Science.gov

Sample records for machine learning methods

  1. Machine learning methods in chemoinformatics

    PubMed Central

    Mitchell, John B O

    2014-01-01

    Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure–activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers. WIREs Comput Mol Sci 2014, 4:468–481. How to cite this article: WIREs Comput Mol Sci 2014, 4:468–481. doi:10.1002/wcms.1183 PMID:25285160

  2. Machine Learning methods for Quantitative Radiomic Biomarkers

    PubMed Central

    Parmar, Chintan; Grossmann, Patrick; Bussink, Johan; Lambin, Philippe; Aerts, Hugo J. W. L.

    2015-01-01

    Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice. PMID:26278466

  3. Machine Learning methods for Quantitative Radiomic Biomarkers.

    PubMed

    Parmar, Chintan; Grossmann, Patrick; Bussink, Johan; Lambin, Philippe; Aerts, Hugo J W L

    2015-08-17

    Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

  4. Multi-Stage Convex Relaxation Methods for Machine Learning

    DTIC Science & Technology

    2013-03-01

    Many problems in machine learning can be naturally formulated as non-convex optimization problems. However, such direct nonconvex formulations have...original nonconvex formulation. We will develop theoretical properties of this method and algorithmic consequences. Related convex and nonconvex machine learning methods will also be investigated.

  5. Studying depression using imaging and machine learning methods.

    PubMed

    Patel, Meenal J; Khalaf, Alexander; Aizenstein, Howard J

    2016-01-01

    Depression is a complex clinical entity that can pose challenges for clinicians regarding both accurate diagnosis and effective timely treatment. These challenges have prompted the development of multiple machine learning methods to help improve the management of this disease. These methods utilize anatomical and physiological data acquired from neuroimaging to create models that can identify depressed patients vs. non-depressed patients and predict treatment outcomes. This article (1) presents a background on depression, imaging, and machine learning methodologies; (2) reviews methodologies of past studies that have used imaging and machine learning to study depression; and (3) suggests directions for future depression-related studies.

  6. Risk prediction with machine learning and regression methods.

    PubMed

    Steyerberg, Ewout W; van der Ploeg, Tjeerd; Van Calster, Ben

    2014-07-01

    This is a discussion of issues in risk prediction based on the following papers: "Probability estimation with machine learning methods for dichotomous and multicategory outcome: Theory" by Jochen Kruppa, Yufeng Liu, Gérard Biau, Michael Kohler, Inke R. König, James D. Malley, and Andreas Ziegler; and "Probability estimation with machine learning methods for dichotomous and multicategory outcome: Applications" by Jochen Kruppa, Yufeng Liu, Hans-Christian Diener, Theresa Holste, Christian Weimar, Inke R. König, and Andreas Ziegler.

  7. In silico machine learning methods in drug development.

    PubMed

    Dobchev, Dimitar A; Pillai, Girinath G; Karelson, Mati

    2014-01-01

    Machine learning (ML) computational methods for predicting compounds with pharmacological activity, specific pharmacodynamic and ADMET (absorption, distribution, metabolism, excretion and toxicity) properties are being increasingly applied in drug discovery and evaluation. Recently, machine learning techniques such as artificial neural networks, support vector machines and genetic programming have been explored for predicting inhibitors, antagonists, blockers, agonists, activators and substrates of proteins related to specific therapeutic targets. These methods are particularly useful for screening compound libraries of diverse chemical structures, "noisy" and high-dimensional data to complement QSAR methods, and in cases of unavailable receptor 3D structure to complement structure-based methods. A variety of studies have demonstrated the potential of machine-learning methods for predicting compounds as potential drug candidates. The present review is intended to give an overview of the strategies and current progress in using machine learning methods for drug design and the potential of the respective model development tools. We also regard a number of applications of the machine learning algorithms based on common classes of diseases.

  8. Machine Learning

    NASA Astrophysics Data System (ADS)

    Hoffmann, Achim; Mahidadia, Ashesh

    The purpose of this chapter is to present fundamental ideas and techniques of machine learning suitable for the field of this book, i.e., for automated scientific discovery. The chapter focuses on those symbolic machine learning methods, which produce results that are suitable to be interpreted and understood by humans. This is particularly important in the context of automated scientific discovery as the scientific theories to be produced by machines are usually meant to be interpreted by humans. This chapter contains some of the most influential ideas and concepts in machine learning research to give the reader a basic insight into the field. After the introduction in Sect. 1, general ideas of how learning problems can be framed are given in Sect. 2. The section provides useful perspectives to better understand what learning algorithms actually do. Section 3 presents the Version space model which is an early learning algorithm as well as a conceptual framework, that provides important insight into the general mechanisms behind most learning algorithms. In section 4, a family of learning algorithms, the AQ family for learning classification rules is presented. The AQ family belongs to the early approaches in machine learning. The next, Sect. 5 presents the basic principles of decision tree learners. Decision tree learners belong to the most influential class of inductive learning algorithms today. Finally, a more recent group of learning systems are presented in Sect. 6, which learn relational concepts within the framework of logic programming. This is a particularly interesting group of learning systems since the framework allows also to incorporate background knowledge which may assist in generalisation. Section 7 discusses Association Rules - a technique that comes from the related field of Data mining. Section 8 presents the basic idea of the Naive Bayesian Classifier. While this is a very popular learning technique, the learning result is not well suited for

