè, Giampiero; Cao, Tuong-Vi; Ahmadi, Nourollah

2018-05-09

Developing rice varieties adapted to alternate wetting and drying water management is crucial for the sustainability of irrigated rice cropping systems. Here we report the first study exploring the feasibility of breeding rice for adaptation to alternate wetting and drying using genomic prediction methods that account for genotype by environment interactions. Two breeding populations (a reference panel of 284 accessions and a progeny population of 97 advanced lines) were evaluated under alternate wetting and drying and continuous flooding management systems. The predictive ability of genomic prediction for response variables (index of relative performance and the slope of the joint regression) and for multi-environment genomic prediction models were compared. For the three traits considered (days to flowering, panicle weight and nitrogen-balance index), significant genotype by environment interactions were observed in both populations. In cross validation, predictive ability for the index was on average lower (0.31) than that of the slope of the joint regression (0.64) whatever the trait considered. Similar results were found for progeny validation. Both cross-validation and progeny validation experiments showed that the performance of multi-environment models predicting unobserved phenotypes of untested entrees was similar to the performance of single environment models with differences in predictive ability ranging from -6% to 4% depending on the trait and on the statistical model concerned. The predictive ability of multi-environment models predicting unobserved phenotypes of entrees evaluated under both water management systems outperformed single environment models by an average of 30%. Practical implications for breeding rice for adaptation to alternate wetting and drying system are discussed. Copyright © 2018, G3: Genes, Genomes, Genetics.

Using Performance Data Gathered at Several Stages of Achievement in Predicting Subsequent Performance.

ERIC Educational Resources Information Center

Owen, Steven V.; Feldhusen, John F.

This study compares the effectiveness of three models of multivariate prediction for academic success in identifying the criterion variance of achievement in nursing education. The first model involves the use of an optimum set of predictors and one equation derived from a regression analysis on first semester grade average in predicting the…

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

PubMed

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

2016-11-01

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

ILS Glide Slope Performance Prediction. Volume B

DTIC Science & Technology

1974-09-01

figures are identical in both volumes. 󈧔. Abottec A mathematical model for predicting the performance of ILS glide slope arrays in the presence of...irregularities on the performance of ILS Glide Slope antenna systems, a mathematical -electromagnetic scattering computer model has been developed. This work was...Antenna ........... 4-4 9. Test Case Results ..................................... r-3 ix PART I. IEO -j 1.INTRODUCTION IA mathematical model has been

LiDAR based prediction of forest biomass using hierarchical models with spatially varying coefficients

USGS Publications Warehouse

Babcock, Chad; Finley, Andrew O.; Bradford, John B.; Kolka, Randall K.; Birdsey, Richard A.; Ryan, Michael G.

2015-01-01

Many studies and production inventory systems have shown the utility of coupling covariates derived from Light Detection and Ranging (LiDAR) data with forest variables measured on georeferenced inventory plots through regression models. The objective of this study was to propose and assess the use of a Bayesian hierarchical modeling framework that accommodates both residual spatial dependence and non-stationarity of model covariates through the introduction of spatial random effects. We explored this objective using four forest inventory datasets that are part of the North American Carbon Program, each comprising point-referenced measures of above-ground forest biomass and discrete LiDAR. For each dataset, we considered at least five regression model specifications of varying complexity. Models were assessed based on goodness of fit criteria and predictive performance using a 10-fold cross-validation procedure. Results showed that the addition of spatial random effects to the regression model intercept improved fit and predictive performance in the presence of substantial residual spatial dependence. Additionally, in some cases, allowing either some or all regression slope parameters to vary spatially, via the addition of spatial random effects, further improved model fit and predictive performance. In other instances, models showed improved fit but decreased predictive performance—indicating over-fitting and underscoring the need for cross-validation to assess predictive ability. The proposed Bayesian modeling framework provided access to pixel-level posterior predictive distributions that were useful for uncertainty mapping, diagnosing spatial extrapolation issues, revealing missing model covariates, and discovering locally significant parameters.

Predicting performance: relative importance of students' background and past performance.

PubMed

Stegers-Jager, Karen M; Themmen, Axel P N; Cohen-Schotanus, Janke; Steyerberg, Ewout W

2015-09-01

Despite evidence for the predictive value of both pre-admission characteristics and past performance at medical school, their relative contribution to predicting medical school performance has not been thoroughly investigated. This study was designed to determine the relative importance of pre-admission characteristics and past performance in medical school in predicting student performance in pre-clinical and clinical training. This longitudinal prospective study followed six cohorts of students admitted to a Dutch, 6-year, undergraduate medical course during 2002-2007 (n = 2357). Four prediction models were developed using multivariate logistic regression analysis. Main outcome measures were 'Year 1 course completion within 1 year' (models 1a, 1b), 'Pre-clinical course completion within 4 years' (model 2) and 'Achievement of at least three of five clerkship grades of ≥ 8.0' (model 3). Pre-admission characteristics (models 1a, 1b, 2, 3) and past performance at medical school (models 1b, 2, 3) were included as predictor variables. In model 1a - including pre-admission characteristics only - the strongest predictor for Year 1 course completion was pre-university grade point average (GPA). Success factors were 'selected by admission testing' and 'age > 21 years'; risk factors were 'Surinamese/Antillean background', 'foreign pre-university degree', 'doctor parent' and male gender. In model 1b, number of attempts and GPA at 4 months were the strongest predictors for Year 1 course completion, and male gender remained a risk factor. Year 1 GPA was the strongest predictor for pre-clinical course completion, whereas being male or aged 19-21 years were risk factors. Pre-clinical course GPA positively predicted clinical performance, whereas being non-Dutch or a first-generation university student were important risk factors for lower clinical grades. Nagelkerke's R(2) ranged from 0.16 to 0.62. This study not only confirms the importance of past performance as a predictor of future performance in pre-clinical training, but also reveals the importance of a student's background as a predictor in clinical training. These findings have important practical implications for selection and support during medical school. © 2015 John Wiley & Sons Ltd.

Dissimilarity based Partial Least Squares (DPLS) for genomic prediction from SNPs.

PubMed

Singh, Priyanka; Engel, Jasper; Jansen, Jeroen; de Haan, Jorn; Buydens, Lutgarde Maria Celina

2016-05-04

Genomic prediction (GP) allows breeders to select plants and animals based on their breeding potential for desirable traits, without lengthy and expensive field trials or progeny testing. We have proposed to use Dissimilarity-based Partial Least Squares (DPLS) for GP. As a case study, we use the DPLS approach to predict Bacterial wilt (BW) in tomatoes using SNPs as predictors. The DPLS approach was compared with the Genomic Best-Linear Unbiased Prediction (GBLUP) and single-SNP regression with SNP as a fixed effect to assess the performance of DPLS. Eight genomic distance measures were used to quantify relationships between the tomato accessions from the SNPs. Subsequently, each of these distance measures was used to predict the BW using the DPLS prediction model. The DPLS model was found to be robust to the choice of distance measures; similar prediction performances were obtained for each distance measure. DPLS greatly outperformed the single-SNP regression approach, showing that BW is a comprehensive trait dependent on several loci. Next, the performance of the DPLS model was compared to that of GBLUP. Although GBLUP and DPLS are conceptually very different, the prediction quality (PQ) measured by DPLS models were similar to the prediction statistics obtained from GBLUP. A considerable advantage of DPLS is that the genotype-phenotype relationship can easily be visualized in a 2-D scatter plot. This so-called score-plot provides breeders an insight to select candidates for their future breeding program. DPLS is a highly appropriate method for GP. The model prediction performance was similar to the GBLUP and far better than the single-SNP approach. The proposed method can be used in combination with a wide range of genomic dissimilarity measures and genotype representations such as allele-count, haplotypes or allele-intensity values. Additionally, the data can be insightfully visualized by the DPLS model, allowing for selection of desirable candidates from the breeding experiments. In this study, we have assessed the DPLS performance on a single trait.

Incorporating uncertainty in predictive species distribution modelling.

PubMed

Beale, Colin M; Lennon, Jack J

2012-01-19

Motivated by the need to solve ecological problems (climate change, habitat fragmentation and biological invasions), there has been increasing interest in species distribution models (SDMs). Predictions from these models inform conservation policy, invasive species management and disease-control measures. However, predictions are subject to uncertainty, the degree and source of which is often unrecognized. Here, we review the SDM literature in the context of uncertainty, focusing on three main classes of SDM: niche-based models, demographic models and process-based models. We identify sources of uncertainty for each class and discuss how uncertainty can be minimized or included in the modelling process to give realistic measures of confidence around predictions. Because this has typically not been performed, we conclude that uncertainty in SDMs has often been underestimated and a false precision assigned to predictions of geographical distribution. We identify areas where development of new statistical tools will improve predictions from distribution models, notably the development of hierarchical models that link different types of distribution model and their attendant uncertainties across spatial scales. Finally, we discuss the need to develop more defensible methods for assessing predictive performance, quantifying model goodness-of-fit and for assessing the significance of model covariates.

Multi-model comparison highlights consistency in predicted effect of warming on a semi-arid shrub

USGS Publications Warehouse

Renwick, Katherine M.; Curtis, Caroline; Kleinhesselink, Andrew R.; Schlaepfer, Daniel R.; Bradley, Bethany A.; Aldridge, Cameron L.; Poulter, Benjamin; Adler, Peter B.

2018-01-01

A number of modeling approaches have been developed to predict the impacts of climate change on species distributions, performance, and abundance. The stronger the agreement from models that represent different processes and are based on distinct and independent sources of information, the greater the confidence we can have in their predictions. Evaluating the level of confidence is particularly important when predictions are used to guide conservation or restoration decisions. We used a multi-model approach to predict climate change impacts on big sagebrush (Artemisia tridentata), the dominant plant species on roughly 43 million hectares in the western United States and a key resource for many endemic wildlife species. To evaluate the climate sensitivity of A. tridentata, we developed four predictive models, two based on empirically derived spatial and temporal relationships, and two that applied mechanistic approaches to simulate sagebrush recruitment and growth. This approach enabled us to produce an aggregate index of climate change vulnerability and uncertainty based on the level of agreement between models. Despite large differences in model structure, predictions of sagebrush response to climate change were largely consistent. Performance, as measured by change in cover, growth, or recruitment, was predicted to decrease at the warmest sites, but increase throughout the cooler portions of sagebrush's range. A sensitivity analysis indicated that sagebrush performance responds more strongly to changes in temperature than precipitation. Most of the uncertainty in model predictions reflected variation among the ecological models, raising questions about the reliability of forecasts based on a single modeling approach. Our results highlight the value of a multi-model approach in forecasting climate change impacts and uncertainties and should help land managers to maximize the value of conservation investments.

Deep learning architecture for air quality predictions.

PubMed

Li, Xiang; Peng, Ling; Hu, Yuan; Shao, Jing; Chi, Tianhe

2016-11-01

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.

Sootblowing optimization for improved boiler performance

DOEpatents

James, John Robert; McDermott, John; Piche, Stephen; Pickard, Fred; Parikh, Neel J.

2012-12-25

A sootblowing control system that uses predictive models to bridge the gap between sootblower operation and boiler performance goals. The system uses predictive modeling and heuristics (rules) associated with different zones in a boiler to determine an optimal sequence of sootblower operations and achieve boiler performance targets. The system performs the sootblower optimization while observing any operational constraints placed on the sootblowers.

Sootblowing optimization for improved boiler performance

DOEpatents

James, John Robert; McDermott, John; Piche, Stephen; Pickard, Fred; Parikh, Neel J

2013-07-30

A sootblowing control system that uses predictive models to bridge the gap between sootblower operation and boiler performance goals. The system uses predictive modeling and heuristics (rules) associated with different zones in a boiler to determine an optimal sequence of sootblower operations and achieve boiler performance targets. The system performs the sootblower optimization while observing any operational constraints placed on the sootblowers.

Model Verification and Validation Concepts for a Probabilistic Fracture Assessment Model to Predict Cracking of Knife Edge Seals in the Space Shuttle Main Engine High Pressure Oxidizer

NASA Technical Reports Server (NTRS)

Pai, Shantaram S.; Riha, David S.

2013-01-01

Physics-based models are routinely used to predict the performance of engineered systems to make decisions such as when to retire system components, how to extend the life of an aging system, or if a new design will be safe or available. Model verification and validation (V&V) is a process to establish credibility in model predictions. Ideally, carefully controlled validation experiments will be designed and performed to validate models or submodels. In reality, time and cost constraints limit experiments and even model development. This paper describes elements of model V&V during the development and application of a probabilistic fracture assessment model to predict cracking in space shuttle main engine high-pressure oxidizer turbopump knife-edge seals. The objective of this effort was to assess the probability of initiating and growing a crack to a specified failure length in specific flight units for different usage and inspection scenarios. The probabilistic fracture assessment model developed in this investigation combined a series of submodels describing the usage, temperature history, flutter tendencies, tooth stresses and numbers of cycles, fatigue cracking, nondestructive inspection, and finally the probability of failure. The analysis accounted for unit-to-unit variations in temperature, flutter limit state, flutter stress magnitude, and fatigue life properties. The investigation focused on the calculation of relative risk rather than absolute risk between the usage scenarios. Verification predictions were first performed for three units with known usage and cracking histories to establish credibility in the model predictions. Then, numerous predictions were performed for an assortment of operating units that had flown recently or that were projected for future flights. Calculations were performed using two NASA-developed software tools: NESSUS(Registered Trademark) for the probabilistic analysis, and NASGRO(Registered Trademark) for the fracture mechanics analysis. The goal of these predictions was to provide additional information to guide decisions on the potential of reusing existing and installed units prior to the new design certification.

Shuttle active thermal control system development testing. Volume 3: Modular radiator system test data correlation with thermal model

NASA Technical Reports Server (NTRS)

Phillips, M. A.

1973-01-01

Results are presented of an analysis which compares the performance predictions of a thermal model of a multi-panel modular radiator system with thermal vacuum test data. Comparisons between measured and predicted individual panel outlet temperatures and pressure drops and system outlet temperatures have been made over the full range of heat loads, environments and plumbing arrangements expected for the shuttle radiators. Both two sided and one sided radiation have been included. The model predictions show excellent agreement with the test data for the maximum design conditions of high load and hot environment. Predictions under minimum design conditions of low load-cold environments indicate good agreement with the measured data, but evaluation of low load predictions should consider the possibility of parallel flow instabilities due to main system freezing. Performance predictions under intermediate conditions in which the majority of the flow is not in either the main or prime system are adequate although model improvements in this area may be desired. The primary modeling objective of providing an analytical technique for performance predictions of a multi-panel radiator system under the design conditions has been met.

Comparison of in silico models for prediction of mutagenicity.

PubMed

Bakhtyari, Nazanin G; Raitano, Giuseppa; Benfenati, Emilio; Martin, Todd; Young, Douglas

2013-01-01

Using a dataset with more than 6000 compounds, the performance of eight quantitative structure activity relationships (QSAR) models was evaluated: ACD/Tox Suite, Absorption, Distribution, Metabolism, Elimination, and Toxicity of chemical substances (ADMET) predictor, Derek, Toxicity Estimation Software Tool (T.E.S.T.), TOxicity Prediction by Komputer Assisted Technology (TOPKAT), Toxtree, CEASAR, and SARpy (SAR in python). In general, the results showed a high level of performance. To have a realistic estimate of the predictive ability, the results for chemicals inside and outside the training set for each model were considered. The effect of applicability domain tools (when available) on the prediction accuracy was also evaluated. The predictive tools included QSAR models, knowledge-based systems, and a combination of both methods. Models based on statistical QSAR methods gave better results.

Predicting University Performance in Psychology: The Role of Previous Performance and Discipline-Specific Knowledge

ERIC Educational Resources Information Center

Betts, Lucy R.; Elder, Tracey J.; Hartley, James; Blurton, Anthony

2008-01-01

Recent initiatives to enhance retention and widen participation ensure it is crucial to understand the factors that predict students' performance during their undergraduate degree. The present research used Structural Equation Modeling (SEM) to test three separate models that examined the extent to which British Psychology students' A-level entry…

Predicting Examination Performance Using an Expanded Integrated Hierarchical Model of Test Emotions and Achievement Goals

ERIC Educational Resources Information Center

Putwain, Dave; Deveney, Carolyn

2009-01-01

The aim of this study was to examine an expanded integrative hierarchical model of test emotions and achievement goal orientations in predicting the examination performance of undergraduate students. Achievement goals were theorised as mediating the relationship between test emotions and performance. 120 undergraduate students completed…

What do we gain with Probabilistic Flood Loss Models?

NASA Astrophysics Data System (ADS)

Schroeter, K.; Kreibich, H.; Vogel, K.; Merz, B.; Lüdtke, S.

2015-12-01

The reliability of flood loss models is a prerequisite for their practical usefulness. Oftentimes, traditional uni-variate damage models as for instance depth-damage curves fail to reproduce the variability of observed flood damage. Innovative multi-variate probabilistic modelling approaches are promising to capture and quantify the uncertainty involved and thus to improve the basis for decision making. In this study we compare the predictive capability of two probabilistic modelling approaches, namely Bagging Decision Trees and Bayesian Networks and traditional stage damage functions which are cast in a probabilistic framework. For model evaluation we use empirical damage data which are available from computer aided telephone interviews that were respectively compiled after the floods in 2002, 2005, 2006 and 2013 in the Elbe and Danube catchments in Germany. We carry out a split sample test by sub-setting the damage records. One sub-set is used to derive the models and the remaining records are used to evaluate the predictive performance of the model. Further we stratify the sample according to catchments which allows studying model performance in a spatial transfer context. Flood damage estimation is carried out on the scale of the individual buildings in terms of relative damage. The predictive performance of the models is assessed in terms of systematic deviations (mean bias), precision (mean absolute error) as well as in terms of reliability which is represented by the proportion of the number of observations that fall within the 95-quantile and 5-quantile predictive interval. The reliability of the probabilistic predictions within validation runs decreases only slightly and achieves a very good coverage of observations within the predictive interval. Probabilistic models provide quantitative information about prediction uncertainty which is crucial to assess the reliability of model predictions and improves the usefulness of model results.

Delirium prediction in the intensive care unit: comparison of two delirium prediction models.

PubMed

Wassenaar, Annelies; Schoonhoven, Lisette; Devlin, John W; van Haren, Frank M P; Slooter, Arjen J C; Jorens, Philippe G; van der Jagt, Mathieu; Simons, Koen S; Egerod, Ingrid; Burry, Lisa D; Beishuizen, Albertus; Matos, Joaquim; Donders, A Rogier T; Pickkers, Peter; van den Boogaard, Mark

2018-05-05

Accurate prediction of delirium in the intensive care unit (ICU) may facilitate efficient use of early preventive strategies and stratification of ICU patients by delirium risk in clinical research, but the optimal delirium prediction model to use is unclear. We compared the predictive performance and user convenience of the prediction  model for delirium (PRE-DELIRIC) and early prediction model for delirium (E-PRE-DELIRIC) in ICU patients and determined the value of a two-stage calculation. This 7-country, 11-hospital, prospective cohort study evaluated consecutive adults admitted to the ICU who could be reliably assessed for delirium using the Confusion Assessment Method-ICU or the Intensive Care Delirium Screening Checklist. The predictive performance of the models was measured using the area under the receiver operating characteristic curve. Calibration was assessed graphically. A physician questionnaire evaluated user convenience. For the two-stage calculation we used E-PRE-DELIRIC immediately after ICU admission and updated the prediction using PRE-DELIRIC after 24 h. In total 2178 patients were included. The area under the receiver operating characteristic curve was significantly greater for PRE-DELIRIC (0.74 (95% confidence interval 0.71-0.76)) compared to E-PRE-DELIRIC (0.68 (95% confidence interval 0.66-0.71)) (z score of - 2.73 (p < 0.01)). Both models were well-calibrated. The sensitivity improved when using the two-stage calculation in low-risk patients. Compared to PRE-DELIRIC, ICU physicians (n = 68) rated the E-PRE-DELIRIC model more feasible. While both ICU delirium prediction models have moderate-to-good performance, the PRE-DELIRIC model predicts delirium better. However, ICU physicians rated the user convenience of E-PRE-DELIRIC superior to PRE-DELIRIC. In low-risk patients the delirium prediction further improves after an update with the PRE-DELIRIC model after 24 h. ClinicalTrials.gov, NCT02518646 . Registered on 21 July 2015.

Electrochemical carbon dioxide concentrator subsystem math model. [for manned space station

NASA Technical Reports Server (NTRS)

Marshall, R. D.; Carlson, J. N.; Schubert, F. H.

1974-01-01

A steady state computer simulation model has been developed to describe the performance of a total six man, self-contained electrochemical carbon dioxide concentrator subsystem built for the space station prototype. The math model combines expressions describing the performance of the electrochemical depolarized carbon dioxide concentrator cells and modules previously developed with expressions describing the performance of the other major CS-6 components. The model is capable of accurately predicting CS-6 performance over EDC operating ranges and the computer simulation results agree with experimental data obtained over the prediction range.

Deriving the polarization behavior of many-layer mirror coatings

NASA Astrophysics Data System (ADS)

White, Amanda J.; Harrington, David M.; Sueoka, Stacey R.

2018-06-01

End-to-end models of astronomical instrument performance are becoming commonplace to demonstrate feasibility and guarantee performance at large observatories. Astronomical techniques like adaptive optics and high contrast imaging have made great strides towards making detailed performance predictions, however, for polarimetric techniques, fundamental tools for predicting performance do not exist. One big missing piece is predicting the wavelength and field of view dependence of a many-mirror articulated optical system particularly with complex protected metal coatings. Predicting polarization performance of instruments requires combining metrology of mirror coatings, tools to create mirror coating models, and optical modeling software for polarized beam propagation. The inability to predict instrument induced polarization or to define polarization performance expectations has far reaching implications for up and coming major observatories, such as the Daniel K. Inouye Solar Telescope (DKIST), that aim to take polarization measurements at unprecedented sensitivity and resolution.Here we present a method for modelling the wavelength dependent refractive index of an optic using Berreman calculus - a mathematical formalism that describes how an electromagnetic field propagates through a birefringent medium. From Berreman calculus, we can better predict the Mueller matrix, diattenuation, and retardance of an arbitrary thicknesses of amorphous many-layer coatings as well as stacks of birefringent crystals from laboratory measurements. This will allow for the wavelength dependent refractive index to be accurately determined and the polarization behavior to be derived for a given optic.

Criterion for evaluating the predictive ability of nonlinear regression models without cross-validation.

PubMed

Kaneko, Hiromasa; Funatsu, Kimito

2013-09-23

We propose predictive performance criteria for nonlinear regression models without cross-validation. The proposed criteria are the determination coefficient and the root-mean-square error for the midpoints between k-nearest-neighbor data points. These criteria can be used to evaluate predictive ability after the regression models are updated, whereas cross-validation cannot be performed in such a situation. The proposed method is effective and helpful in handling big data when cross-validation cannot be applied. By analyzing data from numerical simulations and quantitative structural relationships, we confirm that the proposed criteria enable the predictive ability of the nonlinear regression models to be appropriately quantified.

A comparison of the Full Outline of UnResponsiveness (FOUR) score and Glasgow Coma Score (GCS) in predictive modelling in traumatic brain injury.

PubMed

Kasprowicz, Magdalena; Burzynska, Malgorzata; Melcer, Tomasz; Kübler, Andrzej

2016-01-01

To compare the performance of multivariate predictive models incorporating either the Full Outline of UnResponsiveness (FOUR) score or Glasgow Coma Score (GCS) in order to test whether substituting GCS with the FOUR score in predictive models for outcome in patients after TBI is beneficial. A total of 162 TBI patients were prospectively enrolled in the study. Stepwise logistic regression analysis was conducted to compare the prediction of (1) in-ICU mortality and (2) unfavourable outcome at 3 months post-injury using as predictors either the FOUR score or GCS along with other factors that may affect patient outcome. The areas under the ROC curves (AUCs) were used to compare the discriminant ability and predictive power of the models. The internal validation was performed with bootstrap technique and expressed as accuracy rate (AcR). The FOUR score, age, the CT Rotterdam score, systolic ABP and being placed on ventilator within day one (model 1: AUC: 0.906 ± 0.024; AcR: 80.3 ± 4.8%) performed equally well in predicting in-ICU mortality as the combination of GCS with the same set of predictors plus pupil reactivity (model 2: AUC: 0.913 ± 0.022; AcR: 81.1 ± 4.8%). The CT Rotterdam score, age and either the FOUR score (model 3) or GCS (model 4) equally well predicted unfavourable outcome at 3 months post-injury (AUC: 0.852 ± 0.037 vs. 0.866 ± 0.034; AcR: 72.3 ± 6.6% vs. 71.9%±6.6%, respectively). Adding the FOUR score or GCS at discharge from ICU to predictive models for unfavourable outcome increased significantly their performances (AUC: 0.895 ± 0.029, p = 0.05; AcR: 76.1 ± 6.5%; p < 0.004 when compared with model 3; and AUC: 0.918 ± 0.025, p < 0.05; AcR: 79.6 ± 7.2%, p < 0.009 when compared with model 4), but there was no benefit from substituting GCS with the FOUR score. Results showed that FOUR score and GCS perform equally well in multivariate predictive modelling in TBI.

Modeling to predict pilot performance during CDTI-based in-trail following experiments

NASA Technical Reports Server (NTRS)

Sorensen, J. A.; Goka, T.

1984-01-01

A mathematical model was developed of the flight system with the pilot using a cockpit display of traffic information (CDTI) to establish and maintain in-trail spacing behind a lead aircraft during approach. Both in-trail and vertical dynamics were included. The nominal spacing was based on one of three criteria (Constant Time Predictor; Constant Time Delay; or Acceleration Cue). This model was used to simulate digitally the dynamics of a string of multiple following aircraft, including response to initial position errors. The simulation was used to predict the outcome of a series of in-trail following experiments, including pilot performance in maintaining correct longitudinal spacing and vertical position. The experiments were run in the NASA Ames Research Center multi-cab cockpit simulator facility. The experimental results were then used to evaluate the model and its prediction accuracy. Model parameters were adjusted, so that modeled performance matched experimental results. Lessons learned in this modeling and prediction study are summarized.

Development of an in Silico Model of DPPH• Free Radical Scavenging Capacity: Prediction of Antioxidant Activity of Coumarin Type Compounds.

PubMed

Goya Jorge, Elizabeth; Rayar, Anita Maria; Barigye, Stephen J; Jorge Rodríguez, María Elisa; Sylla-Iyarreta Veitía, Maité

2016-06-07

A quantitative structure-activity relationship (QSAR) study of the 2,2-diphenyl-l-picrylhydrazyl (DPPH•) radical scavenging ability of 1373 chemical compounds, using DRAGON molecular descriptors (MD) and the neural network technique, a technique based on the multilayer multilayer perceptron (MLP), was developed. The built model demonstrated a satisfactory performance for the training ( R 2 = 0.713 ) and test set ( Q ext 2 = 0.654 ) , respectively. To gain greater insight on the relevance of the MD contained in the MLP model, sensitivity and principal component analyses were performed. Moreover, structural and mechanistic interpretation was carried out to comprehend the relationship of the variables in the model with the modeled property. The constructed MLP model was employed to predict the radical scavenging ability for a group of coumarin-type compounds. Finally, in order to validate the model's predictions, an in vitro assay for one of the compounds (4-hydroxycoumarin) was performed, showing a satisfactory proximity between the experimental and predicted pIC50 values.

Predicting ICU mortality: a comparison of stationary and nonstationary temporal models.

PubMed Central

Kayaalp, M.; Cooper, G. F.; Clermont, G.

2000-01-01

OBJECTIVE: This study evaluates the effectiveness of the stationarity assumption in predicting the mortality of intensive care unit (ICU) patients at the ICU discharge. DESIGN: This is a comparative study. A stationary temporal Bayesian network learned from data was compared to a set of (33) nonstationary temporal Bayesian networks learned from data. A process observed as a sequence of events is stationary if its stochastic properties stay the same when the sequence is shifted in a positive or negative direction by a constant time parameter. The temporal Bayesian networks forecast mortalities of patients, where each patient has one record per day. The predictive performance of the stationary model is compared with nonstationary models using the area under the receiver operating characteristics (ROC) curves. RESULTS: The stationary model usually performed best. However, one nonstationary model using large data sets performed significantly better than the stationary model. CONCLUSION: Results suggest that using a combination of stationary and nonstationary models may predict better than using either alone. PMID:11079917

Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes

PubMed Central

Bai, Cong; Peng, Zhong-Ren; Lu, Qing-Chang; Sun, Jian

2015-01-01

Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes. PMID:26294903

Dynamic Bus Travel Time Prediction Models on Road with Multiple Bus Routes.

PubMed

Bai, Cong; Peng, Zhong-Ren; Lu, Qing-Chang; Sun, Jian

2015-01-01

Accurate and real-time travel time information for buses can help passengers better plan their trips and minimize waiting times. A dynamic travel time prediction model for buses addressing the cases on road with multiple bus routes is proposed in this paper, based on support vector machines (SVMs) and Kalman filtering-based algorithm. In the proposed model, the well-trained SVM model predicts the baseline bus travel times from the historical bus trip data; the Kalman filtering-based dynamic algorithm can adjust bus travel times with the latest bus operation information and the estimated baseline travel times. The performance of the proposed dynamic model is validated with the real-world data on road with multiple bus routes in Shenzhen, China. The results show that the proposed dynamic model is feasible and applicable for bus travel time prediction and has the best prediction performance among all the five models proposed in the study in terms of prediction accuracy on road with multiple bus routes.

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

NASA Astrophysics Data System (ADS)

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

2018-01-01

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

ILS Glide Slope Performance Prediction Multipath Scattering

DOT National Transportation Integrated Search

1976-12-01

A mathematical model has been developed which predicts the performance of ILS glide slope systems subject to multipath scattering and the effects of irregular terrain contours. The model is discussed in detail and then applied to a test case for purp...

Prediction-error variance in Bayesian model updating: a comparative study

NASA Astrophysics Data System (ADS)

Asadollahi, Parisa; Li, Jian; Huang, Yong

2017-04-01

In Bayesian model updating, the likelihood function is commonly formulated by stochastic embedding in which the maximum information entropy probability model of prediction error variances plays an important role and it is Gaussian distribution subject to the first two moments as constraints. The selection of prediction error variances can be formulated as a model class selection problem, which automatically involves a trade-off between the average data-fit of the model class and the information it extracts from the data. Therefore, it is critical for the robustness in the updating of the structural model especially in the presence of modeling errors. To date, three ways of considering prediction error variances have been seem in the literature: 1) setting constant values empirically, 2) estimating them based on the goodness-of-fit of the measured data, and 3) updating them as uncertain parameters by applying Bayes' Theorem at the model class level. In this paper, the effect of different strategies to deal with the prediction error variances on the model updating performance is investigated explicitly. A six-story shear building model with six uncertain stiffness parameters is employed as an illustrative example. Transitional Markov Chain Monte Carlo is used to draw samples of the posterior probability density function of the structure model parameters as well as the uncertain prediction variances. The different levels of modeling uncertainty and complexity are modeled through three FE models, including a true model, a model with more complexity, and a model with modeling error. Bayesian updating is performed for the three FE models considering the three aforementioned treatments of the prediction error variances. The effect of number of measurements on the model updating performance is also examined in the study. The results are compared based on model class assessment and indicate that updating the prediction error variances as uncertain parameters at the model class level produces more robust results especially when the number of measurement is small.

Prediction of HDR quality by combining perceptually transformed display measurements with machine learning

NASA Astrophysics Data System (ADS)

Choudhury, Anustup; Farrell, Suzanne; Atkins, Robin; Daly, Scott

2017-09-01

We present an approach to predict overall HDR display quality as a function of key HDR display parameters. We first performed subjective experiments on a high quality HDR display that explored five key HDR display parameters: maximum luminance, minimum luminance, color gamut, bit-depth and local contrast. Subjects rated overall quality for different combinations of these display parameters. We explored two models | a physical model solely based on physically measured display characteristics and a perceptual model that transforms physical parameters using human vision system models. For the perceptual model, we use a family of metrics based on a recently published color volume model (ICT-CP), which consists of the PQ luminance non-linearity (ST2084) and LMS-based opponent color, as well as an estimate of the display point spread function. To predict overall visual quality, we apply linear regression and machine learning techniques such as Multilayer Perceptron, RBF and SVM networks. We use RMSE and Pearson/Spearman correlation coefficients to quantify performance. We found that the perceptual model is better at predicting subjective quality than the physical model and that SVM is better at prediction than linear regression. The significance and contribution of each display parameter was investigated. In addition, we found that combined parameters such as contrast do not improve prediction. Traditional perceptual models were also evaluated and we found that models based on the PQ non-linearity performed better.

Predictive performance models and multiple task performance

NASA Technical Reports Server (NTRS)

Wickens, Christopher D.; Larish, Inge; Contorer, Aaron

1989-01-01

Five models that predict how performance of multiple tasks will interact in complex task scenarios are discussed. The models are shown in terms of the assumptions they make about human operator divided attention. The different assumptions about attention are then empirically validated in a multitask helicopter flight simulation. It is concluded from this simulation that the most important assumption relates to the coding of demand level of different component tasks.

Prediction impact curve is a new measure integrating intervention effects in the evaluation of risk models.

PubMed

Campbell, William; Ganna, Andrea; Ingelsson, Erik; Janssens, A Cecile J W

2016-01-01

We propose a new measure of assessing the performance of risk models, the area under the prediction impact curve (auPIC), which quantifies the performance of risk models in terms of their average health impact in the population. Using simulated data, we explain how the prediction impact curve (PIC) estimates the percentage of events prevented when a risk model is used to assign high-risk individuals to an intervention. We apply the PIC to the Atherosclerosis Risk in Communities (ARIC) Study to illustrate its application toward prevention of coronary heart disease. We estimated that if the ARIC cohort received statins at baseline, 5% of events would be prevented when the risk model was evaluated at a cutoff threshold of 20% predicted risk compared to 1% when individuals were assigned to the intervention without the use of a model. By calculating the auPIC, we estimated that an average of 15% of events would be prevented when considering performance across the entire interval. We conclude that the PIC is a clinically meaningful measure for quantifying the expected health impact of risk models that supplements existing measures of model performance. Copyright © 2016 Elsevier Inc. All rights reserved.

A grey NGM(1,1, k) self-memory coupling prediction model for energy consumption prediction.

PubMed

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

2014-01-01

Energy consumption prediction is an important issue for governments, energy sector investors, and other related corporations. Although there are several prediction techniques, selection of the most appropriate technique is of vital importance. As for the approximate nonhomogeneous exponential data sequence often emerging in the energy system, a novel grey NGM(1,1, k) self-memory coupling prediction model is put forward in order to promote the predictive performance. It achieves organic integration of the self-memory principle of dynamic system and grey NGM(1,1, k) model. The traditional grey model's weakness as being sensitive to initial value can be overcome by the self-memory principle. In this study, total energy, coal, and electricity consumption of China is adopted for demonstration by using the proposed coupling prediction technique. The results show the superiority of NGM(1,1, k) self-memory coupling prediction model when compared with the results from the literature. Its excellent prediction performance lies in that the proposed coupling model can take full advantage of the systematic multitime historical data and catch the stochastic fluctuation tendency. This work also makes a significant contribution to the enrichment of grey prediction theory and the extension of its application span.

Using an external surrogate for predictor model training in real-time motion management of lung tumors.

PubMed

Rottmann, Joerg; Berbeco, Ross

2014-12-01

Precise prediction of respiratory motion is a prerequisite for real-time motion compensation techniques such as beam, dynamic couch, or dynamic multileaf collimator tracking. Collection of tumor motion data to train the prediction model is required for most algorithms. To avoid exposure of patients to additional dose from imaging during this procedure, the feasibility of training a linear respiratory motion prediction model with an external surrogate signal is investigated and its performance benchmarked against training the model with tumor positions directly. The authors implement a lung tumor motion prediction algorithm based on linear ridge regression that is suitable to overcome system latencies up to about 300 ms. Its performance is investigated on a data set of 91 patient breathing trajectories recorded from fiducial marker tracking during radiotherapy delivery to the lung of ten patients. The expected 3D geometric error is quantified as a function of predictor lookahead time, signal sampling frequency and history vector length. Additionally, adaptive model retraining is evaluated, i.e., repeatedly updating the prediction model after initial training. Training length for this is gradually increased with incoming (internal) data availability. To assess practical feasibility model calculation times as well as various minimum data lengths for retraining are evaluated. Relative performance of model training with external surrogate motion data versus tumor motion data is evaluated. However, an internal-external motion correlation model is not utilized, i.e., prediction is solely driven by internal motion in both cases. Similar prediction performance was achieved for training the model with external surrogate data versus internal (tumor motion) data. Adaptive model retraining can substantially boost performance in the case of external surrogate training while it has little impact for training with internal motion data. A minimum adaptive retraining data length of 8 s and history vector length of 3 s achieve maximal performance. Sampling frequency appears to have little impact on performance confirming previously published work. By using the linear predictor, a relative geometric 3D error reduction of about 50% was achieved (using adaptive retraining, a history vector length of 3 s and with results averaged over all investigated lookahead times and signal sampling frequencies). The absolute mean error could be reduced from (2.0 ± 1.6) mm when using no prediction at all to (0.9 ± 0.8) mm and (1.0 ± 0.9) mm when using the predictor trained with internal tumor motion training data and external surrogate motion training data, respectively (for a typical lookahead time of 250 ms and sampling frequency of 15 Hz). A linear prediction model can reduce latency induced tracking errors by an average of about 50% in real-time image guided radiotherapy systems with system latencies of up to 300 ms. Training a linear model for lung tumor motion prediction with an external surrogate signal alone is feasible and results in similar performance as training with (internal) tumor motion. Particularly for scenarios where motion data are extracted from fluoroscopic imaging with ionizing radiation, this may alleviate the need for additional imaging dose during the collection of model training data.

Analysis of the performance, emission and combustion characteristics of a turbocharged diesel engine fuelled with Jatropha curcas biodiesel-diesel blends using kernel-based extreme learning machine.

PubMed

Silitonga, Arridina Susan; Hassan, Masjuki Haji; Ong, Hwai Chyuan; Kusumo, Fitranto

2017-11-01

The purpose of this study is to investigate the performance, emission and combustion characteristics of a four-cylinder common-rail turbocharged diesel engine fuelled with Jatropha curcas biodiesel-diesel blends. A kernel-based extreme learning machine (KELM) model is developed in this study using MATLAB software in order to predict the performance, combustion and emission characteristics of the engine. To acquire the data for training and testing the KELM model, the engine speed was selected as the input parameter, whereas the performance, exhaust emissions and combustion characteristics were chosen as the output parameters of the KELM model. The performance, emissions and combustion characteristics predicted by the KELM model were validated by comparing the predicted data with the experimental data. The results show that the coefficient of determination of the parameters is within a range of 0.9805-0.9991 for both the KELM model and the experimental data. The mean absolute percentage error is within a range of 0.1259-2.3838. This study shows that KELM modelling is a useful technique in biodiesel production since it facilitates scientists and researchers to predict the performance, exhaust emissions and combustion characteristics of internal combustion engines with high accuracy.

Prediction of wastewater treatment plants performance based on artificial fish school neural network

NASA Astrophysics Data System (ADS)

Zhang, Ruicheng; Li, Chong

2011-10-01

A reliable model for wastewater treatment plant is essential in providing a tool for predicting its performance and to form a basis for controlling the operation of the process. This would minimize the operation costs and assess the stability of environmental balance. For the multi-variable, uncertainty, non-linear characteristics of the wastewater treatment system, an artificial fish school neural network prediction model is established standing on actual operation data in the wastewater treatment system. The model overcomes several disadvantages of the conventional BP neural network. The results of model calculation show that the predicted value can better match measured value, played an effect on simulating and predicting and be able to optimize the operation status. The establishment of the predicting model provides a simple and practical way for the operation and management in wastewater treatment plant, and has good research and engineering practical value.

Sensor fusion display evaluation using information integration models in enhanced/synthetic vision applications

NASA Technical Reports Server (NTRS)

Foyle, David C.

1993-01-01

Based on existing integration models in the psychological literature, an evaluation framework is developed to assess sensor fusion displays as might be implemented in an enhanced/synthetic vision system. The proposed evaluation framework for evaluating the operator's ability to use such systems is a normative approach: The pilot's performance with the sensor fusion image is compared to models' predictions based on the pilot's performance when viewing the original component sensor images prior to fusion. This allows for the determination as to when a sensor fusion system leads to: poorer performance than one of the original sensor displays, clearly an undesirable system in which the fused sensor system causes some distortion or interference; better performance than with either single sensor system alone, but at a sub-optimal level compared to model predictions; optimal performance compared to model predictions; or, super-optimal performance, which may occur if the operator were able to use some highly diagnostic 'emergent features' in the sensor fusion display, which were unavailable in the original sensor displays.

Predicting Power Outages Using Multi-Model Ensemble Forecasts

NASA Astrophysics Data System (ADS)

Cerrai, D.; Anagnostou, E. N.; Yang, J.; Astitha, M.

2017-12-01

Power outages affect every year millions of people in the United States, affecting the economy and conditioning the everyday life. An Outage Prediction Model (OPM) has been developed at the University of Connecticut for helping utilities to quickly restore outages and to limit their adverse consequences on the population. The OPM, operational since 2015, combines several non-parametric machine learning (ML) models that use historical weather storm simulations and high-resolution weather forecasts, satellite remote sensing data, and infrastructure and land cover data to predict the number and spatial distribution of power outages. A new methodology, developed for improving the outage model performances by combining weather- and soil-related variables using three different weather models (WRF 3.7, WRF 3.8 and RAMS/ICLAMS), will be presented in this study. First, we will present a performance evaluation of each model variable, by comparing historical weather analyses with station data or reanalysis over the entire storm data set. Hence, each variable of the new outage model version is extracted from the best performing weather model for that variable, and sensitivity tests are performed for investigating the most efficient variable combination for outage prediction purposes. Despite that the final variables combination is extracted from different weather models, this ensemble based on multi-weather forcing and multi-statistical model power outage prediction outperforms the currently operational OPM version that is based on a single weather forcing variable (WRF 3.7), because each model component is the closest to the actual atmospheric state.

Ant colony optimization algorithm for interpretable Bayesian classifiers combination: application to medical predictions.

PubMed

Bouktif, Salah; Hanna, Eileen Marie; Zaki, Nazar; Abu Khousa, Eman

2014-01-01

Prediction and classification techniques have been well studied by machine learning researchers and developed for several real-word problems. However, the level of acceptance and success of prediction models are still below expectation due to some difficulties such as the low performance of prediction models when they are applied in different environments. Such a problem has been addressed by many researchers, mainly from the machine learning community. A second problem, principally raised by model users in different communities, such as managers, economists, engineers, biologists, and medical practitioners, etc., is the prediction models' interpretability. The latter is the ability of a model to explain its predictions and exhibit the causality relationships between the inputs and the outputs. In the case of classification, a successful way to alleviate the low performance is to use ensemble classiers. It is an intuitive strategy to activate collaboration between different classifiers towards a better performance than individual classier. Unfortunately, ensemble classifiers method do not take into account the interpretability of the final classification outcome. It even worsens the original interpretability of the individual classifiers. In this paper we propose a novel implementation of classifiers combination approach that does not only promote the overall performance but also preserves the interpretability of the resulting model. We propose a solution based on Ant Colony Optimization and tailored for the case of Bayesian classifiers. We validate our proposed solution with case studies from medical domain namely, heart disease and Cardiotography-based predictions, problems where interpretability is critical to make appropriate clinical decisions. The datasets, Prediction Models and software tool together with supplementary materials are available at http://faculty.uaeu.ac.ae/salahb/ACO4BC.htm.

Utilizing uncoded consultation notes from electronic medical records for predictive modeling of colorectal cancer.

PubMed

Hoogendoorn, Mark; Szolovits, Peter; Moons, Leon M G; Numans, Mattijs E

2016-05-01

Machine learning techniques can be used to extract predictive models for diseases from electronic medical records (EMRs). However, the nature of EMRs makes it difficult to apply off-the-shelf machine learning techniques while still exploiting the rich content of the EMRs. In this paper, we explore the usage of a range of natural language processing (NLP) techniques to extract valuable predictors from uncoded consultation notes and study whether they can help to improve predictive performance. We study a number of existing techniques for the extraction of predictors from the consultation notes, namely a bag of words based approach and topic modeling. In addition, we develop a dedicated technique to match the uncoded consultation notes with a medical ontology. We apply these techniques as an extension to an existing pipeline to extract predictors from EMRs. We evaluate them in the context of predictive modeling for colorectal cancer (CRC), a disease known to be difficult to diagnose before performing an endoscopy. Our results show that we are able to extract useful information from the consultation notes. The predictive performance of the ontology-based extraction method moves significantly beyond the benchmark of age and gender alone (area under the receiver operating characteristic curve (AUC) of 0.870 versus 0.831). We also observe more accurate predictive models by adding features derived from processing the consultation notes compared to solely using coded data (AUC of 0.896 versus 0.882) although the difference is not significant. The extracted features from the notes are shown be equally predictive (i.e. there is no significant difference in performance) compared to the coded data of the consultations. It is possible to extract useful predictors from uncoded consultation notes that improve predictive performance. Techniques linking text to concepts in medical ontologies to derive these predictors are shown to perform best for predicting CRC in our EMR dataset. Copyright © 2016 Elsevier B.V. All rights reserved.

A computationally efficient modelling of laminar separation bubbles

NASA Technical Reports Server (NTRS)

Dini, Paolo; Maughmer, Mark D.

1989-01-01

The goal is to accurately predict the characteristics of the laminar separation bubble and its effects on airfoil performance. Toward this end, a computational model of the separation bubble was developed and incorporated into the Eppler and Somers airfoil design and analysis program. Thus far, the focus of the research was limited to the development of a model which can accurately predict situations in which the interaction between the bubble and the inviscid velocity distribution is weak, the so-called short bubble. A summary of the research performed in the past nine months is presented. The bubble model in its present form is then described. Lastly, the performance of this model in predicting bubble characteristics is shown for a few cases.

MQAPRank: improved global protein model quality assessment by learning-to-rank.

PubMed

Jing, Xiaoyang; Dong, Qiwen

2017-05-25

Protein structure prediction has achieved a lot of progress during the last few decades and a greater number of models for a certain sequence can be predicted. Consequently, assessing the qualities of predicted protein models in perspective is one of the key components of successful protein structure prediction. Over the past years, a number of methods have been developed to address this issue, which could be roughly divided into three categories: single methods, quasi-single methods and clustering (or consensus) methods. Although these methods achieve much success at different levels, accurate protein model quality assessment is still an open problem. Here, we present the MQAPRank, a global protein model quality assessment program based on learning-to-rank. The MQAPRank first sorts the decoy models by using single method based on learning-to-rank algorithm to indicate their relative qualities for the target protein. And then it takes the first five models as references to predict the qualities of other models by using average GDT_TS scores between reference models and other models. Benchmarked on CASP11 and 3DRobot datasets, the MQAPRank achieved better performances than other leading protein model quality assessment methods. Recently, the MQAPRank participated in the CASP12 under the group name FDUBio and achieved the state-of-the-art performances. The MQAPRank provides a convenient and powerful tool for protein model quality assessment with the state-of-the-art performances, it is useful for protein structure prediction and model quality assessment usages.

Benchmarking test of empirical root water uptake models

NASA Astrophysics Data System (ADS)

dos Santos, Marcos Alex; de Jong van Lier, Quirijn; van Dam, Jos C.; Freire Bezerra, Andre Herman

2017-01-01

Detailed physical models describing root water uptake (RWU) are an important tool for the prediction of RWU and crop transpiration, but the hydraulic parameters involved are hardly ever available, making them less attractive for many studies. Empirical models are more readily used because of their simplicity and the associated lower data requirements. The purpose of this study is to evaluate the capability of some empirical models to mimic the RWU distribution under varying environmental conditions predicted from numerical simulations with a detailed physical model. A review of some empirical models used as sub-models in ecohydrological models is presented, and alternative empirical RWU models are proposed. All these empirical models are analogous to the standard Feddes model, but differ in how RWU is partitioned over depth or how the transpiration reduction function is defined. The parameters of the empirical models are determined by inverse modelling of simulated depth-dependent RWU. The performance of the empirical models and their optimized empirical parameters depends on the scenario. The standard empirical Feddes model only performs well in scenarios with low root length density R, i.e. for scenarios with low RWU compensation. For medium and high R, the Feddes RWU model cannot mimic properly the root uptake dynamics as predicted by the physical model. The Jarvis RWU model in combination with the Feddes reduction function (JMf) only provides good predictions for low and medium R scenarios. For high R, it cannot mimic the uptake patterns predicted by the physical model. Incorporating a newly proposed reduction function into the Jarvis model improved RWU predictions. Regarding the ability of the models to predict plant transpiration, all models accounting for compensation show good performance. The Akaike information criterion (AIC) indicates that the Jarvis (2010) model (JMII), with no empirical parameters to be estimated, is the best model. The proposed models are better in predicting RWU patterns similar to the physical model. The statistical indices point to them as the best alternatives for mimicking RWU predictions of the physical model.

Use of mobile and passive badge air monitoring data for NOX and ozone air pollution spatial exposure prediction models.

PubMed

Xu, Wei; Riley, Erin A; Austin, Elena; Sasakura, Miyoko; Schaal, Lanae; Gould, Timothy R; Hartin, Kris; Simpson, Christopher D; Sampson, Paul D; Yost, Michael G; Larson, Timothy V; Xiu, Guangli; Vedal, Sverre

2017-03-01

Air pollution exposure prediction models can make use of many types of air monitoring data. Fixed location passive samples typically measure concentrations averaged over several days to weeks. Mobile monitoring data can generate near continuous concentration measurements. It is not known whether mobile monitoring data are suitable for generating well-performing exposure prediction models or how they compare with other types of monitoring data in generating exposure models. Measurements from fixed site passive samplers and mobile monitoring platform were made over a 2-week period in Baltimore in the summer and winter months in 2012. Performance of exposure prediction models for long-term nitrogen oxides (NO X ) and ozone (O 3 ) concentrations were compared using a state-of-the-art approach for model development based on land use regression (LUR) and geostatistical smoothing. Model performance was evaluated using leave-one-out cross-validation (LOOCV). Models performed well using the mobile peak traffic monitoring data for both NO X and O 3 , with LOOCV R 2 s of 0.70 and 0.71, respectively, in the summer, and 0.90 and 0.58, respectively, in the winter. Models using 2-week passive samples for NO X had LOOCV R 2 s of 0.60 and 0.65 in the summer and winter months, respectively. The passive badge sampling data were not adequate for developing models for O 3 . Mobile air monitoring data can be used to successfully build well-performing LUR exposure prediction models for NO X and O 3 and are a better source of data for these models than 2-week passive badge data.

Model Performance Evaluation and Scenario Analysis (MPESA)

EPA Pesticide Factsheets

Model Performance Evaluation and Scenario Analysis (MPESA) assesses the performance with which models predict time series data. The tool was developed Hydrological Simulation Program-Fortran (HSPF) and the Stormwater Management Model (SWMM)

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

Wosnik, Martin; Bachant, Pete; Neary, Vincent Sinclair

CACTUS, developed by Sandia National Laboratories, is an open-source code for the design and analysis of wind and hydrokinetic turbines. While it has undergone extensive validation for both vertical axis and horizontal axis wind turbines, and it has been demonstrated to accurately predict the performance of horizontal (axial-flow) hydrokinetic turbines, its ability to predict the performance of crossflow hydrokinetic turbines has yet to be tested. The present study addresses this problem by comparing the predicted performance curves derived from CACTUS simulations of the U.S. Department of Energy’s 1:6 scale reference model crossflow turbine to those derived by experimental measurements inmore » a tow tank using the same model turbine at the University of New Hampshire. It shows that CACTUS cannot accurately predict the performance of this crossflow turbine, raising concerns on its application to crossflow hydrokinetic turbines generally. The lack of quality data on NACA 0021 foil aerodynamic (hydrodynamic) characteristics over the wide range of angles of attack (AoA) and Reynolds numbers is identified as the main cause for poor model prediction. A comparison of several different NACA 0021 foil data sources, derived using both physical and numerical modeling experiments, indicates significant discrepancies at the high AoA experienced by foils on crossflow turbines. Users of CACTUS for crossflow hydrokinetic turbines are, therefore, advised to limit its application to higher tip speed ratios (lower AoA), and to carefully verify the reliability and accuracy of their foil data. Accurate empirical data on the aerodynamic characteristics of the foil is the greatest limitation to predicting performance for crossflow turbines with semi-empirical models like CACTUS. Future improvements of CACTUS for crossflow turbine performance prediction will require the development of accurate foil aerodynamic characteristic data sets within the appropriate ranges of Reynolds numbers and AoA.« less

Predicting survival of de novo metastatic breast cancer in Asian women: systematic review and validation study.

