Learned Predictiveness Influences Rapid Attentional Capture: Evidence from the Dot Probe Task

Science.gov (United States)

Le Pelley, Mike E.; Vadillo, Miguel; Luque, David

2013-01-01

Attentional theories of associative learning and categorization propose that learning about the predictiveness of a stimulus influences the amount of attention that is paid to that stimulus. Three experiments tested this idea by looking at the extent to which stimuli that had previously been experienced as predictive or nonpredictive in a…

Learning to predict is spared in mild cognitive impairment due to Alzheimer's disease.

Science.gov (United States)

Baker, Rosalind; Bentham, Peter; Kourtzi, Zoe

2015-10-01

Learning the statistics of the environment is critical for predicting upcoming events. However, little is known about how we translate previous knowledge about scene regularities to sensory predictions. Here, we ask whether patients with mild cognitive impairment due to Alzheimer's disease (MCI-AD) that are known to have spared implicit but impaired explicit recognition memory are able to learn temporal regularities and predict upcoming events. We tested the ability of MCI-AD patients and age-matched controls to predict the orientation of a test stimulus following exposure to sequences of leftwards or rightwards oriented gratings. Our results demonstrate that exposure to temporal sequences without feedback facilitates the ability to predict an upcoming stimulus in both MCI-AD patients and controls. Further, we show that executive cognitive control may account for individual variability in predictive learning. That is, we observed significant positive correlations of performance in attentional and working memory tasks with post-training performance in the prediction task. Taken together, these results suggest a mediating role of circuits involved in cognitive control (i.e. frontal circuits) that may support the ability for predictive learning in MCI-AD.

Decoding the future from past experience: learning shapes predictions in early visual cortex.

Science.gov (United States)

Luft, Caroline D B; Meeson, Alan; Welchman, Andrew E; Kourtzi, Zoe

2015-05-01

Learning the structure of the environment is critical for interpreting the current scene and predicting upcoming events. However, the brain mechanisms that support our ability to translate knowledge about scene statistics to sensory predictions remain largely unknown. Here we provide evidence that learning of temporal regularities shapes representations in early visual cortex that relate to our ability to predict sensory events. We tested the participants' ability to predict the orientation of a test stimulus after exposure to sequences of leftward- or rightward-oriented gratings. Using fMRI decoding, we identified brain patterns related to the observers' visual predictions rather than stimulus-driven activity. Decoding of predicted orientations following structured sequences was enhanced after training, while decoding of cued orientations following exposure to random sequences did not change. These predictive representations appear to be driven by the same large-scale neural populations that encode actual stimulus orientation and to be specific to the learned sequence structure. Thus our findings provide evidence that learning temporal structures supports our ability to predict future events by reactivating selective sensory representations as early as in primary visual cortex. Copyright © 2015 the American Physiological Society.

Prediction of skin sensitization potency using machine learning approaches.

Science.gov (United States)

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

2017-07-01

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

Applications of machine learning in cancer prediction and prognosis.

Science.gov (United States)

Cruz, Joseph A; Wishart, David S

2007-02-11

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to "learn" from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on "older" technologies such artificial neural networks (ANNs) instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15-25%) improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression.

Prediction of beta-turns with learning machines.

Science.gov (United States)

Cai, Yu-Dong; Liu, Xiao-Jun; Li, Yi-Xue; Xu, Xue-biao; Chou, Kuo-Chen

2003-05-01

The support vector machine approach was introduced to predict the beta-turns in proteins. The overall self-consistency rate by the re-substitution test for the training or learning dataset reached 100%. Both the training dataset and independent testing dataset were taken from Chou [J. Pept. Res. 49 (1997) 120]. The success prediction rates by the jackknife test for the beta-turn subset of 455 tetrapeptides and non-beta-turn subset of 3807 tetrapeptides in the training dataset were 58.1 and 98.4%, respectively. The success rates with the independent dataset test for the beta-turn subset of 110 tetrapeptides and non-beta-turn subset of 30,231 tetrapeptides were 69.1 and 97.3%, respectively. The results obtained from this study support the conclusion that the residue-coupled effect along a tetrapeptide is important for the formation of a beta-turn.

Predicting Student Success from the "LASSI for Learning Online" (LLO)

Science.gov (United States)

Carson, Andrew D.

2011-01-01

This study tested the degree to which subscales of the "LASSI for Learning Online" (LLO) (Weinstein & Palmer, 2006), a measure of learning strategies and study skills, predict student success in the form of passing grades, using a combination of large training (N = 4,409) and cross-validation (N = 3,203) samples. Discriminant function analysis…

Do sophisticated epistemic beliefs predict meaningful learning? Findings from a structural equation model of undergraduate biology learning

Science.gov (United States)

Lee, Silvia Wen-Yu; Liang, Jyh-Chong; Tsai, Chin-Chung

2016-10-01

This study investigated the relationships among college students' epistemic beliefs in biology (EBB), conceptions of learning biology (COLB), and strategies of learning biology (SLB). EBB includes four dimensions, namely 'multiple-source,' 'uncertainty,' 'development,' and 'justification.' COLB is further divided into 'constructivist' and 'reproductive' conceptions, while SLB represents deep strategies and surface learning strategies. Questionnaire responses were gathered from 303 college students. The results of the confirmatory factor analysis and structural equation modelling showed acceptable model fits. Mediation testing further revealed two paths with complete mediation. In sum, students' epistemic beliefs of 'uncertainty' and 'justification' in biology were statistically significant in explaining the constructivist and reproductive COLB, respectively; and 'uncertainty' was statistically significant in explaining the deep SLB as well. The results of mediation testing further revealed that 'uncertainty' predicted surface strategies through the mediation of 'reproductive' conceptions; and the relationship between 'justification' and deep strategies was mediated by 'constructivist' COLB. This study provides evidence for the essential roles some epistemic beliefs play in predicting students' learning.

Spontaneous eye movements and trait empathy predict vicarious learning of fear.

Science.gov (United States)

Kleberg, Johan L; Selbing, Ida; Lundqvist, Daniel; Hofvander, Björn; Olsson, Andreas

2015-12-01

Learning to predict dangerous outcomes is important to survival. In humans, this kind of learning is often transmitted through the observation of others' emotional responses. We analyzed eye movements during an observational/vicarious fear learning procedure, in which healthy participants (N=33) watched another individual ('learning model') receiving aversive treatment (shocks) paired with a predictive conditioned stimulus (CS+), but not a control stimulus (CS-). Participants' gaze pattern towards the model differentiated as a function of whether the CS was predictive or not of a shock to the model. Consistent with our hypothesis that the face of a conspecific in distress can act as an unconditioned stimulus (US), we found that the total fixation time at a learning model's face increased when the CS+ was shown. Furthermore, we found that the total fixation time at the CS+ during learning predicted participants' conditioned responses (CRs) at a later test in the absence of the model. We also demonstrated that trait empathy was associated with stronger CRs, and that autistic traits were positively related to autonomic reactions to watching the model receiving the aversive treatment. Our results have implications for both healthy and dysfunctional socio-emotional learning. Copyright © 2015 Elsevier B.V. All rights reserved.

Improved method for SNR prediction in machine-learning-based test

NARCIS (Netherlands)

Sheng, Xiaoqin; Kerkhoff, Hans G.

2010-01-01

This paper applies an improved method for testing the signal-to-noise ratio (SNR) of Analogue-to-Digital Converters (ADC). In previous work, a noisy and nonlinear pulse signal is exploited as the input stimulus to obtain the signature results of ADC. By applying a machine-learning-based approach,

Applications of Machine Learning in Cancer Prediction and Prognosis

Directory of Open Access Journals (Sweden)

Joseph A. Cruz

2006-01-01

Full Text Available Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and microarray data, a strong bias towards applications in prostate and breast cancer, and a heavy reliance on “older” technologies such artificial neural networks (ANNs instead of more recently developed or more easily interpretable machine learning methods. A number of published studies also appear to lack an appropriate level of validation or testing. Among the better designed and validated studies it is clear that machine learning methods can be used to substantially (15-25% improve the accuracy of predicting cancer susceptibility, recurrence and mortality. At a more fundamental level, it is also evident that machine learning is also helping to improve our basic understanding of cancer development and progression.

PEDLA: predicting enhancers with a deep learning-based algorithmic framework.

Science.gov (United States)

Liu, Feng; Li, Hao; Ren, Chao; Bo, Xiaochen; Shu, Wenjie

2016-06-22

Transcriptional enhancers are non-coding segments of DNA that play a central role in the spatiotemporal regulation of gene expression programs. However, systematically and precisely predicting enhancers remain a major challenge. Although existing methods have achieved some success in enhancer prediction, they still suffer from many issues. We developed a deep learning-based algorithmic framework named PEDLA (https://github.com/wenjiegroup/PEDLA), which can directly learn an enhancer predictor from massively heterogeneous data and generalize in ways that are mostly consistent across various cell types/tissues. We first trained PEDLA with 1,114-dimensional heterogeneous features in H1 cells, and demonstrated that PEDLA framework integrates diverse heterogeneous features and gives state-of-the-art performance relative to five existing methods for enhancer prediction. We further extended PEDLA to iteratively learn from 22 training cell types/tissues. Our results showed that PEDLA manifested superior performance consistency in both training and independent test sets. On average, PEDLA achieved 95.0% accuracy and a 96.8% geometric mean (GM) of sensitivity and specificity across 22 training cell types/tissues, as well as 95.7% accuracy and a 96.8% GM across 20 independent test cell types/tissues. Together, our work illustrates the power of harnessing state-of-the-art deep learning techniques to consistently identify regulatory elements at a genome-wide scale from massively heterogeneous data across diverse cell types/tissues.

Machine learning-based methods for prediction of linear B-cell epitopes.

Science.gov (United States)

Wang, Hsin-Wei; Pai, Tun-Wen

2014-01-01

B-cell epitope prediction facilitates immunologists in designing peptide-based vaccine, diagnostic test, disease prevention, treatment, and antibody production. In comparison with T-cell epitope prediction, the performance of variable length B-cell epitope prediction is still yet to be satisfied. Fortunately, due to increasingly available verified epitope databases, bioinformaticians could adopt machine learning-based algorithms on all curated data to design an improved prediction tool for biomedical researchers. Here, we have reviewed related epitope prediction papers, especially those for linear B-cell epitope prediction. It should be noticed that a combination of selected propensity scales and statistics of epitope residues with machine learning-based tools formulated a general way for constructing linear B-cell epitope prediction systems. It is also observed from most of the comparison results that the kernel method of support vector machine (SVM) classifier outperformed other machine learning-based approaches. Hence, in this chapter, except reviewing recently published papers, we have introduced the fundamentals of B-cell epitope and SVM techniques. In addition, an example of linear B-cell prediction system based on physicochemical features and amino acid combinations is illustrated in details.

PREDICTING ACADEMIC ACHIEVEMENT: THE ROLE OF MOTIVATION AND LEARNING STRATEGIES

Directory of Open Access Journals (Sweden)

Juliana Beatriz Stover

2014-04-01

Full Text Available The aim of this study consists in testing a predictive model of academic achievement including motivation and learning strategies as predictors. Motivation is defined as the energy and the direction of behaviors; it is categorized in three types of motivation –intrinsic, extrinsic and amotivation (Deci & Ryan, 1985. Learning strategies are deliberate operations oriented towards information processing in academic activities (Valle, Barca, González & Núñez, 1999. Several studies analysed the relationship between motivation and learning strategies in high school and college environments. Students with higher academic achievement were intrinsically motivated and used a wider variety of learning strategies more frequently. A non-experimental predictive design was developed. The sample was composed by 459 students (55.2% high-schoolers; 44.8% college students. Data were gathered by means of sociodemographic and academic surveys, and also by the local versions of the Academic Motivation Scale –EMA, Echelle de Motivation en Éducation (Stover, de la Iglesia, Rial Boubeta & Fernández Liporace, 2012; Vallerand, Blais, Briere & Pelletier, 1989 and the Learning and Study Strategies Inventory –LASSI (Stover, Uriel & Fernández Liporace, 2012; Weinstein, Schulte & Palmer, 1987. Several path analyses were carried out to test a hypothetical model to predict academic achievement (Kline, 1998. Results indicated that self-determined motivation explained academic achievement through the use of learning strategies. The final model obtained an excellent fit (χ2=16.523, df= 6, p=0.011; GFI=0.987; AGFI=0.955; SRMR=0.0320; NFI=0.913; IFI=0.943; CFI=0.940. Results are discussed considering Self Determination Theory and previous research.

Sequence-based prediction of protein protein interaction using a deep-learning algorithm.

Science.gov (United States)

Sun, Tanlin; Zhou, Bo; Lai, Luhua; Pei, Jianfeng

2017-05-25

Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.

Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project.

Science.gov (United States)

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

Predicting Academic Success and Technological Literacy in Secondary Education: A Learning Styles Perspective

Science.gov (United States)

Avsec, Stanislav; Szewczyk-Zakrzewska, Agnieszka

2017-01-01

This paper aims to investigate the predictive validity of learning styles on academic achievement and technological literacy (TL). For this purpose, secondary school students were recruited (n = 150). An empirical research design was followed where the TL test was used with a learning style inventory measuring learning orientation, processing…

Predict-share-observe-explain learning activity for the Torricelli's tank experiment

Science.gov (United States)

Panich, Charunya; Puttharugsa, Chokchai; Khemmani, Supitch

2018-01-01

The purpose of this research was to study the students' scientific concept and achievement on fluid mechanics before and after the predict-share-observe-explain (PSOE) learning activity for the Torricelli's tank experiment. The 24 participants, who were selected by purposive sampling, were students at grade 12 at Nannakorn School, Nan province. A one group pre-test/post-test design was employed in the study. The research instruments were 1) the lesson plans using the PSOE learning activity and 2) two-tier multiple choice question and subjective tests. The results indicated that students had better scientific concept about Torricelli's tank experiment and the post-test mean score was significantly higher than the pre-test mean score at a 0.05 level of significance. Moreover, the students had retention of knowledge after the PSOE learning activity for 4 weeks at a 0.05 level of significance. The study showed that the PSOE learning activity is suitable for developing students' scientific concept and achievement.

Learning Predictive Statistics: Strategies and Brain Mechanisms.

Science.gov (United States)

Wang, Rui; Shen, Yuan; Tino, Peter; Welchman, Andrew E; Kourtzi, Zoe

2017-08-30

When immersed in a new environment, we are challenged to decipher initially incomprehensible streams of sensory information. However, quite rapidly, the brain finds structure and meaning in these incoming signals, helping us to predict and prepare ourselves for future actions. This skill relies on extracting the statistics of event streams in the environment that contain regularities of variable complexity from simple repetitive patterns to complex probabilistic combinations. Here, we test the brain mechanisms that mediate our ability to adapt to the environment's statistics and predict upcoming events. By combining behavioral training and multisession fMRI in human participants (male and female), we track the corticostriatal mechanisms that mediate learning of temporal sequences as they change in structure complexity. We show that learning of predictive structures relates to individual decision strategy; that is, selecting the most probable outcome in a given context (maximizing) versus matching the exact sequence statistics. These strategies engage distinct human brain regions: maximizing engages dorsolateral prefrontal, cingulate, sensory-motor regions, and basal ganglia (dorsal caudate, putamen), whereas matching engages occipitotemporal regions (including the hippocampus) and basal ganglia (ventral caudate). Our findings provide evidence for distinct corticostriatal mechanisms that facilitate our ability to extract behaviorally relevant statistics to make predictions. SIGNIFICANCE STATEMENT Making predictions about future events relies on interpreting streams of information that may initially appear incomprehensible. Past work has studied how humans identify repetitive patterns and associative pairings. However, the natural environment contains regularities that vary in complexity from simple repetition to complex probabilistic combinations. Here, we combine behavior and multisession fMRI to track the brain mechanisms that mediate our ability to adapt to

Using a Comprehensive Model to Test and Predict the Factors of Online Learning Effectiveness

Science.gov (United States)

He, Minyan

2013-01-01

As online learning is an important part of higher education, the effectiveness of online learning has been tested with different methods. Although the literature regarding online learning effectiveness has been related to various factors, a more comprehensive review of the factors may result in broader understanding of online learning…

Prediction of Glucose Tolerance without an Oral Glucose Tolerance Test

Directory of Open Access Journals (Sweden)

Rohit Babbar

2018-03-01

Full Text Available IntroductionImpaired glucose tolerance (IGT is diagnosed by a standardized oral glucose tolerance test (OGTT. However, the OGTT is laborious, and when not performed, glucose tolerance cannot be determined from fasting samples retrospectively. We tested if glucose tolerance status is reasonably predictable from a combination of demographic, anthropometric, and laboratory data assessed at one time point in a fasting state.MethodsGiven a set of 22 variables selected upon clinical feasibility such as sex, age, height, weight, waist circumference, blood pressure, fasting glucose, HbA1c, hemoglobin, mean corpuscular volume, serum potassium, fasting levels of insulin, C-peptide, triglyceride, non-esterified fatty acids (NEFA, proinsulin, prolactin, cholesterol, low-density lipoprotein, HDL, uric acid, liver transaminases, and ferritin, we used supervised machine learning to estimate glucose tolerance status in 2,337 participants of the TUEF study who were recruited before 2012. We tested the performance of 10 different machine learning classifiers on data from 929 participants in the test set who were recruited after 2012. In addition, reproducibility of IGT was analyzed in 78 participants who had 2 repeated OGTTs within 1 year.ResultsThe most accurate prediction of IGT was reached with the recursive partitioning method (accuracy = 0.78. For all classifiers, mean accuracy was 0.73 ± 0.04. The most important model variable was fasting glucose in all models. Using mean variable importance across all models, fasting glucose was followed by NEFA, triglycerides, HbA1c, and C-peptide. The accuracy of predicting IGT from a previous OGTT was 0.77.ConclusionMachine learning methods yield moderate accuracy in predicting glucose tolerance from a wide set of clinical and laboratory variables. A substitution of OGTT does not currently seem to be feasible. An important constraint could be the limited reproducibility of glucose tolerance status during a

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction.

Science.gov (United States)

Spencer, Matt; Eickholt, Jesse; Jianlin Cheng

2015-01-01

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80 percent and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test dataset of 198 proteins, achieving a Q3 accuracy of 80.7 percent and a Sov accuracy of 74.2 percent.

Do Judgments of Learning Predict Automatic Influences of Memory?

Science.gov (United States)

Undorf, Monika; Böhm, Simon; Cüpper, Lutz

2016-01-01

Current memory theories generally assume that memory performance reflects both recollection and automatic influences of memory. Research on people's predictions about the likelihood of remembering recently studied information on a memory test, that is, on judgments of learning (JOLs), suggests that both magnitude and resolution of JOLs are linked…

Powerful Tests for Multi-Marker Association Analysis Using Ensemble Learning.

Directory of Open Access Journals (Sweden)

Badri Padhukasahasram

Full Text Available Multi-marker approaches have received a lot of attention recently in genome wide association studies and can enhance power to detect new associations under certain conditions. Gene-, gene-set- and pathway-based association tests are increasingly being viewed as useful supplements to the more widely used single marker association analysis which have successfully uncovered numerous disease variants. A major drawback of single-marker based methods is that they do not look at the joint effects of multiple genetic variants which individually may have weak or moderate signals. Here, we describe novel tests for multi-marker association analyses that are based on phenotype predictions obtained from machine learning algorithms. Instead of assuming a linear or logistic regression model, we propose the use of ensembles of diverse machine learning algorithms for prediction. We show that phenotype predictions obtained from ensemble learning algorithms provide a new framework for multi-marker association analysis. They can be used for constructing tests for the joint association of multiple variants, adjusting for covariates and testing for the presence of interactions. To demonstrate the power and utility of this new approach, we first apply our method to simulated SNP datasets. We show that the proposed method has the correct Type-1 error rates and can be considerably more powerful than alternative approaches in some situations. Then, we apply our method to previously studied asthma-related genes in 2 independent asthma cohorts to conduct association tests.

Probabilistic Category Learning in Developmental Dyslexia: Evidence from Feedback and Paired-Associate Weather Prediction Tasks

Science.gov (United States)

Gabay, Yafit; Vakil, Eli; Schiff, Rachel; Holt, Lori L.

2015-01-01

Objective Developmental dyslexia is presumed to arise from specific phonological impairments. However, an emerging theoretical framework suggests that phonological impairments may be symptoms stemming from an underlying dysfunction of procedural learning. Method We tested procedural learning in adults with dyslexia (n=15) and matched-controls (n=15) using two versions of the Weather Prediction Task: Feedback (FB) and Paired-associate (PA). In the FB-based task, participants learned associations between cues and outcomes initially by guessing and subsequently through feedback indicating the correctness of response. In the PA-based learning task, participants viewed the cue and its associated outcome simultaneously without overt response or feedback. In both versions, participants trained across 150 trials. Learning was assessed in a subsequent test without presentation of the outcome, or corrective feedback. Results The Dyslexia group exhibited impaired learning compared with the Control group on both the FB and PA versions of the weather prediction task. Conclusions The results indicate that the ability to learn by feedback is not selectively impaired in dyslexia. Rather it seems that the probabilistic nature of the task, shared by the FB and PA versions of the weather prediction task, hampers learning in those with dyslexia. Results are discussed in light of procedural learning impairments among participants with dyslexia. PMID:25730732

Predicting Process Behaviour using Deep Learning

OpenAIRE

Evermann, Joerg; Rehse, Jana-Rebecca; Fettke, Peter

2016-01-01

Predicting business process behaviour is an important aspect of business process management. Motivated by research in natural language processing, this paper describes an application of deep learning with recurrent neural networks to the problem of predicting the next event in a business process. This is both a novel method in process prediction, which has largely relied on explicit process models, and also a novel application of deep learning methods. The approach is evaluated on two real da...

Predictive Variable Gain Iterative Learning Control for PMSM

Directory of Open Access Journals (Sweden)

Huimin Xu

2015-01-01

Full Text Available A predictive variable gain strategy in iterative learning control (ILC is introduced. Predictive variable gain iterative learning control is constructed to improve the performance of trajectory tracking. A scheme based on predictive variable gain iterative learning control for eliminating undesirable vibrations of PMSM system is proposed. The basic idea is that undesirable vibrations of PMSM system are eliminated from two aspects of iterative domain and time domain. The predictive method is utilized to determine the learning gain in the ILC algorithm. Compression mapping principle is used to prove the convergence of the algorithm. Simulation results demonstrate that the predictive variable gain is superior to constant gain and other variable gains.

SU-E-J-191: Motion Prediction Using Extreme Learning Machine in Image Guided Radiotherapy

International Nuclear Information System (INIS)

Jia, J; Cao, R; Pei, X; Wang, H; Hu, L

2015-01-01

Purpose: Real-time motion tracking is a critical issue in image guided radiotherapy due to the time latency caused by image processing and system response. It is of great necessity to fast and accurately predict the future position of the respiratory motion and the tumor location. Methods: The prediction of respiratory position was done based on the positioning and tracking module in ARTS-IGRT system which was developed by FDS Team (www.fds.org.cn). An approach involving with the extreme learning machine (ELM) was adopted to predict the future respiratory position as well as the tumor’s location by training the past trajectories. For the training process, a feed-forward neural network with one single hidden layer was used for the learning. First, the number of hidden nodes was figured out for the single layered feed forward network (SLFN). Then the input weights and hidden layer biases of the SLFN were randomly assigned to calculate the hidden neuron output matrix. Finally, the predicted movement were obtained by applying the output weights and compared with the actual movement. Breathing movement acquired from the external infrared markers was used to test the prediction accuracy. And the implanted marker movement for the prostate cancer was used to test the implementation of the tumor motion prediction. Results: The accuracy of the predicted motion and the actual motion was tested. Five volunteers with different breathing patterns were tested. The average prediction time was 0.281s. And the standard deviation of prediction accuracy was 0.002 for the respiratory motion and 0.001 for the tumor motion. Conclusion: The extreme learning machine method can provide an accurate and fast prediction of the respiratory motion and the tumor location and therefore can meet the requirements of real-time tumor-tracking in image guided radiotherapy

SU-E-J-191: Motion Prediction Using Extreme Learning Machine in Image Guided Radiotherapy

Energy Technology Data Exchange (ETDEWEB)

Jia, J; Cao, R; Pei, X; Wang, H; Hu, L [Key Laboratory of Neutronics and Radiation Safety, Institute of Nuclear Energy Safety Technology, Chinese Academy of Sciences, Hefei, Anhui, 230031 (China); Engineering Technology Research Center of Accurate Radiotherapy of Anhui Province, Hefei 230031 (China); Collaborative Innovation Center of Radiation Medicine of Jiangsu Higher Education Institutions, SuZhou (China)

2015-06-15

Purpose: Real-time motion tracking is a critical issue in image guided radiotherapy due to the time latency caused by image processing and system response. It is of great necessity to fast and accurately predict the future position of the respiratory motion and the tumor location. Methods: The prediction of respiratory position was done based on the positioning and tracking module in ARTS-IGRT system which was developed by FDS Team (www.fds.org.cn). An approach involving with the extreme learning machine (ELM) was adopted to predict the future respiratory position as well as the tumor’s location by training the past trajectories. For the training process, a feed-forward neural network with one single hidden layer was used for the learning. First, the number of hidden nodes was figured out for the single layered feed forward network (SLFN). Then the input weights and hidden layer biases of the SLFN were randomly assigned to calculate the hidden neuron output matrix. Finally, the predicted movement were obtained by applying the output weights and compared with the actual movement. Breathing movement acquired from the external infrared markers was used to test the prediction accuracy. And the implanted marker movement for the prostate cancer was used to test the implementation of the tumor motion prediction. Results: The accuracy of the predicted motion and the actual motion was tested. Five volunteers with different breathing patterns were tested. The average prediction time was 0.281s. And the standard deviation of prediction accuracy was 0.002 for the respiratory motion and 0.001 for the tumor motion. Conclusion: The extreme learning machine method can provide an accurate and fast prediction of the respiratory motion and the tumor location and therefore can meet the requirements of real-time tumor-tracking in image guided radiotherapy.

Automatically explaining machine learning prediction results: a demonstration on type 2 diabetes risk prediction.

Science.gov (United States)

Luo, Gang

2016-01-01

Predictive modeling is a key component of solutions to many healthcare problems. Among all predictive modeling approaches, machine learning methods often achieve the highest prediction accuracy, but suffer from a long-standing open problem precluding their widespread use in healthcare. Most machine learning models give no explanation for their prediction results, whereas interpretability is essential for a predictive model to be adopted in typical healthcare settings. This paper presents the first complete method for automatically explaining results for any machine learning predictive model without degrading accuracy. We did a computer coding implementation of the method. Using the electronic medical record data set from the Practice Fusion diabetes classification competition containing patient records from all 50 states in the United States, we demonstrated the method on predicting type 2 diabetes diagnosis within the next year. For the champion machine learning model of the competition, our method explained prediction results for 87.4 % of patients who were correctly predicted by the model to have type 2 diabetes diagnosis within the next year. Our demonstration showed the feasibility of automatically explaining results for any machine learning predictive model without degrading accuracy.

Recent Advances in Predictive (Machine) Learning

Energy Technology Data Exchange (ETDEWEB)

Friedman, J

2004-01-24

Prediction involves estimating the unknown value of an attribute of a system under study given the values of other measured attributes. In prediction (machine) learning the prediction rule is derived from data consisting of previously solved cases. Most methods for predictive learning were originated many years ago at the dawn of the computer age. Recently two new techniques have emerged that have revitalized the field. These are support vector machines and boosted decision trees. This paper provides an introduction to these two new methods tracing their respective ancestral roots to standard kernel methods and ordinary decision trees.

Deep learning methods for protein torsion angle prediction.

Science.gov (United States)

Li, Haiou; Hou, Jie; Adhikari, Badri; Lyu, Qiang; Cheng, Jianlin

2017-09-18

Deep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins. We design four different deep learning architectures to predict protein torsion angles. The architectures including deep neural network (DNN) and deep restricted Boltzmann machine (DRBN), deep recurrent neural network (DRNN) and deep recurrent restricted Boltzmann machine (DReRBM) since the protein torsion angle prediction is a sequence related problem. In addition to existing protein features, two new features (predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments) are used as input to each of the four deep learning architectures to predict phi and psi angles of protein backbone. The mean absolute error (MAE) of phi and psi angles predicted by DRNN, DReRBM, DRBM and DNN is about 20-21° and 29-30° on an independent dataset. The MAE of phi angle is comparable to the existing methods, but the MAE of psi angle is 29°, 2° lower than the existing methods. On the latest CASP12 targets, our methods also achieved the performance better than or comparable to a state-of-the art method. Our experiment demonstrates that deep learning is a valuable method for predicting protein torsion angles. The deep recurrent network architecture performs slightly better than deep feed-forward architecture, and the predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments are useful features for improving prediction accuracy.

Machine learning landscapes and predictions for patient outcomes

Science.gov (United States)

Das, Ritankar; Wales, David J.

2017-07-01

The theory and computational tools developed to interpret and explore energy landscapes in molecular science are applied to the landscapes defined by local minima for neural networks. These machine learning landscapes correspond to fits of training data, where the inputs are vital signs and laboratory measurements for a database of patients, and the objective is to predict a clinical outcome. In this contribution, we test the predictions obtained by fitting to single measurements, and then to combinations of between 2 and 10 different patient medical data items. The effect of including measurements over different time intervals from the 48 h period in question is analysed, and the most recent values are found to be the most important. We also compare results obtained for neural networks as a function of the number of hidden nodes, and for different values of a regularization parameter. The predictions are compared with an alternative convex fitting function, and a strong correlation is observed. The dependence of these results on the patients randomly selected for training and testing decreases systematically with the size of the database available. The machine learning landscapes defined by neural network fits in this investigation have single-funnel character, which probably explains why it is relatively straightforward to obtain the global minimum solution, or a fit that behaves similarly to this optimal parameterization.

Prediction of Student Dropout in E-Learning Program Through the Use of Machine Learning Method

Directory of Open Access Journals (Sweden)

Mingjie Tan

2015-02-01

Full Text Available The high rate of dropout is a serious problem in E-learning program. Thus it has received extensive concern from the education administrators and researchers. Predicting the potential dropout students is a workable solution to prevent dropout. Based on the analysis of related literature, this study selected student’s personal characteristic and academic performance as input attributions. Prediction models were developed using Artificial Neural Network (ANN, Decision Tree (DT and Bayesian Networks (BNs. A large sample of 62375 students was utilized in the procedures of model training and testing. The results of each model were presented in confusion matrix, and analyzed by calculating the rates of accuracy, precision, recall, and F-measure. The results suggested all of the three machine learning methods were effective in student dropout prediction, and DT presented a better performance. Finally, some suggestions were made for considerable future research.

Auditory working memory predicts individual differences in absolute pitch learning.

Science.gov (United States)

Van Hedger, Stephen C; Heald, Shannon L M; Koch, Rachelle; Nusbaum, Howard C

2015-07-01

Absolute pitch (AP) is typically defined as the ability to label an isolated tone as a musical note in the absence of a reference tone. At first glance the acquisition of AP note categories seems like a perceptual learning task, since individuals must assign a category label to a stimulus based on a single perceptual dimension (pitch) while ignoring other perceptual dimensions (e.g., loudness, octave, instrument). AP, however, is rarely discussed in terms of domain-general perceptual learning mechanisms. This is because AP is typically assumed to depend on a critical period of development, in which early exposure to pitches and musical labels is thought to be necessary for the development of AP precluding the possibility of adult acquisition of AP. Despite this view of AP, several previous studies have found evidence that absolute pitch category learning is, to an extent, trainable in a post-critical period adult population, even if the performance typically achieved by this population is below the performance of a "true" AP possessor. The current studies attempt to understand the individual differences in learning to categorize notes using absolute pitch cues by testing a specific prediction regarding cognitive capacity related to categorization - to what extent does an individual's general auditory working memory capacity (WMC) predict the success of absolute pitch category acquisition. Since WMC has been shown to predict performance on a wide variety of other perceptual and category learning tasks, we predict that individuals with higher WMC should be better at learning absolute pitch note categories than individuals with lower WMC. Across two studies, we demonstrate that auditory WMC predicts the efficacy of learning absolute pitch note categories. These results suggest that a higher general auditory WMC might underlie the formation of absolute pitch categories for post-critical period adults. Implications for understanding the mechanisms that underlie the

Predicting the concentration of residual methanol in industrial formalin using machine learning

OpenAIRE

Heidkamp, William

2016-01-01

In this thesis, a machine learning approach was used to develop a predictive model for residual methanol concentration in industrial formalin produced at the Akzo Nobel factory in Kristinehamn, Sweden. The MATLABTM computational environment supplemented with the Statistics and Machine LearningTM toolbox from the MathWorks were used to test various machine learning algorithms on the formalin production data from Akzo Nobel. As a result, the Gaussian Process Regression algorithm was found to pr...

Prostate Cancer Probability Prediction By Machine Learning Technique.

Science.gov (United States)

Jović, Srđan; Miljković, Milica; Ivanović, Miljan; Šaranović, Milena; Arsić, Milena

2017-11-26

The main goal of the study was to explore possibility of prostate cancer prediction by machine learning techniques. In order to improve the survival probability of the prostate cancer patients it is essential to make suitable prediction models of the prostate cancer. If one make relevant prediction of the prostate cancer it is easy to create suitable treatment based on the prediction results. Machine learning techniques are the most common techniques for the creation of the predictive models. Therefore in this study several machine techniques were applied and compared. The obtained results were analyzed and discussed. It was concluded that the machine learning techniques could be used for the relevant prediction of prostate cancer.

Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg-Marquardt learning algorithm

International Nuclear Information System (INIS)

Mirzaee, Hossein

2009-01-01

The Levenberg-Marquardt learning algorithm is applied for training a multilayer perception with three hidden layer each with ten neurons in order to carefully map the structure of chaotic time series such as Mackey-Glass time series. First the MLP network is trained with 1000 data, and then it is tested with next 500 data. After that the trained and tested network is applied for long-term prediction of next 120 data which come after test data. The prediction is such a way that, the first inputs to network for prediction are the four last data of test data, then the predicted value is shifted to the regression vector which is the input to the network, then after first four-step of prediction, the input regression vector to network is fully predicted values and in continue, each predicted data is shifted to input vector for subsequent prediction.

Machine learning approach for the outcome prediction of temporal lobe epilepsy surgery.

Directory of Open Access Journals (Sweden)

Rubén Armañanzas

Full Text Available Epilepsy surgery is effective in reducing both the number and frequency of seizures, particularly in temporal lobe epilepsy (TLE. Nevertheless, a significant proportion of these patients continue suffering seizures after surgery. Here we used a machine learning approach to predict the outcome of epilepsy surgery based on supervised classification data mining taking into account not only the common clinical variables, but also pathological and neuropsychological evaluations. We have generated models capable of predicting whether a patient with TLE secondary to hippocampal sclerosis will fully recover from epilepsy or not. The machine learning analysis revealed that outcome could be predicted with an estimated accuracy of almost 90% using some clinical and neuropsychological features. Importantly, not all the features were needed to perform the prediction; some of them proved to be irrelevant to the prognosis. Personality style was found to be one of the key features to predict the outcome. Although we examined relatively few cases, findings were verified across all data, showing that the machine learning approach described in the present study may be a powerful method. Since neuropsychological assessment of epileptic patients is a standard protocol in the pre-surgical evaluation, we propose to include these specific psychological tests and machine learning tools to improve the selection of candidates for epilepsy surgery.

Learning to predict chemical reactions.

Science.gov (United States)

Kayala, Matthew A; Azencott, Chloé-Agathe; Chen, Jonathan H; Baldi, Pierre

2011-09-26

Being able to predict the course of arbitrary chemical reactions is essential to the theory and applications of organic chemistry. Approaches to the reaction prediction problems can be organized around three poles corresponding to: (1) physical laws; (2) rule-based expert systems; and (3) inductive machine learning. Previous approaches at these poles, respectively, are not high throughput, are not generalizable or scalable, and lack sufficient data and structure to be implemented. We propose a new approach to reaction prediction utilizing elements from each pole. Using a physically inspired conceptualization, we describe single mechanistic reactions as interactions between coarse approximations of molecular orbitals (MOs) and use topological and physicochemical attributes as descriptors. Using an existing rule-based system (Reaction Explorer), we derive a restricted chemistry data set consisting of 1630 full multistep reactions with 2358 distinct starting materials and intermediates, associated with 2989 productive mechanistic steps and 6.14 million unproductive mechanistic steps. And from machine learning, we pose identifying productive mechanistic steps as a statistical ranking, information retrieval problem: given a set of reactants and a description of conditions, learn a ranking model over potential filled-to-unfilled MO interactions such that the top-ranked mechanistic steps yield the major products. The machine learning implementation follows a two-stage approach, in which we first train atom level reactivity filters to prune 94.00% of nonproductive reactions with a 0.01% error rate. Then, we train an ensemble of ranking models on pairs of interacting MOs to learn a relative productivity function over mechanistic steps in a given system. Without the use of explicit transformation patterns, the ensemble perfectly ranks the productive mechanism at the top 89.05% of the time, rising to 99.86% of the time when the top four are considered. Furthermore, the system

Learning to Predict Chemical Reactions

Science.gov (United States)

Kayala, Matthew A.; Azencott, Chloé-Agathe; Chen, Jonathan H.

2011-01-01

Being able to predict the course of arbitrary chemical reactions is essential to the theory and applications of organic chemistry. Approaches to the reaction prediction problems can be organized around three poles corresponding to: (1) physical laws; (2) rule-based expert systems; and (3) inductive machine learning. Previous approaches at these poles respectively are not high-throughput, are not generalizable or scalable, or lack sufficient data and structure to be implemented. We propose a new approach to reaction prediction utilizing elements from each pole. Using a physically inspired conceptualization, we describe single mechanistic reactions as interactions between coarse approximations of molecular orbitals (MOs) and use topological and physicochemical attributes as descriptors. Using an existing rule-based system (Reaction Explorer), we derive a restricted chemistry dataset consisting of 1630 full multi-step reactions with 2358 distinct starting materials and intermediates, associated with 2989 productive mechanistic steps and 6.14 million unproductive mechanistic steps. And from machine learning, we pose identifying productive mechanistic steps as a statistical ranking, information retrieval, problem: given a set of reactants and a description of conditions, learn a ranking model over potential filled-to-unfilled MO interactions such that the top ranked mechanistic steps yield the major products. The machine learning implementation follows a two-stage approach, in which we first train atom level reactivity filters to prune 94.00% of non-productive reactions with a 0.01% error rate. Then, we train an ensemble of ranking models on pairs of interacting MOs to learn a relative productivity function over mechanistic steps in a given system. Without the use of explicit transformation patterns, the ensemble perfectly ranks the productive mechanism at the top 89.05% of the time, rising to 99.86% of the time when the top four are considered. Furthermore, the system

Can personality predict individual differences in brook trout spatial learning ability?

Science.gov (United States)

White, S.L.; Wagner, Tyler; Gowan, C.; Braithwaite, V.A.

2017-01-01

While differences in individual personality are common in animal populations, understanding the ecological significance of variation has not yet been resolved. Evidence suggests that personality may influence learning and memory; a finding that could improve our understanding of the evolutionary processes that produce and maintain intraspecific behavioural heterogeneity. Here, we tested whether boldness, the most studied personality trait in fish, could predict learning ability in brook trout. After quantifying boldness, fish were trained to find a hidden food patch in a maze environment. Stable landmark cues were provided to indicate the location of food and, at the conclusion of training, cues were rearranged to test for learning. There was a negative relationship between boldness and learning as shy fish were increasingly more successful at navigating the maze and locating food during training trials compared to bold fish. In the altered testing environment, only shy fish continued using cues to search for food. Overall, the learning rate of bold fish was found to be lower than that of shy fish for several metrics suggesting that personality could have widespread effects on behaviour. Because learning can increase plasticity to environmental change, these results have significant implications for fish conservation.

Using Machine Learning to Predict Student Performance

OpenAIRE

Pojon, Murat

2017-01-01

This thesis examines the application of machine learning algorithms to predict whether a student will be successful or not. The specific focus of the thesis is the comparison of machine learning methods and feature engineering techniques in terms of how much they improve the prediction performance. Three different machine learning methods were used in this thesis. They are linear regression, decision trees, and naïve Bayes classification. Feature engineering, the process of modification ...

Learned predictiveness and outcome predictability effects are not simply two sides of the same coin.

Science.gov (United States)

Thorwart, Anna; Livesey, Evan J; Wilhelm, Francisco; Liu, Wei; Lachnit, Harald

2017-10-01

The Learned Predictiveness effect refers to the observation that learning about the relationship between a cue and an outcome is influenced by the predictive relevance of the cue for other outcomes. Similarly, the Outcome Predictability effect refers to a recent observation that the previous predictability of an outcome affects learning about this outcome in new situations, too. We hypothesize that both effects may be two manifestations of the same phenomenon and stimuli that have been involved in highly predictive relationships may be learned about faster when they are involved in new relationships regardless of their functional role in predictive learning as cues and outcomes. Four experiments manipulated both the relationships and the function of the stimuli. While we were able to replicate the standard effects, they did not survive a transfer to situations where the functional role of the stimuli changed, that is the outcome of the first phase becomes a cue in the second learning phase or the cue of the first phase becomes the outcome of the second phase. Furthermore, unlike learned predictiveness, there was little indication that the distribution of overt attention in the second phase was influenced by previous predictability. The results suggest that these 2 very similar effects are not manifestations of a more general phenomenon but rather independent from each other. (PsycINFO Database Record (c) 2017 APA, all rights reserved).

Fuzzy-logic based learning style prediction in e-learning using web ...

Indian Academy of Sciences (India)

tion, especially in web environments and proposes to use Fuzzy rules to handle the uncertainty in .... learning in safe and supportive environment ... working of the proposed Fuzzy-logic based learning style prediction in e-learning. Section 4.

Predicting Increased Blood Pressure Using Machine Learning

Science.gov (United States)

Golino, Hudson Fernandes; Amaral, Liliany Souza de Brito; Duarte, Stenio Fernando Pimentel; Soares, Telma de Jesus; dos Reis, Luciana Araujo

2014-01-01

The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo R 2 (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo R 2 (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power. PMID:24669313

Predicting Increased Blood Pressure Using Machine Learning

Directory of Open Access Journals (Sweden)

Hudson Fernandes Golino

2014-01-01

Full Text Available The present study investigates the prediction of increased blood pressure by body mass index (BMI, waist (WC and hip circumference (HC, and waist hip ratio (WHR using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42, misclassification (.19, and the higher pseudo R2 (.43. This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25, misclassification (.16, and the higher pseudo R2 (.46. This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

Predicting increased blood pressure using machine learning.

Science.gov (United States)

Golino, Hudson Fernandes; Amaral, Liliany Souza de Brito; Duarte, Stenio Fernando Pimentel; Gomes, Cristiano Mauro Assis; Soares, Telma de Jesus; Dos Reis, Luciana Araujo; Santos, Joselito

2014-01-01

The present study investigates the prediction of increased blood pressure by body mass index (BMI), waist (WC) and hip circumference (HC), and waist hip ratio (WHR) using a machine learning technique named classification tree. Data were collected from 400 college students (56.3% women) from 16 to 63 years old. Fifteen trees were calculated in the training group for each sex, using different numbers and combinations of predictors. The result shows that for women BMI, WC, and WHR are the combination that produces the best prediction, since it has the lowest deviance (87.42), misclassification (.19), and the higher pseudo R (2) (.43). This model presented a sensitivity of 80.86% and specificity of 81.22% in the training set and, respectively, 45.65% and 65.15% in the test sample. For men BMI, WC, HC, and WHC showed the best prediction with the lowest deviance (57.25), misclassification (.16), and the higher pseudo R (2) (.46). This model had a sensitivity of 72% and specificity of 86.25% in the training set and, respectively, 58.38% and 69.70% in the test set. Finally, the result from the classification tree analysis was compared with traditional logistic regression, indicating that the former outperformed the latter in terms of predictive power.

The Prediction of Students' Academic Performance With Fluid Intelligence in Giving Special Consideration to the Contribution of Learning.

Science.gov (United States)

Ren, Xuezhu; Schweizer, Karl; Wang, Tengfei; Xu, Fen

2015-01-01

The present study provides a new account of how fluid intelligence influences academic performance. In this account a complex learning component of fluid intelligence tests is proposed to play a major role in predicting academic performance. A sample of 2, 277 secondary school students completed two reasoning tests that were assumed to represent fluid intelligence and standardized math and verbal tests assessing academic performance. The fluid intelligence data were decomposed into a learning component that was associated with the position effect of intelligence items and a constant component that was independent of the position effect. Results showed that the learning component contributed significantly more to the prediction of math and verbal performance than the constant component. The link from the learning component to math performance was especially strong. These results indicated that fluid intelligence, which has so far been considered as homogeneous, could be decomposed in such a way that the resulting components showed different properties and contributed differently to the prediction of academic performance. Furthermore, the results were in line with the expectation that learning was a predictor of performance in school.