  9. Osteoporosis risk prediction using machine learning and conventional methods.

    PubMed

    Kim, Sung Kean; Yoo, Tae Keun; Oh, Ein; Kim, Deok Won

    2013-01-01

    A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women, and compared with the ability of a conventional clinical decision tool, osteoporosis self-assessment tool (OST). We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Surveys (KNHANES V-1). The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests (RF), artificial neural networks (ANN), and logistic regression (LR) based on various predictors associated with low bone density. The learning models were compared with OST. SVM had significantly better area under the curve (AUC) of the receiver operating characteristic (ROC) than ANN, LR, and OST. Validation on the test set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0%. We were the first to perform comparisons of the performance of osteoporosis prediction between the machine learning and conventional methods using population-based epidemiological data. The machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

  10. Machine learning methods without tears: a primer for ecologists.

    PubMed

    Olden, Julian D; Lawler, Joshua J; Poff, N LeRoy

    2008-06-01

    Machine learning methods, a family of statistical techniques with origins in the field of artificial intelligence, are recognized as holding great promise for the advancement of understanding and prediction about ecological phenomena. These modeling techniques are flexible enough to handle complex problems with multiple interacting elements and typically outcompete traditional approaches (e.g., generalized linear models), making them ideal for modeling ecological systems. Despite their inherent advantages, a review of the literature reveals only a modest use of these approaches in ecology as compared to other disciplines. One potential explanation for this lack of interest is that machine learning techniques do not fall neatly into the class of statistical modeling approaches with which most ecologists are familiar. In this paper, we provide an introduction to three machine learning approaches that can be broadly used by ecologists: classification and regression trees, artificial neural networks, and evolutionary computation. For each approach, we provide a brief background to the methodology, give examples of its application in ecology, describe model development and implementation, discuss strengths and weaknesses, explore the availability of statistical software, and provide an illustrative example. Although the ecological application of machine learning approaches has increased, there remains considerable skepticism with respect to the role of these techniques in ecology. Our review encourages a greater understanding of machin learning approaches and promotes their future application and utilization, while also providing a basis from which ecologists can make informed decisions about whether to select or avoid these approaches in their future modeling endeavors.

  11. Oceanic eddy detection and lifetime forecast using machine learning methods

    NASA Astrophysics Data System (ADS)

    Ashkezari, Mohammad D.; Hill, Christopher N.; Follett, Christopher N.; Forget, Gaël.; Follows, Michael J.

    2016-12-01

    We report a novel altimetry-based machine learning approach for eddy identification and characterization. The machine learning models use daily maps of geostrophic velocity anomalies and are trained according to the phase angle between the zonal and meridional components at each grid point. The trained models are then used to identify the corresponding eddy phase patterns and to predict the lifetime of a detected eddy structure. The performance of the proposed method is examined at two dynamically different regions to demonstrate its robust behavior and region independency.

  12. Plasma disruption prediction using machine learning methods: DIII-D

    NASA Astrophysics Data System (ADS)

    Lupin-Jimenez, L.; Kolemen, E.; Eldon, D.; Eidietis, N.

    2016-10-01

    Plasma disruption prediction is becoming more important with the development of larger tokamaks, due to the larger amount of thermal and magnetic energy that can be stored. By accurately predicting an impending disruption, the disruption's impact can be mitigated or, better, prevented. Recent approaches to disruption prediction have been through implementation of machine learning methods, which characterize raw and processed diagnostic data to develop accurate prediction models. Using disruption trials from the DIII-D database, the effectiveness of different machine learning methods are characterized. Developed real time disruption prediction approaches are focused on tearing and locking modes. Machine learning methods used include random forests, multilayer perceptrons, and traditional regression analysis. The algorithms are trained with data within short time frames, and whether or not a disruption occurs within the time window after the end of the frame. Initial results from the machine learning algorithms will be presented. Work supported by US DOE under the Science Undergraduate Laboratory Internship (SULI) program, DE-FC02-04ER54698, and DE-AC02-09CH11466.

  13. Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

    PubMed Central

    Belo, David; Gamboa, Hugo

    2017-01-01

    The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components. PMID:28831239

  14. Machine Learning Methods for Articulatory Data

    ERIC Educational Resources Information Center

    Berry, Jeffrey James

    2012-01-01

    Humans make use of more than just the audio signal to perceive speech. Behavioral and neurological research has shown that a person's knowledge of how speech is produced influences what is perceived. With methods for collecting articulatory data becoming more ubiquitous, methods for extracting useful information are needed to make this data…

  15. Machine Learning Methods for Articulatory Data

    ERIC Educational Resources Information Center

    Berry, Jeffrey James

    2012-01-01

    Humans make use of more than just the audio signal to perceive speech. Behavioral and neurological research has shown that a person's knowledge of how speech is produced influences what is perceived. With methods for collecting articulatory data becoming more ubiquitous, methods for extracting useful information are needed to make this data…

  16. Machine Learning and Data Mining Methods in Diabetes Research.

    PubMed

    Kavakiotis, Ioannis; Tsave, Olga; Salifoglou, Athanasios; Maglaveras, Nicos; Vlahavas, Ioannis; Chouvarda, Ioanna

    2017-01-01

    The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.

  17. Adaptive Kernel Based Machine Learning Methods

    DTIC Science & Technology

    2012-10-15

    Multiscale collocation methods are developed in [3] for solving a system of integral equations which is a reformulation of the Tikhonov - regularized ...Direct numerical solutions of the Tikhonov regularization equation require one to gener- ate a matrix representation of the composition of the...issue, rather than directly solving the Tikhonov - regularized equation, we propose to solve an equivalent coupled system of integral equations. We apply a

  18. Machine Learning Methods for Attack Detection in the Smart Grid.

    PubMed

    Ozay, Mete; Esnaola, Inaki; Yarman Vural, Fatos Tunay; Kulkarni, Sanjeev R; Poor, H Vincent

    2016-08-01

    Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semisupervised) are employed with decision- and feature-level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than attack detection algorithms that employ state vector estimation methods in the proposed attack detection framework.