PubMed

Miao, Hui; Hartman, Mikael; Bhoo-Pathy, Nirmala; Lee, Soo-Chin; Taib, Nur Aishah; Tan, Ern-Yu; Chan, Patrick; Moons, Karel G M; Wong, Hoong-Seam; Goh, Jeremy; Rahim, Siti Mastura; Yip, Cheng-Har; Verkooijen, Helena M

2014-01-01

In Asia, up to 25% of breast cancer patients present with distant metastases at diagnosis. Given the heterogeneous survival probabilities of de novo metastatic breast cancer, individual outcome prediction is challenging. The aim of the study is to identify existing prognostic models for patients with de novo metastatic breast cancer and validate them in Asia. We performed a systematic review to identify prediction models for metastatic breast cancer. Models were validated in 642 women with de novo metastatic breast cancer registered between 2000 and 2010 in the Singapore Malaysia Hospital Based Breast Cancer Registry. Survival curves for low, intermediate and high-risk groups according to each prognostic score were compared by log-rank test and discrimination of the models was assessed by concordance statistic (C-statistic). We identified 16 prediction models, seven of which were for patients with brain metastases only. Performance status, estrogen receptor status, metastatic site(s) and disease-free interval were the most common predictors. We were able to validate nine prediction models. The capacity of the models to discriminate between poor and good survivors varied from poor to fair with C-statistics ranging from 0.50 (95% CI, 0.48-0.53) to 0.63 (95% CI, 0.60-0.66). The discriminatory performance of existing prediction models for de novo metastatic breast cancer in Asia is modest. Development of an Asian-specific prediction model is needed to improve prognostication and guide decision making.

Improving stability of prediction models based on correlated omics data by using network approaches.

PubMed

Tissier, Renaud; Houwing-Duistermaat, Jeanine; Rodríguez-Girondo, Mar

2018-01-01

Building prediction models based on complex omics datasets such as transcriptomics, proteomics, metabolomics remains a challenge in bioinformatics and biostatistics. Regularized regression techniques are typically used to deal with the high dimensionality of these datasets. However, due to the presence of correlation in the datasets, it is difficult to select the best model and application of these methods yields unstable results. We propose a novel strategy for model selection where the obtained models also perform well in terms of overall predictability. Several three step approaches are considered, where the steps are 1) network construction, 2) clustering to empirically derive modules or pathways, and 3) building a prediction model incorporating the information on the modules. For the first step, we use weighted correlation networks and Gaussian graphical modelling. Identification of groups of features is performed by hierarchical clustering. The grouping information is included in the prediction model by using group-based variable selection or group-specific penalization. We compare the performance of our new approaches with standard regularized regression via simulations. Based on these results we provide recommendations for selecting a strategy for building a prediction model given the specific goal of the analysis and the sizes of the datasets. Finally we illustrate the advantages of our approach by application of the methodology to two problems, namely prediction of body mass index in the DIetary, Lifestyle, and Genetic determinants of Obesity and Metabolic syndrome study (DILGOM) and prediction of response of each breast cancer cell line to treatment with specific drugs using a breast cancer cell lines pharmacogenomics dataset.

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.

Application of a High-Fidelity Icing Analysis Method to a Model-Scale Rotor in Forward Flight

NASA Technical Reports Server (NTRS)

Narducci, Robert; Orr, Stanley; Kreeger, Richard E.

2012-01-01

An icing analysis process involving the loose coupling of OVERFLOW-RCAS for rotor performance prediction and with LEWICE3D for thermal analysis and ice accretion is applied to a model-scale rotor for validation. The process offers high-fidelity rotor analysis for the noniced and iced rotor performance evaluation that accounts for the interaction of nonlinear aerodynamics with blade elastic deformations. Ice accumulation prediction also involves loosely coupled data exchanges between OVERFLOW and LEWICE3D to produce accurate ice shapes. Validation of the process uses data collected in the 1993 icing test involving Sikorsky's Powered Force Model. Non-iced and iced rotor performance predictions are compared to experimental measurements as are predicted ice shapes.

Modeling Heavy/Medium-Duty Fuel Consumption Based on Drive Cycle Properties

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

Wang, Lijuan; Duran, Adam; Gonder, Jeffrey

This paper presents multiple methods for predicting heavy/medium-duty vehicle fuel consumption based on driving cycle information. A polynomial model, a black box artificial neural net model, a polynomial neural network model, and a multivariate adaptive regression splines (MARS) model were developed and verified using data collected from chassis testing performed on a parcel delivery diesel truck operating over the Heavy Heavy-Duty Diesel Truck (HHDDT), City Suburban Heavy Vehicle Cycle (CSHVC), New York Composite Cycle (NYCC), and hydraulic hybrid vehicle (HHV) drive cycles. Each model was trained using one of four drive cycles as a training cycle and the other threemore » as testing cycles. By comparing the training and testing results, a representative training cycle was chosen and used to further tune each method. HHDDT as the training cycle gave the best predictive results, because HHDDT contains a variety of drive characteristics, such as high speed, acceleration, idling, and deceleration. Among the four model approaches, MARS gave the best predictive performance, with an average absolute percent error of -1.84% over the four chassis dynamometer drive cycles. To further evaluate the accuracy of the predictive models, the approaches were first applied to real-world data. MARS outperformed the other three approaches, providing an average absolute percent error of -2.2% of four real-world road segments. The MARS model performance was then compared to HHDDT, CSHVC, NYCC, and HHV drive cycles with the performance from Future Automotive System Technology Simulator (FASTSim). The results indicated that the MARS method achieved a comparative predictive performance with FASTSim.« less

Application of ANN and fuzzy logic algorithms for streamflow modelling of Savitri catchment

NASA Astrophysics Data System (ADS)

Kothari, Mahesh; Gharde, K. D.

2015-07-01

The streamflow prediction is an essentially important aspect of any watershed modelling. The black box models (soft computing techniques) have proven to be an efficient alternative to physical (traditional) methods for simulating streamflow and sediment yield of the catchments. The present study focusses on development of models using ANN and fuzzy logic (FL) algorithm for predicting the streamflow for catchment of Savitri River Basin. The input vector to these models were daily rainfall, mean daily evaporation, mean daily temperature and lag streamflow used. In the present study, 20 years (1992-2011) rainfall and other hydrological data were considered, of which 13 years (1992-2004) was for training and rest 7 years (2005-2011) for validation of the models. The mode performance was evaluated by R, RMSE, EV, CE, and MAD statistical parameters. It was found that, ANN model performance improved with increasing input vectors. The results with fuzzy logic models predict the streamflow with single input as rainfall better in comparison to multiple input vectors. While comparing both ANN and FL algorithms for prediction of streamflow, ANN model performance is quite superior.

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

Rottmann, Joerg; Berbeco, Ross

Purpose: Precise prediction of respiratory motion is a prerequisite for real-time motion compensation techniques such as beam, dynamic couch, or dynamic multileaf collimator tracking. Collection of tumor motion data to train the prediction model is required for most algorithms. To avoid exposure of patients to additional dose from imaging during this procedure, the feasibility of training a linear respiratory motion prediction model with an external surrogate signal is investigated and its performance benchmarked against training the model with tumor positions directly. Methods: The authors implement a lung tumor motion prediction algorithm based on linear ridge regression that is suitable tomore » overcome system latencies up to about 300 ms. Its performance is investigated on a data set of 91 patient breathing trajectories recorded from fiducial marker tracking during radiotherapy delivery to the lung of ten patients. The expected 3D geometric error is quantified as a function of predictor lookahead time, signal sampling frequency and history vector length. Additionally, adaptive model retraining is evaluated, i.e., repeatedly updating the prediction model after initial training. Training length for this is gradually increased with incoming (internal) data availability. To assess practical feasibility model calculation times as well as various minimum data lengths for retraining are evaluated. Relative performance of model training with external surrogate motion data versus tumor motion data is evaluated. However, an internal–external motion correlation model is not utilized, i.e., prediction is solely driven by internal motion in both cases. Results: Similar prediction performance was achieved for training the model with external surrogate data versus internal (tumor motion) data. Adaptive model retraining can substantially boost performance in the case of external surrogate training while it has little impact for training with internal motion data. A minimum adaptive retraining data length of 8 s and history vector length of 3 s achieve maximal performance. Sampling frequency appears to have little impact on performance confirming previously published work. By using the linear predictor, a relative geometric 3D error reduction of about 50% was achieved (using adaptive retraining, a history vector length of 3 s and with results averaged over all investigated lookahead times and signal sampling frequencies). The absolute mean error could be reduced from (2.0 ± 1.6) mm when using no prediction at all to (0.9 ± 0.8) mm and (1.0 ± 0.9) mm when using the predictor trained with internal tumor motion training data and external surrogate motion training data, respectively (for a typical lookahead time of 250 ms and sampling frequency of 15 Hz). Conclusions: A linear prediction model can reduce latency induced tracking errors by an average of about 50% in real-time image guided radiotherapy systems with system latencies of up to 300 ms. Training a linear model for lung tumor motion prediction with an external surrogate signal alone is feasible and results in similar performance as training with (internal) tumor motion. Particularly for scenarios where motion data are extracted from fluoroscopic imaging with ionizing radiation, this may alleviate the need for additional imaging dose during the collection of model training data.« less

Electrochemical carbon dioxide concentrator: Math model

NASA Technical Reports Server (NTRS)

Marshall, R. D.; Schubert, F. H.; Carlson, J. N.

1973-01-01

A steady state computer simulation model of an Electrochemical Depolarized Carbon Dioxide Concentrator (EDC) has been developed. The mathematical model combines EDC heat and mass balance equations with empirical correlations derived from experimental data to describe EDC performance as a function of the operating parameters involved. The model is capable of accurately predicting performance over EDC operating ranges. Model simulation results agree with the experimental data obtained over the prediction range.

Long-Term Post-CABG Survival: Performance of Clinical Risk Models Versus Actuarial Predictions.

PubMed

Carr, Brendan M; Romeiser, Jamie; Ruan, Joyce; Gupta, Sandeep; Seifert, Frank C; Zhu, Wei; Shroyer, A Laurie

2016-01-01

Clinical risk models are commonly used to predict short-term coronary artery bypass grafting (CABG) mortality but are less commonly used to predict long-term mortality. The added value of long-term mortality clinical risk models over traditional actuarial models has not been evaluated. To address this, the predictive performance of a long-term clinical risk model was compared with that of an actuarial model to identify the clinical variable(s) most responsible for any differences observed. Long-term mortality for 1028 CABG patients was estimated using the Hannan New York State clinical risk model and an actuarial model (based on age, gender, and race/ethnicity). Vital status was assessed using the Social Security Death Index. Observed/expected (O/E) ratios were calculated, and the models' predictive performances were compared using a nested c-index approach. Linear regression analyses identified the subgroup of risk factors driving the differences observed. Mortality rates were 3%, 9%, and 17% at one-, three-, and five years, respectively (median follow-up: five years). The clinical risk model provided more accurate predictions. Greater divergence between model estimates occurred with increasing long-term mortality risk, with baseline renal dysfunction identified as a particularly important driver of these differences. Long-term mortality clinical risk models provide enhanced predictive power compared to actuarial models. Using the Hannan risk model, a patient's long-term mortality risk can be accurately assessed and subgroups of higher-risk patients can be identified for enhanced follow-up care. More research appears warranted to refine long-term CABG clinical risk models. © 2015 The Authors. Journal of Cardiac Surgery Published by Wiley Periodicals, Inc.

Long‐Term Post‐CABG Survival: Performance of Clinical Risk Models Versus Actuarial Predictions

PubMed Central

Carr, Brendan M.; Romeiser, Jamie; Ruan, Joyce; Gupta, Sandeep; Seifert, Frank C.; Zhu, Wei

2015-01-01

Abstract Background/aim Clinical risk models are commonly used to predict short‐term coronary artery bypass grafting (CABG) mortality but are less commonly used to predict long‐term mortality. The added value of long‐term mortality clinical risk models over traditional actuarial models has not been evaluated. To address this, the predictive performance of a long‐term clinical risk model was compared with that of an actuarial model to identify the clinical variable(s) most responsible for any differences observed. Methods Long‐term mortality for 1028 CABG patients was estimated using the Hannan New York State clinical risk model and an actuarial model (based on age, gender, and race/ethnicity). Vital status was assessed using the Social Security Death Index. Observed/expected (O/E) ratios were calculated, and the models' predictive performances were compared using a nested c‐index approach. Linear regression analyses identified the subgroup of risk factors driving the differences observed. Results Mortality rates were 3%, 9%, and 17% at one‐, three‐, and five years, respectively (median follow‐up: five years). The clinical risk model provided more accurate predictions. Greater divergence between model estimates occurred with increasing long‐term mortality risk, with baseline renal dysfunction identified as a particularly important driver of these differences. Conclusions Long‐term mortality clinical risk models provide enhanced predictive power compared to actuarial models. Using the Hannan risk model, a patient's long‐term mortality risk can be accurately assessed and subgroups of higher‐risk patients can be identified for enhanced follow‐up care. More research appears warranted to refine long‐term CABG clinical risk models. doi: 10.1111/jocs.12665 (J Card Surg 2016;31:23–30) PMID:26543019

Probability-based collaborative filtering model for predicting gene-disease associations.

PubMed

Zeng, Xiangxiang; Ding, Ningxiang; Rodríguez-Patón, Alfonso; Zou, Quan

2017-12-28

Accurately predicting pathogenic human genes has been challenging in recent research. Considering extensive gene-disease data verified by biological experiments, we can apply computational methods to perform accurate predictions with reduced time and expenses. We propose a probability-based collaborative filtering model (PCFM) to predict pathogenic human genes. Several kinds of data sets, containing data of humans and data of other nonhuman species, are integrated in our model. Firstly, on the basis of a typical latent factorization model, we propose model I with an average heterogeneous regularization. Secondly, we develop modified model II with personal heterogeneous regularization to enhance the accuracy of aforementioned models. In this model, vector space similarity or Pearson correlation coefficient metrics and data on related species are also used. We compared the results of PCFM with the results of four state-of-arts approaches. The results show that PCFM performs better than other advanced approaches. PCFM model can be leveraged for predictions of disease genes, especially for new human genes or diseases with no known relationships.

Method for evaluation of predictive models of microwave ablation via post-procedural clinical imaging

NASA Astrophysics Data System (ADS)

Collins, Jarrod A.; Brown, Daniel; Kingham, T. Peter; Jarnagin, William R.; Miga, Michael I.; Clements, Logan W.

2015-03-01

Development of a clinically accurate predictive model of microwave ablation (MWA) procedures would represent a significant advancement and facilitate an implementation of patient-specific treatment planning to achieve optimal probe placement and ablation outcomes. While studies have been performed to evaluate predictive models of MWA, the ability to quantify the performance of predictive models via clinical data has been limited to comparing geometric measurements of the predicted and actual ablation zones. The accuracy of placement, as determined by the degree of spatial overlap between ablation zones, has not been achieved. In order to overcome this limitation, a method of evaluation is proposed where the actual location of the MWA antenna is tracked and recorded during the procedure via a surgical navigation system. Predictive models of the MWA are then computed using the known position of the antenna within the preoperative image space. Two different predictive MWA models were used for the preliminary evaluation of the proposed method: (1) a geometric model based on the labeling associated with the ablation antenna and (2) a 3-D finite element method based computational model of MWA using COMSOL. Given the follow-up tomographic images that are acquired at approximately 30 days after the procedure, a 3-D surface model of the necrotic zone was generated to represent the true ablation zone. A quantification of the overlap between the predicted ablation zones and the true ablation zone was performed after a rigid registration was computed between the pre- and post-procedural tomograms. While both model show significant overlap with the true ablation zone, these preliminary results suggest a slightly higher degree of overlap with the geometric model.

Climate change, species distribution models, and physiological performance metrics: predicting when biogeographic models are likely to fail.

PubMed

Woodin, Sarah A; Hilbish, Thomas J; Helmuth, Brian; Jones, Sierra J; Wethey, David S

2013-09-01

Modeling the biogeographic consequences of climate change requires confidence in model predictions under novel conditions. However, models often fail when extended to new locales, and such instances have been used as evidence of a change in physiological tolerance, that is, a fundamental niche shift. We explore an alternative explanation and propose a method for predicting the likelihood of failure based on physiological performance curves and environmental variance in the original and new environments. We define the transient event margin (TEM) as the gap between energetic performance failure, defined as CTmax, and the upper lethal limit, defined as LTmax. If TEM is large relative to environmental fluctuations, models will likely fail in new locales. If TEM is small relative to environmental fluctuations, models are likely to be robust for new locales, even when mechanism is unknown. Using temperature, we predict when biogeographic models are likely to fail and illustrate this with a case study. We suggest that failure is predictable from an understanding of how climate drives nonlethal physiological responses, but for many species such data have not been collected. Successful biogeographic forecasting thus depends on understanding when the mechanisms limiting distribution of a species will differ among geographic regions, or at different times, resulting in realized niche shifts. TEM allows prediction of the likelihood of such model failure.

Interactions of Team Mental Models and Monitoring Behaviors Predict Team Performance in Simulated Anesthesia Inductions

ERIC Educational Resources Information Center

Burtscher, Michael J.; Kolbe, Michaela; Wacker, Johannes; Manser, Tanja

2011-01-01

In the present study, we investigated how two team mental model properties (similarity vs. accuracy) and two forms of monitoring behavior (team vs. systems) interacted to predict team performance in anesthesia. In particular, we were interested in whether the relationship between monitoring behavior and team performance was moderated by team…

What Matters from Admissions? Identifying Success and Risk Among Canadian Dental Students.

PubMed

Plouffe, Rachel A; Hammond, Robert; Goldberg, Harvey A; Chahine, Saad

2018-05-01

The aims of this study were to determine whether different student profiles would emerge in terms of high and low GPA performance in each year of dental school and to investigate the utility of preadmissions variables in predicting performance and performance stability throughout each year of dental school. Data from 11 graduating cohorts (2004-14) at the Schulich School of Medicine & Dentistry, University of Western Ontario, Canada, were collected and analyzed using bivariate correlations, latent profile analysis, and hierarchical generalized linear models (HGLMs). The data analyzed were for 616 students in total (332 males and 284 females). Four models were developed to predict adequate and poor performance throughout each of four dental school years. An additional model was developed to predict student performance stability across time. Two separate student profiles reflecting high and low GPA performance across each year of dental school were identified, and scores on cognitive preadmissions variables differentially predicted the probability of grouping into high and low performance profiles. Students with higher pre-dental GPAs and DAT chemistry were most likely to remain stable in a high-performance group across each year of dental school. Overall, the findings suggest that selection committees should consider pre-dental GPA and DAT chemistry scores as important tools for predicting dental school performance and stability across time. This research is important in determining how to better predict success and failure in various areas of preclinical dentistry courses and to provide low-performing students with adequate academic assistance.

The OPALS Plan for Operations: Use of ISS Trajectory and Attitude Models in the OPALS Pointing Strategy

NASA Technical Reports Server (NTRS)

Abrahamson, Matthew J.; Oaida, Bogdan; Erkmen, Baris

2013-01-01

This paper will discuss the OPALS pointing strategy, focusing on incorporation of ISS trajectory and attitude models to build pointing predictions. Methods to extrapolate an ISS prediction based on past data will be discussed and will be compared to periodically published ISS predictions and Two-Line Element (TLE) predictions. The prediction performance will also be measured against GPS states available in telemetry. The performance of the pointing products will be compared to the allocated values in the OPALS pointing budget to assess compliance with requirements.

A dynamic multi-scale Markov model based methodology for remaining life prediction

NASA Astrophysics Data System (ADS)

Yan, Jihong; Guo, Chaozhong; Wang, Xing

2011-05-01

The ability to accurately predict the remaining life of partially degraded components is crucial in prognostics. In this paper, a performance degradation index is designed using multi-feature fusion techniques to represent deterioration severities of facilities. Based on this indicator, an improved Markov model is proposed for remaining life prediction. Fuzzy C-Means (FCM) algorithm is employed to perform state division for Markov model in order to avoid the uncertainty of state division caused by the hard division approach. Considering the influence of both historical and real time data, a dynamic prediction method is introduced into Markov model by a weighted coefficient. Multi-scale theory is employed to solve the state division problem of multi-sample prediction. Consequently, a dynamic multi-scale Markov model is constructed. An experiment is designed based on a Bently-RK4 rotor testbed to validate the dynamic multi-scale Markov model, experimental results illustrate the effectiveness of the methodology.

Prediction of chemo-response in serous ovarian cancer.

PubMed

Gonzalez Bosquet, Jesus; Newtson, Andreea M; Chung, Rebecca K; Thiel, Kristina W; Ginader, Timothy; Goodheart, Michael J; Leslie, Kimberly K; Smith, Brian J

2016-10-19

Nearly one-third of serous ovarian cancer (OVCA) patients will not respond to initial treatment with surgery and chemotherapy and die within one year of diagnosis. If patients who are unlikely to respond to current standard therapy can be identified up front, enhanced tumor analyses and treatment regimens could potentially be offered. Using the Cancer Genome Atlas (TCGA) serous OVCA database, we previously identified a robust molecular signature of 422-genes associated with chemo-response. Our objective was to test whether this signature is an accurate and sensitive predictor of chemo-response in serous OVCA. We first constructed prediction models to predict chemo-response using our previously described 422-gene signature that was associated with response to treatment in serous OVCA. Performance of all prediction models were measured with area under the curves (AUCs, a measure of the model's accuracy) and their respective confidence intervals (CIs). To optimize the prediction process, we determined which elements of the signature most contributed to chemo-response prediction. All prediction models were replicated and validated using six publicly available independent gene expression datasets. The 422-gene signature prediction models predicted chemo-response with AUCs of ~70 %. Optimization of prediction models identified the 34 most important genes in chemo-response prediction. These 34-gene models had improved performance, with AUCs approaching 80 %. Both 422-gene and 34-gene prediction models were replicated and validated in six independent datasets. These prediction models serve as the foundation for the future development and implementation of a diagnostic tool to predict response to chemotherapy for serous OVCA patients.

Multi-model ensemble hydrologic prediction using Bayesian model averaging

NASA Astrophysics Data System (ADS)

Duan, Qingyun; Ajami, Newsha K.; Gao, Xiaogang; Sorooshian, Soroosh

2007-05-01

Multi-model ensemble strategy is a means to exploit the diversity of skillful predictions from different models. This paper studies the use of Bayesian model averaging (BMA) scheme to develop more skillful and reliable probabilistic hydrologic predictions from multiple competing predictions made by several hydrologic models. BMA is a statistical procedure that infers consensus predictions by weighing individual predictions based on their probabilistic likelihood measures, with the better performing predictions receiving higher weights than the worse performing ones. Furthermore, BMA provides a more reliable description of the total predictive uncertainty than the original ensemble, leading to a sharper and better calibrated probability density function (PDF) for the probabilistic predictions. In this study, a nine-member ensemble of hydrologic predictions was used to test and evaluate the BMA scheme. This ensemble was generated by calibrating three different hydrologic models using three distinct objective functions. These objective functions were chosen in a way that forces the models to capture certain aspects of the hydrograph well (e.g., peaks, mid-flows and low flows). Two sets of numerical experiments were carried out on three test basins in the US to explore the best way of using the BMA scheme. In the first set, a single set of BMA weights was computed to obtain BMA predictions, while the second set employed multiple sets of weights, with distinct sets corresponding to different flow intervals. In both sets, the streamflow values were transformed using Box-Cox transformation to ensure that the probability distribution of the prediction errors is approximately Gaussian. A split sample approach was used to obtain and validate the BMA predictions. The test results showed that BMA scheme has the advantage of generating more skillful and equally reliable probabilistic predictions than original ensemble. The performance of the expected BMA predictions in terms of daily root mean square error (DRMS) and daily absolute mean error (DABS) is generally superior to that of the best individual predictions. Furthermore, the BMA predictions employing multiple sets of weights are generally better than those using single set of weights.

Image Discrimination Predictions of a Single Channel Model with Contrast Gain Control

NASA Technical Reports Server (NTRS)

Ahumada, Albert J., Jr.; Null, Cynthia H.

1995-01-01

Image discrimination models predict the number of just-noticeable-differences between two images. We report the predictions of a single channel model with contrast masking for a range of standard discrimination experiments. Despite its computational simplicity, this model has performed as well as a multiple channel model in an object detection task.

Choosing a model to predict hospital admission: an observational study of new variants of predictive models for case finding

PubMed Central

Billings, John; Georghiou, Theo; Blunt, Ian; Bardsley, Martin

2013-01-01

Objectives To test the performance of new variants of models to identify people at risk of an emergency hospital admission. We compared (1) the impact of using alternative data sources (hospital inpatient, A&E, outpatient and general practitioner (GP) electronic medical records) (2) the effects of local calibration on the performance of the models and (3) the choice of population denominators. Design Multivariate logistic regressions using person-level data adding each data set sequentially to test value of additional variables and denominators. Setting 5 Primary Care Trusts within England. Participants 1 836 099 people aged 18–95 registered with GPs on 31 July 2009. Main outcome measures Models to predict hospital admission and readmission were compared in terms of the positive predictive value and sensitivity for various risk strata and with the receiver operating curve C statistic. Results The addition of each data set showed moderate improvement in the number of patients identified with little or no loss of positive predictive value. However, even with inclusion of GP electronic medical record information, the algorithms identified only a small number of patients with no emergency hospital admissions in the previous 2 years. The model pooled across all sites performed almost as well as the models calibrated to local data from just one site. Using population denominators from GP registers led to better case finding. Conclusions These models provide a basis for wider application in the National Health Service. Each of the models examined produces reasonably robust performance and offers some predictive value. The addition of more complex data adds some value, but we were unable to conclude that pooled models performed less well than those in individual sites. Choices about model should be linked to the intervention design. Characteristics of patients identified by the algorithms provide useful information in the design/costing of intervention strategies to improve care coordination/outcomes for these patients. PMID:23980068

Lightweight ZERODUR: Validation of Mirror Performance and Mirror Modeling Predictions

NASA Technical Reports Server (NTRS)

Hull, Tony; Stahl, H. Philip; Westerhoff, Thomas; Valente, Martin; Brooks, Thomas; Eng, Ron

2017-01-01

Upcoming spaceborne missions, both moderate and large in scale, require extreme dimensional stability while relying both upon established lightweight mirror materials, and also upon accurate modeling methods to predict performance under varying boundary conditions. We describe tests, recently performed at NASA's XRCF chambers and laboratories in Huntsville Alabama, during which a 1.2 m diameter, f/1.2988% lightweighted SCHOTT lightweighted ZERODUR(TradeMark) mirror was tested for thermal stability under static loads in steps down to 230K. Test results are compared to model predictions, based upon recently published data on ZERODUR(TradeMark). In addition to monitoring the mirror surface for thermal perturbations in XRCF Thermal Vacuum tests, static load gravity deformations have been measured and compared to model predictions. Also the Modal Response(dynamic disturbance) was measured and compared to model. We will discuss the fabrication approach and optomechanical design of the ZERODUR(TradeMark) mirror substrate by SCHOTT, its optical preparation for test by Arizona Optical Systems (AOS). Summarize the outcome of NASA's XRCF tests and model validations

Lightweight ZERODUR®: Validation of mirror performance and mirror modeling predictions

NASA Astrophysics Data System (ADS)

Hull, Anthony B.; Stahl, H. Philip; Westerhoff, Thomas; Valente, Martin; Brooks, Thomas; Eng, Ron

2017-01-01

Upcoming spaceborne missions, both moderate and large in scale, require extreme dimensional stability while relying both upon established lightweight mirror materials, and also upon accurate modeling methods to predict performance under varying boundary conditions. We describe tests, recently performed at NASA’s XRCF chambers and laboratories in Huntsville Alabama, during which a 1.2m diameter, f/1.29 88% lightweighted SCHOTT lightweighted ZERODUR® mirror was tested for thermal stability under static loads in steps down to 230K. Test results are compared to model predictions, based upon recently published data on ZERODUR®. In addition to monitoring the mirror surface for thermal perturbations in XRCF Thermal Vacuum tests, static load gravity deformations have been measured and compared to model predictions. Also the Modal Response (dynamic disturbance) was measured and compared to model. We will discuss the fabrication approach and optomechanical design of the ZERODUR® mirror substrate by SCHOTT, its optical preparation for test by Arizona Optical Systems (AOS), and summarize the outcome of NASA’s XRCF tests and model validations.

Clinical Predictive Modeling Development and Deployment through FHIR Web Services.

PubMed

Khalilia, Mohammed; Choi, Myung; Henderson, Amelia; Iyengar, Sneha; Braunstein, Mark; Sun, Jimeng

2015-01-01

Clinical predictive modeling involves two challenging tasks: model development and model deployment. In this paper we demonstrate a software architecture for developing and deploying clinical predictive models using web services via the Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR) standard. The services enable model development using electronic health records (EHRs) stored in OMOP CDM databases and model deployment for scoring individual patients through FHIR resources. The MIMIC2 ICU dataset and a synthetic outpatient dataset were transformed into OMOP CDM databases for predictive model development. The resulting predictive models are deployed as FHIR resources, which receive requests of patient information, perform prediction against the deployed predictive model and respond with prediction scores. To assess the practicality of this approach we evaluated the response and prediction time of the FHIR modeling web services. We found the system to be reasonably fast with one second total response time per patient prediction.

Clinical Predictive Modeling Development and Deployment through FHIR Web Services

PubMed Central

Khalilia, Mohammed; Choi, Myung; Henderson, Amelia; Iyengar, Sneha; Braunstein, Mark; Sun, Jimeng

2015-01-01

Clinical predictive modeling involves two challenging tasks: model development and model deployment. In this paper we demonstrate a software architecture for developing and deploying clinical predictive models using web services via the Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR) standard. The services enable model development using electronic health records (EHRs) stored in OMOP CDM databases and model deployment for scoring individual patients through FHIR resources. The MIMIC2 ICU dataset and a synthetic outpatient dataset were transformed into OMOP CDM databases for predictive model development. The resulting predictive models are deployed as FHIR resources, which receive requests of patient information, perform prediction against the deployed predictive model and respond with prediction scores. To assess the practicality of this approach we evaluated the response and prediction time of the FHIR modeling web services. We found the system to be reasonably fast with one second total response time per patient prediction. PMID:26958207

Analysis of a virtual memory model for maintaining database views

NASA Technical Reports Server (NTRS)

Kinsley, Kathryn C.; Hughes, Charles E.

1992-01-01

This paper presents an analytical model for predicting the performance of a new support strategy for database views. This strategy, called the virtual method, is compared with traditional methods for supporting views. The analytical model's predictions of improved performance by the virtual method are then validated by comparing these results with those achieved in an experimental implementation.

A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS

NASA Astrophysics Data System (ADS)

Pradhan, Biswajeet

2013-02-01

The purpose of the present study is to compare the prediction performances of three different approaches such as decision tree (DT), support vector machine (SVM) and adaptive neuro-fuzzy inference system (ANFIS) for landslide susceptibility mapping at Penang Hill area, Malaysia. The necessary input parameters for the landslide susceptibility assessments were obtained from various sources. At first, landslide locations were identified by aerial photographs and field surveys and a total of 113 landslide locations were constructed. The study area contains 340,608 pixels while total 8403 pixels include landslides. The landslide inventory was randomly partitioned into two subsets: (1) part 1 that contains 50% (4000 landslide grid cells) was used in the training phase of the models; (2) part 2 is a validation dataset 50% (4000 landslide grid cells) for validation of three models and to confirm its accuracy. The digitally processed images of input parameters were combined in GIS. Finally, landslide susceptibility maps were produced, and the performances were assessed and discussed. Total fifteen landslide susceptibility maps were produced using DT, SVM and ANFIS based models, and the resultant maps were validated using the landslide locations. Prediction performances of these maps were checked by receiver operating characteristics (ROC) by using both success rate curve and prediction rate curve. The validation results showed that, area under the ROC curve for the fifteen models produced using DT, SVM and ANFIS varied from 0.8204 to 0.9421 for success rate curve and 0.7580 to 0.8307 for prediction rate curves, respectively. Moreover, the prediction curves revealed that model 5 of DT has slightly higher prediction performance (83.07), whereas the success rate showed that model 5 of ANFIS has better prediction (94.21) capability among all models. The results of this study showed that landslide susceptibility mapping in the Penang Hill area using the three approaches (e.g., DT, SVM and ANFIS) is viable. As far as the performance of the models are concerned, the results appeared to be quite satisfactory, i.e., the zones determined on the map being zones of relative susceptibility.

Modelling the multidimensional niche by linking functional traits to competitive performance

PubMed Central

Maynard, Daniel S.; Leonard, Kenneth E.; Drake, John M.; Hall, David W.; Crowther, Thomas W.; Bradford, Mark A.

2015-01-01

Linking competitive outcomes to environmental conditions is necessary for understanding species' distributions and responses to environmental change. Despite this importance, generalizable approaches for predicting competitive outcomes across abiotic gradients are lacking, driven largely by the highly complex and context-dependent nature of biotic interactions. Here, we present and empirically test a novel niche model that uses functional traits to model the niche space of organisms and predict competitive outcomes of co-occurring populations across multiple resource gradients. The model makes no assumptions about the underlying mode of competition and instead applies to those settings where relative competitive ability across environments correlates with a quantifiable performance metric. To test the model, a series of controlled microcosm experiments were conducted using genetically related strains of a widespread microbe. The model identified trait microevolution and performance differences among strains, with the predicted competitive ability of each organism mapped across a two-dimensional carbon and nitrogen resource space. Areas of coexistence and competitive dominance between strains were identified, and the predicted competitive outcomes were validated in approximately 95% of the pairings. By linking trait variation to competitive ability, our work demonstrates a generalizable approach for predicting and modelling competitive outcomes across changing environmental contexts. PMID:26136444

Selecting the minimum prediction base of historical data to perform 5-year predictions of the cancer burden: The GoF-optimal method.

PubMed

Valls, Joan; Castellà, Gerard; Dyba, Tadeusz; Clèries, Ramon

2015-06-01

Predicting the future burden of cancer is a key issue for health services planning, where a method for selecting the predictive model and the prediction base is a challenge. A method, named here Goodness-of-Fit optimal (GoF-optimal), is presented to determine the minimum prediction base of historical data to perform 5-year predictions of the number of new cancer cases or deaths. An empirical ex-post evaluation exercise for cancer mortality data in Spain and cancer incidence in Finland using simple linear and log-linear Poisson models was performed. Prediction bases were considered within the time periods 1951-2006 in Spain and 1975-2007 in Finland, and then predictions were made for 37 and 33 single years in these periods, respectively. The performance of three fixed different prediction bases (last 5, 10, and 20 years of historical data) was compared to that of the prediction base determined by the GoF-optimal method. The coverage (COV) of the 95% prediction interval and the discrepancy ratio (DR) were calculated to assess the success of the prediction. The results showed that (i) models using the prediction base selected through GoF-optimal method reached the highest COV and the lowest DR and (ii) the best alternative strategy to GoF-optimal was the one using the base of prediction of 5-years. The GoF-optimal approach can be used as a selection criterion in order to find an adequate base of prediction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Forecasting influenza-like illness dynamics for military populations using neural networks and social media

PubMed Central

Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D.

2017-01-01

This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in “real-time”) and forecasting (predicting the future) ILI dynamics in the 2011 – 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets. PMID:29244814

Forecasting influenza-like illness dynamics for military populations using neural networks and social media.

PubMed

Volkova, Svitlana; Ayton, Ellyn; Porterfield, Katherine; Corley, Courtney D

2017-01-01

This work is the first to take advantage of recurrent neural networks to predict influenza-like illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data and the state-of-the-art machine learning models, we build and evaluate the predictive power of neural network architectures based on Long Short Term Memory (LSTMs) units capable of nowcasting (predicting in "real-time") and forecasting (predicting the future) ILI dynamics in the 2011 - 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, embeddings, word ngrams, stylistic patterns, and communication behavior using hashtags and mentions. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks using a diverse set of evaluation metrics. Finally, we combine ILI and social media signals to build a joint neural network model for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance, specifically for military rather than general populations in 26 U.S. and six international locations., and analyze how model performance depends on the amount of social media data available per location. Our approach demonstrates several advantages: (a) Neural network architectures that rely on LSTM units trained on social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than stylistic and topic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns. (g) Model performance improves with more tweets available per geo-location e.g., the error gets lower and the Pearson score gets higher for locations with more tweets.

Predictive accuracy of a model of volatile anesthetic uptake.

PubMed

Kennedy, R Ross; French, Richard A; Spencer, Christopher

2002-12-01

A computer program that models anesthetic uptake and distribution has been in use in our department for 20 yr as a teaching tool. New anesthesia machines that electronically measure fresh gas flow rates and vaporizer settings allowed us to assess the performance of this model during clinical anesthesia. Gas flow, vaporizer settings, and end-tidal concentrations were collected from the anesthesia machine (Datex S/5 ADU) at 10-s intervals during 30 elective anesthetics. These were entered into the uptake model. Expired anesthetic vapor concentrations were calculated and compared with actual values as measured by the patient monitor (Datex AS/3). Sevoflurane was used in 16 patients and isoflurane in 14 patients. For all patients, the median performance error was -0.24%, the median absolute performance error was 13.7%, divergence was 2.3%/h, and wobble was 3.1%. There was no significant difference between sevoflurane and isoflurane. This model predicted expired concentrations well in these patients. These results are similar to those seen when comparing calculated and actual propofol concentrations in propofol infusion systems and meet published guidelines for the accuracy of models used in target-controlled anesthesia systems. This model may be useful for predicting responses to changes in fresh gas and vapor settings. We compared measured inhaled anesthetic concentrations with those predicted by a model. The method used for comparison has been used to study models of propofol administration. Our model predicts expired isoflurane and sevoflurane concentrations at least as well as common propofol models predict arterial propofol concentrations.

An evaluation of the predictive performance of distributional models for flora and fauna in north-east New South Wales.

PubMed

Pearce, J; Ferrier, S; Scotts, D

2001-06-01

To use models of species distributions effectively in conservation planning, it is important to determine the predictive accuracy of such models. Extensive modelling of the distribution of vascular plant and vertebrate fauna species within north-east New South Wales has been undertaken by linking field survey data to environmental and geographical predictors using logistic regression. These models have been used in the development of a comprehensive and adequate reserve system within the region. We evaluate the predictive accuracy of models for 153 small reptile, arboreal marsupial, diurnal bird and vascular plant species for which independent evaluation data were available. The predictive performance of each model was evaluated using the relative operating characteristic curve to measure discrimination capacity. Good discrimination ability implies that a model's predictions provide an acceptable index of species occurrence. The discrimination capacity of 89% of the models was significantly better than random, with 70% of the models providing high levels of discrimination. Predictions generated by this type of modelling therefore provide a reasonably sound basis for regional conservation planning. The discrimination ability of models was highest for the less mobile biological groups, particularly the vascular plants and small reptiles. In the case of diurnal birds, poor performing models tended to be for species which occur mainly within specific habitats not well sampled by either the model development or evaluation data, highly mobile species, species that are locally nomadic or those that display very broad habitat requirements. Particular care needs to be exercised when employing models for these types of species in conservation planning.

On the comparison of stochastic model predictive control strategies applied to a hydrogen-based microgrid

NASA Astrophysics Data System (ADS)

Velarde, P.; Valverde, L.; Maestre, J. M.; Ocampo-Martinez, C.; Bordons, C.

2017-03-01

In this paper, a performance comparison among three well-known stochastic model predictive control approaches, namely, multi-scenario, tree-based, and chance-constrained model predictive control is presented. To this end, three predictive controllers have been designed and implemented in a real renewable-hydrogen-based microgrid. The experimental set-up includes a PEM electrolyzer, lead-acid batteries, and a PEM fuel cell as main equipment. The real experimental results show significant differences from the plant components, mainly in terms of use of energy, for each implemented technique. Effectiveness, performance, advantages, and disadvantages of these techniques are extensively discussed and analyzed to give some valid criteria when selecting an appropriate stochastic predictive controller.

Thermal model of attic systems with radiant barriers

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

Wilkes, K.E.

This report summarizes the first phase of a project to model the thermal performance of radiant barriers. The objective of this phase of the project was to develop a refined model for the thermal performance of residential house attics, with and without radiant barriers, and to verify the model by comparing its predictions against selected existing experimental thermal performance data. Models for the thermal performance of attics with and without radiant barriers have been developed and implemented on an IBM PC/AT computer. The validity of the models has been tested by comparing their predictions with ceiling heat fluxes measured inmore » a number of laboratory and field experiments on attics with and without radiant barriers. Cumulative heat flows predicted by the models were usually within about 5 to 10 percent of measured values. In future phases of the project, the models for attic/radiant barrier performance will be coupled with a whole-house model and further comparisons with experimental data will be made. Following this, the models will be utilized to provide an initial assessment of the energy savings potential of radiant barriers in various configurations and under various climatic conditions. 38 refs., 14 figs., 22 tabs.« less

On the predictability of land surface fluxes from meteorological variables

NASA Astrophysics Data System (ADS)

Haughton, Ned; Abramowitz, Gab; Pitman, Andy J.

2018-01-01

Previous research has shown that land surface models (LSMs) are performing poorly when compared with relatively simple empirical models over a wide range of metrics and environments. Atmospheric driving data appear to provide information about land surface fluxes that LSMs are not fully utilising. Here, we further quantify the information available in the meteorological forcing data that are used by LSMs for predicting land surface fluxes, by interrogating FLUXNET data, and extending the benchmarking methodology used in previous experiments. We show that substantial performance improvement is possible for empirical models using meteorological data alone, with no explicit vegetation or soil properties, thus setting lower bounds on a priori expectations on LSM performance. The process also identifies key meteorological variables that provide predictive power. We provide an ensemble of empirical benchmarks that are simple to reproduce and provide a range of behaviours and predictive performance, acting as a baseline benchmark set for future studies. We reanalyse previously published LSM simulations and show that there is more diversity between LSMs than previously indicated, although it remains unclear why LSMs are broadly performing so much worse than simple empirical models.

Assessing the impact of land use change on hydrology by ensemble modelling (LUCHEM) II: Ensemble combinations and predictions

USGS Publications Warehouse

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

2009-01-01

This paper reports on a project to compare predictions from a range of catchment models applied to a mesoscale river basin in central Germany and to assess various ensemble predictions of catchment streamflow. The models encompass a large range in inherent complexity and input requirements. In approximate order of decreasing complexity, they are DHSVM, MIKE-SHE, TOPLATS, WASIM-ETH, SWAT, PRMS, SLURP, HBV, LASCAM and IHACRES. The models are calibrated twice using different sets of input data. The two predictions from each model are then combined by simple averaging to produce a single-model ensemble. The 10 resulting single-model ensembles are combined in various ways to produce multi-model ensemble predictions. Both the single-model ensembles and the multi-model ensembles are shown to give predictions that are generally superior to those of their respective constituent models, both during a 7-year calibration period and a 9-year validation period. This occurs despite a considerable disparity in performance of the individual models. Even the weakest of models is shown to contribute useful information to the ensembles they are part of. The best model combination methods are a trimmed mean (constructed using the central four or six predictions each day) and a weighted mean ensemble (with weights calculated from calibration performance) that places relatively large weights on the better performing models. Conditional ensembles, in which separate model weights are used in different system states (e.g. summer and winter, high and low flows) generally yield little improvement over the weighted mean ensemble. However a conditional ensemble that discriminates between rising and receding flows shows moderate improvement. An analysis of ensemble predictions shows that the best ensembles are not necessarily those containing the best individual models. Conversely, it appears that some models that predict well individually do not necessarily combine well with other models in multi-model ensembles. The reasons behind these observations may relate to the effects of the weighting schemes, non-stationarity of the climate series and possible cross-correlations between models. Crown Copyright ?? 2008.

Phenobarbital in intensive care unit pediatric population: predictive performances of population pharmacokinetic model.

PubMed

Marsot, Amélie; Michel, Fabrice; Chasseloup, Estelle; Paut, Olivier; Guilhaumou, Romain; Blin, Olivier

2017-10-01

An external evaluation of phenobarbital population pharmacokinetic model described by Marsot et al. was performed in pediatric intensive care unit. Model evaluation is an important issue for dose adjustment. This external evaluation should allow confirming the proposed dosage adaptation and extending these recommendations to the entire intensive care pediatric population. External evaluation of phenobarbital published population pharmacokinetic model of Marsot et al. was realized in a new retrospective dataset of 35 patients hospitalized in a pediatric intensive care unit. The published population pharmacokinetic model was implemented in nonmem 7.3. Predictive performance was assessed by quantifying bias and inaccuracy of model prediction. Normalized prediction distribution errors (NPDE) and visual predictive check (VPC) were also evaluated. A total of 35 infants were studied with a mean age of 33.5 weeks (range: 12 days-16 years) and a mean weight of 12.6 kg (range: 2.7-70.0 kg). The model predicted the observed phenobarbital concentrations with a reasonable bias and inaccuracy. The median prediction error was 3.03% (95% CI: -8.52 to 58.12%), and the median absolute prediction error was 26.20% (95% CI: 13.07-75.59%). No trends in NPDE and VPC were observed. The model previously proposed by Marsot et al. in neonates hospitalized in intensive care unit was externally validated for IV infusion administration. The model-based dosing regimen was extended in all pediatric intensive care unit to optimize treatment. Due to inter- and intravariability in pharmacokinetic model, this dosing regimen should be combined with therapeutic drug monitoring. © 2017 Société Française de Pharmacologie et de Thérapeutique.

Tank System Integrated Model: A Cryogenic Tank Performance Prediction Program

NASA Technical Reports Server (NTRS)

Bolshinskiy, L. G.; Hedayat, A.; Hastings, L. J.; Sutherlin, S. G.; Schnell, A. R.; Moder, J. P.

2017-01-01

Accurate predictions of the thermodynamic state of the cryogenic propellants, pressurization rate, and performance of pressure control techniques in cryogenic tanks are required for development of cryogenic fluid long-duration storage technology and planning for future space exploration missions. This Technical Memorandum (TM) presents the analytical tool, Tank System Integrated Model (TankSIM), which can be used for modeling pressure control and predicting the behavior of cryogenic propellant for long-term storage for future space missions. Utilizing TankSIM, the following processes can be modeled: tank self-pressurization, boiloff, ullage venting, mixing, and condensation on the tank wall. This TM also includes comparisons of TankSIM program predictions with the test data andexamples of multiphase mission calculations.

A Feature Fusion Based Forecasting Model for Financial Time Series

PubMed Central

Guo, Zhiqiang; Wang, Huaiqing; Liu, Quan; Yang, Jie

2014-01-01

Predicting the stock market has become an increasingly interesting research area for both researchers and investors, and many prediction models have been proposed. In these models, feature selection techniques are used to pre-process the raw data and remove noise. In this paper, a prediction model is constructed to forecast stock market behavior with the aid of independent component analysis, canonical correlation analysis, and a support vector machine. First, two types of features are extracted from the historical closing prices and 39 technical variables obtained by independent component analysis. Second, a canonical correlation analysis method is utilized to combine the two types of features and extract intrinsic features to improve the performance of the prediction model. Finally, a support vector machine is applied to forecast the next day's closing price. The proposed model is applied to the Shanghai stock market index and the Dow Jones index, and experimental results show that the proposed model performs better in the area of prediction than other two similar models. PMID:24971455

In-silico wear prediction for knee replacements--methodology and corroboration.

PubMed

Strickland, M A; Taylor, M

2009-07-22

The capability to predict in-vivo wear of knee replacements is a valuable pre-clinical analysis tool for implant designers. Traditionally, time-consuming experimental tests provided the principal means of investigating wear. Today, computational models offer an alternative. However, the validity of these models has not been demonstrated across a range of designs and test conditions, and several different formulas are in contention for estimating wear rates, limiting confidence in the predictive power of these in-silico models. This study collates and retrospectively simulates a wide range of experimental wear tests using fast rigid-body computational models with extant wear prediction algorithms, to assess the performance of current in-silico wear prediction tools. The number of tests corroborated gives a broader, more general assessment of the performance of these wear-prediction tools, and provides better estimates of the wear 'constants' used in computational models. High-speed rigid-body modelling allows a range of alternative algorithms to be evaluated. Whilst most cross-shear (CS)-based models perform comparably, the 'A/A+B' wear model appears to offer the best predictive power amongst existing wear algorithms. However, the range and variability of experimental data leaves considerable uncertainty in the results. More experimental data with reduced variability and more detailed reporting of studies will be necessary to corroborate these models with greater confidence. With simulation times reduced to only a few minutes, these models are ideally suited to large-volume 'design of experiment' or probabilistic studies (which are essential if pre-clinical assessment tools are to begin addressing the degree of variation observed clinically and in explanted components).

Correlation tracking study for meter-class solar telescope on space shuttle. [solar granulation

NASA Technical Reports Server (NTRS)

Smithson, R. C.; Tarbell, T. D.

1977-01-01

The theory and expected performance level of correlation trackers used to control the pointing of a solar telescope in space using white light granulation as a target were studied. Three specific trackers were modeled and their performance levels predicted for telescopes of various apertures. The performance of the computer model trackers on computer enhanced granulation photographs was evaluated. Parametric equations for predicting tracker performance are presented.

Developing a local least-squares support vector machines-based neuro-fuzzy model for nonlinear and chaotic time series prediction.

PubMed

Miranian, A; Abdollahzade, M

2013-02-01

Local modeling approaches, owing to their ability to model different operating regimes of nonlinear systems and processes by independent local models, seem appealing for modeling, identification, and prediction applications. In this paper, we propose a local neuro-fuzzy (LNF) approach based on the least-squares support vector machines (LSSVMs). The proposed LNF approach employs LSSVMs, which are powerful in modeling and predicting time series, as local models and uses hierarchical binary tree (HBT) learning algorithm for fast and efficient estimation of its parameters. The HBT algorithm heuristically partitions the input space into smaller subdomains by axis-orthogonal splits. In each partitioning, the validity functions automatically form a unity partition and therefore normalization side effects, e.g., reactivation, are prevented. Integration of LSSVMs into the LNF network as local models, along with the HBT learning algorithm, yield a high-performance approach for modeling and prediction of complex nonlinear time series. The proposed approach is applied to modeling and predictions of different nonlinear and chaotic real-world and hand-designed systems and time series. Analysis of the prediction results and comparisons with recent and old studies demonstrate the promising performance of the proposed LNF approach with the HBT learning algorithm for modeling and prediction of nonlinear and chaotic systems and time series.

Dynamic modeling of Listeria monocytogenes growth in pasteurized vanilla cream after postprocessing contamination.

PubMed

Panagou, Efstathios Z; Nychas, George-John E

2008-09-01

A product-specific model was developed and validated under dynamic temperature conditions for predicting the growth of Listeria monocytogenes in pasteurized vanilla cream, a traditional milk-based product. Model performance was also compared with Growth Predictor and Sym'Previus predictive microbiology software packages. Commercially prepared vanilla cream samples were artificially inoculated with a five-strain cocktail of L. monocytogenes, with an initial concentration of 102 CFU g(-1), and stored at 3, 5, 10, and 15 degrees C for 36 days. The growth kinetic parameters at each temperature were determined by the primary model of Baranyi and Roberts. The maximum specific growth rate (mu(max)) was further modeled as a function of temperature by means of a square root-type model. The performance of the model in predicting the growth of the pathogen under dynamic temperature conditions was based on two different temperature scenarios with periodic changes from 4 to 15 degrees C. Growth prediction for dynamic temperature profiles was based on the square root model and the differential equations of the Baranyi and Roberts model, which were numerically integrated with respect to time. Model performance was based on the bias factor (B(f)), the accuracy factor (A(f)), the goodness-of-fit index (GoF), and the percent relative errors between observed and predicted growth. The product-specific model developed in the present study accurately predicted the growth of L. monocytogenes under dynamic temperature conditions. The average values for the performance indices were 1.038, 1.068, and 0.397 for B(f), A(f), and GoF, respectively for both temperature scenarios assayed. Predictions from Growth Predictor and Sym'Previus overestimated pathogen growth. The average values of B(f), A(f), and GoF were 1.173, 1.174, 1.162, and 0.956, 1.115, 0.713 for [corrected] Growth Predictor and Sym'Previus, respectively.

Prediction of enteric methane production, yield, and intensity in dairy cattle using an intercontinental database.

PubMed

Niu, Mutian; Kebreab, Ermias; Hristov, Alexander N; Oh, Joonpyo; Arndt, Claudia; Bannink, André; Bayat, Ali R; Brito, André F; Boland, Tommy; Casper, David; Crompton, Les A; Dijkstra, Jan; Eugène, Maguy A; Garnsworthy, Phil C; Haque, Md Najmul; Hellwing, Anne L F; Huhtanen, Pekka; Kreuzer, Michael; Kuhla, Bjoern; Lund, Peter; Madsen, Jørgen; Martin, Cécile; McClelland, Shelby C; McGee, Mark; Moate, Peter J; Muetzel, Stefan; Muñoz, Camila; O'Kiely, Padraig; Peiren, Nico; Reynolds, Christopher K; Schwarm, Angela; Shingfield, Kevin J; Storlien, Tonje M; Weisbjerg, Martin R; Yáñez-Ruiz, David R; Yu, Zhongtang

2018-02-16

Enteric methane (CH 4 ) production from cattle contributes to global greenhouse gas emissions. Measurement of enteric CH 4 is complex, expensive, and impractical at large scales; therefore, models are commonly used to predict CH 4 production. However, building robust prediction models requires extensive data from animals under different management systems worldwide. The objectives of this study were to (1) collate a global database of enteric CH 4 production from individual lactating dairy cattle; (2) determine the availability of key variables for predicting enteric CH 4 production (g/day per cow), yield [g/kg dry matter intake (DMI)], and intensity (g/kg energy corrected milk) and their respective relationships; (3) develop intercontinental and regional models and cross-validate their performance; and (4) assess the trade-off between availability of on-farm inputs and CH 4 prediction accuracy. The intercontinental database covered Europe (EU), the United States (US), and Australia (AU). A sequential approach was taken by incrementally adding key variables to develop models with increasing complexity. Methane emissions were predicted by fitting linear mixed models. Within model categories, an intercontinental model with the most available independent variables performed best with root mean square prediction error (RMSPE) as a percentage of mean observed value of 16.6%, 14.7%, and 19.8% for intercontinental, EU, and United States regions, respectively. Less complex models requiring only DMI had predictive ability comparable to complex models. Enteric CH 4 production, yield, and intensity prediction models developed on an intercontinental basis had similar performance across regions, however, intercepts and slopes were different with implications for prediction. Revised CH 4 emission conversion factors for specific regions are required to improve CH 4 production estimates in national inventories. In conclusion, information on DMI is required for good prediction, and other factors such as dietary neutral detergent fiber (NDF) concentration, improve the prediction. For enteric CH 4 yield and intensity prediction, information on milk yield and composition is required for better estimation. © 2018 John Wiley & Sons Ltd.