Monitoring and regulation of learning in medical education: the need for predictive cues.

Science.gov (United States)

de Bruin, Anique B H; Dunlosky, John; Cavalcanti, Rodrigo B

2017-06-01

Being able to accurately monitor learning activities is a key element in self-regulated learning in all settings, including medical schools. Yet students' ability to monitor their progress is often limited, leading to inefficient use of study time. Interventions that improve the accuracy of students' monitoring can optimise self-regulated learning, leading to higher achievement. This paper reviews findings from cognitive psychology and explores potential applications in medical education, as well as areas for future research. Effective monitoring depends on students' ability to generate information ('cues') that accurately reflects their knowledge and skills. The ability of these 'cues' to predict achievement is referred to as 'cue diagnosticity'. Interventions that improve the ability of students to elicit predictive cues typically fall into two categories: (i) self-generation of cues and (ii) generation of cues that is delayed after self-study. Providing feedback and support is useful when cues are predictive but may be too complex to be readily used. Limited evidence exists about interventions to improve the accuracy of self-monitoring among medical students or trainees. Developing interventions that foster use of predictive cues can enhance the accuracy of self-monitoring, thereby improving self-study and clinical reasoning. First, insight should be gained into the characteristics of predictive cues used by medical students and trainees. Next, predictive cue prompts should be designed and tested to improve monitoring and regulation of learning. Finally, the use of predictive cues should be explored in relation to teaching and learning clinical reasoning. Improving self-regulated learning is important to help medical students and trainees efficiently acquire knowledge and skills necessary for clinical practice. Interventions that help students generate and use predictive cues hold the promise of improved self-regulated learning and achievement. This framework is

Stress before extinction learning enhances and generalizes extinction memory in a predictive learning task.

Science.gov (United States)

Meir Drexler, Shira; Hamacher-Dang, Tanja C; Wolf, Oliver T

2017-05-01

In extinction learning, the individual learns that a previously acquired association (e.g. between a threat and its predictor) is no longer valid. This learning is the principle underlying many cognitive-behavioral psychotherapeutic treatments, e.g. 'exposure therapy'. However, extinction is often highly-context dependent, leading to renewal (relapse of extinguished conditioned response following context change). We have previously shown that post-extinction stress leads to a more context-dependent extinction memory in a predictive learning task. Yet as stress prior to learning can impair the integration of contextual cues, here we aim to create a more generalized extinction memory by inducing stress prior to extinction. Forty-nine men and women learned the associations between stimuli and outcomes in a predictive learning task (day 1), extinguished them shortly after an exposure to a stress/control condition (day 2), and were tested for renewal (day 3). No group differences were seen in acquisition and extinction learning, and a renewal effect was present in both groups. However, the groups differed in the strength and context-dependency of the extinction memory. Compared to the control group, the stress group showed an overall reduced recovery of responding to the extinguished stimuli, in particular in the acquisition context. These results, together with our previous findings, demonstrate that the effects of stress exposure on extinction memory depend on its timing. While post-extinction stress makes the memory more context-bound, pre-extinction stress strengthens its consolidation for the acquisition context as well, making it potentially more resistant to relapse. These results have implications for the use of glucocorticoids as extinction-enhancers in exposure therapy. Copyright © 2017 Elsevier Inc. All rights reserved.

Boosting compound-protein interaction prediction by deep learning.

Science.gov (United States)

Tian, Kai; Shao, Mingyu; Wang, Yang; Guan, Jihong; Zhou, Shuigeng

2016-11-01

The identification of interactions between compounds and proteins plays an important role in network pharmacology and drug discovery. However, experimentally identifying compound-protein interactions (CPIs) is generally expensive and time-consuming, computational approaches are thus introduced. Among these, machine-learning based methods have achieved a considerable success. However, due to the nonlinear and imbalanced nature of biological data, many machine learning approaches have their own limitations. Recently, deep learning techniques show advantages over many state-of-the-art machine learning methods in some applications. In this study, we aim at improving the performance of CPI prediction based on deep learning, and propose a method called DL-CPI (the abbreviation of Deep Learning for Compound-Protein Interactions prediction), which employs deep neural network (DNN) to effectively learn the representations of compound-protein pairs. Extensive experiments show that DL-CPI can learn useful features of compound-protein pairs by a layerwise abstraction, and thus achieves better prediction performance than existing methods on both balanced and imbalanced datasets. Copyright © 2016 Elsevier Inc. All rights reserved.

Prediction of outcome in internet-delivered cognitive behaviour therapy for paediatric obsessive-compulsive disorder: A machine learning approach.

Science.gov (United States)

Lenhard, Fabian; Sauer, Sebastian; Andersson, Erik; Månsson, Kristoffer Nt; Mataix-Cols, David; Rück, Christian; Serlachius, Eva

2018-03-01

There are no consistent predictors of treatment outcome in paediatric obsessive-compulsive disorder (OCD). One reason for this might be the use of suboptimal statistical methodology. Machine learning is an approach to efficiently analyse complex data. Machine learning has been widely used within other fields, but has rarely been tested in the prediction of paediatric mental health treatment outcomes. To test four different machine learning methods in the prediction of treatment response in a sample of paediatric OCD patients who had received Internet-delivered cognitive behaviour therapy (ICBT). Participants were 61 adolescents (12-17 years) who enrolled in a randomized controlled trial and received ICBT. All clinical baseline variables were used to predict strictly defined treatment response status three months after ICBT. Four machine learning algorithms were implemented. For comparison, we also employed a traditional logistic regression approach. Multivariate logistic regression could not detect any significant predictors. In contrast, all four machine learning algorithms performed well in the prediction of treatment response, with 75 to 83% accuracy. The results suggest that machine learning algorithms can successfully be applied to predict paediatric OCD treatment outcome. Validation studies and studies in other disorders are warranted. Copyright © 2017 John Wiley & Sons, Ltd.

Action-outcome learning and prediction shape the window of simultaneity of audiovisual outcomes.

Science.gov (United States)

Desantis, Andrea; Haggard, Patrick

2016-08-01

To form a coherent representation of the objects around us, the brain must group the different sensory features composing these objects. Here, we investigated whether actions contribute in this grouping process. In particular, we assessed whether action-outcome learning and prediction contribute to audiovisual temporal binding. Participants were presented with two audiovisual pairs: one pair was triggered by a left action, and the other by a right action. In a later test phase, the audio and visual components of these pairs were presented at different onset times. Participants judged whether they were simultaneous or not. To assess the role of action-outcome prediction on audiovisual simultaneity, each action triggered either the same audiovisual pair as in the learning phase ('predicted' pair), or the pair that had previously been associated with the other action ('unpredicted' pair). We found the time window within which auditory and visual events appeared simultaneous increased for predicted compared to unpredicted pairs. However, no change in audiovisual simultaneity was observed when audiovisual pairs followed visual cues, rather than voluntary actions. This suggests that only action-outcome learning promotes temporal grouping of audio and visual effects. In a second experiment we observed that changes in audiovisual simultaneity do not only depend on our ability to predict what outcomes our actions generate, but also on learning the delay between the action and the multisensory outcome. When participants learned that the delay between action and audiovisual pair was variable, the window of audiovisual simultaneity for predicted pairs increased, relative to a fixed action-outcome pair delay. This suggests that participants learn action-based predictions of audiovisual outcome, and adapt their temporal perception of outcome events based on such predictions. Copyright © 2016 The Authors. Published by Elsevier B.V. All rights reserved.

Strength of Temporal White Matter Pathways Predicts Semantic Learning.

Science.gov (United States)

Ripollés, Pablo; Biel, Davina; Peñaloza, Claudia; Kaufmann, Jörn; Marco-Pallarés, Josep; Noesselt, Toemme; Rodríguez-Fornells, Antoni

2017-11-15

Learning the associations between words and meanings is a fundamental human ability. Although the language network is cortically well defined, the role of the white matter pathways supporting novel word-to-meaning mappings remains unclear. Here, by using contextual and cross-situational word learning, we tested whether learning the meaning of a new word is related to the integrity of the language-related white matter pathways in 40 adults (18 women). The arcuate, uncinate, inferior-fronto-occipital and inferior-longitudinal fasciculi were virtually dissected using manual and automatic deterministic fiber tracking. Critically, the automatic method allowed assessing the white matter microstructure along the tract. Results demonstrate that the microstructural properties of the left inferior-longitudinal fasciculus predict contextual learning, whereas the left uncinate was associated with cross-situational learning. In addition, we identified regions of special importance within these pathways: the posterior middle temporal gyrus, thought to serve as a lexical interface and specifically related to contextual learning; the anterior temporal lobe, known to be an amodal hub for semantic processing and related to cross-situational learning; and the white matter near the hippocampus, a structure fundamental for the initial stages of new-word learning and, remarkably, related to both types of word learning. No significant associations were found for the inferior-fronto-occipital fasciculus or the arcuate. While previous results suggest that learning new phonological word forms is mediated by the arcuate fasciculus, these findings show that the temporal pathways are the crucial neural substrate supporting one of the most striking human abilities: our capacity to identify correct associations between words and meanings under referential indeterminacy. SIGNIFICANCE STATEMENT The language-processing network is cortically (i.e., gray matter) well defined. However, the role of the

Can personality predict individual differences in brook trout spatial learning ability?

Science.gov (United States)

White, S L; Wagner, T; Gowan, C; Braithwaite, V A

2017-08-01

While differences in individual personality are common in animal populations, understanding the ecological significance of variation has not yet been resolved. Evidence suggests that personality may influence learning and memory; a finding that could improve our understanding of the evolutionary processes that produce and maintain intraspecific behavioural heterogeneity. Here, we tested whether boldness, the most studied personality trait in fish, could predict learning ability in brook trout. After quantifying boldness, fish were trained to find a hidden food patch in a maze environment. Stable landmark cues were provided to indicate the location of food and, at the conclusion of training, cues were rearranged to test for learning. There was a negative relationship between boldness and learning as shy fish were increasingly more successful at navigating the maze and locating food during training trials compared to bold fish. In the altered testing environment, only shy fish continued using cues to search for food. Overall, the learning rate of bold fish was found to be lower than that of shy fish for several metrics suggesting that personality could have widespread effects on behaviour. Because learning can increase plasticity to environmental change, these results have significant implications for fish conservation. Copyright © 2016 Elsevier B.V. All rights reserved.

Reinforcement Learning Based Novel Adaptive Learning Framework for Smart Grid Prediction

Directory of Open Access Journals (Sweden)

Tian Li

2017-01-01

Full Text Available Smart grid is a potential infrastructure to supply electricity demand for end users in a safe and reliable manner. With the rapid increase of the share of renewable energy and controllable loads in smart grid, the operation uncertainty of smart grid has increased briskly during recent years. The forecast is responsible for the safety and economic operation of the smart grid. However, most existing forecast methods cannot account for the smart grid due to the disabilities to adapt to the varying operational conditions. In this paper, reinforcement learning is firstly exploited to develop an online learning framework for the smart grid. With the capability of multitime scale resolution, wavelet neural network has been adopted in the online learning framework to yield reinforcement learning and wavelet neural network (RLWNN based adaptive learning scheme. The simulations on two typical prediction problems in smart grid, including wind power prediction and load forecast, validate the effectiveness and the scalability of the proposed RLWNN based learning framework and algorithm.

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

Science.gov (United States)

Cornejo-Bueno, L.; Casanova-Mateo, C.; Sanz-Justo, J.; Cerro-Prada, E.; Salcedo-Sanz, S.

2017-11-01

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is {>}1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ({algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.

Reminder cues modulate the renewal effect in human predictive learning

Directory of Open Access Journals (Sweden)

Javier Bustamante

2016-12-01

Full Text Available Associative learning refers to our ability to learn about regularities in our environment. When a stimulus is repeatedly followed by a specific outcome, we learn to expect the outcome in the presence of the stimulus. We are also able to modify established expectations in the face of disconfirming information (the stimulus is no longer followed by the outcome. Both the change of environmental regularities and the related processes of adaptation are referred to as extinction. However, extinction does not erase the initially acquired expectations. For instance, following successful extinction, the initially learned expectations can recover when there is a context change – a phenomenon called the renewal effect, which is considered as a model for relapse after exposure therapy. Renewal was found to be modulated by reminder cues of acquisition and extinction. However, the mechanisms underlying the effectiveness of reminder cues are not well understood. The aim of the present study was to investigate the impact of reminder cues on renewal in the field of human predictive learning. Experiment I demonstrated that renewal in human predictive learning is modulated by cues related to acquisition or extinction. Initially, participants received pairings of a stimulus and an outcome in one context. These stimulus-outcome pairings were preceded by presentations of a reminder cue (acquisition cue. Then, participants received extinction in a different context in which presentations of the stimulus were no longer followed by the outcome. These extinction trials were preceded by a second reminder cue (extinction cue. During a final phase conducted in a third context, participants showed stronger expectations of the outcome in the presence of the stimulus when testing was accompanied by the acquisition cue compared to the extinction cue. Experiment II tested an explanation of the reminder cue effect in terms of simple cue-outcome associations. Therefore

Pipeline defect prediction using long range ultrasonic testing and intelligent processing

International Nuclear Information System (INIS)

Dino Isa; Rajprasad Rajkumar

2009-01-01

This paper deals with efforts to improve nondestructive testing (NDT) techniques by using artificial intelligence in detecting and predicting pipeline defects such as cracks and wall thinning. The main emphasis here will be on the prediction of corrosion type defects rather than just detection after the fact. Long range ultrasonic testing will be employed, where a ring of piezoelectric transducers are used to generate torsional guided waves. Various defects such as cracks as well as corrosion under insulation (CUI) will be simulated on a test pipe. The machine learning algorithm known as the Support Vector Machine (SVM) will be used to predict and classify transducer signals using regression and large margin classification. Regression results show that the SVM is able to accurately predict future defects based on trends of previous defect. The classification performance was also exceptional showing a facility to detect defects at different depths as well as for distinguishing closely spaced defects. (author)

Predicting Solar Activity Using Machine-Learning Methods

Science.gov (United States)

Bobra, M.

2017-12-01

Of all the activity observed on the Sun, two of the most energetic events are flares and coronal mass ejections. However, we do not, as of yet, fully understand the physical mechanism that triggers solar eruptions. A machine-learning algorithm, which is favorable in cases where the amount of data is large, is one way to [1] empirically determine the signatures of this mechanism in solar image data and [2] use them to predict solar activity. In this talk, we discuss the application of various machine learning algorithms - specifically, a Support Vector Machine, a sparse linear regression (Lasso), and Convolutional Neural Network - to image data from the photosphere, chromosphere, transition region, and corona taken by instruments aboard the Solar Dynamics Observatory in order to predict solar activity on a variety of time scales. Such an approach may be useful since, at the present time, there are no physical models of flares available for real-time prediction. We discuss our results (Bobra and Couvidat, 2015; Bobra and Ilonidis, 2016; Jonas et al., 2017) as well as other attempts to predict flares using machine-learning (e.g. Ahmed et al., 2013; Nishizuka et al. 2017) and compare these results with the more traditional techniques used by the NOAA Space Weather Prediction Center (Crown, 2012). We also discuss some of the challenges in using machine-learning algorithms for space science applications.

Testing a cue outside the training context increases attention to the contexts and impairs performance in human predictive learning.

Science.gov (United States)

Aristizabal, José A; Ramos-Álvarez, Manuel M; Callejas-Aguilera, José E; Rosas, Juan M

2017-12-01

One experiment in human predictive learning explored the impact of a context change on attention to contexts and predictive ratings controlled by the cue. In Context A: cue X was paired with an outcome four times, while cue Y was presented without an outcome four times in Context B:. In both contexts filler cues were presented without the outcome. During the test, target cues X and Y were presented either in the context where they were trained, or in the alternative context. With the context change expectation of the outcome X, expressed as predictive ratings, decreased in the presence of X and increased in the presence of Y. Looking at the contexts, expressed as a percentage of the overall gaze dwell time on a trial, was high across the four training trials, and increased with the context change. Results suggest that the presentation of unexpected information leads to increases in attention to contextual cues. Implications for contextual control of behavior are discussed. Copyright © 2017 Elsevier B.V. All rights reserved.

Long-term associative learning predicts verbal short-term memory performance.

Science.gov (United States)

Jones, Gary; Macken, Bill

2018-02-01

Studies using tests such as digit span and nonword repetition have implicated short-term memory across a range of developmental domains. Such tests ostensibly assess specialized processes for the short-term manipulation and maintenance of information that are often argued to enable long-term learning. However, there is considerable evidence for an influence of long-term linguistic learning on performance in short-term memory tasks that brings into question the role of a specialized short-term memory system separate from long-term knowledge. Using natural language corpora, we show experimentally and computationally that performance on three widely used measures of short-term memory (digit span, nonword repetition, and sentence recall) can be predicted from simple associative learning operating on the linguistic environment to which a typical child may have been exposed. The findings support the broad view that short-term verbal memory performance reflects the application of long-term language knowledge to the experimental setting.

Machine learning methods in predicting the student academic motivation

Directory of Open Access Journals (Sweden)

Ivana Đurđević Babić

2017-01-01

Full Text Available Academic motivation is closely related to academic performance. For educators, it is equally important to detect early students with a lack of academic motivation as it is to detect those with a high level of academic motivation. In endeavouring to develop a classification model for predicting student academic motivation based on their behaviour in learning management system (LMS courses, this paper intends to establish links between the predicted student academic motivation and their behaviour in the LMS course. Students from all years at the Faculty of Education in Osijek participated in this research. Three machine learning classifiers (neural networks, decision trees, and support vector machines were used. To establish whether a significant difference in the performance of models exists, a t-test of the difference in proportions was used. Although, all classifiers were successful, the neural network model was shown to be the most successful in detecting the student academic motivation based on their behaviour in LMS course.

Supervised machine learning techniques to predict binding affinity. A study for cyclin-dependent kinase 2.

Science.gov (United States)

de Ávila, Maurício Boff; Xavier, Mariana Morrone; Pintro, Val Oliveira; de Azevedo, Walter Filgueira

2017-12-09

Here we report the development of a machine-learning model to predict binding affinity based on the crystallographic structures of protein-ligand complexes. We used an ensemble of crystallographic structures (resolution better than 1.5 Å resolution) for which half-maximal inhibitory concentration (IC 50 ) data is available. Polynomial scoring functions were built using as explanatory variables the energy terms present in the MolDock and PLANTS scoring functions. Prediction performance was tested and the supervised machine learning models showed improvement in the prediction power, when compared with PLANTS and MolDock scoring functions. In addition, the machine-learning model was applied to predict binding affinity of CDK2, which showed a better performance when compared with AutoDock4, AutoDock Vina, MolDock, and PLANTS scores. Copyright © 2017 Elsevier Inc. All rights reserved.

A Test of Two Alternative Cognitive Processing Models: Learning Styles and Dual Coding

Science.gov (United States)

Cuevas, Joshua; Dawson, Bryan L.

2018-01-01

This study tested two cognitive models, learning styles and dual coding, which make contradictory predictions about how learners process and retain visual and auditory information. Learning styles-based instructional practices are common in educational environments despite a questionable research base, while the use of dual coding is less…

Historical maintenance relevant information road-map for a self-learning maintenance prediction procedural approach

Science.gov (United States)

Morales, Francisco J.; Reyes, Antonio; Cáceres, Noelia; Romero, Luis M.; Benitez, Francisco G.; Morgado, Joao; Duarte, Emanuel; Martins, Teresa

2017-09-01

A large percentage of transport infrastructures are composed of linear assets, such as roads and rail tracks. The large social and economic relevance of these constructions force the stakeholders to ensure a prolonged health/durability. Even though, inevitable malfunctioning, breaking down, and out-of-service periods arise randomly during the life cycle of the infrastructure. Predictive maintenance techniques tend to diminish the appearance of unpredicted failures and the execution of needed corrective interventions, envisaging the adequate interventions to be conducted before failures show up. This communication presents: i) A procedural approach, to be conducted, in order to collect the relevant information regarding the evolving state condition of the assets involved in all maintenance interventions; this reported and stored information constitutes a rich historical data base to train Machine Learning algorithms in order to generate reliable predictions of the interventions to be carried out in further time scenarios. ii) A schematic flow chart of the automatic learning procedure. iii) Self-learning rules from automatic learning from false positive/negatives. The description, testing, automatic learning approach and the outcomes of a pilot case are presented; finally some conclusions are outlined regarding the methodology proposed for improving the self-learning predictive capability.

Hippocampal dose volume histogram predicts Hopkins Verbal Learning Test scores after brain irradiation

Directory of Open Access Journals (Sweden)

Catherine Okoukoni, PhD

2017-10-01

Full Text Available Purpose: Radiation-induced cognitive decline is relatively common after treatment for primary and metastatic brain tumors; however, identifying dosimetric parameters that are predictive of radiation-induced cognitive decline is difficult due to the heterogeneity of patient characteristics. The memory function is especially susceptible to radiation effects after treatment. The objective of this study is to correlate volumetric radiation doses received by critical neuroanatomic structures to post–radiation therapy (RT memory impairment. Methods and materials: Between 2008 and 2011, 53 patients with primary brain malignancies were treated with conventionally fractionated RT in prospectively accrued clinical trials performed at our institution. Dose-volume histogram analysis was performed for the hippocampus, parahippocampus, amygdala, and fusiform gyrus. Hopkins Verbal Learning Test-Revised scores were obtained at least 6 months after RT. Impairment was defined as an immediate recall score ≤15. For each anatomic region, serial regression was performed to correlate volume receiving a given dose (VD(Gy with memory impairment. Results: Hippocampal V53.4Gy to V60.9Gy significantly predicted post-RT memory impairment (P < .05. Within this range, the hippocampal V55Gy was the most significant predictor (P = .004. Hippocampal V55Gy of 0%, 25%, and 50% was associated with tumor-induced impairment rates of 14.9% (95% confidence interval [CI], 7.2%-28.7%, 45.9% (95% CI, 24.7%-68.6%, and 80.6% (95% CI, 39.2%-96.4%, respectively. Conclusions: The hippocampal V55Gy is a significant predictor for impairment, and a limiting dose below 55 Gy may minimize radiation-induced cognitive impairment.

Informal Workplace Learning among Nurses: Organisational Learning Conditions and Personal Characteristics That Predict Learning Outcomes

Science.gov (United States)

Kyndt, Eva; Vermeire, Eva; Cabus, Shana

2016-01-01

Purpose: This paper aims to examine which organisational learning conditions and individual characteristics predict the learning outcomes nurses achieve through informal learning activities. There is specific relevance for the nursing profession because of the rapidly changing healthcare systems. Design/Methodology/Approach: In total, 203 nurses…

How we learn to make decisions: rapid propagation of reinforcement learning prediction errors in humans.

Science.gov (United States)

Krigolson, Olav E; Hassall, Cameron D; Handy, Todd C

2014-03-01

Our ability to make decisions is predicated upon our knowledge of the outcomes of the actions available to us. Reinforcement learning theory posits that actions followed by a reward or punishment acquire value through the computation of prediction errors-discrepancies between the predicted and the actual reward. A multitude of neuroimaging studies have demonstrated that rewards and punishments evoke neural responses that appear to reflect reinforcement learning prediction errors [e.g., Krigolson, O. E., Pierce, L. J., Holroyd, C. B., & Tanaka, J. W. Learning to become an expert: Reinforcement learning and the acquisition of perceptual expertise. Journal of Cognitive Neuroscience, 21, 1833-1840, 2009; Bayer, H. M., & Glimcher, P. W. Midbrain dopamine neurons encode a quantitative reward prediction error signal. Neuron, 47, 129-141, 2005; O'Doherty, J. P. Reward representations and reward-related learning in the human brain: Insights from neuroimaging. Current Opinion in Neurobiology, 14, 769-776, 2004; Holroyd, C. B., & Coles, M. G. H. The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity. Psychological Review, 109, 679-709, 2002]. Here, we used the brain ERP technique to demonstrate that not only do rewards elicit a neural response akin to a prediction error but also that this signal rapidly diminished and propagated to the time of choice presentation with learning. Specifically, in a simple, learnable gambling task, we show that novel rewards elicited a feedback error-related negativity that rapidly decreased in amplitude with learning. Furthermore, we demonstrate the existence of a reward positivity at choice presentation, a previously unreported ERP component that has a similar timing and topography as the feedback error-related negativity that increased in amplitude with learning. The pattern of results we observed mirrored the output of a computational model that we implemented to compute reward

Deep learning versus traditional machine learning methods for aggregated energy demand prediction

NARCIS (Netherlands)

Paterakis, N.G.; Mocanu, E.; Gibescu, M.; Stappers, B.; van Alst, W.

2018-01-01

In this paper the more advanced, in comparison with traditional machine learning approaches, deep learning methods are explored with the purpose of accurately predicting the aggregated energy consumption. Despite the fact that a wide range of machine learning methods have been applied to

Implementation of Chaotic Gaussian Particle Swarm Optimization for Optimize Learning-to-Rank Software Defect Prediction Model Construction

Science.gov (United States)

Buchari, M. A.; Mardiyanto, S.; Hendradjaya, B.

2018-03-01

Finding the existence of software defect as early as possible is the purpose of research about software defect prediction. Software defect prediction activity is required to not only state the existence of defects, but also to be able to give a list of priorities which modules require a more intensive test. Therefore, the allocation of test resources can be managed efficiently. Learning to rank is one of the approach that can provide defect module ranking data for the purposes of software testing. In this study, we propose a meta-heuristic chaotic Gaussian particle swarm optimization to improve the accuracy of learning to rank software defect prediction approach. We have used 11 public benchmark data sets as experimental data. Our overall results has demonstrated that the prediction models construct using Chaotic Gaussian Particle Swarm Optimization gets better accuracy on 5 data sets, ties in 5 data sets and gets worse in 1 data sets. Thus, we conclude that the application of Chaotic Gaussian Particle Swarm Optimization in Learning-to-Rank approach can improve the accuracy of the defect module ranking in data sets that have high-dimensional features.

Test-Enhanced Learning in an Immunology and Infectious Disease Medicinal Chemistry/Pharmacology Course.

Science.gov (United States)

Hernick, Marcy

2015-09-25

Objective. To develop a series of active-learning modules that would improve pharmacy students' performance on summative assessments. Design. A series of optional online active-learning modules containing questions with multiple formats for topics in a first-year (P1) course was created using a test-enhanced learning approach. A subset of module questions was modified and included on summative assessments. Assessment. Student performance on module questions improved with repeated attempts and was predictive of student performance on summative assessments. Performance on examination questions was higher for students with access to modules than for those without access to modules. Module use appeared to have the most impact on low performing students. Conclusion. Test-enhanced learning modules with immediate feedback provide pharmacy students with a learning tool that improves student performance on summative assessments and also may improve metacognitive and test-taking skills.

Pressure Prediction of Coal Slurry Transportation Pipeline Based on Particle Swarm Optimization Kernel Function Extreme Learning Machine

Directory of Open Access Journals (Sweden)

Xue-cun Yang

2015-01-01

Full Text Available For coal slurry pipeline blockage prediction problem, through the analysis of actual scene, it is determined that the pressure prediction from each measuring point is the premise of pipeline blockage prediction. Kernel function of support vector machine is introduced into extreme learning machine, the parameters are optimized by particle swarm algorithm, and blockage prediction method based on particle swarm optimization kernel function extreme learning machine (PSOKELM is put forward. The actual test data from HuangLing coal gangue power plant are used for simulation experiments and compared with support vector machine prediction model optimized by particle swarm algorithm (PSOSVM and kernel function extreme learning machine prediction model (KELM. The results prove that mean square error (MSE for the prediction model based on PSOKELM is 0.0038 and the correlation coefficient is 0.9955, which is superior to prediction model based on PSOSVM in speed and accuracy and superior to KELM prediction model in accuracy.

Pediatric residents' learning styles and temperaments and their relationships to standardized test scores.

Science.gov (United States)

Tuli, Sanjeev Y; Thompson, Lindsay A; Saliba, Heidi; Black, Erik W; Ryan, Kathleen A; Kelly, Maria N; Novak, Maureen; Mellott, Jane; Tuli, Sonal S

2011-12-01

Board certification is an important professional qualification and a prerequisite for credentialing, and the Accreditation Council for Graduate Medical Education (ACGME) assesses board certification rates as a component of residency program effectiveness. To date, research has shown that preresidency measures, including National Board of Medical Examiners scores, Alpha Omega Alpha Honor Medical Society membership, or medical school grades poorly predict postresidency board examination scores. However, learning styles and temperament have been identified as factors that 5 affect test-taking performance. The purpose of this study is to characterize the learning styles and temperaments of pediatric residents and to evaluate their relationships to yearly in-service and postresidency board examination scores. This cross-sectional study analyzed the learning styles and temperaments of current and past pediatric residents by administration of 3 validated tools: the Kolb Learning Style Inventory, the Keirsey Temperament Sorter, and the Felder-Silverman Learning Style test. These results were compared with known, normative, general and medical population data and evaluated for correlation to in-service examination and postresidency board examination scores. The predominant learning style for pediatric residents was converging 44% (33 of 75 residents) and the predominant temperament was guardian 61% (34 of 56 residents). The learning style and temperament distribution of the residents was significantly different from published population data (P  =  .002 and .04, respectively). Learning styles, with one exception, were found to be unrelated to standardized test scores. The predominant learning style and temperament of pediatric residents is significantly different than that of the populations of general and medical trainees. However, learning styles and temperament do not predict outcomes on standardized in-service and board examinations in pediatric residents.

Predicting radiotherapy outcomes using statistical learning techniques

International Nuclear Information System (INIS)

El Naqa, Issam; Bradley, Jeffrey D; Deasy, Joseph O; Lindsay, Patricia E; Hope, Andrew J

2009-01-01

Radiotherapy outcomes are determined by complex interactions between treatment, anatomical and patient-related variables. A common obstacle to building maximally predictive outcome models for clinical practice is the failure to capture potential complexity of heterogeneous variable interactions and applicability beyond institutional data. We describe a statistical learning methodology that can automatically screen for nonlinear relations among prognostic variables and generalize to unseen data before. In this work, several types of linear and nonlinear kernels to generate interaction terms and approximate the treatment-response function are evaluated. Examples of institutional datasets of esophagitis, pneumonitis and xerostomia endpoints were used. Furthermore, an independent RTOG dataset was used for 'generalizabilty' validation. We formulated the discrimination between risk groups as a supervised learning problem. The distribution of patient groups was initially analyzed using principle components analysis (PCA) to uncover potential nonlinear behavior. The performance of the different methods was evaluated using bivariate correlations and actuarial analysis. Over-fitting was controlled via cross-validation resampling. Our results suggest that a modified support vector machine (SVM) kernel method provided superior performance on leave-one-out testing compared to logistic regression and neural networks in cases where the data exhibited nonlinear behavior on PCA. For instance, in prediction of esophagitis and pneumonitis endpoints, which exhibited nonlinear behavior on PCA, the method provided 21% and 60% improvements, respectively. Furthermore, evaluation on the independent pneumonitis RTOG dataset demonstrated good generalizabilty beyond institutional data in contrast with other models. This indicates that the prediction of treatment response can be improved by utilizing nonlinear kernel methods for discovering important nonlinear interactions among model

Predicting Learned Helplessness Based on Personality

Science.gov (United States)

Maadikhah, Elham; Erfani, Nasrollah

2014-01-01

Learned helplessness as a negative motivational state can latently underlie repeated failures and create negative feelings toward the education as well as depression in students and other members of a society. The purpose of this paper is to predict learned helplessness based on students' personality traits. The research is a predictive…

Video Scene Parsing with Predictive Feature Learning

OpenAIRE

Jin, Xiaojie; Li, Xin; Xiao, Huaxin; Shen, Xiaohui; Lin, Zhe; Yang, Jimei; Chen, Yunpeng; Dong, Jian; Liu, Luoqi; Jie, Zequn; Feng, Jiashi; Yan, Shuicheng

2016-01-01

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing framework. (1) \\textbf{Predictive feature learning}} from nearly unlimited unlabeled video data. Different from existing methods learning features from single frame parsing, we learn spatiotemporal discriminative features by enforcing a parsing network to ...

Learning and Retention through Predictive Inference and Classification

Science.gov (United States)

Sakamoto, Yasuaki; Love, Bradley C.

2010-01-01

Work in category learning addresses how humans acquire knowledge and, thus, should inform classroom practices. In two experiments, we apply and evaluate intuitions garnered from laboratory-based research in category learning to learning tasks situated in an educational context. In Experiment 1, learning through predictive inference and…

Scaling prediction errors to reward variability benefits error-driven learning in humans.

Science.gov (United States)

Diederen, Kelly M J; Schultz, Wolfram

2015-09-01

Effective error-driven learning requires individuals to adapt learning to environmental reward variability. The adaptive mechanism may involve decays in learning rate across subsequent trials, as shown previously, and rescaling of reward prediction errors. The present study investigated the influence of prediction error scaling and, in particular, the consequences for learning performance. Participants explicitly predicted reward magnitudes that were drawn from different probability distributions with specific standard deviations. By fitting the data with reinforcement learning models, we found scaling of prediction errors, in addition to the learning rate decay shown previously. Importantly, the prediction error scaling was closely related to learning performance, defined as accuracy in predicting the mean of reward distributions, across individual participants. In addition, participants who scaled prediction errors relative to standard deviation also presented with more similar performance for different standard deviations, indicating that increases in standard deviation did not substantially decrease "adapters'" accuracy in predicting the means of reward distributions. However, exaggerated scaling beyond the standard deviation resulted in impaired performance. Thus efficient adaptation makes learning more robust to changing variability. Copyright © 2015 the American Physiological Society.

Transfer of test-enhanced learning: Meta-analytic review and synthesis.

Science.gov (United States)

Pan, Steven C; Rickard, Timothy C

2018-05-07

Attempting recall of information from memory, as occurs when taking a practice test, is one of the most potent training techniques known to learning science. However, does testing yield learning that transfers to different contexts? In the present article, we report the findings of the first comprehensive meta-analytic review into that question. Our review encompassed 192 transfer effect sizes extracted from 122 experiments and 67 published and unpublished articles (N = 10,382) that together comprise more than 40 years of research. A random-effects model revealed that testing can yield transferrable learning as measured relative to a nontesting reexposure control condition (d = 0.40, 95% CI [0.31, 0.50]). That transfer of learning is greatest across test formats, to application and inference questions, to problems involving medical diagnoses, and to mediator and related word cues; it is weakest to rearranged stimulus-response items, to untested materials seen during initial study, and to problems involving worked examples. Moderator analyses further indicated that response congruency and elaborated retrieval practice, as well as initial test performance, strongly influence the likelihood of positive transfer. In two assessments for publication bias using PET-PEESE and various selection methods, the moderator effect sizes were minimally affected. However, the intercept predictions were substantially reduced, often indicating no positive transfer when none of the aforementioned moderators are present. Overall, our results motivate a three-factor framework for transfer of test-enhanced learning and have practical implications for the effective use of practice testing in educational and other training contexts. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Conformal prediction for reliable machine learning theory, adaptations and applications

CERN Document Server

Balasubramanian, Vineeth; Vovk, Vladimir

2014-01-01

The conformal predictions framework is a recent development in machine learning that can associate a reliable measure of confidence with a prediction in any real-world pattern recognition application, including risk-sensitive applications such as medical diagnosis, face recognition, and financial risk prediction. Conformal Predictions for Reliable Machine Learning: Theory, Adaptations and Applications captures the basic theory of the framework, demonstrates how to apply it to real-world problems, and presents several adaptations, including active learning, change detection, and anomaly detecti

A data-driven predictive approach for drug delivery using machine learning techniques.

Directory of Open Access Journals (Sweden)

Yuanyuan Li

Full Text Available In drug delivery, there is often a trade-off between effective killing of the pathogen, and harmful side effects associated with the treatment. Due to the difficulty in testing every dosing scenario experimentally, a computational approach will be helpful to assist with the prediction of effective drug delivery methods. In this paper, we have developed a data-driven predictive system, using machine learning techniques, to determine, in silico, the effectiveness of drug dosing. The system framework is scalable, autonomous, robust, and has the ability to predict the effectiveness of the current drug treatment and the subsequent drug-pathogen dynamics. The system consists of a dynamic model incorporating both the drug concentration and pathogen population into distinct states. These states are then analyzed using a temporal model to describe the drug-cell interactions over time. The dynamic drug-cell interactions are learned in an adaptive fashion and used to make sequential predictions on the effectiveness of the dosing strategy. Incorporated into the system is the ability to adjust the sensitivity and specificity of the learned models based on a threshold level determined by the operator for the specific application. As a proof-of-concept, the system was validated experimentally using the pathogen Giardia lamblia and the drug metronidazole in vitro.

Social learning through prediction error in the brain

Science.gov (United States)

Joiner, Jessica; Piva, Matthew; Turrin, Courtney; Chang, Steve W. C.

2017-06-01

Learning about the world is critical to survival and success. In social animals, learning about others is a necessary component of navigating the social world, ultimately contributing to increasing evolutionary fitness. How humans and nonhuman animals represent the internal states and experiences of others has long been a subject of intense interest in the developmental psychology tradition, and, more recently, in studies of learning and decision making involving self and other. In this review, we explore how psychology conceptualizes the process of representing others, and how neuroscience has uncovered correlates of reinforcement learning signals to explore the neural mechanisms underlying social learning from the perspective of representing reward-related information about self and other. In particular, we discuss self-referenced and other-referenced types of reward prediction errors across multiple brain structures that effectively allow reinforcement learning algorithms to mediate social learning. Prediction-based computational principles in the brain may be strikingly conserved between self-referenced and other-referenced information.

A novel time series link prediction method: Learning automata approach

Science.gov (United States)

Moradabadi, Behnaz; Meybodi, Mohammad Reza

2017-09-01

Link prediction is a main social network challenge that uses the network structure to predict future links. The common link prediction approaches to predict hidden links use a static graph representation where a snapshot of the network is analyzed to find hidden or future links. For example, similarity metric based link predictions are a common traditional approach that calculates the similarity metric for each non-connected link and sort the links based on their similarity metrics and label the links with higher similarity scores as the future links. Because people activities in social networks are dynamic and uncertainty, and the structure of the networks changes over time, using deterministic graphs for modeling and analysis of the social network may not be appropriate. In the time-series link prediction problem, the time series link occurrences are used to predict the future links In this paper, we propose a new time series link prediction based on learning automata. In the proposed algorithm for each link that must be predicted there is one learning automaton and each learning automaton tries to predict the existence or non-existence of the corresponding link. To predict the link occurrence in time T, there is a chain consists of stages 1 through T - 1 and the learning automaton passes from these stages to learn the existence or non-existence of the corresponding link. Our preliminary link prediction experiments with co-authorship and email networks have provided satisfactory results when time series link occurrences are considered.

Signed reward prediction errors drive declarative learning

NARCIS (Netherlands)

De Loof, E.; Ergo, K.; Naert, L.; Janssens, C.; Talsma, D.; van Opstal, F.; Verguts, T.

2018-01-01

Reward prediction errors (RPEs) are thought to drive learning. This has been established in procedural learning (e.g., classical and operant conditioning). However, empirical evidence on whether RPEs drive declarative learning–a quintessentially human form of learning–remains surprisingly absent. We

Statistical and Machine Learning Models to Predict Programming Performance

OpenAIRE

Bergin, Susan

2006-01-01

This thesis details a longitudinal study on factors that influence introductory programming success and on the development of machine learning models to predict incoming student performance. Although numerous studies have developed models to predict programming success, the models struggled to achieve high accuracy in predicting the likely performance of incoming students. Our approach overcomes this by providing a machine learning technique, using a set of three significant...

Quicksilver: Fast predictive image registration - A deep learning approach.

Science.gov (United States)

Yang, Xiao; Kwitt, Roland; Styner, Martin; Niethammer, Marc

2017-09-01

This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during the testing time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. We show experimental results for uni-modal atlas-to-image as well as uni-/multi-modal image-to-image registrations. These experiments demonstrate that our method accurately predicts registrations obtained by numerical optimization, is very fast, achieves state-of-the-art registration results on four standard validation datasets, and can jointly learn an image similarity measure. Quicksilver is freely available as an open-source software. Copyright © 2017 Elsevier Inc. All rights reserved.

Learning and Prediction of Slip from Visual Information

Science.gov (United States)

Angelova, Anelia; Matthies, Larry; Helmick, Daniel; Perona, Pietro

2007-01-01

This paper presents an approach for slip prediction from a distance for wheeled ground robots using visual information as input. Large amounts of slippage which can occur on certain surfaces, such as sandy slopes, will negatively affect rover mobility. Therefore, obtaining information about slip before entering such terrain can be very useful for better planning and avoiding these areas. To address this problem, terrain appearance and geometry information about map cells are correlated to the slip measured by the rover while traversing each cell. This relationship is learned from previous experience, so slip can be predicted remotely from visual information only. The proposed method consists of terrain type recognition and nonlinear regression modeling. The method has been implemented and tested offline on several off-road terrains including: soil, sand, gravel, and woodchips. The final slip prediction error is about 20%. The system is intended for improved navigation on steep slopes and rough terrain for Mars rovers.

Learning receptive fields using predictive feedback.

Science.gov (United States)

Jehee, Janneke F M; Rothkopf, Constantin; Beck, Jeffrey M; Ballard, Dana H

2006-01-01

Previously, it was suggested that feedback connections from higher- to lower-level areas carry predictions of lower-level neural activities, whereas feedforward connections carry the residual error between the predictions and the actual lower-level activities [Rao, R.P.N., Ballard, D.H., 1999. Nature Neuroscience 2, 79-87.]. A computational model implementing the hypothesis learned simple cell receptive fields when exposed to natural images. Here, we use predictive feedback to explain tuning properties in medial superior temporal area (MST). We implement the hypothesis using a new, biologically plausible, algorithm based on matching pursuit, which retains all the features of the previous implementation, including its ability to efficiently encode input. When presented with natural images, the model developed receptive field properties as found in primary visual cortex. In addition, when exposed to visual motion input resulting from movements through space, the model learned receptive field properties resembling those in MST. These results corroborate the idea that predictive feedback is a general principle used by the visual system to efficiently encode natural input.

Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

Science.gov (United States)

Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

2018-01-05

Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

Learning Python testing

CERN Document Server

Arbuckle, Daniel

2014-01-01

This book is ideal if you want to learn about the testing disciplines and automated testing tools from a hands-on, conversational guide. You should already know Python and be comfortable with Python 3.

Prediction of stroke thrombolysis outcome using CT brain machine learning

Directory of Open Access Journals (Sweden)

Paul Bentley

2014-01-01

Full Text Available A critical decision-step in the emergency treatment of ischemic stroke is whether or not to administer thrombolysis — a treatment that can result in good recovery, or deterioration due to symptomatic intracranial haemorrhage (SICH. Certain imaging features based upon early computerized tomography (CT, in combination with clinical variables, have been found to predict SICH, albeit with modest accuracy. In this proof-of-concept study, we determine whether machine learning of CT images can predict which patients receiving tPA will develop SICH as opposed to showing clinical improvement with no haemorrhage. Clinical records and CT brains of 116 acute ischemic stroke patients treated with intravenous thrombolysis were collected retrospectively (including 16 who developed SICH. The sample was split into training (n = 106 and test sets (n = 10, repeatedly for 1760 different combinations. CT brain images acted as inputs into a support vector machine (SVM, along with clinical severity. Performance of the SVM was compared with established prognostication tools (SEDAN and HAT scores; original, or after adaptation to our cohort. Predictive performance, assessed as area under receiver-operating-characteristic curve (AUC, of the SVM (0.744 compared favourably with that of prognostic scores (original and adapted versions: 0.626–0.720; p < 0.01. The SVM also identified 9 out of 16 SICHs, as opposed to 1–5 using prognostic scores, assuming a 10% SICH frequency (p < 0.001. In summary, machine learning methods applied to acute stroke CT images offer automation, and potentially improved performance, for prediction of SICH following thrombolysis. Larger-scale cohorts, and incorporation of advanced imaging, should be tested with such methods.

Randomized Prediction Games for Adversarial Machine Learning.