  19. Machine Learning

    DTIC Science & Technology

    1990-04-01

    DTIC i.LE COPY RADC-TR-90-25 Final Technical Report April 1990 MACHINE LEARNING The MITRE Corporation Melissa P. Chase Cs) CTIC ’- CT E 71 IN 2 11990...S. FUNDING NUMBERS MACHINE LEARNING C - F19628-89-C-0001 PE - 62702F PR - MOlE S. AUTHO(S) TA - 79 Melissa P. Chase WUT - 80 S. PERFORMING...341.280.5500 pm I " Aw Sig rill Ia 2110-01 SECTION 1 INTRODUCTION 1.1 BACKGROUND Research in machine learning has taken two directions in the problem of

  20. Newton Methods for Large Scale Problems in Machine Learning

    ERIC Educational Resources Information Center

    Hansen, Samantha Leigh

    2014-01-01

    The focus of this thesis is on practical ways of designing optimization algorithms for minimizing large-scale nonlinear functions with applications in machine learning. Chapter 1 introduces the overarching ideas in the thesis. Chapters 2 and 3 are geared towards supervised machine learning applications that involve minimizing a sum of loss…

  1. Newton Methods for Large Scale Problems in Machine Learning

    ERIC Educational Resources Information Center

    Hansen, Samantha Leigh

    2014-01-01

    The focus of this thesis is on practical ways of designing optimization algorithms for minimizing large-scale nonlinear functions with applications in machine learning. Chapter 1 introduces the overarching ideas in the thesis. Chapters 2 and 3 are geared towards supervised machine learning applications that involve minimizing a sum of loss…

  2. Supervised Machine Learning Methods Applied to Predict Ligand- Binding Affinity.

    PubMed

    Heck, Gabriela S; Pintro, Val O; Pereira, Richard R; de Ávila, Mauricio B; Levin, Nayara M B; de Azevedo, Walter F

    2017-01-01

    Calculation of ligand-binding affinity is an open problem in computational medicinal chemistry. The ability to computationally predict affinities has a beneficial impact in the early stages of drug development, since it allows a mathematical model to assess protein-ligand interactions. Due to the availability of structural and binding information, machine learning methods have been applied to generate scoring functions with good predictive power. Our goal here is to review recent developments in the application of machine learning methods to predict ligand-binding affinity. We focus our review on the application of computational methods to predict binding affinity for protein targets. In addition, we also describe the major available databases for experimental binding constants and protein structures. Furthermore, we explain the most successful methods to evaluate the predictive power of scoring functions. Association of structural information with ligand-binding affinity makes it possible to generate scoring functions targeted to a specific biological system. Through regression analysis, this data can be used as a base to generate mathematical models to predict ligandbinding affinities, such as inhibition constant, dissociation constant and binding energy. Experimental biophysical techniques were able to determine the structures of over 120,000 macromolecules. Considering also the evolution of binding affinity information, we may say that we have a promising scenario for development of scoring functions, making use of machine learning techniques. Recent developments in this area indicate that building scoring functions targeted to the biological systems of interest shows superior predictive performance, when compared with other approaches. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  3. Extremely Randomized Machine Learning Methods for Compound Activity Prediction.

    PubMed

    Czarnecki, Wojciech M; Podlewska, Sabina; Bojarski, Andrzej J

    2015-11-09

    Speed, a relatively low requirement for computational resources and high effectiveness of the evaluation of the bioactivity of compounds have caused a rapid growth of interest in the application of machine learning methods to virtual screening tasks. However, due to the growth of the amount of data also in cheminformatics and related fields, the aim of research has shifted not only towards the development of algorithms of high predictive power but also towards the simplification of previously existing methods to obtain results more quickly. In the study, we tested two approaches belonging to the group of so-called 'extremely randomized methods'-Extreme Entropy Machine and Extremely Randomized Trees-for their ability to properly identify compounds that have activity towards particular protein targets. These methods were compared with their 'non-extreme' competitors, i.e., Support Vector Machine and Random Forest. The extreme approaches were not only found out to improve the efficiency of the classification of bioactive compounds, but they were also proved to be less computationally complex, requiring fewer steps to perform an optimization procedure.

  4. A Photometric Machine-Learning Method to Infer Stellar Metallicity

    NASA Technical Reports Server (NTRS)

    Miller, Adam A.

    2015-01-01

    Following its formation, a star's metal content is one of the few factors that can significantly alter its evolution. Measurements of stellar metallicity ([Fe/H]) typically require a spectrum, but spectroscopic surveys are limited to a few x 10(exp 6) targets; photometric surveys, on the other hand, have detected > 10(exp 9) stars. I present a new machine-learning method to predict [Fe/H] from photometric colors measured by the Sloan Digital Sky Survey (SDSS). The training set consists of approx. 120,000 stars with SDSS photometry and reliable [Fe/H] measurements from the SEGUE Stellar Parameters Pipeline (SSPP). For bright stars (g' < or = 18 mag), with 4500 K < or = Teff < or = 7000 K, corresponding to those with the most reliable SSPP estimates, I find that the model predicts [Fe/H] values with a root-mean-squared-error (RMSE) of approx.0.27 dex. The RMSE from this machine-learning method is similar to the scatter in [Fe/H] measurements from low-resolution spectra..