A Multiscale Virtual Fabrication and Lattice Modeling Approach for the Fatigue Performance Prediction of Asphalt Concrete

NASA Astrophysics Data System (ADS)

Dehghan Banadaki, Arash

Predicting the ultimate performance of asphalt concrete under realistic loading conditions is the main key to developing better-performing materials, designing long-lasting pavements, and performing reliable lifecycle analysis for pavements. The fatigue performance of asphalt concrete depends on the mechanical properties of the constituent materials, namely asphalt binder and aggregate. This dependent link between performance and mechanical properties is extremely complex, and experimental techniques often are used to try to characterize the performance of hot mix asphalt. However, given the seemingly uncountable number of mixture designs and loading conditions, it is simply not economical to try to understand and characterize the material behavior solely by experimentation. It is well known that analytical and computational modeling methods can be combined with experimental techniques to reduce the costs associated with understanding and characterizing the mechanical behavior of the constituent materials. This study aims to develop a multiscale micromechanical lattice-based model to predict cracking in asphalt concrete using component material properties. The proposed algorithm, while capturing different phenomena for different scales, also minimizes the need for laboratory experiments. The developed methodology builds on a previously developed lattice model and the viscoelastic continuum damage model to link the component material properties to the mixture fatigue performance. The resulting lattice model is applied to predict the dynamic modulus mastercurves for different scales. A framework for capturing the so-called structuralization effects is introduced that significantly improves the accuracy of the modulus prediction. Furthermore, air voids are added to the model to help capture this important micromechanical feature that affects the fatigue performance of asphalt concrete as well as the modulus value. The effects of rate dependency are captured by implementing the viscoelastic fracture criterion. In the end, an efficient cyclic loading framework is developed to evaluate the damage accumulation in the material that is caused by long-sustained cyclic loads.

Prediction of Cognitive Performance and Subjective Sleepiness Using a Model of Arousal Dynamics.

PubMed

Postnova, Svetlana; Lockley, Steven W; Robinson, Peter A

2018-04-01

A model of arousal dynamics is applied to predict objective performance and subjective sleepiness measures, including lapses and reaction time on a visual Performance Vigilance Test (vPVT), performance on a mathematical addition task (ADD), and the Karolinska Sleepiness Scale (KSS). The arousal dynamics model is comprised of a physiologically based flip-flop switch between the wake- and sleep-active neuronal populations and a dynamic circadian oscillator, thus allowing prediction of sleep propensity. Published group-level experimental constant routine (CR) and forced desynchrony (FD) data are used to calibrate the model to predict performance and sleepiness. Only the studies using dim light (<15 lux) during alertness measurements and controlling for sleep and entrainment before the start of the protocol are selected for modeling. This is done to avoid the direct alerting effects of light and effects of prior sleep debt and circadian misalignment on the data. The results show that linear combination of circadian and homeostatic drives is sufficient to predict dynamics of a variety of sleepiness and performance measures during CR and FD protocols, with sleep-wake cycles ranging from 20 to 42.85 h and a 2:1 wake-to-sleep ratio. New metrics relating model outputs to performance and sleepiness data are developed and tested against group average outcomes from 7 (vPVT lapses), 5 (ADD), and 8 (KSS) experimental protocols, showing good quantitative and qualitative agreement with the data (root mean squared error of 0.38, 0.19, and 0.35, respectively). The weights of the homeostatic and circadian effects are found to be different between the measures, with KSS having stronger homeostatic influence compared with the objective measures of performance. Using FD data in addition to CR data allows us to challenge the model in conditions of both acute sleep deprivation and structured circadian misalignment, ensuring that the role of the circadian and homeostatic drives in performance is properly captured.

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

PubMed Central

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

2014-01-01

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

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

PubMed

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

2014-01-01

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

Human and Server Docking Prediction for CAPRI Round 30–35 Using LZerD with Combined Scoring Functions

PubMed Central

Peterson, Lenna X.; Kim, Hyungrae; Esquivel-Rodriguez, Juan; Roy, Amitava; Han, Xusi; Shin, Woong-Hee; Zhang, Jian; Terashi, Genki; Lee, Matt; Kihara, Daisuke

2016-01-01

We report the performance of protein-protein docking predictions by our group for recent rounds of the Critical Assessment of Prediction of Interactions (CAPRI), a community-wide assessment of state-of-the-art docking methods. Our prediction procedure uses a protein-protein docking program named LZerD developed in our group. LZerD represents a protein surface with 3D Zernike descriptors (3DZD), which are based on a mathematical series expansion of a 3D function. The appropriate soft representation of protein surface with 3DZD makes the method more tolerant to conformational change of proteins upon docking, which adds an advantage for unbound docking. Docking was guided by interface residue prediction performed with BindML and cons-PPISP as well as literature information when available. The generated docking models were ranked by a combination of scoring functions, including PRESCO, which evaluates the native-likeness of residues’ spatial environments in structure models. First, we discuss the overall performance of our group in the CAPRI prediction rounds and investigate the reasons for unsuccessful cases. Then, we examine the performance of several knowledge-based scoring functions and their combinations for ranking docking models. It was found that the quality of a pool of docking models generated by LZerD, i.e. whether or not the pool includes near-native models, can be predicted by the correlation of multiple scores. Although the current analysis used docking models generated by LZerD, findings on scoring functions are expected to be universally applicable to other docking methods. PMID:27654025

Vehicular traffic noise prediction using soft computing approach.

PubMed

Singh, Daljeet; Nigam, S P; Agrawal, V P; Kumar, Maneek

2016-12-01

A new approach for the development of vehicular traffic noise prediction models is presented. Four different soft computing methods, namely, Generalized Linear Model, Decision Trees, Random Forests and Neural Networks, have been used to develop models to predict the hourly equivalent continuous sound pressure level, Leq, at different locations in the Patiala city in India. The input variables include the traffic volume per hour, percentage of heavy vehicles and average speed of vehicles. The performance of the four models is compared on the basis of performance criteria of coefficient of determination, mean square error and accuracy. 10-fold cross validation is done to check the stability of the Random Forest model, which gave the best results. A t-test is performed to check the fit of the model with the field data. Copyright © 2016 Elsevier Ltd. All rights reserved.

Statistical modelling of networked human-automation performance using working memory capacity.

PubMed

Ahmed, Nisar; de Visser, Ewart; Shaw, Tyler; Mohamed-Ameen, Amira; Campbell, Mark; Parasuraman, Raja

2014-01-01

This study examines the challenging problem of modelling the interaction between individual attentional limitations and decision-making performance in networked human-automation system tasks. Analysis of real experimental data from a task involving networked supervision of multiple unmanned aerial vehicles by human participants shows that both task load and network message quality affect performance, but that these effects are modulated by individual differences in working memory (WM) capacity. These insights were used to assess three statistical approaches for modelling and making predictions with real experimental networked supervisory performance data: classical linear regression, non-parametric Gaussian processes and probabilistic Bayesian networks. It is shown that each of these approaches can help designers of networked human-automated systems cope with various uncertainties in order to accommodate future users by linking expected operating conditions and performance from real experimental data to observable cognitive traits like WM capacity. Practitioner Summary: Working memory (WM) capacity helps account for inter-individual variability in operator performance in networked unmanned aerial vehicle supervisory tasks. This is useful for reliable performance prediction near experimental conditions via linear models; robust statistical prediction beyond experimental conditions via Gaussian process models and probabilistic inference about unknown task conditions/WM capacities via Bayesian network models.

AEETES - A solar reflux receiver thermal performance numerical model

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

Hogan, R.E. Jr.

1994-02-01

Reflux solar receivers for dish-Stirling electric power generation systems are currently being investigated by several companies and laboratories. In support of these efforts, the AEETES thermal performance numerical model has been developed to predict thermal performance of pool-boiler and heat-pipe reflux receivers. The formulation of the AEETES numerical model, which is applicable to axisymmetric geometries with asymmetric incident fluxes, is presented in detail. Thermal efficiency predictions agree to within 4.1% with test data from on-sun tests of a pool-boiler reflux receiver. Predicted absorber and sidewall temperatures agree with thermocouple data to within 3.3 and 7.3%, respectively. The importance of accountingmore » for the asymmetric incident fluxes is demonstrated in comparisons with predictions using azimuthally averaged variables. The predicted receiver heat losses are characterized in terms of convective, solar radiative, and infrared radiative, and conductive heat transfer mechanisms.« less

Solar radio proxies for improved satellite orbit prediction

NASA Astrophysics Data System (ADS)

Yaya, Philippe; Hecker, Louis; Dudok de Wit, Thierry; Fèvre, Clémence Le; Bruinsma, Sean

2017-12-01

Specification and forecasting of solar drivers to thermosphere density models is critical for satellite orbit prediction and debris avoidance. Satellite operators routinely forecast orbits up to 30 days into the future. This requires forecasts of the drivers to these orbit prediction models such as the solar Extreme-UV (EUV) flux and geomagnetic activity. Most density models use the 10.7 cm radio flux (F10.7 index) as a proxy for solar EUV. However, daily measurements at other centimetric wavelengths have also been performed by the Nobeyama Radio Observatory (Japan) since the 1950's, thereby offering prospects for improving orbit modeling. Here we present a pre-operational service at the Collecte Localisation Satellites company that collects these different observations in one single homogeneous dataset and provides a 30 days forecast on a daily basis. Interpolation and preprocessing algorithms were developed to fill in missing data and remove anomalous values. We compared various empirical time series prediction techniques and selected a multi-wavelength non-recursive analogue neural network. The prediction of the 30 cm flux, and to a lesser extent that of the 10.7 cm flux, performs better than NOAA's present prediction of the 10.7 cm flux, especially during periods of high solar activity. In addition, we find that the DTM-2013 density model (Drag Temperature Model) performs better with (past and predicted) values of the 30 cm radio flux than with the 10.7 flux.

An integrated physiology model to study regional lung damage effects and the physiologic response

PubMed Central

2014-01-01

Background This work expands upon a previously developed exercise dynamic physiology model (DPM) with the addition of an anatomic pulmonary system in order to quantify the impact of lung damage on oxygen transport and physical performance decrement. Methods A pulmonary model is derived with an anatomic structure based on morphometric measurements, accounting for heterogeneous ventilation and perfusion observed experimentally. The model is incorporated into an existing exercise physiology model; the combined system is validated using human exercise data. Pulmonary damage from blast, blunt trauma, and chemical injury is quantified in the model based on lung fluid infiltration (edema) which reduces oxygen delivery to the blood. The pulmonary damage component is derived and calibrated based on published animal experiments; scaling laws are used to predict the human response to lung injury in terms of physical performance decrement. Results The augmented dynamic physiology model (DPM) accurately predicted the human response to hypoxia, altitude, and exercise observed experimentally. The pulmonary damage parameters (shunt and diffusing capacity reduction) were fit to experimental animal data obtained in blast, blunt trauma, and chemical damage studies which link lung damage to lung weight change; the model is able to predict the reduced oxygen delivery in damage conditions. The model accurately estimates physical performance reduction with pulmonary damage. Conclusions We have developed a physiologically-based mathematical model to predict performance decrement endpoints in the presence of thoracic damage; simulations can be extended to estimate human performance and escape in extreme situations. PMID:25044032

A prediction model for lift-fan simulator performance. M.S. Thesis - Cleveland State Univ.

NASA Technical Reports Server (NTRS)

Yuska, J. A.

1972-01-01

The performance characteristics of a model VTOL lift-fan simulator installed in a two-dimensional wing are presented. The lift-fan simulator consisted of a 15-inch diameter fan driven by a turbine contained in the fan hub. The performance of the lift-fan simulator was measured in two ways: (1) the calculated momentum thrust of the fan and turbine (total thrust loading), and (2) the axial-force measured on a load cell force balance (axial-force loading). Tests were conducted over a wide range of crossflow velocities, corrected tip speeds, and wing angle of attack. A prediction modeling technique was developed to help in analyzing the performance characteristics of lift-fan simulators. A multiple linear regression analysis technique is presented which calculates prediction model equations for the dependent variables.

Evaluation of global climate model on performances of precipitation simulation and prediction in the Huaihe River basin

NASA Astrophysics Data System (ADS)

Wu, Yenan; Zhong, Ping-an; Xu, Bin; Zhu, Feilin; Fu, Jisi

2017-06-01

Using climate models with high performance to predict the future climate changes can increase the reliability of results. In this paper, six kinds of global climate models that selected from the Coupled Model Intercomparison Project Phase 5 (CMIP5) under Representative Concentration Path (RCP) 4.5 scenarios were compared to the measured data during baseline period (1960-2000) and evaluate the simulation performance on precipitation. Since the results of single climate models are often biased and highly uncertain, we examine the back propagation (BP) neural network and arithmetic mean method in assembling the precipitation of multi models. The delta method was used to calibrate the result of single model and multimodel ensembles by arithmetic mean method (MME-AM) during the validation period (2001-2010) and the predicting period (2011-2100). We then use the single models and multimodel ensembles to predict the future precipitation process and spatial distribution. The result shows that BNU-ESM model has the highest simulation effect among all the single models. The multimodel assembled by BP neural network (MME-BP) has a good simulation performance on the annual average precipitation process and the deterministic coefficient during the validation period is 0.814. The simulation capability on spatial distribution of precipitation is: calibrated MME-AM > MME-BP > calibrated BNU-ESM. The future precipitation predicted by all models tends to increase as the time period increases. The order of average increase amplitude of each season is: winter > spring > summer > autumn. These findings can provide useful information for decision makers to make climate-related disaster mitigation plans.

A Grey NGM(1,1, k) Self-Memory Coupling Prediction Model for Energy Consumption Prediction

PubMed Central

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

2014-01-01

Energy consumption prediction is an important issue for governments, energy sector investors, and other related corporations. Although there are several prediction techniques, selection of the most appropriate technique is of vital importance. As for the approximate nonhomogeneous exponential data sequence often emerging in the energy system, a novel grey NGM(1,1, k) self-memory coupling prediction model is put forward in order to promote the predictive performance. It achieves organic integration of the self-memory principle of dynamic system and grey NGM(1,1, k) model. The traditional grey model's weakness as being sensitive to initial value can be overcome by the self-memory principle. In this study, total energy, coal, and electricity consumption of China is adopted for demonstration by using the proposed coupling prediction technique. The results show the superiority of NGM(1,1, k) self-memory coupling prediction model when compared with the results from the literature. Its excellent prediction performance lies in that the proposed coupling model can take full advantage of the systematic multitime historical data and catch the stochastic fluctuation tendency. This work also makes a significant contribution to the enrichment of grey prediction theory and the extension of its application span. PMID:25054174

A three-step approach for the derivation and validation of high-performing predictive models using an operational dataset: congestive heart failure readmission case study.

PubMed

AbdelRahman, Samir E; Zhang, Mingyuan; Bray, Bruce E; Kawamoto, Kensaku

2014-05-27

The aim of this study was to propose an analytical approach to develop high-performing predictive models for congestive heart failure (CHF) readmission using an operational dataset with incomplete records and changing data over time. Our analytical approach involves three steps: pre-processing, systematic model development, and risk factor analysis. For pre-processing, variables that were absent in >50% of records were removed. Moreover, the dataset was divided into a validation dataset and derivation datasets which were separated into three temporal subsets based on changes to the data over time. For systematic model development, using the different temporal datasets and the remaining explanatory variables, the models were developed by combining the use of various (i) statistical analyses to explore the relationships between the validation and the derivation datasets; (ii) adjustment methods for handling missing values; (iii) classifiers; (iv) feature selection methods; and (iv) discretization methods. We then selected the best derivation dataset and the models with the highest predictive performance. For risk factor analysis, factors in the highest-performing predictive models were analyzed and ranked using (i) statistical analyses of the best derivation dataset, (ii) feature rankers, and (iii) a newly developed algorithm to categorize risk factors as being strong, regular, or weak. The analysis dataset consisted of 2,787 CHF hospitalizations at University of Utah Health Care from January 2003 to June 2013. In this study, we used the complete-case analysis and mean-based imputation adjustment methods; the wrapper subset feature selection method; and four ranking strategies based on information gain, gain ratio, symmetrical uncertainty, and wrapper subset feature evaluators. The best-performing models resulted from the use of a complete-case analysis derivation dataset combined with the Class-Attribute Contingency Coefficient discretization method and a voting classifier which averaged the results of multi-nominal logistic regression and voting feature intervals classifiers. Of 42 final model risk factors, discharge disposition, discretized age, and indicators of anemia were the most significant. This model achieved a c-statistic of 86.8%. The proposed three-step analytical approach enhanced predictive model performance for CHF readmissions. It could potentially be leveraged to improve predictive model performance in other areas of clinical medicine.

Utilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome

PubMed Central

Hu, Danqing; Huang, Zhengxing; Chan, Tak-Ming; Dong, Wei; Lu, Xudong; Duan, Huilong

2016-01-01

Background: Clinical major adverse cardiovascular event (MACE) prediction of acute coronary syndrome (ACS) is important for a number of applications including physician decision support, quality of care assessment, and efficient healthcare service delivery on ACS patients. Admission records, as typical media to contain clinical information of patients at the early stage of their hospitalizations, provide significant potential to be explored for MACE prediction in a proactive manner. Methods: We propose a hybrid approach for MACE prediction by utilizing a large volume of admission records. Firstly, both a rule-based medical language processing method and a machine learning method (i.e., Conditional Random Fields (CRFs)) are developed to extract essential patient features from unstructured admission records. After that, state-of-the-art supervised machine learning algorithms are applied to construct MACE prediction models from data. Results: We comparatively evaluate the performance of the proposed approach on a real clinical dataset consisting of 2930 ACS patient samples collected from a Chinese hospital. Our best model achieved 72% AUC in MACE prediction. In comparison of the performance between our models and two well-known ACS risk score tools, i.e., GRACE and TIMI, our learned models obtain better performances with a significant margin. Conclusions: Experimental results reveal that our approach can obtain competitive performance in MACE prediction. The comparison of classifiers indicates the proposed approach has a competitive generality with datasets extracted by different feature extraction methods. Furthermore, our MACE prediction model obtained a significant improvement by comparison with both GRACE and TIMI. It indicates that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations. PMID:27649220

Long-term particulate matter modeling for health effect studies in California - Part 1: Model performance on temporal and spatial variations

NASA Astrophysics Data System (ADS)

Hu, J.; Zhang, H.; Ying, Q.; Chen, S.-H.; Vandenberghe, F.; Kleeman, M. J.

2015-03-01

For the first time, a ~ decadal (9 years from 2000 to 2008) air quality model simulation with 4 km horizontal resolution over populated regions and daily time resolution has been conducted for California to provide air quality data for health effect studies. Model predictions are compared to measurements to evaluate the accuracy of the simulation with an emphasis on spatial and temporal variations that could be used in epidemiology studies. Better model performance is found at longer averaging times, suggesting that model results with averaging times ≥ 1 month should be the first to be considered in epidemiological studies. The UCD/CIT model predicts spatial and temporal variations in the concentrations of O3, PM2.5, elemental carbon (EC), organic carbon (OC), nitrate, and ammonium that meet standard modeling performance criteria when compared to monthly-averaged measurements. Predicted sulfate concentrations do not meet target performance metrics due to missing sulfur sources in the emissions. Predicted seasonal and annual variations of PM2.5, EC, OC, nitrate, and ammonium have mean fractional biases that meet the model performance criteria in 95, 100, 71, 73, and 92% of the simulated months, respectively. The base data set provides an improvement for predicted population exposure to PM concentrations in California compared to exposures estimated by central site monitors operated 1 day out of every 3 days at a few urban locations. Uncertainties in the model predictions arise from several issues. Incomplete understanding of secondary organic aerosol formation mechanisms leads to OC bias in the model results in summertime but does not affect OC predictions in winter when concentrations are typically highest. The CO and NO (species dominated by mobile emissions) results reveal temporal and spatial uncertainties associated with the mobile emissions generated by the EMFAC 2007 model. The WRF model tends to overpredict wind speed during stagnation events, leading to underpredictions of high PM concentrations, usually in winter months. The WRF model also generally underpredicts relative humidity, resulting in less particulate nitrate formation, especially during winter months. These limitations must be recognized when using data in health studies. All model results included in the current manuscript can be downloaded free of charge at http://faculty.engineering.ucdavis.edu/kleeman/ .

A Multiple Agent Model of Human Performance in Automated Air Traffic Control and Flight Management Operations

NASA Technical Reports Server (NTRS)

Corker, Kevin; Pisanich, Gregory; Condon, Gregory W. (Technical Monitor)

1995-01-01

A predictive model of human operator performance (flight crew and air traffic control (ATC)) has been developed and applied in order to evaluate the impact of automation developments in flight management and air traffic control. The model is used to predict the performance of a two person flight crew and the ATC operators generating and responding to clearances aided by the Center TRACON Automation System (CTAS). The purpose of the modeling is to support evaluation and design of automated aids for flight management and airspace management and to predict required changes in procedure both air and ground in response to advancing automation in both domains. Additional information is contained in the original extended abstract.

Analysis of Free Modeling Predictions by RBO Aleph in CASP11

PubMed Central

Mabrouk, Mahmoud; Werner, Tim; Schneider, Michael; Putz, Ines; Brock, Oliver

2015-01-01

The CASP experiment is a biannual benchmark for assessing protein structure prediction methods. In CASP11, RBO Aleph ranked as one of the top-performing automated servers in the free modeling category. This category consists of targets for which structural templates are not easily retrievable. We analyze the performance of RBO Aleph and show that its success in CASP was a result of its ab initio structure prediction protocol. A detailed analysis of this protocol demonstrates that two components unique to our method greatly contributed to prediction quality: residue–residue contact prediction by EPC-map and contact–guided conformational space search by model-based search (MBS). Interestingly, our analysis also points to a possible fundamental problem in evaluating the performance of protein structure prediction methods: Improvements in components of the method do not necessarily lead to improvements of the entire method. This points to the fact that these components interact in ways that are poorly understood. This problem, if indeed true, represents a significant obstacle to community-wide progress. PMID:26492194

Evaluating diagnosis-based risk-adjustment methods in a population with spinal cord dysfunction.

PubMed

Warner, Grace; Hoenig, Helen; Montez, Maria; Wang, Fei; Rosen, Amy

2004-02-01

To examine performance of models in predicting health care utilization for individuals with spinal cord dysfunction. Regression models compared 2 diagnosis-based risk-adjustment methods, the adjusted clinical groups (ACGs) and diagnostic cost groups (DCGs). To improve prediction, we added to our model: (1) spinal cord dysfunction-specific diagnostic information, (2) limitations in self-care function, and (3) both 1 and 2. Models were replicated in 3 populations. Samples from 3 populations: (1) 40% of veterans using Veterans Health Administration services in fiscal year 1997 (FY97) (N=1,046,803), (2) veteran sample with spinal cord dysfunction identified by codes from the International Statistical Classification of Diseases, 9th Revision, Clinical Modifications (N=7666), and (3) veteran sample identified in Veterans Affairs Spinal Cord Dysfunction Registry (N=5888). Not applicable. Inpatient, outpatient, and total days of care in FY97. The DCG models (R(2) range,.22-.38) performed better than ACG models (R(2) range,.04-.34) for all outcomes. Spinal cord dysfunction-specific diagnostic information improved prediction more in the ACG model than in the DCG model (R(2) range for ACG,.14-.34; R(2) range for DCG,.24-.38). Information on self-care function slightly improved performance (R(2) range increased from 0 to.04). The DCG risk-adjustment models predicted health care utilization better than ACG models. ACG model prediction was improved by adding information.

A probabilistic and adaptive approach to modeling performance of pavement infrastructure

DOT National Transportation Integrated Search

2007-08-01

Accurate prediction of pavement performance is critical to pavement management agencies. Reliable and accurate predictions of pavement infrastructure performance can save significant amounts of money for pavement infrastructure management agencies th...

Predicting Survival of De Novo Metastatic Breast Cancer in Asian Women: Systematic Review and Validation Study

PubMed Central

Miao, Hui; Hartman, Mikael; Bhoo-Pathy, Nirmala; Lee, Soo-Chin; Taib, Nur Aishah; Tan, Ern-Yu; Chan, Patrick; Moons, Karel G. M.; Wong, Hoong-Seam; Goh, Jeremy; Rahim, Siti Mastura; Yip, Cheng-Har; Verkooijen, Helena M.

2014-01-01

Background In Asia, up to 25% of breast cancer patients present with distant metastases at diagnosis. Given the heterogeneous survival probabilities of de novo metastatic breast cancer, individual outcome prediction is challenging. The aim of the study is to identify existing prognostic models for patients with de novo metastatic breast cancer and validate them in Asia. Materials and Methods We performed a systematic review to identify prediction models for metastatic breast cancer. Models were validated in 642 women with de novo metastatic breast cancer registered between 2000 and 2010 in the Singapore Malaysia Hospital Based Breast Cancer Registry. Survival curves for low, intermediate and high-risk groups according to each prognostic score were compared by log-rank test and discrimination of the models was assessed by concordance statistic (C-statistic). Results We identified 16 prediction models, seven of which were for patients with brain metastases only. Performance status, estrogen receptor status, metastatic site(s) and disease-free interval were the most common predictors. We were able to validate nine prediction models. The capacity of the models to discriminate between poor and good survivors varied from poor to fair with C-statistics ranging from 0.50 (95% CI, 0.48–0.53) to 0.63 (95% CI, 0.60–0.66). Conclusion The discriminatory performance of existing prediction models for de novo metastatic breast cancer in Asia is modest. Development of an Asian-specific prediction model is needed to improve prognostication and guide decision making. PMID:24695692

Predicting performance of power converters operating with switching frequencies in the vicinity of 100 kHZ

NASA Technical Reports Server (NTRS)

Bahler, D. D.; Owen, H. A., Jr.; Wilson, T. G.

1978-01-01

A model describing the turning-on period of a power switching transistor in an energy storage voltage step-up converter is presented. Comparisons between an experimental layout and the circuit model during the turning-on interval demonstrate the ability of the model to closely predict the effects of circuit topology on the performance of the converter. A phenomenon of particular importance that is observed in the experimental circuits and is predicted by the model is the deleterious feedback effect of the parasitic emitter lead inductance on the base current waveform during the turning-on interval.

Does Rational Selection of Training and Test Sets Improve the Outcome of QSAR Modeling?

EPA Science Inventory

Prior to using a quantitative structure activity relationship (QSAR) model for external predictions, its predictive power should be established and validated. In the absence of a true external dataset, the best way to validate the predictive ability of a model is to perform its s...

Improved Fuzzy Modelling to Predict the Academic Performance of Distance Education Students

ERIC Educational Resources Information Center

Yildiz, Osman; Bal, Abdullah; Gulsecen, Sevinc

2013-01-01

It is essential to predict distance education students' year-end academic performance early during the course of the semester and to take precautions using such prediction-based information. This will, in particular, help enhance their academic performance and, therefore, improve the overall educational quality. The present study was on the…

Testing Bayesian and heuristic predictions of mass judgments of colliding objects

PubMed Central

Sanborn, Adam N.

2014-01-01

Mass judgments of colliding objects have been used to explore people's understanding of the physical world because they are ecologically relevant, yet people display biases that are most easily explained by a small set of heuristics. Recent work has challenged the heuristic explanation, by producing the same biases from a model that copes with perceptual uncertainty by using Bayesian inference with a prior based on the correct combination rules from Newtonian mechanics (noisy Newton). Here I test the predictions of the leading heuristic model (Gilden and Proffitt, 1989) against the noisy Newton model using a novel manipulation of the standard mass judgment task: making one of the objects invisible post-collision. The noisy Newton model uses the remaining information to predict above-chance performance, while the leading heuristic model predicts chance performance when one or the other final velocity is occluded. An experiment using two different types of occlusion showed better-than-chance performance and response patterns that followed the predictions of the noisy Newton model. The results demonstrate that people can make sensible physical judgments even when information critical for the judgment is missing, and that a Bayesian model can serve as a guide in these situations. Possible algorithmic-level accounts of this task that more closely correspond to the noisy Newton model are explored. PMID:25206345

External validation of the Garvan nomograms for predicting absolute fracture risk: the Tromsø study.

PubMed

Ahmed, Luai A; Nguyen, Nguyen D; Bjørnerem, Åshild; Joakimsen, Ragnar M; Jørgensen, Lone; Størmer, Jan; Bliuc, Dana; Center, Jacqueline R; Eisman, John A; Nguyen, Tuan V; Emaus, Nina

2014-01-01

Absolute risk estimation is a preferred approach for assessing fracture risk and treatment decision making. This study aimed to evaluate and validate the predictive performance of the Garvan Fracture Risk Calculator in a Norwegian cohort. The analysis included 1637 women and 1355 aged 60+ years from the Tromsø study. All incident fragility fractures between 2001 and 2009 were registered. The predicted probabilities of non-vertebral osteoporotic and hip fractures were determined using models with and without BMD. The discrimination and calibration of the models were assessed. Reclassification analysis was used to compare the models performance. The incidence of osteoporotic and hip fracture was 31.5 and 8.6 per 1000 population in women, respectively; in men the corresponding incidence was 12.2 and 5.1. The predicted 5-year and 10-year probability of fractures was consistently higher in the fracture group than the non-fracture group for all models. The 10-year predicted probabilities of hip fracture in those with fracture was 2.8 (women) to 3.1 times (men) higher than those without fracture. There was a close agreement between predicted and observed risk in both sexes and up to the fifth quintile. Among those in the highest quintile of risk, the models over-estimated the risk of fracture. Models with BMD performed better than models with body weight in correct classification of risk in individuals with and without fracture. The overall net decrease in reclassification of the model with weight compared to the model with BMD was 10.6% (p = 0.008) in women and 17.2% (p = 0.001) in men for osteoporotic fractures, and 13.3% (p = 0.07) in women and 17.5% (p = 0.09) in men for hip fracture. The Garvan Fracture Risk Calculator is valid and clinically useful in identifying individuals at high risk of fracture. The models with BMD performed better than those with body weight in fracture risk prediction.

A two-model hydrologic ensemble prediction of hydrograph: case study from the upper Nysa Klodzka river basin (SW Poland)

NASA Astrophysics Data System (ADS)

Niedzielski, Tomasz; Mizinski, Bartlomiej

2016-04-01

The HydroProg system has been elaborated in frame of the research project no. 2011/01/D/ST10/04171 of the National Science Centre of Poland and is steadily producing multimodel ensemble predictions of hydrograph in real time. Although there are six ensemble members available at present, the longest record of predictions and their statistics is available for two data-based models (uni- and multivariate autoregressive models). Thus, we consider 3-hour predictions of water levels, with lead times ranging from 15 to 180 minutes, computed every 15 minutes since August 2013 for the Nysa Klodzka basin (SW Poland) using the two approaches and their two-model ensemble. Since the launch of the HydroProg system there have been 12 high flow episodes, and the objective of this work is to present the performance of the two-model ensemble in the process of forecasting these events. For a sake of brevity, we limit our investigation to a single gauge located at the Nysa Klodzka river in the town of Klodzko, which is centrally located in the studied basin. We identified certain regular scenarios of how the models perform in predicting the high flows in Klodzko. At the initial phase of the high flow, well before the rising limb of hydrograph, the two-model ensemble is found to provide the most skilful prognoses of water levels. However, while forecasting the rising limb of hydrograph, either the two-model solution or the vector autoregressive model offers the best predictive performance. In addition, it is hypothesized that along with the development of the rising limb phase, the vector autoregression becomes the most skilful approach amongst the scrutinized ones. Our simple two-model exercise confirms that multimodel hydrologic ensemble predictions cannot be treated as universal solutions suitable for forecasting the entire high flow event, but their superior performance may hold only for certain phases of a high flow.

Evaluation of procedures for prediction of unconventional gas in the presence of geologic trends

USGS Publications Warehouse

Attanasi, E.D.; Coburn, T.C.

2009-01-01

This study extends the application of local spatial nonparametric prediction models to the estimation of recoverable gas volumes in continuous-type gas plays to regimes where there is a single geologic trend. A transformation is presented, originally proposed by Tomczak, that offsets the distortions caused by the trend. This article reports on numerical experiments that compare predictive and classification performance of the local nonparametric prediction models based on the transformation with models based on Euclidean distance. The transformation offers improvement in average root mean square error when the trend is not severely misspecified. Because of the local nature of the models, even those based on Euclidean distance in the presence of trends are reasonably robust. The tests based on other model performance metrics such as prediction error associated with the high-grade tracts and the ability of the models to identify sites with the largest gas volumes also demonstrate the robustness of both local modeling approaches. ?? International Association for Mathematical Geology 2009.

Application of Support Vector Machine to Forex Monitoring

NASA Astrophysics Data System (ADS)

Kamruzzaman, Joarder; Sarker, Ruhul A.

Previous studies have demonstrated superior performance of artificial neural network (ANN) based forex forecasting models over traditional regression models. This paper applies support vector machines to build a forecasting model from the historical data using six simple technical indicators and presents a comparison with an ANN based model trained by scaled conjugate gradient (SCG) learning algorithm. The models are evaluated and compared on the basis of five commonly used performance metrics that measure closeness of prediction as well as correctness in directional change. Forecasting results of six different currencies against Australian dollar reveal superior performance of SVM model using simple linear kernel over ANN-SCG model in terms of all the evaluation metrics. The effect of SVM parameter selection on prediction performance is also investigated and analyzed.

Twelve-month, 12 km resolution North American WRF-Chem v3.4 air quality simulation: performance evaluation

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

Tessum, C. W.; Hill, J. D.; Marshall, J. D.

We present results from and evaluate the performance of a 12-month, 12 km horizontal resolution year 2005 air pollution simulation for the contiguous United States using the WRF-Chem (Weather Research and Forecasting with Chemistry) meteorology and chemical transport model (CTM). We employ the 2005 US National Emissions Inventory, the Regional Atmospheric Chemistry Mechanism (RACM), and the Modal Aerosol Dynamics Model for Europe (MADE) with a volatility basis set (VBS) secondary aerosol module. Overall, model performance is comparable to contemporary modeling efforts used for regulatory and health-effects analysis, with an annual average daytime ozone (O 3) mean fractional bias (MFB) ofmore » 12% and an annual average fine particulate matter (PM 2.5) MFB of −1%. WRF-Chem, as configured here, tends to overpredict total PM 2.5 at some high concentration locations and generally overpredicts average 24 h O 3 concentrations. Performance is better at predicting daytime-average and daily peak O 3 concentrations, which are more relevant for regulatory and health effects analyses relative to annual average values. Predictive performance for PM 2.5 subspecies is mixed: the model overpredicts particulate sulfate (MFB = 36%), underpredicts particulate nitrate (MFB = −110%) and organic carbon (MFB = −29%), and relatively accurately predicts particulate ammonium (MFB = 3%) and elemental carbon (MFB = 3%), so that the accuracy in total PM 2.5 predictions is to some extent a function of offsetting over- and underpredictions of PM 2.5 subspecies. Model predictive performance for PM 2.5 and its subspecies is in general worse in winter and in the western US than in other seasons and regions, suggesting spatial and temporal opportunities for future WRF-Chem model development and evaluation.« less

Twelve-month, 12 km resolution North American WRF-Chem v3.4 air quality simulation: performance evaluation

DOE PAGES

Tessum, C. W.; Hill, J. D.; Marshall, J. D.

2015-04-07

We present results from and evaluate the performance of a 12-month, 12 km horizontal resolution year 2005 air pollution simulation for the contiguous United States using the WRF-Chem (Weather Research and Forecasting with Chemistry) meteorology and chemical transport model (CTM). We employ the 2005 US National Emissions Inventory, the Regional Atmospheric Chemistry Mechanism (RACM), and the Modal Aerosol Dynamics Model for Europe (MADE) with a volatility basis set (VBS) secondary aerosol module. Overall, model performance is comparable to contemporary modeling efforts used for regulatory and health-effects analysis, with an annual average daytime ozone (O 3) mean fractional bias (MFB) ofmore » 12% and an annual average fine particulate matter (PM 2.5) MFB of −1%. WRF-Chem, as configured here, tends to overpredict total PM 2.5 at some high concentration locations and generally overpredicts average 24 h O 3 concentrations. Performance is better at predicting daytime-average and daily peak O 3 concentrations, which are more relevant for regulatory and health effects analyses relative to annual average values. Predictive performance for PM 2.5 subspecies is mixed: the model overpredicts particulate sulfate (MFB = 36%), underpredicts particulate nitrate (MFB = −110%) and organic carbon (MFB = −29%), and relatively accurately predicts particulate ammonium (MFB = 3%) and elemental carbon (MFB = 3%), so that the accuracy in total PM 2.5 predictions is to some extent a function of offsetting over- and underpredictions of PM 2.5 subspecies. Model predictive performance for PM 2.5 and its subspecies is in general worse in winter and in the western US than in other seasons and regions, suggesting spatial and temporal opportunities for future WRF-Chem model development and evaluation.« less

Evaluation of Turbulence-Model Performance as Applied to Jet-Noise Prediction

NASA Technical Reports Server (NTRS)

Woodruff, S. L.; Seiner, J. M.; Hussaini, M. Y.; Erlebacher, G.

1998-01-01

The accurate prediction of jet noise is possible only if the jet flow field can be predicted accurately. Predictions for the mean velocity and turbulence quantities in the jet flowfield are typically the product of a Reynolds-averaged Navier-Stokes solver coupled with a turbulence model. To evaluate the effectiveness of solvers and turbulence models in predicting those quantities most important to jet noise prediction, two CFD codes and several turbulence models were applied to a jet configuration over a range of jet temperatures for which experimental data is available.

Prospective validation of pathologic complete response models in rectal cancer: Transferability and reproducibility.

PubMed

van Soest, Johan; Meldolesi, Elisa; van Stiphout, Ruud; Gatta, Roberto; Damiani, Andrea; Valentini, Vincenzo; Lambin, Philippe; Dekker, Andre

2017-09-01

Multiple models have been developed to predict pathologic complete response (pCR) in locally advanced rectal cancer patients. Unfortunately, validation of these models normally omit the implications of cohort differences on prediction model performance. In this work, we will perform a prospective validation of three pCR models, including information whether this validation will target transferability or reproducibility (cohort differences) of the given models. We applied a novel methodology, the cohort differences model, to predict whether a patient belongs to the training or to the validation cohort. If the cohort differences model performs well, it would suggest a large difference in cohort characteristics meaning we would validate the transferability of the model rather than reproducibility. We tested our method in a prospective validation of three existing models for pCR prediction in 154 patients. Our results showed a large difference between training and validation cohort for one of the three tested models [Area under the Receiver Operating Curve (AUC) cohort differences model: 0.85], signaling the validation leans towards transferability. Two out of three models had a lower AUC for validation (0.66 and 0.58), one model showed a higher AUC in the validation cohort (0.70). We have successfully applied a new methodology in the validation of three prediction models, which allows us to indicate if a validation targeted transferability (large differences between training/validation cohort) or reproducibility (small cohort differences). © 2017 American Association of Physicists in Medicine.

Applying mathematical models to predict resident physician performance and alertness on traditional and novel work schedules.

PubMed

Klerman, Elizabeth B; Beckett, Scott A; Landrigan, Christopher P

2016-09-13

In 2011 the U.S. Accreditation Council for Graduate Medical Education began limiting first year resident physicians (interns) to shifts of ≤16 consecutive hours. Controversy persists regarding the effectiveness of this policy for reducing errors and accidents while promoting education and patient care. Using a mathematical model of the effects of circadian rhythms and length of time awake on objective performance and subjective alertness, we quantitatively compared predictions for traditional intern schedules to those that limit work to ≤ 16 consecutive hours. We simulated two traditional schedules and three novel schedules using the mathematical model. The traditional schedules had extended duration work shifts (≥24 h) with overnight work shifts every second shift (including every third night, Q3) or every third shift (including every fourth night, Q4) night; the novel schedules had two different cross-cover (XC) night team schedules (XC-V1 and XC-V2) and a Rapid Cycle Rotation (RCR) schedule. Predicted objective performance and subjective alertness for each work shift were computed for each individual's schedule within a team and then combined for the team as a whole. Our primary outcome was the amount of time within a work shift during which a team's model-predicted objective performance and subjective alertness were lower than that expected after 16 or 24 h of continuous wake in an otherwise rested individual. The model predicted fewer hours with poor performance and alertness, especially during night-time work hours, for all three novel schedules than for either the traditional Q3 or Q4 schedules. Three proposed schedules that eliminate extended shifts may improve performance and alertness compared with traditional Q3 or Q4 schedules. Predicted times of worse performance and alertness were at night, which is also a time when supervision of trainees is lower. Mathematical modeling provides a quantitative comparison approach with potential to aid residency programs in schedule analysis and redesign.

Research and development on performance models of thermal imaging systems

NASA Astrophysics Data System (ADS)

Wang, Ji-hui; Jin, Wei-qi; Wang, Xia; Cheng, Yi-nan

2009-07-01

Traditional ACQUIRE models perform the discrimination tasks of detection (target orientation, recognition and identification) for military target based upon minimum resolvable temperature difference (MRTD) and Johnson criteria for thermal imaging systems (TIS). Johnson criteria is generally pessimistic for performance predict of sampled imager with the development of focal plane array (FPA) detectors and digital image process technology. Triangle orientation discrimination threshold (TOD) model, minimum temperature difference perceived (MTDP)/ thermal range model (TRM3) Model and target task performance (TTP) metric have been developed to predict the performance of sampled imager, especially TTP metric can provides better accuracy than the Johnson criteria. In this paper, the performance models above are described; channel width metrics have been presented to describe the synthesis performance including modulate translate function (MTF) channel width for high signal noise to ration (SNR) optoelectronic imaging systems and MRTD channel width for low SNR TIS; the under resolvable questions for performance assessment of TIS are indicated; last, the development direction of performance models for TIS are discussed.

A computational cognitive model of self-efficacy and daily adherence in mHealth.

PubMed

Pirolli, Peter

2016-12-01

Mobile health (mHealth) applications provide an excellent opportunity for collecting rich, fine-grained data necessary for understanding and predicting day-to-day health behavior change dynamics. A computational predictive model (ACT-R-DStress) is presented and fit to individual daily adherence in 28-day mHealth exercise programs. The ACT-R-DStress model refines the psychological construct of self-efficacy. To explain and predict the dynamics of self-efficacy and predict individual performance of targeted behaviors, the self-efficacy construct is implemented as a theory-based neurocognitive simulation of the interaction of behavioral goals, memories of past experiences, and behavioral performance.

Single non-invasive model to diagnose non-alcoholic fatty liver disease (NAFLD) and non-alcoholic steatohepatitis (NASH).

PubMed

Otgonsuren, Munkhzul; Estep, Michael J; Hossain, Nayeem; Younossi, Elena; Frost, Spencer; Henry, Linda; Hunt, Sharon; Fang, Yun; Goodman, Zachary; Younossi, Zobair M

2014-12-01

Non-alcoholic steatohepatitis (NASH) is the progressive form of non-alcoholic fatty liver disease (NAFLD). A liver biopsy is considered the "gold standard" for diagnosing/staging NASH. Identification of NAFLD/NASH using non-invasive tools is important for intervention. The study aims were to: develop/validate the predictive performance of a non-invasive model (index of NASH [ION]); assess the performance of a recognized non-invasive model (fatty liver index [FLI]) compared with ION for NAFLD diagnosis; determine which non-invasive model (FLI, ION, or NAFLD fibrosis score [NFS]) performed best in predicting age-adjusted mortality. From the National Health and Nutrition Examination Survey III database, anthropometric, clinical, ultrasound, laboratory, and mortality data were obtained (n = 4458; n = 861 [19.3%] NAFLD by ultrasound) and used to develop the ION model, and then to compare the ION and FLI models for NAFLD diagnosis. For validation and diagnosis of NASH, liver biopsy data were used (n = 152). Age-adjusted Cox proportional hazard modeling estimated the association among the three non-invasive tests (FLI, ION, and NFS) and mortality. FLI's threshold score > 60 and ION's threshold score > 22 had similar specificity (FLI = 80% vs ION = 82%) for NAFLD diagnosis; FLI < 30 (80% sensitivity) and ION < 11 (81% sensitivity) excluded NAFLD. An ION score > 50 predicted histological NASH (92% specificity); the FLI model did not predict NASH or mortality. The ION model was best in predicting cardiovascular/diabetes-related mortality; NFS predicted overall or diabetes-related mortality. The ION model was superior in predicting NASH and mortality compared with the FLI model. Studies are needed to validate ION. © 2014 Journal of Gastroenterology and Hepatology Foundation and Wiley Publishing Asia Pty Ltd.

Predicting Pilot Error in Nextgen: Pilot Performance Modeling and Validation Efforts

NASA Technical Reports Server (NTRS)

Wickens, Christopher; Sebok, Angelia; Gore, Brian; Hooey, Becky

2012-01-01

We review 25 articles presenting 5 general classes of computational models to predict pilot error. This more targeted review is placed within the context of the broader review of computational models of pilot cognition and performance, including such aspects as models of situation awareness or pilot-automation interaction. Particular emphasis is placed on the degree of validation of such models against empirical pilot data, and the relevance of the modeling and validation efforts to Next Gen technology and procedures.

Computer-Assisted Decision Support for Student Admissions Based on Their Predicted Academic Performance.

PubMed

Muratov, Eugene; Lewis, Margaret; Fourches, Denis; Tropsha, Alexander; Cox, Wendy C

2017-04-01

Objective. To develop predictive computational models forecasting the academic performance of students in the didactic-rich portion of a doctor of pharmacy (PharmD) curriculum as admission-assisting tools. Methods. All PharmD candidates over three admission cycles were divided into two groups: those who completed the PharmD program with a GPA ≥ 3; and the remaining candidates. Random Forest machine learning technique was used to develop a binary classification model based on 11 pre-admission parameters. Results. Robust and externally predictive models were developed that had particularly high overall accuracy of 77% for candidates with high or low academic performance. These multivariate models were highly accurate in predicting these groups to those obtained using undergraduate GPA and composite PCAT scores only. Conclusion. The models developed in this study can be used to improve the admission process as preliminary filters and thus quickly identify candidates who are likely to be successful in the PharmD curriculum.

An Application to the Prediction of LOD Change Based on General Regression Neural Network

NASA Astrophysics Data System (ADS)

Zhang, X. H.; Wang, Q. J.; Zhu, J. J.; Zhang, H.

2011-07-01

Traditional prediction of the LOD (length of day) change was based on linear models, such as the least square model and the autoregressive technique, etc. Due to the complex non-linear features of the LOD variation, the performances of the linear model predictors are not fully satisfactory. This paper applies a non-linear neural network - general regression neural network (GRNN) model to forecast the LOD change, and the results are analyzed and compared with those obtained with the back propagation neural network and other models. The comparison shows that the performance of the GRNN model in the prediction of the LOD change is efficient and feasible.

Prediction Of The Expected Safety Performance Of Rural Two-Lane Highways

DOT National Transportation Integrated Search

2000-12-01

This report presents an algorithm for predicting the safety performance of a rural two-lane highway. The accident prediction algorithm consists of base models and accident modification factors for both roadway segments and at-grade intersections on r...

Parameterization of the InVEST Crop Pollination Model to spatially predict abundance of wild blueberry (Vaccinium angustifolium Aiton) native bee pollinators in Maine, USA

USGS Publications Warehouse

Groff, Shannon C.; Loftin, Cynthia S.; Drummond, Frank; Bushmann, Sara; McGill, Brian J.

2016-01-01

Non-native honeybees historically have been managed for crop pollination, however, recent population declines draw attention to pollination services provided by native bees. We applied the InVEST Crop Pollination model, developed to predict native bee abundance from habitat resources, in Maine's wild blueberry crop landscape. We evaluated model performance with parameters informed by four approaches: 1) expert opinion; 2) sensitivity analysis; 3) sensitivity analysis informed model optimization; and, 4) simulated annealing (uninformed) model optimization. Uninformed optimization improved model performance by 29% compared to expert opinion-informed model, while sensitivity-analysis informed optimization improved model performance by 54%. This suggests that expert opinion may not result in the best parameter values for the InVEST model. The proportion of deciduous/mixed forest within 2000 m of a blueberry field also reliably predicted native bee abundance in blueberry fields, however, the InVEST model provides an efficient tool to estimate bee abundance beyond the field perimeter.

Feature Extraction of Event-Related Potentials Using Wavelets: An Application to Human Performance Monitoring

NASA Technical Reports Server (NTRS)

Trejo, Leonard J.; Shensa, Mark J.; Remington, Roger W. (Technical Monitor)

1998-01-01

This report describes the development and evaluation of mathematical models for predicting human performance from discrete wavelet transforms (DWT) of event-related potentials (ERP) elicited by task-relevant stimuli. The DWT was compared to principal components analysis (PCA) for representation of ERPs in linear regression and neural network models developed to predict a composite measure of human signal detection performance. Linear regression models based on coefficients of the decimated DWT predicted signal detection performance with half as many f ree parameters as comparable models based on PCA scores. In addition, the DWT-based models were more resistant to model degradation due to over-fitting than PCA-based models. Feed-forward neural networks were trained using the backpropagation,-, algorithm to predict signal detection performance based on raw ERPs, PCA scores, or high-power coefficients of the DWT. Neural networks based on high-power DWT coefficients trained with fewer iterations, generalized to new data better, and were more resistant to overfitting than networks based on raw ERPs. Networks based on PCA scores did not generalize to new data as well as either the DWT network or the raw ERP network. The results show that wavelet expansions represent the ERP efficiently and extract behaviorally important features for use in linear regression or neural network models of human performance. The efficiency of the DWT is discussed in terms of its decorrelation and energy compaction properties. In addition, the DWT models provided evidence that a pattern of low-frequency activity (1 to 3.5 Hz) occurring at specific times and scalp locations is a reliable correlate of human signal detection performance.

Feature extraction of event-related potentials using wavelets: an application to human performance monitoring

NASA Technical Reports Server (NTRS)

Trejo, L. J.; Shensa, M. J.

1999-01-01

This report describes the development and evaluation of mathematical models for predicting human performance from discrete wavelet transforms (DWT) of event-related potentials (ERP) elicited by task-relevant stimuli. The DWT was compared to principal components analysis (PCA) for representation of ERPs in linear regression and neural network models developed to predict a composite measure of human signal detection performance. Linear regression models based on coefficients of the decimated DWT predicted signal detection performance with half as many free parameters as comparable models based on PCA scores. In addition, the DWT-based models were more resistant to model degradation due to over-fitting than PCA-based models. Feed-forward neural networks were trained using the backpropagation algorithm to predict signal detection performance based on raw ERPs, PCA scores, or high-power coefficients of the DWT. Neural networks based on high-power DWT coefficients trained with fewer iterations, generalized to new data better, and were more resistant to overfitting than networks based on raw ERPs. Networks based on PCA scores did not generalize to new data as well as either the DWT network or the raw ERP network. The results show that wavelet expansions represent the ERP efficiently and extract behaviorally important features for use in linear regression or neural network models of human performance. The efficiency of the DWT is discussed in terms of its decorrelation and energy compaction properties. In addition, the DWT models provided evidence that a pattern of low-frequency activity (1 to 3.5 Hz) occurring at specific times and scalp locations is a reliable correlate of human signal detection performance. Copyright 1999 Academic Press.

Multistep-Ahead Air Passengers Traffic Prediction with Hybrid ARIMA-SVMs Models

PubMed Central

Ming, Wei; Xiong, Tao

2014-01-01

The hybrid ARIMA-SVMs prediction models have been established recently, which take advantage of the unique strength of ARIMA and SVMs models in linear and nonlinear modeling, respectively. Built upon this hybrid ARIMA-SVMs models alike, this study goes further to extend them into the case of multistep-ahead prediction for air passengers traffic with the two most commonly used multistep-ahead prediction strategies, that is, iterated strategy and direct strategy. Additionally, the effectiveness of data preprocessing approaches, such as deseasonalization and detrending, is investigated and proofed along with the two strategies. Real data sets including four selected airlines' monthly series were collected to justify the effectiveness of the proposed approach. Empirical results demonstrate that the direct strategy performs better than iterative one in long term prediction case while iterative one performs better in the case of short term prediction. Furthermore, both deseasonalization and detrending can significantly improve the prediction accuracy for both strategies, indicating the necessity of data preprocessing. As such, this study contributes as a full reference to the planners from air transportation industries on how to tackle multistep-ahead prediction tasks in the implementation of either prediction strategy. PMID:24723814

Benchmarking novel approaches for modelling species range dynamics

PubMed Central

Zurell, Damaris; Thuiller, Wilfried; Pagel, Jörn; Cabral, Juliano S; Münkemüller, Tamara; Gravel, Dominique; Dullinger, Stefan; Normand, Signe; Schiffers, Katja H.; Moore, Kara A.; Zimmermann, Niklaus E.