Science.gov (United States)

Rota Bulo, Samuel; Biggio, Battista; Pillai, Ignazio; Pelillo, Marcello; Roli, Fabio

In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time, e.g., malware code is typically obfuscated using random strings or byte sequences to hide known exploits. Interestingly, randomization has also been proposed to improve security of learning algorithms against evasion attacks, as it results in hiding information about the classifier to the attacker. Recent work has proposed game-theoretical formulations to learn secure classifiers, by simulating different evasion attacks and modifying the classification function accordingly. However, both the classification function and the simulated data manipulations have been modeled in a deterministic manner, without accounting for any form of randomization. In this paper, we overcome this limitation by proposing a randomized prediction game, namely, a noncooperative game-theoretic formulation in which the classifier and the attacker make randomized strategy selections according to some probability distribution defined over the respective strategy set. We show that our approach allows one to improve the tradeoff between attack detection and false alarms with respect to the state-of-the-art secure classifiers, even against attacks that are different from those hypothesized during design, on application examples including handwritten digit recognition, spam, and malware detection.In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time, e.g., malware code is typically obfuscated using random strings or byte sequences to hide known exploits. Interestingly, randomization has also been proposed to improve security of learning algorithms against evasion attacks, as it results in hiding information about the classifier to the attacker. Recent work has proposed game-theoretical formulations to learn secure classifiers, by simulating different

Predicting DPP-IV inhibitors with machine learning approaches

Science.gov (United States)

Cai, Jie; Li, Chanjuan; Liu, Zhihong; Du, Jiewen; Ye, Jiming; Gu, Qiong; Xu, Jun

2017-04-01

Dipeptidyl peptidase IV (DPP-IV) is a promising Type 2 diabetes mellitus (T2DM) drug target. DPP-IV inhibitors prolong the action of glucagon-like peptide-1 (GLP-1) and gastric inhibitory peptide (GIP), improve glucose homeostasis without weight gain, edema, and hypoglycemia. However, the marketed DPP-IV inhibitors have adverse effects such as nasopharyngitis, headache, nausea, hypersensitivity, skin reactions and pancreatitis. Therefore, it is still expected for novel DPP-IV inhibitors with minimal adverse effects. The scaffolds of existing DPP-IV inhibitors are structurally diversified. This makes it difficult to build virtual screening models based upon the known DPP-IV inhibitor libraries using conventional QSAR approaches. In this paper, we report a new strategy to predict DPP-IV inhibitors with machine learning approaches involving naïve Bayesian (NB) and recursive partitioning (RP) methods. We built 247 machine learning models based on 1307 known DPP-IV inhibitors with optimized molecular properties and topological fingerprints as descriptors. The overall predictive accuracies of the optimized models were greater than 80%. An external test set, composed of 65 recently reported compounds, was employed to validate the optimized models. The results demonstrated that both NB and RP models have a good predictive ability based on different combinations of descriptors. Twenty "good" and twenty "bad" structural fragments for DPP-IV inhibitors can also be derived from these models for inspiring the new DPP-IV inhibitor scaffold design.

Predicting Student Performance in a Collaborative Learning Environment

Science.gov (United States)

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…

Predicting Smoking Status Using Machine Learning Algorithms and Statistical Analysis

Directory of Open Access Journals (Sweden)

Charles Frank

2018-03-01

Full Text Available Smoking has been proven to negatively affect health in a multitude of ways. As of 2009, smoking has been considered the leading cause of preventable morbidity and mortality in the United States, continuing to plague the country’s overall health. This study aims to investigate the viability and effectiveness of some machine learning algorithms for predicting the smoking status of patients based on their blood tests and vital readings results. The analysis of this study is divided into two parts: In part 1, we use One-way ANOVA analysis with SAS tool to show the statistically significant difference in blood test readings between smokers and non-smokers. The results show that the difference in INR, which measures the effectiveness of anticoagulants, was significant in favor of non-smokers which further confirms the health risks associated with smoking. In part 2, we use five machine learning algorithms: Naïve Bayes, MLP, Logistic regression classifier, J48 and Decision Table to predict the smoking status of patients. To compare the effectiveness of these algorithms we use: Precision, Recall, F-measure and Accuracy measures. The results show that the Logistic algorithm outperformed the four other algorithms with Precision, Recall, F-Measure, and Accuracy of 83%, 83.4%, 83.2%, 83.44%, respectively.

An investigation of classification algorithms for predicting HIV drug resistance without genotype resistance testing

CSIR Research Space (South Africa)

Brandt, P

2014-01-01

Full Text Available is limited in low-resource settings. In this paper we investigate machine learning techniques for drug resistance prediction from routine treatment and laboratory data to help clinicians select patients for confirmatory genotype testing. The techniques...

Machine learning for outcome prediction of acute ischemic stroke post intra-arterial therapy.

Directory of Open Access Journals (Sweden)

Hamed Asadi

Full Text Available INTRODUCTION: Stroke is a major cause of death and disability. Accurately predicting stroke outcome from a set of predictive variables may identify high-risk patients and guide treatment approaches, leading to decreased morbidity. Logistic regression models allow for the identification and validation of predictive variables. However, advanced machine learning algorithms offer an alternative, in particular, for large-scale multi-institutional data, with the advantage of easily incorporating newly available data to improve prediction performance. Our aim was to design and compare different machine learning methods, capable of predicting the outcome of endovascular intervention in acute anterior circulation ischaemic stroke. METHOD: We conducted a retrospective study of a prospectively collected database of acute ischaemic stroke treated by endovascular intervention. Using SPSS®, MATLAB®, and Rapidminer®, classical statistics as well as artificial neural network and support vector algorithms were applied to design a supervised machine capable of classifying these predictors into potential good and poor outcomes. These algorithms were trained, validated and tested using randomly divided data. RESULTS: We included 107 consecutive acute anterior circulation ischaemic stroke patients treated by endovascular technique. Sixty-six were male and the mean age of 65.3. All the available demographic, procedural and clinical factors were included into the models. The final confusion matrix of the neural network, demonstrated an overall congruency of ∼ 80% between the target and output classes, with favourable receiving operative characteristics. However, after optimisation, the support vector machine had a relatively better performance, with a root mean squared error of 2.064 (SD: ± 0.408. DISCUSSION: We showed promising accuracy of outcome prediction, using supervised machine learning algorithms, with potential for incorporation of larger multicenter

Clinical chemistry in higher dimensions: Machine-learning and enhanced prediction from routine clinical chemistry data.

Science.gov (United States)

Richardson, Alice; Signor, Ben M; Lidbury, Brett A; Badrick, Tony

2016-11-01

Big Data is having an impact on many areas of research, not the least of which is biomedical science. In this review paper, big data and machine learning are defined in terms accessible to the clinical chemistry community. Seven myths associated with machine learning and big data are then presented, with the aim of managing expectation of machine learning amongst clinical chemists. The myths are illustrated with four examples investigating the relationship between biomarkers in liver function tests, enhanced laboratory prediction of hepatitis virus infection, the relationship between bilirubin and white cell count, and the relationship between red cell distribution width and laboratory prediction of anaemia. Copyright © 2016 The Canadian Society of Clinical Chemists. Published by Elsevier Inc. All rights reserved.

What roles do errors serve in motor skill learning? An examination of two theoretical predictions.

Science.gov (United States)

Sanli, Elizabeth A; Lee, Timothy D

2014-01-01

Easy-to-difficult and difficult-to-easy progressions of task difficulty during skill acquisition were examined in 2 experiments that assessed retention, dual-task, and transfer tests of learning. Findings of the first experiment suggest that an easy-to difficult progression did not consistently induce implicit learning processes and was not consistently beneficial to performance under a secondary-task load. The findings of experiment two did not support the predictions made based on schema theory and only partially supported predictions based on reinvestment theory. The authors interpret these findings to suggest that the timing of error in relation to the difficulty of the task (functional task difficulty) plays a role in the transfer of learning to novel versions of a task.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods.

Science.gov (United States)

Zheng, Suqing; Jiang, Mengying; Zhao, Chengwei; Zhu, Rui; Hu, Zhicheng; Xu, Yong; Lin, Fu

2018-01-01

In-silico bitterant prediction received the considerable attention due to the expensive and laborious experimental-screening of the bitterant. In this work, we collect the fully experimental dataset containing 707 bitterants and 592 non-bitterants, which is distinct from the fully or partially hypothetical non-bitterant dataset used in the previous works. Based on this experimental dataset, we harness the consensus votes from the multiple machine-learning methods (e.g., deep learning etc.) combined with the molecular fingerprint to build the bitter/bitterless classification models with five-fold cross-validation, which are further inspected by the Y-randomization test and applicability domain analysis. One of the best consensus models affords the accuracy, precision, specificity, sensitivity, F1-score, and Matthews correlation coefficient (MCC) of 0.929, 0.918, 0.898, 0.954, 0.936, and 0.856 respectively on our test set. For the automatic prediction of bitterant, a graphic program "e-Bitter" is developed for the convenience of users via the simple mouse click. To our best knowledge, it is for the first time to adopt the consensus model for the bitterant prediction and develop the first free stand-alone software for the experimental food scientist.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-learning Methods

Science.gov (United States)

Zheng, Suqing; Jiang, Mengying; Zhao, Chengwei; Zhu, Rui; Hu, Zhicheng; Xu, Yong; Lin, Fu

2018-03-01

In-silico bitterant prediction received the considerable attention due to the expensive and laborious experimental-screening of the bitterant. In this work, we collect the fully experimental dataset containing 707 bitterants and 592 non-bitterants, which is distinct from the fully or partially hypothetical non-bitterant dataset used in the previous works. Based on this experimental dataset, we harness the consensus votes from the multiple machine-learning methods (e.g., deep learning etc.) combined with the molecular fingerprint to build the bitter/bitterless classification models with five-fold cross-validation, which are further inspected by the Y-randomization test and applicability domain analysis. One of the best consensus models affords the accuracy, precision, specificity, sensitivity, F1-score, and Matthews correlation coefficient (MCC) of 0.929, 0.918, 0.898, 0.954, 0.936, and 0.856 respectively on our test set. For the automatic prediction of bitterant, a graphic program “e-Bitter” is developed for the convenience of users via the simple mouse click. To our best knowledge, it is for the first time to adopt the consensus model for the bitterant prediction and develop the first free stand-alone software for the experimental food scientist.

Dropout Prediction in E-Learning Courses through the Combination of Machine Learning Techniques

Science.gov (United States)

Lykourentzou, Ioanna; Giannoukos, Ioannis; Nikolopoulos, Vassilis; Mpardis, George; Loumos, Vassili

2009-01-01

In this paper, a dropout prediction method for e-learning courses, based on three popular machine learning techniques and detailed student data, is proposed. The machine learning techniques used are feed-forward neural networks, support vector machines and probabilistic ensemble simplified fuzzy ARTMAP. Since a single technique may fail to…

Deep learning architectures for multi-label classification of intelligent health risk prediction.

Science.gov (United States)

Maxwell, Andrew; Li, Runzhi; Yang, Bei; Weng, Heng; Ou, Aihua; Hong, Huixiao; Zhou, Zhaoxian; Gong, Ping; Zhang, Chaoyang

2017-12-28

Multi-label classification of data remains to be a challenging problem. Because of the complexity of the data, it is sometimes difficult to infer information about classes that are not mutually exclusive. For medical data, patients could have symptoms of multiple different diseases at the same time and it is important to develop tools that help to identify problems early. Intelligent health risk prediction models built with deep learning architectures offer a powerful tool for physicians to identify patterns in patient data that indicate risks associated with certain types of chronic diseases. Physical examination records of 110,300 anonymous patients were used to predict diabetes, hypertension, fatty liver, a combination of these three chronic diseases, and the absence of disease (8 classes in total). The dataset was split into training (90%) and testing (10%) sub-datasets. Ten-fold cross validation was used to evaluate prediction accuracy with metrics such as precision, recall, and F-score. Deep Learning (DL) architectures were compared with standard and state-of-the-art multi-label classification methods. Preliminary results suggest that Deep Neural Networks (DNN), a DL architecture, when applied to multi-label classification of chronic diseases, produced accuracy that was comparable to that of common methods such as Support Vector Machines. We have implemented DNNs to handle both problem transformation and algorithm adaption type multi-label methods and compare both to see which is preferable. Deep Learning architectures have the potential of inferring more information about the patterns of physical examination data than common classification methods. The advanced techniques of Deep Learning can be used to identify the significance of different features from physical examination data as well as to learn the contributions of each feature that impact a patient's risk for chronic diseases. However, accurate prediction of chronic disease risks remains a challenging

Playing off the curve - testing quantitative predictions of skill acquisition theories in development of chess performance.

Science.gov (United States)

Gaschler, Robert; Progscha, Johanna; Smallbone, Kieran; Ram, Nilam; Bilalić, Merim

2014-01-01

Learning curves have been proposed as an adequate description of learning processes, no matter whether the processes manifest within minutes or across years. Different mechanisms underlying skill acquisition can lead to differences in the shape of learning curves. In the current study, we analyze the tournament performance data of 1383 chess players who begin competing at young age and play tournaments for at least 10 years. We analyze the performance development with the goal to test the adequacy of learning curves, and the skill acquisition theories they are based on, for describing and predicting expertise acquisition. On the one hand, we show that the skill acquisition theories implying a negative exponential learning curve do a better job in both describing early performance gains and predicting later trajectories of chess performance than those theories implying a power function learning curve. On the other hand, the learning curves of a large proportion of players show systematic qualitative deviations from the predictions of either type of skill acquisition theory. While skill acquisition theories predict larger performance gains in early years and smaller gains in later years, a substantial number of players begin to show substantial improvements with a delay of several years (and no improvement in the first years), deviations not fully accounted for by quantity of practice. The current work adds to the debate on how learning processes on a small time scale combine to large-scale changes.

Gene Prediction in Metagenomic Fragments with Deep Learning

Directory of Open Access Journals (Sweden)

Shao-Wu Zhang

2017-01-01

Full Text Available Next generation sequencing technologies used in metagenomics yield numerous sequencing fragments which come from thousands of different species. Accurately identifying genes from metagenomics fragments is one of the most fundamental issues in metagenomics. In this article, by fusing multifeatures (i.e., monocodon usage, monoamino acid usage, ORF length coverage, and Z-curve features and using deep stacking networks learning model, we present a novel method (called Meta-MFDL to predict the metagenomic genes. The results with 10 CV and independent tests show that Meta-MFDL is a powerful tool for identifying genes from metagenomic fragments.

Learning predictive statistics from temporal sequences: Dynamics and strategies.

Science.gov (United States)

Wang, Rui; Shen, Yuan; Tino, Peter; Welchman, Andrew E; Kourtzi, Zoe

2017-10-01

Human behavior is guided by our expectations about the future. Often, we make predictions by monitoring how event sequences unfold, even though such sequences may appear incomprehensible. Event structures in the natural environment typically vary in complexity, from simple repetition to complex probabilistic combinations. How do we learn these structures? Here we investigate the dynamics of structure learning by tracking human responses to temporal sequences that change in structure unbeknownst to the participants. Participants were asked to predict the upcoming item following a probabilistic sequence of symbols. Using a Markov process, we created a family of sequences, from simple frequency statistics (e.g., some symbols are more probable than others) to context-based statistics (e.g., symbol probability is contingent on preceding symbols). We demonstrate the dynamics with which individuals adapt to changes in the environment's statistics-that is, they extract the behaviorally relevant structures to make predictions about upcoming events. Further, we show that this structure learning relates to individual decision strategy; faster learning of complex structures relates to selection of the most probable outcome in a given context (maximizing) rather than matching of the exact sequence statistics. Our findings provide evidence for alternate routes to learning of behaviorally relevant statistics that facilitate our ability to predict future events in variable environments.

Different protein-protein interface patterns predicted by different machine learning methods.

Science.gov (United States)

Wang, Wei; Yang, Yongxiao; Yin, Jianxin; Gong, Xinqi

2017-11-22

Different types of protein-protein interactions make different protein-protein interface patterns. Different machine learning methods are suitable to deal with different types of data. Then, is it the same situation that different interface patterns are preferred for prediction by different machine learning methods? Here, four different machine learning methods were employed to predict protein-protein interface residue pairs on different interface patterns. The performances of the methods for different types of proteins are different, which suggest that different machine learning methods tend to predict different protein-protein interface patterns. We made use of ANOVA and variable selection to prove our result. Our proposed methods taking advantages of different single methods also got a good prediction result compared to single methods. In addition to the prediction of protein-protein interactions, this idea can be extended to other research areas such as protein structure prediction and design.

Field tests and machine learning approaches for refining algorithms and correlations of driver's model parameters.

Science.gov (United States)

Tango, Fabio; Minin, Luca; Tesauri, Francesco; Montanari, Roberto

2010-03-01

This paper describes the field tests on a driving simulator carried out to validate the algorithms and the correlations of dynamic parameters, specifically driving task demand and drivers' distraction, able to predict drivers' intentions. These parameters belong to the driver's model developed by AIDE (Adaptive Integrated Driver-vehicle InterfacE) European Integrated Project. Drivers' behavioural data have been collected from the simulator tests to model and validate these parameters using machine learning techniques, specifically the adaptive neuro fuzzy inference systems (ANFIS) and the artificial neural network (ANN). Two models of task demand and distraction have been developed, one for each adopted technique. The paper provides an overview of the driver's model, the description of the task demand and distraction modelling and the tests conducted for the validation of these parameters. A test comparing predicted and expected outcomes of the modelled parameters for each machine learning technique has been carried out: for distraction, in particular, promising results (low prediction errors) have been obtained by adopting an artificial neural network.

Application of Machine Learning to Predict Dietary Lapses During Weight Loss.

Science.gov (United States)

Goldstein, Stephanie P; Zhang, Fengqing; Thomas, John G; Butryn, Meghan L; Herbert, James D; Forman, Evan M

2018-05-01

Individuals who adhere to dietary guidelines provided during weight loss interventions tend to be more successful with weight control. Any deviation from dietary guidelines can be referred to as a "lapse." There is a growing body of research showing that lapses are predictable using a variety of physiological, environmental, and psychological indicators. With recent technological advancements, it may be possible to assess these triggers and predict dietary lapses in real time. The current study sought to use machine learning techniques to predict lapses and evaluate the utility of combining both group- and individual-level data to enhance lapse prediction. The current study trained and tested a machine learning algorithm capable of predicting dietary lapses from a behavioral weight loss program among adults with overweight/obesity (n = 12). Participants were asked to follow a weight control diet for 6 weeks and complete ecological momentary assessment (EMA; repeated brief surveys delivered via smartphone) regarding dietary lapses and relevant triggers. WEKA decision trees were used to predict lapses with an accuracy of 0.72 for the group of participants. However, generalization of the group algorithm to each individual was poor, and as such, group- and individual-level data were combined to improve prediction. The findings suggest that 4 weeks of individual data collection is recommended to attain optimal model performance. The predictive algorithm could be utilized to provide in-the-moment interventions to prevent dietary lapses and therefore enhance weight losses. Furthermore, methods in the current study could be translated to other types of health behavior lapses.

Wind Power Ramp Events Prediction with Hybrid Machine Learning Regression Techniques and Reanalysis Data

Directory of Open Access Journals (Sweden)

Laura Cornejo-Bueno

2017-11-01

Full Text Available Wind Power Ramp Events (WPREs are large fluctuations of wind power in a short time interval, which lead to strong, undesirable variations in the electric power produced by a wind farm. Its accurate prediction is important in the effort of efficiently integrating wind energy in the electric system, without affecting considerably its stability, robustness and resilience. In this paper, we tackle the problem of predicting WPREs by applying Machine Learning (ML regression techniques. Our approach consists of using variables from atmospheric reanalysis data as predictive inputs for the learning machine, which opens the possibility of hybridizing numerical-physical weather models with ML techniques for WPREs prediction in real systems. Specifically, we have explored the feasibility of a number of state-of-the-art ML regression techniques, such as support vector regression, artificial neural networks (multi-layer perceptrons and extreme learning machines and Gaussian processes to solve the problem. Furthermore, the ERA-Interim reanalysis from the European Center for Medium-Range Weather Forecasts is the one used in this paper because of its accuracy and high resolution (in both spatial and temporal domains. Aiming at validating the feasibility of our predicting approach, we have carried out an extensive experimental work using real data from three wind farms in Spain, discussing the performance of the different ML regression tested in this wind power ramp event prediction problem.

Machine Learning Algorithms Outperform Conventional Regression Models in Predicting Development of Hepatocellular Carcinoma

Science.gov (United States)

Singal, Amit G.; Mukherjee, Ashin; Elmunzer, B. Joseph; Higgins, Peter DR; Lok, Anna S.; Zhu, Ji; Marrero, Jorge A; Waljee, Akbar K

2015-01-01

Background Predictive models for hepatocellular carcinoma (HCC) have been limited by modest accuracy and lack of validation. Machine learning algorithms offer a novel methodology, which may improve HCC risk prognostication among patients with cirrhosis. Our study's aim was to develop and compare predictive models for HCC development among cirrhotic patients, using conventional regression analysis and machine learning algorithms. Methods We enrolled 442 patients with Child A or B cirrhosis at the University of Michigan between January 2004 and September 2006 (UM cohort) and prospectively followed them until HCC development, liver transplantation, death, or study termination. Regression analysis and machine learning algorithms were used to construct predictive models for HCC development, which were tested on an independent validation cohort from the Hepatitis C Antiviral Long-term Treatment against Cirrhosis (HALT-C) Trial. Both models were also compared to the previously published HALT-C model. Discrimination was assessed using receiver operating characteristic curve analysis and diagnostic accuracy was assessed with net reclassification improvement and integrated discrimination improvement statistics. Results After a median follow-up of 3.5 years, 41 patients developed HCC. The UM regression model had a c-statistic of 0.61 (95%CI 0.56-0.67), whereas the machine learning algorithm had a c-statistic of 0.64 (95%CI 0.60–0.69) in the validation cohort. The machine learning algorithm had significantly better diagnostic accuracy as assessed by net reclassification improvement (pmachine learning algorithm (p=0.047). Conclusion Machine learning algorithms improve the accuracy of risk stratifying patients with cirrhosis and can be used to accurately identify patients at high-risk for developing HCC. PMID:24169273

Can Learning Motivation Predict Learning Achievement? A Case Study of a Mobile Game-Based English Learning Approach

Science.gov (United States)

Tsai, Chia-Hui; Cheng, Ching-Hsue; Yeh, Duen-Yian; Lin, Shih-Yun

2017-01-01

This study applied a quasi-experimental design to investigate the influence and predictive power of learner motivation for achievement, employing a mobile game-based English learning approach. A system called the Happy English Learning System, integrating learning material into a game-based context, was constructed and installed on mobile devices…

Test-enhanced learning: the potential for testing to promote greater learning in undergraduate science courses.

Science.gov (United States)

Brame, Cynthia J; Biel, Rachel

2015-01-01

Testing within the science classroom is commonly used for both formative and summative assessment purposes to let the student and the instructor gauge progress toward learning goals. Research within cognitive science suggests, however, that testing can also be a learning event. We present summaries of studies that suggest that repeated retrieval can enhance long-term learning in a laboratory setting; various testing formats can promote learning; feedback enhances the benefits of testing; testing can potentiate further study; and benefits of testing are not limited to rote memory. Most of these studies were performed in a laboratory environment, so we also present summaries of experiments suggesting that the benefits of testing can extend to the classroom. Finally, we suggest opportunities that these observations raise for the classroom and for further research. © 2015 C. J. Brame and R. Biel. CBE—Life Sciences Education © 2015 The American Society for Cell Biology. This article is distributed by The American Society for Cell Biology under license from the author(s). It is available to the public under an Attribution–Noncommercial–Share Alike 3.0 Unported Creative Commons License (http://creativecommons.org/licenses/by-nc-sa/3.0).

Stress enhances the consolidation of extinction memory in a predictive learning task

Directory of Open Access Journals (Sweden)

Tanja eHamacher-Dang

2013-08-01

Full Text Available Extinction is not always permanent, as indicated by several types of recovery effects, such as the renewal effect, which may occur after a context change and points towards the importance of contextual cues. Strengthening the retrieval of extinction memory is a crucial aim of extinction-based psychotherapeutic treatments of anxiety disorders to prevent relapse. Stress is known to modulate learning and memory, with mostly enhancing effects on memory consolidation. However, whether such a consolidation-enhancing effect of acute stress can also be found for extinction memory has not yet been examined in humans. In this study, we investigated the effect of stress after extinction learning on the retrieval of extinction memory in a predictive learning renewal paradigm. Participants took the part of being the doctor of a fictitious patient and learned to predict whether certain food stimuli were associated with ‘stomach trouble’ in two different restaurants (contexts. On the first day, critical stimuli were associated with stomach trouble in context A (acquisition phase. On the second day, these associations were extinguished in context B. Directly after extinction, participants were either exposed to a stressor (socially evaluated cold pressor test; n = 22 or a control condition (n = 24. On the third day, we tested retrieval of critical associations in contexts A and B. Participants exposed to stress after extinction exhibited a reduced recovery of responding at test in context B, suggesting that stress may context-dependently enhance the consolidation of extinction memory. Furthermore, the increase in cortisol in response to the stressor was negatively correlated with the recovery of responding in context A. Our findings suggest that in parallel to the known effects of stress on the consolidation of episodic memory, stress also enhances the consolidation of extinction memory, which might be relevant for potential applications in extinction

Machine learning in Python essential techniques for predictive analysis

CERN Document Server

Bowles, Michael

2015-01-01

Learn a simpler and more effective way to analyze data and predict outcomes with Python Machine Learning in Python shows you how to successfully analyze data using only two core machine learning algorithms, and how to apply them using Python. By focusing on two algorithm families that effectively predict outcomes, this book is able to provide full descriptions of the mechanisms at work, and the examples that illustrate the machinery with specific, hackable code. The algorithms are explained in simple terms with no complex math and applied using Python, with guidance on algorithm selection, d

Machine Learning Methods to Predict Diabetes Complications.

Science.gov (United States)

Dagliati, Arianna; Marini, Simone; Sacchi, Lucia; Cogni, Giulia; Teliti, Marsida; Tibollo, Valentina; De Cata, Pasquale; Chiovato, Luca; Bellazzi, Riccardo

2018-03-01

One of the areas where Artificial Intelligence is having more impact is machine learning, which develops algorithms able to learn patterns and decision rules from data. Machine learning algorithms have been embedded into data mining pipelines, which can combine them with classical statistical strategies, to extract knowledge from data. Within the EU-funded MOSAIC project, a data mining pipeline has been used to derive a set of predictive models of type 2 diabetes mellitus (T2DM) complications based on electronic health record data of nearly one thousand patients. Such pipeline comprises clinical center profiling, predictive model targeting, predictive model construction and model validation. After having dealt with missing data by means of random forest (RF) and having applied suitable strategies to handle class imbalance, we have used Logistic Regression with stepwise feature selection to predict the onset of retinopathy, neuropathy, or nephropathy, at different time scenarios, at 3, 5, and 7 years from the first visit at the Hospital Center for Diabetes (not from the diagnosis). Considered variables are gender, age, time from diagnosis, body mass index (BMI), glycated hemoglobin (HbA1c), hypertension, and smoking habit. Final models, tailored in accordance with the complications, provided an accuracy up to 0.838. Different variables were selected for each complication and time scenario, leading to specialized models easy to translate to the clinical practice.

Distributed Learning, Recognition, and Prediction by ART and ARTMAP Neural Networks.

Science.gov (United States)

Carpenter, Gail A.

1997-11-01

A class of adaptive resonance theory (ART) models for learning, recognition, and prediction with arbitrarily distributed code representations is introduced. Distributed ART neural networks combine the stable fast learning capabilities of winner-take-all ART systems with the noise tolerance and code compression capabilities of multilayer perceptrons. With a winner-take-all code, the unsupervised model dART reduces to fuzzy ART and the supervised model dARTMAP reduces to fuzzy ARTMAP. With a distributed code, these networks automatically apportion learned changes according to the degree of activation of each coding node, which permits fast as well as slow learning without catastrophic forgetting. Distributed ART models replace the traditional neural network path weight with a dynamic weight equal to the rectified difference between coding node activation and an adaptive threshold. Thresholds increase monotonically during learning according to a principle of atrophy due to disuse. However, monotonic change at the synaptic level manifests itself as bidirectional change at the dynamic level, where the result of adaptation resembles long-term potentiation (LTP) for single-pulse or low frequency test inputs but can resemble long-term depression (LTD) for higher frequency test inputs. This paradoxical behavior is traced to dual computational properties of phasic and tonic coding signal components. A parallel distributed match-reset-search process also helps stabilize memory. Without the match-reset-search system, dART becomes a type of distributed competitive learning network.

Spontaneous brain activity predicts learning ability of foreign sounds.

Science.gov (United States)

Ventura-Campos, Noelia; Sanjuán, Ana; González, Julio; Palomar-García, María-Ángeles; Rodríguez-Pujadas, Aina; Sebastián-Gallés, Núria; Deco, Gustavo; Ávila, César

2013-05-29

Can learning capacity of the human brain be predicted from initial spontaneous functional connectivity (FC) between brain areas involved in a task? We combined task-related functional magnetic resonance imaging (fMRI) and resting-state fMRI (rs-fMRI) before and after training with a Hindi dental-retroflex nonnative contrast. Previous fMRI results were replicated, demonstrating that this learning recruited the left insula/frontal operculum and the left superior parietal lobe, among other areas of the brain. Crucially, resting-state FC (rs-FC) between these two areas at pretraining predicted individual differences in learning outcomes after distributed (Experiment 1) and intensive training (Experiment 2). Furthermore, this rs-FC was reduced at posttraining, a change that may also account for learning. Finally, resting-state network analyses showed that the mechanism underlying this reduction of rs-FC was mainly a transfer in intrinsic activity of the left frontal operculum/anterior insula from the left frontoparietal network to the salience network. Thus, rs-FC may contribute to predict learning ability and to understand how learning modifies the functioning of the brain. The discovery of this correspondence between initial spontaneous brain activity in task-related areas and posttraining performance opens new avenues to find predictors of learning capacities in the brain using task-related fMRI and rs-fMRI combined.

Using Tests as Learning Opportunities.

Science.gov (United States)

Foos, Paul W.; Fisher, Ronald P.

1988-01-01

A study involving 105 undergraduates assessed the value of testing as a means of increasing, rather than simply monitoring, learning. Results indicate that fill-in-the-blank and items requiring student inferences were more effective, respectively, than multiple-choice tests and verbatim items in furthering student learning. (TJH)

Episodic Memory Encoding Interferes with Reward Learning and Decreases Striatal Prediction Errors

Science.gov (United States)

Braun, Erin Kendall; Daw, Nathaniel D.

2014-01-01

Learning is essential for adaptive decision making. The striatum and its dopaminergic inputs are known to support incremental reward-based learning, while the hippocampus is known to support encoding of single events (episodic memory). Although traditionally studied separately, in even simple experiences, these two types of learning are likely to co-occur and may interact. Here we sought to understand the nature of this interaction by examining how incremental reward learning is related to concurrent episodic memory encoding. During the experiment, human participants made choices between two options (colored squares), each associated with a drifting probability of reward, with the goal of earning as much money as possible. Incidental, trial-unique object pictures, unrelated to the choice, were overlaid on each option. The next day, participants were given a surprise memory test for these pictures. We found that better episodic memory was related to a decreased influence of recent reward experience on choice, both within and across participants. fMRI analyses further revealed that during learning the canonical striatal reward prediction error signal was significantly weaker when episodic memory was stronger. This decrease in reward prediction error signals in the striatum was associated with enhanced functional connectivity between the hippocampus and striatum at the time of choice. Our results suggest a mechanism by which memory encoding may compete for striatal processing and provide insight into how interactions between different forms of learning guide reward-based decision making. PMID:25378157

A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

Science.gov (United States)

Benvenuto, Federico; Piana, Michele; Campi, Cristina; Massone, Anna Maria

2018-01-01

This paper introduces a novel method for flare forecasting, combining prediction accuracy with the ability to identify the most relevant predictive variables. This result is obtained by means of a two-step approach: first, a supervised regularization method for regression, namely, LASSO is applied, where a sparsity-enhancing penalty term allows the identification of the significance with which each data feature contributes to the prediction; then, an unsupervised fuzzy clustering technique for classification, namely, Fuzzy C-Means, is applied, where the regression outcome is partitioned through the minimization of a cost function and without focusing on the optimization of a specific skill score. This approach is therefore hybrid, since it combines supervised and unsupervised learning; realizes classification in an automatic, skill-score-independent way; and provides effective prediction performances even in the case of imbalanced data sets. Its prediction power is verified against NOAA Space Weather Prediction Center data, using as a test set, data in the range between 1996 August and 2010 December and as training set, data in the range between 1988 December and 1996 June. To validate the method, we computed several skill scores typically utilized in flare prediction and compared the values provided by the hybrid approach with the ones provided by several standard (non-hybrid) machine learning methods. The results showed that the hybrid approach performs classification better than all other supervised methods and with an effectiveness comparable to the one of clustering methods; but, in addition, it provides a reliable ranking of the weights with which the data properties contribute to the forecast.

When bad stress goes good: increased threat reactivity predicts improved category learning performance.

Science.gov (United States)

Ell, Shawn W; Cosley, Brandon; McCoy, Shannon K

2011-02-01

The way in which we respond to everyday stressors can have a profound impact on cognitive functioning. Maladaptive stress responses in particular are generally associated with impaired cognitive performance. We argue, however, that the cognitive system mediating task performance is also a critical determinant of the stress-cognition relationship. Consistent with this prediction, we observed that stress reactivity consistent with a maladaptive, threat response differentially predicted performance on two categorization tasks. Increased threat reactivity predicted enhanced performance on an information-integration task (i.e., learning is thought to depend upon a procedural-based memory system), and a (nonsignificant) trend for impaired performance on a rule-based task (i.e., learning is thought to depend upon a hypothesis-testing system). These data suggest that it is critical to consider both variability in the stress response and variability in the cognitive system mediating task performance in order to fully understand the stress-cognition relationship.

The conditions that promote fear learning: prediction error and Pavlovian fear conditioning.

Science.gov (United States)

Li, Susan Shi Yuan; McNally, Gavan P

2014-02-01

A key insight of associative learning theory is that learning depends on the actions of prediction error: a discrepancy between the actual and expected outcomes of a conditioning trial. When positive, such error causes increments in associative strength and, when negative, such error causes decrements in associative strength. Prediction error can act directly on fear learning by determining the effectiveness of the aversive unconditioned stimulus or indirectly by determining the effectiveness, or associability, of the conditioned stimulus. Evidence from a variety of experimental preparations in human and non-human animals suggest that discrete neural circuits code for these actions of prediction error during fear learning. Here we review the circuits and brain regions contributing to the neural coding of prediction error during fear learning and highlight areas of research (safety learning, extinction, and reconsolidation) that may profit from this approach to understanding learning. Crown Copyright © 2013. Published by Elsevier Inc. All rights reserved.

Dopamine prediction errors in reward learning and addiction: from theory to neural circuitry

Science.gov (United States)

Keiflin, Ronald; Janak, Patricia H.

2015-01-01

Summary Midbrain dopamine (DA) neurons are proposed to signal reward prediction error (RPE), a fundamental parameter in associative learning models. This RPE hypothesis provides a compelling theoretical framework for understanding DA function in reward learning and addiction. New studies support a causal role for DA-mediated RPE activity in promoting learning about natural reward; however, this question has not been explicitly tested in the context of drug addiction. In this review, we integrate theoretical models with experimental findings on the activity of DA systems, and on the causal role of specific neuronal projections and cell types, to provide a circuit-based framework for probing DA-RPE function in addiction. By examining error-encoding DA neurons in the neural network in which they are embedded, hypotheses regarding circuit-level adaptations that possibly contribute to pathological error-signaling and addiction can be formulated and tested. PMID:26494275

Dopamine Prediction Errors in Reward Learning and Addiction: From Theory to Neural Circuitry.

Science.gov (United States)

Keiflin, Ronald; Janak, Patricia H

2015-10-21

Midbrain dopamine (DA) neurons are proposed to signal reward prediction error (RPE), a fundamental parameter in associative learning models. This RPE hypothesis provides a compelling theoretical framework for understanding DA function in reward learning and addiction. New studies support a causal role for DA-mediated RPE activity in promoting learning about natural reward; however, this question has not been explicitly tested in the context of drug addiction. In this review, we integrate theoretical models with experimental findings on the activity of DA systems, and on the causal role of specific neuronal projections and cell types, to provide a circuit-based framework for probing DA-RPE function in addiction. By examining error-encoding DA neurons in the neural network in which they are embedded, hypotheses regarding circuit-level adaptations that possibly contribute to pathological error signaling and addiction can be formulated and tested. Copyright © 2015 Elsevier Inc. All rights reserved.

WORMHOLE: Novel Least Diverged Ortholog Prediction through Machine Learning

Science.gov (United States)

Sutphin, George L.; Mahoney, J. Matthew; Sheppard, Keith; Walton, David O.; Korstanje, Ron

2016-01-01

The rapid advancement of technology in genomics and targeted genetic manipulation has made comparative biology an increasingly prominent strategy to model human disease processes. Predicting orthology relationships between species is a vital component of comparative biology. Dozens of strategies for predicting orthologs have been developed using combinations of gene and protein sequence, phylogenetic history, and functional interaction with progressively increasing accuracy. A relatively new class of orthology prediction strategies combines aspects of multiple methods into meta-tools, resulting in improved prediction performance. Here we present WORMHOLE, a novel ortholog prediction meta-tool that applies machine learning to integrate 17 distinct ortholog prediction algorithms to identify novel least diverged orthologs (LDOs) between 6 eukaryotic species—humans, mice, zebrafish, fruit flies, nematodes, and budding yeast. Machine learning allows WORMHOLE to intelligently incorporate predictions from a wide-spectrum of strategies in order to form aggregate predictions of LDOs with high confidence. In this study we demonstrate the performance of WORMHOLE across each combination of query and target species. We show that WORMHOLE is particularly adept at improving LDO prediction performance between distantly related species, expanding the pool of LDOs while maintaining low evolutionary distance and a high level of functional relatedness between genes in LDO pairs. We present extensive validation, including cross-validated prediction of PANTHER LDOs and evaluation of evolutionary divergence and functional similarity, and discuss future applications of machine learning in ortholog prediction. A WORMHOLE web tool has been developed and is available at http://wormhole.jax.org/. PMID:27812085

WORMHOLE: Novel Least Diverged Ortholog Prediction through Machine Learning.

Directory of Open Access Journals (Sweden)

George L Sutphin

2016-11-01

Full Text Available The rapid advancement of technology in genomics and targeted genetic manipulation has made comparative biology an increasingly prominent strategy to model human disease processes. Predicting orthology relationships between species is a vital component of comparative biology. Dozens of strategies for predicting orthologs have been developed using combinations of gene and protein sequence, phylogenetic history, and functional interaction with progressively increasing accuracy. A relatively new class of orthology prediction strategies combines aspects of multiple methods into meta-tools, resulting in improved prediction performance. Here we present WORMHOLE, a novel ortholog prediction meta-tool that applies machine learning to integrate 17 distinct ortholog prediction algorithms to identify novel least diverged orthologs (LDOs between 6 eukaryotic species-humans, mice, zebrafish, fruit flies, nematodes, and budding yeast. Machine learning allows WORMHOLE to intelligently incorporate predictions from a wide-spectrum of strategies in order to form aggregate predictions of LDOs with high confidence. In this study we demonstrate the performance of WORMHOLE across each combination of query and target species. We show that WORMHOLE is particularly adept at improving LDO prediction performance between distantly related species, expanding the pool of LDOs while maintaining low evolutionary distance and a high level of functional relatedness between genes in LDO pairs. We present extensive validation, including cross-validated prediction of PANTHER LDOs and evaluation of evolutionary divergence and functional similarity, and discuss future applications of machine learning in ortholog prediction. A WORMHOLE web tool has been developed and is available at http://wormhole.jax.org/.

Resting alpha activity predicts learning ability in alpha neurofeedback

Directory of Open Access Journals (Sweden)

Wenya eNan

2014-07-01

Full Text Available Individuals differ in their ability to learn how to regulate the alpha activity by neurofeedback. This study aimed to investigate whether the resting alpha activity is related to the learning ability of alpha enhancement in neurofeedback and could be used as a predictor. A total of 25 subjects performed 20 sessions of individualized alpha neurofeedback in order to learn how to enhance activity in the alpha frequency band. The learning ability was assessed by three indices respectively: the training parameter changes between two periods, within a short period and across the whole training time. It was found that the resting alpha amplitude measured before training had significant positive correlations with all learning indices and could be used as a predictor for the learning ability prediction. This finding would help the researchers in not only predicting the training efficacy in individuals but also gaining further insight into the mechanisms of alpha neurofeedback.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods

Directory of Open Access Journals (Sweden)

Suqing Zheng

2018-03-01

Full Text Available In-silico bitterant prediction received the considerable attention due to the expensive and laborious experimental-screening of the bitterant. In this work, we collect the fully experimental dataset containing 707 bitterants and 592 non-bitterants, which is distinct from the fully or partially hypothetical non-bitterant dataset used in the previous works. Based on this experimental dataset, we harness the consensus votes from the multiple machine-learning methods (e.g., deep learning etc. combined with the molecular fingerprint to build the bitter/bitterless classification models with five-fold cross-validation, which are further inspected by the Y-randomization test and applicability domain analysis. One of the best consensus models affords the accuracy, precision, specificity, sensitivity, F1-score, and Matthews correlation coefficient (MCC of 0.929, 0.918, 0.898, 0.954, 0.936, and 0.856 respectively on our test set. For the automatic prediction of bitterant, a graphic program “e-Bitter” is developed for the convenience of users via the simple mouse click. To our best knowledge, it is for the first time to adopt the consensus model for the bitterant prediction and develop the first free stand-alone software for the experimental food scientist.

Resting heart rate variability predicts safety learning and fear extinction in an interoceptive fear conditioning paradigm.

Directory of Open Access Journals (Sweden)

Meike Pappens

Full Text Available This study aimed to investigate whether interindividual differences in autonomic inhibitory control predict safety learning and fear extinction in an interoceptive fear conditioning paradigm. Data from a previously reported study (N = 40 were extended (N = 17 and re-analyzed to test whether healthy participants' resting heart rate variability (HRV - a proxy of cardiac vagal tone - predicts learning performance. The conditioned stimulus (CS was a slight sensation of breathlessness induced by a flow resistor, the unconditioned stimulus (US was an aversive short-lasting suffocation experience induced by a complete occlusion of the breathing circuitry. During acquisition, the paired group received 6 paired CS-US presentations; the control group received 6 explicitly unpaired CS-US presentations. In the extinction phase, both groups were exposed to 6 CS-only presentations. Measures included startle blink EMG, skin conductance responses (SCR and US-expectancy ratings. Resting HRV significantly predicted the startle blink EMG learning curves both during acquisition and extinction. In the unpaired group, higher levels of HRV at rest predicted safety learning to the CS during acquisition. In the paired group, higher levels of HRV were associated with better extinction. Our findings suggest that the strength or integrity of prefrontal inhibitory mechanisms involved in safety- and extinction learning can be indexed by HRV at rest.

Machine learning applied to the prediction of citrus production

OpenAIRE

Díaz Rodríguez, Susana Irene; Mazza, Silvia M.; Fernández-Combarro Álvarez, Elías; Giménez, Laura I.; Gaiad, José E.

2017-01-01

An in-depth knowledge about variables affecting production is required in order to predict global production and take decisions in agriculture. Machine learning is a technique used in agricultural planning and precision agriculture. This work (i) studies the effectiveness of machine learning techniques for predicting orchards production; and (ii) variables affecting this production were also identified. Data from 964 orchards of lemon, mandarin, and orange in Corrientes, Argentina are analyse...