  5. Using Wolfe's Method in Support Vector Machines Learning Stage

    NASA Astrophysics Data System (ADS)

    Frausto-Solís, Juan; González-Mendoza, Miguel; López-Díaz, Roberto

    In this paper, the application of Wolfe’s method in Support Vector Machines learning stage is presented. This stage is usually performed by solving a quadratic programming problem and a common approach for solving it, is breaking down that problem in smaller subproblems easier to solve and manage. In this manner, instead of dividing the problem, the application of Wolfe’s method is proposed. The method transforms a quadratic programming problem into an Equivalent Linear Model and uses a variation of simplex method employed in linear programming. The proposed approach is compared against QuadProg Matlab function used to solve quadratic programming problems. Experimental results show that the proposed approach has better quality of classification compared with that function.

  6. Machine Learning Methods for Predicting HLA–Peptide Binding Activity

    PubMed Central

    Luo, Heng; Ye, Hao; Ng, Hui Wen; Shi, Leming; Tong, Weida; Mendrick, Donna L.; Hong, Huixiao

    2015-01-01

    As major histocompatibility complexes in humans, the human leukocyte antigens (HLAs) have important functions to present antigen peptides onto T-cell receptors for immunological recognition and responses. Interpreting and predicting HLA–peptide binding are important to study T-cell epitopes, immune reactions, and the mechanisms of adverse drug reactions. We review different types of machine learning methods and tools that have been used for HLA–peptide binding prediction. We also summarize the descriptors based on which the HLA–peptide binding prediction models have been constructed and discuss the limitation and challenges of the current methods. Lastly, we give a future perspective on the HLA–peptide binding prediction method based on network analysis. PMID:26512199

  7. A survey of machine learning methods for secondary and supersecondary protein structure prediction.

    PubMed

    Ho, Hui Kian; Zhang, Lei; Ramamohanarao, Kotagiri; Martin, Shawn

    2013-01-01

    In this chapter we provide a survey of protein secondary and supersecondary structure prediction using methods from machine learning. Our focus is on machine learning methods applicable to β-hairpin and β-sheet prediction, but we also discuss methods for more general supersecondary structure prediction. We provide background on the secondary and supersecondary structures that we discuss, the features used to describe them, and the basic theory behind the machine learning methods used. We survey the machine learning methods available for secondary and supersecondary structure prediction and compare them where possible.

  8. A review for detecting gene-gene interactions using machine learning methods in genetic epidemiology.

    PubMed

    Koo, Ching Lee; Liew, Mei Jing; Mohamad, Mohd Saberi; Salleh, Abdul Hakim Mohamed

    2013-01-01

    Recently, the greatest statistical computational challenge in genetic epidemiology is to identify and characterize the genes that interact with other genes and environment factors that bring the effect on complex multifactorial disease. These gene-gene interactions are also denoted as epitasis in which this phenomenon cannot be solved by traditional statistical method due to the high dimensionality of the data and the occurrence of multiple polymorphism. Hence, there are several machine learning methods to solve such problems by identifying such susceptibility gene which are neural networks (NNs), support vector machine (SVM), and random forests (RFs) in such common and multifactorial disease. This paper gives an overview on machine learning methods, describing the methodology of each machine learning methods and its application in detecting gene-gene and gene-environment interactions. Lastly, this paper discussed each machine learning method and presents the strengths and weaknesses of each machine learning method in detecting gene-gene interactions in complex human disease.

  9. Introduction to machine learning.

    PubMed

    Baştanlar, Yalin; Ozuysal, Mustafa

    2014-01-01

    The machine learning field, which can be briefly defined as enabling computers make successful predictions using past experiences, has exhibited an impressive development recently with the help of the rapid increase in the storage capacity and processing power of computers. Together with many other disciplines, machine learning methods have been widely employed in bioinformatics. The difficulties and cost of biological analyses have led to the development of sophisticated machine learning approaches for this application area. In this chapter, we first review the fundamental concepts of machine learning such as feature assessment, unsupervised versus supervised learning and types of classification. Then, we point out the main issues of designing machine learning experiments and their performance evaluation. Finally, we introduce some supervised learning methods.

  10. Approaches to Machine Learning.

    DTIC Science & Technology

    1984-02-16

    The field of machine learning strives to develop methods and techniques to automatic the acquisition of new information, new skills, and new ways of organizing existing information. In this article, we review the major approaches to machine learning in symbolic domains, covering the tasks of learning concepts from examples, learning search methods, conceptual clustering, and language acquisition. We illustrate each of the basic approaches with paradigmatic examples. (Author)

  11. Machine-learning approaches in drug discovery: methods and applications.

    PubMed

    Lavecchia, Antonio

    2015-03-01

    During the past decade, virtual screening (VS) has evolved from traditional similarity searching, which utilizes single reference compounds, into an advanced application domain for data mining and machine-learning approaches, which require large and representative training-set compounds to learn robust decision rules. The explosive growth in the amount of public domain-available chemical and biological data has generated huge effort to design, analyze, and apply novel learning methodologies. Here, I focus on machine-learning techniques within the context of ligand-based VS (LBVS). In addition, I analyze several relevant VS studies from recent publications, providing a detailed view of the current state-of-the-art in this field and highlighting not only the problematic issues, but also the successes and opportunities for further advances. Copyright © 2014 Elsevier Ltd. All rights reserved.