2016-01-01

Increasing biodiversity loss due to climate change is one of the most vital challenges of the 21st century. To anticipate and mitigate biodiversity loss, models are needed that reliably project species’ range dynamics and extinction risks. Recently, several new approaches to model range dynamics have been developed to supplement correlative species distribution models (SDMs), but applications clearly lag behind model development. Indeed, no comparative analysis has been performed to evaluate their performance. Here, we build on process-based, simulated data for benchmarking five range (dynamic) models of varying complexity including classical SDMs, SDMs coupled with simple dispersal or more complex population dynamic models (SDM hybrids), and a hierarchical Bayesian process-based dynamic range model (DRM). We specifically test the effects of demographic and community processes on model predictive performance. Under current climate, DRMs performed best, although only marginally. Under climate change, predictive performance varied considerably, with no clear winners. Yet, all range dynamic models improved predictions under climate change substantially compared to purely correlative SDMs, and the population dynamic models also predicted reasonable extinction risks for most scenarios. When benchmarking data were simulated with more complex demographic and community processes, simple SDM hybrids including only dispersal often proved most reliable. Finally, we found that structural decisions during model building can have great impact on model accuracy, but prior system knowledge on important processes can reduce these uncertainties considerably. Our results reassure the clear merit in using dynamic approaches for modelling species’ response to climate change but also emphasise several needs for further model and data improvement. We propose and discuss perspectives for improving range projections through combination of multiple models and for making these approaches operational for large numbers of species. PMID:26872305

Benchmarking novel approaches for modelling species range dynamics.

PubMed

Zurell, Damaris; Thuiller, Wilfried; Pagel, Jörn; Cabral, Juliano S; Münkemüller, Tamara; Gravel, Dominique; Dullinger, Stefan; Normand, Signe; Schiffers, Katja H; Moore, Kara A; Zimmermann, Niklaus E

2016-08-01

Increasing biodiversity loss due to climate change is one of the most vital challenges of the 21st century. To anticipate and mitigate biodiversity loss, models are needed that reliably project species' range dynamics and extinction risks. Recently, several new approaches to model range dynamics have been developed to supplement correlative species distribution models (SDMs), but applications clearly lag behind model development. Indeed, no comparative analysis has been performed to evaluate their performance. Here, we build on process-based, simulated data for benchmarking five range (dynamic) models of varying complexity including classical SDMs, SDMs coupled with simple dispersal or more complex population dynamic models (SDM hybrids), and a hierarchical Bayesian process-based dynamic range model (DRM). We specifically test the effects of demographic and community processes on model predictive performance. Under current climate, DRMs performed best, although only marginally. Under climate change, predictive performance varied considerably, with no clear winners. Yet, all range dynamic models improved predictions under climate change substantially compared to purely correlative SDMs, and the population dynamic models also predicted reasonable extinction risks for most scenarios. When benchmarking data were simulated with more complex demographic and community processes, simple SDM hybrids including only dispersal often proved most reliable. Finally, we found that structural decisions during model building can have great impact on model accuracy, but prior system knowledge on important processes can reduce these uncertainties considerably. Our results reassure the clear merit in using dynamic approaches for modelling species' response to climate change but also emphasize several needs for further model and data improvement. We propose and discuss perspectives for improving range projections through combination of multiple models and for making these approaches operational for large numbers of species. © 2016 John Wiley & Sons Ltd.

Statistical-learning strategies generate only modestly performing predictive models for urinary symptoms following external beam radiotherapy of the prostate: A comparison of conventional and machine-learning methods

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

Yahya, Noorazrul, E-mail: noorazrul.yahya@research.uwa.edu.au; Ebert, Martin A.; Bulsara, Max

Purpose: Given the paucity of available data concerning radiotherapy-induced urinary toxicity, it is important to ensure derivation of the most robust models with superior predictive performance. This work explores multiple statistical-learning strategies for prediction of urinary symptoms following external beam radiotherapy of the prostate. Methods: The performance of logistic regression, elastic-net, support-vector machine, random forest, neural network, and multivariate adaptive regression splines (MARS) to predict urinary symptoms was analyzed using data from 754 participants accrued by TROG03.04-RADAR. Predictive features included dose-surface data, comorbidities, and medication-intake. Four symptoms were analyzed: dysuria, haematuria, incontinence, and frequency, each with three definitions (grade ≥more » 1, grade ≥ 2 and longitudinal) with event rate between 2.3% and 76.1%. Repeated cross-validations producing matched models were implemented. A synthetic minority oversampling technique was utilized in endpoints with rare events. Parameter optimization was performed on the training data. Area under the receiver operating characteristic curve (AUROC) was used to compare performance using sample size to detect differences of ≥0.05 at the 95% confidence level. Results: Logistic regression, elastic-net, random forest, MARS, and support-vector machine were the highest-performing statistical-learning strategies in 3, 3, 3, 2, and 1 endpoints, respectively. Logistic regression, MARS, elastic-net, random forest, neural network, and support-vector machine were the best, or were not significantly worse than the best, in 7, 7, 5, 5, 3, and 1 endpoints. The best-performing statistical model was for dysuria grade ≥ 1 with AUROC ± standard deviation of 0.649 ± 0.074 using MARS. For longitudinal frequency and dysuria grade ≥ 1, all strategies produced AUROC>0.6 while all haematuria endpoints and longitudinal incontinence models produced AUROC<0.6. Conclusions: Logistic regression and MARS were most likely to be the best-performing strategy for the prediction of urinary symptoms with elastic-net and random forest producing competitive results. The predictive power of the models was modest and endpoint-dependent. New features, including spatial dose maps, may be necessary to achieve better models.« less

Structural, Thermal, and Optical Performance (STOP) Modeling and Results for the James Webb Space Telescope Integrated Science Instrument Module

NASA Technical Reports Server (NTRS)

Gracey, Renee; Bartoszyk, Andrew; Cofie, Emmanuel; Comber, Brian; Hartig, George; Howard, Joseph; Sabatke, Derek; Wenzel, Greg; Ohl, Raymond

2016-01-01

The James Webb Space Telescope includes the Integrated Science Instrument Module (ISIM) element that contains four science instruments (SI) including a Guider. We performed extensive structural, thermal, and optical performance(STOP) modeling in support of all phases of ISIM development. In this paper, we focus on modeling and results associated with test and verification. ISIMs test program is bound by ground environments, mostly notably the 1g and test chamber thermal environments. This paper describes STOP modeling used to predict ISIM system performance in 0g and at various on-orbit temperature environments. The predictions are used to project results obtained during testing to on-orbit performance.

Modelling and Predicting Backstroke Start Performance Using Non-Linear and Linear Models.

PubMed

de Jesus, Karla; Ayala, Helon V H; de Jesus, Kelly; Coelho, Leandro Dos S; Medeiros, Alexandre I A; Abraldes, José A; Vaz, Mário A P; Fernandes, Ricardo J; Vilas-Boas, João Paulo

2018-03-01

Our aim was to compare non-linear and linear mathematical model responses for backstroke start performance prediction. Ten swimmers randomly completed eight 15 m backstroke starts with feet over the wedge, four with hands on the highest horizontal and four on the vertical handgrip. Swimmers were videotaped using a dual media camera set-up, with the starts being performed over an instrumented block with four force plates. Artificial neural networks were applied to predict 5 m start time using kinematic and kinetic variables and to determine the accuracy of the mean absolute percentage error. Artificial neural networks predicted start time more robustly than the linear model with respect to changing training to the validation dataset for the vertical handgrip (3.95 ± 1.67 vs. 5.92 ± 3.27%). Artificial neural networks obtained a smaller mean absolute percentage error than the linear model in the horizontal (0.43 ± 0.19 vs. 0.98 ± 0.19%) and vertical handgrip (0.45 ± 0.19 vs. 1.38 ± 0.30%) using all input data. The best artificial neural network validation revealed a smaller mean absolute error than the linear model for the horizontal (0.007 vs. 0.04 s) and vertical handgrip (0.01 vs. 0.03 s). Artificial neural networks should be used for backstroke 5 m start time prediction due to the quite small differences among the elite level performances.

Exploring predictive performance: A reanalysis of the geospace model transition challenge

NASA Astrophysics Data System (ADS)

Welling, D. T.; Anderson, B. J.; Crowley, G.; Pulkkinen, A. A.; Rastätter, L.

2017-01-01

The Pulkkinen et al. (2013) study evaluated the ability of five different geospace models to predict surface dB/dt as a function of upstream solar drivers. This was an important step in the assessment of research models for predicting and ultimately preventing the damaging effects of geomagnetically induced currents. Many questions remain concerning the capabilities of these models. This study presents a reanalysis of the Pulkkinen et al. (2013) results in an attempt to better understand the models' performance. The range of validity of the models is determined by examining the conditions corresponding to the empirical input data. It is found that the empirical conductance models on which global magnetohydrodynamic models rely are frequently used outside the limits of their input data. The prediction error for the models is sorted as a function of solar driving and geomagnetic activity. It is found that all models show a bias toward underprediction, especially during active times. These results have implications for future research aimed at improving operational forecast models.

Modeling the prediction of business intelligence system effectiveness.

PubMed

Weng, Sung-Shun; Yang, Ming-Hsien; Koo, Tian-Lih; Hsiao, Pei-I

2016-01-01

Although business intelligence (BI) technologies are continually evolving, the capability to apply BI technologies has become an indispensable resource for enterprises running in today's complex, uncertain and dynamic business environment. This study performed pioneering work by constructing models and rules for the prediction of business intelligence system effectiveness (BISE) in relation to the implementation of BI solutions. For enterprises, effectively managing critical attributes that determine BISE to develop prediction models with a set of rules for self-evaluation of the effectiveness of BI solutions is necessary to improve BI implementation and ensure its success. The main study findings identified the critical prediction indicators of BISE that are important to forecasting BI performance and highlighted five classification and prediction rules of BISE derived from decision tree structures, as well as a refined regression prediction model with four critical prediction indicators constructed by logistic regression analysis that can enable enterprises to improve BISE while effectively managing BI solution implementation and catering to academics to whom theory is important.

Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling: A Novel Approach to Solve the Inverse ECG Problem

NASA Astrophysics Data System (ADS)

Yao, Bing; Yang, Hui

2016-12-01

This paper presents a novel physics-driven spatiotemporal regularization (STRE) method for high-dimensional predictive modeling in complex healthcare systems. This model not only captures the physics-based interrelationship between time-varying explanatory and response variables that are distributed in the space, but also addresses the spatial and temporal regularizations to improve the prediction performance. The STRE model is implemented to predict the time-varying distribution of electric potentials on the heart surface based on the electrocardiogram (ECG) data from the distributed sensor network placed on the body surface. The model performance is evaluated and validated in both a simulated two-sphere geometry and a realistic torso-heart geometry. Experimental results show that the STRE model significantly outperforms other regularization models that are widely used in current practice such as Tikhonov zero-order, Tikhonov first-order and L1 first-order regularization methods.

Development of a Pavement Maintenance Management System. Volume 9. Development of Airfield Pavement Performance Prediction Models.

DTIC Science & Technology

1984-05-01

materials, traffic, and climate, were used to develop PCI and key distress prediction models for both asphalt-concrete- and jointed-concrete- surfaced...Predicted PCI for PCC and AC/PCC Pavements Using Model Presented in Section III ...... 35 31 Effect of PCC Thickness on the PCI as a Function of Age...of Corner Breaking Observed vs Predicted Percent of Corner Breaking Using Model Presented in Section III

Performance of genomic prediction within and across generations in maritime pine.

PubMed

Bartholomé, Jérôme; Van Heerwaarden, Joost; Isik, Fikret; Boury, Christophe; Vidal, Marjorie; Plomion, Christophe; Bouffier, Laurent

2016-08-11

Genomic selection (GS) is a promising approach for decreasing breeding cycle length in forest trees. Assessment of progeny performance and of the prediction accuracy of GS models over generations is therefore a key issue. A reference population of maritime pine (Pinus pinaster) with an estimated effective inbreeding population size (status number) of 25 was first selected with simulated data. This reference population (n = 818) covered three generations (G0, G1 and G2) and was genotyped with 4436 single-nucleotide polymorphism (SNP) markers. We evaluated the effects on prediction accuracy of both the relatedness between the calibration and validation sets and validation on the basis of progeny performance. Pedigree-based (best linear unbiased prediction, ABLUP) and marker-based (genomic BLUP and Bayesian LASSO) models were used to predict breeding values for three different traits: circumference, height and stem straightness. On average, the ABLUP model outperformed genomic prediction models, with a maximum difference in prediction accuracies of 0.12, depending on the trait and the validation method. A mean difference in prediction accuracy of 0.17 was found between validation methods differing in terms of relatedness. Including the progenitors in the calibration set reduced this difference in prediction accuracy to 0.03. When only genotypes from the G0 and G1 generations were used in the calibration set and genotypes from G2 were used in the validation set (progeny validation), prediction accuracies ranged from 0.70 to 0.85. This study suggests that the training of prediction models on parental populations can predict the genetic merit of the progeny with high accuracy: an encouraging result for the implementation of GS in the maritime pine breeding program.

Performance of a block detector PET scanner in imaging non-pure positron emitters—modelling and experimental validation with 124I

NASA Astrophysics Data System (ADS)

Robinson, S.; Julyan, P. J.; Hastings, D. L.; Zweit, J.

2004-12-01

The key performance measures of resolution, count rate, sensitivity and scatter fraction are predicted for a dedicated BGO block detector patient PET scanner (GE Advance) in 2D mode for imaging with the non-pure positron-emitting radionuclides 124I, 55Co, 61Cu, 62Cu, 64Cu and 76Br. Model calculations including parameters of the scanner, decay characteristics of the radionuclides and measured parameters in imaging the pure positron-emitter 18F are used to predict performance according to the National Electrical Manufacturers Association (NEMA) NU 2-1994 criteria. Predictions are tested with measurements made using 124I and show that, in comparison with 18F, resolution degrades by 1.2 mm radially and tangentially throughout the field-of-view (prediction: 1.2 mm), count-rate performance reduces considerably and in close accordance with calculations, sensitivity decreases to 23.4% of that with 18F (prediction: 22.9%) and measured scatter fraction increases from 10.0% to 14.5% (prediction: 14.7%). Model predictions are expected to be equally accurate for other radionuclides and may be extended to similar scanners. Although performance is worse with 124I than 18F, imaging is not precluded in 2D mode. The viability of 124I imaging and performance in a clinical context compared with 18F is illustrated with images of a patient with recurrent thyroid cancer acquired using both [124I]-sodium iodide and [18F]-2-fluoro-2-deoxyglucose.

External validation of Vascular Study Group of New England risk predictive model of mortality after elective abdominal aorta aneurysm repair in the Vascular Quality Initiative and comparison against established models.

PubMed

Eslami, Mohammad H; Rybin, Denis V; Doros, Gheorghe; Siracuse, Jeffrey J; Farber, Alik

2018-01-01

The purpose of this study is to externally validate a recently reported Vascular Study Group of New England (VSGNE) risk predictive model of postoperative mortality after elective abdominal aortic aneurysm (AAA) repair and to compare its predictive ability across different patients' risk categories and against the established risk predictive models using the Vascular Quality Initiative (VQI) AAA sample. The VQI AAA database (2010-2015) was queried for patients who underwent elective AAA repair. The VSGNE cases were excluded from the VQI sample. The external validation of a recently published VSGNE AAA risk predictive model, which includes only preoperative variables (age, gender, history of coronary artery disease, chronic obstructive pulmonary disease, cerebrovascular disease, creatinine levels, and aneurysm size) and planned type of repair, was performed using the VQI elective AAA repair sample. The predictive value of the model was assessed via the C-statistic. Hosmer-Lemeshow method was used to assess calibration and goodness of fit. This model was then compared with the Medicare, Vascular Governance Northwest model, and Glasgow Aneurysm Score for predicting mortality in VQI sample. The Vuong test was performed to compare the model fit between the models. Model discrimination was assessed in different risk group VQI quintiles. Data from 4431 cases from the VSGNE sample with the overall mortality rate of 1.4% was used to develop the model. The internally validated VSGNE model showed a very high discriminating ability in predicting mortality (C = 0.822) and good model fit (Hosmer-Lemeshow P = .309) among the VSGNE elective AAA repair sample. External validation on 16,989 VQI cases with an overall 0.9% mortality rate showed very robust predictive ability of mortality (C = 0.802). Vuong tests yielded a significant fit difference favoring the VSGNE over then Medicare model (C = 0.780), Vascular Governance Northwest (0.774), and Glasgow Aneurysm Score (0.639). Across the 5 risk quintiles, the VSGNE model predicted observed mortality significantly with great accuracy. This simple VSGNE AAA risk predictive model showed very high discriminative ability in predicting mortality after elective AAA repair among a large external independent sample of AAA cases performed by a diverse array of physicians nationwide. The risk score based on this simple VSGNE model can reliably stratify patients according to their risk of mortality after elective AAA repair better than other established models. Copyright © 2017 Society for Vascular Surgery. Published by Elsevier Inc. All rights reserved.

Solid rocket booster performance evaluation model. Volume 1: Engineering description

NASA Technical Reports Server (NTRS)

1974-01-01

The space shuttle solid rocket booster performance evaluation model (SRB-II) is made up of analytical and functional simulation techniques linked together so that a single pass through the model will predict the performance of the propulsion elements of a space shuttle solid rocket booster. The available options allow the user to predict static test performance, predict nominal and off nominal flight performance, and reconstruct actual flight and static test performance. Options selected by the user are dependent on the data available. These can include data derived from theoretical analysis, small scale motor test data, large motor test data and motor configuration data. The user has several options for output format that include print, cards, tape and plots. Output includes all major performance parameters (Isp, thrust, flowrate, mass accounting and operating pressures) as a function of time as well as calculated single point performance data. The engineering description of SRB-II discusses the engineering and programming fundamentals used, the function of each module, and the limitations of each module.

[Determination of soluble solids content in Nanfeng Mandarin by Vis/NIR spectroscopy and UVE-ICA-LS-SVM].

PubMed

Sun, Tong; Xu, Wen-Li; Hu, Tian; Liu, Mu-Hua

2013-12-01

The objective of the present research was to assess soluble solids content (SSC) of Nanfeng mandarin by visible/near infrared (Vis/NIR) spectroscopy combined with new variable selection method, simplify prediction model and improve the performance of prediction model for SSC of Nanfeng mandarin. A total of 300 Nanfeng mandarin samples were used, the numbers of Nanfeng mandarin samples in calibration, validation and prediction sets were 150, 75 and 75, respectively. Vis/NIR spectra of Nanfeng mandarin samples were acquired by a QualitySpec spectrometer in the wavelength range of 350-1000 nm. Uninformative variables elimination (UVE) was used to eliminate wavelength variables that had few information of SSC, then independent component analysis (ICA) was used to extract independent components (ICs) from spectra that eliminated uninformative wavelength variables. At last, least squares support vector machine (LS-SVM) was used to develop calibration models for SSC of Nanfeng mandarin using extracted ICs, and 75 prediction samples that had not been used for model development were used to evaluate the performance of SSC model of Nanfeng mandarin. The results indicate t hat Vis/NIR spectroscopy combinedwith UVE-ICA-LS-SVM is suitable for assessing SSC o f Nanfeng mandarin, and t he precision o f prediction ishigh. UVE--ICA is an effective method to eliminate uninformative wavelength variables, extract important spectral information, simplify prediction model and improve the performance of prediction model. The SSC model developed by UVE-ICA-LS-SVM is superior to that developed by PLS, PCA-LS-SVM or ICA-LS-SVM, and the coefficient of determination and root mean square error in calibration, validation and prediction sets were 0.978, 0.230%, 0.965, 0.301% and 0.967, 0.292%, respectively.

ToxiM: A Toxicity Prediction Tool for Small Molecules Developed Using Machine Learning and Chemoinformatics Approaches.

PubMed

Sharma, Ashok K; Srivastava, Gopal N; Roy, Ankita; Sharma, Vineet K

2017-01-01

The experimental methods for the prediction of molecular toxicity are tedious and time-consuming tasks. Thus, the computational approaches could be used to develop alternative methods for toxicity prediction. We have developed a tool for the prediction of molecular toxicity along with the aqueous solubility and permeability of any molecule/metabolite. Using a comprehensive and curated set of toxin molecules as a training set, the different chemical and structural based features such as descriptors and fingerprints were exploited for feature selection, optimization and development of machine learning based classification and regression models. The compositional differences in the distribution of atoms were apparent between toxins and non-toxins, and hence, the molecular features were used for the classification and regression. On 10-fold cross-validation, the descriptor-based, fingerprint-based and hybrid-based classification models showed similar accuracy (93%) and Matthews's correlation coefficient (0.84). The performances of all the three models were comparable (Matthews's correlation coefficient = 0.84-0.87) on the blind dataset. In addition, the regression-based models using descriptors as input features were also compared and evaluated on the blind dataset. Random forest based regression model for the prediction of solubility performed better ( R 2 = 0.84) than the multi-linear regression (MLR) and partial least square regression (PLSR) models, whereas, the partial least squares based regression model for the prediction of permeability (caco-2) performed better ( R 2 = 0.68) in comparison to the random forest and MLR based regression models. The performance of final classification and regression models was evaluated using the two validation datasets including the known toxins and commonly used constituents of health products, which attests to its accuracy. The ToxiM web server would be a highly useful and reliable tool for the prediction of toxicity, solubility, and permeability of small molecules.

ToxiM: A Toxicity Prediction Tool for Small Molecules Developed Using Machine Learning and Chemoinformatics Approaches

PubMed Central

Sharma, Ashok K.; Srivastava, Gopal N.; Roy, Ankita; Sharma, Vineet K.

2017-01-01

The experimental methods for the prediction of molecular toxicity are tedious and time-consuming tasks. Thus, the computational approaches could be used to develop alternative methods for toxicity prediction. We have developed a tool for the prediction of molecular toxicity along with the aqueous solubility and permeability of any molecule/metabolite. Using a comprehensive and curated set of toxin molecules as a training set, the different chemical and structural based features such as descriptors and fingerprints were exploited for feature selection, optimization and development of machine learning based classification and regression models. The compositional differences in the distribution of atoms were apparent between toxins and non-toxins, and hence, the molecular features were used for the classification and regression. On 10-fold cross-validation, the descriptor-based, fingerprint-based and hybrid-based classification models showed similar accuracy (93%) and Matthews's correlation coefficient (0.84). The performances of all the three models were comparable (Matthews's correlation coefficient = 0.84–0.87) on the blind dataset. In addition, the regression-based models using descriptors as input features were also compared and evaluated on the blind dataset. Random forest based regression model for the prediction of solubility performed better (R2 = 0.84) than the multi-linear regression (MLR) and partial least square regression (PLSR) models, whereas, the partial least squares based regression model for the prediction of permeability (caco-2) performed better (R2 = 0.68) in comparison to the random forest and MLR based regression models. The performance of final classification and regression models was evaluated using the two validation datasets including the known toxins and commonly used constituents of health products, which attests to its accuracy. The ToxiM web server would be a highly useful and reliable tool for the prediction of toxicity, solubility, and permeability of small molecules. PMID:29249969

Review and evaluation of performance measures for survival prediction models in external validation settings.

PubMed

Rahman, M Shafiqur; Ambler, Gareth; Choodari-Oskooei, Babak; Omar, Rumana Z

2017-04-18

When developing a prediction model for survival data it is essential to validate its performance in external validation settings using appropriate performance measures. Although a number of such measures have been proposed, there is only limited guidance regarding their use in the context of model validation. This paper reviewed and evaluated a wide range of performance measures to provide some guidelines for their use in practice. An extensive simulation study based on two clinical datasets was conducted to investigate the performance of the measures in external validation settings. Measures were selected from categories that assess the overall performance, discrimination and calibration of a survival prediction model. Some of these have been modified to allow their use with validation data, and a case study is provided to describe how these measures can be estimated in practice. The measures were evaluated with respect to their robustness to censoring and ease of interpretation. All measures are implemented, or are straightforward to implement, in statistical software. Most of the performance measures were reasonably robust to moderate levels of censoring. One exception was Harrell's concordance measure which tended to increase as censoring increased. We recommend that Uno's concordance measure is used to quantify concordance when there are moderate levels of censoring. Alternatively, Gönen and Heller's measure could be considered, especially if censoring is very high, but we suggest that the prediction model is re-calibrated first. We also recommend that Royston's D is routinely reported to assess discrimination since it has an appealing interpretation. The calibration slope is useful for both internal and external validation settings and recommended to report routinely. Our recommendation would be to use any of the predictive accuracy measures and provide the corresponding predictive accuracy curves. In addition, we recommend to investigate the characteristics of the validation data such as the level of censoring and the distribution of the prognostic index derived in the validation setting before choosing the performance measures.

Model for Predicting the Performance of Planetary Suit Hip Bearing Designs

NASA Technical Reports Server (NTRS)

Cowley, Matthew S.; Margerum, Sarah; Hharvill, Lauren; Rajulu, Sudhakar

2012-01-01

Designing a space suit is very complex and often requires difficult trade-offs between performance, cost, mass, and system complexity. During the development period of the suit numerous design iterations need to occur before the hardware meets human performance requirements. Using computer models early in the design phase of hardware development is advantageous, by allowing virtual prototyping to take place. A virtual design environment allows designers to think creatively, exhaust design possibilities, and study design impacts on suit and human performance. A model of the rigid components of the Mark III Technology Demonstrator Suit (planetary-type space suit) and a human manikin were created and tested in a virtual environment. The performance of the Mark III hip bearing model was first developed and evaluated virtually by comparing the differences in mobility performance between the nominal bearing configurations and modified bearing configurations. Suited human performance was then simulated with the model and compared to actual suited human performance data using the same bearing configurations. The Mark III hip bearing model was able to visually represent complex bearing rotations and the theoretical volumetric ranges of motion in three dimensions. The model was also able to predict suited human hip flexion and abduction maximums to within 10% of the actual suited human subject data, except for one modified bearing condition in hip flexion which was off by 24%. Differences between the model predictions and the human subject performance data were attributed to the lack of joint moment limits in the model, human subject fitting issues, and the limited suit experience of some of the subjects. The results demonstrate that modeling space suit rigid segments is a feasible design tool for evaluating and optimizing suited human performance. Keywords: space suit, design, modeling, performance

An improved predictive functional control method with application to PMSM systems

NASA Astrophysics Data System (ADS)

Li, Shihua; Liu, Huixian; Fu, Wenshu

2017-01-01

In common design of prediction model-based control method, usually disturbances are not considered in the prediction model as well as the control design. For the control systems with large amplitude or strong disturbances, it is difficult to precisely predict the future outputs according to the conventional prediction model, and thus the desired optimal closed-loop performance will be degraded to some extent. To this end, an improved predictive functional control (PFC) method is developed in this paper by embedding disturbance information into the system model. Here, a composite prediction model is thus obtained by embedding the estimated value of disturbances, where disturbance observer (DOB) is employed to estimate the lumped disturbances. So the influence of disturbances on system is taken into account in optimisation procedure. Finally, considering the speed control problem for permanent magnet synchronous motor (PMSM) servo system, a control scheme based on the improved PFC method is designed to ensure an optimal closed-loop performance even in the presence of disturbances. Simulation and experimental results based on a hardware platform are provided to confirm the effectiveness of the proposed algorithm.

Modelling invasion for a habitat generalist and a specialist plant species

USGS Publications Warehouse

Evangelista, P.H.; Kumar, S.; Stohlgren, T.J.; Jarnevich, C.S.; Crall, A.W.; Norman, J. B.; Barnett, D.T.

2008-01-01

Predicting suitable habitat and the potential distribution of invasive species is a high priority for resource managers and systems ecologists. Most models are designed to identify habitat characteristics that define the ecological niche of a species with little consideration to individual species' traits. We tested five commonly used modelling methods on two invasive plant species, the habitat generalist Bromus tectorum and habitat specialist Tamarix chinensis, to compare model performances, evaluate predictability, and relate results to distribution traits associated with each species. Most of the tested models performed similarly for each species; however, the generalist species proved to be more difficult to predict than the specialist species. The highest area under the receiver-operating characteristic curve values with independent validation data sets of B. tectorum and T. chinensis was 0.503 and 0.885, respectively. Similarly, a confusion matrix for B. tectorum had the highest overall accuracy of 55%, while the overall accuracy for T. chinensis was 85%. Models for the generalist species had varying performances, poor evaluations, and inconsistent results. This may be a result of a generalist's capability to persist in a wide range of environmental conditions that are not easily defined by the data, independent variables or model design. Models for the specialist species had consistently strong performances, high evaluations, and similar results among different model applications. This is likely a consequence of the specialist's requirement for explicit environmental resources and ecological barriers that are easily defined by predictive models. Although defining new invaders as generalist or specialist species can be challenging, model performances and evaluations may provide valuable information on a species' potential invasiveness.

Review of numerical models to predict cooling tower performance

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

Johnson, B.M.; Nomura, K.K.; Bartz, J.A.

1987-01-01

Four state-of-the-art computer models developed to predict the thermal performance of evaporative cooling towers are summarized. The formulation of these models, STAR and TEFERI (developed in Europe) and FACTS and VERA2D (developed in the U.S.), is summarized. A fifth code, based on Merkel analysis, is also discussed. Principal features of the codes, computation time and storage requirements are described. A discussion of model validation is also provided.

Integrating in silico models to enhance predictivity for developmental toxicity.

PubMed

Marzo, Marco; Kulkarni, Sunil; Manganaro, Alberto; Roncaglioni, Alessandra; Wu, Shengde; Barton-Maclaren, Tara S; Lester, Cathy; Benfenati, Emilio

2016-08-31

Application of in silico models to predict developmental toxicity has demonstrated limited success particularly when employed as a single source of information. It is acknowledged that modelling the complex outcomes related to this endpoint is a challenge; however, such models have been developed and reported in the literature. The current study explored the possibility of integrating the selected public domain models (CAESAR, SARpy and P&G model) with the selected commercial modelling suites (Multicase, Leadscope and Derek Nexus) to assess if there is an increase in overall predictive performance. The results varied according to the data sets used to assess performance which improved upon model integration relative to individual models. Moreover, because different models are based on different specific developmental toxicity effects, integration of these models increased the applicable chemical and biological spaces. It is suggested that this approach reduces uncertainty associated with in silico predictions by achieving a consensus among a battery of models. The use of tools to assess the applicability domain also improves the interpretation of the predictions. This has been verified in the case of the software VEGA, which makes freely available QSAR models with a measurement of the applicability domain. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Real-time Ensemble Forecasting of Coronal Mass Ejections using the WSA-ENLIL+Cone Model

NASA Astrophysics Data System (ADS)

Mays, M. L.; Taktakishvili, A.; Pulkkinen, A. A.; MacNeice, P. J.; Rastaetter, L.; Kuznetsova, M. M.; Odstrcil, D.

2013-12-01

Ensemble forecasting of coronal mass ejections (CMEs) provides significant information in that it provides an estimation of the spread or uncertainty in CME arrival time predictions due to uncertainties in determining CME input parameters. Ensemble modeling of CME propagation in the heliosphere is performed by forecasters at the Space Weather Research Center (SWRC) using the WSA-ENLIL cone model available at the Community Coordinated Modeling Center (CCMC). SWRC is an in-house research-based operations team at the CCMC which provides interplanetary space weather forecasting for NASA's robotic missions and performs real-time model validation. A distribution of n (routinely n=48) CME input parameters are generated using the CCMC Stereo CME Analysis Tool (StereoCAT) which employs geometrical triangulation techniques. These input parameters are used to perform n different simulations yielding an ensemble of solar wind parameters at various locations of interest (satellites or planets), including a probability distribution of CME shock arrival times (for hits), and geomagnetic storm strength (for Earth-directed hits). Ensemble simulations have been performed experimentally in real-time at the CCMC since January 2013. We present the results of ensemble simulations for a total of 15 CME events, 10 of which were performed in real-time. The observed CME arrival was within the range of ensemble arrival time predictions for 5 out of the 12 ensemble runs containing hits. The average arrival time prediction was computed for each of the twelve ensembles predicting hits and using the actual arrival time an average absolute error of 8.20 hours was found for all twelve ensembles, which is comparable to current forecasting errors. Some considerations for the accuracy of ensemble CME arrival time predictions include the importance of the initial distribution of CME input parameters, particularly the mean and spread. When the observed arrivals are not within the predicted range, this still allows the ruling out of prediction errors caused by tested CME input parameters. Prediction errors can also arise from ambient model parameters such as the accuracy of the solar wind background, and other limitations. Additionally the ensemble modeling setup was used to complete a parametric event case study of the sensitivity of the CME arrival time prediction to free parameters for ambient solar wind model and CME.

Prediction models for the risk of spontaneous preterm birth based on maternal characteristics: a systematic review and independent external validation.

PubMed

Meertens, Linda J E; van Montfort, Pim; Scheepers, Hubertina C J; van Kuijk, Sander M J; Aardenburg, Robert; Langenveld, Josje; van Dooren, Ivo M A; Zwaan, Iris M; Spaanderman, Marc E A; Smits, Luc J M

2018-04-17

Prediction models may contribute to personalized risk-based management of women at high risk of spontaneous preterm delivery. Although prediction models are published frequently, often with promising results, external validation generally is lacking. We performed a systematic review of prediction models for the risk of spontaneous preterm birth based on routine clinical parameters. Additionally, we externally validated and evaluated the clinical potential of the models. Prediction models based on routinely collected maternal parameters obtainable during first 16 weeks of gestation were eligible for selection. Risk of bias was assessed according to the CHARMS guidelines. We validated the selected models in a Dutch multicenter prospective cohort study comprising 2614 unselected pregnant women. Information on predictors was obtained by a web-based questionnaire. Predictive performance of the models was quantified by the area under the receiver operating characteristic curve (AUC) and calibration plots for the outcomes spontaneous preterm birth <37 weeks and <34 weeks of gestation. Clinical value was evaluated by means of decision curve analysis and calculating classification accuracy for different risk thresholds. Four studies describing five prediction models fulfilled the eligibility criteria. Risk of bias assessment revealed a moderate to high risk of bias in three studies. The AUC of the models ranged from 0.54 to 0.67 and from 0.56 to 0.70 for the outcomes spontaneous preterm birth <37 weeks and <34 weeks of gestation, respectively. A subanalysis showed that the models discriminated poorly (AUC 0.51-0.56) for nulliparous women. Although we recalibrated the models, two models retained evidence of overfitting. The decision curve analysis showed low clinical benefit for the best performing models. This review revealed several reporting and methodological shortcomings of published prediction models for spontaneous preterm birth. Our external validation study indicated that none of the models had the ability to predict spontaneous preterm birth adequately in our population. Further improvement of prediction models, using recent knowledge about both model development and potential risk factors, is necessary to provide an added value in personalized risk assessment of spontaneous preterm birth. © 2018 The Authors Acta Obstetricia et Gynecologica Scandinavica published by John Wiley & Sons Ltd on behalf of Nordic Federation of Societies of Obstetrics and Gynecology (NFOG).

Prediction of global and local model quality in CASP8 using the ModFOLD server.

PubMed

McGuffin, Liam J

2009-01-01

The development of effective methods for predicting the quality of three-dimensional (3D) models is fundamentally important for the success of tertiary structure (TS) prediction strategies. Since CASP7, the Quality Assessment (QA) category has existed to gauge the ability of various model quality assessment programs (MQAPs) at predicting the relative quality of individual 3D models. For the CASP8 experiment, automated predictions were submitted in the QA category using two methods from the ModFOLD server-ModFOLD version 1.1 and ModFOLDclust. ModFOLD version 1.1 is a single-model machine learning based method, which was used for automated predictions of global model quality (QMODE1). ModFOLDclust is a simple clustering based method, which was used for automated predictions of both global and local quality (QMODE2). In addition, manual predictions of model quality were made using ModFOLD version 2.0--an experimental method that combines the scores from ModFOLDclust and ModFOLD v1.1. Predictions from the ModFOLDclust method were the most successful of the three in terms of the global model quality, whilst the ModFOLD v1.1 method was comparable in performance to other single-model based methods. In addition, the ModFOLDclust method performed well at predicting the per-residue, or local, model quality scores. Predictions of the per-residue errors in our own 3D models, selected using the ModFOLD v2.0 method, were also the most accurate compared with those from other methods. All of the MQAPs described are publicly accessible via the ModFOLD server at: http://www.reading.ac.uk/bioinf/ModFOLD/. The methods are also freely available to download from: http://www.reading.ac.uk/bioinf/downloads/. Copyright 2009 Wiley-Liss, Inc.

An improved computer model for prediction of axial gas turbine performance losses

NASA Technical Reports Server (NTRS)

Jenkins, R. M.

1984-01-01

The calculation model performs a rapid preliminary pitchline optimization of axial gas turbine annular flowpath geometry, as well as an initial estimate of blade profile shapes, given only a minimum of thermodynamic cycle requirements. No geometric parameters need be specified. The following preliminary design data are determined: (1) the optimum flowpath geometry, within mechanical stress limits; (2) initial estimates of cascade blade shapes; and (3) predictions of expected turbine performance. The model uses an inverse calculation technique whereby blade profiles are generated by designing channels to yield a specified velocity distribution on the two walls. Velocity distributions are then used to calculate the cascade loss parameters. Calculated blade shapes are used primarily to determine whether the assumed velocity loadings are physically realistic. Model verification is accomplished by comparison of predicted turbine geometry and performance with an array of seven NASA single-stage axial gas turbine configurations.

Exploration of Machine Learning Approaches to Predict Pavement Performance

DOT National Transportation Integrated Search

2018-03-23

Machine learning (ML) techniques were used to model and predict pavement condition index (PCI) for various pavement types using a variety of input variables. The primary objective of this research was to develop and assess PCI predictive models for t...

OPTIMIZING MODEL PERFORMANCE: VARIABLE SIZE RESOLUTION IN CLOUD CHEMISTRY MODELING. (R826371C005)

EPA Science Inventory

Under many conditions size-resolved aqueous-phase chemistry models predict higher sulfate production rates than comparable bulk aqueous-phase models. However, there are special circumstances under which bulk and size-resolved models offer similar predictions. These special con...

Using Student and Institutional Characteristics to Predict Graduation Rates at Community Colleges: New Developments in Performance Measures and Institutional Effectiveness

ERIC Educational Resources Information Center

Moosai, Susan; Walker, David A.; Floyd, Deborah L.

2011-01-01

Prediction models using graduation rate as the performance indicator were obtained for community colleges in California, Florida, and Michigan. The results of this study indicated that institutional graduation rate could be predicted effectively from an aggregate of student and institutional characteristics. A performance measure was computed, the…

Predicting NonInertial Effects with Algebraic Stress Models which Account for Dissipation Rate Anisotropies

NASA Technical Reports Server (NTRS)

Jongen, T.; Machiels, L.; Gatski, T. B.

1997-01-01

Three types of turbulence models which account for rotational effects in noninertial frames of reference are evaluated for the case of incompressible, fully developed rotating turbulent channel flow. The different types of models are a Coriolis-modified eddy-viscosity model, a realizable algebraic stress model, and an algebraic stress model which accounts for dissipation rate anisotropies. A direct numerical simulation of a rotating channel flow is used for the turbulent model validation. This simulation differs from previous studies in that significantly higher rotation numbers are investigated. Flows at these higher rotation numbers are characterized by a relaminarization on the cyclonic or suction side of the channel, and a linear velocity profile on the anticyclonic or pressure side of the channel. The predictive performance of the three types of models are examined in detail, and formulation deficiencies are identified which cause poor predictive performance for some of the models. Criteria are identified which allow for accurate prediction of such flows by algebraic stress models and their corresponding Reynolds stress formulations.

Comparative analysis of remotely-sensed data products via ecological niche modeling of avian influenza case occurrences in Middle Eastern poultry.

PubMed

Bodbyl-Roels, Sarah; Peterson, A Townsend; Xiao, Xiangming

2011-03-28

Ecological niche modeling integrates known sites of occurrence of species or phenomena with data on environmental variation across landscapes to infer environmental spaces potentially inhabited (i.e., the ecological niche) to generate predictive maps of potential distributions in geographic space. Key inputs to this process include raster data layers characterizing spatial variation in environmental parameters, such as vegetation indices from remotely sensed satellite imagery. The extent to which ecological niche models reflect real-world distributions depends on a number of factors, but an obvious concern is the quality and content of the environmental data layers. We assessed ecological niche model predictions of H5N1 avian flu presence quantitatively within and among four geographic regions, based on models incorporating two means of summarizing three vegetation indices derived from the MODIS satellite. We evaluated our models for predictive ability using partial ROC analysis and GLM ANOVA to compare performance among indices and regions. We found correlations between vegetation indices to be high, such that they contain information that overlaps broadly. Neither the type of vegetation index used nor method of summary affected model performance significantly. However, the degree to which model predictions had to be transferred (i.e., projected onto landscapes and conditions not represented on the landscape of training) impacted predictive strength greatly (within-region model predictions far out-performed models projected among regions). Our results provide the first quantitative tests of most appropriate uses of different remotely sensed data sets in ecological niche modeling applications. While our testing did not result in a decisive "best" index product or means of summarizing indices, it emphasizes the need for careful evaluation of products used in modeling (e.g. matching temporal dimensions and spatial resolution) for optimum performance, instead of simple reliance on large numbers of data layers.

Joint use of over- and under-sampling techniques and cross-validation for the development and assessment of prediction models.

PubMed

Blagus, Rok; Lusa, Lara

2015-11-04

Prediction models are used in clinical research to develop rules that can be used to accurately predict the outcome of the patients based on some of their characteristics. They represent a valuable tool in the decision making process of clinicians and health policy makers, as they enable them to estimate the probability that patients have or will develop a disease, will respond to a treatment, or that their disease will recur. The interest devoted to prediction models in the biomedical community has been growing in the last few years. Often the data used to develop the prediction models are class-imbalanced as only few patients experience the event (and therefore belong to minority class). Prediction models developed using class-imbalanced data tend to achieve sub-optimal predictive accuracy in the minority class. This problem can be diminished by using sampling techniques aimed at balancing the class distribution. These techniques include under- and oversampling, where a fraction of the majority class samples are retained in the analysis or new samples from the minority class are generated. The correct assessment of how the prediction model is likely to perform on independent data is of crucial importance; in the absence of an independent data set, cross-validation is normally used. While the importance of correct cross-validation is well documented in the biomedical literature, the challenges posed by the joint use of sampling techniques and cross-validation have not been addressed. We show that care must be taken to ensure that cross-validation is performed correctly on sampled data, and that the risk of overestimating the predictive accuracy is greater when oversampling techniques are used. Examples based on the re-analysis of real datasets and simulation studies are provided. We identify some results from the biomedical literature where the incorrect cross-validation was performed, where we expect that the performance of oversampling techniques was heavily overestimated.

Validation of High Frequency (HF) Propagation Prediction Models in the Arctic region

NASA Astrophysics Data System (ADS)

Athieno, R.; Jayachandran, P. T.

2014-12-01

Despite the emergence of modern techniques for long distance communication, Ionospheric communication in the high frequency (HF) band (3-30 MHz) remains significant to both civilian and military users. However, the efficient use of the ever-varying ionosphere as a propagation medium is dependent on the reliability of ionospheric and HF propagation prediction models. Most available models are empirical implying that data collection has to be sufficiently large to provide good intended results. The models we present were developed with little data from the high latitudes which necessitates their validation. This paper presents the validation of three long term High Frequency (HF) propagation prediction models over a path within the Arctic region. Measurements of the Maximum Usable Frequency for a 3000 km range (MUF (3000) F2) for Resolute, Canada (74.75° N, 265.00° E), are obtained from hand-scaled ionograms generated by the Canadian Advanced Digital Ionosonde (CADI). The observations have been compared with predictions obtained from the Ionospheric Communication Enhanced Profile Analysis Program (ICEPAC), Voice of America Coverage Analysis Program (VOACAP) and International Telecommunication Union Recommendation 533 (ITU-REC533) for 2009, 2011, 2012 and 2013. A statistical analysis shows that the monthly predictions seem to reproduce the general features of the observations throughout the year though it is more evident in the winter and equinox months. Both predictions and observations show a diurnal and seasonal variation. The analysed models did not show large differences in their performances. However, there are noticeable differences across seasons for the entire period analysed: REC533 gives a better performance in winter months while VOACAP has a better performance for both equinox and summer months. VOACAP gives a better performance in the daily predictions compared to ICEPAC though, in general, the monthly predictions seem to agree more with the observations compared to the daily predictions.

Evaluation of internal noise methods for Hotelling observers

NASA Astrophysics Data System (ADS)

Zhang, Yani; Pham, Binh T.; Eckstein, Miguel P.

2005-04-01

Including internal noise in computer model observers to degrade model observer performance to human levels is a common method to allow for quantitatively comparisons of human and model performance. In this paper, we studied two different types of methods for injecting internal noise to Hotelling model observers. The first method adds internal noise to the output of the individual channels: a) Independent non-uniform channel noise, b) Independent uniform channel noise. The second method adds internal noise to the decision variable arising from the combination of channel responses: a) internal noise standard deviation proportional to decision variable's standard deviation due to the external noise, b) internal noise standard deviation proportional to decision variable's variance caused by the external noise. We tested the square window Hotelling observer (HO), channelized Hotelling observer (CHO), and Laguerre-Gauss Hotelling observer (LGHO). The studied task was detection of a filling defect of varying size/shape in one of four simulated arterial segment locations with real x-ray angiography backgrounds. Results show that the internal noise method that leads to the best prediction of human performance differs across the studied models observers. The CHO model best predicts human observer performance with the channel internal noise. The HO and LGHO best predict human observer performance with the decision variable internal noise. These results might help explain why previous studies have found different results on the ability of each Hotelling model to predict human performance. Finally, the present results might guide researchers with the choice of method to include internal noise into their Hotelling models.

Human and server docking prediction for CAPRI round 30-35 using LZerD with combined scoring functions.

PubMed

Peterson, Lenna X; Kim, Hyungrae; Esquivel-Rodriguez, Juan; Roy, Amitava; Han, Xusi; Shin, Woong-Hee; Zhang, Jian; Terashi, Genki; Lee, Matt; Kihara, Daisuke

2017-03-01

We report the performance of protein-protein docking predictions by our group for recent rounds of the Critical Assessment of Prediction of Interactions (CAPRI), a community-wide assessment of state-of-the-art docking methods. Our prediction procedure uses a protein-protein docking program named LZerD developed in our group. LZerD represents a protein surface with 3D Zernike descriptors (3DZD), which are based on a mathematical series expansion of a 3D function. The appropriate soft representation of protein surface with 3DZD makes the method more tolerant to conformational change of proteins upon docking, which adds an advantage for unbound docking. Docking was guided by interface residue prediction performed with BindML and cons-PPISP as well as literature information when available. The generated docking models were ranked by a combination of scoring functions, including PRESCO, which evaluates the native-likeness of residues' spatial environments in structure models. First, we discuss the overall performance of our group in the CAPRI prediction rounds and investigate the reasons for unsuccessful cases. Then, we examine the performance of several knowledge-based scoring functions and their combinations for ranking docking models. It was found that the quality of a pool of docking models generated by LZerD, that is whether or not the pool includes near-native models, can be predicted by the correlation of multiple scores. Although the current analysis used docking models generated by LZerD, findings on scoring functions are expected to be universally applicable to other docking methods. Proteins 2017; 85:513-527. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.

PubMed

Stylianou, Neophytos; Akbarov, Artur; Kontopantelis, Evangelos; Buchan, Iain; Dunn, Ken W

2015-08-01

Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn. An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts. Copyright © 2015 Elsevier Ltd and ISBI. All rights reserved.

Prediction of Slot Shape and Slot Size for Improving the Performance of Microstrip Antennas Using Knowledge-Based Neural Networks.

PubMed

Khan, Taimoor; De, Asok

2014-01-01

In the last decade, artificial neural networks have become very popular techniques for computing different performance parameters of microstrip antennas. The proposed work illustrates a knowledge-based neural networks model for predicting the appropriate shape and accurate size of the slot introduced on the radiating patch for achieving desired level of resonance, gain, directivity, antenna efficiency, and radiation efficiency for dual-frequency operation. By incorporating prior knowledge in neural model, the number of required training patterns is drastically reduced. Further, the neural model incorporated with prior knowledge can be used for predicting response in extrapolation region beyond the training patterns region. For validation, a prototype is also fabricated and its performance parameters are measured. A very good agreement is attained between measured, simulated, and predicted results.

Prediction of Slot Shape and Slot Size for Improving the Performance of Microstrip Antennas Using Knowledge-Based Neural Networks

PubMed Central

De, Asok

2014-01-01

In the last decade, artificial neural networks have become very popular techniques for computing different performance parameters of microstrip antennas. The proposed work illustrates a knowledge-based neural networks model for predicting the appropriate shape and accurate size of the slot introduced on the radiating patch for achieving desired level of resonance, gain, directivity, antenna efficiency, and radiation efficiency for dual-frequency operation. By incorporating prior knowledge in neural model, the number of required training patterns is drastically reduced. Further, the neural model incorporated with prior knowledge can be used for predicting response in extrapolation region beyond the training patterns region. For validation, a prototype is also fabricated and its performance parameters are measured. A very good agreement is attained between measured, simulated, and predicted results. PMID:27382616

Static and transient performance prediction for CFB boilers using a Bayesian-Gaussian Neural Network

NASA Astrophysics Data System (ADS)

Ye, Haiwen; Ni, Weidou

1997-06-01

A Bayesian-Gaussian Neural Network (BGNN) is put forward in this paper to predict the static and transient performance of Circulating Fluidized Bed (CFB) boilers. The advantages of this network over Back-Propagation Neural Networks (BPNNs), easier determination of topology, simpler and time saving in training process as well as self-organizing ability, make this network more practical in on-line performance prediction for complicated processes. Simulation shows that this network is comparable to the BPNNs in predicting the performance of CFB boilers. Good and practical on-line performance predictions are essential for operation guide and model predictive control of CFB boilers, which are under research by the authors.

Inter-comparison of time series models of lake levels predicted by several modeling strategies

NASA Astrophysics Data System (ADS)

Khatibi, R.; Ghorbani, M. A.; Naghipour, L.; Jothiprakash, V.; Fathima, T. A.; Fazelifard, M. H.

2014-04-01

Five modeling strategies are employed to analyze water level time series of six lakes with different physical characteristics such as shape, size, altitude and range of variations. The models comprise chaos theory, Auto-Regressive Integrated Moving Average (ARIMA) - treated for seasonality and hence SARIMA, Artificial Neural Networks (ANN), Gene Expression Programming (GEP) and Multiple Linear Regression (MLR). Each is formulated on a different premise with different underlying assumptions. Chaos theory is elaborated in a greater detail as it is customary to identify the existence of chaotic signals by a number of techniques (e.g. average mutual information and false nearest neighbors) and future values are predicted using the Nonlinear Local Prediction (NLP) technique. This paper takes a critical view of past inter-comparison studies seeking a superior performance, against which it is reported that (i) the performances of all five modeling strategies vary from good to poor, hampering the recommendation of a clear-cut predictive model; (ii) the performances of the datasets of two cases are consistently better with all five modeling strategies; (iii) in other cases, their performances are poor but the results can still be fit-for-purpose; (iv) the simultaneous good performances of NLP and SARIMA pull their underlying assumptions to different ends, which cannot be reconciled. A number of arguments are presented including the culture of pluralism, according to which the various modeling strategies facilitate an insight into the data from different vantages.

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

NASA Astrophysics Data System (ADS)

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

2013-10-01

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

United3D: a protein model quality assessment program that uses two consensus based methods.

PubMed

Terashi, Genki; Oosawa, Makoto; Nakamura, Yuuki; Kanou, Kazuhiko; Takeda-Shitaka, Mayuko

2012-01-01

In protein structure prediction, such as template-based modeling and free modeling (ab initio modeling), the step that assesses the quality of protein models is very important. We have developed a model quality assessment (QA) program United3D that uses an optimized clustering method and a simple Cα atom contact-based potential. United3D automatically estimates the quality scores (Qscore) of predicted protein models that are highly correlated with the actual quality (GDT_TS). The performance of United3D was tested in the ninth Critical Assessment of protein Structure Prediction (CASP9) experiment. In CASP9, United3D showed the lowest average loss of GDT_TS (5.3) among the QA methods participated in CASP9. This result indicates that the performance of United3D to identify the high quality models from the models predicted by CASP9 servers on 116 targets was best among the QA methods that were tested in CASP9. United3D also produced high average Pearson correlation coefficients (0.93) and acceptable Kendall rank correlation coefficients (0.68) between the Qscore and GDT_TS. This performance was competitive with the other top ranked QA methods that were tested in CASP9. These results indicate that United3D is a useful tool for selecting high quality models from many candidate model structures provided by various modeling methods. United3D will improve the accuracy of protein structure prediction.

A Sensor Dynamic Measurement Error Prediction Model Based on NAPSO-SVM.

PubMed

Jiang, Minlan; Jiang, Lan; Jiang, Dingde; Li, Fei; Song, Houbing

2018-01-15

Dynamic measurement error correction is an effective way to improve sensor precision. Dynamic measurement error prediction is an important part of error correction, and support vector machine (SVM) is often used for predicting the dynamic measurement errors of sensors. Traditionally, the SVM parameters were always set manually, which cannot ensure the model's performance. In this paper, a SVM method based on an improved particle swarm optimization (NAPSO) is proposed to predict the dynamic measurement errors of sensors. Natural selection and simulated annealing are added in the PSO to raise the ability to avoid local optima. To verify the performance of NAPSO-SVM, three types of algorithms are selected to optimize the SVM's parameters: the particle swarm optimization algorithm (PSO), the improved PSO optimization algorithm (NAPSO), and the glowworm swarm optimization (GSO). The dynamic measurement error data of two sensors are applied as the test data. The root mean squared error and mean absolute percentage error are employed to evaluate the prediction models' performances. The experimental results show that among the three tested algorithms the NAPSO-SVM method has a better prediction precision and a less prediction errors, and it is an effective method for predicting the dynamic measurement errors of sensors.