SU-F-P-20: Predicting Waiting Times in Radiation Oncology Using Machine Learning

International Nuclear Information System (INIS)

Joseph, A; Herrera, D; Hijal, T; Kildea, J; Hendren, L; Leung, A; Wainberg, J; Sawaf, M; Gorshkov, M; Maglieri, R; Keshavarz, M

2016-01-01

Purpose: Waiting times remain one of the most vexing patient satisfaction challenges facing healthcare. Waiting time uncertainty can cause patients, who are already sick or in pain, to worry about when they will receive the care they need. These waiting periods are often difficult for staff to predict and only rough estimates are typically provided based on personal experience. This level of uncertainty leaves most patients unable to plan their calendar, making the waiting experience uncomfortable, even painful. In the present era of electronic health records (EHRs), waiting times need not be so uncertain. Extensive EHRs provide unprecedented amounts of data that can statistically cluster towards representative values when appropriate patient cohorts are selected. Predictive modelling, such as machine learning, is a powerful approach that benefits from large, potentially complex, datasets. The essence of machine learning is to predict future outcomes by learning from previous experience. The application of a machine learning algorithm to waiting time data has the potential to produce personalized waiting time predictions such that the uncertainty may be removed from the patient’s waiting experience. Methods: In radiation oncology, patients typically experience several types of waiting (eg waiting at home for treatment planning, waiting in the waiting room for oncologist appointments and daily waiting in the waiting room for radiotherapy treatments). A daily treatment wait time model is discussed in this report. To develop a prediction model using our large dataset (with more than 100k sample points) a variety of machine learning algorithms from the Python package sklearn were tested. Results: We found that the Random Forest Regressor model provides the best predictions for daily radiotherapy treatment waiting times. Using this model, we achieved a median residual (actual value minus predicted value) of 0.25 minutes and a standard deviation residual of 6.5 minutes

SU-F-P-20: Predicting Waiting Times in Radiation Oncology Using Machine Learning

Energy Technology Data Exchange (ETDEWEB)

Joseph, A; Herrera, D; Hijal, T; Kildea, J [McGill University Health Centre, Montreal, Quebec (Canada); Hendren, L; Leung, A; Wainberg, J; Sawaf, M; Gorshkov, M; Maglieri, R; Keshavarz, M [McGill University, Montreal, Quebec (Canada)

2016-06-15

Purpose: Waiting times remain one of the most vexing patient satisfaction challenges facing healthcare. Waiting time uncertainty can cause patients, who are already sick or in pain, to worry about when they will receive the care they need. These waiting periods are often difficult for staff to predict and only rough estimates are typically provided based on personal experience. This level of uncertainty leaves most patients unable to plan their calendar, making the waiting experience uncomfortable, even painful. In the present era of electronic health records (EHRs), waiting times need not be so uncertain. Extensive EHRs provide unprecedented amounts of data that can statistically cluster towards representative values when appropriate patient cohorts are selected. Predictive modelling, such as machine learning, is a powerful approach that benefits from large, potentially complex, datasets. The essence of machine learning is to predict future outcomes by learning from previous experience. The application of a machine learning algorithm to waiting time data has the potential to produce personalized waiting time predictions such that the uncertainty may be removed from the patient’s waiting experience. Methods: In radiation oncology, patients typically experience several types of waiting (eg waiting at home for treatment planning, waiting in the waiting room for oncologist appointments and daily waiting in the waiting room for radiotherapy treatments). A daily treatment wait time model is discussed in this report. To develop a prediction model using our large dataset (with more than 100k sample points) a variety of machine learning algorithms from the Python package sklearn were tested. Results: We found that the Random Forest Regressor model provides the best predictions for daily radiotherapy treatment waiting times. Using this model, we achieved a median residual (actual value minus predicted value) of 0.25 minutes and a standard deviation residual of 6.5 minutes

Can machine-learning improve cardiovascular risk prediction using routine clinical data?

Science.gov (United States)

Kai, Joe; Garibaldi, Jonathan M.; Qureshi, Nadeem

2017-01-01

Background Current approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction. Methods Prospective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the ‘receiver operating curve’ (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins). Findings 24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723–0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739–0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755–0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755–0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759–0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm. Conclusions Machine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others

Functional connectivity between somatosensory and motor brain areas predicts individual differences in motor learning by observing.

Science.gov (United States)

McGregor, Heather R; Gribble, Paul L

2017-08-01

Action observation can facilitate the acquisition of novel motor skills; however, there is considerable individual variability in the extent to which observation promotes motor learning. Here we tested the hypothesis that individual differences in brain function or structure can predict subsequent observation-related gains in motor learning. Subjects underwent an anatomical MRI scan and resting-state fMRI scans to assess preobservation gray matter volume and preobservation resting-state functional connectivity (FC), respectively. On the following day, subjects observed a video of a tutor adapting her reaches to a novel force field. After observation, subjects performed reaches in a force field as a behavioral assessment of gains in motor learning resulting from observation. We found that individual differences in resting-state FC, but not gray matter volume, predicted postobservation gains in motor learning. Preobservation resting-state FC between left primary somatosensory cortex and bilateral dorsal premotor cortex, primary motor cortex, and primary somatosensory cortex and left superior parietal lobule was positively correlated with behavioral measures of postobservation motor learning. Sensory-motor resting-state FC can thus predict the extent to which observation will promote subsequent motor learning. NEW & NOTEWORTHY We show that individual differences in preobservation brain function can predict subsequent observation-related gains in motor learning. Preobservation resting-state functional connectivity within a sensory-motor network may be used as a biomarker for the extent to which observation promotes motor learning. This kind of information may be useful if observation is to be used as a way to boost neuroplasticity and sensory-motor recovery for patients undergoing rehabilitation for diseases that impair movement such as stroke. Copyright © 2017 the American Physiological Society.

Deep learning predictions of survival based on MRI in amyotrophic lateral sclerosis.

Science.gov (United States)

van der Burgh, Hannelore K; Schmidt, Ruben; Westeneng, Henk-Jan; de Reus, Marcel A; van den Berg, Leonard H; van den Heuvel, Martijn P

2017-01-01

Amyotrophic lateral sclerosis (ALS) is a progressive neuromuscular disease, with large variation in survival between patients. Currently, it remains rather difficult to predict survival based on clinical parameters alone. Here, we set out to use clinical characteristics in combination with MRI data to predict survival of ALS patients using deep learning, a machine learning technique highly effective in a broad range of big-data analyses. A group of 135 ALS patients was included from whom high-resolution diffusion-weighted and T1-weighted images were acquired at the first visit to the outpatient clinic. Next, each of the patients was monitored carefully and survival time to death was recorded. Patients were labeled as short, medium or long survivors, based on their recorded time to death as measured from the time of disease onset. In the deep learning procedure, the total group of 135 patients was split into a training set for deep learning (n = 83 patients), a validation set (n = 20) and an independent evaluation set (n = 32) to evaluate the performance of the obtained deep learning networks. Deep learning based on clinical characteristics predicted survival category correctly in 68.8% of the cases. Deep learning based on MRI predicted 62.5% correctly using structural connectivity and 62.5% using brain morphology data. Notably, when we combined the three sources of information, deep learning prediction accuracy increased to 84.4%. Taken together, our findings show the added value of MRI with respect to predicting survival in ALS, demonstrating the advantage of deep learning in disease prognostication.

Curiosity and reward: Valence predicts choice and information prediction errors enhance learning.

Science.gov (United States)

Marvin, Caroline B; Shohamy, Daphna

2016-03-01

Curiosity drives many of our daily pursuits and interactions; yet, we know surprisingly little about how it works. Here, we harness an idea implied in many conceptualizations of curiosity: that information has value in and of itself. Reframing curiosity as the motivation to obtain reward-where the reward is information-allows one to leverage major advances in theoretical and computational mechanisms of reward-motivated learning. We provide new evidence supporting 2 predictions that emerge from this framework. First, we find an asymmetric effect of positive versus negative information, with positive information enhancing both curiosity and long-term memory for information. Second, we find that it is not the absolute value of information that drives learning but, rather, the gap between the reward expected and reward received, an "information prediction error." These results support the idea that information functions as a reward, much like money or food, guiding choices and driving learning in systematic ways. (c) 2016 APA, all rights reserved).

Multi-fidelity machine learning models for accurate bandgap predictions of solids

International Nuclear Information System (INIS)

Pilania, Ghanshyam; Gubernatis, James E.; Lookman, Turab

2016-01-01

Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelity quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.

Application of Machine Learning Approaches for Protein-protein Interactions Prediction.

Science.gov (United States)

Zhang, Mengying; Su, Qiang; Lu, Yi; Zhao, Manman; Niu, Bing

2017-01-01

Proteomics endeavors to study the structures, functions and interactions of proteins. Information of the protein-protein interactions (PPIs) helps to improve our knowledge of the functions and the 3D structures of proteins. Thus determining the PPIs is essential for the study of the proteomics. In this review, in order to study the application of machine learning in predicting PPI, some machine learning approaches such as support vector machine (SVM), artificial neural networks (ANNs) and random forest (RF) were selected, and the examples of its applications in PPIs were listed. SVM and RF are two commonly used methods. Nowadays, more researchers predict PPIs by combining more than two methods. This review presents the application of machine learning approaches in predicting PPI. Many examples of success in identification and prediction in the area of PPI prediction have been discussed, and the PPIs research is still in progress. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Machine learning models in breast cancer survival prediction.

Science.gov (United States)

Montazeri, Mitra; Montazeri, Mohadeseh; Montazeri, Mahdieh; Beigzadeh, Amin

2016-01-01

Breast cancer is one of the most common cancers with a high mortality rate among women. With the early diagnosis of breast cancer survival will increase from 56% to more than 86%. Therefore, an accurate and reliable system is necessary for the early diagnosis of this cancer. The proposed model is the combination of rules and different machine learning techniques. Machine learning models can help physicians to reduce the number of false decisions. They try to exploit patterns and relationships among a large number of cases and predict the outcome of a disease using historical cases stored in datasets. The objective of this study is to propose a rule-based classification method with machine learning techniques for the prediction of different types of Breast cancer survival. We use a dataset with eight attributes that include the records of 900 patients in which 876 patients (97.3%) and 24 (2.7%) patients were females and males respectively. Naive Bayes (NB), Trees Random Forest (TRF), 1-Nearest Neighbor (1NN), AdaBoost (AD), Support Vector Machine (SVM), RBF Network (RBFN), and Multilayer Perceptron (MLP) machine learning techniques with 10-cross fold technique were used with the proposed model for the prediction of breast cancer survival. The performance of machine learning techniques were evaluated with accuracy, precision, sensitivity, specificity, and area under ROC curve. Out of 900 patients, 803 patients and 97 patients were alive and dead, respectively. In this study, Trees Random Forest (TRF) technique showed better results in comparison to other techniques (NB, 1NN, AD, SVM and RBFN, MLP). The accuracy, sensitivity and the area under ROC curve of TRF are 96%, 96%, 93%, respectively. However, 1NN machine learning technique provided poor performance (accuracy 91%, sensitivity 91% and area under ROC curve 78%). This study demonstrates that Trees Random Forest model (TRF) which is a rule-based classification model was the best model with the highest level of

Predictive ability of machine learning methods for massive crop yield prediction

Directory of Open Access Journals (Sweden)

Alberto Gonzalez-Sanchez

2014-04-01

Full Text Available An important issue for agricultural planning purposes is the accurate yield estimation for the numerous crops involved in the planning. Machine learning (ML is an essential approach for achieving practical and effective solutions for this problem. Many comparisons of ML methods for yield prediction have been made, seeking for the most accurate technique. Generally, the number of evaluated crops and techniques is too low and does not provide enough information for agricultural planning purposes. This paper compares the predictive accuracy of ML and linear regression techniques for crop yield prediction in ten crop datasets. Multiple linear regression, M5-Prime regression trees, perceptron multilayer neural networks, support vector regression and k-nearest neighbor methods were ranked. Four accuracy metrics were used to validate the models: the root mean square error (RMS, root relative square error (RRSE, normalized mean absolute error (MAE, and correlation factor (R. Real data of an irrigation zone of Mexico were used for building the models. Models were tested with samples of two consecutive years. The results show that M5-Prime and k-nearest neighbor techniques obtain the lowest average RMSE errors (5.14 and 4.91, the lowest RRSE errors (79.46% and 79.78%, the lowest average MAE errors (18.12% and 19.42%, and the highest average correlation factors (0.41 and 0.42. Since M5-Prime achieves the largest number of crop yield models with the lowest errors, it is a very suitable tool for massive crop yield prediction in agricultural planning.

A predictive validity study of the Learning Style Questionnaire (LSQ) using multiple, specific learning criteria

NARCIS (Netherlands)

Kappe, F.R.; Boekholt, L.; den Rooyen, C.; van der Flier, H.

2009-01-01

Multiple and specific learning criteria were used to examine the predictive validity of the Learning Style Questionnaire (LSQ). Ninety-nine students in a college of higher learning in The Netherlands participated in a naturally occurring field study. The students were categorized into one of four

Machine-Learning-Based No Show Prediction in Outpatient Visits

Directory of Open Access Journals (Sweden)

Carlos Elvira

2018-03-01

Full Text Available A recurring problem in healthcare is the high percentage of patients who miss their appointment, be it a consultation or a hospital test. The present study seeks patient’s behavioural patterns that allow predicting the probability of no- shows. We explore the convenience of using Big Data Machine Learning models to accomplish this task. To begin with, a predictive model based only on variables associated with the target appointment is built. Then the model is improved by considering the patient’s history of appointments. In both cases, the Gradient Boosting algorithm was the predictor of choice. Our numerical results are considered promising given the small amount of information available. However, there seems to be plenty of room to improve the model if we manage to collect additional data for both patients and appointments.

Predicting the time of conversion to MCI in the elderly: role of verbal expression and learning.

Science.gov (United States)

Oulhaj, Abderrahim; Wilcock, Gordon K; Smith, A David; de Jager, Celeste A

2009-11-03

Increasing awareness that minimal or mild cognitive impairment (MCI) in the elderly may be a precursor of dementia has led to an increase in the number of people attending memory clinics. We aimed to develop a way of predicting the period of time before cognitive impairment occurs in community-dwelling elderly. The method is illustrated by the use of simple tests of different cognitive domains. A cohort of 241 normal elderly volunteers was followed for up to 20 years with regular assessments of cognitive abilities using the Cambridge Cognitive Examination (CAMCOG); 91 participants developed MCI. We used interval-censored survival analysis statistical methods to model which baseline cognitive tests best predicted the time to convert to MCI. Out of several baseline variables, only age and CAMCOG subscores for expression and learning/memory were predictors of the time to conversion. The time to conversion was 14% shorter for each 5 years of age, 17% shorter for each point lower in the expression score, and 15% shorter for each point lower in the learning score. We present in tabular form the probability of converting to MCI over intervals between 2 and 10 years for different combinations of expression and learning scores. In apparently normal elderly people, subtle measurable cognitive deficits that occur within the normal range on standard testing protocols reliably predict the time to clinically relevant cognitive impairment long before clinical symptoms are reported.

Application of Machine-Learning Models to Predict Tacrolimus Stable Dose in Renal Transplant Recipients

Science.gov (United States)

Tang, Jie; Liu, Rong; Zhang, Yue-Li; Liu, Mou-Ze; Hu, Yong-Fang; Shao, Ming-Jie; Zhu, Li-Jun; Xin, Hua-Wen; Feng, Gui-Wen; Shang, Wen-Jun; Meng, Xiang-Guang; Zhang, Li-Rong; Ming, Ying-Zi; Zhang, Wei

2017-02-01

Tacrolimus has a narrow therapeutic window and considerable variability in clinical use. Our goal was to compare the performance of multiple linear regression (MLR) and eight machine learning techniques in pharmacogenetic algorithm-based prediction of tacrolimus stable dose (TSD) in a large Chinese cohort. A total of 1,045 renal transplant patients were recruited, 80% of which were randomly selected as the “derivation cohort” to develop dose-prediction algorithm, while the remaining 20% constituted the “validation cohort” to test the final selected algorithm. MLR, artificial neural network (ANN), regression tree (RT), multivariate adaptive regression splines (MARS), boosted regression tree (BRT), support vector regression (SVR), random forest regression (RFR), lasso regression (LAR) and Bayesian additive regression trees (BART) were applied and their performances were compared in this work. Among all the machine learning models, RT performed best in both derivation [0.71 (0.67-0.76)] and validation cohorts [0.73 (0.63-0.82)]. In addition, the ideal rate of RT was 4% higher than that of MLR. To our knowledge, this is the first study to use machine learning models to predict TSD, which will further facilitate personalized medicine in tacrolimus administration in the future.

Episodic memory encoding interferes with reward learning and decreases striatal prediction errors.

Science.gov (United States)

Wimmer, G Elliott; Braun, Erin Kendall; Daw, Nathaniel D; Shohamy, Daphna

2014-11-05

Learning is essential for adaptive decision making. The striatum and its dopaminergic inputs are known to support incremental reward-based learning, while the hippocampus is known to support encoding of single events (episodic memory). Although traditionally studied separately, in even simple experiences, these two types of learning are likely to co-occur and may interact. Here we sought to understand the nature of this interaction by examining how incremental reward learning is related to concurrent episodic memory encoding. During the experiment, human participants made choices between two options (colored squares), each associated with a drifting probability of reward, with the goal of earning as much money as possible. Incidental, trial-unique object pictures, unrelated to the choice, were overlaid on each option. The next day, participants were given a surprise memory test for these pictures. We found that better episodic memory was related to a decreased influence of recent reward experience on choice, both within and across participants. fMRI analyses further revealed that during learning the canonical striatal reward prediction error signal was significantly weaker when episodic memory was stronger. This decrease in reward prediction error signals in the striatum was associated with enhanced functional connectivity between the hippocampus and striatum at the time of choice. Our results suggest a mechanism by which memory encoding may compete for striatal processing and provide insight into how interactions between different forms of learning guide reward-based decision making. Copyright © 2014 the authors 0270-6474/14/3414901-12$15.00/0.

An Approach for Predicting Essential Genes Using Multiple Homology Mapping and Machine Learning Algorithms.

Science.gov (United States)

Hua, Hong-Li; Zhang, Fa-Zhan; Labena, Abraham Alemayehu; Dong, Chuan; Jin, Yan-Ting; Guo, Feng-Biao

Investigation of essential genes is significant to comprehend the minimal gene sets of cell and discover potential drug targets. In this study, a novel approach based on multiple homology mapping and machine learning method was introduced to predict essential genes. We focused on 25 bacteria which have characterized essential genes. The predictions yielded the highest area under receiver operating characteristic (ROC) curve (AUC) of 0.9716 through tenfold cross-validation test. Proper features were utilized to construct models to make predictions in distantly related bacteria. The accuracy of predictions was evaluated via the consistency of predictions and known essential genes of target species. The highest AUC of 0.9552 and average AUC of 0.8314 were achieved when making predictions across organisms. An independent dataset from Synechococcus elongatus , which was released recently, was obtained for further assessment of the performance of our model. The AUC score of predictions is 0.7855, which is higher than other methods. This research presents that features obtained by homology mapping uniquely can achieve quite great or even better results than those integrated features. Meanwhile, the work indicates that machine learning-based method can assign more efficient weight coefficients than using empirical formula based on biological knowledge.

Neural prediction errors reveal a risk-sensitive reinforcement-learning process in the human brain.

Science.gov (United States)

Niv, Yael; Edlund, Jeffrey A; Dayan, Peter; O'Doherty, John P

2012-01-11

Humans and animals are exquisitely, though idiosyncratically, sensitive to risk or variance in the outcomes of their actions. Economic, psychological, and neural aspects of this are well studied when information about risk is provided explicitly. However, we must normally learn about outcomes from experience, through trial and error. Traditional models of such reinforcement learning focus on learning about the mean reward value of cues and ignore higher order moments such as variance. We used fMRI to test whether the neural correlates of human reinforcement learning are sensitive to experienced risk. Our analysis focused on anatomically delineated regions of a priori interest in the nucleus accumbens, where blood oxygenation level-dependent (BOLD) signals have been suggested as correlating with quantities derived from reinforcement learning. We first provide unbiased evidence that the raw BOLD signal in these regions corresponds closely to a reward prediction error. We then derive from this signal the learned values of cues that predict rewards of equal mean but different variance and show that these values are indeed modulated by experienced risk. Moreover, a close neurometric-psychometric coupling exists between the fluctuations of the experience-based evaluations of risky options that we measured neurally and the fluctuations in behavioral risk aversion. This suggests that risk sensitivity is integral to human learning, illuminating economic models of choice, neuroscientific models of affective learning, and the workings of the underlying neural mechanisms.

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Science.gov (United States)

Park, Saerom; Lee, Jaewook; Son, Youngdoo

2016-01-01

Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

Computational prediction of multidisciplinary team decision-making for adjuvant breast cancer drug therapies: a machine learning approach.

Science.gov (United States)

Lin, Frank P Y; Pokorny, Adrian; Teng, Christina; Dear, Rachel; Epstein, Richard J

2016-12-01

Multidisciplinary team (MDT) meetings are used to optimise expert decision-making about treatment options, but such expertise is not digitally transferable between centres. To help standardise medical decision-making, we developed a machine learning model designed to predict MDT decisions about adjuvant breast cancer treatments. We analysed MDT decisions regarding adjuvant systemic therapy for 1065 breast cancer cases over eight years. Machine learning classifiers with and without bootstrap aggregation were correlated with MDT decisions (recommended, not recommended, or discussable) regarding adjuvant cytotoxic, endocrine and biologic/targeted therapies, then tested for predictability using stratified ten-fold cross-validations. The predictions so derived were duly compared with those based on published (ESMO and NCCN) cancer guidelines. Machine learning more accurately predicted adjuvant chemotherapy MDT decisions than did simple application of guidelines. No differences were found between MDT- vs. ESMO/NCCN- based decisions to prescribe either adjuvant endocrine (97%, p = 0.44/0.74) or biologic/targeted therapies (98%, p = 0.82/0.59). In contrast, significant discrepancies were evident between MDT- and guideline-based decisions to prescribe chemotherapy (87%, p machine learning models. A machine learning approach based on clinicopathologic characteristics can predict MDT decisions about adjuvant breast cancer drug therapies. The discrepancy between MDT- and guideline-based decisions regarding adjuvant chemotherapy implies that certain non-clincopathologic criteria, such as patient preference and resource availability, are factored into clinical decision-making by local experts but not captured by guidelines.

An ensemble machine learning approach to predict survival in breast cancer.

Science.gov (United States)

Djebbari, Amira; Liu, Ziying; Phan, Sieu; Famili, Fazel

2008-01-01

Current breast cancer predictive signatures are not unique. Can we use this fact to our advantage to improve prediction? From the machine learning perspective, it is well known that combining multiple classifiers can improve classification performance. We propose an ensemble machine learning approach which consists of choosing feature subsets and learning predictive models from them. We then combine models based on certain model fusion criteria and we also introduce a tuning parameter to control sensitivity. Our method significantly improves classification performance with a particular emphasis on sensitivity which is critical to avoid misclassifying poor prognosis patients as good prognosis.

An analysis of a digital variant of the Trail Making Test using machine learning techniques.

Science.gov (United States)

Dahmen, Jessamyn; Cook, Diane; Fellows, Robert; Schmitter-Edgecombe, Maureen

2017-01-01

The goal of this work is to develop a digital version of a standard cognitive assessment, the Trail Making Test (TMT), and assess its utility. This paper introduces a novel digital version of the TMT and introduces a machine learning based approach to assess its capabilities. Using digital Trail Making Test (dTMT) data collected from (N = 54) older adult participants as feature sets, we use machine learning techniques to analyze the utility of the dTMT and evaluate the insights provided by the digital features. Predicted TMT scores correlate well with clinical digital test scores (r = 0.98) and paper time to completion scores (r = 0.65). Predicted TICS exhibited a small correlation with clinically derived TICS scores (r = 0.12 Part A, r = 0.10 Part B). Predicted FAB scores exhibited a small correlation with clinically derived FAB scores (r = 0.13 Part A, r = 0.29 for Part B). Digitally derived features were also used to predict diagnosis (AUC of 0.65). Our findings indicate that the dTMT is capable of measuring the same aspects of cognition as the paper-based TMT. Furthermore, the dTMT's additional data may be able to help monitor other cognitive processes not captured by the paper-based TMT alone.

A new approach for crude oil price prediction based on stream learning

Directory of Open Access Journals (Sweden)

Shuang Gao

2017-01-01

Full Text Available Crude oil is the world's leading fuel, and its prices have a big impact on the global environment, economy as well as oil exploration and exploitation activities. Oil price forecasts are very useful to industries, governments and individuals. Although many methods have been developed for predicting oil prices, it remains one of the most challenging forecasting problems due to the high volatility of oil prices. In this paper, we propose a novel approach for crude oil price prediction based on a new machine learning paradigm called stream learning. The main advantage of our stream learning approach is that the prediction model can capture the changing pattern of oil prices since the model is continuously updated whenever new oil price data are available, with very small constant overhead. To evaluate the forecasting ability of our stream learning model, we compare it with three other popular oil price prediction models. The experiment results show that our stream learning model achieves the highest accuracy in terms of both mean squared prediction error and directional accuracy ratio over a variety of forecast time horizons.

Learning software testing with Test Studio

CERN Document Server

Madi, Rawane

2013-01-01

Learning Software Testing with Test Studio is a practical, hands-on guide that will help you get started with Test Studio to design your automated solution and tests. All through the book, there are best practices and tips and tricks inside Test Studio which can be employed to improve your solution just like an experienced QA.If you are a beginner or a professional QA who is seeking a fast, clear, and direct to the point start in automated software testing inside Test Studio, this book is for you. You should be familiar with the .NET framework, mainly Visual Studio, C#, and SQL, as the book's

Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System.

Science.gov (United States)

Kiral-Kornek, Isabell; Roy, Subhrajit; Nurse, Ewan; Mashford, Benjamin; Karoly, Philippa; Carroll, Thomas; Payne, Daniel; Saha, Susmita; Baldassano, Steven; O'Brien, Terence; Grayden, David; Cook, Mark; Freestone, Dean; Harrer, Stefan

2018-01-01

Seizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept for a seizure prediction system that is accurate, fully automated, patient-specific, and tunable to an individual's needs. Intracranial electroencephalography (iEEG) data of ten patients obtained from a seizure advisory system were analyzed as part of a pseudoprospective seizure prediction study. First, a deep learning classifier was trained to distinguish between preictal and interictal signals. Second, classifier performance was tested on held-out iEEG data from all patients and benchmarked against the performance of a random predictor. Third, the prediction system was tuned so sensitivity or time in warning could be prioritized by the patient. Finally, a demonstration of the feasibility of deployment of the prediction system onto an ultra-low power neuromorphic chip for autonomous operation on a wearable device is provided. The prediction system achieved mean sensitivity of 69% and mean time in warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%. This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance. Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

Early hospital mortality prediction of intensive care unit patients using an ensemble learning approach.

Science.gov (United States)

Awad, Aya; Bader-El-Den, Mohamed; McNicholas, James; Briggs, Jim

2017-12-01

Mortality prediction of hospitalized patients is an important problem. Over the past few decades, several severity scoring systems and machine learning mortality prediction models have been developed for predicting hospital mortality. By contrast, early mortality prediction for intensive care unit patients remains an open challenge. Most research has focused on severity of illness scoring systems or data mining (DM) models designed for risk estimation at least 24 or 48h after ICU admission. This study highlights the main data challenges in early mortality prediction in ICU patients and introduces a new machine learning based framework for Early Mortality Prediction for Intensive Care Unit patients (EMPICU). The proposed method is evaluated on the Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II) database. Mortality prediction models are developed for patients at the age of 16 or above in Medical ICU (MICU), Surgical ICU (SICU) or Cardiac Surgery Recovery Unit (CSRU). We employ the ensemble learning Random Forest (RF), the predictive Decision Trees (DT), the probabilistic Naive Bayes (NB) and the rule-based Projective Adaptive Resonance Theory (PART) models. The primary outcome was hospital mortality. The explanatory variables included demographic, physiological, vital signs and laboratory test variables. Performance measures were calculated using cross-validated area under the receiver operating characteristic curve (AUROC) to minimize bias. 11,722 patients with single ICU stays are considered. Only patients at the age of 16 years old and above in Medical ICU (MICU), Surgical ICU (SICU) or Cardiac Surgery Recovery Unit (CSRU) are considered in this study. The proposed EMPICU framework outperformed standard scoring systems (SOFA, SAPS-I, APACHE-II, NEWS and qSOFA) in terms of AUROC and time (i.e. at 6h compared to 48h or more after admission). The results show that although there are many values missing in the first few hour of ICU admission

DeepRT: deep learning for peptide retention time prediction in proteomics

OpenAIRE

Ma, Chunwei; Zhu, Zhiyong; Ye, Jun; Yang, Jiarui; Pei, Jianguo; Xu, Shaohang; Zhou, Ruo; Yu, Chang; Mo, Fan; Wen, Bo; Liu, Siqi

2017-01-01

Accurate predictions of peptide retention times (RT) in liquid chromatography have many applications in mass spectrometry-based proteomics. Herein, we present DeepRT, a deep learning based software for peptide retention time prediction. DeepRT automatically learns features directly from the peptide sequences using the deep convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) model, which eliminates the need to use hand-crafted features or rules. After the feature learning, pr...

Evaluating outcomes of computer-based classroom testing: Student acceptance and impact on learning and exam performance.

Science.gov (United States)

Zheng, Meixun; Bender, Daniel

2018-03-13

Computer-based testing (CBT) has made progress in health sciences education. In 2015, the authors led implementation of a CBT system (ExamSoft) at a dental school in the U.S. Guided by the Technology Acceptance Model (TAM), the purposes of this study were to (a) examine dental students' acceptance of ExamSoft; (b) understand factors impacting acceptance; and (c) evaluate the impact of ExamSoft on students' learning and exam performance. Survey and focus group data revealed that ExamSoft was well accepted by students as a testing tool and acknowledged by most for its potential to support learning. Regression analyses showed that perceived ease of use and perceived usefulness of ExamSoft significantly predicted student acceptance. Prior CBT experience and computer skills did not significantly predict acceptance of ExamSoft. Students reported that ExamSoft promoted learning in the first program year, primarily through timely and rich feedback on examination performance. t-Tests yielded mixed results on whether students performed better on computerized or paper examinations. The study contributes to the literature on CBT and the application of the TAM model in health sciences education. Findings also suggest ways in which health sciences institutions can implement CBT to maximize its potential as an assessment and learning tool.

Deep-Learning-Based Approach for Prediction of Algal Blooms

Directory of Open Access Journals (Sweden)

Feng Zhang

2016-10-01

Full Text Available Algal blooms have recently become a critical global environmental concern which might put economic development and sustainability at risk. However, the accurate prediction of algal blooms remains a challenging scientific problem. In this study, a novel prediction approach for algal blooms based on deep learning is presented—a powerful tool to represent and predict highly dynamic and complex phenomena. The proposed approach constructs a five-layered model to extract detailed relationships between the density of phytoplankton cells and various environmental parameters. The algal blooms can be predicted by the phytoplankton density obtained from the output layer. A case study is conducted in coastal waters of East China using both our model and a traditional back-propagation neural network for comparison. The results show that the deep-learning-based model yields better generalization and greater accuracy in predicting algal blooms than a traditional shallow neural network does.

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Directory of Open Access Journals (Sweden)

Saerom Park

Full Text Available Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

In Silico Prediction of Chemicals Binding to Aromatase with Machine Learning Methods.

Science.gov (United States)

Du, Hanwen; Cai, Yingchun; Yang, Hongbin; Zhang, Hongxiao; Xue, Yuhan; Liu, Guixia; Tang, Yun; Li, Weihua

2017-05-15

Environmental chemicals may affect endocrine systems through multiple mechanisms, one of which is via effects on aromatase (also known as CYP19A1), an enzyme critical for maintaining the normal balance of estrogens and androgens in the body. Therefore, rapid and efficient identification of aromatase-related endocrine disrupting chemicals (EDCs) is important for toxicology and environment risk assessment. In this study, on the basis of the Tox21 10K compound library, in silico classification models for predicting aromatase binders/nonbinders were constructed by machine learning methods. To improve the prediction ability of the models, a combined classifier (CC) strategy that combines different independent machine learning methods was adopted. Performances of the models were measured by test and external validation sets containing 1336 and 216 chemicals, respectively. The best model was obtained with the MACCS (Molecular Access System) fingerprint and CC method, which exhibited an accuracy of 0.84 for the test set and 0.91 for the external validation set. Additionally, several representative substructures for characterizing aromatase binders, such as ketone, lactone, and nitrogen-containing derivatives, were identified using information gain and substructure frequency analysis. Our study provided a systematic assessment of chemicals binding to aromatase. The built models can be helpful to rapidly identify potential EDCs targeting aromatase.

Students' views of cooperative learning and group testing.

Science.gov (United States)

Hicks, Jay

2007-01-01

Today's radiologic technology students must learn to collaborate and communicate to function as part of the health care team. Innovative educational techniques such as cooperative learning (working collectively in small groups) and group testing (collaborating on tests) can foster these skills. Assess students' familiarity with and opinions about cooperative learning and group testing before and after participation in a semester-long course incorporating these methods. Twenty-eight students enrolled in a baccalaureate-level radiologic technology program in Louisiana were surveyed at the beginning and end of the semester. Results showed that students were more knowledgeable about and more accepting of cooperative learning and group testing after participating in the course. However, some students continued to prefer independent learning. Students are open to new learning methods such as cooperative learning and group testing. These techniques can help them develop the skills they will need to function collaboratively in the workplace.

ComplexContact: a web server for inter-protein contact prediction using deep learning

KAUST Repository

Zeng, Hong; Wang, Sheng; Zhou, Tianming; Zhao, Feifeng; Li, Xiufeng; Wu, Qing; Xu, Jinbo

2018-01-01

ComplexContact (http://raptorx2.uchicago.edu/ComplexContact/) is a web server for sequence-based interfacial residue-residue contact prediction of a putative protein complex. Interfacial residue-residue contacts are critical for understanding how proteins form complex and interact at residue level. When receiving a pair of protein sequences, ComplexContact first searches for their sequence homologs and builds two paired multiple sequence alignments (MSA), then it applies co-evolution analysis and a CASP-winning deep learning (DL) method to predict interfacial contacts from paired MSAs and visualizes the prediction as an image. The DL method was originally developed for intra-protein contact prediction and performed the best in CASP12. Our large-scale experimental test further shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.

ComplexContact: a web server for inter-protein contact prediction using deep learning

KAUST Repository

Zeng, Hong

2018-05-20

ComplexContact (http://raptorx2.uchicago.edu/ComplexContact/) is a web server for sequence-based interfacial residue-residue contact prediction of a putative protein complex. Interfacial residue-residue contacts are critical for understanding how proteins form complex and interact at residue level. When receiving a pair of protein sequences, ComplexContact first searches for their sequence homologs and builds two paired multiple sequence alignments (MSA), then it applies co-evolution analysis and a CASP-winning deep learning (DL) method to predict interfacial contacts from paired MSAs and visualizes the prediction as an image. The DL method was originally developed for intra-protein contact prediction and performed the best in CASP12. Our large-scale experimental test further shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.

ComplexContact: a web server for inter-protein contact prediction using deep learning.

Science.gov (United States)

Zeng, Hong; Wang, Sheng; Zhou, Tianming; Zhao, Feifeng; Li, Xiufeng; Wu, Qing; Xu, Jinbo

2018-05-22

ComplexContact (http://raptorx2.uchicago.edu/ComplexContact/) is a web server for sequence-based interfacial residue-residue contact prediction of a putative protein complex. Interfacial residue-residue contacts are critical for understanding how proteins form complex and interact at residue level. When receiving a pair of protein sequences, ComplexContact first searches for their sequence homologs and builds two paired multiple sequence alignments (MSA), then it applies co-evolution analysis and a CASP-winning deep learning (DL) method to predict interfacial contacts from paired MSAs and visualizes the prediction as an image. The DL method was originally developed for intra-protein contact prediction and performed the best in CASP12. Our large-scale experimental test further shows that ComplexContact greatly outperforms pure co-evolution methods for inter-protein contact prediction, regardless of the species.

Surprised at all the entropy: hippocampal, caudate and midbrain contributions to learning from prediction errors.

Directory of Open Access Journals (Sweden)

Anne-Marike Schiffer

Full Text Available Influential concepts in neuroscientific research cast the brain a predictive machine that revises its predictions when they are violated by sensory input. This relates to the predictive coding account of perception, but also to learning. Learning from prediction errors has been suggested for take place in the hippocampal memory system as well as in the basal ganglia. The present fMRI study used an action-observation paradigm to investigate the contributions of the hippocampus, caudate nucleus and midbrain dopaminergic system to different types of learning: learning in the absence of prediction errors, learning from prediction errors, and responding to the accumulation of prediction errors in unpredictable stimulus configurations. We conducted analyses of the regions of interests' BOLD response towards these different types of learning, implementing a bootstrapping procedure to correct for false positives. We found both, caudate nucleus and the hippocampus to be activated by perceptual prediction errors. The hippocampal responses seemed to relate to the associative mismatch between a stored representation and current sensory input. Moreover, its response was significantly influenced by the average information, or Shannon entropy of the stimulus material. In accordance with earlier results, the habenula was activated by perceptual prediction errors. Lastly, we found that the substantia nigra was activated by the novelty of sensory input. In sum, we established that the midbrain dopaminergic system, the hippocampus, and the caudate nucleus were to different degrees significantly involved in the three different types of learning: acquisition of new information, learning from prediction errors and responding to unpredictable stimulus developments. We relate learning from perceptual prediction errors to the concept of predictive coding and related information theoretic accounts.

Surprised at all the entropy: hippocampal, caudate and midbrain contributions to learning from prediction errors.

Science.gov (United States)

Schiffer, Anne-Marike; Ahlheim, Christiane; Wurm, Moritz F; Schubotz, Ricarda I

2012-01-01

Influential concepts in neuroscientific research cast the brain a predictive machine that revises its predictions when they are violated by sensory input. This relates to the predictive coding account of perception, but also to learning. Learning from prediction errors has been suggested for take place in the hippocampal memory system as well as in the basal ganglia. The present fMRI study used an action-observation paradigm to investigate the contributions of the hippocampus, caudate nucleus and midbrain dopaminergic system to different types of learning: learning in the absence of prediction errors, learning from prediction errors, and responding to the accumulation of prediction errors in unpredictable stimulus configurations. We conducted analyses of the regions of interests' BOLD response towards these different types of learning, implementing a bootstrapping procedure to correct for false positives. We found both, caudate nucleus and the hippocampus to be activated by perceptual prediction errors. The hippocampal responses seemed to relate to the associative mismatch between a stored representation and current sensory input. Moreover, its response was significantly influenced by the average information, or Shannon entropy of the stimulus material. In accordance with earlier results, the habenula was activated by perceptual prediction errors. Lastly, we found that the substantia nigra was activated by the novelty of sensory input. In sum, we established that the midbrain dopaminergic system, the hippocampus, and the caudate nucleus were to different degrees significantly involved in the three different types of learning: acquisition of new information, learning from prediction errors and responding to unpredictable stimulus developments. We relate learning from perceptual prediction errors to the concept of predictive coding and related information theoretic accounts.

Physiognomy: Personality Traits Prediction by Learning

Institute of Scientific and Technical Information of China (English)

Ting Zhang; Ri-Zhen Qin; Qiu-Lei Dong; Wei Gao; Hua-Rong Xu; Zhan-Yi Hu

2017-01-01

Evaluating individuals' personality traits and intelligence from their faces plays a crucial role in interpersonal relationship and important social events such as elections and court sentences.To assess the possible correlations between personality traits (also measured intelligence) and face images,we first construct a dataset consisting of face photographs,personality measurements,and intelligence measurements.Then,we build an end-to-end convolutional neural network for prediction of personality traits and intelligence to investigate whether self-reported personality traits and intelligence can be predicted reliably from a face image.To our knowledge,it is the first work where deep learning is applied to this problem.Experimental results show the following three points:1)"Rule-consciousness" and "Tension" can be reliably predicted from face images.2) It is difficult,if not impossible,to predict intelligence from face images,a finding in accord with previous studies.3) Convolutional neural network (CNN) features outperform traditional handcrafted features in predicting traits.

Exploration of Machine Learning Approaches to Predict Pavement Performance

Science.gov (United States)

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...

Evaluation of Machine Learning and Rules-Based Approaches for Predicting Antimicrobial Resistance Profiles in Gram-negative Bacilli from Whole Genome Sequence Data.

Science.gov (United States)

Pesesky, Mitchell W; Hussain, Tahir; Wallace, Meghan; Patel, Sanket; Andleeb, Saadia; Burnham, Carey-Ann D; Dantas, Gautam

2016-01-01

The time-to-result for culture-based microorganism recovery and phenotypic antimicrobial susceptibility testing necessitates initial use of empiric (frequently broad-spectrum) antimicrobial therapy. If the empiric therapy is not optimal, this can lead to adverse patient outcomes and contribute to increasing antibiotic resistance in pathogens. New, more rapid technologies are emerging to meet this need. Many of these are based on identifying resistance genes, rather than directly assaying resistance phenotypes, and thus require interpretation to translate the genotype into treatment recommendations. These interpretations, like other parts of clinical diagnostic workflows, are likely to be increasingly automated in the future. We set out to evaluate the two major approaches that could be amenable to automation pipelines: rules-based methods and machine learning methods. The rules-based algorithm makes predictions based upon current, curated knowledge of Enterobacteriaceae resistance genes. The machine-learning algorithm predicts resistance and susceptibility based on a model built from a training set of variably resistant isolates. As our test set, we used whole genome sequence data from 78 clinical Enterobacteriaceae isolates, previously identified to represent a variety of phenotypes, from fully-susceptible to pan-resistant strains for the antibiotics tested. We tested three antibiotic resistance determinant databases for their utility in identifying the complete resistome for each isolate. The predictions of the rules-based and machine learning algorithms for these isolates were compared to results of phenotype-based diagnostics. The rules based and machine-learning predictions achieved agreement with standard-of-care phenotypic diagnostics of 89.0 and 90.3%, respectively, across twelve antibiotic agents from six major antibiotic classes. Several sources of disagreement between the algorithms were identified. Novel variants of known resistance factors and

Evaluation of Machine Learning and Rules-Based Approaches for Predicting Antimicrobial Resistance Profiles in Gram-negative Bacilli from Whole Genome Sequence Data

Directory of Open Access Journals (Sweden)

Mitchell Pesesky

2016-11-01

Full Text Available The time-to-result for culture-based microorganism recovery and phenotypic antimicrobial susceptibility testing necessitate initial use of empiric (frequently broad-spectrum antimicrobial therapy. If the empiric therapy is not optimal, this can lead to adverse patient outcomes and contribute to increasing antibiotic resistance in pathogens. New, more rapid technologies are emerging to meet this need. Many of these are based on identifying resistance genes, rather than directly assaying resistance phenotypes, and thus require interpretation to translate the genotype into treatment recommendations. These interpretations, like other parts of clinical diagnostic workflows, are likely to be increasingly automated in the future. We set out to evaluate the two major approaches that could be amenable to automation pipelines: rules-based methods and machine learning methods. The rules-based algorithm makes predictions based upon current, curated knowledge of Enterobacteriaceae resistance genes. The machine-learning algorithm predicts resistance and susceptibility based on a model built from a training set of variably resistant isolates. As our test set, we used whole genome sequence data from 78 clinical Enterobacteriaceae isolates, previously identified to represent a variety of phenotypes, from fully-susceptible to pan-resistant strains for the antibiotics tested. We tested three antibiotic resistance determinant databases for their utility in identifying the complete resistome for each isolate. The predictions of the rules-based and machine learning algorithms for these isolates were compared to results of phenotype-based diagnostics. The rules based and machine-learning predictions achieved agreement with standard-of-care phenotypic diagnostics of 89.0% and 90.3%, respectively, across twelve antibiotic agents from six major antibiotic classes. Several sources of disagreement between the algorithms were identified. Novel variants of known resistance

Machine learning for predicting soil classes in three semi-arid landscapes

Science.gov (United States)

Brungard, Colby W.; Boettinger, Janis L.; Duniway, Michael C.; Wills, Skye A.; Edwards, Thomas C.

2015-01-01

Mapping the spatial distribution of soil taxonomic classes is important for informing soil use and management decisions. Digital soil mapping (DSM) can quantitatively predict the spatial distribution of soil taxonomic classes. Key components of DSM are the method and the set of environmental covariates used to predict soil classes. Machine learning is a general term for a broad set of statistical modeling techniques. Many different machine learning models have been applied in the literature and there are different approaches for selecting covariates for DSM. However, there is little guidance as to which, if any, machine learning model and covariate set might be optimal for predicting soil classes across different landscapes. Our objective was to compare multiple machine learning models and covariate sets for predicting soil taxonomic classes at three geographically distinct areas in the semi-arid western United States of America (southern New Mexico, southwestern Utah, and northeastern Wyoming). All three areas were the focus of digital soil mapping studies. Sampling sites at each study area were selected using conditioned Latin hypercube sampling (cLHS). We compared models that had been used in other DSM studies, including clustering algorithms, discriminant analysis, multinomial logistic regression, neural networks, tree based methods, and support vector machine classifiers. Tested machine learning models were divided into three groups based on model complexity: simple, moderate, and complex. We also compared environmental covariates derived from digital elevation models and Landsat imagery that were divided into three different sets: 1) covariates selected a priori by soil scientists familiar with each area and used as input into cLHS, 2) the covariates in set 1 plus 113 additional covariates, and 3) covariates selected using recursive feature elimination. Overall, complex models were consistently more accurate than simple or moderately complex models. Random

Learning Behavior Models for Interpreting and Predicting Traffic Situations

OpenAIRE

Gindele, Tobias

2014-01-01

In this thesis, we present Bayesian state estimation and machine learning methods for predicting traffic situations. The cognitive ability to assess situations and behaviors of traffic participants, and to anticipate possible developments is an essential requirement for several applications in the traffic domain, especially for self-driving cars. We present a method for learning behavior models from unlabeled traffic observations and develop improved learning methods for decision trees.

Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method

Directory of Open Access Journals (Sweden)

Yuhan Jia

2017-01-01

Full Text Available Accurate traffic flow prediction is increasingly essential for successful traffic modeling, operation, and management. Traditional data driven traffic flow prediction approaches have largely assumed restrictive (shallow model architectures and do not leverage the large amount of environmental data available. Inspired by deep learning methods with more complex model architectures and effective data mining capabilities, this paper introduces the deep belief network (DBN and long short-term memory (LSTM to predict urban traffic flow considering the impact of rainfall. The rainfall-integrated DBN and LSTM can learn the features of traffic flow under various rainfall scenarios. Experimental results indicate that, with the consideration of additional rainfall factor, the deep learning predictors have better accuracy than existing predictors and also yield improvements over the original deep learning models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time series characteristics of traffic flow data.

Hebbian Learning is about contingency, not contiguity, and explains the emergence of predictive mirror neurons.

Science.gov (United States)

Keysers, Christian; Perrett, David I; Gazzola, Valeria

2014-04-01

Hebbian Learning should not be reduced to contiguity, as it detects contingency and causality. Hebbian Learning accounts of mirror neurons make predictions that differ from associative learning: Through Hebbian Learning, mirror neurons become dynamic networks that calculate predictions and prediction errors and relate to ideomotor theories. The social force of imitation is important for mirror neuron emergence and suggests canalization.

Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

Science.gov (United States)

Nishizuka, N.; Sugiura, K.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.

2017-02-01

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010-2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions (ARs) from the full-disk magnetogram, from which ˜60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.

Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

International Nuclear Information System (INIS)

Nishizuka, N.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M.; Sugiura, K.

2017-01-01

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite . We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.

Solar Flare Prediction Model with Three Machine-learning Algorithms using Ultraviolet Brightening and Vector Magnetograms

Energy Technology Data Exchange (ETDEWEB)

Nishizuka, N.; Kubo, Y.; Den, M.; Watari, S.; Ishii, M. [Applied Electromagnetic Research Institute, National Institute of Information and Communications Technology, 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795 (Japan); Sugiura, K., E-mail: nishizuka.naoto@nict.go.jp [Advanced Speech Translation Research and Development Promotion Center, National Institute of Information and Communications Technology (Japan)

2017-02-01

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010–2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite . We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.

An initial investigation on developing a new method to predict short-term breast cancer risk based on deep learning technology

Science.gov (United States)

Qiu, Yuchen; Wang, Yunzhi; Yan, Shiju; Tan, Maxine; Cheng, Samuel; Liu, Hong; Zheng, Bin

2016-03-01

In order to establish a new personalized breast cancer screening paradigm, it is critically important to accurately predict the short-term risk of a woman having image-detectable cancer after a negative mammographic screening. In this study, we developed and tested a novel short-term risk assessment model based on deep learning method. During the experiment, a number of 270 "prior" negative screening cases was assembled. In the next sequential ("current") screening mammography, 135 cases were positive and 135 cases remained negative. These cases were randomly divided into a training set with 200 cases and a testing set with 70 cases. A deep learning based computer-aided diagnosis (CAD) scheme was then developed for the risk assessment, which consists of two modules: adaptive feature identification module and risk prediction module. The adaptive feature identification module is composed of three pairs of convolution-max-pooling layers, which contains 20, 10, and 5 feature maps respectively. The risk prediction module is implemented by a multiple layer perception (MLP) classifier, which produces a risk score to predict the likelihood of the woman developing short-term mammography-detectable cancer. The result shows that the new CAD-based risk model yielded a positive predictive value of 69.2% and a negative predictive value of 74.2%, with a total prediction accuracy of 71.4%. This study demonstrated that applying a new deep learning technology may have significant potential to develop a new short-term risk predicting scheme with improved performance in detecting early abnormal symptom from the negative mammograms.

Prediction of Bispectral Index during Target-controlled Infusion of Propofol and Remifentanil: A Deep Learning Approach.

Science.gov (United States)

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 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.

Cognitive Learning Strategy as a Partial Effect on Major Field Test in Business Results

Science.gov (United States)

Strang, Kenneth David

2014-01-01

An experiment was developed to determine if cognitive learning strategies improved standardized university business exam results. Previous studies revealed that factors such as prior ability, age, gender, and culture predicted a student's Major Field Test in Business (MFTB) score better than course content. The experiment control consisted of…

A Symbiotic Framework for coupling Machine Learning and Geosciences in Prediction and Predictability

Science.gov (United States)

Ravela, S.

2017-12-01

In this presentation we review the two directions of a symbiotic relationship between machine learning and the geosciences in relation to prediction and predictability. In the first direction, we develop ensemble, information theoretic and manifold learning framework to adaptively improve state and parameter estimates in nonlinear high-dimensional non-Gaussian problems, showing in particular that tractable variational approaches can be produced. We demonstrate these applications in the context of autonomous mapping of environmental coherent structures and other idealized problems. In the reverse direction, we show that data assimilation, particularly probabilistic approaches for filtering and smoothing offer a novel and useful way to train neural networks, and serve as a better basis than gradient based approaches when we must quantify uncertainty in association with nonlinear, chaotic processes. In many inference problems in geosciences we seek to build reduced models to characterize local sensitivies, adjoints or other mechanisms that propagate innovations and errors. Here, the particular use of neural approaches for such propagation trained using ensemble data assimilation provides a novel framework. Through these two examples of inference problems in the earth sciences, we show that not only is learning useful to broaden existing methodology, but in reverse, geophysical methodology can be used to influence paradigms in learning.

Predicting the dissolution kinetics of silicate glasses using machine learning

Science.gov (United States)

Anoop Krishnan, N. M.; Mangalathu, Sujith; Smedskjaer, Morten M.; Tandia, Adama; Burton, Henry; Bauchy, Mathieu

2018-05-01

Predicting the dissolution rates of silicate glasses in aqueous conditions is a complex task as the underlying mechanism(s) remain poorly understood and the dissolution kinetics can depend on a large number of intrinsic and extrinsic factors. Here, we assess the potential of data-driven models based on machine learning to predict the dissolution rates of various aluminosilicate glasses exposed to a wide range of solution pH values, from acidic to caustic conditions. Four classes of machine learning methods are investigated, namely, linear regression, support vector machine regression, random forest, and artificial neural network. We observe that, although linear methods all fail to describe the dissolution kinetics, the artificial neural network approach offers excellent predictions, thanks to its inherent ability to handle non-linear data. Overall, we suggest that a more extensive use of machine learning approaches could significantly accelerate the design of novel glasses with tailored properties.

Hebbian Learning is about contingency, not contiguity, and explains the emergence of predictive mirror neurons

NARCIS (Netherlands)

Keysers, C.; Perrett, David I; Gazzola, Valeria

Hebbian Learning should not be reduced to contiguity, as it detects contingency and causality. Hebbian Learning accounts of mirror neurons make predictions that differ from associative learning: Through Hebbian Learning, mirror neurons become dynamic networks that calculate predictions and

Roles of dopamine neurons in mediating the prediction error in aversive learning in insects.

Science.gov (United States)

Terao, Kanta; Mizunami, Makoto

2017-10-31

In associative learning in mammals, it is widely accepted that the discrepancy, or error, between actual and predicted reward determines whether learning occurs. The prediction error theory has been proposed to account for the finding of a blocking phenomenon, in which pairing of a stimulus X with an unconditioned stimulus (US) could block subsequent association of a second stimulus Y to the US when the two stimuli were paired in compound with the same US. Evidence for this theory, however, has been imperfect since blocking can also be accounted for by competitive theories. We recently reported blocking in classical conditioning of an odor with water reward in crickets. We also reported an "auto-blocking" phenomenon in appetitive learning, which supported the prediction error theory and rejected alternative theories. The presence of auto-blocking also suggested that octopamine neurons mediate reward prediction error signals. Here we show that blocking and auto-blocking occur in aversive learning to associate an odor with salt water (US) in crickets, and our results suggest that dopamine neurons mediate aversive prediction error signals. We conclude that the prediction error theory is applicable to both appetitive learning and aversive learning in insects.

Hebbian Learning is about contingency, not contiguity, and explains the emergence of predictive mirror neurons

OpenAIRE

Keysers, C.; Perrett, D.I.; Gazzola, V.

2014-01-01

Hebbian Learning should not be reduced to contiguity, as it detects contingency and causality. Hebbian Learning accounts of mirror neurons make predictions that differ from associative learning: Through Hebbian Learning, mirror neurons become dynamic networks that calculate predictions and prediction errors and relate to ideomotor theories. The social force of imitation is important for mirror neuron emergence and suggests canalization. Publisher PDF Peer reviewed

A Model for Predicting Learning Flow and Achievement in Corporate e-Learning

Science.gov (United States)

Joo, Young Ju; Lim, Kyu Yon; Kim, Su Mi

2012-01-01

The primary objective of this study was to investigate the determinants of learning flow and achievement in corporate online training. Self-efficacy, intrinsic value, and test anxiety were selected as learners' motivational factors, while perceived usefulness and ease of use were also selected as learning environmental factors. Learning flow was…

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

Science.gov (United States)

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 persistent post-surgery pain by preoperative cold pain sensitivity: biomarker development with machine-learning-derived analysis.

Science.gov (United States)

Lötsch, J; Ultsch, A; Kalso, E

2017-10-01

To prevent persistent post-surgery pain, early identification of patients at high risk is a clinical need. Supervised machine-learning techniques were used to test how accurately the patients' performance in a preoperatively performed tonic cold pain test could predict persistent post-surgery pain. We analysed 763 patients from a cohort of 900 women who were treated for breast cancer, of whom 61 patients had developed signs of persistent pain during three yr of follow-up. Preoperatively, all patients underwent a cold pain test (immersion of the hand into a water bath at 2-4 °C). The patients rated the pain intensity using a numerical ratings scale (NRS) from 0 to 10. Supervised machine-learning techniques were used to construct a classifier that could predict patients at risk of persistent pain. Whether or not a patient rated the pain intensity at NRS=10 within less than 45 s during the cold water immersion test provided a negative predictive value of 94.4% to assign a patient to the "persistent pain" group. If NRS=10 was never reached during the cold test, the predictive value for not developing persistent pain was almost 97%. However, a low negative predictive value of 10% implied a high false positive rate. Results provide a robust exclusion of persistent pain in women with an accuracy of 94.4%. Moreover, results provide further support for the hypothesis that the endogenous pain inhibitory system may play an important role in the process of pain becoming persistent. © The Author 2017. Published by Oxford University Press on behalf of the British Journal of Anaesthesia.

Implicit Learning Abilities Predict Treatment Response in Autism Spectrum Disorders

Science.gov (United States)

2015-09-01

early behavioral interventions are the most effective treatment for Autism Spectrum Disorder (ASD), but almost half of the children do not make...behavioral intervention . 2. KEYWORDS Autism Spectrum Disorder , implicit learning, associative learning, individual differences, functional Magnetic...2 AWARD NUMBER: W81XWH-14-1-0261 TITLE: Implicit Learning Abilities Predict Treatment Response in Autism Spectrum Disorders PRINCIPAL

Is Romantic Desire Predictable? Machine Learning Applied to Initial Romantic Attraction.

Science.gov (United States)

Joel, Samantha; Eastwick, Paul W; Finkel, Eli J

2017-10-01

Matchmaking companies and theoretical perspectives on close relationships suggest that initial attraction is, to some extent, a product of two people's self-reported traits and preferences. We used machine learning to test how well such measures predict people's overall tendencies to romantically desire other people (actor variance) and to be desired by other people (partner variance), as well as people's desire for specific partners above and beyond actor and partner variance (relationship variance). In two speed-dating studies, romantically unattached individuals completed more than 100 self-report measures about traits and preferences that past researchers have identified as being relevant to mate selection. Each participant met each opposite-sex participant attending a speed-dating event for a 4-min speed date. Random forests models predicted 4% to 18% of actor variance and 7% to 27% of partner variance; crucially, however, they were unable to predict relationship variance using any combination of traits and preferences reported before the dates. These results suggest that compatibility elements of human mating are challenging to predict before two people meet.

Improving students' meaningful learning on the predictive nature of quantum mechanics

Directory of Open Access Journals (Sweden)

Rodolfo Alves de Carvalho Neto

2009-03-01

Full Text Available This paper deals with research about teaching quantum mechanics to 3rd year high school students and their meaningful learning of its predictive aspect; it is based on the Master’s dissertation of one of the authors (CARVALHO NETO, 2006. While teaching quantum mechanics, we emphasized its predictive and essentially probabilistic nature, based on Niels Bohr’s complementarity interpretation (BOHR, 1958. In this context, we have discussed the possibility of predicting measurement results in well-defined experimental contexts, even for individual events. Interviews with students reveal that they have used quantum mechanical ideas, suggesting their meaningful learning of the essentially probabilistic predictions of quantum mechanics.

The use of machine learning and nonlinear statistical tools for ADME prediction.

Science.gov (United States)

Sakiyama, Yojiro

2009-02-01

Absorption, distribution, metabolism and excretion (ADME)-related failure of drug candidates is a major issue for the pharmaceutical industry today. Prediction of ADME by in silico tools has now become an inevitable paradigm to reduce cost and enhance efficiency in pharmaceutical research. Recently, machine learning as well as nonlinear statistical tools has been widely applied to predict routine ADME end points. To achieve accurate and reliable predictions, it would be a prerequisite to understand the concepts, mechanisms and limitations of these tools. Here, we have devised a small synthetic nonlinear data set to help understand the mechanism of machine learning by 2D-visualisation. We applied six new machine learning methods to four different data sets. The methods include Naive Bayes classifier, classification and regression tree, random forest, Gaussian process, support vector machine and k nearest neighbour. The results demonstrated that ensemble learning and kernel machine displayed greater accuracy of prediction than classical methods irrespective of the data set size. The importance of interaction with the engineering field is also addressed. The results described here provide insights into the mechanism of machine learning, which will enable appropriate usage in the future.

Are traditional cognitive tests useful in predicting clinical success?

Science.gov (United States)

Gray, Sarah A; Deem, Lisa P; Straja, Sorin R

2002-11-01

The purpose of this research was to determine the predictive value of the Dental Admission Test (DAT) for clinical success using Ackerman's theory of ability determinants of skilled performance. The Ackerman theory is a valid, reliable schema in the applied psychology literature used to predict complex skill acquisition. Inconsistent stimulus-response skill acquisition depends primarily on determinants of cognitive ability. Consistent information-processing tasks have been described as "automatic," in which stimuli and responses are mapped in a manner that allows for complete certainty once the relationships have been learned. It is theorized that the skills necessary for success in the clinical component of dental schools involve a significant amount of automatic processing demands and, as such, student performance in the clinics should begin to converge as task practice is realized and tasks become more consistent. Subtest scores of the DAT of four classes were correlated with final grades in nine clinical courses. Results showed that the DAT subtest scores played virtually no role with regard to the final clinical grades. Based on this information, the DAT scores were determined to be of no predictive value in clinical achievement.

Predicting Knowledge Workers' Participation in Voluntary Learning with Employee Characteristics and Online Learning Tools

Science.gov (United States)

Hicks, Catherine

2018-01-01

Purpose: This paper aims to explore predicting employee learning activity via employee characteristics and usage for two online learning tools. Design/methodology/approach: Statistical analysis focused on observational data collected from user logs. Data are analyzed via regression models. Findings: Findings are presented for over 40,000…

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies.

Science.gov (United States)

Huang, Cai; Mezencev, Roman; McDonald, John F; Vannberg, Fredrik

2017-01-01

Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be "drivers" of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm "open source", we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies.

Directory of Open Access Journals (Sweden)

Cai Huang

Full Text Available Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM algorithm combined with a standard recursive feature elimination (RFE approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60. The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be "drivers" of cancer onset/progression. Application of our models to publically available ovarian cancer (OC patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm "open source", we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.

Machine learning derived risk prediction of anorexia nervosa.

Science.gov (United States)

Guo, Yiran; Wei, Zhi; Keating, Brendan J; Hakonarson, Hakon

2016-01-20

Anorexia nervosa (AN) is a complex psychiatric disease with a moderate to strong genetic contribution. In addition to conventional genome wide association (GWA) studies, researchers have been using machine learning methods in conjunction with genomic data to predict risk of diseases in which genetics play an important role. In this study, we collected whole genome genotyping data on 3940 AN cases and 9266 controls from the Genetic Consortium for Anorexia Nervosa (GCAN), the Wellcome Trust Case Control Consortium 3 (WTCCC3), Price Foundation Collaborative Group and the Children's Hospital of Philadelphia (CHOP), and applied machine learning methods for predicting AN disease risk. The prediction performance is measured by area under the receiver operating characteristic curve (AUC), indicating how well the model distinguishes cases from unaffected control subjects. Logistic regression model with the lasso penalty technique generated an AUC of 0.693, while Support Vector Machines and Gradient Boosted Trees reached AUC's of 0.691 and 0.623, respectively. Using different sample sizes, our results suggest that larger datasets are required to optimize the machine learning models and achieve higher AUC values. To our knowledge, this is the first attempt to assess AN risk based on genome wide genotype level data. Future integration of genomic, environmental and family-based information is likely to improve the AN risk evaluation process, eventually benefitting AN patients and families in the clinical setting.

Theory of mind selectively predicts preschoolers' knowledge-based selective word learning.

Science.gov (United States)

Brosseau-Liard, Patricia; Penney, Danielle; Poulin-Dubois, Diane

2015-11-01

Children can selectively attend to various attributes of a model, such as past accuracy or physical strength, to guide their social learning. There is a debate regarding whether a relation exists between theory-of-mind skills and selective learning. We hypothesized that high performance on theory-of-mind tasks would predict preference for learning new words from accurate informants (an epistemic attribute), but not from physically strong informants (a non-epistemic attribute). Three- and 4-year-olds (N = 65) completed two selective learning tasks, and their theory-of-mind abilities were assessed. As expected, performance on a theory-of-mind battery predicted children's preference to learn from more accurate informants but not from physically stronger informants. Results thus suggest that preschoolers with more advanced theory of mind have a better understanding of knowledge and apply that understanding to guide their selection of informants. This work has important implications for research on children's developing social cognition and early learning. © 2015 The British Psychological Society.

Theory of mind selectively predicts preschoolers’ knowledge-based selective word learning

Science.gov (United States)

Brosseau-Liard, Patricia; Penney, Danielle; Poulin-Dubois, Diane

2015-01-01

Children can selectively attend to various attributes of a model, such as past accuracy or physical strength, to guide their social learning. There is a debate regarding whether a relation exists between theory-of-mind skills and selective learning. We hypothesized that high performance on theory-of-mind tasks would predict preference for learning new words from accurate informants (an epistemic attribute), but not from physically strong informants (a non-epistemic attribute). Three- and 4-year-olds (N = 65) completed two selective learning tasks, and their theory of mind abilities were assessed. As expected, performance on a theory-of-mind battery predicted children’s preference to learn from more accurate informants but not from physically stronger informants. Results thus suggest that preschoolers with more advanced theory of mind have a better understanding of knowledge and apply that understanding to guide their selection of informants. This work has important implications for research on children’s developing social cognition and early learning. PMID:26211504

Role of Personality Traits, Learning Styles and Metacognition in Predicting Critical Thinking of Undergraduate Students

Directory of Open Access Journals (Sweden)

Soliemanifar O

2015-04-01

The aim of this study was to investigate the role of personality traits, learning styles and metacognition in predicting critical thinking. Instrument & Methods: In this descriptive correlative study, 240 students (130 girls and 110 boys of Ahvaz Shahid Chamran University were selected by multi-stage random sampling method. The instruments for collecting data were NEO Five-Factor Inventory, learning style inventory of Kolb (LSI, metacognitive assessment inventory (MAI of Schraw & Dennison (1994 and California Critical Thinking Skills Test (CCTST. The data were analyzed using Pearson correlation coefficient, stepwise regression analysis and Canonical correlation analysis.  Findings: Openness to experiment (b=0.41, conscientiousness (b=0.28, abstract conceptualization (b=0.39, active experimentation (b=0.22, reflective observation (b=0.12, knowledge of cognition (b=0.47 and regulation of cognition (b=0.29 were effective in predicting critical thinking. Openness to experiment and conscientiousness (r2=0.25, active experimentation, abstract conceptualization and reflective observation learning styles (r2=0.21 and knowledge and regulation of cognition metacognitions (r2=0.3 had an important role in explaining critical thinking. The linear combination of critical thinking skills (evaluation, analysis, inference was predictable by a linear combination of dispositional-cognitive factors (openness, conscientiousness, abstract conceptualization, active experimentation, knowledge of cognition and regulation of cognition. Conclusion: Personality traits, learning styles and metacognition, as dispositional-cognitive factors, play a significant role in students' critical thinking.

The Prediction of Yarn Elongation of Kenyan Ring-Spun Yarn using Extreme Learning Machines (ELM

Directory of Open Access Journals (Sweden)

Josphat Igadwa Mwasiagi

2017-03-01

Full Text Available The optimization of the manufacture of cotton yarns involves several processes, while the prediction of yarn quality parameters forms an important area of investigation. This research work concentrated on the prediction of cotton yarn elongation. Cotton lint and yarn samples were collected in textile factories in Kenya.The collected samples were tested under standard testing conditions. Cotton lint parameters, machine parameters and yarn elongation were used to design yarn elongation prediction models. The elongation prediction models used three network training algorithms, including backpropagation (BP, an extreme learning machine (ELM, and a hybrid of differential evolution (DE and an ELM referred to as DE-ELM. The prediction models recorded a mean squared error (mse value of 0.001 using 11, 43 and 2 neurons in the hidden layer for the BP, ELM and DE-ELM models respectively. The ELM models exhibited faster training speeds than the BP algorithms, but required more neurons in the hidden layer than other models. The DEELM hybrid algorithm was faster than the BP algorithm, but slower than the ELM algorithm.

Effectiveness of Cooperative Learning Instructional Tools With Predict-Observe-Explain Strategy on the Topic of Cuboid and Cube Volume

Science.gov (United States)

Nurhuda; Lukito, A.; Masriyah

2018-01-01

This study aims to develop instructional tools and implement it to see the effectiveness. The method used in this research referred to Designing Effective Instruction. Experimental research with two-group pretest-posttest design method was conducted. The instructional tools have been developed is cooperative learning model with predict-observe-explain strategy on the topic of cuboid and cube volume which consist of lesson plans, POE tasks, and Tests. Instructional tools were of good quality by criteria of validity, practicality, and effectiveness. These instructional tools was very effective for teaching the volume of cuboid and cube. Cooperative instructional tool with predict-observe-explain (POE) strategy was good of quality because the teacher was easy to implement the steps of learning, students easy to understand the material and students’ learning outcomes completed classically. Learning by using this instructional tool was effective because learning activities were appropriate and students were very active. Students’ learning outcomes were completed classically and better than conventional learning. This study produced a good instructional tool and effectively used in learning. Therefore, these instructional tools can be used as an alternative to teach volume of cuboid and cube topics.

Multi-Label Learning via Random Label Selection for Protein Subcellular Multi-Locations Prediction.

Science.gov (United States)

Wang, Xiao; Li, Guo-Zheng

2013-03-12

Prediction of protein subcellular localization is an important but challenging problem, particularly when proteins may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular localization methods are only used to deal with the single-location proteins. In the past few years, only a few methods have been proposed to tackle proteins with multiple locations. However, they only adopt a simple strategy, that is, transforming the multi-location proteins to multiple proteins with single location, which doesn't take correlations among different subcellular locations into account. In this paper, a novel method named RALS (multi-label learning via RAndom Label Selection), is proposed to learn from multi-location proteins in an effective and efficient way. Through five-fold cross validation test on a benchmark dataset, we demonstrate our proposed method with consideration of label correlations obviously outperforms the baseline BR method without consideration of label correlations, indicating correlations among different subcellular locations really exist and contribute to improvement of prediction performance. Experimental results on two benchmark datasets also show that our proposed methods achieve significantly higher performance than some other state-of-the-art methods in predicting subcellular multi-locations of proteins. The prediction web server is available at http://levis.tongji.edu.cn:8080/bioinfo/MLPred-Euk/ for the public usage.

Learning Digital Test and Diagnostics via Internet

Directory of Open Access Journals (Sweden)

Heinz-Dietrich Wuttke

2007-02-01

Full Text Available An environment targeted to e-learning is presented for teaching design and test of electronic systems. The environment consists of a set of Java applets, and of web based access to the hardware equipments, which can be used in the classroom, for learning at home, in laboratory research and training, or for carrying out testing of students during exams. The tools support university courses on digital electronics, computer hardware, testing and design for testability to learn by hands-on exercises how to design digital systems, how to make them testable, how to build self-testing systems, how to generate test patterns, how to analyze the quality of tests, and how to localize faults in hardware. The tasks chosen for hands-on training represent simultaneously research problems, which allow to fostering in students critical thinking, problem solving skills and creativity.

Didactic training vs. computer-based self-learning in the prediction of diminutive colon polyp histology by trainees: a randomized controlled study.

Science.gov (United States)

Khan, Taimur; Cinnor, Birtukan; Gupta, Neil; Hosford, Lindsay; Bansal, Ajay; Olyaee, Mojtaba S; Wani, Sachin; Rastogi, Amit

2017-12-01

Background and study aim  Experts can accurately predict diminutive polyp histology, but the ideal method to train nonexperts is not known. The aim of the study was to compare accuracy in diminutive polyp histology characterization using narrow-band imaging (NBI) between participants undergoing classroom didactic training vs. computer-based self-learning. Participants and methods  Trainees at two institutions were randomized to classroom didactic training or computer-based self-learning. In didactic training, experienced endoscopists reviewed a presentation on NBI patterns for adenomatous and hyperplastic polyps and 40 NBI videos, along with interactive discussion. The self-learning group reviewed the same presentation of 40 teaching videos independently, without interactive discussion. A total of 40 testing videos of diminutive polyps under NBI were then evaluated by both groups. Performance characteristics were calculated by comparing predicted and actual histology. Fisher's exact test was used and P  didactic training and 9 self-learning). A larger proportion of polyps were diagnosed with high confidence in the classroom group (66.5 % vs. 50.8 %; P  didactic training for predicting diminutive polyp histology. This approach can help in widespread training and clinical implementation of real-time polyp histology characterization. © Georg Thieme Verlag KG Stuttgart · New York.

Huntington's disease : Psychological aspects of predictive testing

NARCIS (Netherlands)

Timman, Reinier

2005-01-01

Predictive testing for Huntington's disease appears to have long lasting psychological effects. The predictive test for Huntington's disease (HD), a hereditary disease of the nervous system, was introduced in the Netherlands in the late eighties. As adverse consequences of the test were

Semi-supervised prediction of gene regulatory networks using machine learning algorithms.

Science.gov (United States)

Patel, Nihir; Wang, Jason T L

2015-10-01

Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging task. Many studies have been conducted using unsupervised methods to fulfill the task; however, such methods usually yield low prediction accuracies due to the lack of training data. In this article, we propose semi-supervised methods for GRN prediction by utilizing two machine learning algorithms, namely, support vector machines (SVM) and random forests (RF). The semi-supervised methods make use of unlabelled data for training. We investigated inductive and transductive learning approaches, both of which adopt an iterative procedure to obtain reliable negative training data from the unlabelled data. We then applied our semi-supervised methods to gene expression data of Escherichia coli and Saccharomyces cerevisiae, and evaluated the performance of our methods using the expression data. Our analysis indicated that the transductive learning approach outperformed the inductive learning approach for both organisms. However, there was no conclusive difference identified in the performance of SVM and RF. Experimental results also showed that the proposed semi-supervised methods performed better than existing supervised methods for both organisms.

Predicting novel substrates for enzymes with minimal experimental effort with active learning.

Science.gov (United States)

Pertusi, Dante A; Moura, Matthew E; Jeffryes, James G; Prabhu, Siddhant; Walters Biggs, Bradley; Tyo, Keith E J

2017-11-01

Enzymatic substrate promiscuity is more ubiquitous than previously thought, with significant consequences for understanding metabolism and its application to biocatalysis. This realization has given rise to the need for efficient characterization of enzyme promiscuity. Enzyme promiscuity is currently characterized with a limited number of human-selected compounds that may not be representative of the enzyme's versatility. While testing large numbers of compounds may be impractical, computational approaches can exploit existing data to determine the most informative substrates to test next, thereby more thoroughly exploring an enzyme's versatility. To demonstrate this, we used existing studies and tested compounds for four different enzymes, developed support vector machine (SVM) models using these datasets, and selected additional compounds for experiments using an active learning approach. SVMs trained on a chemically diverse set of compounds were discovered to achieve maximum accuracies of ~80% using ~33% fewer compounds than datasets based on all compounds tested in existing studies. Active learning-selected compounds for testing resolved apparent conflicts in the existing training data, while adding diversity to the dataset. The application of these algorithms to wide arrays of metabolic enzymes would result in a library of SVMs that can predict high-probability promiscuous enzymatic reactions and could prove a valuable resource for the design of novel metabolic pathways. Copyright © 2017 International Metabolic Engineering Society. Published by Elsevier Inc. All rights reserved.

Predicting novel substrates for enzymes with minimal experimental effort with active learning

Energy Technology Data Exchange (ETDEWEB)

Pertusi, Dante A.; Moura, Matthew E.; Jeffryes, James G.; Prabhu, Siddhant; Walters Biggs, Bradley; Tyo, Keith E. J.

2017-11-01

Enzymatic substrate promiscuity is more ubiquitous than previously thought, with significant consequences for understanding metabolism and its application to biocatalysis. This realization has given rise to the need for efficient characterization of enzyme promiscuity. Enzyme promiscuity is currently characterized with a limited number of human-selected compounds that may not be representative of the enzyme's versatility. While testing large numbers of compounds may be impractical, computational approaches can exploit existing data to determine the most informative substrates to test next, thereby more thoroughly exploring an enzyme's versatility. To demonstrate this, we used existing studies and tested compounds for four different enzymes, developed support vector machine (SVM) models using these datasets, and selected additional compounds for experiments using an active learning approach. SVMs trained on a chemically diverse set of compounds were discovered to achieve maximum accuracies of similar to 80% using similar to 33% fewer compounds than datasets based on all compounds tested in existing studies. Active learning-selected compounds for testing resolved apparent conflicts in the existing training data, while adding diversity to the dataset. The application of these algorithms to wide arrays of metabolic enzymes would result in a library of SVMs that can predict high-probability promiscuous enzymatic reactions and could prove a valuable resource for the design of novel metabolic pathways.

Predictive codes of familiarity and context during the perceptual learning of facial identities

Science.gov (United States)

Apps, Matthew A. J.; Tsakiris, Manos

2013-11-01

Face recognition is a key component of successful social behaviour. However, the computational processes that underpin perceptual learning and recognition as faces transition from unfamiliar to familiar are poorly understood. In predictive coding, learning occurs through prediction errors that update stimulus familiarity, but recognition is a function of both stimulus and contextual familiarity. Here we show that behavioural responses on a two-option face recognition task can be predicted by the level of contextual and facial familiarity in a computational model derived from predictive-coding principles. Using fMRI, we show that activity in the superior temporal sulcus varies with the contextual familiarity in the model, whereas activity in the fusiform face area covaries with the prediction error parameter that updated facial familiarity. Our results characterize the key computations underpinning the perceptual learning of faces, highlighting that the functional properties of face-processing areas conform to the principles of predictive coding.

Perbedaan hasil belajar fisika siswa antara model pembelajaran Problem Based Learning (PBL dengan model pembelajaran Prediction, Observation, and Explanation (POE di kelas X SMA Negeri 5 Lubuklinggau

Directory of Open Access Journals (Sweden)

Tri Ariani

2016-11-01

Full Text Available Penelitian ini bertujuan untuk mengetahui Perbedaan Hasil Belajar Fisika Siswa antara Model Pembelajaran Problem Based Learning (PBL dengan Model Pembelajaran Prediction, Observation, And Explanation (POE di Kelas X SMA Negeri 5 Lubuklinggau Tahun Pelajaran 2015/2016. Jenis penelitian ini adalah penelitian kuantitatif dengan metode penelitian eksperimen semu yang dilaksanakan dengan membandingkan kelompok eksperimen I dan kelompok eksperimen II desain penelitian  ini pre-test post-test group design. Populasi penelitian ini adalah seluruh siswa kelas X SMA Negeri 5 Lubuklinggau Tahun Pelajaran 2015/2016, yang terdiri dari 314 siswa dari 9 kelas. Pengambilan sampel dilakukan secara acak (Simple Random Sampling dengan cara pengundian nomor kelas populasi. Pengumpulan data berupa tes, data tes yang sudah dianalisis dengan uji-t, pada taraf  a= 0,05, diperoleh thitung > ttabel (2,17 > 2,00. Rata-rata akhir hasil belajar fisika kelas eksperimen I sebesar 73,4 sedangkan pada kelas kelas eksperimen II  sebesar 69,14. Sehingga dapat disimpulkan ada Perbedaan Hasil Belajar Fisika Siswa antara Model Pembelajaran Problem Based Learning (PBL Dengan Model Pembelajaran Prediction, Observation, And Explanation (POE Di Kelas X SMA Negeri 5 Lubuklinggau Tahun Pelajaran 2015/2016. The aim of this research was to find out the Comparative Results Between Students Studying Physics Learning Model Problem Based Learning (PBL with Learning Model Prediction, Observation, And Explanation (POE in the Class X SMAN 5 Lubuklinggau 2015/2016 Academic Year . This research was a quantitative research methods of experimental research conducted by comparing the experimental group I and group II experimental research design was a pre-test post-test group design. As the population in this research were all students of class X SMA Negeri 5 Lubuklinggau Academic Year 2015/2016, consisting of 314 students from the ninth grade. Sampling is done randomly (Simple Random Sampling by

Modeling learning and memory using verbal learning tests: results from ACTIVE.

Science.gov (United States)

Gross, Alden L; Rebok, George W; Brandt, Jason; Tommet, Doug; Marsiske, Michael; Jones, Richard N

2013-03-01

To investigate the influence of memory training on initial recall and learning. The Advanced Cognitive Training for Independent and Vital Elderly study of community-dwelling adults older than age 65 (n = 1,401). We decomposed trial-level recall in the Auditory Verbal Learning Test (AVLT) and Hopkins Verbal Learning Test (HVLT) into initial recall and learning across trials using latent growth models. Trial-level increases in words recalled in the AVLT and HVLT at each follow-up visit followed an approximately logarithmic shape. Over the 5-year study period, memory training was associated with slower decline in Trial 1 AVLT recall (Cohen's d = 0.35, p = .03) and steep pre- and posttraining acceleration in learning (d = 1.56, p learning, d = 3.10, p memory-trained group had a higher level of recall than the control group through the end of the 5-year study period despite faster decline in learning. This study contributes to the understanding of the mechanisms by which training benefits memory and expands current knowledge by reporting long-term changes in initial recall and learning, as measured from growth models and by characterization of the impact of memory training on these components. Results reveal that memory training delays the worsening of memory span and boosts learning.

Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning

Directory of Open Access Journals (Sweden)

Shandilya Sharad

2012-10-01

Full Text Available Abstract Background Ventricular Fibrillation (VF is a common presenting dysrhythmia in the setting of cardiac arrest whose main treatment is defibrillation through direct current countershock to achieve return of spontaneous circulation. However, often defibrillation is unsuccessful and may even lead to the transition of VF to more nefarious rhythms such as asystole or pulseless electrical activity. Multiple methods have been proposed for predicting defibrillation success based on examination of the VF waveform. To date, however, no analytical technique has been widely accepted. We developed a unique approach of computational VF waveform analysis, with and without addition of the signal of end-tidal carbon dioxide (PetCO2, using advanced machine learning algorithms. We compare these results with those obtained using the Amplitude Spectral Area (AMSA technique. Methods A total of 90 pre-countershock ECG signals were analyzed form an accessible preshosptial cardiac arrest database. A unified predictive model, based on signal processing and machine learning, was developed with time-series and dual-tree complex wavelet transform features. Upon selection of correlated variables, a parametrically optimized support vector machine (SVM model was trained for predicting outcomes on the test sets. Training and testing was performed with nested 10-fold cross validation and 6–10 features for each test fold. Results The integrative model performs real-time, short-term (7.8 second analysis of the Electrocardiogram (ECG. For a total of 90 signals, 34 successful and 56 unsuccessful defibrillations were classified with an average Accuracy and Receiver Operator Characteristic (ROC Area Under the Curve (AUC of 82.2% and 85%, respectively. Incorporation of the end-tidal carbon dioxide signal boosted Accuracy and ROC AUC to 83.3% and 93.8%, respectively, for a smaller dataset containing 48 signals. VF analysis using AMSA resulted in accuracy and ROC AUC of 64

Predictive coding accelerates word recognition and learning in the early stages of language development.

Science.gov (United States)

Ylinen, Sari; Bosseler, Alexis; Junttila, Katja; Huotilainen, Minna

2017-11-01

The ability to predict future events in the environment and learn from them is a fundamental component of adaptive behavior across species. Here we propose that inferring predictions facilitates speech processing and word learning in the early stages of language development. Twelve- and 24-month olds' electrophysiological brain responses to heard syllables are faster and more robust when the preceding word context predicts the ending of a familiar word. For unfamiliar, novel word forms, however, word-expectancy violation generates a prediction error response, the strength of which significantly correlates with children's vocabulary scores at 12 months. These results suggest that predictive coding may accelerate word recognition and support early learning of novel words, including not only the learning of heard word forms but also their mapping to meanings. Prediction error may mediate learning via attention, since infants' attention allocation to the entire learning situation in natural environments could account for the link between prediction error and the understanding of word meanings. On the whole, the present results on predictive coding support the view that principles of brain function reported across domains in humans and non-human animals apply to language and its development in the infant brain. A video abstract of this article can be viewed at: http://hy.fi/unitube/video/e1cbb495-41d8-462e-8660-0864a1abd02c. [Correction added on 27 January 2017, after first online publication: The video abstract link was added.]. © 2016 John Wiley & Sons Ltd.

Opportunity to learn: Investigating possible predictors for pre-course Test Of Astronomy STandards TOAST scores

Science.gov (United States)

Berryhill, Katie J.

As astronomy education researchers become more interested in experimentally testing innovative teaching strategies to enhance learning in introductory astronomy survey courses ("ASTRO 101"), scholars are placing increased attention toward better understanding factors impacting student gain scores on the widely used Test Of Astronomy STandards (TOAST). Usually used in a pre-test and post-test research design, one might naturally assume that the pre-course differences observed between high- and low-scoring college students might be due in large part to their pre-existing motivation, interest, experience in science, and attitudes about astronomy. To explore this notion, 11 non-science majoring undergraduates taking ASTRO 101 at west coast community colleges were interviewed in the first few weeks of the course to better understand students' pre-existing affect toward learning astronomy with an eye toward predicting student success. In answering this question, we hope to contribute to our understanding of the incoming knowledge of students taking undergraduate introductory astronomy classes, but also gain insight into how faculty can best meet those students' needs and assist them in achieving success. Perhaps surprisingly, there was only weak correlation between students' motivation toward learning astronomy and their pre-test scores. Instead, the most fruitful predictor of TOAST pre-test scores was the quantity of pre-existing, informal, self-directed astronomy learning experiences.

Hebbian learning and predictive mirror neurons for actions, sensations and emotions

OpenAIRE

Keysers, C.; Gazzola, Valeria

2014-01-01

Spike-timing-dependent plasticity is considered the neurophysiological basis of Hebbian learning and has been shown to be sensitive to both contingency and contiguity between pre- and postsynaptic activity. Here, we will examine how applying this Hebbian learning rule to a system of interconnected neurons in the presence of direct or indirect re-afference (e.g. seeing/hearing one's own actions) predicts the emergence of mirror neurons with predictive properties. In this framework, we analyse ...

Individual differences in spatial configuration learning predict the occurrence of intrusive memories.

Science.gov (United States)

Meyer, Thomas; Smeets, Tom; Giesbrecht, Timo; Quaedflieg, Conny W E M; Girardelli, Marta M; Mackay, Georgina R N; Merckelbach, Harald

2013-03-01

The dual-representation model of posttraumatic stress disorder (PTSD; Brewin, Gregory, Lipton, & Burgess, Psychological Review, 117, 210-232 2010) argues that intrusions occur when people fail to construct context-based representations during adverse experiences. The present study tested a specific prediction flowing from this model. In particular, we investigated whether the efficiency of temporal-lobe-based spatial configuration learning would account for individual differences in intrusive experiences and physiological reactivity in the laboratory. Participants (N = 82) completed the contextual cuing paradigm, which assesses spatial configuration learning that is believed to depend on associative encoding in the parahippocampus. They were then shown a trauma film. Afterward, startle responses were quantified during presentation of trauma reminder pictures versus unrelated neutral and emotional pictures. PTSD symptoms were recorded in the week following participation. Better configuration learning performance was associated with fewer perceptual intrusions, r = -.33, p .46) and had no direct effect on intrusion-related distress and overall PTSD symptoms, rs > -.12, ps > .29. However, configuration learning performance tended to be associated with reduced physiological responses to unrelated negative images, r = -.20, p = .07. Thus, while spatial configuration learning appears to be unrelated to affective responding to trauma reminders, our overall findings support the idea that the context-based memory system helps to reduce intrusions.

Comparison of machine-learning algorithms to build a predictive model for detecting undiagnosed diabetes - ELSA-Brasil: accuracy study.

Science.gov (United States)

Olivera, André Rodrigues; Roesler, Valter; Iochpe, Cirano; Schmidt, Maria Inês; Vigo, Álvaro; Barreto, Sandhi Maria; Duncan, Bruce Bartholow

2017-01-01

Type 2 diabetes is a chronic disease associated with a wide range of serious health complications that have a major impact on overall health. The aims here were to develop and validate predictive models for detecting undiagnosed diabetes using data from the Longitudinal Study of Adult Health (ELSA-Brasil) and to compare the performance of different machine-learning algorithms in this task. Comparison of machine-learning algorithms to develop predictive models using data from ELSA-Brasil. After selecting a subset of 27 candidate variables from the literature, models were built and validated in four sequential steps: (i) parameter tuning with tenfold cross-validation, repeated three times; (ii) automatic variable selection using forward selection, a wrapper strategy with four different machine-learning algorithms and tenfold cross-validation (repeated three times), to evaluate each subset of variables; (iii) error estimation of model parameters with tenfold cross-validation, repeated ten times; and (iv) generalization testing on an independent dataset. The models were created with the following machine-learning algorithms: logistic regression, artificial neural network, naïve Bayes, K-nearest neighbor and random forest. The best models were created using artificial neural networks and logistic regression. -These achieved mean areas under the curve of, respectively, 75.24% and 74.98% in the error estimation step and 74.17% and 74.41% in the generalization testing step. Most of the predictive models produced similar results, and demonstrated the feasibility of identifying individuals with highest probability of having undiagnosed diabetes, through easily-obtained clinical data.

Applying machine learning to predict patient-specific current CD 4 ...

African Journals Online (AJOL)

This work shows the application of machine learning to predict current CD4 cell count of an HIV-positive patient using genome sequences, viral load and time. A regression model predicting actual CD4 cell counts and a classification model predicting if a patient's CD4 cell count is less than 200 was built using a support ...

Translating visual information into action predictions: Statistical learning in action and nonaction contexts.

Science.gov (United States)

Monroy, Claire D; Gerson, Sarah A; Hunnius, Sabine

2018-05-01

Humans are sensitive to the statistical regularities in action sequences carried out by others. In the present eyetracking study, we investigated whether this sensitivity can support the prediction of upcoming actions when observing unfamiliar action sequences. In two between-subjects conditions, we examined whether observers would be more sensitive to statistical regularities in sequences performed by a human agent versus self-propelled 'ghost' events. Secondly, we investigated whether regularities are learned better when they are associated with contingent effects. Both implicit and explicit measures of learning were compared between agent and ghost conditions. Implicit learning was measured via predictive eye movements to upcoming actions or events, and explicit learning was measured via both uninstructed reproduction of the action sequences and verbal reports of the regularities. The findings revealed that participants, regardless of condition, readily learned the regularities and made correct predictive eye movements to upcoming events during online observation. However, different patterns of explicit-learning outcomes emerged following observation: Participants were most likely to re-create the sequence regularities and to verbally report them when they had observed an actor create a contingent effect. These results suggest that the shift from implicit predictions to explicit knowledge of what has been learned is facilitated when observers perceive another agent's actions and when these actions cause effects. These findings are discussed with respect to the potential role of the motor system in modulating how statistical regularities are learned and used to modify behavior.