  12. A novel virtual viewpoint merging method based on machine learning

    NASA Astrophysics Data System (ADS)

    Zheng, Di; Peng, Zongju; Wang, Hui; Jiang, Gangyi; Chen, Fen

    2014-11-01

    In multi-view video system, multiple video plus depth is main data format of 3D scene representation. Continuous virtual views can be generated by using depth image based rendering (DIBR) technique. DIBR process includes geometric mapping, hole filling and merging. Unique weights, inversely proportional to the distance between the virtual and real cameras, are used to merge the virtual views. However, the weights might not the optimal ones in terms of virtual view quality. In this paper, a novel virtual view merging algorithm is proposed. In the proposed algorithm, machine learning method is utilized to establish an optimal weight model. In the model, color, depth, color gradient and sequence parameters are taken into consideration. Firstly, we render the same virtual view from left and right views, and select the training samples by using a threshold. Then, the eigenvalues of the samples are extracted and the optimal merging weights are calculated as training labels. Finally, support vector classifier (SVC) is adopted to establish the model which is used for guiding virtual views rendering. Experimental results show that the proposed method can improve the quality of virtual views for most sequences. Especially, it is effective in the case of large distance between the virtual and real cameras. And compared to the original method of virtual view synthesis, the proposed method can obtain more than 0.1dB gain for some sequences.

  13. Recent Advances in Conotoxin Classification by Using Machine Learning Methods.

    PubMed

    Dao, Fu-Ying; Yang, Hui; Su, Zhen-Dong; Yang, Wuritu; Wu, Yun; Hui, Ding; Chen, Wei; Tang, Hua; Lin, Hao

    2017-06-25

    Conotoxins are disulfide-rich small peptides, which are invaluable peptides that target ion channel and neuronal receptors. Conotoxins have been demonstrated as potent pharmaceuticals in the treatment of a series of diseases, such as Alzheimer's disease, Parkinson's disease, and epilepsy. In addition, conotoxins are also ideal molecular templates for the development of new drug lead compounds and play important roles in neurobiological research as well. Thus, the accurate identification of conotoxin types will provide key clues for the biological research and clinical medicine. Generally, conotoxin types are confirmed when their sequence, structure, and function are experimentally validated. However, it is time-consuming and costly to acquire the structure and function information by using biochemical experiments. Therefore, it is important to develop computational tools for efficiently and effectively recognizing conotoxin types based on sequence information. In this work, we reviewed the current progress in computational identification of conotoxins in the following aspects: (i) construction of benchmark dataset; (ii) strategies for extracting sequence features; (iii) feature selection techniques; (iv) machine learning methods for classifying conotoxins; (v) the results obtained by these methods and the published tools; and (vi) future perspectives on conotoxin classification. The paper provides the basis for in-depth study of conotoxins and drug therapy research.

  14. Survey of Machine Learning Methods for Database Security

    NASA Astrophysics Data System (ADS)

    Kamra, Ashish; Ber, Elisa

    Application of machine learning techniques to database security is an emerging area of research. In this chapter, we present a survey of various approaches that use machine learning/data mining techniques to enhance the traditional security mechanisms of databases. There are two key database security areas in which these techniques have found applications, namely, detection of SQL Injection attacks and anomaly detection for defending against insider threats. Apart from the research prototypes and tools, various third-party commercial products are also available that provide database activity monitoring solutions by profiling database users and applications. We present a survey of such products. We end the chapter with a primer on mechanisms for responding to database anomalies.

  15. Computerization of Hungarian reforestation manual with machine learning methods

    NASA Astrophysics Data System (ADS)

    Czimber, Kornél; Gálos, Borbála; Mátyás, Csaba; Bidló, András; Gribovszki, Zoltán

    2017-04-01

    Hungarian forests are highly sensitive to the changing climate, especially to the available precipitation amount. Over the past two decades several drought damages were observed for tree species which are in the lower xeric limit of their distribution. From year to year these affected forest stands become more difficult to reforest with the same native species because these are not able to adapt to the increasing probability of droughts. The climate related parameter set of the Hungarian forest stand database needs updates. Air humidity that was formerly used to define the forest climate zones is not measured anymore and its value based on climate model outputs is highly uncertain. The aim was to develop a novel computerized and objective method to describe the species-specific climate conditions that is essential for survival, growth and optimal production of the forest ecosystems. The method is expected to project the species spatial distribution until 2100 on the basis of regional climate model simulations. Until now, Hungarian forest managers have been using a carefully edited spreadsheet for reforestation purposes. Applying binding regulations this spreadsheet prescribes the stand-forming and admixed tree species and their expected growth rate for each forest site types. We are going to present a new machine learning based method to replace the former spreadsheet. We took into great consideration of various methods, such as maximum likelihood, Bayesian networks, Fuzzy logic. The method calculates distributions, setups classification, which can be validated and modified by experts if necessary. Projected climate change conditions makes necessary to include into this system an additional climate zone that does not exist in our region now, as well as new options for potential tree species. In addition to or instead of the existing ones, the influence of further limiting parameters (climatic extremes, soil water retention) are also investigated. Results will be

  16. Paradigms for machine learning

    NASA Technical Reports Server (NTRS)

    Schlimmer, Jeffrey C.; Langley, Pat

    1991-01-01

    Five paradigms are described for machine learning: connectionist (neural network) methods, genetic algorithms and classifier systems, empirical methods for inducing rules and decision trees, analytic learning methods, and case-based approaches. Some dimensions are considered along with these paradigms vary in their approach to learning, and the basic methods are reviewed that are used within each framework, together with open research issues. It is argued that the similarities among the paradigms are more important than their differences, and that future work should attempt to bridge the existing boundaries. Finally, some recent developments in the field of machine learning are discussed, and their impact on both research and applications is examined.