Physically based approaches incorporating evaporation for early warning predictions of rainfall-induced landslides

NASA Astrophysics Data System (ADS)

Reder, Alfredo; Rianna, Guido; Pagano, Luca

2018-02-01

In the field of rainfall-induced landslides on sloping covers, models for early warning predictions require an adequate trade-off between two aspects: prediction accuracy and timeliness. When a cover's initial hydrological state is a determining factor in triggering landslides, taking evaporative losses into account (or not) could significantly affect both aspects. This study evaluates the performance of three physically based predictive models, converting precipitation and evaporative fluxes into hydrological variables useful in assessing slope safety conditions. Two of the models incorporate evaporation, with one representing evaporation as both a boundary and internal phenomenon, and the other only a boundary phenomenon. The third model totally disregards evaporation. Model performances are assessed by analysing a well-documented case study involving a 2 m thick sloping volcanic cover. The large amount of monitoring data collected for the soil involved in the case study, reconstituted in a suitably equipped lysimeter, makes it possible to propose procedures for calibrating and validating the parameters of the models. All predictions indicate a hydrological singularity at the landslide time (alarm). A comparison of the models' predictions also indicates that the greater the complexity and completeness of the model, the lower the number of predicted hydrological singularities when no landslides occur (false alarms).

Climate Prediction for Brazil's Nordeste: Performance of Empirical and Numerical Modeling Methods.

NASA Astrophysics Data System (ADS)

Moura, Antonio Divino; Hastenrath, Stefan

2004-07-01

Comparisons of performance of climate forecast methods require consistency in the predictand and a long common reference period. For Brazil's Nordeste, empirical methods developed at the University of Wisconsin use preseason (October January) rainfall and January indices of the fields of meridional wind component and sea surface temperature (SST) in the tropical Atlantic and the equatorial Pacific as input to stepwise multiple regression and neural networking. These are used to predict the March June rainfall at a network of 27 stations. An experiment at the International Research Institute for Climate Prediction, Columbia University, with a numerical model (ECHAM4.5) used global SST information through February to predict the March June rainfall at three grid points in the Nordeste. The predictands for the empirical and numerical model forecasts are correlated at +0.96, and the period common to the independent portion of record of the empirical prediction and the numerical modeling is 1968 99. Over this period, predicted versus observed rainfall are evaluated in terms of correlation, root-mean-square error, absolute error, and bias. Performance is high for both approaches. Numerical modeling produces a correlation of +0.68, moderate errors, and strong negative bias. For the empirical methods, errors and bias are small, and correlations of +0.73 and +0.82 are reached between predicted and observed rainfall.

Software reliability studies

NASA Technical Reports Server (NTRS)

Hoppa, Mary Ann; Wilson, Larry W.

1994-01-01

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

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

Smith, Kandler A; Santhanagopalan, Shriram; Yang, Chuanbo

Computer models are helping to accelerate the design and validation of next generation batteries and provide valuable insights not possible through experimental testing alone. Validated 3-D physics-based models exist for predicting electrochemical performance, thermal and mechanical response of cells and packs under normal and abuse scenarios. The talk describes present efforts to make the models better suited for engineering design, including improving their computation speed, developing faster processes for model parameter identification including under aging, and predicting the performance of a proposed electrode material recipe a priori using microstructure models.

Test anxiety and academic performance in chiropractic students.

PubMed

Zhang, Niu; Henderson, Charles N R

2014-01-01

Objective : We assessed the level of students' test anxiety, and the relationship between test anxiety and academic performance. Methods : We recruited 166 third-quarter students. The Test Anxiety Inventory (TAI) was administered to all participants. Total scores from written examinations and objective structured clinical examinations (OSCEs) were used as response variables. Results : Multiple regression analysis shows that there was a modest, but statistically significant negative correlation between TAI scores and written exam scores, but not OSCE scores. Worry and emotionality were the best predictive models for written exam scores. Mean total anxiety and emotionality scores for females were significantly higher than those for males, but not worry scores. Conclusion : Moderate-to-high test anxiety was observed in 85% of the chiropractic students examined. However, total test anxiety, as measured by the TAI score, was a very weak predictive model for written exam performance. Multiple regression analysis demonstrated that replacing total anxiety (TAI) with worry and emotionality (TAI subscales) produces a much more effective predictive model of written exam performance. Sex, age, highest current academic degree, and ethnicity contributed little additional predictive power in either regression model. Moreover, TAI scores were not found to be statistically significant predictors of physical exam skill performance, as measured by OSCEs.

Multimodel predictive system for carbon dioxide solubility in saline formation waters.

PubMed

Wang, Zan; Small, Mitchell J; Karamalidis, Athanasios K

2013-02-05

The prediction of carbon dioxide solubility in brine at conditions relevant to carbon sequestration (i.e., high temperature, pressure, and salt concentration (T-P-X)) is crucial when this technology is applied. Eleven mathematical models for predicting CO(2) solubility in brine are compared and considered for inclusion in a multimodel predictive system. Model goodness of fit is evaluated over the temperature range 304-433 K, pressure range 74-500 bar, and salt concentration range 0-7 m (NaCl equivalent), using 173 published CO(2) solubility measurements, particularly selected for those conditions. The performance of each model is assessed using various statistical methods, including the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC). Different models emerge as best fits for different subranges of the input conditions. A classification tree is generated using machine learning methods to predict the best-performing model under different T-P-X subranges, allowing development of a multimodel predictive system (MMoPS) that selects and applies the model expected to yield the most accurate CO(2) solubility prediction. Statistical analysis of the MMoPS predictions, including a stratified 5-fold cross validation, shows that MMoPS outperforms each individual model and increases the overall accuracy of CO(2) solubility prediction across the range of T-P-X conditions likely to be encountered in carbon sequestration applications.

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

PubMed Central

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

2016-01-01

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

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

PubMed

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

2016-05-11

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

On the predictive information criteria for model determination in seismic hazard analysis

NASA Astrophysics Data System (ADS)

Varini, Elisa; Rotondi, Renata

2016-04-01

Many statistical tools have been developed for evaluating, understanding, and comparing models, from both frequentist and Bayesian perspectives. In particular, the problem of model selection can be addressed according to whether the primary goal is explanation or, alternatively, prediction. In the former case, the criteria for model selection are defined over the parameter space whose physical interpretation can be difficult; in the latter case, they are defined over the space of the observations, which has a more direct physical meaning. In the frequentist approaches, model selection is generally based on an asymptotic approximation which may be poor for small data sets (e.g. the F-test, the Kolmogorov-Smirnov test, etc.); moreover, these methods often apply under specific assumptions on models (e.g. models have to be nested in the likelihood ratio test). In the Bayesian context, among the criteria for explanation, the ratio of the observed marginal densities for two competing models, named Bayes Factor (BF), is commonly used for both model choice and model averaging (Kass and Raftery, J. Am. Stat. Ass., 1995). But BF does not apply to improper priors and, even when the prior is proper, it is not robust to the specification of the prior. These limitations can be extended to two famous penalized likelihood methods as the Akaike Information Criterion (AIC) and the Bayesian Information Criterion (BIC), since they are proved to be approximations of -2log BF . In the perspective that a model is as good as its predictions, the predictive information criteria aim at evaluating the predictive accuracy of Bayesian models or, in other words, at estimating expected out-of-sample prediction error using a bias-correction adjustment of within-sample error (Gelman et al., Stat. Comput., 2014). In particular, the Watanabe criterion is fully Bayesian because it averages the predictive distribution over the posterior distribution of parameters rather than conditioning on a point estimate, but it is hardly applicable to data which are not independent given parameters (Watanabe, J. Mach. Learn. Res., 2010). A solution is given by Ando and Tsay criterion where the joint density may be decomposed into the product of the conditional densities (Ando and Tsay, Int. J. Forecast., 2010). The above mentioned criteria are global summary measures of model performance, but more detailed analysis could be required to discover the reasons for poor global performance. In this latter case, a retrospective predictive analysis is performed on each individual observation. In this study we performed the Bayesian analysis of Italian data sets by four versions of a long-term hazard model known as the stress release model (Vere-Jones, J. Physics Earth, 1978; Bebbington and Harte, Geophys. J. Int., 2003; Varini and Rotondi, Environ. Ecol. Stat., 2015). Then we illustrate the results on their performance evaluated by Bayes Factor, predictive information criteria and retrospective predictive analysis.

Predicting the Impacts of Intravehicular Displays on Driving Performance with Human Performance Modeling

NASA Technical Reports Server (NTRS)

Mitchell, Diane Kuhl; Wojciechowski, Josephine; Samms, Charneta

2012-01-01

A challenge facing the U.S. National Highway Traffic Safety Administration (NHTSA), as well as international safety experts, is the need to educate car drivers about the dangers associated with performing distraction tasks while driving. Researchers working for the U.S. Army Research Laboratory have developed a technique for predicting the increase in mental workload that results when distraction tasks are combined with driving. They implement this technique using human performance modeling. They have predicted workload associated with driving combined with cell phone use. In addition, they have predicted the workload associated with driving military vehicles combined with threat detection. Their technique can be used by safety personnel internationally to demonstrate the dangers of combining distracter tasks with driving and to mitigate the safety risks.

Comprehensive and critical review of the predictive properties of the various mass models

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

Haustein, P.E.

1984-01-01

Since the publication of the 1975 Mass Predictions approximately 300 new atomic masses have been reported. These data come from a variety of experimental studies using diverse techniques and they span a mass range from the lightest isotopes to the very heaviest. It is instructive to compare these data with the 1975 predictions and several others (Moeller and Nix, Monahan, Serduke, Uno and Yamada which appeared latter. Extensive numerical and graphical analyses have been performed to examine the quality of the mass predictions from the various models and to identify features in these models that require correction. In general, theremore » is only rough correlation between the ability of a particular model to reproduce the measured mass surface which had been used to refine its adjustable parameters and that model's ability to predict correctly the new masses. For some models distinct systematic features appear when the new mass data are plotted as functions of relevant physical variables. Global intercomparisons of all the models are made first, followed by several examples of types of analysis performed with individual mass models.« less

How many sightings to model rare marine species distributions

PubMed Central

Authier, Matthieu; Monestiez, Pascal; Ridoux, Vincent

2018-01-01

Despite large efforts, datasets with few sightings are often available for rare species of marine megafauna that typically live at low densities. This paucity of data makes modelling the habitat of these taxa particularly challenging. We tested the predictive performance of different types of species distribution models fitted to decreasing numbers of sightings. Generalised additive models (GAMs) with three different residual distributions and the presence only model MaxEnt were tested on two megafauna case studies differing in both the number of sightings and ecological niches. From a dolphin (277 sightings) and an auk (1,455 sightings) datasets, we simulated rarity with a sighting thinning protocol by random sampling (without replacement) of a decreasing fraction of sightings. Better prediction of the distribution of a rarely sighted species occupying a narrow habitat (auk dataset) was expected compared to the distribution of a rarely sighted species occupying a broad habitat (dolphin dataset). We used the original datasets to set up a baseline model and fitted additional models on fewer sightings but keeping effort constant. Model predictive performance was assessed with mean squared error and area under the curve. Predictions provided by the models fitted to the thinned-out datasets were better than a homogeneous spatial distribution down to a threshold of approximately 30 sightings for a GAM with a Tweedie distribution and approximately 130 sightings for the other models. Thinning the sighting data for the taxon with narrower habitats seemed to be less detrimental to model predictive performance than for the broader habitat taxon. To generate reliable habitat modelling predictions for rarely sighted marine predators, our results suggest (1) using GAMs with a Tweedie distribution with presence-absence data and (2) implementing, as a conservative empirical measure, at least 50 sightings in the models. PMID:29529097

A Novel RSSI Prediction Using Imperialist Competition Algorithm (ICA), Radial Basis Function (RBF) and Firefly Algorithm (FFA) in Wireless Networks.

PubMed

Goudarzi, Shidrokh; Haslina Hassan, Wan; Abdalla Hashim, Aisha-Hassan; Soleymani, Seyed Ahmad; Anisi, Mohammad Hossein; Zakaria, Omar M

2016-01-01

This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF-FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model's performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF-FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF-FFA model can be applied as an efficient technique for the accurate prediction of vertical handover.

Individualized prediction of perineural invasion in colorectal cancer: development and validation of a radiomics prediction model.

PubMed

Huang, Yanqi; He, Lan; Dong, Di; Yang, Caiyun; Liang, Cuishan; Chen, Xin; Ma, Zelan; Huang, Xiaomei; Yao, Su; Liang, Changhong; Tian, Jie; Liu, Zaiyi

2018-02-01

To develop and validate a radiomics prediction model for individualized prediction of perineural invasion (PNI) in colorectal cancer (CRC). After computed tomography (CT) radiomics features extraction, a radiomics signature was constructed in derivation cohort (346 CRC patients). A prediction model was developed to integrate the radiomics signature and clinical candidate predictors [age, sex, tumor location, and carcinoembryonic antigen (CEA) level]. Apparent prediction performance was assessed. After internal validation, independent temporal validation (separate from the cohort used to build the model) was then conducted in 217 CRC patients. The final model was converted to an easy-to-use nomogram. The developed radiomics nomogram that integrated the radiomics signature and CEA level showed good calibration and discrimination performance [Harrell's concordance index (c-index): 0.817; 95% confidence interval (95% CI): 0.811-0.823]. Application of the nomogram in validation cohort gave a comparable calibration and discrimination (c-index: 0.803; 95% CI: 0.794-0.812). Integrating the radiomics signature and CEA level into a radiomics prediction model enables easy and effective risk assessment of PNI in CRC. This stratification of patients according to their PNI status may provide a basis for individualized auxiliary treatment.

Characterization and validation of an in silico toxicology model to predict the mutagenic potential of drug impurities*

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

Valerio, Luis G., E-mail: luis.valerio@fda.hhs.gov; Cross, Kevin P.

Control and minimization of human exposure to potential genotoxic impurities found in drug substances and products is an important part of preclinical safety assessments of new drug products. The FDA's 2008 draft guidance on genotoxic and carcinogenic impurities in drug substances and products allows use of computational quantitative structure–activity relationships (QSAR) to identify structural alerts for known and expected impurities present at levels below qualified thresholds. This study provides the information necessary to establish the practical use of a new in silico toxicology model for predicting Salmonella t. mutagenicity (Ames assay outcome) of drug impurities and other chemicals. We describemore » the model's chemical content and toxicity fingerprint in terms of compound space, molecular and structural toxicophores, and have rigorously tested its predictive power using both cross-validation and external validation experiments, as well as case studies. Consistent with desired regulatory use, the model performs with high sensitivity (81%) and high negative predictivity (81%) based on external validation with 2368 compounds foreign to the model and having known mutagenicity. A database of drug impurities was created from proprietary FDA submissions and the public literature which found significant overlap between the structural features of drug impurities and training set chemicals in the QSAR model. Overall, the model's predictive performance was found to be acceptable for screening drug impurities for Salmonella mutagenicity. -- Highlights: ► We characterize a new in silico model to predict mutagenicity of drug impurities. ► The model predicts Salmonella mutagenicity and will be useful for safety assessment. ► We examine toxicity fingerprints and toxicophores of this Ames assay model. ► We compare these attributes to those found in drug impurities known to FDA/CDER. ► We validate the model and find it has a desired predictive performance.« less

Metabolomics biomarkers to predict acamprosate treatment response in alcohol-dependent subjects.

PubMed

Hinton, David J; Vázquez, Marely Santiago; Geske, Jennifer R; Hitschfeld, Mario J; Ho, Ada M C; Karpyak, Victor M; Biernacka, Joanna M; Choi, Doo-Sup

2017-05-31

Precision medicine for alcohol use disorder (AUD) allows optimal treatment of the right patient with the right drug at the right time. Here, we generated multivariable models incorporating clinical information and serum metabolite levels to predict acamprosate treatment response. The sample of 120 patients was randomly split into a training set (n = 80) and test set (n = 40) five independent times. Treatment response was defined as complete abstinence (no alcohol consumption during 3 months of acamprosate treatment) while nonresponse was defined as any alcohol consumption during this period. In each of the five training sets, we built a predictive model using a least absolute shrinkage and section operator (LASSO) penalized selection method and then evaluated the predictive performance of each model in the corresponding test set. The models predicted acamprosate treatment response with a mean sensitivity and specificity in the test sets of 0.83 and 0.31, respectively, suggesting our model performed well at predicting responders, but not non-responders (i.e. many non-responders were predicted to respond). Studies with larger sample sizes and additional biomarkers will expand the clinical utility of predictive algorithms for pharmaceutical response in AUD.

Using a Guided Machine Learning Ensemble Model to Predict Discharge Disposition following Meningioma Resection.

PubMed

Muhlestein, Whitney E; Akagi, Dallin S; Kallos, Justiss A; Morone, Peter J; Weaver, Kyle D; Thompson, Reid C; Chambless, Lola B

2018-04-01

Objective  Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods  A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results  Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p  = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion  Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

Prediction of the diffuse-field transmission loss of interior natural-ventilation openings and silencers.

PubMed

Bibby, Chris; Hodgson, Murray

2017-01-01

The work reported here, part of a study on the performance and optimal design of interior natural-ventilation openings and silencers ("ventilators"), discusses the prediction of the acoustical performance of such ventilators, and the factors that affect it. A wave-based numerical approach-the finite-element method (FEM)-is applied. The development of a FEM technique for the prediction of ventilator diffuse-field transmission loss is presented. Model convergence is studied with respect to mesh, frequency-sampling and diffuse-field convergence. The modeling technique is validated by way of predictions and the comparison of them to analytical and experimental results. The transmission-loss performance of crosstalk silencers of four shapes, and the factors that affect it, are predicted and discussed. Performance increases with flow-path length for all silencer types. Adding elbows significantly increases high-frequency transmission loss, but does not increase overall silencer performance which is controlled by low-to-mid-frequency transmission loss.

Stock price change rate prediction by utilizing social network activities.

PubMed

Deng, Shangkun; Mitsubuchi, Takashi; Sakurai, Akito

2014-01-01

Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques.

Stock Price Change Rate Prediction by Utilizing Social Network Activities

PubMed Central

Mitsubuchi, Takashi; Sakurai, Akito

2014-01-01

Predicting stock price change rates for providing valuable information to investors is a challenging task. Individual participants may express their opinions in social network service (SNS) before or after their transactions in the market; we hypothesize that stock price change rate is better predicted by a function of social network service activities and technical indicators than by a function of just stock market activities. The hypothesis is tested by accuracy of predictions as well as performance of simulated trading because success or failure of prediction is better measured by profits or losses the investors gain or suffer. In this paper, we propose a hybrid model that combines multiple kernel learning (MKL) and genetic algorithm (GA). MKL is adopted to optimize the stock price change rate prediction models that are expressed in a multiple kernel linear function of different types of features extracted from different sources. GA is used to optimize the trading rules used in the simulated trading by fusing the return predictions and values of three well-known overbought and oversold technical indicators. Accumulated return and Sharpe ratio were used to test the goodness of performance of the simulated trading. Experimental results show that our proposed model performed better than other models including ones using state of the art techniques. PMID:24790586

Systematic review and retrospective validation of prediction models for weight loss after bariatric surgery.

PubMed

Sharples, Alistair J; Mahawar, Kamal; Cheruvu, Chandra V N

2017-11-01

Patients often have less than realistic expectations of the weight loss they are likely to achieve after bariatric surgery. It would be useful to have a well-validated prediction tool that could give patients a realistic estimate of their expected weight loss. To perform a systematic review of the literature to identify existing prediction models and attempt to validate these models. University hospital, United Kingdom. A systematic review was performed. All English language studies were included if they used data to create a prediction model for postoperative weight loss after bariatric surgery. These models were then tested on patients undergoing bariatric surgery between January 1, 2013 and December 31, 2014 within our unit. An initial literature search produced 446 results, of which only 4 were included in the final review. Our study population included 317 patients. Mean preoperative body mass index was 46.1 ± 7.1. For 257 (81.1%) patients, 12-month follow-up was available, and mean body mass index and percentage excess weight loss at 12 months was 33.0 ± 6.7 and 66.1% ± 23.7%, respectively. All 4 of the prediction models significantly overestimated the amount of weight loss achieved by patients. The best performing prediction model in our series produced a correlation coefficient (R 2 ) of .61 and an area under the curve of .71 on receiver operating curve analysis. All prediction models overestimated weight loss after bariatric surgery in our cohort. There is a need to develop better procedures and patient-specific models for better patient counselling. Copyright © 2017 American Society for Bariatric Surgery. Published by Elsevier Inc. All rights reserved.

Genomic prediction in a nuclear population of layers using single-step models.

PubMed

Yan, Yiyuan; Wu, Guiqin; Liu, Aiqiao; Sun, Congjiao; Han, Wenpeng; Li, Guangqi; Yang, Ning

2018-02-01

Single-step genomic prediction method has been proposed to improve the accuracy of genomic prediction by incorporating information of both genotyped and ungenotyped animals. The objective of this study is to compare the prediction performance of single-step model with a 2-step models and the pedigree-based models in a nuclear population of layers. A total of 1,344 chickens across 4 generations were genotyped by a 600 K SNP chip. Four traits were analyzed, i.e., body weight at 28 wk (BW28), egg weight at 28 wk (EW28), laying rate at 38 wk (LR38), and Haugh unit at 36 wk (HU36). In predicting offsprings, individuals from generation 1 to 3 were used as training data and females from generation 4 were used as validation set. The accuracies of predicted breeding values by pedigree BLUP (PBLUP), genomic BLUP (GBLUP), SSGBLUP and single-step blending (SSBlending) were compared for both genotyped and ungenotyped individuals. For genotyped females, GBLUP performed no better than PBLUP because of the small size of training data, while the 2 single-step models predicted more accurately than the PBLUP model. The average predictive ability of SSGBLUP and SSBlending were 16.0% and 10.8% higher than the PBLUP model across traits, respectively. Furthermore, the predictive abilities for ungenotyped individuals were also enhanced. The average improvements of prediction abilities were 5.9% and 1.5% for SSGBLUP and SSBlending model, respectively. It was concluded that single-step models, especially the SSGBLUP model, can yield more accurate prediction of genetic merits and are preferable for practical implementation of genomic selection in layers. © 2017 Poultry Science Association Inc.

A Probabilistic Strategy for Understanding Action Selection

PubMed Central

Kim, Byounghoon; Basso, Michele A.

2010-01-01

Brain regions involved in transforming sensory signals into movement commands are the likely sites where decisions are formed. Once formed, a decision must be read-out from the activity of populations of neurons to produce a choice of action. How this occurs remains unresolved. We recorded from four superior colliculus (SC) neurons simultaneously while monkeys performed a target selection task. We implemented three models to gain insight into the computational principles underlying population coding of action selection. We compared the population vector average (PVA), winner-takes-all (WTA) and a Bayesian model, maximum a posteriori estimate (MAP) to determine which predicted choices most often. The probabilistic model predicted more trials correctly than both the WTA and the PVA. The MAP model predicted 81.88% whereas WTA predicted 71.11% and PVA/OLE predicted the least number of trials at 55.71 and 69.47%. Recovering MAP estimates using simulated, non-uniform priors that correlated with monkeys’ choice performance, improved the accuracy of the model by 2.88%. A dynamic analysis revealed that the MAP estimate evolved over time and the posterior probability of the saccade choice reached a maximum at the time of the saccade. MAP estimates also scaled with choice performance accuracy. Although there was overlap in the prediction abilities of all the models, we conclude that movement choice from populations of neurons may be best understood by considering frameworks based on probability. PMID:20147560

Interpretable Deep Models for ICU Outcome Prediction

PubMed Central

Che, Zhengping; Purushotham, Sanjay; Khemani, Robinder; Liu, Yan

2016-01-01

Exponential surge in health care data, such as longitudinal data from electronic health records (EHR), sensor data from intensive care unit (ICU), etc., is providing new opportunities to discover meaningful data-driven characteristics and patterns ofdiseases. Recently, deep learning models have been employedfor many computational phenotyping and healthcare prediction tasks to achieve state-of-the-art performance. However, deep models lack interpretability which is crucial for wide adoption in medical research and clinical decision-making. In this paper, we introduce a simple yet powerful knowledge-distillation approach called interpretable mimic learning, which uses gradient boosting trees to learn interpretable models and at the same time achieves strong prediction performance as deep learning models. Experiment results on Pediatric ICU dataset for acute lung injury (ALI) show that our proposed method not only outperforms state-of-the-art approaches for morality and ventilator free days prediction tasks but can also provide interpretable models to clinicians. PMID:28269832

Driver's mental workload prediction model based on physiological indices.

PubMed

Yan, Shengyuan; Tran, Cong Chi; Wei, Yingying; Habiyaremye, Jean Luc

2017-09-15

Developing an early warning model to predict the driver's mental workload (MWL) is critical and helpful, especially for new or less experienced drivers. The present study aims to investigate the correlation between new drivers' MWL and their work performance, regarding the number of errors. Additionally, the group method of data handling is used to establish the driver's MWL predictive model based on subjective rating (NASA task load index [NASA-TLX]) and six physiological indices. The results indicate that the NASA-TLX and the number of errors are positively correlated, and the predictive model shows the validity of the proposed model with an R 2 value of 0.745. The proposed model is expected to provide a reference value for the new drivers of their MWL by providing the physiological indices, and the driving lesson plans can be proposed to sustain an appropriate MWL as well as improve the driver's work performance.

Development of speed models for improving travel forecasting and highway performance evaluation : [technical summary].

DOT National Transportation Integrated Search

2013-12-01

Travel forecasting models predict travel demand based on the present transportation system and its use. Transportation modelers must develop, validate, and calibrate models to ensure that predicted travel demand is as close to reality as possible. Mo...

Dose-dependent model of caffeine effects on human vigilance during total sleep deprivation.

PubMed

Ramakrishnan, Sridhar; Laxminarayan, Srinivas; Wesensten, Nancy J; Kamimori, Gary H; Balkin, Thomas J; Reifman, Jaques

2014-10-07

Caffeine is the most widely consumed stimulant to counter sleep-loss effects. While the pharmacokinetics of caffeine in the body is well-understood, its alertness-restoring effects are still not well characterized. In fact, mathematical models capable of predicting the effects of varying doses of caffeine on objective measures of vigilance are not available. In this paper, we describe a phenomenological model of the dose-dependent effects of caffeine on psychomotor vigilance task (PVT) performance of sleep-deprived subjects. We used the two-process model of sleep regulation to quantify performance during sleep loss in the absence of caffeine and a dose-dependent multiplier factor derived from the Hill equation to model the effects of single and repeated caffeine doses. We developed and validated the model fits and predictions on PVT lapse (number of reaction times exceeding 500 ms) data from two separate laboratory studies. At the population-average level, the model captured the effects of a range of caffeine doses (50-300 mg), yielding up to a 90% improvement over the two-process model. Individual-specific caffeine models, on average, predicted the effects up to 23% better than population-average caffeine models. The proposed model serves as a useful tool for predicting the dose-dependent effects of caffeine on the PVT performance of sleep-deprived subjects and, therefore, can be used for determining caffeine doses that optimize the timing and duration of peak performance. Published by Elsevier Ltd.

Aerodynamics and thermal physics of helicopter ice accretion

NASA Astrophysics Data System (ADS)

Han, Yiqiang

Ice accretion on aircraft introduces significant loss in airfoil performance. Reduced lift-to- drag ratio reduces the vehicle capability to maintain altitude and also limits its maneuverability. Current ice accretion performance degradation modeling approaches are calibrated only to a limited envelope of liquid water content, impact velocity, temperature, and water droplet size; consequently inaccurate aerodynamic performance degradations are estimated. The reduced ice accretion prediction capabilities in the glaze ice regime are primarily due to a lack of knowledge of surface roughness induced by ice accretion. A comprehensive understanding of the ice roughness effects on airfoil heat transfer, ice accretion shapes, and ultimately aerodynamics performance is critical for the design of ice protection systems. Surface roughness effects on both heat transfer and aerodynamic performance degradation on airfoils have been experimentally evaluated. Novel techniques, such as ice molding and casting methods and transient heat transfer measurement using non-intrusive thermal imaging methods, were developed at the Adverse Environment Rotor Test Stand (AERTS) facility at Penn State. A novel heat transfer scaling method specifically for turbulent flow regime was also conceived. A heat transfer scaling parameter, labeled as Coefficient of Stanton and Reynolds Number (CSR = Stx/Rex --0.2), has been validated against reference data found in the literature for rough flat plates with Reynolds number (Re) up to 1x107, for rough cylinders with Re ranging from 3x104 to 4x106, and for turbine blades with Re from 7.5x105 to 7x106. This is the first time that the effect of Reynolds number is shown to be successfully eliminated on heat transfer magnitudes measured on rough surfaces. Analytical models for ice roughness distribution, heat transfer prediction, and aerodynamics performance degradation due to ice accretion have also been developed. The ice roughness prediction model was developed based on a set of 82 experimental measurements and also compared to existing predictions tools. Two reference predictions found in the literature yielded 76% and 54% discrepancy with respect to experimental testing, whereas the proposed ice roughness prediction model resulted in a 31% minimum accuracy in prediction. It must be noted that the accuracy of the proposed model is within the ice shape reproduction uncertainty of icing facilities. Based on the new ice roughness prediction model and the CSR heat transfer scaling method, an icing heat transfer model was developed. The approach achieved high accuracy in heat transfer prediction compared to experiments conducted at the AERTS facility. The discrepancy between predictions and experimental results was within +/-15%, which was within the measurement uncertainty range of the facility. By combining both the ice roughness and heat transfer predictions, and incorporating the modules into an existing ice prediction tool (LEWICE), improved prediction capability was obtained, especially for the glaze regime. With the available ice shapes accreted at the AERTS facility and additional experiments found in the literature, 490 sets of experimental ice shapes and corresponding aerodynamics testing data were available. A physics-based performance degradation empirical tool was developed and achieved a mean absolute deviation of 33% when compared to the entire experimental dataset, whereas 60% to 243% discrepancies were observed using legacy drag penalty prediction tools. Rotor torque predictions coupling Blade Element Momentum Theory and the proposed drag performance degradation tool was conducted on a total of 17 validation cases. The coupled prediction tool achieved a 10% predicting error for clean rotor conditions, and 16% error for iced rotor conditions. It was shown that additional roughness element could affect the measured drag by up to 25% during experimental testing, emphasizing the need of realistic ice structures during aerodynamics modeling and testing for ice accretion.

Examination of multi-model ensemble seasonal prediction methods using a simple climate system

NASA Astrophysics Data System (ADS)

Kang, In-Sik; Yoo, Jin Ho

2006-02-01

A simple climate model was designed as a proxy for the real climate system, and a number of prediction models were generated by slightly perturbing the physical parameters of the simple model. A set of long (240 years) historical hindcast predictions were performed with various prediction models, which are used to examine various issues of multi-model ensemble seasonal prediction, such as the best ways of blending multi-models and the selection of models. Based on these results, we suggest a feasible way of maximizing the benefit of using multi models in seasonal prediction. In particular, three types of multi-model ensemble prediction systems, i.e., the simple composite, superensemble, and the composite after statistically correcting individual predictions (corrected composite), are examined and compared to each other. The superensemble has more of an overfitting problem than the others, especially for the case of small training samples and/or weak external forcing, and the corrected composite produces the best prediction skill among the multi-model systems.

JUNO Photovoltaic Power at Jupiter

NASA Technical Reports Server (NTRS)

Dawson, Stephen F.; Stella, Paul; McAlpine, William; Smith, Brian

2012-01-01

This paper summarizes the Juno modeling team work on predicting the Juno solar array performance at critical mission points including Juno Orbit Insertion (JOI) and End of Mission (EOM). This report consists of background on Juno solar array design, a summary of power estimates, an explanation of the modeling approach used by Aerospace, a detailed discussion of loss factors and performance predictions, a thermal analysis, and a review of risks to solar array performance

Biological and functional relevance of CASP predictions

PubMed Central

Liu, Tianyun; Ish‐Shalom, Shirbi; Torng, Wen; Lafita, Aleix; Bock, Christian; Mort, Matthew; Cooper, David N; Bliven, Spencer; Capitani, Guido; Mooney, Sean D.

2017-01-01

Abstract Our goal is to answer the question: compared with experimental structures, how useful are predicted models for functional annotation? We assessed the functional utility of predicted models by comparing the performances of a suite of methods for functional characterization on the predictions and the experimental structures. We identified 28 sites in 25 protein targets to perform functional assessment. These 28 sites included nine sites with known ligand binding (holo‐sites), nine sites that are expected or suggested by experimental authors for small molecule binding (apo‐sites), and Ten sites containing important motifs, loops, or key residues with important disease‐associated mutations. We evaluated the utility of the predictions by comparing their microenvironments to the experimental structures. Overall structural quality correlates with functional utility. However, the best‐ranked predictions (global) may not have the best functional quality (local). Our assessment provides an ability to discriminate between predictions with high structural quality. When assessing ligand‐binding sites, most prediction methods have higher performance on apo‐sites than holo‐sites. Some servers show consistently high performance for certain types of functional sites. Finally, many functional sites are associated with protein‐protein interaction. We also analyzed biologically relevant features from the protein assemblies of two targets where the active site spanned the protein‐protein interface. For the assembly targets, we find that the features in the models are mainly determined by the choice of template. PMID:28975675

Using the weighted area under the net benefit curve for decision curve analysis.

PubMed

Talluri, Rajesh; Shete, Sanjay

2016-07-18

Risk prediction models have been proposed for various diseases and are being improved as new predictors are identified. A major challenge is to determine whether the newly discovered predictors improve risk prediction. Decision curve analysis has been proposed as an alternative to the area under the curve and net reclassification index to evaluate the performance of prediction models in clinical scenarios. The decision curve computed using the net benefit can evaluate the predictive performance of risk models at a given or range of threshold probabilities. However, when the decision curves for 2 competing models cross in the range of interest, it is difficult to identify the best model as there is no readily available summary measure for evaluating the predictive performance. The key deterrent for using simple measures such as the area under the net benefit curve is the assumption that the threshold probabilities are uniformly distributed among patients. We propose a novel measure for performing decision curve analysis. The approach estimates the distribution of threshold probabilities without the need of additional data. Using the estimated distribution of threshold probabilities, the weighted area under the net benefit curve serves as the summary measure to compare risk prediction models in a range of interest. We compared 3 different approaches, the standard method, the area under the net benefit curve, and the weighted area under the net benefit curve. Type 1 error and power comparisons demonstrate that the weighted area under the net benefit curve has higher power compared to the other methods. Several simulation studies are presented to demonstrate the improvement in model comparison using the weighted area under the net benefit curve compared to the standard method. The proposed measure improves decision curve analysis by using the weighted area under the curve and thereby improves the power of the decision curve analysis to compare risk prediction models in a clinical scenario.

Comparison of four statistical and machine learning methods for crash severity prediction.

PubMed

Iranitalab, Amirfarrokh; Khattak, Aemal

2017-11-01

Crash severity prediction models enable different agencies to predict the severity of a reported crash with unknown severity or the severity of crashes that may be expected to occur sometime in the future. This paper had three main objectives: comparison of the performance of four statistical and machine learning methods including Multinomial Logit (MNL), Nearest Neighbor Classification (NNC), Support Vector Machines (SVM) and Random Forests (RF), in predicting traffic crash severity; developing a crash costs-based approach for comparison of crash severity prediction methods; and investigating the effects of data clustering methods comprising K-means Clustering (KC) and Latent Class Clustering (LCC), on the performance of crash severity prediction models. The 2012-2015 reported crash data from Nebraska, United States was obtained and two-vehicle crashes were extracted as the analysis data. The dataset was split into training/estimation (2012-2014) and validation (2015) subsets. The four prediction methods were trained/estimated using the training/estimation dataset and the correct prediction rates for each crash severity level, overall correct prediction rate and a proposed crash costs-based accuracy measure were obtained for the validation dataset. The correct prediction rates and the proposed approach showed NNC had the best prediction performance in overall and in more severe crashes. RF and SVM had the next two sufficient performances and MNL was the weakest method. Data clustering did not affect the prediction results of SVM, but KC improved the prediction performance of MNL, NNC and RF, while LCC caused improvement in MNL and RF but weakened the performance of NNC. Overall correct prediction rate had almost the exact opposite results compared to the proposed approach, showing that neglecting the crash costs can lead to misjudgment in choosing the right prediction method. Copyright © 2017 Elsevier Ltd. All rights reserved.

Modeling ready biodegradability of fragrance materials.

PubMed

Ceriani, Lidia; Papa, Ester; Kovarich, Simona; Boethling, Robert; Gramatica, Paola

2015-06-01

In the present study, quantitative structure activity relationships were developed for predicting ready biodegradability of approximately 200 heterogeneous fragrance materials. Two classification methods, classification and regression tree (CART) and k-nearest neighbors (kNN), were applied to perform the modeling. The models were validated with multiple external prediction sets, and the structural applicability domain was verified by the leverage approach. The best models had good sensitivity (internal ≥80%; external ≥68%), specificity (internal ≥80%; external 73%), and overall accuracy (≥75%). Results from the comparison with BIOWIN global models, based on group contribution method, show that specific models developed in the present study perform better in prediction than BIOWIN6, in particular for the correct classification of not readily biodegradable fragrance materials. © 2015 SETAC.

Applying Risk Prediction Models to Optimize Lung Cancer Screening: Current Knowledge, Challenges, and Future Directions.

PubMed

Sakoda, Lori C; Henderson, Louise M; Caverly, Tanner J; Wernli, Karen J; Katki, Hormuzd A

2017-12-01

Risk prediction models may be useful for facilitating effective and high-quality decision-making at critical steps in the lung cancer screening process. This review provides a current overview of published lung cancer risk prediction models and their applications to lung cancer screening and highlights both challenges and strategies for improving their predictive performance and use in clinical practice. Since the 2011 publication of the National Lung Screening Trial results, numerous prediction models have been proposed to estimate the probability of developing or dying from lung cancer or the probability that a pulmonary nodule is malignant. Respective models appear to exhibit high discriminatory accuracy in identifying individuals at highest risk of lung cancer or differentiating malignant from benign pulmonary nodules. However, validation and critical comparison of the performance of these models in independent populations are limited. Little is also known about the extent to which risk prediction models are being applied in clinical practice and influencing decision-making processes and outcomes related to lung cancer screening. Current evidence is insufficient to determine which lung cancer risk prediction models are most clinically useful and how to best implement their use to optimize screening effectiveness and quality. To address these knowledge gaps, future research should be directed toward validating and enhancing existing risk prediction models for lung cancer and evaluating the application of model-based risk calculators and its corresponding impact on screening processes and outcomes.

Application of a new dynamic transport model to predict the evolution of performances throughout the nanofiltration of single salt solutions in concentration and diafiltration modes.

PubMed

Déon, Sébastien; Lam, Boukary; Fievet, Patrick

2018-06-01

Although many knowledge models describing the rejection of ionic compounds by nanofiltration membranes are available in literature, they are all used in full recycling mode. Indeed, both permeate and retentate streams are recycled in order to maintain constant concentrations in the feed solution. However, nanofiltration of real effluents is implemented either in concentration or diafiltration modes, for which the permeate stream is collected. In these conditions, concentrations progressively evolve during filtration and classical models fail to predict performances. In this paper, an improvement of the so called "Donnan Steric Pore Model", which includes both volume and concentration variations over time is proposed. This dynamic model is used here to predict the evolution of volumes and concentrations in both permeate and retentate streams during the filtration of salt solutions. This model was found to predict accurately the filtration performances with various salts whether the filtration is performed in concentration or diafiltration modes. The parameters of the usual model can be easily assessed from full batch experiments before being used in the dynamic version. Nevertheless, it is also highlighted that the variation of the membrane charge due to the evolution of feed concentration over time has to be taken into account in the model through the use of adsorption isotherms. Copyright © 2018 Elsevier Ltd. All rights reserved.

Purposes and methods of scoring earthquake forecasts

NASA Astrophysics Data System (ADS)

Zhuang, J.

2010-12-01

There are two kinds of purposes in the studies on earthquake prediction or forecasts: one is to give a systematic estimation of earthquake risks in some particular region and period in order to give advice to governments and enterprises for the use of reducing disasters, the other one is to search for reliable precursors that can be used to improve earthquake prediction or forecasts. For the first case, a complete score is necessary, while for the latter case, a partial score, which can be used to evaluate whether the forecasts or predictions have some advantages than a well know model, is necessary. This study reviews different scoring methods for evaluating the performance of earthquake prediction and forecasts. Especially, the gambling scoring method, which is developed recently, shows its capacity in finding good points in an earthquake prediction algorithm or model that are not in a reference model, even if its overall performance is no better than the reference model.

Species distribution models: A comparison of statistical approaches for livestock and disease epidemics.

PubMed

Hollings, Tracey; Robinson, Andrew; van Andel, Mary; Jewell, Chris; Burgman, Mark

2017-01-01

In livestock industries, reliable up-to-date spatial distribution and abundance records for animals and farms are critical for governments to manage and respond to risks. Yet few, if any, countries can afford to maintain comprehensive, up-to-date agricultural census data. Statistical modelling can be used as a proxy for such data but comparative modelling studies have rarely been undertaken for livestock populations. Widespread species, including livestock, can be difficult to model effectively due to complex spatial distributions that do not respond predictably to environmental gradients. We assessed three machine learning species distribution models (SDM) for their capacity to estimate national-level farm animal population numbers within property boundaries: boosted regression trees (BRT), random forests (RF) and K-nearest neighbour (K-NN). The models were built from a commercial livestock database and environmental and socio-economic predictor data for New Zealand. We used two spatial data stratifications to test (i) support for decision making in an emergency response situation, and (ii) the ability for the models to predict to new geographic regions. The performance of the three model types varied substantially, but the best performing models showed very high accuracy. BRTs had the best performance overall, but RF performed equally well or better in many simulations; RFs were superior at predicting livestock numbers for all but very large commercial farms. K-NN performed poorly relative to both RF and BRT in all simulations. The predictions of both multi species and single species models for farms and within hypothetical quarantine zones were very close to observed data. These models are generally applicable for livestock estimation with broad applications in disease risk modelling, biosecurity, policy and planning.

Species distribution models: A comparison of statistical approaches for livestock and disease epidemics

PubMed Central

Robinson, Andrew; van Andel, Mary; Jewell, Chris; Burgman, Mark

2017-01-01

In livestock industries, reliable up-to-date spatial distribution and abundance records for animals and farms are critical for governments to manage and respond to risks. Yet few, if any, countries can afford to maintain comprehensive, up-to-date agricultural census data. Statistical modelling can be used as a proxy for such data but comparative modelling studies have rarely been undertaken for livestock populations. Widespread species, including livestock, can be difficult to model effectively due to complex spatial distributions that do not respond predictably to environmental gradients. We assessed three machine learning species distribution models (SDM) for their capacity to estimate national-level farm animal population numbers within property boundaries: boosted regression trees (BRT), random forests (RF) and K-nearest neighbour (K-NN). The models were built from a commercial livestock database and environmental and socio-economic predictor data for New Zealand. We used two spatial data stratifications to test (i) support for decision making in an emergency response situation, and (ii) the ability for the models to predict to new geographic regions. The performance of the three model types varied substantially, but the best performing models showed very high accuracy. BRTs had the best performance overall, but RF performed equally well or better in many simulations; RFs were superior at predicting livestock numbers for all but very large commercial farms. K-NN performed poorly relative to both RF and BRT in all simulations. The predictions of both multi species and single species models for farms and within hypothetical quarantine zones were very close to observed data. These models are generally applicable for livestock estimation with broad applications in disease risk modelling, biosecurity, policy and planning. PMID:28837685

Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs

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

Zhang, Baichuan; Choudhury, Sutanay; Al-Hasan, Mohammad

2016-02-01

Estimating the confidence for a link is a critical task for Knowledge Graph construction. Link prediction, or predicting the likelihood of a link in a knowledge graph based on prior state is a key research direction within this area. We propose a Latent Feature Embedding based link recommendation model for prediction task and utilize Bayesian Personalized Ranking based optimization technique for learning models for each predicate. Experimental results on large-scale knowledge bases such as YAGO2 show that our approach achieves substantially higher performance than several state-of-art approaches. Furthermore, we also study the performance of the link prediction algorithm in termsmore » of topological properties of the Knowledge Graph and present a linear regression model to reason about its expected level of accuracy.« less

Intelligent Decisions Need Intelligent Choice of Models and Data - a Bayesian Justifiability Analysis for Models with Vastly Different Complexity

NASA Astrophysics Data System (ADS)

Nowak, W.; Schöniger, A.; Wöhling, T.; Illman, W. A.

2016-12-01

Model-based decision support requires justifiable models with good predictive capabilities. This, in turn, calls for a fine adjustment between predictive accuracy (small systematic model bias that can be achieved with rather complex models), and predictive precision (small predictive uncertainties that can be achieved with simpler models with fewer parameters). The implied complexity/simplicity trade-off depends on the availability of informative data for calibration. If not available, additional data collection can be planned through optimal experimental design. We present a model justifiability analysis that can compare models of vastly different complexity. It rests on Bayesian model averaging (BMA) to investigate the complexity/performance trade-off dependent on data availability. Then, we disentangle the complexity component from the performance component. We achieve this by replacing actually observed data by realizations of synthetic data predicted by the models. This results in a "model confusion matrix". Based on this matrix, the modeler can identify the maximum model complexity that can be justified by the available (or planned) amount and type of data. As a side product, the matrix quantifies model (dis-)similarity. We apply this analysis to aquifer characterization via hydraulic tomography, comparing four models with a vastly different number of parameters (from a homogeneous model to geostatistical random fields). As a testing scenario, we consider hydraulic tomography data. Using subsets of these data, we determine model justifiability as a function of data set size. The test case shows that geostatistical parameterization requires a substantial amount of hydraulic tomography data to be justified, while a zonation-based model can be justified with more limited data set sizes. The actual model performance (as opposed to model justifiability), however, depends strongly on the quality of prior geological information.

A robust operational model for predicting where tropical cyclone waves damage coral reefs

NASA Astrophysics Data System (ADS)

Puotinen, Marji; Maynard, Jeffrey A.; Beeden, Roger; Radford, Ben; Williams, Gareth J.

2016-05-01

Tropical cyclone (TC) waves can severely damage coral reefs. Models that predict where to find such damage (the ‘damage zone’) enable reef managers to: 1) target management responses after major TCs in near-real time to promote recovery at severely damaged sites; and 2) identify spatial patterns in historic TC exposure to explain habitat condition trajectories. For damage models to meet these needs, they must be valid for TCs of varying intensity, circulation size and duration. Here, we map damage zones for 46 TCs that crossed Australia’s Great Barrier Reef from 1985-2015 using three models - including one we develop which extends the capability of the others. We ground truth model performance with field data of wave damage from seven TCs of varying characteristics. The model we develop (4MW) out-performed the other models at capturing all incidences of known damage. The next best performing model (AHF) both under-predicted and over-predicted damage for TCs of various types. 4MW and AHF produce strikingly different spatial and temporal patterns of damage potential when used to reconstruct past TCs from 1985-2015. The 4MW model greatly enhances both of the main capabilities TC damage models provide to managers, and is useful wherever TCs and coral reefs co-occur.

A robust operational model for predicting where tropical cyclone waves damage coral reefs.

PubMed

Puotinen, Marji; Maynard, Jeffrey A; Beeden, Roger; Radford, Ben; Williams, Gareth J

2016-05-17

Tropical cyclone (TC) waves can severely damage coral reefs. Models that predict where to find such damage (the 'damage zone') enable reef managers to: 1) target management responses after major TCs in near-real time to promote recovery at severely damaged sites; and 2) identify spatial patterns in historic TC exposure to explain habitat condition trajectories. For damage models to meet these needs, they must be valid for TCs of varying intensity, circulation size and duration. Here, we map damage zones for 46 TCs that crossed Australia's Great Barrier Reef from 1985-2015 using three models - including one we develop which extends the capability of the others. We ground truth model performance with field data of wave damage from seven TCs of varying characteristics. The model we develop (4MW) out-performed the other models at capturing all incidences of known damage. The next best performing model (AHF) both under-predicted and over-predicted damage for TCs of various types. 4MW and AHF produce strikingly different spatial and temporal patterns of damage potential when used to reconstruct past TCs from 1985-2015. The 4MW model greatly enhances both of the main capabilities TC damage models provide to managers, and is useful wherever TCs and coral reefs co-occur.

Microscopic prediction of speech recognition for listeners with normal hearing in noise using an auditory model.

PubMed

Jürgens, Tim; Brand, Thomas

2009-11-01

This study compares the phoneme recognition performance in speech-shaped noise of a microscopic model for speech recognition with the performance of normal-hearing listeners. "Microscopic" is defined in terms of this model twofold. First, the speech recognition rate is predicted on a phoneme-by-phoneme basis. Second, microscopic modeling means that the signal waveforms to be recognized are processed by mimicking elementary parts of human's auditory processing. The model is based on an approach by Holube and Kollmeier [J. Acoust. Soc. Am. 100, 1703-1716 (1996)] and consists of a psychoacoustically and physiologically motivated preprocessing and a simple dynamic-time-warp speech recognizer. The model is evaluated while presenting nonsense speech in a closed-set paradigm. Averaged phoneme recognition rates, specific phoneme recognition rates, and phoneme confusions are analyzed. The influence of different perceptual distance measures and of the model's a-priori knowledge is investigated. The results show that human performance can be predicted by this model using an optimal detector, i.e., identical speech waveforms for both training of the recognizer and testing. The best model performance is yielded by distance measures which focus mainly on small perceptual distances and neglect outliers.

Multivariate Modelling of the Career Intent of Air Force Personnel.

DTIC Science & Technology

1980-09-01

index (HOPP) was used as a measure of current job satisfaction . As with the Vroom and Fishbein/Graen models, two separate validations were accom...34 Organizational Behavior and Human Performance , 23: 251-267, 1979. Lewis, Logan M. "Expectancy Theory as a Predictive Model of Career Intent, Job Satisfaction ...W. Albright. "Expectancy Theory Predictions of the Satisfaction , Effort, Performance , and Retention of Naval Aviation Officers," Organizational

Instrument Landing System performance prediction

DOT National Transportation Integrated Search

1974-01-01

Further achievements made in fiscal year 1973 on the development : of an Instrument Landing System (ILS) performance prediction model : are reported. These include (ILS) localizer scattering from generalized : slanted rectangular, triangular and cyli...

Configuration of the thermal landscape determines thermoregulatory performance of ectotherms

PubMed Central

Sears, Michael W.; Angilletta, Michael J.; Schuler, Matthew S.; Borchert, Jason; Dilliplane, Katherine F.; Stegman, Monica; Rusch, Travis W.; Mitchell, William A.

2016-01-01

Although most organisms thermoregulate behaviorally, biologists still cannot easily predict whether mobile animals will thermoregulate in natural environments. Current models fail because they ignore how the spatial distribution of thermal resources constrains thermoregulatory performance over space and time. To overcome this limitation, we modeled the spatially explicit movements of animals constrained by access to thermal resources. Our models predict that ectotherms thermoregulate more accurately when thermal resources are dispersed throughout space than when these resources are clumped. This prediction was supported by thermoregulatory behaviors of lizards in outdoor arenas with known distributions of environmental temperatures. Further, simulations showed how the spatial structure of the landscape qualitatively affects responses of animals to climate. Biologists will need spatially explicit models to predict impacts of climate change on local scales. PMID:27601639

Performance of five surface energy balance models for estimating daily evapotranspiration in high biomass sorghum

NASA Astrophysics Data System (ADS)

Wagle, Pradeep; Bhattarai, Nishan; Gowda, Prasanna H.; Kakani, Vijaya G.

2017-06-01

Robust evapotranspiration (ET) models are required to predict water usage in a variety of terrestrial ecosystems under different geographical and agrometeorological conditions. As a result, several remote sensing-based surface energy balance (SEB) models have been developed to estimate ET over large regions. However, comparison of the performance of several SEB models at the same site is limited. In addition, none of the SEB models have been evaluated for their ability to predict ET in rain-fed high biomass sorghum grown for biofuel production. In this paper, we evaluated the performance of five widely used single-source SEB models, namely Surface Energy Balance Algorithm for Land (SEBAL), Mapping ET with Internalized Calibration (METRIC), Surface Energy Balance System (SEBS), Simplified Surface Energy Balance Index (S-SEBI), and operational Simplified Surface Energy Balance (SSEBop), for estimating ET over a high biomass sorghum field during the 2012 and 2013 growing seasons. The predicted ET values were compared against eddy covariance (EC) measured ET (ETEC) for 19 cloud-free Landsat image. In general, S-SEBI, SEBAL, and SEBS performed reasonably well for the study period, while METRIC and SSEBop performed poorly. All SEB models substantially overestimated ET under extremely dry conditions as they underestimated sensible heat (H) and overestimated latent heat (LE) fluxes under dry conditions during the partitioning of available energy. METRIC, SEBAL, and SEBS overestimated LE regardless of wet or dry periods. Consequently, predicted seasonal cumulative ET by METRIC, SEBAL, and SEBS were higher than seasonal cumulative ETEC in both seasons. In contrast, S-SEBI and SSEBop substantially underestimated ET under too wet conditions, and predicted seasonal cumulative ET by S-SEBI and SSEBop were lower than seasonal cumulative ETEC in the relatively wetter 2013 growing season. Our results indicate the necessity of inclusion of soil moisture or plant water stress component in SEB models for the improvement of their performance, especially under too dry or wet environments.

Growth and food consumption by tiger muskellunge: Effects of temperature and ration level on bioenergetic model predictions

USGS Publications Warehouse

Chipps, S.R.; Einfalt, L.M.; Wahl, David H.