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

Science.gov (United States)

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

2018-04-01

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

Just do it: action-dependent learning allows sensory prediction.

Directory of Open Access Journals (Sweden)

Itai Novick

Full Text Available Sensory-motor learning is commonly considered as a mapping process, whereby sensory information is transformed into the motor commands that drive actions. However, this directional mapping, from inputs to outputs, is part of a loop; sensory stimuli cause actions and vice versa. Here, we explore whether actions affect the understanding of the sensory input that they cause. Using a visuo-motor task in humans, we demonstrate two types of learning-related behavioral effects. Stimulus-dependent effects reflect stimulus-response learning, while action-dependent effects reflect a distinct learning component, allowing the brain to predict the forthcoming sensory outcome of actions. Together, the stimulus-dependent and the action-dependent learning components allow the brain to construct a complete internal representation of the sensory-motor loop.

Sleep Quality Prediction From Wearable Data Using Deep Learning.

Science.gov (United States)

Sathyanarayana, Aarti; Joty, Shafiq; Fernandez-Luque, Luis; Ofli, Ferda; Srivastava, Jaideep; Elmagarmid, Ahmed; Arora, Teresa; Taheri, Shahrad

2016-11-04

The importance of sleep is paramount to health. Insufficient sleep can reduce physical, emotional, and mental well-being and can lead to a multitude of health complications among people with chronic conditions. Physical activity and sleep are highly interrelated health behaviors. Our physical activity during the day (ie, awake time) influences our quality of sleep, and vice versa. The current popularity of wearables for tracking physical activity and sleep, including actigraphy devices, can foster the development of new advanced data analytics. This can help to develop new electronic health (eHealth) applications and provide more insights into sleep science. The objective of this study was to evaluate the feasibility of predicting sleep quality (ie, poor or adequate sleep efficiency) given the physical activity wearable data during awake time. In this study, we focused on predicting good or poor sleep efficiency as an indicator of sleep quality. Actigraphy sensors are wearable medical devices used to study sleep and physical activity patterns. The dataset used in our experiments contained the complete actigraphy data from a subset of 92 adolescents over 1 full week. Physical activity data during awake time was used to create predictive models for sleep quality, in particular, poor or good sleep efficiency. The physical activity data from sleep time was used for the evaluation. We compared the predictive performance of traditional logistic regression with more advanced deep learning methods: multilayer perceptron (MLP), convolutional neural network (CNN), simple Elman-type recurrent neural network (RNN), long short-term memory (LSTM-RNN), and a time-batched version of LSTM-RNN (TB-LSTM). Deep learning models were able to predict the quality of sleep (ie, poor or good sleep efficiency) based on wearable data from awake periods. More specifically, the deep learning methods performed better than traditional logistic regression. “CNN had the highest specificity and

Supervised learning classification models for prediction of plant virus encoded RNA silencing suppressors.

Directory of Open Access Journals (Sweden)

Zeenia Jagga

Full Text Available Viral encoded RNA silencing suppressor proteins interfere with the host RNA silencing machinery, facilitating viral infection by evading host immunity. In plant hosts, the viral proteins have several basic science implications and biotechnology applications. However in silico identification of these proteins is limited by their high sequence diversity. In this study we developed supervised learning based classification models for plant viral RNA silencing suppressor proteins in plant viruses. We developed four classifiers based on supervised learning algorithms: J48, Random Forest, LibSVM and Naïve Bayes algorithms, with enriched model learning by correlation based feature selection. Structural and physicochemical features calculated for experimentally verified primary protein sequences were used to train the classifiers. The training features include amino acid composition; auto correlation coefficients; composition, transition, and distribution of various physicochemical properties; and pseudo amino acid composition. Performance analysis of predictive models based on 10 fold cross-validation and independent data testing revealed that the Random Forest based model was the best and achieved 86.11% overall accuracy and 86.22% balanced accuracy with a remarkably high area under the Receivers Operating Characteristic curve of 0.95 to predict viral RNA silencing suppressor proteins. The prediction models for plant viral RNA silencing suppressors can potentially aid identification of novel viral RNA silencing suppressors, which will provide valuable insights into the mechanism of RNA silencing and could be further explored as potential targets for designing novel antiviral therapeutics. Also, the key subset of identified optimal features may help in determining compositional patterns in the viral proteins which are important determinants for RNA silencing suppressor activities. The best prediction model developed in the study is available as a

A Model of the Smooth Pursuit Eye Movement with Prediction and Learning

Directory of Open Access Journals (Sweden)

Davide Zambrano

2010-01-01

Full Text Available Smooth pursuit is one of the five main eye movements in humans, consisting of tracking a steadily moving visual target. Smooth pursuit is a good example of a sensory-motor task that is deeply based on prediction: tracking a visual target is not possible by correcting the error between the eye and the target position or velocity with a feedback loop, but it is only possible by predicting the trajectory of the target. This paper presents a model of smooth pursuit based on prediction and learning. It starts from amodel of the neuro-physiological system proposed by Shibata and Schaal (Shibata et al., Neural Networks, vol. 18, pp. 213-224, 2005. The learning component added here decreases the prediction time in the case of target dynamics already experienced by the system. In the implementation described here, the convergence time is, after the learning phase, 0.8 s.

Value of supervised learning events in predicting doctors in difficulty.

Science.gov (United States)

Patel, Mumtaz; Agius, Steven; Wilkinson, Jack; Patel, Leena; Baker, Paul

2016-07-01

In the UK, supervised learning events (SLE) replaced traditional workplace-based assessments for foundation-year trainees in 2012. A key element of SLEs was to incorporate trainee reflection and assessor feedback in order to drive learning and identify training issues early. Few studies, however, have investigated the value of SLEs in predicting doctors in difficulty. This study aimed to identify principles that would inform understanding about how and why SLEs work or not in identifying doctors in difficulty (DiD). A retrospective case-control study of North West Foundation School trainees' electronic portfolios was conducted. Cases comprised all known DiD. Controls were randomly selected from the same cohort. Free-text supervisor comments from each SLE were assessed for the four domains defined in the General Medical Council's Good Medical Practice Guidelines and each scored blindly for level of concern using a three-point ordinal scale. Cumulative scores for each SLE were then analysed quantitatively for their predictive value of actual DiD. A qualitative thematic analysis was also conducted. The prevalence of DiD in this sample was 6.5%. Receiver operator characteristic curve analysis showed that Team Assessment of Behaviour (TAB) was the only SLE strongly predictive of actual DiD status. The Educational Supervisor Report (ESR) was also strongly predictive of DiD status. Fisher's test showed significant associations of TAB and ESR for both predicted and actual DiD status and also the health and performance subtypes. None of the other SLEs showed significant associations. Qualitative data analysis revealed inadequate completion and lack of constructive, particularly negative, feedback. This indicated that SLEs were not used to their full potential. TAB and the ESR are strongly predictive of DiD. However, SLEs are not being used to their full potential, and the quality of completion of reports on SLEs and feedback needs to be improved in order to better identify

Hebbian learning and predictive mirror neurons for actions, sensations and emotions.

Science.gov (United States)

Keysers, Christian; Gazzola, Valeria

2014-01-01

Spike-timing-dependent plasticity is considered the neurophysiological basis of Hebbian learning and has been shown to be sensitive to both contingency and contiguity between pre- and postsynaptic activity. Here, we will examine how applying this Hebbian learning rule to a system of interconnected neurons in the presence of direct or indirect re-afference (e.g. seeing/hearing one's own actions) predicts the emergence of mirror neurons with predictive properties. In this framework, we analyse how mirror neurons become a dynamic system that performs active inferences about the actions of others and allows joint actions despite sensorimotor delays. We explore how this system performs a projection of the self onto others, with egocentric biases to contribute to mind-reading. Finally, we argue that Hebbian learning predicts mirror-like neurons for sensations and emotions and review evidence for the presence of such vicarious activations outside the motor system.

Human medial frontal cortex activity predicts learning from errors.

Science.gov (United States)

Hester, Robert; Barre, Natalie; Murphy, Kevin; Silk, Tim J; Mattingley, Jason B

2008-08-01

Learning from errors is a critical feature of human cognition. It underlies our ability to adapt to changing environmental demands and to tune behavior for optimal performance. The posterior medial frontal cortex (pMFC) has been implicated in the evaluation of errors to control behavior, although it has not previously been shown that activity in this region predicts learning from errors. Using functional magnetic resonance imaging, we examined activity in the pMFC during an associative learning task in which participants had to recall the spatial locations of 2-digit targets and were provided with immediate feedback regarding accuracy. Activity within the pMFC was significantly greater for errors that were subsequently corrected than for errors that were repeated. Moreover, pMFC activity during recall errors predicted future responses (correct vs. incorrect), despite a sizeable interval (on average 70 s) between an error and the next presentation of the same recall probe. Activity within the hippocampus also predicted future performance and correlated with error-feedback-related pMFC activity. A relationship between performance expectations and pMFC activity, in the absence of differing reinforcement value for errors, is consistent with the idea that error-related pMFC activity reflects the extent to which an outcome is "worse than expected."

Computerized adaptive testing in computer assisted learning?

NARCIS (Netherlands)

Veldkamp, Bernard P.; Matteucci, Mariagiulia; Eggen, Theodorus Johannes Hendrikus Maria; De Wannemacker, Stefan; Clarebout, Geraldine; De Causmaecker, Patrick

2011-01-01

A major goal in computerized learning systems is to optimize learning, while in computerized adaptive tests (CAT) efficient measurement of the proficiency of students is the main focus. There seems to be a common interest to integrate computerized adaptive item selection in learning systems and

Statistical learning and probabilistic prediction in music cognition: mechanisms of stylistic enculturation.

Science.gov (United States)

Pearce, Marcus T

2018-05-11

Music perception depends on internal psychological models derived through exposure to a musical culture. It is hypothesized that this musical enculturation depends on two cognitive processes: (1) statistical learning, in which listeners acquire internal cognitive models of statistical regularities present in the music to which they are exposed; and (2) probabilistic prediction based on these learned models that enables listeners to organize and process their mental representations of music. To corroborate these hypotheses, I review research that uses a computational model of probabilistic prediction based on statistical learning (the information dynamics of music (IDyOM) model) to simulate data from empirical studies of human listeners. The results show that a broad range of psychological processes involved in music perception-expectation, emotion, memory, similarity, segmentation, and meter-can be understood in terms of a single, underlying process of probabilistic prediction using learned statistical models. Furthermore, IDyOM simulations of listeners from different musical cultures demonstrate that statistical learning can plausibly predict causal effects of differential cultural exposure to musical styles, providing a quantitative model of cultural distance. Understanding the neural basis of musical enculturation will benefit from close coordination between empirical neuroimaging and computational modeling of underlying mechanisms, as outlined here. © 2018 The Authors. Annals of the New York Academy of Sciences published by Wiley Periodicals, Inc. on behalf of New York Academy of Sciences.

Context effects in a temporal discrimination task" further tests of the Scalar Expectancy Theory and Learning-to-Time models.

Science.gov (United States)

Arantes, Joana; Machado, Armando

2008-07-01

Pigeons were trained on two temporal bisection tasks, which alternated every two sessions. In the first task, they learned to choose a red key after a 1-s signal and a green key after a 4-s signal; in the second task, they learned to choose a blue key after a 4-s signal and a yellow key after a 16-s signal. Then the pigeons were exposed to a series of test trials in order to contrast two timing models, Learning-to-Time (LeT) and Scalar Expectancy Theory (SET). The models made substantially different predictions particularly for the test trials in which the sample duration ranged from 1 s to 16 s and the choice keys were Green and Blue, the keys associated with the same 4-s samples: LeT predicted that preference for Green should increase with sample duration, a context effect, but SET predicted that preference for Green should not vary with sample duration. The results were consistent with LeT. The present study adds to the literature the finding that the context effect occurs even when the two basic discriminations are never combined in the same session.

Optimized Extreme Learning Machine for Power System Transient Stability Prediction Using Synchrophasors

Directory of Open Access Journals (Sweden)

Yanjun Zhang

2015-01-01

Full Text Available A new optimized extreme learning machine- (ELM- based method for power system transient stability prediction (TSP using synchrophasors is presented in this paper. First, the input features symbolizing the transient stability of power systems are extracted from synchronized measurements. Then, an ELM classifier is employed to build the TSP model. And finally, the optimal parameters of the model are optimized by using the improved particle swarm optimization (IPSO algorithm. The novelty of the proposal is in the fact that it improves the prediction performance of the ELM-based TSP model by using IPSO to optimize the parameters of the model with synchrophasors. And finally, based on the test results on both IEEE 39-bus system and a large-scale real power system, the correctness and validity of the presented approach are verified.

Sex differences in cognitive ageing: testing predictions derived from life-history theory in a dioecious nematode.

Science.gov (United States)

Zwoinska, Martyna K; Kolm, Niclas; Maklakov, Alexei A

2013-12-01

Life-history theory maintains that organisms allocate limited resources to different traits to maximize fitness. Learning ability and memory are costly and known to trade-off with longevity in invertebrates. However, since the relationship between longevity and fitness often differs between the sexes, it is likely that sexes will differentially resolve the trade-off between learning and longevity. We used an established associative learning paradigm in the dioecious nematode Caenorhabditis remanei, which is sexually dimorphic for lifespan, to study age-related learning ability in males and females. In particular, we tested the hypothesis that females (the shorter-lived sex) show higher learning ability than males early in life but senesce faster. Indeed, young females outperformed young males in learning a novel association between an odour (butanone) and food (bacteria). However, while learning ability and offspring production declined rapidly with age in females, males maintained high levels of these traits until mid-age. These results not only demonstrate sexual dimorphism in age-related learning ability but also suggest that it conforms to predictions derived from the life-history theory. © 2013.

Soil-pipe interaction modeling for pipe behavior prediction with super learning based methods

Science.gov (United States)

Shi, Fang; Peng, Xiang; Liu, Huan; Hu, Yafei; Liu, Zheng; Li, Eric

2018-03-01

Underground pipelines are subject to severe distress from the surrounding expansive soil. To investigate the structural response of water mains to varying soil movements, field data, including pipe wall strains in situ soil water content, soil pressure and temperature, was collected. The research on monitoring data analysis has been reported, but the relationship between soil properties and pipe deformation has not been well-interpreted. To characterize the relationship between soil property and pipe deformation, this paper presents a super learning based approach combining feature selection algorithms to predict the water mains structural behavior in different soil environments. Furthermore, automatic variable selection method, e.i. recursive feature elimination algorithm, were used to identify the critical predictors contributing to the pipe deformations. To investigate the adaptability of super learning to different predictive models, this research employed super learning based methods to three different datasets. The predictive performance was evaluated by R-squared, root-mean-square error and mean absolute error. Based on the prediction performance evaluation, the superiority of super learning was validated and demonstrated by predicting three types of pipe deformations accurately. In addition, a comprehensive understand of the water mains working environments becomes possible.

A machine learning approach to the accurate prediction of monitor units for a compact proton machine.

Science.gov (United States)

Sun, Baozhou; Lam, Dao; Yang, Deshan; Grantham, Kevin; Zhang, Tiezhi; Mutic, Sasa; Zhao, Tianyu

2018-05-01

Clinical treatment planning systems for proton therapy currently do not calculate monitor units (MUs) in passive scatter proton therapy due to the complexity of the beam delivery systems. Physical phantom measurements are commonly employed to determine the field-specific output factors (OFs) but are often subject to limited machine time, measurement uncertainties and intensive labor. In this study, a machine learning-based approach was developed to predict output (cGy/MU) and derive MUs, incorporating the dependencies on gantry angle and field size for a single-room proton therapy system. The goal of this study was to develop a secondary check tool for OF measurements and eventually eliminate patient-specific OF measurements. The OFs of 1754 fields previously measured in a water phantom with calibrated ionization chambers and electrometers for patient-specific fields with various range and modulation width combinations for 23 options were included in this study. The training data sets for machine learning models in three different methods (Random Forest, XGBoost and Cubist) included 1431 (~81%) OFs. Ten-fold cross-validation was used to prevent "overfitting" and to validate each model. The remaining 323 (~19%) OFs were used to test the trained models. The difference between the measured and predicted values from machine learning models was analyzed. Model prediction accuracy was also compared with that of the semi-empirical model developed by Kooy (Phys. Med. Biol. 50, 2005). Additionally, gantry angle dependence of OFs was measured for three groups of options categorized on the selection of the second scatters. Field size dependence of OFs was investigated for the measurements with and without patient-specific apertures. All three machine learning methods showed higher accuracy than the semi-empirical model which shows considerably large discrepancy of up to 7.7% for the treatment fields with full range and full modulation width. The Cubist-based solution

Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees.

Science.gov (United States)

Williams, Philip H; Eyles, Rod; Weiller, Georg

2012-01-01

MicroRNAs (miRNAs) are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predicted miRNA precursors, mature miRNAs, and other nonprotein coding sequences. MirTools, mirDeep2, and miRanalyzer require "read count" to be included with the input sequences, which restricts their use to deep-sequencing data. Our aim was to train a predictor using a cross-section of different species to accurately predict miRNAs outside the training set. We wanted a system that did not require read-count for prediction and could therefore be applied to short sequences extracted from genomic, EST, or RNA-seq sources. A miRNA-predictive decision-tree model has been developed by supervised machine learning. It only requires that the corresponding genome or transcriptome is available within a sequence window that includes the precursor candidate so that the required sequence features can be collected. Some of the most critical features for training the predictor are the miRNA:miRNA(∗) duplex energy and the number of mismatches in the duplex. We present a cross-species plant miRNA predictor with 84.08% sensitivity and 98.53% specificity based on rigorous testing by leave-one-out validation.

Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees

Directory of Open Access Journals (Sweden)

Philip H. Williams

2012-01-01

Full Text Available MicroRNAs (miRNAs are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predicted miRNA precursors, mature miRNAs, and other nonprotein coding sequences. MirTools, mirDeep2, and miRanalyzer require “read count” to be included with the input sequences, which restricts their use to deep-sequencing data. Our aim was to train a predictor using a cross-section of different species to accurately predict miRNAs outside the training set. We wanted a system that did not require read-count for prediction and could therefore be applied to short sequences extracted from genomic, EST, or RNA-seq sources. A miRNA-predictive decision-tree model has been developed by supervised machine learning. It only requires that the corresponding genome or transcriptome is available within a sequence window that includes the precursor candidate so that the required sequence features can be collected. Some of the most critical features for training the predictor are the miRNA:miRNA∗ duplex energy and the number of mismatches in the duplex. We present a cross-species plant miRNA predictor with 84.08% sensitivity and 98.53% specificity based on rigorous testing by leave-one-out validation.

A comparison of the efficacy of test-driven learning versus self-assessment learning

Science.gov (United States)

He, Xiaohua; Canty, Anne

2013-01-01

Objective We compared self-assessment and test-driven learning in two groups of students who studied the same subject. Methods This was a randomized comparative experimental study. The subjects were 259 first-quarter students who were divided into a test group and a self-assessment group based on the methods they used for their learning assessments. We measured the scores and difficulty levels of 3 formal written exams. Students' attitudes toward self-assessment or test-driven learning were surveyed. Results The mean scores of exam 1, exam 2, and a summative exam were 34 (±6), 32 (±8), and 44 (±6) for the self-assessment group, respectively, with corresponding scores of 33 (±6), 33 (±7), 43 (±6) for the test group. There were no significant differences in the mean scores on all 3 tests between the two groups (p > .05). Of the students in the self-assessment group, 64% scored at least 90%, whereas 47% of students in the test group answered at least 90% of the questions correctly (p self-assessment and tests could have a significant impact on students' learning, but each offers different strengths and weaknesses. PMID:23957317

Prediction of length-of-day using extreme learning machine

Directory of Open Access Journals (Sweden)

Yu Lei

2015-03-01

Full Text Available Traditional artificial neural networks (ANN such as back-propagation neural networks (BPNN provide good predictions of length-of-day (LOD. However, the determination of network topology is difficult and time consuming. Therefore, we propose a new type of neural network, extreme learning machine (ELM, to improve the efficiency of LOD predictions. Earth orientation parameters (EOP C04 time-series provides daily values from International Earth Rotation and Reference Systems Service (IERS, which serves as our database. First, the known predictable effects that can be described by functional models—such as the effects of solid earth, ocean tides, or seasonal atmospheric variations—are removed a priori from the C04 time-series. Only the residuals after the subtraction of a priori model from the observed LOD data (i.e., the irregular and quasi-periodic variations are employed for training and predictions. The predicted LOD is the sum of a prior extrapolation model and the ELM predictions of the residuals. Different input patterns are discussed and compared to optimize the network solution. The prediction results are analyzed and compared with those obtained by other machine learning-based prediction methods, including BPNN, generalization regression neural networks (GRNN, and adaptive network-based fuzzy inference systems (ANFIS. It is shown that while achieving similar prediction accuracy, the developed method uses much less training time than other methods. Furthermore, to conduct a direct comparison with the existing prediction techniques, the mean-absolute-error (MAE from the proposed method is compared with that from the EOP prediction comparison campaign (EOP PCC. The results indicate that the accuracy of the proposed method is comparable with that of the former techniques. The implementation of the proposed method is simple.

Unique and shared validity of the "Wechsler logical memory test", the "California verbal learning test", and the "verbal learning and memory test" in patients with epilepsy.

Science.gov (United States)

Helmstaedter, Christoph; Wietzke, Jennifer; Lutz, Martin T

2009-12-01

This study was set-up to evaluate the construct validity of three verbal memory tests in epilepsy patients. Sixty-one consecutively evaluated patients with temporal lobe epilepsy (TLE) or extra-temporal epilepsy (E-TLE) underwent testing with the verbal learning and memory test (VLMT, the German equivalent of the Rey auditory verbal learning test, RAVLT); the California verbal learning test (CVLT); the logical memory and digit span subtests of the Wechsler memory scale, revised (WMS-R); and testing of intelligence, attention, speech and executive functions. Factor analysis of the memory tests resulted in test-specific rather than test over-spanning factors. Parameters of the CVLT and WMS-R, and to a much lesser degree of the VLMT, were highly correlated with attention, language function and vocabulary. Delayed recall measures of logical memory and the VLMT differentiated TLE from E-TLE. Learning and memory scores off all three tests differentiated mesial temporal sclerosis from other pathologies. A lateralization of the epilepsy was possible only for a subsample of 15 patients with mesial TLE. Although the three tests provide overlapping indicators for a temporal lobe epilepsy or a mesial pathology, they can hardly be taken in exchange. The tests have different demands on semantic processing and memory organization, and they appear differentially sensitive to performance in non-memory domains. The tests capability to lateralize appears to be poor. The findings encourage the further discussion of the dependency of memory outcomes on test selection.

Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules.

Science.gov (United States)

Lusci, Alessandro; Pollastri, Gianluca; Baldi, Pierre

2013-07-22

Shallow machine learning methods have been applied to chemoinformatics problems with some success. As more data becomes available and more complex problems are tackled, deep machine learning methods may also become useful. Here, we present a brief overview of deep learning methods and show in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties. However, molecules are typically described by undirected cyclic graphs, while recursive approaches typically use directed acyclic graphs. Thus, we develop methods to address this discrepancy, essentially by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph. One advantage of this approach is that it relies only minimally on the identification of suitable molecular descriptors because suitable representations are learned automatically from the data. Several variants of this approach are applied to the problem of predicting aqueous solubility and tested on four benchmark data sets. Experimental results show that the performance of the deep learning methods matches or exceeds the performance of other state-of-the-art methods according to several evaluation metrics and expose the fundamental limitations arising from training sets that are too small or too noisy. A Web-based predictor, AquaSol, is available online through the ChemDB portal ( cdb.ics.uci.edu ) together with additional material.

Help-Seeking Decisions of Battered Women: A Test of Learned Helplessness and Two Stress Theories.

Science.gov (United States)

Wauchope, Barbara A.

This study tested the learned helplessness theory, stress theory, and a modified stress theory to determine the best model for predicting the probability that a woman would seek help when she experienced severe violence from a male partner. The probability was hypothesized to increase as the stress of the violence experienced increased. Data were…

Machine Learning Techniques for Prediction of Early Childhood Obesity.

Science.gov (United States)

Dugan, T M; Mukhopadhyay, S; Carroll, A; Downs, S

2015-01-01

This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.

Building Customer Churn Prediction Models in Fitness Industry with Machine Learning Methods

OpenAIRE

Shan, Min

2017-01-01

With the rapid growth of digital systems, churn management has become a major focus within customer relationship management in many industries. Ample research has been conducted for churn prediction in different industries with various machine learning methods. This thesis aims to combine feature selection and supervised machine learning methods for defining models of churn prediction and apply them on fitness industry. Forward selection is chosen as feature selection methods. Support Vector ...

Predicting effects of noncoding variants with deep learning-based sequence model.

Science.gov (United States)

Zhou, Jian; Troyanskaya, Olga G

2015-10-01

Identifying functional effects of noncoding variants is a major challenge in human genetics. To predict the noncoding-variant effects de novo from sequence, we developed a deep learning-based algorithmic framework, DeepSEA (http://deepsea.princeton.edu/), that directly learns a regulatory sequence code from large-scale chromatin-profiling data, enabling prediction of chromatin effects of sequence alterations with single-nucleotide sensitivity. We further used this capability to improve prioritization of functional variants including expression quantitative trait loci (eQTLs) and disease-associated variants.

To transfer or not to transfer? Kinematics and laterality quotient predict interlimb transfer of motor learning.

Science.gov (United States)

Lefumat, Hannah Z; Vercher, Jean-Louis; Miall, R Chris; Cole, Jonathan; Buloup, Frank; Bringoux, Lionel; Bourdin, Christophe; Sarlegna, Fabrice R

2015-11-01

Humans can remarkably adapt their motor behavior to novel environmental conditions, yet it remains unclear which factors enable us to transfer what we have learned with one limb to the other. Here we tested the hypothesis that interlimb transfer of sensorimotor adaptation is determined by environmental conditions but also by individual characteristics. We specifically examined the adaptation of unconstrained reaching movements to a novel Coriolis, velocity-dependent force field. Right-handed subjects sat at the center of a rotating platform and performed forward reaching movements with the upper limb toward flashed visual targets in prerotation, per-rotation (i.e., adaptation), and postrotation tests. Here only the dominant arm was used during adaptation and interlimb transfer was assessed by comparing performance of the nondominant arm before and after dominant-arm adaptation. Vision and no-vision conditions did not significantly influence interlimb transfer of trajectory adaptation, which on average was significant but limited. We uncovered a substantial heterogeneity of interlimb transfer across subjects and found that interlimb transfer can be qualitatively and quantitatively predicted for each healthy young individual. A classifier showed that in our study, interlimb transfer could be predicted based on the subject's task performance, most notably motor variability during learning, and his or her laterality quotient. Positive correlations suggested that variability of motor performance and lateralization of arm movement control facilitate interlimb transfer. We further show that these individual characteristics can predict the presence and the magnitude of interlimb transfer of left-handers. Overall, this study suggests that individual characteristics shape the way the nervous system can generalize motor learning. Copyright © 2015 the American Physiological Society.

Opponent appetitive-aversive neural processes underlie predictive learning of pain relief.

Science.gov (United States)

Seymour, Ben; O'Doherty, John P; Koltzenburg, Martin; Wiech, Katja; Frackowiak, Richard; Friston, Karl; Dolan, Raymond

2005-09-01

Termination of a painful or unpleasant event can be rewarding. However, whether the brain treats relief in a similar way as it treats natural reward is unclear, and the neural processes that underlie its representation as a motivational goal remain poorly understood. We used fMRI (functional magnetic resonance imaging) to investigate how humans learn to generate expectations of pain relief. Using a pavlovian conditioning procedure, we show that subjects experiencing prolonged experimentally induced pain can be conditioned to predict pain relief. This proceeds in a manner consistent with contemporary reward-learning theory (average reward/loss reinforcement learning), reflected by neural activity in the amygdala and midbrain. Furthermore, these reward-like learning signals are mirrored by opposite aversion-like signals in lateral orbitofrontal cortex and anterior cingulate cortex. This dual coding has parallels to 'opponent process' theories in psychology and promotes a formal account of prediction and expectation during pain.

Decision tree-based learning to predict patient controlled analgesia consumption and readjustment

Directory of Open Access Journals (Sweden)

Hu Yuh-Jyh

2012-11-01

Full Text Available Abstract Background Appropriate postoperative pain management contributes to earlier mobilization, shorter hospitalization, and reduced cost. The under treatment of pain may impede short-term recovery and have a detrimental long-term effect on health. This study focuses on Patient Controlled Analgesia (PCA, which is a delivery system for pain medication. This study proposes and demonstrates how to use machine learning and data mining techniques to predict analgesic requirements and PCA readjustment. Methods The sample in this study included 1099 patients. Every patient was described by 280 attributes, including the class attribute. In addition to commonly studied demographic and physiological factors, this study emphasizes attributes related to PCA. We used decision tree-based learning algorithms to predict analgesic consumption and PCA control readjustment based on the first few hours of PCA medications. We also developed a nearest neighbor-based data cleaning method to alleviate the class-imbalance problem in PCA setting readjustment prediction. Results The prediction accuracies of total analgesic consumption (continuous dose and PCA dose and PCA analgesic requirement (PCA dose only by an ensemble of decision trees were 80.9% and 73.1%, respectively. Decision tree-based learning outperformed Artificial Neural Network, Support Vector Machine, Random Forest, Rotation Forest, and Naïve Bayesian classifiers in analgesic consumption prediction. The proposed data cleaning method improved the performance of every learning method in this study of PCA setting readjustment prediction. Comparative analysis identified the informative attributes from the data mining models and compared them with the correlates of analgesic requirement reported in previous works. Conclusion This study presents a real-world application of data mining to anesthesiology. Unlike previous research, this study considers a wider variety of predictive factors, including PCA

Using Deep Learning Model for Meteorological Satellite Cloud Image Prediction

Science.gov (United States)

Su, X.

2017-12-01

A satellite cloud image contains much weather information such as precipitation information. Short-time cloud movement forecast is important for precipitation forecast and is the primary means for typhoon monitoring. The traditional methods are mostly using the cloud feature matching and linear extrapolation to predict the cloud movement, which makes that the nonstationary process such as inversion and deformation during the movement of the cloud is basically not considered. It is still a hard task to predict cloud movement timely and correctly. As deep learning model could perform well in learning spatiotemporal features, to meet this challenge, we could regard cloud image prediction as a spatiotemporal sequence forecasting problem and introduce deep learning model to solve this problem. In this research, we use a variant of Gated-Recurrent-Unit(GRU) that has convolutional structures to deal with spatiotemporal features and build an end-to-end model to solve this forecast problem. In this model, both the input and output are spatiotemporal sequences. Compared to Convolutional LSTM(ConvLSTM) model, this model has lower amount of parameters. We imply this model on GOES satellite data and the model perform well.

Robust portfolio choice with ambiguity and learning about return predictability

DEFF Research Database (Denmark)

Larsen, Linda Sandris; Branger, Nicole; Munk, Claus

2013-01-01

We analyze the optimal stock-bond portfolio under both learning and ambiguity aversion. Stock returns are predictable by an observable and an unobservable predictor, and the investor has to learn about the latter. Furthermore, the investor is ambiguity-averse and has a preference for investment...... strategies that are robust to model misspecifications. We derive a closed-form solution for the optimal robust investment strategy. We find that both learning and ambiguity aversion impact the level and structure of the optimal stock investment. Suboptimal strategies resulting either from not learning...... or from not considering ambiguity can lead to economically significant losses....

Testing the scalar expectancy theory (SET) and the learning-to-time model (LeT) in a double bisection task.

Science.gov (United States)

Machado, Armando; Pata, Paulo

2005-02-01

Two theories of timing, scalar expectancy theory (SET) and learning-to-time (LeT), make substantially different assumptions about what animals learn in temporal tasks. In a test of these assumptions, pigeons learned two temporal discriminations. On Type 1 trials, they learned to choose a red key after a 1-sec signal and a green key after a 4-sec signal; on Type 2 trials, they learned to choose a blue key after a 4-sec signal and a yellow key after either an 8-sec signal (Group 8) or a 16-sec signal (Group 16). Then, the birds were exposed to signals 1 sec, 4 sec, and 16 sec in length and given a choice between novel key combinations (red or green vs. blue or yellow). The choice between the green key and the blue key was of particular significance because both keys were associated with the same 4-sec signal. Whereas SET predicted no effect of the test signal duration on choice, LeT predicted that preference for green would increase monotonically with the length of the signal but would do so faster for Group 8 than for Group 16. The results were consistent with LeT, but not with SET.

Dissociable neural representations of reinforcement and belief prediction errors underlie strategic learning.

Science.gov (United States)

Zhu, Lusha; Mathewson, Kyle E; Hsu, Ming

2012-01-31

Decision-making in the presence of other competitive intelligent agents is fundamental for social and economic behavior. Such decisions require agents to behave strategically, where in addition to learning about the rewards and punishments available in the environment, they also need to anticipate and respond to actions of others competing for the same rewards. However, whereas we know much about strategic learning at both theoretical and behavioral levels, we know relatively little about the underlying neural mechanisms. Here, we show using a multi-strategy competitive learning paradigm that strategic choices can be characterized by extending the reinforcement learning (RL) framework to incorporate agents' beliefs about the actions of their opponents. Furthermore, using this characterization to generate putative internal values, we used model-based functional magnetic resonance imaging to investigate neural computations underlying strategic learning. We found that the distinct notions of prediction errors derived from our computational model are processed in a partially overlapping but distinct set of brain regions. Specifically, we found that the RL prediction error was correlated with activity in the ventral striatum. In contrast, activity in the ventral striatum, as well as the rostral anterior cingulate (rACC), was correlated with a previously uncharacterized belief-based prediction error. Furthermore, activity in rACC reflected individual differences in degree of engagement in belief learning. These results suggest a model of strategic behavior where learning arises from interaction of dissociable reinforcement and belief-based inputs.

Secondary Structure Prediction of Protein using Resilient Back Propagation Learning Algorithm

Directory of Open Access Journals (Sweden)

Jyotshna Dongardive

2015-12-01

Full Text Available The paper proposes a neural network based approach to predict secondary structure of protein. It uses Multilayer Feed Forward Network (MLFN with resilient back propagation as the learning algorithm. Point Accepted Mutation (PAM is adopted as the encoding scheme and CB396 data set is used for the training and testing of the network. Overall accuracy of the network has been experimentally calculated with different window sizes for the sliding window scheme and by varying the number of units in the hidden layer. The best results were obtained with eleven as the window size and seven as the number of units in the hidden layer.

Neural correlates of testing effects in vocabulary learning.

Science.gov (United States)

van den Broek, Gesa S E; Takashima, Atsuko; Segers, Eliane; Fernández, Guillén; Verhoeven, Ludo

2013-09-01

Tests that require memory retrieval strongly improve long-term retention in comparison to continued studying. For example, once learners know the translation of a word, restudy practice, during which they see the word and its translation again, is less effective than testing practice, during which they see only the word and retrieve the translation from memory. In the present functional magnetic resonance imaging (fMRI) study, we investigated the neuro-cognitive mechanisms underlying this striking testing effect. Twenty-six young adults without prior knowledge of Swahili learned the translation of 100 Swahili words and then further practiced the words in an fMRI scanner by restudying or by testing. Recall of the translations on a final memory test after one week was significantly better and faster for tested words than for restudied words. Brain regions that were more active during testing than during restudying included the left inferior frontal gyrus, ventral striatum, and midbrain areas. Increased activity in the left inferior parietal and left middle temporal areas during testing but not during restudying predicted better recall on the final memory test. Together, results suggest that testing may be more beneficial than restudying due to processes related to targeted semantic elaboration and selective strengthening of associations between retrieval cues and relevant responses, and may involve increased effortful cognitive control and modulations of memory through striatal motivation and reward circuits. Copyright © 2013 Elsevier Inc. All rights reserved.

Prediction of Baseflow Index of Catchments using Machine Learning Algorithms

Science.gov (United States)

Yadav, B.; Hatfield, K.

2017-12-01

We present the results of eight machine learning techniques for predicting the baseflow index (BFI) of ungauged basins using a surrogate of catchment scale climate and physiographic data. The tested algorithms include ordinary least squares, ridge regression, least absolute shrinkage and selection operator (lasso), elasticnet, support vector machine, gradient boosted regression trees, random forests, and extremely randomized trees. Our work seeks to identify the dominant controls of BFI that can be readily obtained from ancillary geospatial databases and remote sensing measurements, such that the developed techniques can be extended to ungauged catchments. More than 800 gauged catchments spanning the continental United States were selected to develop the general methodology. The BFI calculation was based on the baseflow separated from daily streamflow hydrograph using HYSEP filter. The surrogate catchment attributes were compiled from multiple sources including digital elevation model, soil, landuse, climate data, other publicly available ancillary and geospatial data. 80% catchments were used to train the ML algorithms, and the remaining 20% of the catchments were used as an independent test set to measure the generalization performance of fitted models. A k-fold cross-validation using exhaustive grid search was used to fit the hyperparameters of each model. Initial model development was based on 19 independent variables, but after variable selection and feature ranking, we generated revised sparse models of BFI prediction that are based on only six catchment attributes. These key predictive variables selected after the careful evaluation of bias-variance tradeoff include average catchment elevation, slope, fraction of sand, permeability, temperature, and precipitation. The most promising algorithms exceeding an accuracy score (r-square) of 0.7 on test data include support vector machine, gradient boosted regression trees, random forests, and extremely randomized

Learning from sensory and reward prediction errors during motor adaptation.

Science.gov (United States)

Izawa, Jun; Shadmehr, Reza

2011-03-01

Voluntary motor commands produce two kinds of consequences. Initially, a sensory consequence is observed in terms of activity in our primary sensory organs (e.g., vision, proprioception). Subsequently, the brain evaluates the sensory feedback and produces a subjective measure of utility or usefulness of the motor commands (e.g., reward). As a result, comparisons between predicted and observed consequences of motor commands produce two forms of prediction error. How do these errors contribute to changes in motor commands? Here, we considered a reach adaptation protocol and found that when high quality sensory feedback was available, adaptation of motor commands was driven almost exclusively by sensory prediction errors. This form of learning had a distinct signature: as motor commands adapted, the subjects altered their predictions regarding sensory consequences of motor commands, and generalized this learning broadly to neighboring motor commands. In contrast, as the quality of the sensory feedback degraded, adaptation of motor commands became more dependent on reward prediction errors. Reward prediction errors produced comparable changes in the motor commands, but produced no change in the predicted sensory consequences of motor commands, and generalized only locally. Because we found that there was a within subject correlation between generalization patterns and sensory remapping, it is plausible that during adaptation an individual's relative reliance on sensory vs. reward prediction errors could be inferred. We suggest that while motor commands change because of sensory and reward prediction errors, only sensory prediction errors produce a change in the neural system that predicts sensory consequences of motor commands.

eLearning Mobile App for Android and Ios "English Grammar Learn & Test"

Directory of Open Access Journals (Sweden)

Anca-Georgiana FODOR

2016-11-01

Full Text Available This article is aiming to present the architecture and few elements from the developing cycle of "English Grammar Learn & Test" app. This is an e-learning tool for people who want to improve their English Grammar and Vocabulary. The app was approved by Google Play and Apple Store and it is available for free on both platforms as following: Android: https://play.google.com/store/apps/details?id=com.labsterzz.english_tests iOS: https://itunes.apple.com/us/app/english-grammar-learn-test/id1126468980 The app already reached350.000 users, it is rated at 4.43out of maximum 5.0 in Google Play Store. Since mid-June 2016, we launched the app also in the Apple Store iOS devices.

Deep-Learning-Based Drug-Target Interaction Prediction.

Science.gov (United States)

Wen, Ming; Zhang, Zhimin; Niu, Shaoyu; Sha, Haozhi; Yang, Ruihan; Yun, Yonghuan; Lu, Hongmei

2017-04-07

Identifying interactions between known drugs and targets is a major challenge in drug repositioning. In silico prediction of drug-target interaction (DTI) can speed up the expensive and time-consuming experimental work by providing the most potent DTIs. In silico prediction of DTI can also provide insights about the potential drug-drug interaction and promote the exploration of drug side effects. Traditionally, the performance of DTI prediction depends heavily on the descriptors used to represent the drugs and the target proteins. In this paper, to accurately predict new DTIs between approved drugs and targets without separating the targets into different classes, we developed a deep-learning-based algorithmic framework named DeepDTIs. It first abstracts representations from raw input descriptors using unsupervised pretraining and then applies known label pairs of interaction to build a classification model. Compared with other methods, it is found that DeepDTIs reaches or outperforms other state-of-the-art methods. The DeepDTIs can be further used to predict whether a new drug targets to some existing targets or whether a new target interacts with some existing drugs.

Resting-state qEEG predicts rate of second language learning in adults.

Science.gov (United States)

Prat, Chantel S; Yamasaki, Brianna L; Kluender, Reina A; Stocco, Andrea

2016-01-01

Understanding the neurobiological basis of individual differences in second language acquisition (SLA) is important for research on bilingualism, learning, and neural plasticity. The current study used quantitative electroencephalography (qEEG) to predict SLA in college-aged individuals. Baseline, eyes-closed resting-state qEEG was used to predict language learning rate during eight weeks of French exposure using an immersive, virtual scenario software. Individual qEEG indices predicted up to 60% of the variability in SLA, whereas behavioral indices of fluid intelligence, executive functioning, and working-memory capacity were not correlated with learning rate. Specifically, power in beta and low-gamma frequency ranges over right temporoparietal regions were strongly positively correlated with SLA. These results highlight the utility of resting-state EEG for studying the neurobiological basis of SLA in a relatively construct-free, paradigm-independent manner. Published by Elsevier Inc.

The Trail Making test: a study of its ability to predict falls in the acute neurological in-patient population.

Science.gov (United States)

Mateen, Bilal Akhter; Bussas, Matthias; Doogan, Catherine; Waller, Denise; Saverino, Alessia; Király, Franz J; Playford, E Diane

2018-05-01

To determine whether tests of cognitive function and patient-reported outcome measures of motor function can be used to create a machine learning-based predictive tool for falls. Prospective cohort study. Tertiary neurological and neurosurgical center. In all, 337 in-patients receiving neurosurgical, neurological, or neurorehabilitation-based care. Binary (Y/N) for falling during the in-patient episode, the Trail Making Test (a measure of attention and executive function) and the Walk-12 (a patient-reported measure of physical function). The principal outcome was a fall during the in-patient stay ( n = 54). The Trail test was identified as the best predictor of falls. Moreover, addition of other variables, did not improve the prediction (Wilcoxon signed-rank P Test data (Wilcoxon signed-rank P test of cognitive function, the Trail Making test.

Multi-population genomic prediction using a multi-task Bayesian learning model.

Science.gov (United States)

Chen, Liuhong; Li, Changxi; Miller, Stephen; Schenkel, Flavio

2014-05-03

Genomic prediction in multiple populations can be viewed as a multi-task learning problem where tasks are to derive prediction equations for each population and multi-task learning property can be improved by sharing information across populations. The goal of this study was to develop a multi-task Bayesian learning model for multi-population genomic prediction with a strategy to effectively share information across populations. Simulation studies and real data from Holstein and Ayrshire dairy breeds with phenotypes on five milk production traits were used to evaluate the proposed multi-task Bayesian learning model and compare with a single-task model and a simple data pooling method. A multi-task Bayesian learning model was proposed for multi-population genomic prediction. Information was shared across populations through a common set of latent indicator variables while SNP effects were allowed to vary in different populations. Both simulation studies and real data analysis showed the effectiveness of the multi-task model in improving genomic prediction accuracy for the smaller Ayshire breed. Simulation studies suggested that the multi-task model was most effective when the number of QTL was small (n = 20), with an increase of accuracy by up to 0.09 when QTL effects were lowly correlated between two populations (ρ = 0.2), and up to 0.16 when QTL effects were highly correlated (ρ = 0.8). When QTL genotypes were included for training and validation, the improvements were 0.16 and 0.22, respectively, for scenarios of the low and high correlation of QTL effects between two populations. When the number of QTL was large (n = 200), improvement was small with a maximum of 0.02 when QTL genotypes were not included for genomic prediction. Reduction in accuracy was observed for the simple pooling method when the number of QTL was small and correlation of QTL effects between the two populations was low. For the real data, the multi-task model achieved an

Predicting human splicing branchpoints by combining sequence-derived features and multi-label learning methods.