  17. Assessing and comparison of different machine learning methods in parent-offspring trios for genotype imputation.

    PubMed

    Mikhchi, Abbas; Honarvar, Mahmood; Kashan, Nasser Emam Jomeh; Aminafshar, Mehdi

    2016-06-21

    Genotype imputation is an important tool for prediction of unknown genotypes for both unrelated individuals and parent-offspring trios. Several imputation methods are available and can either employ universal machine learning methods, or deploy algorithms dedicated to infer missing genotypes. In this research the performance of eight machine learning methods: Support Vector Machine, K-Nearest Neighbors, Extreme Learning Machine, Radial Basis Function, Random Forest, AdaBoost, LogitBoost, and TotalBoost compared in terms of the imputation accuracy, computation time and the factors affecting imputation accuracy. The methods employed using real and simulated datasets to impute the un-typed SNPs in parent-offspring trios. The tested methods show that imputation of parent-offspring trios can be accurate. The Random Forest and Support Vector Machine were more accurate than the other machine learning methods. The TotalBoost performed slightly worse than the other methods.The running times were different between methods. The ELM was always most fast algorithm. In case of increasing the sample size, the RBF requires long imputation time.The tested methods in this research can be an alternative for imputation of un-typed SNPs in low missing rate of data. However, it is recommended that other machine learning methods to be used for imputation.

  18. Comparative analysis of machine learning methods in ligand-based virtual screening of large compound libraries.

    PubMed

    Ma, Xiao H; Jia, Jia; Zhu, Feng; Xue, Ying; Li, Ze R; Chen, Yu Z

    2009-05-01

    Machine learning methods have been explored as ligand-based virtual screening tools for facilitating drug lead discovery. These methods predict compounds of specific pharmacodynamic, pharmacokinetic or toxicological properties based on their structure-derived structural and physicochemical properties. Increasing attention has been directed at these methods because of their capability in predicting compounds of diverse structures and complex structure-activity relationships without requiring the knowledge of target 3D structure. This article reviews current progresses in using machine learning methods for virtual screening of pharmacodynamically active compounds from large compound libraries, and analyzes and compares the reported performances of machine learning tools with those of structure-based and other ligand-based (such as pharmacophore and clustering) virtual screening methods. The feasibility to improve the performance of machine learning methods in screening large libraries is discussed.

  19. Machine Learning Method Applied in Readout System of Superheated Droplet Detector

    NASA Astrophysics Data System (ADS)

    Liu, Yi; Sullivan, Clair Julia; d'Errico, Francesco

    2017-07-01

    Direct readability is one advantage of superheated droplet detectors in neutron dosimetry. Utilizing such a distinct characteristic, an imaging readout system analyzes image of the detector for neutron dose readout. To improve the accuracy and precision of algorithms in the imaging readout system, machine learning algorithms were developed. Deep learning neural network and support vector machine algorithms are applied and compared with generally used Hough transform and curvature analysis methods. The machine learning methods showed a much higher accuracy and better precision in recognizing circular gas bubbles.

  20. Machine Learning for Education: Learning to Teach

    DTIC Science & Technology

    2016-12-01

    1 Machine Learning for Education: Learning to Teach Matthew C. Gombolay, Reed Jensen, Sung-Hyun Son Massachusetts Institute of Technology Lincoln...development and application of knowledge, but also in data analytics via machine learning. In this paper, we explore an array of machine learning...the tools they need to succeed [9], [12], [16], [25]. Researchers in artificial intelligence and machine learning have sought to develop methods for

  1. Machine learning method for knowledge discovery experimented with otoneurological data.

    PubMed

    Varpa, Kirsi; Iltanen, Kati; Juhola, Martti

    2008-08-01

    We have been interested in developing an otoneurological decision support system that supports diagnostics of vertigo diseases. In this study, we concentrate on testing its inference mechanism and knowledge discovery method. Knowledge is presented as patterns of classes. Each pattern includes attributes with weight and fitness values concerning the class. With the knowledge discovery method it is possible to form fitness values from data. Knowledge formation is based on frequency distributions of attributes. Knowledge formed by the knowledge discovery method is tested with two vertigo data sets and compared to experts' knowledge. The experts' and machine learnt knowledge are also combined in various ways in order to examine effects of weights on classification accuracy. The classification accuracy of knowledge discovery method is compared to 1- and 5-nearest neighbour method and Naive-Bayes classifier. The results showed that knowledge bases combining machine learnt knowledge with the experts' knowledge yielded the best classification accuracies. Further, attribute weighting had an important effect on the classification capability of the system. When considering different diseases in the used data sets, the performance of the knowledge discovery method and the inference method is comparable to other methods employed in this study.

  2. A novel multiple instance learning method based on extreme learning machine.

    PubMed

    Wang, Jie; Cai, Liangjian; Peng, Jinzhu; Jia, Yuheng

    2015-01-01

    Since real-world data sets usually contain large instances, it is meaningful to develop efficient and effective multiple instance learning (MIL) algorithm. As a learning paradigm, MIL is different from traditional supervised learning that handles the classification of bags comprising unlabeled instances. In this paper, a novel efficient method based on extreme learning machine (ELM) is proposed to address MIL problem. First, the most qualified instance is selected in each bag through a single hidden layer feedforward network (SLFN) whose input and output weights are both initialed randomly, and the single selected instance is used to represent every bag. Second, the modified ELM model is trained by using the selected instances to update the output weights. Experiments on several benchmark data sets and multiple instance regression data sets show that the ELM-MIL achieves good performance; moreover, it runs several times or even hundreds of times faster than other similar MIL algorithms.