2000-01-01

We measured growth of age-0 tiger muskellunge as a function of ration size (25, 50, 75, and 100% C(max))and water temperature (7.5-25??C) and compared experimental results with those predicted from a bioenergetic model. Discrepancies between actual and predicted values varied appreciably with water temperature and growth rate. On average, model output overestimated winter consumption rates at 10 and 7.5??C by 113 to 328%, respectively, whereas model predictions in summer and autumn (20-25??C) were in better agreement with actual values (4 to 58%). We postulate that variation in model performance was related to seasonal changes in esocid metabolic rate, which were not accounted for in the bioenergetic model. Moreover, accuracy of model output varied with feeding and growth rate of tiger muskellunge. The model performed poorly for fish fed low rations compared with estimates based on fish fed ad libitum rations and was attributed, in part, to the influence of growth rate on the accuracy of bioenergetic predictions. Based on modeling simulations, we found that errors associated with bioenergetic parameters had more influence on model output when growth rate was low, which is consistent with our observations. In addition, reduced conversion efficiency at high ration levels may contribute to variable model performance, thereby implying that waste losses should be modeled as a function of ration size for esocids. Our findings support earlier field tests of the esocid bioenergetic model and indicate that food consumption is generally overestimated by the model, particularly in winter months and for fish exhibiting low feeding and growth rates.

EVALUATING THE PERFORMANCE OF REGIONAL-SCALE PHOTOCHEMICAL MODELING SYSTEMS: PART II--OZONE PREDICTIONS. (R825260)

EPA Science Inventory

In this paper, the concept of scale analysis is applied to evaluate ozone predictions from two regional-scale air quality models. To this end, seasonal time series of observations and predictions from the RAMS3b/UAM-V and MM5/MAQSIP (SMRAQ) modeling systems for ozone were spectra...

Initial Comparison of Single Cylinder Stirling Engine Computer Model Predictions with Test Results

NASA Technical Reports Server (NTRS)

Tew, R. C., Jr.; Thieme, L. G.; Miao, D.

1979-01-01

A Stirling engine digital computer model developed at NASA Lewis Research Center was configured to predict the performance of the GPU-3 single-cylinder rhombic drive engine. Revisions to the basic equations and assumptions are discussed. Model predictions with the early results of the Lewis Research Center GPU-3 tests are compared.

Deriving Points of Departure and Performance Baselines for Predictive Modeling of Systemic Toxicity using ToxRefDB (SOT)

EPA Science Inventory

A primary goal of computational toxicology is to generate predictive models of toxicity. An elusive target of alternative test methods and models has been the accurate prediction of systemic toxicity points of departure (PoD). We aim not only to provide a large and valuable resou...

Estimation and prediction under local volatility jump-diffusion model

NASA Astrophysics Data System (ADS)

Kim, Namhyoung; Lee, Younhee

2018-02-01

Volatility is an important factor in operating a company and managing risk. In the portfolio optimization and risk hedging using the option, the value of the option is evaluated using the volatility model. Various attempts have been made to predict option value. Recent studies have shown that stochastic volatility models and jump-diffusion models reflect stock price movements accurately. However, these models have practical limitations. Combining them with the local volatility model, which is widely used among practitioners, may lead to better performance. In this study, we propose a more effective and efficient method of estimating option prices by combining the local volatility model with the jump-diffusion model and apply it using both artificial and actual market data to evaluate its performance. The calibration process for estimating the jump parameters and local volatility surfaces is divided into three stages. We apply the local volatility model, stochastic volatility model, and local volatility jump-diffusion model estimated by the proposed method to KOSPI 200 index option pricing. The proposed method displays good estimation and prediction performance.

Maximum likelihood Bayesian model averaging and its predictive analysis for groundwater reactive transport models

USGS Publications Warehouse

Curtis, Gary P.; Lu, Dan; Ye, Ming

2015-01-01

While Bayesian model averaging (BMA) has been widely used in groundwater modeling, it is infrequently applied to groundwater reactive transport modeling because of multiple sources of uncertainty in the coupled hydrogeochemical processes and because of the long execution time of each model run. To resolve these problems, this study analyzed different levels of uncertainty in a hierarchical way, and used the maximum likelihood version of BMA, i.e., MLBMA, to improve the computational efficiency. This study demonstrates the applicability of MLBMA to groundwater reactive transport modeling in a synthetic case in which twenty-seven reactive transport models were designed to predict the reactive transport of hexavalent uranium (U(VI)) based on observations at a former uranium mill site near Naturita, CO. These reactive transport models contain three uncertain model components, i.e., parameterization of hydraulic conductivity, configuration of model boundary, and surface complexation reactions that simulate U(VI) adsorption. These uncertain model components were aggregated into the alternative models by integrating a hierarchical structure into MLBMA. The modeling results of the individual models and MLBMA were analyzed to investigate their predictive performance. The predictive logscore results show that MLBMA generally outperforms the best model, suggesting that using MLBMA is a sound strategy to achieve more robust model predictions relative to a single model. MLBMA works best when the alternative models are structurally distinct and have diverse model predictions. When correlation in model structure exists, two strategies were used to improve predictive performance by retaining structurally distinct models or assigning smaller prior model probabilities to correlated models. Since the synthetic models were designed using data from the Naturita site, the results of this study are expected to provide guidance for real-world modeling. Limitations of applying MLBMA to the synthetic study and future real-world modeling are discussed.

An analytical framework to assist decision makers in the use of forest ecosystem model predictions

USDA-ARS?s Scientific Manuscript database

The predictions of most terrestrial ecosystem models originate from deterministic simulations. Relatively few uncertainty evaluation exercises in model outputs are performed by either model developers or users. This issue has important consequences for decision makers who rely on models to develop n...

A computational approach to compare regression modelling strategies in prediction research.

PubMed

Pajouheshnia, Romin; Pestman, Wiebe R; Teerenstra, Steven; Groenwold, Rolf H H

2016-08-25

It is often unclear which approach to fit, assess and adjust a model will yield the most accurate prediction model. We present an extension of an approach for comparing modelling strategies in linear regression to the setting of logistic regression and demonstrate its application in clinical prediction research. A framework for comparing logistic regression modelling strategies by their likelihoods was formulated using a wrapper approach. Five different strategies for modelling, including simple shrinkage methods, were compared in four empirical data sets to illustrate the concept of a priori strategy comparison. Simulations were performed in both randomly generated data and empirical data to investigate the influence of data characteristics on strategy performance. We applied the comparison framework in a case study setting. Optimal strategies were selected based on the results of a priori comparisons in a clinical data set and the performance of models built according to each strategy was assessed using the Brier score and calibration plots. The performance of modelling strategies was highly dependent on the characteristics of the development data in both linear and logistic regression settings. A priori comparisons in four empirical data sets found that no strategy consistently outperformed the others. The percentage of times that a model adjustment strategy outperformed a logistic model ranged from 3.9 to 94.9 %, depending on the strategy and data set. However, in our case study setting the a priori selection of optimal methods did not result in detectable improvement in model performance when assessed in an external data set. The performance of prediction modelling strategies is a data-dependent process and can be highly variable between data sets within the same clinical domain. A priori strategy comparison can be used to determine an optimal logistic regression modelling strategy for a given data set before selecting a final modelling approach.

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

PubMed

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

2013-02-28

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

Analysis of free modeling predictions by RBO aleph in CASP11.

PubMed

Mabrouk, Mahmoud; Werner, Tim; Schneider, Michael; Putz, Ines; Brock, Oliver

2016-09-01

The CASP experiment is a biannual benchmark for assessing protein structure prediction methods. In CASP11, RBO Aleph ranked as one of the top-performing automated servers in the free modeling category. This category consists of targets for which structural templates are not easily retrievable. We analyze the performance of RBO Aleph and show that its success in CASP was a result of its ab initio structure prediction protocol. A detailed analysis of this protocol demonstrates that two components unique to our method greatly contributed to prediction quality: residue-residue contact prediction by EPC-map and contact-guided conformational space search by model-based search (MBS). Interestingly, our analysis also points to a possible fundamental problem in evaluating the performance of protein structure prediction methods: Improvements in components of the method do not necessarily lead to improvements of the entire method. This points to the fact that these components interact in ways that are poorly understood. This problem, if indeed true, represents a significant obstacle to community-wide progress. Proteins 2016; 84(Suppl 1):87-104. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.

Evaluating the Predictive Value of Growth Prediction Models

ERIC Educational Resources Information Center

Murphy, Daniel L.; Gaertner, Matthew N.

2014-01-01

This study evaluates four growth prediction models--projection, student growth percentile, trajectory, and transition table--commonly used to forecast (and give schools credit for) middle school students' future proficiency. Analyses focused on vertically scaled summative mathematics assessments, and two performance standards conditions (high…

Performance characterization of complex fuel port geometries for hybrid rocket fuel grains

NASA Astrophysics Data System (ADS)

Bath, Andrew

This research investigated the 3D printing and burning of fuel grains with complex geometry and the development of software capable of modeling and predicting the regression of a cross-section of these complex fuel grains. The software developed did predict the geometry to a fair degree of accuracy, especially when enhanced corner rounding was turned on. The model does have some drawbacks, notably being relatively slow, and does not perfectly predict the regression. If corner rounding is turned off, however, the model does become much faster; although less accurate, this method does still predict a relatively accurate resulting burn geometry, and is fast enough to be used for performance-tuning or genetic algorithms. In addition to the modeling method, preliminary investigations into the burning behavior of fuel grains with a helical flow path were performed. The helix fuel grains have a regression rate of nearly 3 times that of any other fuel grain geometry, primarily due to the enhancement of the friction coefficient between the flow and flow path.

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks

PubMed Central

Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

2016-01-01

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423

Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

PubMed

Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli

2016-01-01

In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.

A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy.

PubMed

Kell, Alexander J E; Yamins, Daniel L K; Shook, Erica N; Norman-Haignere, Sam V; McDermott, Josh H

2018-05-02

A core goal of auditory neuroscience is to build quantitative models that predict cortical responses to natural sounds. Reasoning that a complete model of auditory cortex must solve ecologically relevant tasks, we optimized hierarchical neural networks for speech and music recognition. The best-performing network contained separate music and speech pathways following early shared processing, potentially replicating human cortical organization. The network performed both tasks as well as humans and exhibited human-like errors despite not being optimized to do so, suggesting common constraints on network and human performance. The network predicted fMRI voxel responses substantially better than traditional spectrotemporal filter models throughout auditory cortex. It also provided a quantitative signature of cortical representational hierarchy-primary and non-primary responses were best predicted by intermediate and late network layers, respectively. The results suggest that task optimization provides a powerful set of tools for modeling sensory systems. Copyright © 2018 Elsevier Inc. All rights reserved.

A perturbative approach for enhancing the performance of time series forecasting.

PubMed

de Mattos Neto, Paulo S G; Ferreira, Tiago A E; Lima, Aranildo R; Vasconcelos, Germano C; Cavalcanti, George D C

2017-04-01

This paper proposes a method to perform time series prediction based on perturbation theory. The approach is based on continuously adjusting an initial forecasting model to asymptotically approximate a desired time series model. First, a predictive model generates an initial forecasting for a time series. Second, a residual time series is calculated as the difference between the original time series and the initial forecasting. If that residual series is not white noise, then it can be used to improve the accuracy of the initial model and a new predictive model is adjusted using residual series. The whole process is repeated until convergence or the residual series becomes white noise. The output of the method is then given by summing up the outputs of all trained predictive models in a perturbative sense. To test the method, an experimental investigation was conducted on six real world time series. A comparison was made with six other methods experimented and ten other results found in the literature. Results show that not only the performance of the initial model is significantly improved but also the proposed method outperforms the other results previously published. Copyright © 2017 Elsevier Ltd. All rights reserved.

Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

PubMed

Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

2003-01-01

Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

Predicting Directly Measured Trunk and Upper Arm Postures in Paper Mill Work From Administrative Data, Workers' Ratings and Posture Observations.

PubMed

Heiden, Marina; Garza, Jennifer; Trask, Catherine; Mathiassen, Svend Erik

2017-03-01

A cost-efficient approach for assessing working postures could be to build statistical models for predicting results of direct measurements from cheaper data, and apply these models to samples in which only the latter data are available. The present study aimed to build and assess the performance of statistical models predicting inclinometer-assessed trunk and arm posture among paper mill workers. Separate models were built using administrative data, workers' ratings of their exposure, and observations of the work from video recordings as predictors. Trunk and upper arm postures were measured using inclinometry on 28 paper mill workers during three work shifts each. Simultaneously, the workers were video filmed, and their postures were assessed by observation of the videos afterwards. Workers' ratings of exposure, and administrative data on staff and production during the shifts were also collected. Linear mixed models were fitted for predicting inclinometer-assessed exposure variables (median trunk and upper arm angle, proportion of time with neutral trunk and upper arm posture, and frequency of periods in neutral trunk and upper arm inclination) from administrative data, workers' ratings, and observations, respectively. Performance was evaluated in terms of Akaike information criterion, proportion of variance explained (R2), and standard error (SE) of the model estimate. For models performing well, validity was assessed by bootstrap resampling. Models based on administrative data performed poorly (R2 ≤ 15%) and would not be useful for assessing posture in this population. Models using workers' ratings of exposure performed slightly better (8% ≤ R2 ≤ 27% for trunk posture; 14% ≤ R2 ≤ 36% for arm posture). The best model was obtained when using observational data for predicting frequency of periods with neutral arm inclination. It explained 56% of the variance in the postural exposure, and its SE was 5.6. Bootstrap validation of this model showed similar expected performance in other samples (5th-95th percentile: R2 = 45-63%; SE = 5.1-6.2). Observational data had a better ability to predict inclinometer-assessed upper arm exposures than workers' ratings or administrative data. However, observational measurements are typically more expensive to obtain. The results encourage analyses of the cost-efficiency of modeling based on administrative data, workers' ratings, and observation, compared to the performance and cost of measuring exposure directly. © The Author 2017. Published by Oxford University Press on behalf of the British Occupational Hygiene Society.

Validating proposed migration equation and parameters' values as a tool to reproduce and predict 137Cs vertical migration activity in Spanish soils.

PubMed

Olondo, C; Legarda, F; Herranz, M; Idoeta, R

2017-04-01

This paper shows the procedure performed to validate the migration equation and the migration parameters' values presented in a previous paper (Legarda et al., 2011) regarding the migration of 137 Cs in Spanish mainland soils. In this paper, this model validation has been carried out checking experimentally obtained activity concentration values against those predicted by the model. This experimental data come from the measured vertical activity profiles of 8 new sampling points which are located in northern Spain. Before testing predicted values of the model, the uncertainty of those values has been assessed with the appropriate uncertainty analysis. Once establishing the uncertainty of the model, both activity concentration values, experimental versus model predicted ones, have been compared. Model validation has been performed analyzing its accuracy, studying it as a whole and also at different depth intervals. As a result, this model has been validated as a tool to predict 137 Cs behaviour in a Mediterranean environment. Copyright © 2017 Elsevier Ltd. All rights reserved.

Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data

NASA Astrophysics Data System (ADS)

Jothiprakash, V.; Magar, R. B.

2012-07-01

SummaryIn this study, artificial intelligent (AI) techniques such as artificial neural network (ANN), Adaptive neuro-fuzzy inference system (ANFIS) and Linear genetic programming (LGP) are used to predict daily and hourly multi-time-step ahead intermittent reservoir inflow. To illustrate the applicability of AI techniques, intermittent Koyna river watershed in Maharashtra, India is chosen as a case study. Based on the observed daily and hourly rainfall and reservoir inflow various types of time-series, cause-effect and combined models are developed with lumped and distributed input data. Further, the model performance was evaluated using various performance criteria. From the results, it is found that the performances of LGP models are found to be superior to ANN and ANFIS models especially in predicting the peak inflows for both daily and hourly time-step. A detailed comparison of the overall performance indicated that the combined input model (combination of rainfall and inflow) performed better in both lumped and distributed input data modelling. It was observed that the lumped input data models performed slightly better because; apart from reducing the noise in the data, the better techniques and their training approach, appropriate selection of network architecture, required inputs, and also training-testing ratios of the data set. The slight poor performance of distributed data is due to large variations and lesser number of observed values.

Biological Networks for Predicting Chemical Hepatocarcinogenicity Using Gene Expression Data from Treated Mice and Relevance across Human and Rat Species

PubMed Central

Thomas, Reuben; Thomas, Russell S.; Auerbach, Scott S.; Portier, Christopher J.

2013-01-01

Background Several groups have employed genomic data from subchronic chemical toxicity studies in rodents (90 days) to derive gene-centric predictors of chronic toxicity and carcinogenicity. Genes are annotated to belong to biological processes or molecular pathways that are mechanistically well understood and are described in public databases. Objectives To develop a molecular pathway-based prediction model of long term hepatocarcinogenicity using 90-day gene expression data and to evaluate the performance of this model with respect to both intra-species, dose-dependent and cross-species predictions. Methods Genome-wide hepatic mRNA expression was retrospectively measured in B6C3F1 mice following subchronic exposure to twenty-six (26) chemicals (10 were positive, 2 equivocal and 14 negative for liver tumors) previously studied by the US National Toxicology Program. Using these data, a pathway-based predictor model for long-term liver cancer risk was derived using random forests. The prediction model was independently validated on test sets associated with liver cancer risk obtained from mice, rats and humans. Results Using 5-fold cross validation, the developed prediction model had reasonable predictive performance with the area under receiver-operator curve (AUC) equal to 0.66. The developed prediction model was then used to extrapolate the results to data associated with rat and human liver cancer. The extrapolated model worked well for both extrapolated species (AUC value of 0.74 for rats and 0.91 for humans). The prediction models implied a balanced interplay between all pathway responses leading to carcinogenicity predictions. Conclusions Pathway-based prediction models estimated from sub-chronic data hold promise for predicting long-term carcinogenicity and also for its ability to extrapolate results across multiple species. PMID:23737943

Biological networks for predicting chemical hepatocarcinogenicity using gene expression data from treated mice and relevance across human and rat species.

PubMed

Thomas, Reuben; Thomas, Russell S; Auerbach, Scott S; Portier, Christopher J

2013-01-01

Several groups have employed genomic data from subchronic chemical toxicity studies in rodents (90 days) to derive gene-centric predictors of chronic toxicity and carcinogenicity. Genes are annotated to belong to biological processes or molecular pathways that are mechanistically well understood and are described in public databases. To develop a molecular pathway-based prediction model of long term hepatocarcinogenicity using 90-day gene expression data and to evaluate the performance of this model with respect to both intra-species, dose-dependent and cross-species predictions. Genome-wide hepatic mRNA expression was retrospectively measured in B6C3F1 mice following subchronic exposure to twenty-six (26) chemicals (10 were positive, 2 equivocal and 14 negative for liver tumors) previously studied by the US National Toxicology Program. Using these data, a pathway-based predictor model for long-term liver cancer risk was derived using random forests. The prediction model was independently validated on test sets associated with liver cancer risk obtained from mice, rats and humans. Using 5-fold cross validation, the developed prediction model had reasonable predictive performance with the area under receiver-operator curve (AUC) equal to 0.66. The developed prediction model was then used to extrapolate the results to data associated with rat and human liver cancer. The extrapolated model worked well for both extrapolated species (AUC value of 0.74 for rats and 0.91 for humans). The prediction models implied a balanced interplay between all pathway responses leading to carcinogenicity predictions. Pathway-based prediction models estimated from sub-chronic data hold promise for predicting long-term carcinogenicity and also for its ability to extrapolate results across multiple species.

Genetic determinants of freckle occurrence in the Spanish population: Towards ephelides prediction from human DNA samples.

PubMed

Hernando, Barbara; Ibañez, Maria Victoria; Deserio-Cuesta, Julio Alberto; Soria-Navarro, Raquel; Vilar-Sastre, Inca; Martinez-Cadenas, Conrado

2018-03-01

Prediction of human pigmentation traits, one of the most differentiable externally visible characteristics among individuals, from biological samples represents a useful tool in the field of forensic DNA phenotyping. In spite of freckling being a relatively common pigmentation characteristic in Europeans, little is known about the genetic basis of this largely genetically determined phenotype in southern European populations. In this work, we explored the predictive capacity of eight freckle and sunlight sensitivity-related genes in 458 individuals (266 non-freckled controls and 192 freckled cases) from Spain. Four loci were associated with freckling (MC1R, IRF4, ASIP and BNC2), and female sex was also found to be a predictive factor for having a freckling phenotype in our population. After identifying the most informative genetic variants responsible for human ephelides occurrence in our sample set, we developed a DNA-based freckle prediction model using a multivariate regression approach. Once developed, the capabilities of the prediction model were tested by a repeated 10-fold cross-validation approach. The proportion of correctly predicted individuals using the DNA-based freckle prediction model was 74.13%. The implementation of sex into the DNA-based freckle prediction model slightly improved the overall prediction accuracy by 2.19% (76.32%). Further evaluation of the newly-generated prediction model was performed by assessing the model's performance in a new cohort of 212 Spanish individuals, reaching a classification success rate of 74.61%. Validation of this prediction model may be carried out in larger populations, including samples from different European populations. Further research to validate and improve this newly-generated freckle prediction model will be needed before its forensic application. Together with DNA tests already validated for eye and hair colour prediction, this freckle prediction model may lead to a substantially more detailed physical description of unknown individuals from DNA found at the crime scene. Copyright © 2017 Elsevier B.V. All rights reserved.

An exponential filter model predicts lightness illusions

PubMed Central

Zeman, Astrid; Brooks, Kevin R.; Ghebreab, Sennay

2015-01-01

Lightness, or perceived reflectance of a surface, is influenced by surrounding context. This is demonstrated by the Simultaneous Contrast Illusion (SCI), where a gray patch is perceived lighter against a black background and vice versa. Conversely, assimilation is where the lightness of the target patch moves toward that of the bounding areas and can be demonstrated in White's effect. Blakeslee and McCourt (1999) introduced an oriented difference-of-Gaussian (ODOG) model that is able to account for both contrast and assimilation in a number of lightness illusions and that has been subsequently improved using localized normalization techniques. We introduce a model inspired by image statistics that is based on a family of exponential filters, with kernels spanning across multiple sizes and shapes. We include an optional second stage of normalization based on contrast gain control. Our model was tested on a well-known set of lightness illusions that have previously been used to evaluate ODOG and its variants, and model lightness values were compared with typical human data. We investigate whether predictive success depends on filters of a particular size or shape and whether pooling information across filters can improve performance. The best single filter correctly predicted the direction of lightness effects for 21 out of 27 illusions. Combining two filters together increased the best performance to 23, with asymptotic performance at 24 for an arbitrarily large combination of filter outputs. While normalization improved prediction magnitudes, it only slightly improved overall scores in direction predictions. The prediction performance of 24 out of 27 illusions equals that of the best performing ODOG variant, with greater parsimony. Our model shows that V1-style orientation-selectivity is not necessary to account for lightness illusions and that a low-level model based on image statistics is able to account for a wide range of both contrast and assimilation effects. PMID:26157381

The development and testing of a skin tear risk assessment tool.

PubMed

Newall, Nelly; Lewin, Gill F; Bulsara, Max K; Carville, Keryln J; Leslie, Gavin D; Roberts, Pam A

2017-02-01

The aim of the present study is to develop a reliable and valid skin tear risk assessment tool. The six characteristics identified in a previous case control study as constituting the best risk model for skin tear development were used to construct a risk assessment tool. The ability of the tool to predict skin tear development was then tested in a prospective study. Between August 2012 and September 2013, 1466 tertiary hospital patients were assessed at admission and followed up for 10 days to see if they developed a skin tear. The predictive validity of the tool was assessed using receiver operating characteristic (ROC) analysis. When the tool was found not to have performed as well as hoped, secondary analyses were performed to determine whether a potentially better performing risk model could be identified. The tool was found to have high sensitivity but low specificity and therefore have inadequate predictive validity. Secondary analysis of the combined data from this and the previous case control study identified an alternative better performing risk model. The tool developed and tested in this study was found to have inadequate predictive validity. The predictive validity of an alternative, more parsimonious model now needs to be tested. © 2015 Medicalhelplines.com Inc and John Wiley & Sons Ltd.

Modeling and Evaluating Pilot Performance in NextGen: Review of and Recommendations Regarding Pilot Modeling Efforts, Architectures, and Validation Studies

NASA Technical Reports Server (NTRS)

Wickens, Christopher; Sebok, Angelia; Keller, John; Peters, Steve; Small, Ronald; Hutchins, Shaun; Algarin, Liana; Gore, Brian Francis; Hooey, Becky Lee; Foyle, David C.

2013-01-01

NextGen operations are associated with a variety of changes to the national airspace system (NAS) including changes to the allocation of roles and responsibilities among operators and automation, the use of new technologies and automation, additional information presented on the flight deck, and the entire concept of operations (ConOps). In the transition to NextGen airspace, aviation and air operations designers need to consider the implications of design or system changes on human performance and the potential for error. To ensure continued safety of the NAS, it will be necessary for researchers to evaluate design concepts and potential NextGen scenarios well before implementation. One approach for such evaluations is through human performance modeling. Human performance models (HPMs) provide effective tools for predicting and evaluating operator performance in systems. HPMs offer significant advantages over empirical, human-in-the-loop testing in that (1) they allow detailed analyses of systems that have not yet been built, (2) they offer great flexibility for extensive data collection, (3) they do not require experimental participants, and thus can offer cost and time savings. HPMs differ in their ability to predict performance and safety with NextGen procedures, equipment and ConOps. Models also vary in terms of how they approach human performance (e.g., some focus on cognitive processing, others focus on discrete tasks performed by a human, while others consider perceptual processes), and in terms of their associated validation efforts. The objectives of this research effort were to support the Federal Aviation Administration (FAA) in identifying HPMs that are appropriate for predicting pilot performance in NextGen operations, to provide guidance on how to evaluate the quality of different models, and to identify gaps in pilot performance modeling research, that could guide future research opportunities. This research effort is intended to help the FAA evaluate pilot modeling efforts and select the appropriate tools for future modeling efforts to predict pilot performance in NextGen operations.

The use of artificial neural networks and multiple linear regression to predict rate of medical waste generation

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

Jahandideh, Sepideh; Jahandideh, Samad; Asadabadi, Ebrahim Barzegari

2009-11-15

Prediction of the amount of hospital waste production will be helpful in the storage, transportation and disposal of hospital waste management. Based on this fact, two predictor models including artificial neural networks (ANNs) and multiple linear regression (MLR) were applied to predict the rate of medical waste generation totally and in different types of sharp, infectious and general. In this study, a 5-fold cross-validation procedure on a database containing total of 50 hospitals of Fars province (Iran) were used to verify the performance of the models. Three performance measures including MAR, RMSE and R{sup 2} were used to evaluate performancemore » of models. The MLR as a conventional model obtained poor prediction performance measure values. However, MLR distinguished hospital capacity and bed occupancy as more significant parameters. On the other hand, ANNs as a more powerful model, which has not been introduced in predicting rate of medical waste generation, showed high performance measure values, especially 0.99 value of R{sup 2} confirming the good fit of the data. Such satisfactory results could be attributed to the non-linear nature of ANNs in problem solving which provides the opportunity for relating independent variables to dependent ones non-linearly. In conclusion, the obtained results showed that our ANN-based model approach is very promising and may play a useful role in developing a better cost-effective strategy for waste management in future.« less

Modelling and Predicting Backstroke Start Performance Using Non-Linear and Linear Models

PubMed Central

de Jesus, Karla; Ayala, Helon V. H.; de Jesus, Kelly; Coelho, Leandro dos S.; Medeiros, Alexandre I.A.; Abraldes, José A.; Vaz, Mário A.P.; Fernandes, Ricardo J.; Vilas-Boas, João Paulo

2018-01-01

Abstract Our aim was to compare non-linear and linear mathematical model responses for backstroke start performance prediction. Ten swimmers randomly completed eight 15 m backstroke starts with feet over the wedge, four with hands on the highest horizontal and four on the vertical handgrip. Swimmers were videotaped using a dual media camera set-up, with the starts being performed over an instrumented block with four force plates. Artificial neural networks were applied to predict 5 m start time using kinematic and kinetic variables and to determine the accuracy of the mean absolute percentage error. Artificial neural networks predicted start time more robustly than the linear model with respect to changing training to the validation dataset for the vertical handgrip (3.95 ± 1.67 vs. 5.92 ± 3.27%). Artificial neural networks obtained a smaller mean absolute percentage error than the linear model in the horizontal (0.43 ± 0.19 vs. 0.98 ± 0.19%) and vertical handgrip (0.45 ± 0.19 vs. 1.38 ± 0.30%) using all input data. The best artificial neural network validation revealed a smaller mean absolute error than the linear model for the horizontal (0.007 vs. 0.04 s) and vertical handgrip (0.01 vs. 0.03 s). Artificial neural networks should be used for backstroke 5 m start time prediction due to the quite small differences among the elite level performances. PMID:29599857

Using Predictive Uncertainty Analysis to Assess Hydrologic Model Performance for a Watershed in Oregon

NASA Astrophysics Data System (ADS)

Brannan, K. M.; Somor, A.

2016-12-01

A variety of statistics are used to assess watershed model performance but these statistics do not directly answer the question: what is the uncertainty of my prediction. Understanding predictive uncertainty is important when using a watershed model to develop a Total Maximum Daily Load (TMDL). TMDLs are a key component of the US Clean Water Act and specify the amount of a pollutant that can enter a waterbody when the waterbody meets water quality criteria. TMDL developers use watershed models to estimate pollutant loads from nonpoint sources of pollution. We are developing a TMDL for bacteria impairments in a watershed in the Coastal Range of Oregon. We setup an HSPF model of the watershed and used the calibration software PEST to estimate HSPF hydrologic parameters and then perform predictive uncertainty analysis of stream flow. We used Monte-Carlo simulation to run the model with 1,000 different parameter sets and assess predictive uncertainty. In order to reduce the chance of specious parameter sets, we accounted for the relationships among parameter values by using mathematically-based regularization techniques and an estimate of the parameter covariance when generating random parameter sets. We used a novel approach to select flow data for predictive uncertainty analysis. We set aside flow data that occurred on days that bacteria samples were collected. We did not use these flows in the estimation of the model parameters. We calculated a percent uncertainty for each flow observation based 1,000 model runs. We also used several methods to visualize results with an emphasis on making the data accessible to both technical and general audiences. We will use the predictive uncertainty estimates in the next phase of our work, simulating bacteria fate and transport in the watershed.

Artificial neural network analysis based on genetic algorithm to predict the performance characteristics of a cross flow cooling tower

NASA Astrophysics Data System (ADS)

Wu, Jiasheng; Cao, Lin; Zhang, Guoqiang

2018-02-01

Cooling tower of air conditioning has been widely used as cooling equipment, and there will be broad application prospect if it can be reversibly used as heat source under heat pump heating operation condition. In view of the complex non-linear relationship of each parameter in the process of heat and mass transfer inside tower, In this paper, the BP neural network model based on genetic algorithm optimization (GABP neural network model) is established for the reverse use of cross flow cooling tower. The model adopts the structure of 6 inputs, 13 hidden nodes and 8 outputs. With this model, the outlet air dry bulb temperature, wet bulb temperature, water temperature, heat, sensible heat ratio and heat absorbing efficiency, Lewis number, a total of 8 the proportion of main performance parameters were predicted. Furthermore, the established network model is used to predict the water temperature and heat absorption of the tower at different inlet temperatures. The mean relative error MRE between BP predicted value and experimental value are 4.47%, 3.63%, 2.38%, 3.71%, 6.35%,3.14%, 13.95% and 6.80% respectively; the mean relative error MRE between GABP predicted value and experimental value are 2.66%, 3.04%, 2.27%, 3.02%, 6.89%, 3.17%, 11.50% and 6.57% respectively. The results show that the prediction results of GABP network model are better than that of BP network model; the simulation results are basically consistent with the actual situation. The GABP network model can well predict the heat and mass transfer performance of the cross flow cooling tower.

Flood loss model transfer: on the value of additional data

NASA Astrophysics Data System (ADS)

Schröter, Kai; Lüdtke, Stefan; Vogel, Kristin; Kreibich, Heidi; Thieken, Annegret; Merz, Bruno

2017-04-01

The transfer of models across geographical regions and flood events is a key challenge in flood loss estimation. Variations in local characteristics and continuous system changes require regional adjustments and continuous updating with current evidence. However, acquiring data on damage influencing factors is expensive and therefore assessing the value of additional data in terms of model reliability and performance improvement is of high relevance. The present study utilizes empirical flood loss data on direct damage to residential buildings available from computer aided telephone interviews that were carried out after the floods in 2002, 2005, 2006, 2010, 2011 and 2013 mainly in the Elbe and Danube catchments in Germany. Flood loss model performance is assessed for incrementally increased numbers of loss data which are differentiated according to region and flood event. Two flood loss modeling approaches are considered: (i) a multi-variable flood loss model approach using Random Forests and (ii) a uni-variable stage damage function. Both model approaches are embedded in a bootstrapping process which allows evaluating the uncertainty of model predictions. Predictive performance of both models is evaluated with regard to mean bias, mean absolute and mean squared errors, as well as hit rate and sharpness. Mean bias and mean absolute error give information about the accuracy of model predictions; mean squared error and sharpness about precision and hit rate is an indicator for model reliability. The results of incremental, regional and temporal updating demonstrate the usefulness of additional data to improve model predictive performance and increase model reliability, particularly in a spatial-temporal transfer setting.

Predicting Pilot Performance in Off-Nominal Conditions: A Meta-Analysis and Model Validation

NASA Technical Reports Server (NTRS)

Wickens, C.D.; Hooey, B.L.; Gore, B.F.; Sebok, A.; Koenecke, C.; Salud, E.

2009-01-01

Pilot response to off-nominal (very rare) events represents a critical component to understanding the safety of next generation airspace technology and procedures. We describe a meta-analysis designed to integrate the existing data regarding pilot accuracy of detecting rare, unexpected events such as runway incursions in realistic flight simulations. Thirty-five studies were identified and pilot responses were categorized by expectancy, event location, and whether the pilot was flying with a highway-in-the-sky display. All three dichotomies produced large, significant effects on event miss rate. A model of human attention and noticing, N-SEEV, was then used to predict event noticing performance as a function of event salience and expectancy, and retinal eccentricity. Eccentricity is predicted from steady state scanning by the SEEV model of attention allocation. The model was used to predict miss rates for the expectancy, location and highway-in-the-sky (HITS) effects identified in the meta-analysis. The correlation between model-predicted results and data from the meta-analysis was 0.72.

A Five-Stage Prediction-Observation-Explanation Inquiry-Based Learning Model to Improve Students' Learning Performance in Science Courses

ERIC Educational Resources Information Center

Hsiao, Hsien-Sheng; Chen, Jyun-Chen; Hong, Jon-Chao; Chen, Po-Hsi; Lu, Chow-Chin; Chen, Sherry Y.

2017-01-01

A five-stage prediction-observation-explanation inquiry-based learning (FPOEIL) model was developed to improve students' scientific learning performance. In order to intensify the science learning effect, the repertory grid technology-assisted learning (RGTL) approach and the collaborative learning (CL) approach were utilized. A quasi-experimental…

Prediction of fatigue-related driver performance from EEG data by deep Riemannian model.

PubMed

Hajinoroozi, Mehdi; Jianqiu Zhang; Yufei Huang

2017-07-01

Prediction of the drivers' drowsy and alert states is important for safety purposes. The prediction of drivers' drowsy and alert states from electroencephalography (EEG) using shallow and deep Riemannian methods is presented. For shallow Riemannian methods, the minimum distance to Riemannian mean (mdm) and Log-Euclidian metric are investigated, where it is shown that Log-Euclidian metric outperforms the mdm algorithm. In addition the SPDNet, a deep Riemannian model, that takes the EEG covariance matrix as the input is investigated. It is shown that SPDNet outperforms all tested shallow and deep classification methods. Performance of SPDNet is 6.02% and 2.86% higher than the best performance by the conventional Euclidian classifiers and shallow Riemannian models, respectively.

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

NASA Astrophysics Data System (ADS)

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

2017-04-01

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

High capacity demonstration of honeycomb panel heat pipes

NASA Technical Reports Server (NTRS)

Tanzer, H. J.

1989-01-01

The feasibility of performance enhancing the sandwich panel heat pipe was investigated for moderate temperature range heat rejection radiators on future-high-power spacecraft. The hardware development program consisted of performance prediction modeling, fabrication, ground test, and data correlation. Using available sandwich panel materials, a series of subscale test panels were augumented with high-capacity sideflow and temperature control variable conductance features, and test evaluated for correlation with performance prediction codes. Using the correlated prediction model, a 50-kW full size radiator was defined using methanol working fluid and closely spaced sideflows. A new concept called the hybrid radiator individually optimizes heat pipe components. A 2.44-m long hybrid test vehicle demonstrated proof-of-principle performance.

Building a generalized distributed system model

NASA Technical Reports Server (NTRS)

Mukkamala, Ravi; Foudriat, E. C.

1991-01-01

A modeling tool for both analysis and design of distributed systems is discussed. Since many research institutions have access to networks of workstations, the researchers decided to build a tool running on top of the workstations to function as a prototype as well as a distributed simulator for a computing system. The effects of system modeling on performance prediction in distributed systems and the effect of static locking and deadlocks on the performance predictions of distributed transactions are also discussed. While the probability of deadlock is considerably small, its effects on performance could be significant.

Predictive Monitoring for Improved Management of Glucose Levels

PubMed Central

Reifman, Jaques; Rajaraman, Srinivasan; Gribok, Andrei; Ward, W. Kenneth

2007-01-01

Background Recent developments and expected near-future improvements in continuous glucose monitoring (CGM) devices provide opportunities to couple them with mathematical forecasting models to produce predictive monitoring systems for early, proactive glycemia management of diabetes mellitus patients before glucose levels drift to undesirable levels. This article assesses the feasibility of data-driven models to serve as the forecasting engine of predictive monitoring systems. Methods We investigated the capabilities of data-driven autoregressive (AR) models to (1) capture the correlations in glucose time-series data, (2) make accurate predictions as a function of prediction horizon, and (3) be made portable from individual to individual without any need for model tuning. The investigation is performed by employing CGM data from nine type 1 diabetic subjects collected over a continuous 5-day period. Results With CGM data serving as the gold standard, AR model-based predictions of glucose levels assessed over nine subjects with Clarke error grid analysis indicated that, for a 30-minute prediction horizon, individually tuned models yield 97.6 to 100.0% of data in the clinically acceptable zones A and B, whereas cross-subject, portable models yield 95.8 to 99.7% of data in zones A and B. Conclusions This study shows that, for a 30-minute prediction horizon, data-driven AR models provide sufficiently-accurate and clinically-acceptable estimates of glucose levels for timely, proactive therapy and should be considered as the modeling engine for predictive monitoring of patients with type 1 diabetes mellitus. It also suggests that AR models can be made portable from individual to individual with minor performance penalties, while greatly reducing the burden associated with model tuning and data collection for model development. PMID:19885110

A Model for Predicting Student Performance on High-Stakes Assessment

ERIC Educational Resources Information Center

Dammann, Matthew Walter

2010-01-01

This research study examined the use of student achievement on reading and math state assessments to predict success on the science state assessment. Multiple regression analysis was utilized to test the prediction for all students in grades 5 and 8 in a mid-Atlantic state. The prediction model developed from the analysis explored the combined…

Comparative study of turbulence models in predicting hypersonic inlet flows

NASA Technical Reports Server (NTRS)

Kapoor, Kamlesh; Anderson, Bernhard H.; Shaw, Robert J.

1992-01-01

A numerical study was conducted to analyze the performance of different turbulence models when applied to the hypersonic NASA P8 inlet. Computational results from the PARC2D code, which solves the full two-dimensional Reynolds-averaged Navier-Stokes equation, were compared with experimental data. The zero-equation models considered for the study were the Baldwin-Lomax model, the Thomas model, and a combination of the Baldwin-Lomax and Thomas models; the two-equation models considered were the Chien model, the Speziale model (both low Reynolds number), and the Launder and Spalding model (high Reynolds number). The Thomas model performed best among the zero-equation models, and predicted good pressure distributions. The Chien and Speziale models compared wery well with the experimental data, and performed better than the Thomas model near the walls.

Comparative study of turbulence models in predicting hypersonic inlet flows

NASA Technical Reports Server (NTRS)

Kapoor, Kamlesh; Anderson, Bernhard H.; Shaw, Robert J.

1992-01-01

A numerical study was conducted to analyze the performance of different turbulence models when applied to the hypersonic NASA P8 inlet. Computational results from the PARC2D code, which solves the full two-dimensional Reynolds-averaged Navier-Stokes equation, were compared with experimental data. The zero-equation models considered for the study were the Baldwin-Lomax model, the Thomas model, and a combination of the Baldwin-Lomax and Thomas models; the two-equation models considered were the Chien model, the Speziale model (both low Reynolds number), and the Launder and Spalding model (high Reynolds number). The Thomas model performed best among the zero-equation models, and predicted good pressure distributions. The Chien and Speziale models compared very well with the experimental data, and performed better than the Thomas model near the walls.

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

PubMed

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

2014-11-06

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

The Development of Statistical Models for Predicting Surgical Site Infections in Japan: Toward a Statistical Model-Based Standardized Infection Ratio.

PubMed

Fukuda, Haruhisa; Kuroki, Manabu

2016-03-01

To develop and internally validate a surgical site infection (SSI) prediction model for Japan. Retrospective observational cohort study. We analyzed surveillance data submitted to the Japan Nosocomial Infections Surveillance system for patients who had undergone target surgical procedures from January 1, 2010, through December 31, 2012. Logistic regression analyses were used to develop statistical models for predicting SSIs. An SSI prediction model was constructed for each of the procedure categories by statistically selecting the appropriate risk factors from among the collected surveillance data and determining their optimal categorization. Standard bootstrapping techniques were applied to assess potential overfitting. The C-index was used to compare the predictive performances of the new statistical models with those of models based on conventional risk index variables. The study sample comprised 349,987 cases from 428 participant hospitals throughout Japan, and the overall SSI incidence was 7.0%. The C-indices of the new statistical models were significantly higher than those of the conventional risk index models in 21 (67.7%) of the 31 procedure categories (P<.05). No significant overfitting was detected. Japan-specific SSI prediction models were shown to generally have higher accuracy than conventional risk index models. These new models may have applications in assessing hospital performance and identifying high-risk patients in specific procedure categories.

Brain regions engaged by part- and whole-task performance in a video game: a model-based test of the decomposition hypothesis.

PubMed

Anderson, John R; Bothell, Daniel; Fincham, Jon M; Anderson, Abraham R; Poole, Ben; Qin, Yulin

2011-12-01

Part- and whole-task conditions were created by manipulating the presence of certain components of the Space Fortress video game. A cognitive model was created for two-part games that could be combined into a model that performed the whole game. The model generated predictions both for behavioral patterns and activation patterns in various brain regions. The activation predictions concerned both tonic activation that was constant in these regions during performance of the game and phasic activation that occurred when there was resource competition. The model's predictions were confirmed about how tonic and phasic activation in different regions would vary with condition. These results support the Decomposition Hypothesis that the execution of a complex task can be decomposed into a set of information-processing components and that these components combine unchanged in different task conditions. In addition, individual differences in learning gains were predicted by individual differences in phasic activation in those regions that displayed highest tonic activity. This individual difference pattern suggests that the rate of learning of a complex skill is determined by capacity limits.

Railroad Performance Model

DOT National Transportation Integrated Search

1977-10-01

This report describes an operational, though preliminary, version of the Railroad Performance Model, which is a computer simulation model of the nation's railroad system. The ultimate purpose of this model is to predict the effect of changes in gover...

A model for prediction of STOVL ejector dynamics

NASA Technical Reports Server (NTRS)

Drummond, Colin K.

1989-01-01

A semi-empirical control-volume approach to ejector modeling for transient performance prediction is presented. This new approach is motivated by the need for a predictive real-time ejector sub-system simulation for Short Take-Off Verticle Landing (STOVL) integrated flight and propulsion controls design applications. Emphasis is placed on discussion of the approximate characterization of the mixing process central to thrust augmenting ejector operation. The proposed ejector model suggests transient flow predictions are possible with a model based on steady-flow data. A practical test case is presented to illustrate model calibration.

Model predictive control based on reduced order models applied to belt conveyor system.

PubMed

Chen, Wei; Li, Xin

2016-11-01

In the paper, a model predictive controller based on reduced order model is proposed to control belt conveyor system, which is an electro-mechanics complex system with long visco-elastic body. Firstly, in order to design low-degree controller, the balanced truncation method is used for belt conveyor model reduction. Secondly, MPC algorithm based on reduced order model for belt conveyor system is presented. Because of the error bound between the full-order model and reduced order model, two Kalman state estimators are applied in the control scheme to achieve better system performance. Finally, the simulation experiments are shown that balanced truncation method can significantly reduce the model order with high-accuracy and model predictive control based on reduced-model performs well in controlling the belt conveyor system. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Using Neural Networks to Predict MBA Student Success

ERIC Educational Resources Information Center

Naik, Bijayananda; Ragothaman, Srinivasan

2004-01-01

Predicting MBA student performance for admission decisions is crucial for educational institutions. This paper evaluates the ability of three different models--neural networks, logit, and probit to predict MBA student performance in graduate programs. The neural network technique was used to classify applicants into successful and marginal student…

External evaluation of population pharmacokinetic models of vancomycin in neonates: the transferability of published models to different clinical settings

PubMed Central

Zhao, Wei; Kaguelidou, Florentia; Biran, Valérie; Zhang, Daolun; Allegaert, Karel; Capparelli, Edmund V; Holford, Nick; Kimura, Toshimi; Lo, Yoke-Lin; Peris, José-Esteban; Thomson, Alison; Anker, John N; Fakhoury, May; Jacqz-Aigrain, Evelyne

2013-01-01

Aims Vancomycin is one of the most evaluated antibiotics in neonates using modeling and simulation approaches. However no clear consensus on optimal dosing has been achieved. The objective of the present study was to perform an external evaluation of published models, in order to test their predictive performances in an independent dataset and to identify the possible study-related factors influencing the transferability of pharmacokinetic models to different clinical settings. Method Published neonatal vancomycin pharmacokinetic models were screened from the literature. The predictive performance of six models was evaluated using an independent dataset (112 concentrations from 78 neonates). The evaluation procedures used simulation-based diagnostics [visual predictive check (VPC) and normalized prediction distribution errors (NPDE)]. Results Differences in predictive performances of models for vancomycin pharmacokinetics in neonates were found. The mean of NPDE for six evaluated models were 1.35, −0.22, −0.36, 0.24, 0.66 and 0.48, respectively. These differences were explained, at least partly, by taking into account the method used to measure serum creatinine concentrations. The adult conversion factor of 1.3 (enzymatic to Jaffé) was tested with an improvement in the VPC and NPDE, but it still needs to be evaluated and validated in neonates. Differences were also identified between analytical methods for vancomycin. Conclusion The importance of analytical techniques for serum creatinine concentrations and vancomycin as predictors of vancomycin concentrations in neonates have been confirmed. Dosage individualization of vancomycin in neonates should consider not only patients' characteristics and clinical conditions, but also the methods used to measure serum creatinine and vancomycin. PMID:23148919

A prediction model for early death in non-small cell lung cancer patients following curative-intent chemoradiotherapy.

PubMed

Jochems, Arthur; El-Naqa, Issam; Kessler, Marc; Mayo, Charles S; Jolly, Shruti; Matuszak, Martha; Faivre-Finn, Corinne; Price, Gareth; Holloway, Lois; Vinod, Shalini; Field, Matthew; Barakat, Mohamed Samir; Thwaites, David; de Ruysscher, Dirk; Dekker, Andre; Lambin, Philippe

2018-02-01

Early death after a treatment can be seen as a therapeutic failure. Accurate prediction of patients at risk for early mortality is crucial to avoid unnecessary harm and reducing costs. The goal of our work is two-fold: first, to evaluate the performance of a previously published model for early death in our cohorts. Second, to develop a prognostic model for early death prediction following radiotherapy. Patients with NSCLC treated with chemoradiotherapy or radiotherapy alone were included in this study. Four different cohorts from different countries were available for this work (N = 1540). The previous model used age, gender, performance status, tumor stage, income deprivation, no previous treatment given (yes/no) and body mass index to make predictions. A random forest model was developed by learning on the Maastro cohort (N = 698). The new model used performance status, age, gender, T and N stage, total tumor volume (cc), total tumor dose (Gy) and chemotherapy timing (none, sequential, concurrent) to make predictions. Death within 4 months of receiving the first radiotherapy fraction was used as the outcome. Early death rates ranged from 6 to 11% within the four cohorts. The previous model performed with AUC values ranging from 0.54 to 0.64 on the validation cohorts. Our newly developed model had improved AUC values ranging from 0.62 to 0.71 on the validation cohorts. Using advanced machine learning methods and informative variables, prognostic models for early mortality can be developed. Development of accurate prognostic tools for early mortality is important to inform patients about treatment options and optimize care.

Using Modeling and Simulation to Predict Operator Performance and Automation-Induced Complacency With Robotic Automation: A Case Study and Empirical Validation.

PubMed

Wickens, Christopher D; Sebok, Angelia; Li, Huiyang; Sarter, Nadine; Gacy, Andrew M

2015-09-01

The aim of this study was to develop and validate a computational model of the automation complacency effect, as operators work on a robotic arm task, supported by three different degrees of automation. Some computational models of complacency in human-automation interaction exist, but those are formed and validated within the context of fairly simplified monitoring failures. This research extends model validation to a much more complex task, so that system designers can establish, without need for human-in-the-loop (HITL) experimentation, merits and shortcomings of different automation degrees. We developed a realistic simulation of a space-based robotic arm task that could be carried out with three different levels of trajectory visualization and execution automation support. Using this simulation, we performed HITL testing. Complacency was induced via several trials of correctly performing automation and then was assessed on trials when automation failed. Following a cognitive task analysis of the robotic arm operation, we developed a multicomponent model of the robotic operator and his or her reliance on automation, based in part on visual scanning. The comparison of model predictions with empirical results revealed that the model accurately predicted routine performance and predicted the responses to these failures after complacency developed. However, the scanning models do not account for the entire attention allocation effects of complacency. Complacency modeling can provide a useful tool for predicting the effects of different types of imperfect automation. The results from this research suggest that focus should be given to supporting situation awareness in automation development. © 2015, Human Factors and Ergonomics Society.

e-Cow: an animal model that predicts herbage intake, milk yield and live weight change in dairy cows grazing temperate pastures, with and without supplementary feeding.

PubMed

Baudracco, J; Lopez-Villalobos, N; Holmes, C W; Comeron, E A; Macdonald, K A; Barry, T N; Friggens, N C

2012-06-01

This animal simulation model, named e-Cow, represents a single dairy cow at grazing. The model integrates algorithms from three previously published models: a model that predicts herbage dry matter (DM) intake by grazing dairy cows, a mammary gland model that predicts potential milk yield and a body lipid model that predicts genetically driven live weight (LW) and body condition score (BCS). Both nutritional and genetic drives are accounted for in the prediction of energy intake and its partitioning. The main inputs are herbage allowance (HA; kg DM offered/cow per day), metabolisable energy and NDF concentrations in herbage and supplements, supplements offered (kg DM/cow per day), type of pasture (ryegrass or lucerne), days in milk, days pregnant, lactation number, BCS and LW at calving, breed or strain of cow and genetic merit, that is, potential yields of milk, fat and protein. Separate equations are used to predict herbage intake, depending on the cutting heights at which HA is expressed. The e-Cow model is written in Visual Basic programming language within Microsoft Excel®. The model predicts whole-lactation performance of dairy cows on a daily basis, and the main outputs are the daily and annual DM intake, milk yield and changes in BCS and LW. In the e-Cow model, neither herbage DM intake nor milk yield or LW change are needed as inputs; instead, they are predicted by the e-Cow model. The e-Cow model was validated against experimental data for Holstein-Friesian cows with both North American (NA) and New Zealand (NZ) genetics grazing ryegrass-based pastures, with or without supplementary feeding and for three complete lactations, divided into weekly periods. The model was able to predict animal performance with satisfactory accuracy, with concordance correlation coefficients of 0.81, 0.76 and 0.62 for herbage DM intake, milk yield and LW change, respectively. Simulations performed with the model showed that it is sensitive to genotype by feeding environment interactions. The e-Cow model tended to overestimate the milk yield of NA genotype cows at low milk yields, while it underestimated the milk yield of NZ genotype cows at high milk yields. The approach used to define the potential milk yield of the cow and equations used to predict herbage DM intake make the model applicable for predictions in countries with temperate pastures.

Effect of time step size and turbulence model on the open water hydrodynamic performance prediction of contra-rotating propellers

NASA Astrophysics Data System (ADS)

Wang, Zhan-zhi; Xiong, Ying

2013-04-01

A growing interest has been devoted to the contra-rotating propellers (CRPs) due to their high propulsive efficiency, torque balance, low fuel consumption, low cavitations, low noise performance and low hull vibration. Compared with the single-screw system, it is more difficult for the open water performance prediction because forward and aft propellers interact with each other and generate a more complicated flow field around the CRPs system. The current work focuses on the open water performance prediction of contra-rotating propellers by RANS and sliding mesh method considering the effect of computational time step size and turbulence model. The validation study has been performed on two sets of contra-rotating propellers developed by David W Taylor Naval Ship R & D center. Compared with the experimental data, it shows that RANS with sliding mesh method and SST k-ω turbulence model has a good precision in the open water performance prediction of contra-rotating propellers, and small time step size can improve the level of accuracy for CRPs with the same blade number of forward and aft propellers, while a relatively large time step size is a better choice for CRPs with different blade numbers.

Real-time prediction of respiratory motion based on a local dynamic model in an augmented space

NASA Astrophysics Data System (ADS)

Hong, S.-M.; Jung, B.-H.; Ruan, D.