Science.gov (United States)

Zhang, Wen; Zhu, Xiaopeng; Fu, Yu; Tsuji, Junko; Weng, Zhiping

2017-12-01

Alternative splicing is the critical process in a single gene coding, which removes introns and joins exons, and splicing branchpoints are indicators for the alternative splicing. Wet experiments have identified a great number of human splicing branchpoints, but many branchpoints are still unknown. In order to guide wet experiments, we develop computational methods to predict human splicing branchpoints. Considering the fact that an intron may have multiple branchpoints, we transform the branchpoint prediction as the multi-label learning problem, and attempt to predict branchpoint sites from intron sequences. First, we investigate a variety of intron sequence-derived features, such as sparse profile, dinucleotide profile, position weight matrix profile, Markov motif profile and polypyrimidine tract profile. Second, we consider several multi-label learning methods: partial least squares regression, canonical correlation analysis and regularized canonical correlation analysis, and use them as the basic classification engines. Third, we propose two ensemble learning schemes which integrate different features and different classifiers to build ensemble learning systems for the branchpoint prediction. One is the genetic algorithm-based weighted average ensemble method; the other is the logistic regression-based ensemble method. In the computational experiments, two ensemble learning methods outperform benchmark branchpoint prediction methods, and can produce high-accuracy results on the benchmark dataset.

Combining University Student Self-Regulated Learning Indicators and Engagement with Online Learning Events to Predict Academic Performance

Science.gov (United States)

Pardo, Abelardo; Han, Feifei; Ellis, Robert A.

2017-01-01

Self-regulated learning theories are used to understand the reasons for different levels of university student academic performance. Similarly, learning analytics research proposes the combination of detailed data traces derived from technology-mediated tasks with a variety of algorithms to predict student academic performance. The former approach…

Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning

Science.gov (United States)

Yildiz, Yildiray; Agogino, Adrian; Brat, Guillaume

2013-01-01

Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion.

Interaction of Instrumental and Goal-Directed Learning Modulates Prediction Error Representations in the Ventral Striatum.

Science.gov (United States)

Guo, Rong; Böhmer, Wendelin; Hebart, Martin; Chien, Samson; Sommer, Tobias; Obermayer, Klaus; Gläscher, Jan

2016-12-14

Goal-directed and instrumental learning are both important controllers of human behavior. Learning about which stimulus event occurs in the environment and the reward associated with them allows humans to seek out the most valuable stimulus and move through the environment in a goal-directed manner. Stimulus-response associations are characteristic of instrumental learning, whereas response-outcome associations are the hallmark of goal-directed learning. Here we provide behavioral, computational, and neuroimaging results from a novel task in which stimulus-response and response-outcome associations are learned simultaneously but dominate behavior at different stages of the experiment. We found that prediction error representations in the ventral striatum depend on which type of learning dominates. Furthermore, the amygdala tracks the time-dependent weighting of stimulus-response versus response-outcome learning. Our findings suggest that the goal-directed and instrumental controllers dynamically engage the ventral striatum in representing prediction errors whenever one of them is dominating choice behavior. Converging evidence in human neuroimaging studies has shown that the reward prediction errors are correlated with activity in the ventral striatum. Our results demonstrate that this region is simultaneously correlated with a stimulus prediction error. Furthermore, the learning system that is currently dominating behavioral choice dynamically engages the ventral striatum for computing its prediction errors. This demonstrates that the prediction error representations are highly dynamic and influenced by various experimental context. This finding points to a general role of the ventral striatum in detecting expectancy violations and encoding error signals regardless of the specific nature of the reinforcer itself. Copyright © 2016 the authors 0270-6474/16/3612650-11$15.00/0.

Federated learning of predictive models from federated Electronic Health Records.

Science.gov (United States)

Brisimi, Theodora S; Chen, Ruidi; Mela, Theofanie; Olshevsky, Alex; Paschalidis, Ioannis Ch; Shi, Wei

2018-04-01

In an era of "big data," computationally efficient and privacy-aware solutions for large-scale machine learning problems become crucial, especially in the healthcare domain, where large amounts of data are stored in different locations and owned by different entities. Past research has been focused on centralized algorithms, which assume the existence of a central data repository (database) which stores and can process the data from all participants. Such an architecture, however, can be impractical when data are not centrally located, it does not scale well to very large datasets, and introduces single-point of failure risks which could compromise the integrity and privacy of the data. Given scores of data widely spread across hospitals/individuals, a decentralized computationally scalable methodology is very much in need. We aim at solving a binary supervised classification problem to predict hospitalizations for cardiac events using a distributed algorithm. We seek to develop a general decentralized optimization framework enabling multiple data holders to collaborate and converge to a common predictive model, without explicitly exchanging raw data. We focus on the soft-margin l 1 -regularized sparse Support Vector Machine (sSVM) classifier. We develop an iterative cluster Primal Dual Splitting (cPDS) algorithm for solving the large-scale sSVM problem in a decentralized fashion. Such a distributed learning scheme is relevant for multi-institutional collaborations or peer-to-peer applications, allowing the data holders to collaborate, while keeping every participant's data private. We test cPDS on the problem of predicting hospitalizations due to heart diseases within a calendar year based on information in the patients Electronic Health Records prior to that year. cPDS converges faster than centralized methods at the cost of some communication between agents. It also converges faster and with less communication overhead compared to an alternative distributed

Are students' impressions of improved learning through active learning methods reflected by improved test scores?

Science.gov (United States)

Everly, Marcee C

2013-02-01

To report the transformation from lecture to more active learning methods in a maternity nursing course and to evaluate whether student perception of improved learning through active-learning methods is supported by improved test scores. The process of transforming a course into an active-learning model of teaching is described. A voluntary mid-semester survey for student acceptance of the new teaching method was conducted. Course examination results, from both a standardized exam and a cumulative final exam, among students who received lecture in the classroom and students who had active learning activities in the classroom were compared. Active learning activities were very acceptable to students. The majority of students reported learning more from having active-learning activities in the classroom rather than lecture-only and this belief was supported by improved test scores. Students who had active learning activities in the classroom scored significantly higher on a standardized assessment test than students who received lecture only. The findings support the use of student reflection to evaluate the effectiveness of active-learning methods and help validate the use of student reflection of improved learning in other research projects. Copyright © 2011 Elsevier Ltd. All rights reserved.

Ensemble learned vaccination uptake prediction using web search queries

DEFF Research Database (Denmark)

Hansen, Niels Dalum; Lioma, Christina; Mølbak, Kåre

2016-01-01

We present a method that uses ensemble learning to combine clinical and web-mined time-series data in order to predict future vaccination uptake. The clinical data is official vaccination registries, and the web data is query frequencies collected from Google Trends. Experiments with official...... vaccine records show that our method predicts vaccination uptake eff?ectively (4.7 Root Mean Squared Error). Whereas performance is best when combining clinical and web data, using solely web data yields comparative performance. To our knowledge, this is the ?first study to predict vaccination uptake...

Factors Motivating Individuals to Consider Genetic Testing for Type 2 Diabetes Risk Prediction.

Directory of Open Access Journals (Sweden)

Jennifer Wessel

Full Text Available The purpose of this study was to identify attitudes and perceptions of willingness to participate in genetic testing for type 2 diabetes (T2D risk prediction in the general population. Adults (n = 598 were surveyed on attitudes about utilizing genetic testing to predict future risk of T2D. Participants were recruited from public libraries (53%, online registry (37% and a safety net hospital emergency department (10%. Respondents were 37 ± 11 years old, primarily White (54%, female (69%, college educated (46%, with an annual income ≥$25,000 (56%. Half of participants were interested in genetic testing for T2D (52% and 81% agreed/strongly agreed genetic testing should be available to the public. Only 57% of individuals knew T2D is preventable. A multivariate model to predict interest in genetic testing was adjusted for age, gender, recruitment location and BMI; significant predictors were motivation (high perceived personal risk of T2D [OR = 4.38 (1.76, 10.9]; family history [OR = 2.56 (1.46, 4.48]; desire to know risk prior to disease onset [OR = 3.25 (1.94, 5.42]; and knowing T2D is preventable [OR = 2.11 (1.24, 3.60], intention (if the cost is free [OR = 10.2 (4.27, 24.6]; and learning T2D is preventable [OR = 5.18 (1.95, 13.7] and trust of genetic testing results [OR = 0.03 (0.003, 0.30]. Individuals are interested in genetic testing for T2D risk which offers unique information that is personalized. Financial accessibility, validity of the test and availability of diabetes prevention programs were identified as predictors of interest in T2D testing.

Evaluation of a deep learning architecture for MR imaging prediction of ATRX in glioma patients

Science.gov (United States)

Korfiatis, Panagiotis; Kline, Timothy L.; Erickson, Bradley J.

2018-02-01

Predicting mutation/loss of alpha-thalassemia/mental retardation syndrome X-linked (ATRX) gene utilizing MR imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare a deep neural network approach based on a residual deep neural network (ResNet) architecture and one based on a classical machine learning approach and evaluate their ability in predicting ATRX mutation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture, pre trained on ImageNet data was the best performing model, achieving an accuracy of 0.91 for the test set (classification of a slice as no tumor, ATRX mutated, or mutated) in terms of f1 score in a test set of 35 cases. The SVM classifier achieved 0.63 for differentiating the Flair signal abnormality regions from the test patients based on their mutation status. We report a method that alleviates the need for extensive preprocessing and acts as a proof of concept that deep neural network architectures can be used to predict molecular biomarkers from routine medical images.

Prediction of Ionizing Radiation Resistance in Bacteria Using a Multiple Instance Learning Model.

Science.gov (United States)

Aridhi, Sabeur; Sghaier, Haïtham; Zoghlami, Manel; Maddouri, Mondher; Nguifo, Engelbert Mephu

2016-01-01

Ionizing-radiation-resistant bacteria (IRRB) are important in biotechnology. In this context, in silico methods of phenotypic prediction and genotype-phenotype relationship discovery are limited. In this work, we analyzed basal DNA repair proteins of most known proteome sequences of IRRB and ionizing-radiation-sensitive bacteria (IRSB) in order to learn a classifier that correctly predicts this bacterial phenotype. We formulated the problem of predicting bacterial ionizing radiation resistance (IRR) as a multiple-instance learning (MIL) problem, and we proposed a novel approach for this purpose. We provide a MIL-based prediction system that classifies a bacterium to either IRRB or IRSB. The experimental results of the proposed system are satisfactory with 91.5% of successful predictions.

A "Uses and Gratification Expectancy Model" to Predict Students' "Perceived e-Learning Experience"

Science.gov (United States)

Mondi, Makingu; Woods, Peter; Rafi, Ahmad

2008-01-01

This study investigates "how and why" students' "Uses and Gratification Expectancy" (UGE) for e-learning resources influences their "Perceived e-Learning Experience." A "Uses and Gratification Expectancy Model" (UGEM) framework is proposed to predict students' "Perceived e-Learning Experience," and…

Tensile testing

CERN Document Server

2004-01-01

A complete guide to the uniaxial tensile test, the cornerstone test for determining the mechanical properties of materials: Learn ways to predict material behavior through tensile testing. Learn how to test metals, alloys, composites, ceramics, and plastics to determine strength, ductility and elastic/plastic deformation. A must for laboratory managers, technicians, materials and design engineers, and students involved with uniaxial tensile testing. Tensile Testing , Second Edition begins with an introduction and overview of the test, with clear explanations of how materials properties are determined from test results. Subsequent sections illustrate how knowledge gained through tensile tests, such as tension properties to predict the behavior (including strength, ductility, elastic or plastic deformation, tensile and yield strengths) have resulted in improvements in materals applications. The Second Edition is completely revised and updated. It includes expanded coverage throughout the volume on a variety of ...

Predicting High School Student Use of Learning Strategies: The Role of Preferred Learning Styles and Classroom Climate

Science.gov (United States)

Cheema, Jehanzeb; Kitsantas, Anastasia

2016-01-01

This study investigated the predictiveness of preferred learning styles (competitive and cooperative) and classroom climate (teacher support and disciplinary climate) on learning strategy use in mathematics. The student survey part of the Programme for International Student Assessment 2003 comprising of 4633 US observations was used in a weighted…

Hierarchical prediction errors in midbrain and basal forebrain during sensory learning.

Science.gov (United States)

Iglesias, Sandra; Mathys, Christoph; Brodersen, Kay H; Kasper, Lars; Piccirelli, Marco; den Ouden, Hanneke E M; Stephan, Klaas E

2013-10-16

In Bayesian brain theories, hierarchically related prediction errors (PEs) play a central role for predicting sensory inputs and inferring their underlying causes, e.g., the probabilistic structure of the environment and its volatility. Notably, PEs at different hierarchical levels may be encoded by different neuromodulatory transmitters. Here, we tested this possibility in computational fMRI studies of audio-visual learning. Using a hierarchical Bayesian model, we found that low-level PEs about visual stimulus outcome were reflected by widespread activity in visual and supramodal areas but also in the midbrain. In contrast, high-level PEs about stimulus probabilities were encoded by the basal forebrain. These findings were replicated in two groups of healthy volunteers. While our fMRI measures do not reveal the exact neuron types activated in midbrain and basal forebrain, they suggest a dichotomy between neuromodulatory systems, linking dopamine to low-level PEs about stimulus outcome and acetylcholine to more abstract PEs about stimulus probabilities. Copyright © 2013 Elsevier Inc. All rights reserved.

Grammar predicts procedural learning and consolidation deficits in children with Specific Language Impairment.

Science.gov (United States)

Hedenius, Martina; Persson, Jonas; Tremblay, Antoine; Adi-Japha, Esther; Veríssimo, João; Dye, Cristina D; Alm, Per; Jennische, Margareta; Bruce Tomblin, J; Ullman, Michael T

2011-01-01

The Procedural Deficit Hypothesis (PDH) posits that Specific Language Impairment (SLI) can be largely explained by abnormalities of brain structures that subserve procedural memory. The PDH predicts impairments of procedural memory itself, and that such impairments underlie the grammatical deficits observed in the disorder. Previous studies have indeed reported procedural learning impairments in SLI, and have found that these are associated with grammatical difficulties. The present study extends this research by examining consolidation and longer-term procedural sequence learning in children with SLI. The Alternating Serial Reaction Time (ASRT) task was given to children with SLI and typically developing (TD) children in an initial learning session and an average of three days later to test for consolidation and longer-term learning. Although both groups showed evidence of initial sequence learning, only the TD children showed clear signs of consolidation, even though the two groups did not differ in longer-term learning. When the children were re-categorized on the basis of grammar deficits rather than broader language deficits, a clearer pattern emerged. Whereas both the grammar impaired and normal grammar groups showed evidence of initial sequence learning, only those with normal grammar showed consolidation and longer-term learning. Indeed, the grammar-impaired group appeared to lose any sequence knowledge gained during the initial testing session. These findings held even when controlling for vocabulary or a broad non-grammatical language measure, neither of which were associated with procedural memory. When grammar was examined as a continuous variable over all children, the same relationships between procedural memory and grammar, but not vocabulary or the broader language measure, were observed. Overall, the findings support and further specify the PDH. They suggest that consolidation and longer-term procedural learning are impaired in SLI, but that these

Grammar Predicts Procedural Learning and Consolidation Deficits in Children with Specific Language Impairment

Science.gov (United States)

Hedenius, Martina; Persson, Jonas; Tremblay, Antoine; Adi-Japha, Esther; Veríssimo, João; Dye, Cristina D.; Alm, Per; Jennische, Margareta; Tomblin, J. Bruce; Ullman, Michael T.

2011-01-01

The Procedural Deficit Hypothesis (PDH) posits that Specific Language Impairment (SLI) can be largely explained by abnormalities of brain structures that subserve procedural memory. The PDH predicts impairments of procedural memory itself, and that such impairments underlie the grammatical deficits observed in the disorder. Previous studies have indeed reported procedural learning impairments in SLI, and have found that these are associated with grammatical difficulties. The present study extends this research by examining the consolidation and longer-term procedural sequence learning in children with SLI. The Alternating Serial Reaction Time (ASRT) task was given to children with SLI and typically-developing (TD) children in an initial learning session and an average of three days later to test for consolidation and longer-term learning. Although both groups showed evidence of initial sequence learning, only the TD children showed clear signs of consolidation, even though the two groups did not differ in longer-term learning. When the children were re-categorized on the basis of grammar deficits rather than broader language deficits, a clearer pattern emerged. Whereas both the grammar impaired and normal grammar groups showed evidence of initial sequence learning, only those with normal grammar showed consolidation and longer-term learning. Indeed, the grammar-impaired group appeared to lose any sequence knowledge gained during the initial testing session. These findings held even when controlling for vocabulary or a broad non-grammatical language measure, neither of which were associated with procedural memory. When grammar was examined as a continuous variable over all children, the same relationships between procedural memory and grammar, but not vocabulary or the broader language measure, were observed. Overall, the findings support and further specify the PDH. They suggest that consolidation and longer-term procedural learning are impaired in SLI, but that

Perceptual Learning Style and Learning Proficiency: A Test of the Hypothesis

Science.gov (United States)

Kratzig, Gregory P.; Arbuthnott, Katherine D.

2006-01-01

Given the potential importance of using modality preference with instruction, the authors tested whether learning style preference correlated with memory performance in each of 3 sensory modalities: visual, auditory, and kinesthetic. In Study 1, participants completed objective measures of pictorial, auditory, and tactile learning and learning…

Using Five Machine Learning for Breast Cancer Biopsy Predictions Based on Mammographic Diagnosis

OpenAIRE

Oyewola, David; Hakimi, Danladi; Adeboye, Kayode; Shehu, Musa Danjuma

2017-01-01

Breast cancer is one of thecauses of female death in the world. Mammography  is commonly  used for  distinguishing  malignant tumors  from benign  ones. In this research,  a mammographic  diagnostic method  is  presented for breast  cancer  biopsy outcome  predictions  using  fivemachine learning which includes: Logistic Regression(LR), Linear DiscriminantAnalysis(LDA), Quadratic Discriminant Analysis(QDA), Random Forest(RF) andSupport  Vector Machine(SVM)  classification.  The testing result...

The Predictive Value of Ultrasound Learning Curves Across Simulated and Clinical Settings

DEFF Research Database (Denmark)

Madsen, Mette E; Nørgaard, Lone N; Tabor, Ann

2017-01-01

OBJECTIVES: The aim of the study was to explore whether learning curves on a virtual-reality (VR) sonographic simulator can be used to predict subsequent learning curves on a physical mannequin and learning curves during clinical training. METHODS: Twenty midwives completed a simulation-based tra......OBJECTIVES: The aim of the study was to explore whether learning curves on a virtual-reality (VR) sonographic simulator can be used to predict subsequent learning curves on a physical mannequin and learning curves during clinical training. METHODS: Twenty midwives completed a simulation......-based training program in transvaginal sonography. The training was conducted on a VR simulator as well as on a physical mannequin. A subgroup of 6 participants underwent subsequent clinical training. During each of the 3 steps, the participants' performance was assessed using instruments with established...... settings. RESULTS: A good correlation was found between time needed to achieve predefined performance levels on the VR simulator and the physical mannequin (Pearson correlation coefficient .78; P VR simulator correlated well to the clinical performance scores (Pearson...

Classroom Organization and Teacher Stress Predict Learning Motivation in Kindergarten Children

Science.gov (United States)

Pakarinen, Eija; Kiuru, Noona; Lerkkanen, Marja-Kristiina; Poikkeus, Anna-Maija; Siekkinen, Martti; Nurmi, Jari-Erik

2010-01-01

This study examined the extent to which observed teaching practices and self-reported teacher stress predict children's learning motivation and phonological awareness in kindergarten. The pre-reading skills of 1,268 children were measured at the beginning of their kindergarten year. Their learning motivation and phonological awareness were…

Prediction of breast cancer risk using a machine learning approach embedded with a locality preserving projection algorithm

Science.gov (United States)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Hollingsworth, Alan B.; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qiu, Yuchen; Liu, Hong; Zheng, Bin

2018-02-01

In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.

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

Science.gov (United States)

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

2008-09-01

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

Machine learning applied to the prediction of citrus production

International Nuclear Information System (INIS)

Díaz, I.; Mazza, S.M.; Combarro, E.F.; Giménez, L.I.; Gaiad, J.E.

2017-01-01

An in-depth knowledge about variables affecting production is required in order to predict global production and take decisions in agriculture. Machine learning is a technique used in agricultural planning and precision agriculture. This work (i) studies the effectiveness of machine learning techniques for predicting orchards production; and (ii) variables affecting this production were also identified. Data from 964 orchards of lemon, mandarin, and orange in Corrientes, Argentina are analysed. Graphic and analytical descriptive statistics, correlation coefficients, principal component analysis and Biplot were performed. Production was predicted via M5-Prime, a model regression tree constructor which produces a classification based on piecewise linear functions. For all the species studied, the most informative variable was the trees' age; in mandarin and orange orchards, age was followed by between and within row distances; irrigation also affected mandarin production. Also, the performance of M5-Prime in the prediction of production is adequate, as shown when measured with correlation coefficients (~0.8) and relative mean absolute error (~0.1). These results show that M5-Prime is an appropriate method to classify citrus orchards according to production and, in addition, it allows for identifying the most informative variables affecting production by tree.

Machine learning applied to the prediction of citrus production

Directory of Open Access Journals (Sweden)

Irene Díaz

2017-07-01

Full Text Available An in-depth knowledge about variables affecting production is required in order to predict global production and take decisions in agriculture. Machine learning is a technique used in agricultural planning and precision agriculture. This work (i studies the effectiveness of machine learning techniques for predicting orchards production; and (ii variables affecting this production were also identified. Data from 964 orchards of lemon, mandarin, and orange in Corrientes, Argentina are analysed. Graphic and analytical descriptive statistics, correlation coefficients, principal component analysis and Biplot were performed. Production was predicted via M5-Prime, a model regression tree constructor which produces a classification based on piecewise linear functions. For all the species studied, the most informative variable was the trees’ age; in mandarin and orange orchards, age was followed by between and within row distances; irrigation also affected mandarin production. Also, the performance of M5-Prime in the prediction of production is adequate, as shown when measured with correlation coefficients (~0.8 and relative mean absolute error (~0.1. These results show that M5-Prime is an appropriate method to classify citrus orchards according to production and, in addition, it allows for identifying the most informative variables affecting production by tree.

Machine learning applied to the prediction of citrus production

Energy Technology Data Exchange (ETDEWEB)

Díaz, I.; Mazza, S.M.; Combarro, E.F.; Giménez, L.I.; Gaiad, J.E.

2017-07-01

An in-depth knowledge about variables affecting production is required in order to predict global production and take decisions in agriculture. Machine learning is a technique used in agricultural planning and precision agriculture. This work (i) studies the effectiveness of machine learning techniques for predicting orchards production; and (ii) variables affecting this production were also identified. Data from 964 orchards of lemon, mandarin, and orange in Corrientes, Argentina are analysed. Graphic and analytical descriptive statistics, correlation coefficients, principal component analysis and Biplot were performed. Production was predicted via M5-Prime, a model regression tree constructor which produces a classification based on piecewise linear functions. For all the species studied, the most informative variable was the trees' age; in mandarin and orange orchards, age was followed by between and within row distances; irrigation also affected mandarin production. Also, the performance of M5-Prime in the prediction of production is adequate, as shown when measured with correlation coefficients (~0.8) and relative mean absolute error (~0.1). These results show that M5-Prime is an appropriate method to classify citrus orchards according to production and, in addition, it allows for identifying the most informative variables affecting production by tree.

Machine learning in updating predictive models of planning and scheduling transportation projects

Science.gov (United States)

1997-01-01

A method combining machine learning and regression analysis to automatically and intelligently update predictive models used in the Kansas Department of Transportations (KDOTs) internal management system is presented. The predictive models used...

Learning selenium testing tools with Python

CERN Document Server

Gundecha, Unmesh

2014-01-01

If you are a quality testing professional, or a software or web application developer looking to create automation test scripts for your web applications, with an interest in Python, then this is the perfect guide for you. Python developers who need to do Selenium testing need not learn Java, as they can directly use Selenium for testing with this book.

Predictive Coding Accelerates Word Recognition and Learning in the Early Stages of Language Development

Science.gov (United States)

Ylinen, Sari; Bosseler, Alexis; Junttila, Katja; Huotilainen, Minna

2017-01-01

The ability to predict future events in the environment and learn from them is a fundamental component of adaptive behavior across species. Here we propose that inferring predictions facilitates speech processing and word learning in the early stages of language development. Twelve- and 24-month olds' electrophysiological brain responses to heard…

Prediction of mortality after radical cystectomy for bladder cancer by machine learning techniques.

Science.gov (United States)

Wang, Guanjin; Lam, Kin-Man; Deng, Zhaohong; Choi, Kup-Sze

2015-08-01

Bladder cancer is a common cancer in genitourinary malignancy. For muscle invasive bladder cancer, surgical removal of the bladder, i.e. radical cystectomy, is in general the definitive treatment which, unfortunately, carries significant morbidities and mortalities. Accurate prediction of the mortality of radical cystectomy is therefore needed. Statistical methods have conventionally been used for this purpose, despite the complex interactions of high-dimensional medical data. Machine learning has emerged as a promising technique for handling high-dimensional data, with increasing application in clinical decision support, e.g. cancer prediction and prognosis. Its ability to reveal the hidden nonlinear interactions and interpretable rules between dependent and independent variables is favorable for constructing models of effective generalization performance. In this paper, seven machine learning methods are utilized to predict the 5-year mortality of radical cystectomy, including back-propagation neural network (BPN), radial basis function (RBFN), extreme learning machine (ELM), regularized ELM (RELM), support vector machine (SVM), naive Bayes (NB) classifier and k-nearest neighbour (KNN), on a clinicopathological dataset of 117 patients of the urology unit of a hospital in Hong Kong. The experimental results indicate that RELM achieved the highest average prediction accuracy of 0.8 at a fast learning speed. The research findings demonstrate the potential of applying machine learning techniques to support clinical decision making. Copyright © 2015 Elsevier Ltd. All rights reserved.

A Machine Learned Classifier That Uses Gene Expression Data to Accurately Predict Estrogen Receptor Status

Science.gov (United States)

Bastani, Meysam; Vos, Larissa; Asgarian, Nasimeh; Deschenes, Jean; Graham, Kathryn; Mackey, John; Greiner, Russell

2013-01-01

Background Selecting the appropriate treatment for breast cancer requires accurately determining the estrogen receptor (ER) status of the tumor. However, the standard for determining this status, immunohistochemical analysis of formalin-fixed paraffin embedded samples, suffers from numerous technical and reproducibility issues. Assessment of ER-status based on RNA expression can provide more objective, quantitative and reproducible test results. Methods To learn a parsimonious RNA-based classifier of hormone receptor status, we applied a machine learning tool to a training dataset of gene expression microarray data obtained from 176 frozen breast tumors, whose ER-status was determined by applying ASCO-CAP guidelines to standardized immunohistochemical testing of formalin fixed tumor. Results This produced a three-gene classifier that can predict the ER-status of a novel tumor, with a cross-validation accuracy of 93.17±2.44%. When applied to an independent validation set and to four other public databases, some on different platforms, this classifier obtained over 90% accuracy in each. In addition, we found that this prediction rule separated the patients' recurrence-free survival curves with a hazard ratio lower than the one based on the IHC analysis of ER-status. Conclusions Our efficient and parsimonious classifier lends itself to high throughput, highly accurate and low-cost RNA-based assessments of ER-status, suitable for routine high-throughput clinical use. This analytic method provides a proof-of-principle that may be applicable to developing effective RNA-based tests for other biomarkers and conditions. PMID:24312637

Machine learning and predictive data analytics enabling metrology and process control in IC fabrication

Science.gov (United States)

Rana, Narender; Zhang, Yunlin; Wall, Donald; Dirahoui, Bachir; Bailey, Todd C.

2015-03-01

Integrate circuit (IC) technology is going through multiple changes in terms of patterning techniques (multiple patterning, EUV and DSA), device architectures (FinFET, nanowire, graphene) and patterning scale (few nanometers). These changes require tight controls on processes and measurements to achieve the required device performance, and challenge the metrology and process control in terms of capability and quality. Multivariate data with complex nonlinear trends and correlations generally cannot be described well by mathematical or parametric models but can be relatively easily learned by computing machines and used to predict or extrapolate. This paper introduces the predictive metrology approach which has been applied to three different applications. Machine learning and predictive analytics have been leveraged to accurately predict dimensions of EUV resist patterns down to 18 nm half pitch leveraging resist shrinkage patterns. These patterns could not be directly and accurately measured due to metrology tool limitations. Machine learning has also been applied to predict the electrical performance early in the process pipeline for deep trench capacitance and metal line resistance. As the wafer goes through various processes its associated cost multiplies. It may take days to weeks to get the electrical performance readout. Predicting the electrical performance early on can be very valuable in enabling timely actionable decision such as rework, scrap, feedforward, feedback predicted information or information derived from prediction to improve or monitor processes. This paper provides a general overview of machine learning and advanced analytics application in the advanced semiconductor development and manufacturing.

Automatic stimulation of experiments and learning based on prediction failure recognition

NARCIS (Netherlands)

Juarez Cordova, A.G.; Kahl, B.; Henne, T.; Prassler, E.

2009-01-01

In this paper we focus on the task of automatically and autonomously initiating experimentation and learning based on the recognition of prediction failure. We present a mechanism that utilizes conceptual knowledge to predict the outcome of robot actions, observes their execution and indicates when

Daily sea level prediction at Chiayi coast, Taiwan using extreme learning machine and relevance vector machine

Science.gov (United States)

Imani, Moslem; Kao, Huan-Chin; Lan, Wen-Hau; Kuo, Chung-Yen

2018-02-01

The analysis and the prediction of sea level fluctuations are core requirements of marine meteorology and operational oceanography. Estimates of sea level with hours-to-days warning times are especially important for low-lying regions and coastal zone management. The primary purpose of this study is to examine the applicability and capability of extreme learning machine (ELM) and relevance vector machine (RVM) models for predicting sea level variations and compare their performances with powerful machine learning methods, namely, support vector machine (SVM) and radial basis function (RBF) models. The input dataset from the period of January 2004 to May 2011 used in the study was obtained from the Dongshi tide gauge station in Chiayi, Taiwan. Results showed that the ELM and RVM models outperformed the other methods. The performance of the RVM approach was superior in predicting the daily sea level time series given the minimum root mean square error of 34.73 mm and the maximum determination coefficient of 0.93 (R2) during the testing periods. Furthermore, the obtained results were in close agreement with the original tide-gauge data, which indicates that RVM approach is a promising alternative method for time series prediction and could be successfully used for daily sea level forecasts.

CAT-PUMA: CME Arrival Time Prediction Using Machine learning Algorithms

Science.gov (United States)

Liu, Jiajia; Ye, Yudong; Shen, Chenglong; Wang, Yuming; Erdélyi, Robert

2018-04-01

CAT-PUMA (CME Arrival Time Prediction Using Machine learning Algorithms) quickly and accurately predicts the arrival of Coronal Mass Ejections (CMEs) of CME arrival time. The software was trained via detailed analysis of CME features and solar wind parameters using 182 previously observed geo-effective partial-/full-halo CMEs and uses algorithms of the Support Vector Machine (SVM) to make its predictions, which can be made within minutes of providing the necessary input parameters of a CME.

Machine Learning and Neurosurgical Outcome Prediction: A Systematic Review.

Science.gov (United States)

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.

Causal beliefs about depression in different cultural groups—what do cognitive psychological theories of causal learning and reasoning predict?

OpenAIRE

Hagmayer, York; Engelmann, Neele

2014-01-01

Cognitive psychological research focuses on causal learning and reasoning while cognitive anthropological and social science research tend to focus on systems of beliefs. Our aim was to explore how these two types of research can inform each other. Cognitive psychological theories (causal model theory and causal Bayes nets) were used to derive predictions for systems of causal beliefs. These predictions were then applied to lay theories of depression as a specific test case. A systematic lite...

Collaborative testing as a learning strategy in nursing education.

Science.gov (United States)

Sandahl, Sheryl S

2010-01-01

A primary goal of nursing education is to prepare nurses to work collaboratively as members of interprofessional health care teams on behalf of patients. Collaborative testing is a collaborative learning strategy used to foster knowledge development, critical thinking in decision making, and group processing skills. This study incorporated a quasi-experimental design with a comparison group to examine the effect of collaborative testing as a learning strategy on student learning and retention of course content as well as group process skills and student perceptions of their learning and anxiety. The setting was a baccalaureate nursing program; the sample consisted of two groups of senior students enrolled in Medical-Surgical Nursing II. Student learning, as measured by unit examination scores, was greater for students taking examinations collaboratively compared to individually. Retention of course content, as measured by final examination scores, was not greater for students taking examinations collaboratively compared to individually. Student perceptions were overwhelmingly positive, with students reporting increased learning as a result of the collaborative testing experiences. Despite the lack of data to support increased retention, collaborative testing may be a learning strategy worth implementing in nursing education. Students reported more positive interactions and collaboration with their peers, skills required by the professional nurse.

Computational neurorehabilitation: modeling plasticity and learning to predict recovery.

Science.gov (United States)

Reinkensmeyer, David J; Burdet, Etienne; Casadio, Maura; Krakauer, John W; Kwakkel, Gert; Lang, Catherine E; Swinnen, Stephan P; Ward, Nick S; Schweighofer, Nicolas

2016-04-30

Despite progress in using computational approaches to inform medicine and neuroscience in the last 30 years, there have been few attempts to model the mechanisms underlying sensorimotor rehabilitation. We argue that a fundamental understanding of neurologic recovery, and as a result accurate predictions at the individual level, will be facilitated by developing computational models of the salient neural processes, including plasticity and learning systems of the brain, and integrating them into a context specific to rehabilitation. Here, we therefore discuss Computational Neurorehabilitation, a newly emerging field aimed at modeling plasticity and motor learning to understand and improve movement recovery of individuals with neurologic impairment. We first explain how the emergence of robotics and wearable sensors for rehabilitation is providing data that make development and testing of such models increasingly feasible. We then review key aspects of plasticity and motor learning that such models will incorporate. We proceed by discussing how computational neurorehabilitation models relate to the current benchmark in rehabilitation modeling - regression-based, prognostic modeling. We then critically discuss the first computational neurorehabilitation models, which have primarily focused on modeling rehabilitation of the upper extremity after stroke, and show how even simple models have produced novel ideas for future investigation. Finally, we conclude with key directions for future research, anticipating that soon we will see the emergence of mechanistic models of motor recovery that are informed by clinical imaging results and driven by the actual movement content of rehabilitation therapy as well as wearable sensor-based records of daily activity.

Simultaneous learning and filtering without delusions: a Bayes-optimal combination of Predictive Inference and Adaptive Filtering.

Science.gov (United States)

Kneissler, Jan; Drugowitsch, Jan; Friston, Karl; Butz, Martin V

2015-01-01

Predictive coding appears to be one of the fundamental working principles of brain processing. Amongst other aspects, brains often predict the sensory consequences of their own actions. Predictive coding resembles Kalman filtering, where incoming sensory information is filtered to produce prediction errors for subsequent adaptation and learning. However, to generate prediction errors given motor commands, a suitable temporal forward model is required to generate predictions. While in engineering applications, it is usually assumed that this forward model is known, the brain has to learn it. When filtering sensory input and learning from the residual signal in parallel, a fundamental problem arises: the system can enter a delusional loop when filtering the sensory information using an overly trusted forward model. In this case, learning stalls before accurate convergence because uncertainty about the forward model is not properly accommodated. We present a Bayes-optimal solution to this generic and pernicious problem for the case of linear forward models, which we call Predictive Inference and Adaptive Filtering (PIAF). PIAF filters incoming sensory information and learns the forward model simultaneously. We show that PIAF is formally related to Kalman filtering and to the Recursive Least Squares linear approximation method, but combines these procedures in a Bayes optimal fashion. Numerical evaluations confirm that the delusional loop is precluded and that the learning of the forward model is more than 10-times faster when compared to a naive combination of Kalman filtering and Recursive Least Squares.

Controlling misses and false alarms in a machine learning framework for predicting uniformity of printed pages

Science.gov (United States)

Nguyen, Minh Q.; Allebach, Jan P.

2015-01-01

In our previous work1 , we presented a block-based technique to analyze printed page uniformity both visually and metrically. The features learned from the models were then employed in a Support Vector Machine (SVM) framework to classify the pages into one of the two categories of acceptable and unacceptable quality. In this paper, we introduce a set of tools for machine learning in the assessment of printed page uniformity. This work is primarily targeted to the printing industry, specifically the ubiquitous laser, electrophotographic printer. We use features that are well-correlated with the rankings of expert observers to develop a novel machine learning framework that allows one to achieve the minimum "false alarm" rate, subject to a chosen "miss" rate. Surprisingly, most of the research that has been conducted on machine learning does not consider this framework. During the process of developing a new product, test engineers will print hundreds of test pages, which can be scanned and then analyzed by an autonomous algorithm. Among these pages, most may be of acceptable quality. The objective is to find the ones that are not. These will provide critically important information to systems designers, regarding issues that need to be addressed in improving the printer design. A "miss" is defined to be a page that is not of acceptable quality to an expert observer that the prediction algorithm declares to be a "pass". Misses are a serious problem, since they represent problems that will not be seen by the systems designers. On the other hand, "false alarms" correspond to pages that an expert observer would declare to be of acceptable quality, but which are flagged by the prediction algorithm as "fails". In a typical printer testing and development scenario, such pages would be examined by an expert, and found to be of acceptable quality after all. "False alarm" pages result in extra pages to be examined by expert observers, which increases labor cost. But "false

A Supervised Learning Process to Validate Online Disease Reports for Use in Predictive Models.

Science.gov (United States)

Patching, Helena M M; Hudson, Laurence M; Cooke, Warrick; Garcia, Andres J; Hay, Simon I; Roberts, Mark; Moyes, Catherine L

2015-12-01

Pathogen distribution models that predict spatial variation in disease occurrence require data from a large number of geographic locations to generate disease risk maps. Traditionally, this process has used data from public health reporting systems; however, using online reports of new infections could speed up the process dramatically. Data from both public health systems and online sources must be validated before they can be used, but no mechanisms exist to validate data from online media reports. We have developed a supervised learning process to validate geolocated disease outbreak data in a timely manner. The process uses three input features, the data source and two metrics derived from the location of each disease occurrence. The location of disease occurrence provides information on the probability of disease occurrence at that location based on environmental and socioeconomic factors and the distance within or outside the current known disease extent. The process also uses validation scores, generated by disease experts who review a subset of the data, to build a training data set. The aim of the supervised learning process is to generate validation scores that can be used as weights going into the pathogen distribution model. After analyzing the three input features and testing the performance of alternative processes, we selected a cascade of ensembles comprising logistic regressors. Parameter values for the training data subset size, number of predictors, and number of layers in the cascade were tested before the process was deployed. The final configuration was tested using data for two contrasting diseases (dengue and cholera), and 66%-79% of data points were assigned a validation score. The remaining data points are scored by the experts, and the results inform the training data set for the next set of predictors, as well as going to the pathogen distribution model. The new supervised learning process has been implemented within our live site and is

Robust block bootstrap panel predictability tests

NARCIS (Netherlands)

Westerlund, J.; Smeekes, S.

2013-01-01

Most panel data studies of the predictability of returns presume that the cross-sectional units are independent, an assumption that is not realistic. As a response to this, the current paper develops block bootstrap-based panel predictability tests that are valid under very general conditions. Some

Time-sensitive Customer Churn Prediction based on PU Learning

OpenAIRE

Wang, Li; Chen, Chaochao; Zhou, Jun; Li, Xiaolong

2018-01-01

With the fast development of Internet companies throughout the world, customer churn has become a serious concern. To better help the companies retain their customers, it is important to build a customer churn prediction model to identify the customers who are most likely to churn ahead of time. In this paper, we propose a Time-sensitive Customer Churn Prediction (TCCP) framework based on Positive and Unlabeled (PU) learning technique. Specifically, we obtain the recent data by shortening the...

Spatial extreme learning machines: An application on prediction of disease counts.

Science.gov (United States)

Prates, Marcos O

2018-01-01

Extreme learning machines have gained a lot of attention by the machine learning community because of its interesting properties and computational advantages. With the increase in collection of information nowadays, many sources of data have missing information making statistical analysis harder or unfeasible. In this paper, we present a new model, coined spatial extreme learning machine, that combine spatial modeling with extreme learning machines keeping the nice properties of both methodologies and making it very flexible and robust. As explained throughout the text, the spatial extreme learning machines have many advantages in comparison with the traditional extreme learning machines. By a simulation study and a real data analysis we present how the spatial extreme learning machine can be used to improve imputation of missing data and uncertainty prediction estimation.

Learning style, judgements of learning, and learning of verbal and visual information.

Science.gov (United States)

Knoll, Abby R; Otani, Hajime; Skeel, Reid L; Van Horn, K Roger

2017-08-01

The concept of learning style is immensely popular despite the lack of evidence showing that learning style influences performance. This study tested the hypothesis that the popularity of learning style is maintained because it is associated with subjective aspects of learning, such as judgements of learning (JOLs). Preference for verbal and visual information was assessed using the revised Verbalizer-Visualizer Questionnaire (VVQ). Then, participants studied a list of word pairs and a list of picture pairs, making JOLs (immediate, delayed, and global) while studying each list. Learning was tested by cued recall. The results showed that higher VVQ verbalizer scores were associated with higher immediate JOLs for words, and higher VVQ visualizer scores were associated with higher immediate JOLs for pictures. There was no association between VVQ scores and recall or JOL accuracy. As predicted, learning style was associated with subjective aspects of learning but not objective aspects of learning. © 2016 The British Psychological Society.

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

Science.gov (United States)

Patel, Meenal J; Andreescu, Carmen; Price, Julie C; Edelman, Kathryn L; Reynolds, Charles F; Aizenstein, Howard J

2015-10-01

Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features. Late-life depression patients (medicated post-recruitment) (n = 33) and older non-depressed individuals (n = 35) were recruited. Their demographics and cognitive ability scores were recorded, and brain characteristics were acquired using multi-modal magnetic resonance imaging pretreatment. Linear and nonlinear learning methods were tested for estimating accurate prediction models. A learning method called alternating decision trees estimated the most accurate prediction models for late-life depression diagnosis (87.27% accuracy) and treatment response (89.47% accuracy). The diagnosis model included measures of age, Mini-mental state examination score, and structural imaging (e.g. whole brain atrophy and global white mater hyperintensity burden). The treatment response model included measures of structural and functional connectivity. Combinations of multi-modal imaging and/or non-imaging measures may help better predict late-life depression diagnosis and treatment response. As a preliminary observation, we speculate that the results may also suggest that different underlying brain characteristics defined by multi-modal imaging measures-rather than region-based differences-are associated with depression versus depression recovery because to our knowledge this is the first depression study to accurately predict both using the same approach. These findings may help better understand late-life depression and identify preliminary steps toward personalized late-life depression treatment. Copyright © 2015 John Wiley

Test-retest reliability and predictive validity of the Implicit Association Test in children.