  3. Machine learning methods for detection of dust from Meteosat imagery

    NASA Astrophysics Data System (ADS)

    Kolios, Stavros; Hatzianastassiou, Nikos

    2017-04-01

    Dust and sand storms can create potentially hazardous air quality conditions and adversely affect climate on a regional and world-wide scale, by modifying the shortwave and longwave radiation budgets, and human health. The indirect effects of dust are also significant because they modify cloud and precipitation properties and influence the general circulation of the atmosphere. In addition, consideration of dust has been shown to improve the weather forecast ability of models. For these reasons, there is an increasing and strong interest for real-time dust detection and monitoring as well as for dust load estimation from satellite observations, which offer the best solution to the problem. Indeed, remote sensing has been shown to be a valuable tool for detecting, mapping and forecasting dust events. Furthermore, dust satellite remote sensing is also useful in providing long-term and global observations of dust. Nevertheless, the majority of the approaches for dust detection and monitoring are still based on simple thresholding of the multispectral satellite imagery. This study is an effort to investigate the efficiency of machine learning techniques in order to accurately classify different cloud features in Meteosat imagery and detect dust in different atmospheric layers over the greater Mediterranean basin. More specifically, different Support Vector Machines (SVM) and Artificial Neural Network (ANN) schemes are tested to conclude on the most appropriate parameterization of the examined classification schemes. The training samples are collected after spatiotemporal correlation of AERONET station measurements with Meteosat images. Τhe efficiency of the examined algorithms is also tested using AERONET station data in selected cases. This study is first step toward the development of an integrated methodology for an accurate detection, monitoring and estimation of dust using exclusively satellite imagery.

  4. How can machine-learning methods assist in virtual screening for hyperuricemia? A healthcare machine-learning approach.

    PubMed

    Ichikawa, Daisuke; Saito, Toki; Ujita, Waka; Oyama, Hiroshi

    2016-12-01

    Our purpose was to develop a new machine-learning approach (a virtual health check-up) toward identification of those at high risk of hyperuricemia. Applying the system to general health check-ups is expected to reduce medical costs compared with administering an additional test. Data were collected during annual health check-ups performed in Japan between 2011 and 2013 (inclusive). We prepared training and test datasets from the health check-up data to build prediction models; these were composed of 43,524 and 17,789 persons, respectively. Gradient-boosting decision tree (GBDT), random forest (RF), and logistic regression (LR) approaches were trained using the training dataset and were then used to predict hyperuricemia in the test dataset. Undersampling was applied to build the prediction models to deal with the imbalanced class dataset. The results showed that the RF and GBDT approaches afforded the best performances in terms of sensitivity and specificity, respectively. The area under the curve (AUC) values of the models, which reflected the total discriminative ability of the classification, were 0.796 [95% confidence interval (CI): 0.766-0.825] for the GBDT, 0.784 [95% CI: 0.752-0.815] for the RF, and 0.785 [95% CI: 0.752-0.819] for the LR approaches. No significant differences were observed between pairs of each approach. Small changes occurred in the AUCs after applying undersampling to build the models. We developed a virtual health check-up that predicted the development of hyperuricemia using machine-learning methods. The GBDT, RF, and LR methods had similar predictive capability. Undersampling did not remarkably improve predictive power. Copyright © 2016 Elsevier Inc. All rights reserved.

  5. Classification of older adults with/without a fall history using machine learning methods.

    PubMed

    Lin Zhang; Ou Ma; Fabre, Jennifer M; Wood, Robert H; Garcia, Stephanie U; Ivey, Kayla M; McCann, Evan D

    2015-01-01

    Falling is a serious problem in an aged society such that assessment of the risk of falls for individuals is imperative for the research and practice of falls prevention. This paper introduces an application of several machine learning methods for training a classifier which is capable of classifying individual older adults into a high risk group and a low risk group (distinguished by whether or not the members of the group have a recent history of falls). Using a 3D motion capture system, significant gait features related to falls risk are extracted. By training these features, classification hypotheses are obtained based on machine learning techniques (K Nearest-neighbour, Naive Bayes, Logistic Regression, Neural Network, and Support Vector Machine). Training and test accuracies with sensitivity and specificity of each of these techniques are assessed. The feature adjustment and tuning of the machine learning algorithms are discussed. The outcome of the study will benefit the prediction and prevention of falls.

  6. Recent progresses in the exploration of machine learning methods as in-silico ADME prediction tools.

    PubMed

    Tao, L; Zhang, P; Qin, C; Chen, S Y; Zhang, C; Chen, Z; Zhu, F; Yang, S Y; Wei, Y Q; Chen, Y Z

    2015-06-23

    In-silico methods have been explored as potential tools for assessing ADME and ADME regulatory properties particularly in early drug discovery stages. Machine learning methods, with their ability in classifying diverse structures and complex mechanisms, are well suited for predicting ADME and ADME regulatory properties. Recent efforts have been directed at the broadening of application scopes and the improvement of predictive performance with particular focuses on the coverage of ADME properties, and exploration of more diversified training data, appropriate molecular features, and consensus modeling. Moreover, several online machine learning ADME prediction servers have emerged. Here we review these progresses and discuss the performances, application prospects and challenges of exploring machine learning methods as useful tools in predicting ADME and ADME regulatory properties. Copyright © 2015. Published by Elsevier B.V.

  7. Human Machine Learning Symbiosis

    ERIC Educational Resources Information Center

    Walsh, Kenneth R.; Hoque, Md Tamjidul; Williams, Kim H.

    2017-01-01

    Human Machine Learning Symbiosis is a cooperative system where both the human learner and the machine learner learn from each other to create an effective and efficient learning environment adapted to the needs of the human learner. Such a system can be used in online learning modules so that the modules adapt to each learner's learning state both…

  8. Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.