2011-03-01

Motion-adaptive radiotherapy aims to deliver ablative radiation dose to the tumor target with minimal normal tissue exposure, by accounting for real-time target movement. In practice, prediction is usually necessary to compensate for system latency induced by measurement, communication and control. This work focuses on predicting respiratory motion, which is most dominant for thoracic and abdominal tumors. We develop and investigate the use of a local dynamic model in an augmented space, motivated by the observation that respiratory movement exhibits a locally circular pattern in a plane augmented with a delayed axis. By including the angular velocity as part of the system state, the proposed dynamic model effectively captures the natural evolution of respiratory motion. The first-order extended Kalman filter is used to propagate and update the state estimate. The target location is predicted by evaluating the local dynamic model equations at the required prediction length. This method is complementary to existing work in that (1) the local circular motion model characterizes 'turning', overcoming the limitation of linear motion models; (2) it uses a natural state representation including the local angular velocity and updates the state estimate systematically, offering explicit physical interpretations; (3) it relies on a parametric model and is much less data-satiate than the typical adaptive semiparametric or nonparametric method. We tested the performance of the proposed method with ten RPM traces, using the normalized root mean squared difference between the predicted value and the retrospective observation as the error metric. Its performance was compared with predictors based on the linear model, the interacting multiple linear models and the kernel density estimator for various combinations of prediction lengths and observation rates. The local dynamic model based approach provides the best performance for short to medium prediction lengths under relatively low observation rate. Sensitivity analysis indicates its robustness toward the choice of parameters. Its simplicity, robustness and low computation cost makes the proposed local dynamic model an attractive tool for real-time prediction with system latencies below 0.4 s.

Real-time prediction of respiratory motion based on a local dynamic model in an augmented space.

PubMed

Hong, S-M; Jung, B-H; Ruan, D

2011-03-21

Motion-adaptive radiotherapy aims to deliver ablative radiation dose to the tumor target with minimal normal tissue exposure, by accounting for real-time target movement. In practice, prediction is usually necessary to compensate for system latency induced by measurement, communication and control. This work focuses on predicting respiratory motion, which is most dominant for thoracic and abdominal tumors. We develop and investigate the use of a local dynamic model in an augmented space, motivated by the observation that respiratory movement exhibits a locally circular pattern in a plane augmented with a delayed axis. By including the angular velocity as part of the system state, the proposed dynamic model effectively captures the natural evolution of respiratory motion. The first-order extended Kalman filter is used to propagate and update the state estimate. The target location is predicted by evaluating the local dynamic model equations at the required prediction length. This method is complementary to existing work in that (1) the local circular motion model characterizes 'turning', overcoming the limitation of linear motion models; (2) it uses a natural state representation including the local angular velocity and updates the state estimate systematically, offering explicit physical interpretations; (3) it relies on a parametric model and is much less data-satiate than the typical adaptive semiparametric or nonparametric method. We tested the performance of the proposed method with ten RPM traces, using the normalized root mean squared difference between the predicted value and the retrospective observation as the error metric. Its performance was compared with predictors based on the linear model, the interacting multiple linear models and the kernel density estimator for various combinations of prediction lengths and observation rates. The local dynamic model based approach provides the best performance for short to medium prediction lengths under relatively low observation rate. Sensitivity analysis indicates its robustness toward the choice of parameters. Its simplicity, robustness and low computation cost makes the proposed local dynamic model an attractive tool for real-time prediction with system latencies below 0.4 s.

Modelling impacts of performance on the probability of reproducing, and thereby on productive lifespan, allow prediction of lifetime efficiency in dairy cows.

PubMed

Phuong, H N; Blavy, P; Martin, O; Schmidely, P; Friggens, N C

2016-01-01

Reproductive success is a key component of lifetime efficiency - which is the ratio of energy in milk (MJ) to energy intake (MJ) over the lifespan, of cows. At the animal level, breeding and feeding management can substantially impact milk yield, body condition and energy balance of cows, which are known as major contributors to reproductive failure in dairy cattle. This study extended an existing lifetime performance model to incorporate the impacts that performance changes due to changing breeding and feeding strategies have on the probability of reproducing and thereby on the productive lifespan, and thus allow the prediction of a cow's lifetime efficiency. The model is dynamic and stochastic, with an individual cow being the unit modelled and one day being the unit of time. To evaluate the model, data from a French study including Holstein and Normande cows fed high-concentrate diets and data from a Scottish study including Holstein cows selected for high and average genetic merit for fat plus protein that were fed high- v. low-concentrate diets were used. Generally, the model consistently simulated productive and reproductive performance of various genotypes of cows across feeding systems. In the French data, the model adequately simulated the reproductive performance of Holsteins but significantly under-predicted that of Normande cows. In the Scottish data, conception to first service was comparably simulated, whereas interval traits were slightly under-predicted. Selection for greater milk production impaired the reproductive performance and lifespan but not lifetime efficiency. The definition of lifetime efficiency used in this model did not include associated costs or herd-level effects. Further works should include such economic indicators to allow more accurate simulation of lifetime profitability in different production scenarios.

Reevaluation of a walleye (Sander vitreus) bioenergetics model

USGS Publications Warehouse

Madenjian, Charles P.; Wang, Chunfang

2013-01-01

Walleye (Sander vitreus) is an important sport fish throughout much of North America, and walleye populations support valuable commercial fisheries in certain lakes as well. Using a corrected algorithm for balancing the energy budget, we reevaluated the performance of the Wisconsin bioenergetics model for walleye in the laboratory. Walleyes were fed rainbow smelt (Osmerus mordax) in four laboratory tanks each day during a 126-day experiment. Feeding rates ranged from 1.4 to 1.7 % of walleye body weight per day. Based on a statistical comparison of bioenergetics model predictions of monthly consumption with observed monthly consumption, we concluded that the bioenergetics model estimated food consumption by walleye without any significant bias. Similarly, based on a statistical comparison of bioenergetics model predictions of weight at the end of the monthly test period with observed weight, we concluded that the bioenergetics model predicted walleye growth without any detectable bias. In addition, the bioenergetics model predictions of cumulative consumption over the 126-day experiment differed fromobserved cumulative consumption by less than 10 %. Although additional laboratory and field testing will be needed to fully evaluate model performance, based on our laboratory results, the Wisconsin bioenergetics model for walleye appears to be providing unbiased predictions of food consumption.

An alternative covariance estimator to investigate genetic heterogeneity in populations

USDA-ARS?s Scientific Manuscript database

Genomic predictions and GWAS have used mixed models for identification of associations and trait predictions. In both cases, the covariance between individuals for performance is estimated using molecular markers. Mixed model properties indicate that the use of the data for prediction is optimal if ...

Comparing theories' performance in predicting violence.

PubMed

Haas, Henriette; Cusson, Maurice

2015-01-01

The stakes of choosing the best theory as a basis for violence prevention and offender rehabilitation are high. However, no single theory of violence has ever been universally accepted by a majority of established researchers. Psychiatry, psychology and sociology are each subdivided into different schools relying upon different premises. All theories can produce empirical evidence for their validity, some of them stating the opposite of each other. Calculating different models with multivariate logistic regression on a dataset of N = 21,312 observations and ninety-two influences allowed a direct comparison of the performance of operationalizations of some of the most important schools. The psychopathology model ranked as the best model in terms of predicting violence right after the comprehensive interdisciplinary model. Next came the rational choice and lifestyle model and third the differential association and learning theory model. Other models namely the control theory model, the childhood-trauma model and the social conflict and reaction model turned out to have low sensitivities for predicting violence. Nevertheless, all models produced acceptable results in predictions of a non-violent outcome. Copyright © 2015. Published by Elsevier Ltd.

External Validation of the Garvan Nomograms for Predicting Absolute Fracture Risk: The Tromsø Study

PubMed Central

Ahmed, Luai A.; Nguyen, Nguyen D.; Bjørnerem, Åshild; Joakimsen, Ragnar M.; Jørgensen, Lone; Størmer, Jan; Bliuc, Dana; Center, Jacqueline R.; Eisman, John A.; Nguyen, Tuan V.; Emaus, Nina

2014-01-01

Background Absolute risk estimation is a preferred approach for assessing fracture risk and treatment decision making. This study aimed to evaluate and validate the predictive performance of the Garvan Fracture Risk Calculator in a Norwegian cohort. Methods The analysis included 1637 women and 1355 aged 60+ years from the Tromsø study. All incident fragility fractures between 2001 and 2009 were registered. The predicted probabilities of non-vertebral osteoporotic and hip fractures were determined using models with and without BMD. The discrimination and calibration of the models were assessed. Reclassification analysis was used to compare the models performance. Results The incidence of osteoporotic and hip fracture was 31.5 and 8.6 per 1000 population in women, respectively; in men the corresponding incidence was 12.2 and 5.1. The predicted 5-year and 10-year probability of fractures was consistently higher in the fracture group than the non-fracture group for all models. The 10-year predicted probabilities of hip fracture in those with fracture was 2.8 (women) to 3.1 times (men) higher than those without fracture. There was a close agreement between predicted and observed risk in both sexes and up to the fifth quintile. Among those in the highest quintile of risk, the models over-estimated the risk of fracture. Models with BMD performed better than models with body weight in correct classification of risk in individuals with and without fracture. The overall net decrease in reclassification of the model with weight compared to the model with BMD was 10.6% (p = 0.008) in women and 17.2% (p = 0.001) in men for osteoporotic fractures, and 13.3% (p = 0.07) in women and 17.5% (p = 0.09) in men for hip fracture. Conclusions The Garvan Fracture Risk Calculator is valid and clinically useful in identifying individuals at high risk of fracture. The models with BMD performed better than those with body weight in fracture risk prediction. PMID:25255221

Morbidity Rate Prediction of Dengue Hemorrhagic Fever (DHF) Using the Support Vector Machine and the Aedes aegypti Infection Rate in Similar Climates and Geographical Areas

PubMed Central

Kesorn, Kraisak; Ongruk, Phatsavee; Chompoosri, Jakkrawarn; Phumee, Atchara; Thavara, Usavadee; Tawatsin, Apiwat; Siriyasatien, Padet

2015-01-01

Background In the past few decades, several researchers have proposed highly accurate prediction models that have typically relied on climate parameters. However, climate factors can be unreliable and can lower the effectiveness of prediction when they are applied in locations where climate factors do not differ significantly. The purpose of this study was to improve a dengue surveillance system in areas with similar climate by exploiting the infection rate in the Aedes aegypti mosquito and using the support vector machine (SVM) technique for forecasting the dengue morbidity rate. Methods and Findings Areas with high incidence of dengue outbreaks in central Thailand were studied. The proposed framework consisted of the following three major parts: 1) data integration, 2) model construction, and 3) model evaluation. We discovered that the Ae. aegypti female and larvae mosquito infection rates were significantly positively associated with the morbidity rate. Thus, the increasing infection rate of female mosquitoes and larvae led to a higher number of dengue cases, and the prediction performance increased when those predictors were integrated into a predictive model. In this research, we applied the SVM with the radial basis function (RBF) kernel to forecast the high morbidity rate and take precautions to prevent the development of pervasive dengue epidemics. The experimental results showed that the introduced parameters significantly increased the prediction accuracy to 88.37% when used on the test set data, and these parameters led to the highest performance compared to state-of-the-art forecasting models. Conclusions The infection rates of the Ae. aegypti female mosquitoes and larvae improved the morbidity rate forecasting efficiency better than the climate parameters used in classical frameworks. We demonstrated that the SVM-R-based model has high generalization performance and obtained the highest prediction performance compared to classical models as measured by the accuracy, sensitivity, specificity, and mean absolute error (MAE). PMID:25961289

Predicting in vivo effect levels for repeat-dose systemic toxicity using chemical, biological, kinetic and study covariates.

PubMed

Truong, Lisa; Ouedraogo, Gladys; Pham, LyLy; Clouzeau, Jacques; Loisel-Joubert, Sophie; Blanchet, Delphine; Noçairi, Hicham; Setzer, Woodrow; Judson, Richard; Grulke, Chris; Mansouri, Kamel; Martin, Matthew

2018-02-01

In an effort to address a major challenge in chemical safety assessment, alternative approaches for characterizing systemic effect levels, a predictive model was developed. Systemic effect levels were curated from ToxRefDB, HESS-DB and COSMOS-DB from numerous study types totaling 4379 in vivo studies for 1247 chemicals. Observed systemic effects in mammalian models are a complex function of chemical dynamics, kinetics, and inter- and intra-individual variability. To address this complex problem, systemic effect levels were modeled at the study-level by leveraging study covariates (e.g., study type, strain, administration route) in addition to multiple descriptor sets, including chemical (ToxPrint, PaDEL, and Physchem), biological (ToxCast), and kinetic descriptors. Using random forest modeling with cross-validation and external validation procedures, study-level covariates alone accounted for approximately 15% of the variance reducing the root mean squared error (RMSE) from 0.96 log 10 to 0.85 log 10  mg/kg/day, providing a baseline performance metric (lower expectation of model performance). A consensus model developed using a combination of study-level covariates, chemical, biological, and kinetic descriptors explained a total of 43% of the variance with an RMSE of 0.69 log 10  mg/kg/day. A benchmark model (upper expectation of model performance) was also developed with an RMSE of 0.5 log 10  mg/kg/day by incorporating study-level covariates and the mean effect level per chemical. To achieve a representative chemical-level prediction, the minimum study-level predicted and observed effect level per chemical were compared reducing the RMSE from 1.0 to 0.73 log 10  mg/kg/day, equivalent to 87% of predictions falling within an order-of-magnitude of the observed value. Although biological descriptors did not improve model performance, the final model was enriched for biological descriptors that indicated xenobiotic metabolism gene expression, oxidative stress, and cytotoxicity, demonstrating the importance of accounting for kinetics and non-specific bioactivity in predicting systemic effect levels. Herein, we generated an externally predictive model of systemic effect levels for use as a safety assessment tool and have generated forward predictions for over 30,000 chemicals.

Developing and validating risk prediction models in an individual participant data meta-analysis

PubMed Central

2014-01-01

Background Risk prediction models estimate the risk of developing future outcomes for individuals based on one or more underlying characteristics (predictors). We review how researchers develop and validate risk prediction models within an individual participant data (IPD) meta-analysis, in order to assess the feasibility and conduct of the approach. Methods A qualitative review of the aims, methodology, and reporting in 15 articles that developed a risk prediction model using IPD from multiple studies. Results The IPD approach offers many opportunities but methodological challenges exist, including: unavailability of requested IPD, missing patient data and predictors, and between-study heterogeneity in methods of measurement, outcome definitions and predictor effects. Most articles develop their model using IPD from all available studies and perform only an internal validation (on the same set of data). Ten of the 15 articles did not allow for any study differences in baseline risk (intercepts), potentially limiting their model’s applicability and performance in some populations. Only two articles used external validation (on different data), including a novel method which develops the model on all but one of the IPD studies, tests performance in the excluded study, and repeats by rotating the omitted study. Conclusions An IPD meta-analysis offers unique opportunities for risk prediction research. Researchers can make more of this by allowing separate model intercept terms for each study (population) to improve generalisability, and by using ‘internal-external cross-validation’ to simultaneously develop and validate their model. Methodological challenges can be reduced by prospectively planned collaborations that share IPD for risk prediction. PMID:24397587

Vaginal birth after caesarean section prediction models: a UK comparative observational study.

PubMed

Mone, Fionnuala; Harrity, Conor; Mackie, Adam; Segurado, Ricardo; Toner, Brenda; McCormick, Timothy R; Currie, Aoife; McAuliffe, Fionnuala M

2015-10-01

Primarily, to assess the performance of three statistical models in predicting successful vaginal birth in patients attempting a trial of labour after one previous lower segment caesarean section (TOLAC). The statistically most reliable models were subsequently subjected to validation testing in a local antenatal population. A retrospective observational study was performed with study data collected from the Northern Ireland Maternity Service Database (NIMATs). The study population included all women that underwent a TOLAC (n=385) from 2010 to 2012 in a regional UK obstetric unit. Data was collected from the Northern Ireland Maternity Service Database (NIMATs). Area under the curve (AUC) and correlation analysis was performed. Of the three prediction models evaluated, AUC calculations for the Smith et al., Grobman et al. and Troyer and Parisi Models were 0.74, 0.72 and 0.65, respectively. Using the Smith et al. model, 52% of women had a low risk of caesarean section (CS) (predicted VBAC >72%) and 20% had a high risk of CS (predicted VBAC <60%), of whom 20% and 63% had delivery by CS. The fit between observed and predicted outcome in this study cohort using the Smith et al. and Grobman et al. models were greatest (Chi-square test, p=0.228 and 0.904), validating both within the population. The Smith et al. and Grobman et al. models could potentially be utilized within the UK to provide women with an informed choice when deciding on mode of delivery after a previous CS. Crown Copyright © 2015. Published by Elsevier Ireland Ltd. All rights reserved.

Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients.

PubMed

Aguiar, Fabio S; Almeida, Luciana L; Ruffino-Netto, Antonio; Kritski, Afranio Lineu; Mello, Fernanda Cq; Werneck, Guilherme L

2012-08-07

Tuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for predicting pulmonary TB in hospitalized patients in a high prevalence area in order to contribute to a more rational use of isolation rooms without increasing the risk of transmission. Cross sectional study of patients admitted to CFFH from March 2003 to December 2004. A classification and regression tree (CART) model was generated and validated. The area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values were used to evaluate the performance of model. Validation of the model was performed with a different sample of patients admitted to the same hospital from January to December 2005. We studied 290 patients admitted with clinical suspicion of TB. Diagnosis was confirmed in 26.5% of them. Pulmonary TB was present in 83.7% of the patients with TB (62.3% with positive sputum smear) and HIV/AIDS was present in 56.9% of patients. The validated CART model showed sensitivity, specificity, positive predictive value and negative predictive value of 60.00%, 76.16%, 33.33%, and 90.55%, respectively. The AUC was 79.70%. The CART model developed for these hospitalized patients with clinical suspicion of TB had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but our model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.

Time Sharing Between Robotics and Process Control: Validating a Model of Attention Switching.

PubMed

Wickens, Christopher Dow; Gutzwiller, Robert S; Vieane, Alex; Clegg, Benjamin A; Sebok, Angelia; Janes, Jess

2016-03-01

The aim of this study was to validate the strategic task overload management (STOM) model that predicts task switching when concurrence is impossible. The STOM model predicts that in overload, tasks will be switched to, to the extent that they are attractive on task attributes of high priority, interest, and salience and low difficulty. But more-difficult tasks are less likely to be switched away from once they are being performed. In Experiment 1, participants performed four tasks of the Multi-Attribute Task Battery and provided task-switching data to inform the role of difficulty and priority. In Experiment 2, participants concurrently performed an environmental control task and a robotic arm simulation. Workload was varied by automation of arm movement and both the phases of environmental control and existence of decision support for fault management. Attention to the two tasks was measured using a head tracker. Experiment 1 revealed the lack of influence of task priority and confirmed the differing roles of task difficulty. In Experiment 2, the percentage attention allocation across the eight conditions was predicted by the STOM model when participants rated the four attributes. Model predictions were compared against empirical data and accounted for over 95% of variance in task allocation. More-difficult tasks were performed longer than easier tasks. Task priority does not influence allocation. The multiattribute decision model provided a good fit to the data. The STOM model is useful for predicting cognitive tunneling given that human-in-the-loop simulation is time-consuming and expensive. © 2016, Human Factors and Ergonomics Society.

A Novel RSSI Prediction Using Imperialist Competition Algorithm (ICA), Radial Basis Function (RBF) and Firefly Algorithm (FFA) in Wireless Networks

PubMed Central

Goudarzi, Shidrokh; Haslina Hassan, Wan; Abdalla Hashim, Aisha-Hassan; Soleymani, Seyed Ahmad; Anisi, Mohammad Hossein; Zakaria, Omar M.

2016-01-01

This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF–FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model’s performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF–FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF–FFA model can be applied as an efficient technique for the accurate prediction of vertical handover. PMID:27438600

Evaluation of the synoptic and mesoscale predictive capabilities of a mesoscale atmospheric simulation system

NASA Technical Reports Server (NTRS)

Koch, S. E.; Skillman, W. C.; Kocin, P. J.; Wetzel, P. J.; Brill, K.; Keyser, D. A.; Mccumber, M. C.

1983-01-01

The overall performance characteristics of a limited area, hydrostatic, fine (52 km) mesh, primitive equation, numerical weather prediction model are determined in anticipation of satellite data assimilations with the model. The synoptic and mesoscale predictive capabilities of version 2.0 of this model, the Mesoscale Atmospheric Simulation System (MASS 2.0), were evaluated. The two part study is based on a sample of approximately thirty 12h and 24h forecasts of atmospheric flow patterns during spring and early summer. The synoptic scale evaluation results benchmark the performance of MASS 2.0 against that of an operational, synoptic scale weather prediction model, the Limited area Fine Mesh (LFM). The large sample allows for the calculation of statistically significant measures of forecast accuracy and the determination of systematic model errors. The synoptic scale benchmark is required before unsmoothed mesoscale forecast fields can be seriously considered.

Plasmonic Light Trapping in Thin-Film Solar Cells: Impact of Modeling on Performance Prediction

PubMed Central

Micco, Alberto; Pisco, Marco; Ricciardi, Armando; Mercaldo, Lucia V.; Usatii, Iurie; La Ferrara, Vera; Delli Veneri, Paola; Cutolo, Antonello; Cusano, Andrea

2015-01-01

We present a comparative study on numerical models used to predict the absorption enhancement in thin-film solar cells due to the presence of structured back-reflectors exciting, at specific wavelengths, hybrid plasmonic-photonic resonances. To evaluate the effectiveness of the analyzed models, they have been applied in a case study: starting from a U-shaped textured glass thin-film, µc-Si:H solar cells have been successfully fabricated. The fabricated cells, with different intrinsic layer thicknesses, have been morphologically, optically and electrically characterized. The experimental results have been successively compared with the numerical predictions. We have found that, in contrast to basic models based on the underlying schematics of the cell, numerical models taking into account the real morphology of the fabricated device, are able to effectively predict the cells performances in terms of both optical absorption and short-circuit current values.

A new risk prediction model for critical care: the Intensive Care National Audit & Research Centre (ICNARC) model.

PubMed

Harrison, David A; Parry, Gareth J; Carpenter, James R; Short, Alasdair; Rowan, Kathy

2007-04-01

To develop a new model to improve risk prediction for admissions to adult critical care units in the UK. Prospective cohort study. The setting was 163 adult, general critical care units in England, Wales, and Northern Ireland, December 1995 to August 2003. Patients were 216,626 critical care admissions. None. The performance of different approaches to modeling physiologic measurements was evaluated, and the best methods were selected to produce a new physiology score. This physiology score was combined with other information relating to the critical care admission-age, diagnostic category, source of admission, and cardiopulmonary resuscitation before admission-to develop a risk prediction model. Modeling interactions between diagnostic category and physiology score enabled the inclusion of groups of admissions that are frequently excluded from risk prediction models. The new model showed good discrimination (mean c index 0.870) and fit (mean Shapiro's R 0.665, mean Brier's score 0.132) in 200 repeated validation samples and performed well when compared with recalibrated versions of existing published risk prediction models in the cohort of patients eligible for all models. The hypothesis of perfect fit was rejected for all models, including the Intensive Care National Audit & Research Centre (ICNARC) model, as is to be expected in such a large cohort. The ICNARC model demonstrated better discrimination and overall fit than existing risk prediction models, even following recalibration of these models. We recommend it be used to replace previously published models for risk adjustment in the UK.

Modern modeling techniques had limited external validity in predicting mortality from traumatic brain injury.

PubMed

van der Ploeg, Tjeerd; Nieboer, Daan; Steyerberg, Ewout W

2016-10-01

Prediction of medical outcomes may potentially benefit from using modern statistical modeling techniques. We aimed to externally validate modeling strategies for prediction of 6-month mortality of patients suffering from traumatic brain injury (TBI) with predictor sets of increasing complexity. We analyzed individual patient data from 15 different studies including 11,026 TBI patients. We consecutively considered a core set of predictors (age, motor score, and pupillary reactivity), an extended set with computed tomography scan characteristics, and a further extension with two laboratory measurements (glucose and hemoglobin). With each of these sets, we predicted 6-month mortality using default settings with five statistical modeling techniques: logistic regression (LR), classification and regression trees, random forests (RFs), support vector machines (SVM) and neural nets. For external validation, a model developed on one of the 15 data sets was applied to each of the 14 remaining sets. This process was repeated 15 times for a total of 630 validations. The area under the receiver operating characteristic curve (AUC) was used to assess the discriminative ability of the models. For the most complex predictor set, the LR models performed best (median validated AUC value, 0.757), followed by RF and support vector machine models (median validated AUC value, 0.735 and 0.732, respectively). With each predictor set, the classification and regression trees models showed poor performance (median validated AUC value, <0.7). The variability in performance across the studies was smallest for the RF- and LR-based models (inter quartile range for validated AUC values from 0.07 to 0.10). In the area of predicting mortality from TBI, nonlinear and nonadditive effects are not pronounced enough to make modern prediction methods beneficial. Copyright © 2016 Elsevier Inc. All rights reserved.

The Use of a Block Diagram Simulation Language for Rapid Model Prototyping

NASA Technical Reports Server (NTRS)

Whitlow, Johnathan E.; Engrand, Peter

1996-01-01

The research performed this summer was a continuation of work performed during the 1995 NASA/ASEE Summer Fellowship. The focus of the work was to expand previously generated predictive models for liquid oxygen (LOX) loading into the external fuel tank of the shuttle. The models which were developed using a block diagram simulation language known as VisSim, were evaluated on numerous shuttle flights and found to well in most cases. Once the models were refined and validated, the predictive methods were integrated into the existing Rockwell software propulsion advisory tool (PAT). Although time was not sufficient to completely integrate the models developed into PAT, the ability to predict flows and pressures in the orbiter section and graphically display the results was accomplished.

Testing projected wild bee distributions in agricultural habitats: predictive power depends on species traits and habitat type.

PubMed

Marshall, Leon; Carvalheiro, Luísa G; Aguirre-Gutiérrez, Jesús; Bos, Merijn; de Groot, G Arjen; Kleijn, David; Potts, Simon G; Reemer, Menno; Roberts, Stuart; Scheper, Jeroen; Biesmeijer, Jacobus C

2015-10-01

Species distribution models (SDM) are increasingly used to understand the factors that regulate variation in biodiversity patterns and to help plan conservation strategies. However, these models are rarely validated with independently collected data and it is unclear whether SDM performance is maintained across distinct habitats and for species with different functional traits. Highly mobile species, such as bees, can be particularly challenging to model. Here, we use independent sets of occurrence data collected systematically in several agricultural habitats to test how the predictive performance of SDMs for wild bee species depends on species traits, habitat type, and sampling technique. We used a species distribution modeling approach parametrized for the Netherlands, with presence records from 1990 to 2010 for 193 Dutch wild bees. For each species, we built a Maxent model based on 13 climate and landscape variables. We tested the predictive performance of the SDMs with independent datasets collected from orchards and arable fields across the Netherlands from 2010 to 2013, using transect surveys or pan traps. Model predictive performance depended on species traits and habitat type. Occurrence of bee species specialized in habitat and diet was better predicted than generalist bees. Predictions of habitat suitability were also more precise for habitats that are temporally more stable (orchards) than for habitats that suffer regular alterations (arable), particularly for small, solitary bees. As a conservation tool, SDMs are best suited to modeling rarer, specialist species than more generalist and will work best in long-term stable habitats. The variability of complex, short-term habitats is difficult to capture in such models and historical land use generally has low thematic resolution. To improve SDMs' usefulness, models require explanatory variables and collection data that include detailed landscape characteristics, for example, variability of crops and flower availability. Additionally, testing SDMs with field surveys should involve multiple collection techniques.

A contrast-sensitive channelized-Hotelling observer to predict human performance in a detection task using lumpy backgrounds and Gaussian signals

NASA Astrophysics Data System (ADS)

Park, Subok; Badano, Aldo; Gallas, Brandon D.; Myers, Kyle J.

2007-03-01

Previously, a non-prewhitening matched filter (NPWMF) incorporating a model for the contrast sensitivity of the human visual system was introduced for modeling human performance in detection tasks with different viewing angles and white-noise backgrounds by Badano et al. But NPWMF observers do not perform well detection tasks involving complex backgrounds since they do not account for random backgrounds. A channelized-Hotelling observer (CHO) using difference-of-Gaussians (DOG) channels has been shown to track human performance well in detection tasks using lumpy backgrounds. In this work, a CHO with DOG channels, incorporating the model of the human contrast sensitivity, was developed similarly. We call this new observer a contrast-sensitive CHO (CS-CHO). The Barten model was the basis of our human contrast sensitivity model. A scalar was multiplied to the Barten model and varied to control the thresholding effect of the contrast sensitivity on luminance-valued images and hence the performance-prediction ability of the CS-CHO. The performance of the CS-CHO was compared to the average human performance from the psychophysical study by Park et al., where the task was to detect a known Gaussian signal in non-Gaussian distributed lumpy backgrounds. Six different signal-intensity values were used in this study. We chose the free parameter of our model to match the mean human performance in the detection experiment at the strongest signal intensity. Then we compared the model to the human at five different signal-intensity values in order to see if the performance of the CS-CHO matched human performance. Our results indicate that the CS-CHO with the chosen scalar for the contrast sensitivity predicts human performance closely as a function of signal intensity.

Experimental Errors in QSAR Modeling Sets: What We Can Do and What We Cannot Do.

PubMed

Zhao, Linlin; Wang, Wenyi; Sedykh, Alexander; Zhu, Hao

2017-06-30

Numerous chemical data sets have become available for quantitative structure-activity relationship (QSAR) modeling studies. However, the quality of different data sources may be different based on the nature of experimental protocols. Therefore, potential experimental errors in the modeling sets may lead to the development of poor QSAR models and further affect the predictions of new compounds. In this study, we explored the relationship between the ratio of questionable data in the modeling sets, which was obtained by simulating experimental errors, and the QSAR modeling performance. To this end, we used eight data sets (four continuous endpoints and four categorical endpoints) that have been extensively curated both in-house and by our collaborators to create over 1800 various QSAR models. Each data set was duplicated to create several new modeling sets with different ratios of simulated experimental errors (i.e., randomizing the activities of part of the compounds) in the modeling process. A fivefold cross-validation process was used to evaluate the modeling performance, which deteriorates when the ratio of experimental errors increases. All of the resulting models were also used to predict external sets of new compounds, which were excluded at the beginning of the modeling process. The modeling results showed that the compounds with relatively large prediction errors in cross-validation processes are likely to be those with simulated experimental errors. However, after removing a certain number of compounds with large prediction errors in the cross-validation process, the external predictions of new compounds did not show improvement. Our conclusion is that the QSAR predictions, especially consensus predictions, can identify compounds with potential experimental errors. But removing those compounds by the cross-validation procedure is not a reasonable means to improve model predictivity due to overfitting.

External Evaluation of Two Fluconazole Infant Population Pharmacokinetic Models

PubMed Central

Hwang, Michael F.; Beechinor, Ryan J.; Wade, Kelly C.; Benjamin, Daniel K.; Smith, P. Brian; Hornik, Christoph P.; Capparelli, Edmund V.; Duara, Shahnaz; Kennedy, Kathleen A.; Cohen-Wolkowiez, Michael

2017-01-01

ABSTRACT Fluconazole is an antifungal agent used for the treatment of invasive candidiasis, a leading cause of morbidity and mortality in premature infants. Population pharmacokinetic (PK) models of fluconazole in infants have been previously published by Wade et al. (Antimicrob Agents Chemother 52:4043–4049, 2008, https://doi.org/10.1128/AAC.00569-08) and Momper et al. (Antimicrob Agents Chemother 60:5539–5545, 2016, https://doi.org/10.1128/AAC.00963-16). Here we report the results of the first external evaluation of the predictive performance of both models. We used patient-level data from both studies to externally evaluate both PK models. The predictive performance of each model was evaluated using the model prediction error (PE), mean prediction error (MPE), mean absolute prediction error (MAPE), prediction-corrected visual predictive check (pcVPC), and normalized prediction distribution errors (NPDE). The values of the parameters of each model were reestimated using both the external and merged data sets. When evaluated with the external data set, the model proposed by Wade et al. showed lower median PE, MPE, and MAPE (0.429 μg/ml, 41.9%, and 57.6%, respectively) than the model proposed by Momper et al. (2.45 μg/ml, 188%, and 195%, respectively). The values of the majority of reestimated parameters were within 20% of their respective original parameter values for all model evaluations. Our analysis determined that though both models are robust, the model proposed by Wade et al. had greater accuracy and precision than the model proposed by Momper et al., likely because it was derived from a patient population with a wider age range. This study highlights the importance of the external evaluation of infant population PK models. PMID:28893774

Experimental Errors in QSAR Modeling Sets: What We Can Do and What We Cannot Do

PubMed Central

2017-01-01

Numerous chemical data sets have become available for quantitative structure–activity relationship (QSAR) modeling studies. However, the quality of different data sources may be different based on the nature of experimental protocols. Therefore, potential experimental errors in the modeling sets may lead to the development of poor QSAR models and further affect the predictions of new compounds. In this study, we explored the relationship between the ratio of questionable data in the modeling sets, which was obtained by simulating experimental errors, and the QSAR modeling performance. To this end, we used eight data sets (four continuous endpoints and four categorical endpoints) that have been extensively curated both in-house and by our collaborators to create over 1800 various QSAR models. Each data set was duplicated to create several new modeling sets with different ratios of simulated experimental errors (i.e., randomizing the activities of part of the compounds) in the modeling process. A fivefold cross-validation process was used to evaluate the modeling performance, which deteriorates when the ratio of experimental errors increases. All of the resulting models were also used to predict external sets of new compounds, which were excluded at the beginning of the modeling process. The modeling results showed that the compounds with relatively large prediction errors in cross-validation processes are likely to be those with simulated experimental errors. However, after removing a certain number of compounds with large prediction errors in the cross-validation process, the external predictions of new compounds did not show improvement. Our conclusion is that the QSAR predictions, especially consensus predictions, can identify compounds with potential experimental errors. But removing those compounds by the cross-validation procedure is not a reasonable means to improve model predictivity due to overfitting. PMID:28691113

A Measurement and Simulation Based Methodology for Cache Performance Modeling and Tuning

NASA Technical Reports Server (NTRS)

Waheed, Abdul; Yan, Jerry; Saini, Subhash (Technical Monitor)

1998-01-01

We present a cache performance modeling methodology that facilitates the tuning of uniprocessor cache performance for applications executing on shared memory multiprocessors by accurately predicting the effects of source code level modifications. Measurements on a single processor are initially used for identifying parts of code where cache utilization improvements may significantly impact the overall performance. Cache simulation based on trace-driven techniques can be carried out without gathering detailed address traces. Minimal runtime information for modeling cache performance of a selected code block includes: base virtual addresses of arrays, virtual addresses of variables, and loop bounds for that code block. Rest of the information is obtained from the source code. We show that the cache performance predictions are as reliable as those obtained through trace-driven simulations. This technique is particularly helpful to the exploration of various "what-if' scenarios regarding the cache performance impact for alternative code structures. We explain and validate this methodology using a simple matrix-matrix multiplication program. We then apply this methodology to predict and tune the cache performance of two realistic scientific applications taken from the Computational Fluid Dynamics (CFD) domain.

Testcross additive and dominance effects in best linear unbiased prediction of maize single-cross performance.

PubMed

Bernardo, R

1996-11-01

Best linear unbiased prediction (BLUP) has been found to be useful in maize (Zea mays L.) breeding. The advantage of including both testcross additive and dominance effects (Intralocus Model) in BLUP, rather than only testcross additive effects (Additive Model), has not been clearly demonstrated. The objective of this study was to compare the usefulness of Intralocus and Additive Models for BLUP of maize single-cross performance. Multilocation data from 1990 to 1995 were obtained from the hybrid testing program of Limagrain Genetics. Grain yield, moisture, stalk lodging, and root lodging of untested single crosses were predicted from (1) the performance of tested single crosses and (2) known genetic relationships among the parental inbreds. Correlations between predicted and observed performance were obtained with a delete-one cross-validation procedure. For the Intralocus Model, the correlations ranged from 0.50 to 0.66 for yield, 0.88 to 0.94 for moisture, 0.47 to 0.69 for stalk lodging, and 0.31 to 0.45 for root lodging. The BLUP procedure was consistently more effective with the Intralocus Model than with the Additive Model. When the Additive Model was used instead of the Intralocus Model, the reductions in the correlation were largest for root lodging (0.06-0.35), smallest for moisture (0.00-0.02), and intermediate for yield (0.02-0.06) and stalk lodging (0.02-0.08). The ratio of dominance variance (v D) to total genetic variance (v G) was highest for root lodging (0.47) and lowest for moisture (0.10). The Additive Model may be used if prior information indicates that VD for a given trait has little contribution to VG. Otherwise, the continued use of the Intralocus Model for BLUP of single-cross performance is recommended.

Solar array electrical performance assessment for Space Station Freedom

NASA Technical Reports Server (NTRS)

Smith, Bryan K.; Brisco, Holly

1993-01-01

Electrical power for Space Station Freedom will be generated by large Photovoltaic arrays with a beginning of life power requirement of 30.8 kW per array. The solar arrays will operate in a Low Earth Orbit (LEO) over a design life of fifteen years. This paper provides an analysis of the predicted solar array electrical performance over the design life and presents a summary of supporting analysis and test data for the assigned model parameters and performance loss factors. Each model parameter and loss factor is assessed based upon program requirements, component analysis, and test data to date. A description of the LMSC performance model, future test plans, and predicted performance ranges are also given.

Solar array electrical performance assessment for Space Station Freedom

NASA Technical Reports Server (NTRS)

Smith, Bryan K.; Brisco, Holly

1993-01-01

Electrical power for Space Station Freedom will be generated by large photovoltaic arrays with a beginning of life power requirement of 30.8 kW per array. The solar arrays will operate in a Low Earth Orbit (LEO) over a design life of fifteen years. This paper provides an analysis of the predicted solar array electrical performance over the design life and presents a summary of supporting analysis and test data for the assigned model parameters and performance loss factors. Each model parameter and loss factor is assessed based upon program requirements, component analysis and test data to date. A description of the LMSC performance model future test plans and predicted performance ranges are also given.

Blind predictions of protein interfaces by docking calculations in CAPRI.

PubMed

Lensink, Marc F; Wodak, Shoshana J

2010-11-15

Reliable prediction of the amino acid residues involved in protein-protein interfaces can provide valuable insight into protein function, and inform mutagenesis studies, and drug design applications. A fast-growing number of methods are being proposed for predicting protein interfaces, using structural information, energetic criteria, or sequence conservation or by integrating multiple criteria and approaches. Overall however, their performance remains limited, especially when applied to nonobligate protein complexes, where the individual components are also stable on their own. Here, we evaluate interface predictions derived from protein-protein docking calculations. To this end we measure the overlap between the interfaces in models of protein complexes submitted by 76 participants in CAPRI (Critical Assessment of Predicted Interactions) and those of 46 observed interfaces in 20 CAPRI targets corresponding to nonobligate complexes. Our evaluation considers multiple models for each target interface, submitted by different participants, using a variety of docking methods. Although this results in a substantial variability in the prediction performance across participants and targets, clear trends emerge. Docking methods that perform best in our evaluation predict interfaces with average recall and precision levels of about 60%, for a small majority (60%) of the analyzed interfaces. These levels are significantly higher than those obtained for nonobligate complexes by most extant interface prediction methods. We find furthermore that a sizable fraction (24%) of the interfaces in models ranked as incorrect in the CAPRI assessment are actually correctly predicted (recall and precision ≥50%), and that these models contribute to 70% of the correct docking-based interface predictions overall. Our analysis proves that docking methods are much more successful in identifying interfaces than in predicting complexes, and suggests that these methods have an excellent potential of addressing the interface prediction challenge. © 2010 Wiley-Liss, Inc.

Predicting introductory programming performance: A multi-institutional multivariate study

NASA Astrophysics Data System (ADS)

Bergin, Susan; Reilly, Ronan

2006-12-01

A model for predicting student performance on introductory programming modules is presented. The model uses attributes identified in a study carried out at four third-level institutions in the Republic of Ireland. Four instruments were used to collect the data and over 25 attributes were examined. A data reduction technique was applied and a logistic regression model using 10-fold stratified cross validation was developed. The model used three attributes: Leaving Certificate Mathematics result (final mathematics examination at second level), number of hours playing computer games while taking the module and programming self-esteem. Prediction success was significant with 80% of students correctly classified. The model also works well on a per-institution level. A discussion on the implications of the model is provided and future work is outlined.

Prediction modeling of physiological responses and human performance in the heat with application to space operations

NASA Technical Reports Server (NTRS)

Pandolf, Kent B.; Stroschein, Leander A.; Gonzalez, Richard R.; Sawka, Michael N.

1994-01-01

This institute has developed a comprehensive USARIEM heat strain model for predicting physiological responses and soldier performance in the heat which has been programmed for use by hand-held calculators, personal computers, and incorporated into the development of a heat strain decision aid. This model deals directly with five major inputs: the clothing worn, the physical work intensity, the state of heat acclimation, the ambient environment (air temperature, relative humidity, wind speed, and solar load), and the accepted heat casualty level. In addition to predicting rectal temperature, heart rate, and sweat loss given the above inputs, our model predicts the expected physical work/rest cycle, the maximum safe physical work time, the estimated recovery time from maximal physical work, and the drinking water requirements associated with each of these situations. This model provides heat injury risk management guidance based on thermal strain predictions from the user specified environmental conditions, soldier characteristics, clothing worn, and the physical work intensity. If heat transfer values for space operations' clothing are known, NASA can use this prediction model to help avoid undue heat strain in astronauts during space flight.

PHI and PCA3 improve the prognostic performance of PRIAS and Epstein criteria in predicting insignificant prostate cancer in men eligible for active surveillance.

PubMed

Cantiello, Francesco; Russo, Giorgio Ivan; Cicione, Antonio; Ferro, Matteo; Cimino, Sebastiano; Favilla, Vincenzo; Perdonà, Sisto; De Cobelli, Ottavio; Magno, Carlo; Morgia, Giuseppe; Damiano, Rocco

2016-04-01

To assess the performance of prostate health index (PHI) and prostate cancer antigen 3 (PCA3) when added to the PRIAS or Epstein criteria in predicting the presence of pathologically insignificant prostate cancer (IPCa) in patients who underwent radical prostatectomy (RP) but eligible for active surveillance (AS). An observational retrospective study was performed in 188 PCa patients treated with laparoscopic or robot-assisted RP but eligible for AS according to Epstein or PRIAS criteria. Blood and urinary specimens were collected before initial prostate biopsy for PHI and PCA3 measurements. Multivariate logistic regression analyses and decision curve analysis were carried out to identify predictors of IPCa using the updated ERSPC definition. At the multivariate analyses, the inclusion of both PCA3 and PHI significantly increased the accuracy of the Epstein multivariate model in predicting IPCa with an increase of 17 % (AUC = 0.77) and of 32 % (AUC = 0.92), respectively. The inclusion of both PCA3 and PHI also increased the predictive accuracy of the PRIAS multivariate model with an increase of 29 % (AUC = 0.87) and of 39 % (AUC = 0.97), respectively. DCA revealed that the multivariable models with the addition of PHI or PCA3 showed a greater net benefit and performed better than the reference models. In a direct comparison, PHI outperformed PCA3 performance resulting in higher net benefit. In a same cohort of patients eligible for AS, the addition of PHI and PCA3 to Epstein or PRIAS models improved their prognostic performance. PHI resulted in greater net benefit in predicting IPCa compared to PCA3.

Proposed evaluation framework for assessing operator performance with multisensor displays

NASA Technical Reports Server (NTRS)

Foyle, David C.

1992-01-01

Despite aggressive work on the development of sensor fusion algorithms and techniques, no formal evaluation procedures have been proposed. Based on existing integration models in the literature, an evaluation framework is developed to assess an operator's ability to use multisensor, or sensor fusion, displays. The proposed evaluation framework for evaluating the operator's ability to use such systems is a normative approach: The operator's performance with the sensor fusion display can be compared to the models' predictions based on the operator's performance when viewing the original sensor displays prior to fusion. This allows for the determination as to when a sensor fusion system leads to: 1) poorer performance than one of the original sensor displays (clearly an undesirable system in which the fused sensor system causes some distortion or interference); 2) better performance than with either single sensor system alone, but at a sub-optimal (compared to the model predictions) level; 3) optimal performance (compared to model predictions); or, 4) super-optimal performance, which may occur if the operator were able to use some highly diagnostic 'emergent features' in the sensor fusion display, which were unavailable in the original sensor displays. An experiment demonstrating the usefulness of the proposed evaluation framework is discussed.

Toward Skillful Subseasonal Prediction of North Atlantic Hurricanes with regionally-refined GFDL HiRAM

NASA Astrophysics Data System (ADS)

Gao, K.; Harris, L.; Chen, J. H.; Lin, S. J.

2017-12-01

Skillful subseasonal prediction of hurricane activity (from two weeks to less than a season) is important for early preparedness and reducing the hurricane damage in coastal regions. In this study, we will present evaluations of the performance of GFDL HiRAM (High-Resolution Atmospheric Model) for the simulation and prediction of the North Atlantic hurricane activity on the sub-seasonal time scale. A series of sub-seasonal (30-day duration) retrospective predictions were performed over the years 2000-2014 using two configurations of HiRAM: a) global uniform 25km-resolution grid and b) two-way nested grid with a 8km-resolution nest over North Atlantic. The analysis of hurricane structure from the two sets of simulations indicates the two-way-nesting method is an efficient way to improve the representation of hurricanes in global models: the two-way nested configuration produces realistic hurricane inner-core size and structure, which leads to improved lifetime maximum intensity distribution. Both configurations show very promising performance in the subseasonal hurricane genesis prediction, but the two-way nested configuration shows better performance in the prediction of major hurricane (Categories 3-5) activity because of the improved intensity simulation. We will also present the analysis of how the phase and magnitude of MJO, as well as the initial SST anomaly affect the model's prediction skill.

Digital filtering and model updating methods for improving the robustness of near-infrared multivariate calibrations.

PubMed

Kramer, Kirsten E; Small, Gary W

2009-02-01

Fourier transform near-infrared (NIR) transmission spectra are used for quantitative analysis of glucose for 17 sets of prediction data sampled as much as six months outside the timeframe of the corresponding calibration data. Aqueous samples containing physiological levels of glucose in a matrix of bovine serum albumin and triacetin are used to simulate clinical samples such as blood plasma. Background spectra of a single analyte-free matrix sample acquired during the instrumental warm-up period on the prediction day are used for calibration updating and for determining the optimal frequency response of a preprocessing infinite impulse response time-domain digital filter. By tuning the filter and the calibration model to the specific instrumental response associated with the prediction day, the calibration model is given enhanced ability to operate over time. This methodology is demonstrated in conjunction with partial least squares calibration models built with a spectral range of 4700-4300 cm(-1). By using a subset of the background spectra to evaluate the prediction performance of the updated model, projections can be made regarding the success of subsequent glucose predictions. If a threshold standard error of prediction (SEP) of 1.5 mM is used to establish successful model performance with the glucose samples, the corresponding threshold for the SEP of the background spectra is found to be 1.3 mM. For calibration updating in conjunction with digital filtering, SEP values of all 17 prediction sets collected over 3-178 days displaced from the calibration data are below 1.5 mM. In addition, the diagnostic based on the background spectra correctly assesses the prediction performance in 16 of the 17 cases.

Comparison of the predictive validity of diagnosis-based risk adjusters for clinical outcomes.

PubMed

Petersen, Laura A; Pietz, Kenneth; Woodard, LeChauncy D; Byrne, Margaret

2005-01-01

Many possible methods of risk adjustment exist, but there is a dearth of comparative data on their performance. We compared the predictive validity of 2 widely used methods (Diagnostic Cost Groups [DCGs] and Adjusted Clinical Groups [ACGs]) for 2 clinical outcomes using a large national sample of patients. We studied all patients who used Veterans Health Administration (VA) medical services in fiscal year (FY) 2001 (n = 3,069,168) and assigned both a DCG and an ACG to each. We used logistic regression analyses to compare predictive ability for death or long-term care (LTC) hospitalization for age/gender models, DCG models, and ACG models. We also assessed the effect of adding age to the DCG and ACG models. Patients in the highest DCG categories, indicating higher severity of illness, were more likely to die or to require LTC hospitalization. Surprisingly, the age/gender model predicted death slightly more accurately than the ACG model (c-statistic of 0.710 versus 0.700, respectively). The addition of age to the ACG model improved the c-statistic to 0.768. The highest c-statistic for prediction of death was obtained with a DCG/age model (0.830). The lowest c-statistics were obtained for age/gender models for LTC hospitalization (c-statistic 0.593). The c-statistic for use of ACGs to predict LTC hospitalization was 0.783, and improved to 0.792 with the addition of age. The c-statistics for use of DCGs and DCG/age to predict LTC hospitalization were 0.885 and 0.890, respectively, indicating the best prediction. We found that risk adjusters based upon diagnoses predicted an increased likelihood of death or LTC hospitalization, exhibiting good predictive validity. In this comparative analysis using VA data, DCG models were generally superior to ACG models in predicting clinical outcomes, although ACG model performance was enhanced by the addition of age.

Four Major South Korea's Rivers Using Deep Learning Models.

PubMed

Lee, Sangmok; Lee, Donghyun

2018-06-24

Harmful algal blooms are an annual phenomenon that cause environmental damage, economic losses, and disease outbreaks. A fundamental solution to this problem is still lacking, thus, the best option for counteracting the effects of algal blooms is to improve advance warnings (predictions). However, existing physical prediction models have difficulties setting a clear coefficient indicating the relationship between each factor when predicting algal blooms, and many variable data sources are required for the analysis. These limitations are accompanied by high time and economic costs. Meanwhile, artificial intelligence and deep learning methods have become increasingly common in scientific research; attempts to apply the long short-term memory (LSTM) model to environmental research problems are increasing because the LSTM model exhibits good performance for time-series data prediction. However, few studies have applied deep learning models or LSTM to algal bloom prediction, especially in South Korea, where algal blooms occur annually. Therefore, we employed the LSTM model for algal bloom prediction in four major rivers of South Korea. We conducted short-term (one week) predictions by employing regression analysis and deep learning techniques on a newly constructed water quality and quantity dataset drawn from 16 dammed pools on the rivers. Three deep learning models (multilayer perceptron, MLP; recurrent neural network, RNN; and long short-term memory, LSTM) were used to predict chlorophyll-a, a recognized proxy for algal activity. The results were compared to those from OLS (ordinary least square) regression analysis and actual data based on the root mean square error (RSME). The LSTM model showed the highest prediction rate for harmful algal blooms and all deep learning models out-performed the OLS regression analysis. Our results reveal the potential for predicting algal blooms using LSTM and deep learning.

Comparison of simplified models in the prediction of two phase flow in pipelines

NASA Astrophysics Data System (ADS)

Jerez-Carrizales, M.; Jaramillo, J. E.; Fuentes, D.

2014-06-01

Prediction of two phase flow in pipelines is a common task in engineering. It is a complex phenomenon and many models have been developed to find an approximate solution to the problem. Some old models, such as the Hagedorn & Brown (HB) model, have been highlighted by many authors to give very good performance. Furthermore, many modifications have been applied to this method to improve its predictions. In this work two simplified models which are based on empiricism (HB and Mukherjee and Brill, MB) are considered. One mechanistic model which is based on the physics of the phenomenon (AN) and it still needs some correlations called closure relations is also used. Moreover, a drift flux model defined in steady state that is flow pattern dependent (HK model) is implemented. The implementation of these methods was tested using published data in the scientific literature for vertical upward flows. Furthermore, a comparison of the predictive performance of the four models is done against a well from Campo Escuela Colorado. Difference among four models is smaller than difference with experimental data from the well in Campo Escuela Colorado.

Performance Comparison of Systemic Inflammatory Response Syndrome with Logistic Regression Models to Predict Sepsis in Neonates

PubMed Central

Thakur, Jyoti; Pahuja, Sharvan Kumar; Pahuja, Roop

2017-01-01

In 2005, an international pediatric sepsis consensus conference defined systemic inflammatory response syndrome (SIRS) for children <18 years of age, but excluded premature infants. In 2012, Hofer et al. investigated the predictive power of SIRS for term neonates. In this paper, we examined the accuracy of SIRS in predicting sepsis in neonates, irrespective of their gestational age (i.e., pre-term, term, and post-term). We also created two prediction models, named Model A and Model B, using binary logistic regression. Both models performed better than SIRS. We also developed an android application so that physicians can easily use Model A and Model B in real-world scenarios. The sensitivity, specificity, positive likelihood ratio (PLR) and negative likelihood ratio (NLR) in cases of SIRS were 16.15%, 95.53%, 3.61, and 0.88, respectively, whereas they were 29.17%, 97.82%, 13.36, and 0.72, respectively, in the case of Model A, and 31.25%, 97.30%, 11.56, and 0.71, respectively, in the case of Model B. All models were significant with p < 0.001. PMID:29257099

Effect of genetic architecture on the prediction accuracy of quantitative traits in samples of unrelated individuals.