Science.gov (United States)

Rae, James R; Olson, Kristina R

2018-02-01

The Implicit Association Test (IAT) is increasingly used in developmental research despite minimal evidence of whether children's IAT scores are reliable across time or predictive of behavior. When test-retest reliability and predictive validity have been assessed, the results have been mixed, and because these studies have differed on many factors simultaneously (lag-time between testing administrations, domain, etc.), it is difficult to discern what factors may explain variability in existing test-retest reliability and predictive validity estimates. Across five studies (total N = 519; ages 6- to 11-years-old), we manipulated two factors that have varied in previous developmental research-lag-time and domain. An internal meta-analysis of these studies revealed that, across three different methods of analyzing the data, mean test-retest (rs of .48, .38, and .34) and predictive validity (rs of .46, .20, and .10) effect sizes were significantly greater than zero. While lag-time did not moderate the magnitude of test-retest coefficients, whether we observed domain differences in test-retest reliability and predictive validity estimates was contingent on other factors, such as how we scored the IAT or whether we included estimates from a unique sample (i.e., a sample containing gender typical and gender diverse children). Recommendations are made for developmental researchers that utilize the IAT in their research. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Multi-level machine learning prediction of protein–protein interactions in Saccharomyces cerevisiae

Directory of Open Access Journals (Sweden)

Julian Zubek

2015-07-01

Full Text Available Accurate identification of protein–protein interactions (PPI is the key step in understanding proteins’ biological functions, which are typically context-dependent. Many existing PPI predictors rely on aggregated features from protein sequences, however only a few methods exploit local information about specific residue contacts. In this work we present a two-stage machine learning approach for prediction of protein–protein interactions. We start with the carefully filtered data on protein complexes available for Saccharomyces cerevisiae in the Protein Data Bank (PDB database. First, we build linear descriptions of interacting and non-interacting sequence segment pairs based on their inter-residue distances. Secondly, we train machine learning classifiers to predict binary segment interactions for any two short sequence fragments. The final prediction of the protein–protein interaction is done using the 2D matrix representation of all-against-all possible interacting sequence segments of both analysed proteins. The level-I predictor achieves 0.88 AUC for micro-scale, i.e., residue-level prediction. The level-II predictor improves the results further by a more complex learning paradigm. We perform 30-fold macro-scale, i.e., protein-level cross-validation experiment. The level-II predictor using PSIPRED-predicted secondary structure reaches 0.70 precision, 0.68 recall, and 0.70 AUC, whereas other popular methods provide results below 0.6 threshold (recall, precision, AUC. Our results demonstrate that multi-scale sequence features aggregation procedure is able to improve the machine learning results by more than 10% as compared to other sequence representations. Prepared datasets and source code for our experimental pipeline are freely available for download from: http://zubekj.github.io/mlppi/ (open source Python implementation, OS independent.

Analysis of deep learning methods for blind protein contact prediction in CASP12.

Science.gov (United States)

Wang, Sheng; Sun, Siqi; Xu, Jinbo

2018-03-01

Here we present the results of protein contact prediction achieved in CASP12 by our RaptorX-Contact server, which is an early implementation of our deep learning method for contact prediction. On a set of 38 free-modeling target domains with a median family size of around 58 effective sequences, our server obtained an average top L/5 long- and medium-range contact accuracy of 47% and 44%, respectively (L = length). A complete implementation has an average accuracy of 59% and 57%, respectively. Our deep learning method formulates contact prediction as a pixel-level image labeling problem and simultaneously predicts all residue pairs of a protein using a combination of two deep residual neural networks, taking as input the residue conservation information, predicted secondary structure and solvent accessibility, contact potential, and coevolution information. Our approach differs from existing methods mainly in (1) formulating contact prediction as a pixel-level image labeling problem instead of an image-level classification problem; (2) simultaneously predicting all contacts of an individual protein to make effective use of contact occurrence patterns; and (3) integrating both one-dimensional and two-dimensional deep convolutional neural networks to effectively learn complex sequence-structure relationship including high-order residue correlation. This paper discusses the RaptorX-Contact pipeline, both contact prediction and contact-based folding results, and finally the strength and weakness of our method. © 2017 Wiley Periodicals, Inc.

Predicting Pre-planting Risk of Stagonospora nodorum blotch in Winter Wheat Using Machine Learning Models

Directory of Open Access Journals (Sweden)

Lucky eMehra

2016-03-01

Full Text Available Pre-planting factors have been associated with the late-season severity of Stagonospora nodorum blotch (SNB, caused by the fungal pathogen Parastagonospora nodorum, in winter wheat (Triticum aestivum. The relative importance of these factors in the risk of SNB has not been determined and this knowledge can facilitate disease management decisions prior to planting of the wheat crop. In this study, we examined the performance of multiple regression (MR and three machine learning algorithms namely artificial neural networks, categorical and regression trees, and random forests (RF in predicting the pre-planting risk of SNB in wheat. Pre-planting factors tested as potential predictor variables were cultivar resistance, latitude, longitude, previous crop, seeding rate, seed treatment, tillage type, and wheat residue. Disease severity assessed at the end of the growing season was used as the response variable. The models were developed using 431 disease cases (unique combinations of predictors collected from 2012 to 2014 and these cases were randomly divided into training, validation, and test datasets. Models were evaluated based on the regression of observed against predicted severity values of SNB, sensitivity-specificity ROC analysis, and the Kappa statistic. A strong relationship was observed between late-season severity of SNB and specific pre-planting factors in which latitude, longitude, wheat residue, and cultivar resistance were the most important predictors. The MR model explained 33% of variability in the data, while machine learning models explained 47 to 79% of the total variability. Similarly, the MR model correctly classified 74% of the disease cases, while machine learning models correctly classified 81 to 83% of these cases. Results show that the RF algorithm, which explained 79% of the variability within the data, was the most accurate in predicting the risk of SNB, with an accuracy rate of 93%. The RF algorithm could allow early

Predicting Pre-planting Risk of Stagonospora nodorum blotch in Winter Wheat Using Machine Learning Models.

Science.gov (United States)

Mehra, Lucky K; Cowger, Christina; Gross, Kevin; Ojiambo, Peter S

2016-01-01

Pre-planting factors have been associated with the late-season severity of Stagonospora nodorum blotch (SNB), caused by the fungal pathogen Parastagonospora nodorum, in winter wheat (Triticum aestivum). The relative importance of these factors in the risk of SNB has not been determined and this knowledge can facilitate disease management decisions prior to planting of the wheat crop. In this study, we examined the performance of multiple regression (MR) and three machine learning algorithms namely artificial neural networks, categorical and regression trees, and random forests (RF), in predicting the pre-planting risk of SNB in wheat. Pre-planting factors tested as potential predictor variables were cultivar resistance, latitude, longitude, previous crop, seeding rate, seed treatment, tillage type, and wheat residue. Disease severity assessed at the end of the growing season was used as the response variable. The models were developed using 431 disease cases (unique combinations of predictors) collected from 2012 to 2014 and these cases were randomly divided into training, validation, and test datasets. Models were evaluated based on the regression of observed against predicted severity values of SNB, sensitivity-specificity ROC analysis, and the Kappa statistic. A strong relationship was observed between late-season severity of SNB and specific pre-planting factors in which latitude, longitude, wheat residue, and cultivar resistance were the most important predictors. The MR model explained 33% of variability in the data, while machine learning models explained 47 to 79% of the total variability. Similarly, the MR model correctly classified 74% of the disease cases, while machine learning models correctly classified 81 to 83% of these cases. Results show that the RF algorithm, which explained 79% of the variability within the data, was the most accurate in predicting the risk of SNB, with an accuracy rate of 93%. The RF algorithm could allow early assessment of

Optimizing Multiple-Choice Tests as Learning Events

Science.gov (United States)

Little, Jeri Lynn

2011-01-01

Although generally used for assessment, tests can also serve as tools for learning--but different test formats may not be equally beneficial. Specifically, research has shown multiple-choice tests to be less effective than cued-recall tests in improving the later retention of the tested information (e.g., see meta-analysis by Hamaker, 1986),…

Lessons Learned in Software Testing A Context-Driven Approach

CERN Document Server

Kaner, Cem; Pettichord, Bret

2008-01-01

Decades of software testing experience condensed into the most important lessons learned.The world's leading software testing experts lend you their wisdom and years of experience to help you avoid the most common mistakes in testing software. Each lesson is an assertion related to software testing, followed by an explanation or example that shows you the how, when, and why of the testing lesson. More than just tips, tricks, and pitfalls to avoid, Lessons Learned in Software Testing speeds you through the critical testing phase of the software development project without the extensive trial an

Identification of Learning Disabled Bilingual Hispanic Students.

Science.gov (United States)

Zavala, Jesus; Mims, Joan

1983-01-01

The study compared 10 learning disabled and 10 non-learning disabled limited English proficient Mexican American elementary grade children. Six tests were identified as predicting learning disabilities including the Prueba de Lectura y Lenguaje Escrito and the Test of Nonverbal Intelligence. (Author/DB)

Observing others stay or switch - How social prediction errors are integrated into reward reversal learning.

Science.gov (United States)

Ihssen, Niklas; Mussweiler, Thomas; Linden, David E J

2016-08-01

Reward properties of stimuli can undergo sudden changes, and the detection of these 'reversals' is often made difficult by the probabilistic nature of rewards/punishments. Here we tested whether and how humans use social information (someone else's choices) to overcome uncertainty during reversal learning. We show a substantial social influence during reversal learning, which was modulated by the type of observed behavior. Participants frequently followed observed conservative choices (no switches after punishment) made by the (fictitious) other player but ignored impulsive choices (switches), even though the experiment was set up so that both types of response behavior would be similarly beneficial/detrimental (Study 1). Computational modeling showed that participants integrated the observed choices as a 'social prediction error' instead of ignoring or blindly following the other player. Modeling also confirmed higher learning rates for 'conservative' versus 'impulsive' social prediction errors. Importantly, this 'conservative bias' was boosted by interpersonal similarity, which in conjunction with the lack of effects observed in a non-social control experiment (Study 2) confirmed its social nature. A third study suggested that relative weighting of observed impulsive responses increased with increased volatility (frequency of reversals). Finally, simulations showed that in the present paradigm integrating social and reward information was not necessarily more adaptive to maximize earnings than learning from reward alone. Moreover, integrating social information increased accuracy only when conservative and impulsive choices were weighted similarly during learning. These findings suggest that to guide decisions in choice contexts that involve reward reversals humans utilize social cues conforming with their preconceptions more strongly than cues conflicting with them, especially when the other is similar. Copyright © 2016 The Authors. Published by Elsevier B

Machine learning for predicting the response of breast cancer to neoadjuvant chemotherapy.

Science.gov (United States)

Mani, Subramani; Chen, Yukun; Li, Xia; Arlinghaus, Lori; Chakravarthy, A Bapsi; Abramson, Vandana; Bhave, Sandeep R; Levy, Mia A; Xu, Hua; Yankeelov, Thomas E

2013-01-01

To employ machine learning methods to predict the eventual therapeutic response of breast cancer patients after a single cycle of neoadjuvant chemotherapy (NAC). Quantitative dynamic contrast-enhanced MRI and diffusion-weighted MRI data were acquired on 28 patients before and after one cycle of NAC. A total of 118 semiquantitative and quantitative parameters were derived from these data and combined with 11 clinical variables. We used Bayesian logistic regression in combination with feature selection using a machine learning framework for predictive model building. The best predictive models using feature selection obtained an area under the curve of 0.86 and an accuracy of 0.86, with a sensitivity of 0.88 and a specificity of 0.82. With the numerous options for NAC available, development of a method to predict response early in the course of therapy is needed. Unfortunately, by the time most patients are found not to be responding, their disease may no longer be surgically resectable, and this situation could be avoided by the development of techniques to assess response earlier in the treatment regimen. The method outlined here is one possible solution to this important clinical problem. Predictive modeling approaches based on machine learning using readily available clinical and quantitative MRI data show promise in distinguishing breast cancer responders from non-responders after the first cycle of NAC.

Prediction of Student Dropout in E-Learning Program Through the Use of Machine Learning Method

OpenAIRE

Mingjie Tan; Peiji Shao

2015-01-01

The high rate of dropout is a serious problem in E-learning program. Thus it has received extensive concern from the education administrators and researchers. Predicting the potential dropout students is a workable solution to prevent dropout. Based on the analysis of related literature, this study selected student’s personal characteristic and academic performance as input attributions. Prediction models were developed using Artificial Neural Network (ANN), Decision Tree (DT) and Bayesian Ne...

Paired-Associate and Feedback-Based Weather Prediction Tasks Support Multiple Category Learning Systems

OpenAIRE

Li, Kaiyun; Fu, Qiufang; Sun, Xunwei; Zhou, Xiaoyan; Fu, Xiaolan

2016-01-01

It remains unclear whether probabilistic category learning in the feedback-based weather prediction task (FB-WPT) can be mediated by a non-declarative or procedural learning system. To address this issue, we compared the effects of training time and verbal working memory, which influence the declarative learning system but not the non-declarative learning system, in the FB and paired-associate (PA) WPTs, as the PA task recruits a declarative learning system. The results of Experiment 1 showed...

The Impact of Protein Structure and Sequence Similarity on the Accuracy of Machine-Learning Scoring Functions for Binding Affinity Prediction.

Science.gov (United States)

Li, Hongjian; Peng, Jiangjun; Leung, Yee; Leung, Kwong-Sak; Wong, Man-Hon; Lu, Gang; Ballester, Pedro J

2018-03-14

It has recently been claimed that the outstanding performance of machine-learning scoring functions (SFs) is exclusively due to the presence of training complexes with highly similar proteins to those in the test set. Here, we revisit this question using 24 similarity-based training sets, a widely used test set, and four SFs. Three of these SFs employ machine learning instead of the classical linear regression approach of the fourth SF (X-Score which has the best test set performance out of 16 classical SFs). We have found that random forest (RF)-based RF-Score-v3 outperforms X-Score even when 68% of the most similar proteins are removed from the training set. In addition, unlike X-Score, RF-Score-v3 is able to keep learning with an increasing training set size, becoming substantially more predictive than X-Score when the full 1105 complexes are used for training. These results show that machine-learning SFs owe a substantial part of their performance to training on complexes with dissimilar proteins to those in the test set, against what has been previously concluded using the same data. Given that a growing amount of structural and interaction data will be available from academic and industrial sources, this performance gap between machine-learning SFs and classical SFs is expected to enlarge in the future.

Learning new gait patterns: Exploratory muscle activity during motor learning is not predicted by motor modules

Science.gov (United States)

Ranganathan, Rajiv; Krishnan, Chandramouli; Dhaher, Yasin Y.; Rymer, William Z.

2018-01-01

The motor module hypothesis in motor control proposes that the nervous system can simplify the problem of controlling a large number of muscles in human movement by grouping muscles into a smaller number of modules. Here, we tested one prediction of the modular organization hypothesis by examining whether there is preferential exploration along these motor modules during the learning of a new gait pattern. Healthy college-aged participants learned a new gait pattern which required increased hip and knee flexion during the swing phase while walking in a lower-extremity robot (Lokomat). The new gait pattern was displayed as a foot trajectory in the sagittal plane and participants attempted to match their foot trajectory to this template. We recorded EMG from 8 lower-extremity muscles and we extracted motor modules during both baseline walking and target-tracking using non-negative matrix factorization (NMF). Results showed increased trajectory variability in the first block of learning, indicating that participants were engaged in exploratory behavior. Critically, when we examined the muscle activity during this exploratory phase, we found that the composition of motor modules changed significantly within the first few strides of attempting the new gait pattern. The lack of persistence of the motor modules under even short time scales suggests that motor modules extracted during locomotion may be more indicative of correlated muscle activity induced by the task constraints of walking, rather than reflecting a modular control strategy. PMID:26916510

A machine learned classifier that uses gene expression data to accurately predict estrogen receptor status.

Directory of Open Access Journals (Sweden)

Meysam Bastani

Full Text Available BACKGROUND: Selecting the appropriate treatment for breast cancer requires accurately determining the estrogen receptor (ER status of the tumor. However, the standard for determining this status, immunohistochemical analysis of formalin-fixed paraffin embedded samples, suffers from numerous technical and reproducibility issues. Assessment of ER-status based on RNA expression can provide more objective, quantitative and reproducible test results. METHODS: To learn a parsimonious RNA-based classifier of hormone receptor status, we applied a machine learning tool to a training dataset of gene expression microarray data obtained from 176 frozen breast tumors, whose ER-status was determined by applying ASCO-CAP guidelines to standardized immunohistochemical testing of formalin fixed tumor. RESULTS: This produced a three-gene classifier that can predict the ER-status of a novel tumor, with a cross-validation accuracy of 93.17±2.44%. When applied to an independent validation set and to four other public databases, some on different platforms, this classifier obtained over 90% accuracy in each. In addition, we found that this prediction rule separated the patients' recurrence-free survival curves with a hazard ratio lower than the one based on the IHC analysis of ER-status. CONCLUSIONS: Our efficient and parsimonious classifier lends itself to high throughput, highly accurate and low-cost RNA-based assessments of ER-status, suitable for routine high-throughput clinical use. This analytic method provides a proof-of-principle that may be applicable to developing effective RNA-based tests for other biomarkers and conditions.

Hierarchical learning induces two simultaneous, but separable, prediction errors in human basal ganglia.

Science.gov (United States)

Diuk, Carlos; Tsai, Karin; Wallis, Jonathan; Botvinick, Matthew; Niv, Yael

2013-03-27

Studies suggest that dopaminergic neurons report a unitary, global reward prediction error signal. However, learning in complex real-life tasks, in particular tasks that show hierarchical structure, requires multiple prediction errors that may coincide in time. We used functional neuroimaging to measure prediction error signals in humans performing such a hierarchical task involving simultaneous, uncorrelated prediction errors. Analysis of signals in a priori anatomical regions of interest in the ventral striatum and the ventral tegmental area indeed evidenced two simultaneous, but separable, prediction error signals corresponding to the two levels of hierarchy in the task. This result suggests that suitably designed tasks may reveal a more intricate pattern of firing in dopaminergic neurons. Moreover, the need for downstream separation of these signals implies possible limitations on the number of different task levels that we can learn about simultaneously.

Black Ink and Red Ink (BIRI) Testing: A Testing Method to Evaluate Both Recall and Recognition Learning in Accelerated Adult-Learning Courses

Science.gov (United States)

Rodgers, Joseph Lee; Rodgers, Jacci L.

2011-01-01

We propose, develop, and evaluate the black ink-red ink (BIRI) method of testing. This approach uses two different methods within the same test administration setting, one that matches recognition learning and the other that matches recall learning. Students purposively define their own tradeoff between the two approaches. Evaluation of the method…

Taxi-Out Time Prediction for Departures at Charlotte Airport Using Machine Learning Techniques

Science.gov (United States)

Lee, Hanbong; Malik, Waqar; Jung, Yoon C.

2016-01-01

Predicting the taxi-out times of departures accurately is important for improving airport efficiency and takeoff time predictability. In this paper, we attempt to apply machine learning techniques to actual traffic data at Charlotte Douglas International Airport for taxi-out time prediction. To find the key factors affecting aircraft taxi times, surface surveillance data is first analyzed. From this data analysis, several variables, including terminal concourse, spot, runway, departure fix and weight class, are selected for taxi time prediction. Then, various machine learning methods such as linear regression, support vector machines, k-nearest neighbors, random forest, and neural networks model are applied to actual flight data. Different traffic flow and weather conditions at Charlotte airport are also taken into account for more accurate prediction. The taxi-out time prediction results show that linear regression and random forest techniques can provide the most accurate prediction in terms of root-mean-square errors. We also discuss the operational complexity and uncertainties that make it difficult to predict the taxi times accurately.

Multiple Kernel Learning with Random Effects for Predicting Longitudinal Outcomes and Data Integration

Science.gov (United States)

Chen, Tianle; Zeng, Donglin

2015-01-01

Summary Predicting disease risk and progression is one of the main goals in many clinical research studies. Cohort studies on the natural history and etiology of chronic diseases span years and data are collected at multiple visits. Although kernel-based statistical learning methods are proven to be powerful for a wide range of disease prediction problems, these methods are only well studied for independent data but not for longitudinal data. It is thus important to develop time-sensitive prediction rules that make use of the longitudinal nature of the data. In this paper, we develop a novel statistical learning method for longitudinal data by introducing subject-specific short-term and long-term latent effects through a designed kernel to account for within-subject correlation of longitudinal measurements. Since the presence of multiple sources of data is increasingly common, we embed our method in a multiple kernel learning framework and propose a regularized multiple kernel statistical learning with random effects to construct effective nonparametric prediction rules. Our method allows easy integration of various heterogeneous data sources and takes advantage of correlation among longitudinal measures to increase prediction power. We use different kernels for each data source taking advantage of the distinctive feature of each data modality, and then optimally combine data across modalities. We apply the developed methods to two large epidemiological studies, one on Huntington's disease and the other on Alzheimer's Disease (Alzheimer's Disease Neuroimaging Initiative, ADNI) where we explore a unique opportunity to combine imaging and genetic data to study prediction of mild cognitive impairment, and show a substantial gain in performance while accounting for the longitudinal aspect of the data. PMID:26177419

A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals.

Science.gov (United States)

Tsiouris, Κostas Μ; Pezoulas, Vasileios C; Zervakis, Michalis; Konitsiotis, Spiros; Koutsouris, Dimitrios D; Fotiadis, Dimitrios I

2018-05-17

The electroencephalogram (EEG) is the most prominent means to study epilepsy and capture changes in electrical brain activity that could declare an imminent seizure. In this work, Long Short-Term Memory (LSTM) networks are introduced in epileptic seizure prediction using EEG signals, expanding the use of deep learning algorithms with convolutional neural networks (CNN). A pre-analysis is initially performed to find the optimal architecture of the LSTM network by testing several modules and layers of memory units. Based on these results, a two-layer LSTM network is selected to evaluate seizure prediction performance using four different lengths of preictal windows, ranging from 15 min to 2 h. The LSTM model exploits a wide range of features extracted prior to classification, including time and frequency domain features, between EEG channels cross-correlation and graph theoretic features. The evaluation is performed using long-term EEG recordings from the open CHB-MIT Scalp EEG database, suggest that the proposed methodology is able to predict all 185 seizures, providing high rates of seizure prediction sensitivity and low false prediction rates (FPR) of 0.11-0.02 false alarms per hour, depending on the duration of the preictal window. The proposed LSTM-based methodology delivers a significant increase in seizure prediction performance compared to both traditional machine learning techniques and convolutional neural networks that have been previously evaluated in the literature. Copyright © 2018 Elsevier Ltd. All rights reserved.

Cortical ensemble activity increasingly predicts behaviour outcomes during learning of a motor task

Science.gov (United States)

Laubach, Mark; Wessberg, Johan; Nicolelis, Miguel A. L.

2000-06-01

When an animal learns to make movements in response to different stimuli, changes in activity in the motor cortex seem to accompany and underlie this learning. The precise nature of modifications in cortical motor areas during the initial stages of motor learning, however, is largely unknown. Here we address this issue by chronically recording from neuronal ensembles located in the rat motor cortex, throughout the period required for rats to learn a reaction-time task. Motor learning was demonstrated by a decrease in the variance of the rats' reaction times and an increase in the time the animals were able to wait for a trigger stimulus. These behavioural changes were correlated with a significant increase in our ability to predict the correct or incorrect outcome of single trials based on three measures of neuronal ensemble activity: average firing rate, temporal patterns of firing, and correlated firing. This increase in prediction indicates that an association between sensory cues and movement emerged in the motor cortex as the task was learned. Such modifications in cortical ensemble activity may be critical for the initial learning of motor tasks.

Using machine learning, neural networks and statistics to predict bankruptcy

NARCIS (Netherlands)

Pompe, P.P.M.; Feelders, A.J.; Feelders, A.J.

1997-01-01

Recent literature strongly suggests that machine learning approaches to classification outperform "classical" statistical methods. We make a comparison between the performance of linear discriminant analysis, classification trees, and neural networks in predicting corporate bankruptcy. Linear

Regional hippocampal volumes and development predict learning and memory.

Science.gov (United States)

Tamnes, Christian K; Walhovd, Kristine B; Engvig, Andreas; Grydeland, Håkon; Krogsrud, Stine K; Østby, Ylva; Holland, Dominic; Dale, Anders M; Fjell, Anders M

2014-01-01

The hippocampus is an anatomically and functionally heterogeneous structure, but longitudinal studies of its regional development are scarce and it is not known whether protracted maturation of the hippocampus in adolescence is related to memory development. First, we investigated hippocampal subfield development using 170 longitudinally acquired brain magnetic resonance imaging scans from 85 participants aged 8-21 years. Hippocampal subfield volumes were estimated by the use of automated segmentation of 7 subfields, including the cornu ammonis (CA) sectors and the dentate gyrus (DG), while longitudinal subfield volumetric change was quantified using a nonlinear registration procedure. Second, associations between subfield volumes and change and verbal learning/memory across multiple retention intervals (5 min, 30 min and 1 week) were tested. It was hypothesized that short and intermediate memory would be more closely related to CA2-3/CA4-DG and extended, remote memory to CA1. Change rates were significantly different across hippocampal subfields, but nearly all subfields showed significant volume decreases over time throughout adolescence. Several subfield volumes were larger in the right hemisphere and in males, while for change rates there were no hemisphere or sex differences. Partly in support of the hypotheses, greater volume of CA1 and CA2-3 was related to recall and retention after an extended delay, while longitudinal reduction of CA2-3 and CA4-DG was related to learning. This suggests continued regional development of the hippocampus across adolescence and that volume and volume change in specific subfields differentially predict verbal learning and memory over different retention intervals, but future high-resolution studies are called for. © 2014 S. Karger AG, Basel.

Prediction of Human Drug Targets and Their Interactions Using Machine Learning Methods: Current and Future Perspectives.

Science.gov (United States)

Nath, Abhigyan; Kumari, Priyanka; Chaube, Radha

2018-01-01

Identification of drug targets and drug target interactions are important steps in the drug-discovery pipeline. Successful computational prediction methods can reduce the cost and time demanded by the experimental methods. Knowledge of putative drug targets and their interactions can be very useful for drug repurposing. Supervised machine learning methods have been very useful in drug target prediction and in prediction of drug target interactions. Here, we describe the details for developing prediction models using supervised learning techniques for human drug target prediction and their interactions.

Prediction of software operational reliability using testing environment factors

International Nuclear Information System (INIS)

Jung, Hoan Sung; Seong, Poong Hyun

1995-01-01

A number of software reliability models have been developed to estimate and to predict software reliability. However, there are no established standard models to quantify software reliability. Most models estimate the quality of software in reliability figures such as remaining faults, failure rate, or mean time to next failure at the testing phase, and they consider them ultimate indicators of software reliability. Experience shows that there is a large gap between predicted reliability during development and reliability measured during operation, which means that predicted reliability, or so-called test reliability, is not operational reliability. Customers prefer operational reliability to test reliability. In this study, we propose a method that predicts operational reliability rather than test reliability by introducing the testing environment factor that quantifies the changes in environments

A Mobile Health Application to Predict Postpartum Depression Based on Machine Learning.

Science.gov (United States)

Jiménez-Serrano, Santiago; Tortajada, Salvador; García-Gómez, Juan Miguel

2015-07-01

Postpartum depression (PPD) is a disorder that often goes undiagnosed. The development of a screening program requires considerable and careful effort, where evidence-based decisions have to be taken in order to obtain an effective test with a high level of sensitivity and an acceptable specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective. The purpose of this article is twofold: first, to develop classification models for detecting the risk of PPD during the first week after childbirth, thus enabling early intervention; and second, to develop a mobile health (m-health) application (app) for the Android(®) (Google, Mountain View, CA) platform based on the model with best performance for both mothers who have just given birth and clinicians who want to monitor their patient's test. A set of predictive models for estimating the risk of PPD was trained using machine learning techniques and data about postpartum women collected from seven Spanish hospitals. An internal evaluation was carried out using a hold-out strategy. An easy flowchart and architecture for designing the graphical user interface of the m-health app was followed. Naive Bayes showed the best balance between sensitivity and specificity as a predictive model for PPD during the first week after delivery. It was integrated into the clinical decision support system for Android mobile apps. This approach can enable the early prediction and detection of PPD because it fulfills the conditions of an effective screening test with a high level of sensitivity and specificity that is quick to perform, easy to interpret, culturally sensitive, and cost-effective.

DeepLoc: prediction of protein subcellular localization using deep learning

DEFF Research Database (Denmark)

Almagro Armenteros, Jose Juan; Sønderby, Casper Kaae; Sønderby, Søren Kaae

2017-01-01

The prediction of eukaryotic protein subcellular localization is a well-studied topic in bioinformatics due to its relevance in proteomics research. Many machine learning methods have been successfully applied in this task, but in most of them, predictions rely on annotation of homologues from...... knowledge databases. For novel proteins where no annotated homologues exist, and for predicting the effects of sequence variants, it is desirable to have methods for predicting protein properties from sequence information only. Here, we present a prediction algorithm using deep neural networks to predict...... current state-of-the-art algorithms, including those relying on homology information. The method is available as a web server at http://www.cbs.dtu.dk/services/DeepLoc . Example code is available at https://github.com/JJAlmagro/subcellular_localization . The dataset is available at http...

Simultaneous Learning and Filtering without Delusions: A Bayes-Optimal Derivation of Combining Predictive Inference and AdaptiveFiltering

Directory of Open Access Journals (Sweden)

Jan eKneissler

2015-04-01

Full Text Available Predictive coding appears to be one of the fundamental working principles of brain processing. Amongst other aspects, brains often predict the sensory consequences of their own actions. Predictive coding resembles Kalman filtering, where incoming sensory information is filtered to produce prediction errors for subsequent adaptation and learning. However, to generate prediction errors given motor commands, a suitable temporal forward model is required to generate predictions. While in engineering applications, it is usually assumed that this forward model is known, the brain has to learn it. When filtering sensory input and learning from the residual signal in parallel, a fundamental problem arises: the system can enter a delusional loop when filtering the sensory information using an overly trusted forward model. In this case, learning stalls before accurate convergence because uncertainty about the forward model is not properly accommodated. We present a Bayes-optimal solution to this generic and pernicious problem for the case of linear forward models, which we call Predictive Inference and Adaptive Filtering (PIAF. PIAF filters incoming sensory information and learns the forward model simultaneously. We show that PIAF is formally related to Kalman filtering and to the Recursive Least Squares linear approximation method, but combines these procedures in a Bayes optimal fashion. Numerical evaluations confirm that the delusional loop is precluded and that the learning of the forward model is more than ten-times faster when compared to a naive combination of Kalman filtering and Recursive Least Squares.

Exploring prediction uncertainty of spatial data in geostatistical and machine learning Approaches

Science.gov (United States)

Klump, J. F.; Fouedjio, F.

2017-12-01

Geostatistical methods such as kriging with external drift as well as machine learning techniques such as quantile regression forest have been intensively used for modelling spatial data. In addition to providing predictions for target variables, both approaches are able to deliver a quantification of the uncertainty associated with the prediction at a target location. Geostatistical approaches are, by essence, adequate for providing such prediction uncertainties and their behaviour is well understood. However, they often require significant data pre-processing and rely on assumptions that are rarely met in practice. Machine learning algorithms such as random forest regression, on the other hand, require less data pre-processing and are non-parametric. This makes the application of machine learning algorithms to geostatistical problems an attractive proposition. The objective of this study is to compare kriging with external drift and quantile regression forest with respect to their ability to deliver reliable prediction uncertainties of spatial data. In our comparison we use both simulated and real world datasets. Apart from classical performance indicators, comparisons make use of accuracy plots, probability interval width plots, and the visual examinations of the uncertainty maps provided by the two approaches. By comparing random forest regression to kriging we found that both methods produced comparable maps of estimated values for our variables of interest. However, the measure of uncertainty provided by random forest seems to be quite different to the measure of uncertainty provided by kriging. In particular, the lack of spatial context can give misleading results in areas without ground truth data. These preliminary results raise questions about assessing the risks associated with decisions based on the predictions from geostatistical and machine learning algorithms in a spatial context, e.g. mineral exploration.

Prediction of psychological functioning one year after the predictive test for Huntington's disease and impact of the test result on reproductive decision making.

Science.gov (United States)

Decruyenaere, M; Evers-Kiebooms, G; Boogaerts, A; Cassiman, J J; Cloostermans, T; Demyttenaere, K; Dom, R; Fryns, J P; Van den Berghe, H

1996-01-01

For people at risk for Huntington's disease, the anxiety and uncertainty about the future may be very burdensome and may be an obstacle to personal decision making about important life issues, for example, procreation. For some at risk persons, this situation is the reason for requesting predictive DNA testing. The aim of this paper is two-fold. First, we want to evaluate whether knowing one's carrier status reduces anxiety and uncertainty and whether it facilitates decision making about procreation. Second, we endeavour to identify pretest predictors of psychological adaptation one year after the predictive test (psychometric evaluation of general anxiety, depression level, and ego strength). The impact of the predictive test result was assessed in 53 subjects tested, using pre- and post-test psychometric measurement and self-report data of follow up interviews. Mean anxiety and depression levels were significantly decreased one year after a good test result; there was no significant change in the case of a bad test result. The mean personality profile, including ego strength, remained unchanged one year after the test. The study further shows that the test result had a definite impact on reproductive decision making. Stepwise multiple regression analyses were used to select the best predictors of the subject's post-test reactions. The results indicate that a careful evaluation of pretest ego strength, depression level, and coping strategies may be helpful in predicting post-test reactions, independently of the carrier status. Test result (carrier/ non-carrier), gender, and age did not significantly contribute to the prediction. About one third of the variance of post-test anxiety and depression level and more than half of the variance of ego strength was explained, implying that other psychological or social aspects should also be taken into account when predicting individual post-test reactions. PMID:8880572

How to test for partially predictable chaos.

Science.gov (United States)

Wernecke, Hendrik; Sándor, Bulcsú; Gros, Claudius

2017-04-24

For a chaotic system pairs of initially close-by trajectories become eventually fully uncorrelated on the attracting set. This process of decorrelation can split into an initial exponential decrease and a subsequent diffusive process on the chaotic attractor causing the final loss of predictability. Both processes can be either of the same or of very different time scales. In the latter case the two trajectories linger within a finite but small distance (with respect to the overall extent of the attractor) for exceedingly long times and remain partially predictable. Standard tests for chaos widely use inter-orbital correlations as an indicator. However, testing partially predictable chaos yields mostly ambiguous results, as this type of chaos is characterized by attractors of fractally broadened braids. For a resolution we introduce a novel 0-1 indicator for chaos based on the cross-distance scaling of pairs of initially close trajectories. This test robustly discriminates chaos, including partially predictable chaos, from laminar flow. Additionally using the finite time cross-correlation of pairs of initially close trajectories, we are able to identify laminar flow as well as strong and partially predictable chaos in a 0-1 manner solely from the properties of pairs of trajectories.

Novel applications of multitask learning and multiple output regression to multiple genetic trait prediction.

Science.gov (United States)

He, Dan; Kuhn, David; Parida, Laxmi

2016-06-15

Given a set of biallelic molecular markers, such as SNPs, with genotype values encoded numerically on a collection of plant, animal or human samples, the goal of genetic trait prediction is to predict the quantitative trait values by simultaneously modeling all marker effects. Genetic trait prediction is usually represented as linear regression models. In many cases, for the same set of samples and markers, multiple traits are observed. Some of these traits might be correlated with each other. Therefore, modeling all the multiple traits together may improve the prediction accuracy. In this work, we view the multitrait prediction problem from a machine learning angle: as either a multitask learning problem or a multiple output regression problem, depending on whether different traits share the same genotype matrix or not. We then adapted multitask learning algorithms and multiple output regression algorithms to solve the multitrait prediction problem. We proposed a few strategies to improve the least square error of the prediction from these algorithms. Our experiments show that modeling multiple traits together could improve the prediction accuracy for correlated traits. The programs we used are either public or directly from the referred authors, such as MALSAR (http://www.public.asu.edu/~jye02/Software/MALSAR/) package. The Avocado data set has not been published yet and is available upon request. dhe@us.ibm.com. © The Author 2016. Published by Oxford University Press.

Testing protects against proactive interference in face-name learning.

Science.gov (United States)

Weinstein, Yana; McDermott, Kathleen B; Szpunar, Karl K

2011-06-01

Learning face-name pairings at a social function becomes increasingly more difficult the more individuals one meets. This phenomenon is attributable to proactive interference--the negative influence of prior learning on subsequent learning. Recent evidence suggests that taking a memory test can alleviate proactive interference in verbal list learning paradigms. We apply this technique to face-name pair learning. Participants studied four lists of 12 face-name pairings and either attempted to name the 12 faces just studied after every list or did not. Recall attempts after every list improved learning of the fourth list by over 100%. Moreover, no reduction in learning of face-name pairings occurred from list 1 to list 4 for participants who attempted to name studied faces between lists. These results suggest that testing oneself on the names of a group of new acquaintances before moving on to the next group is an effective mnemonic technique for social functions.

Machine learning methods for metabolic pathway prediction

Directory of Open Access Journals (Sweden)

Karp Peter D

2010-01-01

Full Text Available Abstract Background A key challenge in systems biology is the reconstruction of an organism's metabolic network from its genome sequence. One strategy for addressing this problem is to predict which metabolic pathways, from a reference database of known pathways, are present in the organism, based on the annotated genome of the organism. Results To quantitatively validate methods for pathway prediction, we developed a large "gold standard" dataset of 5,610 pathway instances known to be present or absent in curated metabolic pathway databases for six organisms. We defined a collection of 123 pathway features, whose information content we evaluated with respect to the gold standard. Feature data were used as input to an extensive collection of machine learning (ML methods, including naïve Bayes, decision trees, and logistic regression, together with feature selection and ensemble methods. We compared the ML methods to the previous PathoLogic algorithm for pathway prediction using the gold standard dataset. We found that ML-based prediction methods can match the performance of the PathoLogic algorithm. PathoLogic achieved an accuracy of 91% and an F-measure of 0.786. The ML-based prediction methods achieved accuracy as high as 91.2% and F-measure as high as 0.787. The ML-based methods output a probability for each predicted pathway, whereas PathoLogic does not, which provides more information to the user and facilitates filtering of predicted pathways. Conclusions ML methods for pathway prediction perform as well as existing methods, and have qualitative advantages in terms of extensibility, tunability, and explainability. More advanced prediction methods and/or more sophisticated input features may improve the performance of ML methods. However, pathway prediction performance appears to be limited largely by the ability to correctly match enzymes to the reactions they catalyze based on genome annotations.

Machine learning methods for metabolic pathway prediction

Science.gov (United States)

2010-01-01

Background A key challenge in systems biology is the reconstruction of an organism's metabolic network from its genome sequence. One strategy for addressing this problem is to predict which metabolic pathways, from a reference database of known pathways, are present in the organism, based on the annotated genome of the organism. Results To quantitatively validate methods for pathway prediction, we developed a large "gold standard" dataset of 5,610 pathway instances known to be present or absent in curated metabolic pathway databases for six organisms. We defined a collection of 123 pathway features, whose information content we evaluated with respect to the gold standard. Feature data were used as input to an extensive collection of machine learning (ML) methods, including naïve Bayes, decision trees, and logistic regression, together with feature selection and ensemble methods. We compared the ML methods to the previous PathoLogic algorithm for pathway prediction using the gold standard dataset. We found that ML-based prediction methods can match the performance of the PathoLogic algorithm. PathoLogic achieved an accuracy of 91% and an F-measure of 0.786. The ML-based prediction methods achieved accuracy as high as 91.2% and F-measure as high as 0.787. The ML-based methods output a probability for each predicted pathway, whereas PathoLogic does not, which provides more information to the user and facilitates filtering of predicted pathways. Conclusions ML methods for pathway prediction perform as well as existing methods, and have qualitative advantages in terms of extensibility, tunability, and explainability. More advanced prediction methods and/or more sophisticated input features may improve the performance of ML methods. However, pathway prediction performance appears to be limited largely by the ability to correctly match enzymes to the reactions they catalyze based on genome annotations. PMID:20064214

A semi-supervised learning approach for RNA secondary structure prediction.

Science.gov (United States)

Yonemoto, Haruka; Asai, Kiyoshi; Hamada, Michiaki

2015-08-01

RNA secondary structure prediction is a key technology in RNA bioinformatics. Most algorithms for RNA secondary structure prediction use probabilistic models, in which the model parameters are trained with reliable RNA secondary structures. Because of the difficulty of determining RNA secondary structures by experimental procedures, such as NMR or X-ray crystal structural analyses, there are still many RNA sequences that could be useful for training whose secondary structures have not been experimentally determined. In this paper, we introduce a novel semi-supervised learning approach for training parameters in a probabilistic model of RNA secondary structures in which we employ not only RNA sequences with annotated secondary structures but also ones with unknown secondary structures. Our model is based on a hybrid of generative (stochastic context-free grammars) and discriminative models (conditional random fields) that has been successfully applied to natural language processing. Computational experiments indicate that the accuracy of secondary structure prediction is improved by incorporating RNA sequences with unknown secondary structures into training. To our knowledge, this is the first study of a semi-supervised learning approach for RNA secondary structure prediction. This technique will be useful when the number of reliable structures is limited. Copyright © 2015 Elsevier Ltd. All rights reserved.

Genetic Learning of Fuzzy Parameters in Predictive and Decision Support Modelling

Directory of Open Access Journals (Sweden)

Nebot

2012-04-01

Full Text Available In this research a genetic fuzzy system (GFS is proposed that performs discretization parameter learning in the context of the Fuzzy Inductive Reasoning (FIR methodology and the Linguistic Rule FIR (LR-FIR algorithm. The main goal of the GFS is to take advantage of the potentialities of GAs to learn the fuzzification parameters of the FIR and LR-FIR approaches in order to obtain reliable and useful predictive (FIR models and decision support (LR-FIR models. The GFS is evaluated in an e-learning context.

A Tool for Predicting Regulatory Approval After Phase II Testing of New Oncology Compounds.

Science.gov (United States)

DiMasi, J A; Hermann, J C; Twyman, K; Kondru, R K; Stergiopoulos, S; Getz, K A; Rackoff, W

2015-11-01

We developed an algorithm (ANDI) for predicting regulatory marketing approval for new cancer drugs after phase II testing has been conducted, with the objective of providing a tool to improve drug portfolio decision-making. We examined 98 oncology drugs from the top 50 pharmaceutical companies (2006 sales) that first entered clinical development from 1999 to 2007, had been taken to at least phase II development, and had a known final outcome (research abandonment or regulatory marketing approval). Data on safety, efficacy, operational, market, and company characteristics were obtained from public sources. Logistic regression and machine-learning methods were used to provide an unbiased approach to assess overall predictability and to identify the most important individual predictors. We found that a simple four-factor model (activity, number of patients in the pivotal phase II trial, phase II duration, and a prevalence-related measure) had high sensitivity and specificity for predicting regulatory marketing approval. © 2015 American Society for Clinical Pharmacology and Therapeutics.

Caudate nucleus reactivity predicts perceptual learning rate for visual feature conjunctions.

Science.gov (United States)

Reavis, Eric A; Frank, Sebastian M; Tse, Peter U

2015-04-15

Useful information in the visual environment is often contained in specific conjunctions of visual features (e.g., color and shape). The ability to quickly and accurately process such conjunctions can be learned. However, the neural mechanisms responsible for such learning remain largely unknown. It has been suggested that some forms of visual learning might involve the dopaminergic neuromodulatory system (Roelfsema et al., 2010; Seitz and Watanabe, 2005), but this hypothesis has not yet been directly tested. Here we test the hypothesis that learning visual feature conjunctions involves the dopaminergic system, using functional neuroimaging, genetic assays, and behavioral testing techniques. We use a correlative approach to evaluate potential associations between individual differences in visual feature conjunction learning rate and individual differences in dopaminergic function as indexed by neuroimaging and genetic markers. We find a significant correlation between activity in the caudate nucleus (a component of the dopaminergic system connected to visual areas of the brain) and visual feature conjunction learning rate. Specifically, individuals who showed a larger difference in activity between positive and negative feedback on an unrelated cognitive task, indicative of a more reactive dopaminergic system, learned visual feature conjunctions more quickly than those who showed a smaller activity difference. This finding supports the hypothesis that the dopaminergic system is involved in visual learning, and suggests that visual feature conjunction learning could be closely related to associative learning. However, no significant, reliable correlations were found between feature conjunction learning and genotype or dopaminergic activity in any other regions of interest. Copyright © 2015 Elsevier Inc. All rights reserved.

Global discriminative learning for higher-accuracy computational gene prediction.

Directory of Open Access Journals (Sweden)

Axel Bernal

2007-03-01

Full Text Available Most ab initio gene predictors use a probabilistic sequence model, typically a hidden Markov model, to combine separately trained models of genomic signals and content. By combining separate models of relevant genomic features, such gene predictors can exploit small training sets and incomplete annotations, and can be trained fairly efficiently. However, that type of piecewise training does not optimize prediction accuracy and has difficulty in accounting for statistical dependencies among different parts of the gene model. With genomic information being created at an ever-increasing rate, it is worth investigating alternative approaches in which many different types of genomic evidence, with complex statistical dependencies, can be integrated by discriminative learning to maximize annotation accuracy. Among discriminative learning methods, large-margin classifiers have become prominent because of the success of support vector machines (SVM in many classification tasks. We describe CRAIG, a new program for ab initio gene prediction based on a conditional random field model with semi-Markov structure that is trained with an online large-margin algorithm related to multiclass SVMs. Our experiments on benchmark vertebrate datasets and on regions from the ENCODE project show significant improvements in prediction accuracy over published gene predictors that use intrinsic features only, particularly at the gene level and on genes with long introns.

Using Machine Learning to Predict MCNP Bias

Energy Technology Data Exchange (ETDEWEB)

Grechanuk, Pavel Aleksandrovi [Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

2018-01-09