PubMed

Morgante, Fabio; Huang, Wen; Maltecca, Christian; Mackay, Trudy F C

2018-06-01

Predicting complex phenotypes from genomic data is a fundamental aim of animal and plant breeding, where we wish to predict genetic merits of selection candidates; and of human genetics, where we wish to predict disease risk. While genomic prediction models work well with populations of related individuals and high linkage disequilibrium (LD) (e.g., livestock), comparable models perform poorly for populations of unrelated individuals and low LD (e.g., humans). We hypothesized that low prediction accuracies in the latter situation may occur when the genetics architecture of the trait departs from the infinitesimal and additive architecture assumed by most prediction models. We used simulated data for 10,000 lines based on sequence data from a population of unrelated, inbred Drosophila melanogaster lines to evaluate this hypothesis. We show that, even in very simplified scenarios meant as a stress test of the commonly used Genomic Best Linear Unbiased Predictor (G-BLUP) method, using all common variants yields low prediction accuracy regardless of the trait genetic architecture. However, prediction accuracy increases when predictions are informed by the genetic architecture inferred from mapping the top variants affecting main effects and interactions in the training data, provided there is sufficient power for mapping. When the true genetic architecture is largely or partially due to epistatic interactions, the additive model may not perform well, while models that account explicitly for interactions generally increase prediction accuracy. Our results indicate that accounting for genetic architecture can improve prediction accuracy for quantitative traits.

Prediction on carbon dioxide emissions based on fuzzy rules

NASA Astrophysics Data System (ADS)

Pauzi, Herrini; Abdullah, Lazim

2014-06-01

There are several ways to predict air quality, varying from simple regression to models based on artificial intelligence. Most of the conventional methods are not sufficiently able to provide good forecasting performances due to the problems with non-linearity uncertainty and complexity of the data. Artificial intelligence techniques are successfully used in modeling air quality in order to cope with the problems. This paper describes fuzzy inference system (FIS) to predict CO2 emissions in Malaysia. Furthermore, adaptive neuro-fuzzy inference system (ANFIS) is used to compare the prediction performance. Data of five variables: energy use, gross domestic product per capita, population density, combustible renewable and waste and CO2 intensity are employed in this comparative study. The results from the two model proposed are compared and it is clearly shown that the ANFIS outperforms FIS in CO2 prediction.

The Rangeland Hydrology and Erosion Model: A dynamic approach for predicting soil loss on rangelands

USDA-ARS?s Scientific Manuscript database

In this study we present the improved Rangeland Hydrology and Erosion Model (RHEM V2.3), a process-based erosion prediction tool specific for rangeland application. The article provides the mathematical formulation of the model and parameter estimation equations. Model performance is assessed agains...

Predicting Student Performance in a Collaborative Learning Environment

ERIC Educational Resources Information Center

Olsen, Jennifer K.; Aleven, Vincent; Rummel, Nikol

2015-01-01

Student models for adaptive systems may not model collaborative learning optimally. Past research has either focused on modeling individual learning or for collaboration, has focused on group dynamics or group processes without predicting learning. In the current paper, we adjust the Additive Factors Model (AFM), a standard logistic regression…

Predictive Caching Using the TDAG Algorithm

NASA Technical Reports Server (NTRS)

Laird, Philip; Saul, Ronald

1992-01-01

We describe how the TDAG algorithm for learning to predict symbol sequences can be used to design a predictive cache store. A model of a two-level mass storage system is developed and used to calculate the performance of the cache under various conditions. Experimental simulations provide good confirmation of the model.

Obtaining Predictions from Models Fit to Multiply Imputed Data

ERIC Educational Resources Information Center

Miles, Andrew

2016-01-01

Obtaining predictions from regression models fit to multiply imputed data can be challenging because treatments of multiple imputation seldom give clear guidance on how predictions can be calculated, and because available software often does not have built-in routines for performing the necessary calculations. This research note reviews how…

Validating and Verifying Biomathematical Models of Human Fatigue

NASA Technical Reports Server (NTRS)

Martinez, Siera Brooke; Quintero, Luis Ortiz; Flynn-Evans, Erin

2015-01-01

Airline pilots experience acute and chronic sleep deprivation, sleep inertia, and circadian desynchrony due to the need to schedule flight operations around the clock. This sleep loss and circadian desynchrony gives rise to cognitive impairments, reduced vigilance and inconsistent performance. Several biomathematical models, based principally on patterns observed in circadian rhythms and homeostatic drive, have been developed to predict a pilots levels of fatigue or alertness. These models allow for the Federal Aviation Administration (FAA) and commercial airlines to make decisions about pilot capabilities and flight schedules. Although these models have been validated in a laboratory setting, they have not been thoroughly tested in operational environments where uncontrolled factors, such as environmental sleep disrupters, caffeine use and napping, may impact actual pilot alertness and performance. We will compare the predictions of three prominent biomathematical fatigue models (McCauley Model, Harvard Model, and the privately-sold SAFTE-FAST Model) to actual measures of alertness and performance. We collected sleep logs, movement and light recordings, psychomotor vigilance task (PVT), and urinary melatonin (a marker of circadian phase) from 44 pilots in a short-haul commercial airline over one month. We will statistically compare with the model predictions to lapses on the PVT and circadian phase. We will calculate the sensitivity and specificity of each model prediction under different scheduling conditions. Our findings will aid operational decision-makers in determining the reliability of each model under real-world scheduling situations.

Experimental investigations, modeling, and analyses of high-temperature devices for space applications: Part 1. Final report, June 1996--December 1998

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

Tournier, J.; El-Genk, M.S.; Huang, L.

1999-01-01

The Institute of Space and Nuclear Power Studies at the University of New Mexico has developed a computer simulation of cylindrical geometry alkali metal thermal-to-electric converter cells using a standard Fortran 77 computer code. The objective and use of this code was to compare the experimental measurements with computer simulations, upgrade the model as appropriate, and conduct investigations of various methods to improve the design and performance of the devices for improved efficiency, durability, and longer operational lifetime. The Institute of Space and Nuclear Power Studies participated in vacuum testing of PX series alkali metal thermal-to-electric converter cells and developedmore » the alkali metal thermal-to-electric converter Performance Evaluation and Analysis Model. This computer model consisted of a sodium pressure loss model, a cell electrochemical and electric model, and a radiation/conduction heat transfer model. The code closely predicted the operation and performance of a wide variety of PX series cells which led to suggestions for improvements to both lifetime and performance. The code provides valuable insight into the operation of the cell, predicts parameters of components within the cell, and is a useful tool for predicting both the transient and steady state performance of systems of cells.« less

Experimental investigations, modeling, and analyses of high-temperature devices for space applications: Part 2. Final report, June 1996--December 1998

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

Tournier, J.; El-Genk, M.S.; Huang, L.

1999-01-01

The Institute of Space and Nuclear Power Studies at the University of New Mexico has developed a computer simulation of cylindrical geometry alkali metal thermal-to-electric converter cells using a standard Fortran 77 computer code. The objective and use of this code was to compare the experimental measurements with computer simulations, upgrade the model as appropriate, and conduct investigations of various methods to improve the design and performance of the devices for improved efficiency, durability, and longer operational lifetime. The Institute of Space and Nuclear Power Studies participated in vacuum testing of PX series alkali metal thermal-to-electric converter cells and developedmore » the alkali metal thermal-to-electric converter Performance Evaluation and Analysis Model. This computer model consisted of a sodium pressure loss model, a cell electrochemical and electric model, and a radiation/conduction heat transfer model. The code closely predicted the operation and performance of a wide variety of PX series cells which led to suggestions for improvements to both lifetime and performance. The code provides valuable insight into the operation of the cell, predicts parameters of components within the cell, and is a useful tool for predicting both the transient and steady state performance of systems of cells.« less

New Integrated Modeling Capabilities: MIDAS' Recent Behavioral Enhancements

NASA Technical Reports Server (NTRS)

Gore, Brian F.; Jarvis, Peter A.

2005-01-01

The Man-machine Integration Design and Analysis System (MIDAS) is an integrated human performance modeling software tool that is based on mechanisms that underlie and cause human behavior. A PC-Windows version of MIDAS has been created that integrates the anthropometric character "Jack (TM)" with MIDAS' validated perceptual and attention mechanisms. MIDAS now models multiple simulated humans engaging in goal-related behaviors. New capabilities include the ability to predict situations in which errors and/or performance decrements are likely due to a variety of factors including concurrent workload and performance influencing factors (PIFs). This paper describes a new model that predicts the effects of microgravity on a mission specialist's performance, and its first application to simulating the task of conducting a Life Sciences experiment in space according to a sequential or parallel schedule of performance.

Developing and Testing a Model to Predict Outcomes of Organizational Change

PubMed Central

Gustafson, David H; Sainfort, François; Eichler, Mary; Adams, Laura; Bisognano, Maureen; Steudel, Harold

2003-01-01

Objective To test the effectiveness of a Bayesian model employing subjective probability estimates for predicting success and failure of health care improvement projects. Data Sources Experts' subjective assessment data for model development and independent retrospective data on 221 healthcare improvement projects in the United States, Canada, and the Netherlands collected between 1996 and 2000 for validation. Methods A panel of theoretical and practical experts and literature in organizational change were used to identify factors predicting the outcome of improvement efforts. A Bayesian model was developed to estimate probability of successful change using subjective estimates of likelihood ratios and prior odds elicited from the panel of experts. A subsequent retrospective empirical analysis of change efforts in 198 health care organizations was performed to validate the model. Logistic regression and ROC analysis were used to evaluate the model's performance using three alternative definitions of success. Data Collection For the model development, experts' subjective assessments were elicited using an integrative group process. For the validation study, a staff person intimately involved in each improvement project responded to a written survey asking questions about model factors and project outcomes. Results Logistic regression chi-square statistics and areas under the ROC curve demonstrated a high level of model performance in predicting success. Chi-square statistics were significant at the 0.001 level and areas under the ROC curve were greater than 0.84. Conclusions A subjective Bayesian model was effective in predicting the outcome of actual improvement projects. Additional prospective evaluations as well as testing the impact of this model as an intervention are warranted. PMID:12785571

Identification of the prediction model for dengue incidence in Can Tho city, a Mekong Delta area in Vietnam.

PubMed

Phung, Dung; Huang, Cunrui; Rutherford, Shannon; Chu, Cordia; Wang, Xiaoming; Nguyen, Minh; Nguyen, Nga Huy; Manh, Cuong Do

2015-01-01

The Mekong Delta is highly vulnerable to climate change and a dengue endemic area in Vietnam. This study aims to examine the association between climate factors and dengue incidence and to identify the best climate prediction model for dengue incidence in Can Tho city, the Mekong Delta area in Vietnam. We used three different regression models comprising: standard multiple regression model (SMR), seasonal autoregressive integrated moving average model (SARIMA), and Poisson distributed lag model (PDLM) to examine the association between climate factors and dengue incidence over the period 2003-2010. We validated the models by forecasting dengue cases for the period of January-December, 2011 using the mean absolute percentage error (MAPE). Receiver operating characteristics curves were used to analyze the sensitivity of the forecast of a dengue outbreak. The results indicate that temperature and relative humidity are significantly associated with changes in dengue incidence consistently across the model methods used, but not cumulative rainfall. The Poisson distributed lag model (PDLM) performs the best prediction of dengue incidence for a 6, 9, and 12-month period and diagnosis of an outbreak however the SARIMA model performs a better prediction of dengue incidence for a 3-month period. The simple or standard multiple regression performed highly imprecise prediction of dengue incidence. We recommend a follow-up study to validate the model on a larger scale in the Mekong Delta region and to analyze the possibility of incorporating a climate-based dengue early warning method into the national dengue surveillance system. Copyright © 2014 Elsevier B.V. All rights reserved.

Predicting coronary artery disease using different artificial neural network models.

PubMed

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

2008-08-01

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

Methodologic Guide for Evaluating Clinical Performance and Effect of Artificial Intelligence Technology for Medical Diagnosis and Prediction.

PubMed

Park, Seong Ho; Han, Kyunghwa

2018-03-01

The use of artificial intelligence in medicine is currently an issue of great interest, especially with regard to the diagnostic or predictive analysis of medical images. Adoption of an artificial intelligence tool in clinical practice requires careful confirmation of its clinical utility. Herein, the authors explain key methodology points involved in a clinical evaluation of artificial intelligence technology for use in medicine, especially high-dimensional or overparameterized diagnostic or predictive models in which artificial deep neural networks are used, mainly from the standpoints of clinical epidemiology and biostatistics. First, statistical methods for assessing the discrimination and calibration performances of a diagnostic or predictive model are summarized. Next, the effects of disease manifestation spectrum and disease prevalence on the performance results are explained, followed by a discussion of the difference between evaluating the performance with use of internal and external datasets, the importance of using an adequate external dataset obtained from a well-defined clinical cohort to avoid overestimating the clinical performance as a result of overfitting in high-dimensional or overparameterized classification model and spectrum bias, and the essentials for achieving a more robust clinical evaluation. Finally, the authors review the role of clinical trials and observational outcome studies for ultimate clinical verification of diagnostic or predictive artificial intelligence tools through patient outcomes, beyond performance metrics, and how to design such studies. © RSNA, 2018.

Predictions for an invaded world: A strategy to predict the distribution of native and non-indigenous species at multiple scales

USGS Publications Warehouse

Reusser, D.A.; Lee, H.

2008-01-01

Habitat models can be used to predict the distributions of marine and estuarine non-indigenous species (NIS) over several spatial scales. At an estuary scale, our goal is to predict the estuaries most likely to be invaded, but at a habitat scale, the goal is to predict the specific locations within an estuary that are most vulnerable to invasion. As an initial step in evaluating several habitat models, model performance for a suite of benthic species with reasonably well-known distributions on the Pacific coast of the US needs to be compared. We discuss the utility of non-parametric multiplicative regression (NPMR) for predicting habitat- and estuary-scale distributions of native and NIS. NPMR incorporates interactions among variables, allows qualitative and categorical variables, and utilizes data on absence as well as presence. Preliminary results indicate that NPMR generally performs well at both spatial scales and that distributions of NIS are predicted as well as those of native species. For most species, latitude was the single best predictor, although similar model performance could be obtained at both spatial scales with combinations of other habitat variables. Errors of commission were more frequent at a habitat scale, with omission and commission errors approximately equal at an estuary scale. ?? 2008 International Council for the Exploration of the Sea. Published by Oxford Journals. All rights reserved.

Artificial neural networks as alternative tool for minimizing error predictions in manufacturing ultradeformable nanoliposome formulations.

PubMed

León Blanco, José M; González-R, Pedro L; Arroyo García, Carmen Martina; Cózar-Bernal, María José; Calle Suárez, Marcos; Canca Ortiz, David; Rabasco Álvarez, Antonio María; González Rodríguez, María Luisa

2018-01-01

This work was aimed at determining the feasibility of artificial neural networks (ANN) by implementing backpropagation algorithms with default settings to generate better predictive models than multiple linear regression (MLR) analysis. The study was hypothesized on timolol-loaded liposomes. As tutorial data for ANN, causal factors were used, which were fed into the computer program. The number of training cycles has been identified in order to optimize the performance of the ANN. The optimization was performed by minimizing the error between the predicted and real response values in the training step. The results showed that training was stopped at 10 000 training cycles with 80% of the pattern values, because at this point the ANN generalizes better. Minimum validation error was achieved at 12 hidden neurons in a single layer. MLR has great prediction ability, with errors between predicted and real values lower than 1% in some of the parameters evaluated. Thus, the performance of this model was compared to that of the MLR using a factorial design. Optimal formulations were identified by minimizing the distance among measured and theoretical parameters, by estimating the prediction errors. Results indicate that the ANN shows much better predictive ability than the MLR model. These findings demonstrate the increased efficiency of the combination of ANN and design of experiments, compared to the conventional MLR modeling techniques.

Modeling and Analysis of Structural Dynamics for a One-Tenth Scale Model NGST Sunshield

NASA Technical Reports Server (NTRS)

Johnston, John; Lienard, Sebastien; Brodeur, Steve (Technical Monitor)

2001-01-01

New modeling and analysis techniques have been developed for predicting the dynamic behavior of the Next Generation Space Telescope (NGST) sunshield. The sunshield consists of multiple layers of pretensioned, thin-film membranes supported by deployable booms. Modeling the structural dynamic behavior of the sunshield is a challenging aspect of the problem due to the effects of membrane wrinkling. A finite element model of the sunshield was developed using an approximate engineering approach, the cable network method, to account for membrane wrinkling effects. Ground testing of a one-tenth scale model of the NGST sunshield were carried out to provide data for validating the analytical model. A series of analyses were performed to predict the behavior of the sunshield under the ground test conditions. Modal analyses were performed to predict the frequencies and mode shapes of the test article and transient response analyses were completed to simulate impulse excitation tests. Comparison was made between analytical predictions and test measurements for the dynamic behavior of the sunshield. In general, the results show good agreement with the analytical model correctly predicting the approximate frequency and mode shapes for the significant structural modes.

Biological and functional relevance of CASP predictions.

PubMed

Liu, Tianyun; Ish-Shalom, Shirbi; Torng, Wen; Lafita, Aleix; Bock, Christian; Mort, Matthew; Cooper, David N; Bliven, Spencer; Capitani, Guido; Mooney, Sean D; Altman, Russ B

2018-03-01

Our goal is to answer the question: compared with experimental structures, how useful are predicted models for functional annotation? We assessed the functional utility of predicted models by comparing the performances of a suite of methods for functional characterization on the predictions and the experimental structures. We identified 28 sites in 25 protein targets to perform functional assessment. These 28 sites included nine sites with known ligand binding (holo-sites), nine sites that are expected or suggested by experimental authors for small molecule binding (apo-sites), and Ten sites containing important motifs, loops, or key residues with important disease-associated mutations. We evaluated the utility of the predictions by comparing their microenvironments to the experimental structures. Overall structural quality correlates with functional utility. However, the best-ranked predictions (global) may not have the best functional quality (local). Our assessment provides an ability to discriminate between predictions with high structural quality. When assessing ligand-binding sites, most prediction methods have higher performance on apo-sites than holo-sites. Some servers show consistently high performance for certain types of functional sites. Finally, many functional sites are associated with protein-protein interaction. We also analyzed biologically relevant features from the protein assemblies of two targets where the active site spanned the protein-protein interface. For the assembly targets, we find that the features in the models are mainly determined by the choice of template. © 2017 The Authors Proteins: Structure, Function and Bioinformatics Published by Wiley Periodicals, Inc.

Population Pharmacokinetics of Intravenous Paracetamol (Acetaminophen) in Preterm and Term Neonates: Model Development and External Evaluation.

PubMed

Cook, Sarah F; Roberts, Jessica K; Samiee-Zafarghandy, Samira; Stockmann, Chris; King, Amber D; Deutsch, Nina; Williams, Elaine F; Allegaert, Karel; Wilkins, Diana G; Sherwin, Catherine M T; van den Anker, John N

2016-01-01

The aims of this study were to develop a population pharmacokinetic model for intravenous paracetamol in preterm and term neonates and to assess the generalizability of the model by testing its predictive performance in an external dataset. Nonlinear mixed-effects models were constructed from paracetamol concentration-time data in NONMEM 7.2. Potential covariates included body weight, gestational age, postnatal age, postmenstrual age, sex, race, total bilirubin, and estimated glomerular filtration rate. An external dataset was used to test the predictive performance of the model through calculation of bias, precision, and normalized prediction distribution errors. The model-building dataset included 260 observations from 35 neonates with a mean gestational age of 33.6 weeks [standard deviation (SD) 6.6]. Data were well-described by a one-compartment model with first-order elimination. Weight predicted paracetamol clearance and volume of distribution, which were estimated as 0.348 L/h (5.5 % relative standard error; 30.8 % coefficient of variation) and 2.46 L (3.5 % relative standard error; 14.3 % coefficient of variation), respectively, at the mean subject weight of 2.30 kg. An external evaluation was performed on an independent dataset that included 436 observations from 60 neonates with a mean gestational age of 35.6 weeks (SD 4.3). The median prediction error was 10.1 % [95 % confidence interval (CI) 6.1-14.3] and the median absolute prediction error was 25.3 % (95 % CI 23.1-28.1). Weight predicted intravenous paracetamol pharmacokinetics in neonates ranging from extreme preterm to full-term gestational status. External evaluation suggested that these findings should be generalizable to other similar patient populations.

Population Pharmacokinetics of Intravenous Paracetamol (Acetaminophen) in Preterm and Term Neonates: Model Development and External Evaluation

PubMed Central

Cook, Sarah F.; Roberts, Jessica K.; Samiee-Zafarghandy, Samira; Stockmann, Chris; King, Amber D.; Deutsch, Nina; Williams, Elaine F.; Allegaert, Karel; Sherwin, Catherine M. T.; van den Anker, John N.

2017-01-01

Objectives The aims of this study were to develop a population pharmacokinetic model for intravenous paracetamol in preterm and term neonates and to assess the generalizability of the model by testing its predictive performance in an external dataset. Methods Nonlinear mixed-effects models were constructed from paracetamol concentration–time data in NONMEM 7.2. Potential covariates included body weight, gestational age, postnatal age, postmenstrual age, sex, race, total bilirubin, and estimated glomerular filtration rate. An external dataset was used to test the predictive performance of the model through calculation of bias, precision, and normalized prediction distribution errors. Results The model-building dataset included 260 observations from 35 neonates with a mean gestational age of 33.6 weeks [standard deviation (SD) 6.6]. Data were well-described by a one-compartment model with first-order elimination. Weight predicted paracetamol clearance and volume of distribution, which were estimated as 0.348 L/h (5.5 % relative standard error; 30.8 % coefficient of variation) and 2.46 L (3.5 % relative standard error; 14.3 % coefficient of variation), respectively, at the mean subject weight of 2.30 kg. An external evaluation was performed on an independent dataset that included 436 observations from 60 neonates with a mean gestational age of 35.6 weeks (SD 4.3). The median prediction error was 10.1 % [95 % confidence interval (CI) 6.1–14.3] and the median absolute prediction error was 25.3 % (95 % CI 23.1–28.1). Conclusions Weight predicted intravenous paracetamol pharmacokinetics in neonates ranging from extreme preterm to full-term gestational status. External evaluation suggested that these findings should be generalizable to other similar patient populations. PMID:26201306

Prediction of homoprotein and heteroprotein complexes by protein docking and template‐based modeling: A CASP‐CAPRI experiment

PubMed Central

Velankar, Sameer; Kryshtafovych, Andriy; Huang, Shen‐You; Schneidman‐Duhovny, Dina; Sali, Andrej; Segura, Joan; Fernandez‐Fuentes, Narcis; Viswanath, Shruthi; Elber, Ron; Grudinin, Sergei; Popov, Petr; Neveu, Emilie; Lee, Hasup; Baek, Minkyung; Park, Sangwoo; Heo, Lim; Rie Lee, Gyu; Seok, Chaok; Qin, Sanbo; Zhou, Huan‐Xiang; Ritchie, David W.; Maigret, Bernard; Devignes, Marie‐Dominique; Ghoorah, Anisah; Torchala, Mieczyslaw; Chaleil, Raphaël A.G.; Bates, Paul A.; Ben‐Zeev, Efrat; Eisenstein, Miriam; Negi, Surendra S.; Weng, Zhiping; Vreven, Thom; Pierce, Brian G.; Borrman, Tyler M.; Yu, Jinchao; Ochsenbein, Françoise; Guerois, Raphaël; Vangone, Anna; Rodrigues, João P.G.L.M.; van Zundert, Gydo; Nellen, Mehdi; Xue, Li; Karaca, Ezgi; Melquiond, Adrien S.J.; Visscher, Koen; Kastritis, Panagiotis L.; Bonvin, Alexandre M.J.J.; Xu, Xianjin; Qiu, Liming; Yan, Chengfei; Li, Jilong; Ma, Zhiwei; Cheng, Jianlin; Zou, Xiaoqin; Shen, Yang; Peterson, Lenna X.; Kim, Hyung‐Rae; Roy, Amit; Han, Xusi; Esquivel‐Rodriguez, Juan; Kihara, Daisuke; Yu, Xiaofeng; Bruce, Neil J.; Fuller, Jonathan C.; Wade, Rebecca C.; Anishchenko, Ivan; Kundrotas, Petras J.; Vakser, Ilya A.; Imai, Kenichiro; Yamada, Kazunori; Oda, Toshiyuki; Nakamura, Tsukasa; Tomii, Kentaro; Pallara, Chiara; Romero‐Durana, Miguel; Jiménez‐García, Brian; Moal, Iain H.; Férnandez‐Recio, Juan; Joung, Jong Young; Kim, Jong Yun; Joo, Keehyoung; Lee, Jooyoung; Kozakov, Dima; Vajda, Sandor; Mottarella, Scott; Hall, David R.; Beglov, Dmitri; Mamonov, Artem; Xia, Bing; Bohnuud, Tanggis; Del Carpio, Carlos A.; Ichiishi, Eichiro; Marze, Nicholas; Kuroda, Daisuke; Roy Burman, Shourya S.; Gray, Jeffrey J.; Chermak, Edrisse; Cavallo, Luigi; Oliva, Romina; Tovchigrechko, Andrey

2016-01-01

ABSTRACT We present the results for CAPRI Round 30, the first joint CASP‐CAPRI experiment, which brought together experts from the protein structure prediction and protein–protein docking communities. The Round comprised 25 targets from amongst those submitted for the CASP11 prediction experiment of 2014. The targets included mostly homodimers, a few homotetramers, and two heterodimers, and comprised protein chains that could readily be modeled using templates from the Protein Data Bank. On average 24 CAPRI groups and 7 CASP groups submitted docking predictions for each target, and 12 CAPRI groups per target participated in the CAPRI scoring experiment. In total more than 9500 models were assessed against the 3D structures of the corresponding target complexes. Results show that the prediction of homodimer assemblies by homology modeling techniques and docking calculations is quite successful for targets featuring large enough subunit interfaces to represent stable associations. Targets with ambiguous or inaccurate oligomeric state assignments, often featuring crystal contact‐sized interfaces, represented a confounding factor. For those, a much poorer prediction performance was achieved, while nonetheless often providing helpful clues on the correct oligomeric state of the protein. The prediction performance was very poor for genuine tetrameric targets, where the inaccuracy of the homology‐built subunit models and the smaller pair‐wise interfaces severely limited the ability to derive the correct assembly mode. Our analysis also shows that docking procedures tend to perform better than standard homology modeling techniques and that highly accurate models of the protein components are not always required to identify their association modes with acceptable accuracy. Proteins 2016; 84(Suppl 1):323–348. © 2016 The Authors Proteins: Structure, Function, and Bioinformatics Published by Wiley Periodicals, Inc. PMID:27122118

Multi-Step Time Series Forecasting with an Ensemble of Varied Length Mixture Models.

PubMed

Ouyang, Yicun; Yin, Hujun

2018-05-01

Many real-world problems require modeling and forecasting of time series, such as weather temperature, electricity demand, stock prices and foreign exchange (FX) rates. Often, the tasks involve predicting over a long-term period, e.g. several weeks or months. Most existing time series models are inheritably for one-step prediction, that is, predicting one time point ahead. Multi-step or long-term prediction is difficult and challenging due to the lack of information and uncertainty or error accumulation. The main existing approaches, iterative and independent, either use one-step model recursively or treat the multi-step task as an independent model. They generally perform poorly in practical applications. In this paper, as an extension of the self-organizing mixture autoregressive (AR) model, the varied length mixture (VLM) models are proposed to model and forecast time series over multi-steps. The key idea is to preserve the dependencies between the time points within the prediction horizon. Training data are segmented to various lengths corresponding to various forecasting horizons, and the VLM models are trained in a self-organizing fashion on these segments to capture these dependencies in its component AR models of various predicting horizons. The VLM models form a probabilistic mixture of these varied length models. A combination of short and long VLM models and an ensemble of them are proposed to further enhance the prediction performance. The effectiveness of the proposed methods and their marked improvements over the existing methods are demonstrated through a number of experiments on synthetic data, real-world FX rates and weather temperatures.

Short communication: Use of genomic and metabolic information as well as milk performance records for prediction of subclinical ketosis risk via artificial neural networks.

PubMed

Ehret, A; Hochstuhl, D; Krattenmacher, N; Tetens, J; Klein, M S; Gronwald, W; Thaller, G

2015-01-01

Subclinical ketosis is one of the most prevalent metabolic disorders in high-producing dairy cows during early lactation. This renders its early detection and prevention important for both economical and animal-welfare reasons. Construction of reliable predictive models is challenging, because traits like ketosis are commonly affected by multiple factors. In this context, machine learning methods offer great advantages because of their universal learning ability and flexibility in integrating various sorts of data. Here, an artificial-neural-network approach was applied to investigate the utility of metabolic, genetic, and milk performance data for the prediction of milk levels of β-hydroxybutyrate within and across consecutive weeks postpartum. Data were collected from 218 dairy cows during their first 5wk in milk. All animals were genotyped with a 50,000 SNP panel, and weekly information on the concentrations of the milk metabolites glycerophosphocholine and phosphocholine as well as milk composition data (milk yield, fat and protein percentage) was available. The concentration of β-hydroxybutyric acid in milk was used as target variable in all prediction models. Average correlations between observed and predicted target values up to 0.643 could be obtained, if milk metabolite and routine milk recording data were combined for prediction at the same day within weeks. Predictive performance of metabolic as well as milk performance-based models was higher than that of models based on genetic information. Copyright © 2015 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.

PubMed

Senders, Joeky T; Staples, Patrick C; Karhade, Aditya V; Zaki, Mark M; Gormley, William B; Broekman, Marike L D; Smith, Timothy R; Arnaout, Omar

2018-01-01

Accurate measurement of surgical outcomes is highly desirable to optimize surgical decision-making. An important element of surgical decision making is identification of the patient cohort that will benefit from surgery before the intervention. Machine learning (ML) enables computers to learn from previous data to make accurate predictions on new data. In this systematic review, we evaluate the potential of ML for neurosurgical outcome prediction. A systematic search in the PubMed and Embase databases was performed to identify all potential relevant studies up to January 1, 2017. Thirty studies were identified that evaluated ML algorithms used as prediction models for survival, recurrence, symptom improvement, and adverse events in patients undergoing surgery for epilepsy, brain tumor, spinal lesions, neurovascular disease, movement disorders, traumatic brain injury, and hydrocephalus. Depending on the specific prediction task evaluated and the type of input features included, ML models predicted outcomes after neurosurgery with a median accuracy and area under the receiver operating curve of 94.5% and 0.83, respectively. Compared with logistic regression, ML models performed significantly better and showed a median absolute improvement in accuracy and area under the receiver operating curve of 15% and 0.06, respectively. Some studies also demonstrated a better performance in ML models compared with established prognostic indices and clinical experts. In the research setting, ML has been studied extensively, demonstrating an excellent performance in outcome prediction for a wide range of neurosurgical conditions. However, future studies should investigate how ML can be implemented as a practical tool supporting neurosurgical care. Copyright © 2017 Elsevier Inc. All rights reserved.

Testing the Predictive Power of Coulomb Stress on Aftershock Sequences

NASA Astrophysics Data System (ADS)

Woessner, J.; Lombardi, A.; Werner, M. J.; Marzocchi, W.

2009-12-01

Empirical and statistical models of clustered seismicity are usually strongly stochastic and perceived to be uninformative in their forecasts, since only marginal distributions are used, such as the Omori-Utsu and Gutenberg-Richter laws. In contrast, so-called physics-based aftershock models, based on seismic rate changes calculated from Coulomb stress changes and rate-and-state friction, make more specific predictions: anisotropic stress shadows and multiplicative rate changes. We test the predictive power of models based on Coulomb stress changes against statistical models, including the popular Short Term Earthquake Probabilities and Epidemic-Type Aftershock Sequences models: We score and compare retrospective forecasts on the aftershock sequences of the 1992 Landers, USA, the 1997 Colfiorito, Italy, and the 2008 Selfoss, Iceland, earthquakes. To quantify predictability, we use likelihood-based metrics that test the consistency of the forecasts with the data, including modified and existing tests used in prospective forecast experiments within the Collaboratory for the Study of Earthquake Predictability (CSEP). Our results indicate that a statistical model performs best. Moreover, two Coulomb model classes seem unable to compete: Models based on deterministic Coulomb stress changes calculated from a given fault-slip model, and those based on fixed receiver faults. One model of Coulomb stress changes does perform well and sometimes outperforms the statistical models, but its predictive information is diluted, because of uncertainties included in the fault-slip model. Our results suggest that models based on Coulomb stress changes need to incorporate stochastic features that represent model and data uncertainty.

Survival Regression Modeling Strategies in CVD Prediction.

PubMed

Barkhordari, Mahnaz; Padyab, Mojgan; Sardarinia, Mahsa; Hadaegh, Farzad; Azizi, Fereidoun; Bozorgmanesh, Mohammadreza

2016-04-01

A fundamental part of prevention is prediction. Potential predictors are the sine qua non of prediction models. However, whether incorporating novel predictors to prediction models could be directly translated to added predictive value remains an area of dispute. The difference between the predictive power of a predictive model with (enhanced model) and without (baseline model) a certain predictor is generally regarded as an indicator of the predictive value added by that predictor. Indices such as discrimination and calibration have long been used in this regard. Recently, the use of added predictive value has been suggested while comparing the predictive performances of the predictive models with and without novel biomarkers. User-friendly statistical software capable of implementing novel statistical procedures is conspicuously lacking. This shortcoming has restricted implementation of such novel model assessment methods. We aimed to construct Stata commands to help researchers obtain the aforementioned statistical indices. We have written Stata commands that are intended to help researchers obtain the following. 1, Nam-D'Agostino X 2 goodness of fit test; 2, Cut point-free and cut point-based net reclassification improvement index (NRI), relative absolute integrated discriminatory improvement index (IDI), and survival-based regression analyses. We applied the commands to real data on women participating in the Tehran lipid and glucose study (TLGS) to examine if information relating to a family history of premature cardiovascular disease (CVD), waist circumference, and fasting plasma glucose can improve predictive performance of Framingham's general CVD risk algorithm. The command is adpredsurv for survival models. Herein we have described the Stata package "adpredsurv" for calculation of the Nam-D'Agostino X 2 goodness of fit test as well as cut point-free and cut point-based NRI, relative and absolute IDI, and survival-based regression analyses. We hope this work encourages the use of novel methods in examining predictive capacity of the emerging plethora of novel biomarkers.

Monolithic integrated circuit charge amplifier and comparator for MAMA readout

NASA Technical Reports Server (NTRS)

Cole, Edward H.; Smeins, Larry G.

1991-01-01

Prototype ICs for the Solar Heliospheric Observatory's Multi-Anode Microchannel Array (MAMA) have been developed; these ICs' charge-amplifier and comparator components were then tested with a view to pulse response and noise performance. All model performance predictions have been exceeded. Electrostatic discharge protection has been included on all IC connections; device operation over temperature has been consistent with model predictions.

Predictive Modeling of Student Performances for Retention and Academic Support in a Diagnostic Medical Sonography Program

ERIC Educational Resources Information Center

Borghese, Peter; Lacey, Sandi

2014-01-01

As part of a retention and academic support program, data was collected to develop a predictive model of student performances in core classes in a Diagnostic Medical Sonography (DMS) program. The research goal was to identify students likely to have difficulty with coursework and provide supplemental tutorial support. The focus was on the…

An Examination of Pennsylvania's Classroom Diagnostic Testing as a Predictive Model of Pennsylvania System of School Assessment Performance

ERIC Educational Resources Information Center

Matsanka, Christopher

2017-01-01

The purpose of this non-experimental quantitative study was to investigate the relationship between Pennsylvania's Classroom Diagnostic Tools (CDT) interim assessments and the state-mandated Pennsylvania System of School Assessment (PSSA) and to create linear regression equations that could be used as models to predict student performance on the…

Wine grape cultivar influence on the performance of models that predict the lower threshold canopy temperature of a water stress index

USDA-ARS?s Scientific Manuscript database

The calculation of a thermal based Crop Water Stress Index (CWSI) requires an estimate of canopy temperature under non-water stressed conditions. The objective of this study was to assess the influence of different wine grape cultivars on the performance of models that predict canopy temperature non...

Disease-Free Survival after Hepatic Resection in Hepatocellular Carcinoma Patients: A Prediction Approach Using Artificial Neural Network

PubMed Central

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

2012-01-01

Background A database for hepatocellular carcinoma (HCC) patients who had received hepatic resection was used to develop prediction models for 1-, 3- and 5-year disease-free survival based on a set of clinical parameters for this patient group. Methods The three prediction models included an artificial neural network (ANN) model, a logistic regression (LR) model, and a decision tree (DT) model. Data for 427, 354 and 297 HCC patients with histories of 1-, 3- and 5-year disease-free survival after hepatic resection, respectively, were extracted from the HCC patient database. From each of the three groups, 80% of the cases (342, 283 and 238 cases of 1-, 3- and 5-year disease-free survival, respectively) were selected to provide training data for the prediction models. The remaining 20% of cases in each group (85, 71 and 59 cases in the three respective groups) were assigned to validation groups for performance comparisons of the three models. Area under receiver operating characteristics curve (AUROC) was used as the performance index for evaluating the three models. Conclusions The ANN model outperformed the LR and DT models in terms of prediction accuracy. This study demonstrated the feasibility of using ANNs in medical decision support systems for predicting disease-free survival based on clinical databases in HCC patients who have received hepatic resection. PMID:22235270

Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project.

PubMed

Sakr, Sherif; Elshawi, Radwa; Ahmed, Amjad M; Qureshi, Waqas T; Brawner, Clinton A; Keteyian, Steven J; Blaha, Michael J; Al-Mallah, Mouaz H

2017-12-19

Prior studies have demonstrated that cardiorespiratory fitness (CRF) is a strong marker of cardiovascular health. Machine learning (ML) can enhance the prediction of outcomes through classification techniques that classify the data into predetermined categories. The aim of this study is to present an evaluation and comparison of how machine learning techniques can be applied on medical records of cardiorespiratory fitness and how the various techniques differ in terms of capabilities of predicting medical outcomes (e.g. mortality). We use data of 34,212 patients free of 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 10-year follow-up. Seven machine learning classification techniques were evaluated: Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Networks (ANN), Naïve Bayesian Classifier (BC), Bayesian Network (BN), K-Nearest Neighbor (KNN) and Random Forest (RF). In order to handle the imbalanced dataset used, the Synthetic Minority Over-Sampling Technique (SMOTE) is used. Two set of experiments have been conducted with and without the SMOTE sampling technique. On average over different evaluation metrics, SVM Classifier has shown the lowest performance while other models like BN, BC and DT performed better. The RF classifier has shown the best performance (AUC = 0.97) among all models trained using the SMOTE sampling. The results show that various ML techniques can significantly vary in terms of its performance for the different evaluation metrics. It is also not necessarily that the more complex the ML model, the more prediction accuracy can be achieved. The prediction performance of all models trained with SMOTE is much better than the performance of models trained without SMOTE. The study shows the potential of machine learning methods for predicting all-cause mortality using cardiorespiratory fitness data.

Neural network modeling of drying of rice in BAU-STR dryer

NASA Astrophysics Data System (ADS)

Alam, Md. Ashraful; Saha, Chayan Kumer; Alam, Md. Monjurul; Ashraf, Md. Ali; Bala, Bilash Kanti; Harvey, Jagger

2018-05-01

The experimental performance and artificial neural network modeling of rice drying in BAU-STR dryer is presented in this paper. The dryer consists of a biomass stove as a heat source, a perforated inner bin and a perforated outer bin with annular space for grains, and a blower (1 hp) to supply heated air. The dryer capacity was 500 kg of freshly harvested rice. Twenty experimental runs were conducted to investigate the experimental performance of the dryer for drying of rice. An independent multilayer neural network approach was used to predict the performance of the BAU-STR dryer for drying of rice. Ten sets of experimental data were used for training using back propagation algorithm and another ten sets of data were used for testing the artificial neural network model. The prediction of the performance of the dryer was found to be excellent after it was adequately trained. The statistical analysis showed that the errors (MSE and RMSE) were within and acceptable range of ±5% with a coefficient of determination (R2) of 99%. The model can be used to predict the potential of the dryer for different locations, and can also be used in a predictive optimal control algorithm.

Field Validation of Habitat Suitability Models for Vulnerable Marine Ecosystems in the South Pacific Ocean: Implications for the use of Broad-scale Models in Fisheries Management

NASA Astrophysics Data System (ADS)

Anderson, O. F.; Guinotte, J. M.; Clark, M. R.; Rowden, A. A.; Mormede, S.; Davies, A. J.; Bowden, D.

2016-02-01

Spatial management of vulnerable marine ecosystems requires accurate knowledge of their distribution. Predictive habitat suitability modelling, using species presence data and a suite of environmental predictor variables, has emerged as a useful tool for inferring distributions outside of known areas. However, validation of model predictions is typically performed with non-independent data. In this study, we describe the results of habitat suitability models constructed for four deep-sea reef-forming coral species across a large region of the South Pacific Ocean using MaxEnt and Boosted Regression Tree modelling approaches. In order to validate model predictions we conducted a photographic survey on a set of seamounts in an un-sampled area east of New Zealand. The likelihood of habitat suitable for reef forming corals on these seamounts was predicted to be variable, but very high in some regions, particularly where levels of aragonite saturation, dissolved oxygen, and particulate organic carbon were optimal. However, the observed frequency of coral occurrence in analyses of survey photographic data was much lower than expected, and patterns of observed versus predicted coral distribution were not highly correlated. The poor performance of these broad-scale models is attributed to lack of recorded species absences to inform the models, low precision of global bathymetry models, and lack of data on the geomorphology and substrate of the seamounts at scales appropriate to the modelled taxa. This demonstrates the need to use caution when interpreting and applying broad-scale, presence-only model results for fisheries management and conservation planning in data poor areas of the deep sea. Future improvements in the predictive performance of broad-scale models will rely on the continued advancement in modelling of environmental predictor variables, refinements in modelling approaches to deal with missing or biased inputs, and incorporation of true absence data.

A statistical learning framework for groundwater nitrate models of the Central Valley, California, USA

USGS Publications Warehouse

Nolan, Bernard T.; Fienen, Michael N.; Lorenz, David L.

2015-01-01

We used a statistical learning framework to evaluate the ability of three machine-learning methods to predict nitrate concentration in shallow groundwater of the Central Valley, California: boosted regression trees (BRT), artificial neural networks (ANN), and Bayesian networks (BN). Machine learning methods can learn complex patterns in the data but because of overfitting may not generalize well to new data. The statistical learning framework involves cross-validation (CV) training and testing data and a separate hold-out data set for model evaluation, with the goal of optimizing predictive performance by controlling for model overfit. The order of prediction performance according to both CV testing R2 and that for the hold-out data set was BRT > BN > ANN. For each method we identified two models based on CV testing results: that with maximum testing R2 and a version with R2 within one standard error of the maximum (the 1SE model). The former yielded CV training R2 values of 0.94–1.0. Cross-validation testing R2 values indicate predictive performance, and these were 0.22–0.39 for the maximum R2 models and 0.19–0.36 for the 1SE models. Evaluation with hold-out data suggested that the 1SE BRT and ANN models predicted better for an independent data set compared with the maximum R2 versions, which is relevant to extrapolation by mapping. Scatterplots of predicted vs. observed hold-out data obtained for final models helped identify prediction bias, which was fairly pronounced for ANN and BN. Lastly, the models were compared with multiple linear regression (MLR) and a previous random forest regression (RFR) model. Whereas BRT results were comparable to RFR, MLR had low hold-out R2 (0.07) and explained less than half the variation in the training data. Spatial patterns of predictions by the final, 1SE BRT model agreed reasonably well with previously observed patterns of nitrate occurrence in groundwater of the Central Valley.

Modeling Neurocognitive Decline and Recovery During Repeated Cycles of Extended Sleep and Chronic Sleep Deficiency.

PubMed

St Hilaire, Melissa A; Rüger, Melanie; Fratelli, Federico; Hull, Joseph T; Phillips, Andrew J K; Lockley, Steven W

2017-01-01

Intraindividual night-to-night sleep duration is often insufficient and variable. Here we report the effects of such chronic variable sleep deficiency on neurobehavioral performance and the ability of state-of-the-art models to predict these changes. Eight healthy males (mean age ± SD: 23.9 ± 2.4 years) studied at our inpatient intensive physiologic monitoring unit completed an 11-day protocol with a baseline 10-hour sleep opportunity and three cycles of two 3-hour time-in-bed (TIB) and one 10-hour TIB sleep opportunities. Participants received one of three polychromatic white light interventions (200 lux 4100K, 200 or 400 lux 17000K) for 3.5 hours on the morning following the second 3-hour TIB opportunity each cycle. Neurocognitive performance was assessed using the psychomotor vigilance test (PVT) administered every 1-2 hours. PVT data were compared to predictions of five group-average mathematical models that incorporate chronic sleep loss functions. While PVT performance deteriorated cumulatively following each cycle of two 3-hour sleep opportunities, and improved following each 10-hour sleep opportunity, performance declined cumulatively throughout the protocol at a more accelerated rate than predicted by state-of-the-art group-average mathematical models. Subjective sleepiness did not reflect performance. The light interventions had minimal effect. Despite apparent recovery following each extended sleep opportunity, residual performance impairment remained and deteriorated rapidly when rechallenged with subsequent sleep loss. None of the group-average models were capable of predicting both the build-up in impairment and recovery profile of performance observed at the group or individual level, raising concerns regarding their use in real-world settings to predict performance and improve safety. © Sleep Research Society 2016. Published by Oxford University Press on behalf of the Sleep Research Society. All rights reserved. For permissions, please e-mail journals.permissions@oup.com.

Emissions Prediction and Measurement for Liquid-Fueled TVC Combustor with and without Water Injection

NASA Technical Reports Server (NTRS)

Brankovic, A.; Ryder, R. C., Jr.; Hendricks, R. C.; Liu, N.-S.; Shouse, D. T.; Roquemore, W. M.

2005-01-01

An investigation is performed to evaluate the performance of a computational fluid dynamics (CFD) tool for the prediction of the reacting flow in a liquid-fueled combustor that uses water injection for control of pollutant emissions. The experiment consists of a multisector, liquid-fueled combustor rig operated at different inlet pressures and temperatures, and over a range of fuel/air and water/fuel ratios. Fuel can be injected directly into the main combustion airstream and into the cavities. Test rig performance is characterized by combustor exit quantities such as temperature and emissions measurements using rakes and overall pressure drop from upstream plenum to combustor exit. Visualization of the flame is performed using gray scale and color still photographs and high-frame-rate videos. CFD simulations are performed utilizing a methodology that includes computer-aided design (CAD) solid modeling of the geometry, parallel processing over networked computers, and graphical and quantitative post-processing. Physical models include liquid fuel droplet dynamics and evaporation, with combustion modeled using a hybrid finite-rate chemistry model developed for Jet-A fuel. CFD and experimental results are compared for cases with cavity-only fueling, while numerical studies of cavity and main fueling was also performed. Predicted and measured trends in combustor exit temperature, CO and NOx are in general agreement at the different water/fuel loading rates, although quantitative differences exist between the predictions and measurements.

Prediction of Bispectral Index during Target-controlled Infusion of Propofol and Remifentanil: A Deep Learning Approach.

PubMed

Lee, Hyung-Chul; Ryu, Ho-Geol; Chung, Eun-Jin; Jung, Chul-Woo

2018-03-01

The discrepancy between predicted effect-site concentration and measured bispectral index is problematic during intravenous anesthesia with target-controlled infusion of propofol and remifentanil. We hypothesized that bispectral index during total intravenous anesthesia would be more accurately predicted by a deep learning approach. Long short-term memory and the feed-forward neural network were sequenced to simulate the pharmacokinetic and pharmacodynamic parts of an empirical model, respectively, to predict intraoperative bispectral index during combined use of propofol and remifentanil. Inputs of long short-term memory were infusion histories of propofol and remifentanil, which were retrieved from target-controlled infusion pumps for 1,800 s at 10-s intervals. Inputs of the feed-forward network were the outputs of long short-term memory and demographic data such as age, sex, weight, and height. The final output of the feed-forward network was the bispectral index. The performance of bispectral index prediction was compared between the deep learning model and previously reported response surface model. The model hyperparameters comprised 8 memory cells in the long short-term memory layer and 16 nodes in the hidden layer of the feed-forward network. The model training and testing were performed with separate data sets of 131 and 100 cases. The concordance correlation coefficient (95% CI) were 0.561 (0.560 to 0.562) in the deep learning model, which was significantly larger than that in the response surface model (0.265 [0.263 to 0.266], P < 0.001). The deep learning model-predicted bispectral index during target-controlled infusion of propofol and remifentanil more accurately compared to the traditional model. The deep learning approach in anesthetic pharmacology seems promising because of its excellent performance and extensibility.

Prediction of shallow landslide occurrence: Validation of a physically-based approach through a real case study.

PubMed

Schilirò, Luca; Montrasio, Lorella; Scarascia Mugnozza, Gabriele

2016-11-01

In recent years, physically-based numerical models have frequently been used in the framework of early-warning systems devoted to rainfall-induced landslide hazard monitoring and mitigation. For this reason, in this work we describe the potential of SLIP (Shallow Landslides Instability Prediction), a simplified physically-based model for the analysis of shallow landslide occurrence. In order to test the reliability of this model, a back analysis of recent landslide events occurred in the study area (located SW of Messina, northeastern Sicily, Italy) on October 1st, 2009 was performed. The simulation results have been compared with those obtained for the same event by using TRIGRS, another well-established model for shallow landslide prediction. Afterwards, a simulation over a 2-year span period has been performed for the same area, with the aim of evaluating the performance of SLIP as early warning tool. The results confirm the good predictive capability of the model, both in terms of spatial and temporal prediction of the instability phenomena. For this reason, we recommend an operating procedure for the real-time definition of shallow landslide triggering scenarios at the catchment scale, which is based on the use of SLIP calibrated through a specific multi-methodological approach. Copyright © 2016 Elsevier B.V. All rights reserved.

Prediction of Chl-a concentrations in an eutrophic lake using ANN models with hybrid inputs

NASA Astrophysics Data System (ADS)

Aksoy, A.; Yuzugullu, O.

2017-12-01

Chlorophyll-a (Chl-a) concentrations in water bodies exhibit both spatial and temporal variations. As a result, frequent sampling is required with higher number of samples. This motivates the use of remote sensing as a monitoring tool. Yet, prediction performances of models that convert radiance values into Chl-a concentrations can be poor in shallow lakes. In this study, Chl-a concentrations in Lake Eymir, a shallow eutrophic lake in Ankara (Turkey), are determined using artificial neural network (ANN) models that use hybrid inputs composed of water quality and meteorological data as well as remotely sensed radiance values to improve prediction performance. Following a screening based on multi-collinearity and principal component analysis (PCA), dissolved-oxygen concentration (DO), pH, turbidity, and humidity were selected among several parameters as the constituents of the hybrid input dataset. Radiance values were obtained from QuickBird-2 satellite. Conversion of the hybrid input into Chl-a concentrations were studied for two different periods in the lake. ANN models were successful in predicting Chl-a concentrations. Yet, prediction performance declined for low Chl-a concentrations in the lake. In general, models with hybrid inputs were superior over the ones that solely used remotely sensed data.

Prediction of flow duration curves for ungauged basins

NASA Astrophysics Data System (ADS)

Atieh, Maya; Taylor, Graham; M. A. Sattar, Ahmed; Gharabaghi, Bahram

2017-02-01

This study presents novel models for prediction of flow Duration Curves (FDCs) at ungauged basins using artificial neural networks (ANN) and Gene Expression Programming (GEP) trained and tested using historical flow records from 171 unregulated and 89 regulated basins across North America. For the 89 regulated basins, FDCs were generated for both before and after flow regulation. Topographic, climatic, and land use characteristics are used to develop relationships between these basin characteristics and FDC statistical distribution parameters: mean (m) and variance (ν). The two main hypotheses that flow regulation has negligible effect on the mean (m) while it the variance (ν) were confirmed. The novel GEP model that predicts the mean (GEP-m) performed very well with high R2 (0.9) and D (0.95) values and low RAE value of 0.25. The simple regression model that predicts the variance (REG-v) was developed as a function of the mean (m) and a flow regulation index (R). The measured performance and uncertainty analysis indicated that the ANN-m was the best performing model with R2 (0.97), RAE (0.21), D (0.93) and the lowest 95% confidence prediction error interval (+0.22 to +3.49). Both GEP and ANN models were most sensitive to drainage area followed by mean annual precipitation, apportionment entropy disorder index, and shape factor.

Application of the hybrid ANFIS models for long term wind power density prediction with extrapolation capability.

PubMed

Hossain, Monowar; Mekhilef, Saad; Afifi, Firdaus; Halabi, Laith M; Olatomiwa, Lanre; Seyedmahmoudian, Mehdi; Horan, Ben; Stojcevski, Alex

2018-01-01

In this paper, the suitability and performance of ANFIS (adaptive neuro-fuzzy inference system), ANFIS-PSO (particle swarm optimization), ANFIS-GA (genetic algorithm) and ANFIS-DE (differential evolution) has been investigated for the prediction of monthly and weekly wind power density (WPD) of four different locations named Mersing, Kuala Terengganu, Pulau Langkawi and Bayan Lepas all in Malaysia. For this aim, standalone ANFIS, ANFIS-PSO, ANFIS-GA and ANFIS-DE prediction algorithm are developed in MATLAB platform. The performance of the proposed hybrid ANFIS models is determined by computing different statistical parameters such as mean absolute bias error (MABE), mean absolute percentage error (MAPE), root mean square error (RMSE) and coefficient of determination (R2). The results obtained from ANFIS-PSO and ANFIS-GA enjoy higher performance and accuracy than other models, and they can be suggested for practical application to predict monthly and weekly mean wind power density. Besides, the capability of the proposed hybrid ANFIS models is examined to predict the wind data for the locations where measured wind data are not available, and the results are compared with the measured wind data from nearby stations.