    PubMed

    Hansen, Katja; Montavon, Grégoire; Biegler, Franziska; Fazli, Siamac; Rupp, Matthias; Scheffler, Matthias; von Lilienfeld, O Anatole; Tkatchenko, Alexandre; Müller, Klaus-Robert

    2013-08-13

    The accurate and reliable prediction of properties of molecules typically requires computationally intensive quantum-chemical calculations. Recently, machine learning techniques applied to ab initio calculations have been proposed as an efficient approach for describing the energies of molecules in their given ground-state structure throughout chemical compound space (Rupp et al. Phys. Rev. Lett. 2012, 108, 058301). In this paper we outline a number of established machine learning techniques and investigate the influence of the molecular representation on the methods performance. The best methods achieve prediction errors of 3 kcal/mol for the atomization energies of a wide variety of molecules. Rationales for this performance improvement are given together with pitfalls and challenges when applying machine learning approaches to the prediction of quantum-mechanical observables.

  9. Web Mining: Machine Learning for Web Applications.

    ERIC Educational Resources Information Center

    Chen, Hsinchun; Chau, Michael

    2004-01-01

    Presents an overview of machine learning research and reviews methods used for evaluating machine learning systems. Ways that machine-learning algorithms were used in traditional information retrieval systems in the "pre-Web" era are described, and the field of Web mining and how machine learning has been used in different Web mining…

  10. Web Mining: Machine Learning for Web Applications.

    ERIC Educational Resources Information Center

    Chen, Hsinchun; Chau, Michael

    2004-01-01

    Presents an overview of machine learning research and reviews methods used for evaluating machine learning systems. Ways that machine-learning algorithms were used in traditional information retrieval systems in the "pre-Web" era are described, and the field of Web mining and how machine learning has been used in different Web mining…

  11. Quantum machine learning

    NASA Astrophysics Data System (ADS)

    Biamonte, Jacob; Wittek, Peter; Pancotti, Nicola; Rebentrost, Patrick; Wiebe, Nathan; Lloyd, Seth

    2017-09-01

    Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Quantum systems produce atypical patterns that classical systems are thought not to produce efficiently, so it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement quantum software that could enable machine learning that is faster than that of classical computers. Recent work has produced quantum algorithms that could act as the building blocks of machine learning programs, but the hardware and software challenges are still considerable.

  12. Quantum machine learning.

    PubMed

    Biamonte, Jacob; Wittek, Peter; Pancotti, Nicola; Rebentrost, Patrick; Wiebe, Nathan; Lloyd, Seth

    2017-09-13

    Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Quantum systems produce atypical patterns that classical systems are thought not to produce efficiently, so it is reasonable to postulate that quantum computers may outperform classical computers on machine learning tasks. The field of quantum machine learning explores how to devise and implement quantum software that could enable machine learning that is faster than that of classical computers. Recent work has produced quantum algorithms that could act as the building blocks of machine learning programs, but the hardware and software challenges are still considerable.

  13. Concrete Condition Assessment Using Impact-Echo Method and Extreme Learning Machines

    PubMed Central

    Zhang, Jing-Kui; Yan, Weizhong; Cui, De-Mi

    2016-01-01

    The impact-echo (IE) method is a popular non-destructive testing (NDT) technique widely used for measuring the thickness of plate-like structures and for detecting certain defects inside concrete elements or structures. However, the IE method is not effective for full condition assessment (i.e., defect detection, defect diagnosis, defect sizing and location), because the simple frequency spectrum analysis involved in the existing IE method is not sufficient to capture the IE signal patterns associated with different conditions. In this paper, we attempt to enhance the IE technique and enable it for full condition assessment of concrete elements by introducing advanced machine learning techniques for performing comprehensive analysis and pattern recognition of IE signals. Specifically, we use wavelet decomposition for extracting signatures or features out of the raw IE signals and apply extreme learning machine, one of the recently developed machine learning techniques, as classification models for full condition assessment. To validate the capabilities of the proposed method, we build a number of specimens with various types, sizes, and locations of defects and perform IE testing on these specimens in a lab environment. Based on analysis of the collected IE signals using the proposed machine learning based IE method, we demonstrate that the proposed method is effective in performing full condition assessment of concrete elements or structures. PMID:27023563

  14. Concrete Condition Assessment Using Impact-Echo Method and Extreme Learning Machines.

    PubMed

    Zhang, Jing-Kui; Yan, Weizhong; Cui, De-Mi

    2016-03-26

    The impact-echo (IE) method is a popular non-destructive testing (NDT) technique widely used for measuring the thickness of plate-like structures and for detecting certain defects inside concrete elements or structures. However, the IE method is not effective for full condition assessment (i.e., defect detection, defect diagnosis, defect sizing and location), because the simple frequency spectrum analysis involved in the existing IE method is not sufficient to capture the IE signal patterns associated with different conditions. In this paper, we attempt to enhance the IE technique and enable it for full condition assessment of concrete elements by introducing advanced machine learning techniques for performing comprehensive analysis and pattern recognition of IE signals. Specifically, we use wavelet decomposition for extracting signatures or features out of the raw IE signals and apply extreme learning machine, one of the recently developed machine learning techniques, as classification models for full condition assessment. To validate the capabilities of the proposed method, we build a number of specimens with various types, sizes, and locations of defects and perform IE testing on these specimens in a lab environment. Based on analysis of the collected IE signals using the proposed machine learning based IE method, we demonstrate that the proposed method is effective in performing full condition assessment of concrete elements or structures.

  15. Automating Construction of Machine Learning Models With Clinical Big Data: Proposal Rationale and Methods

    PubMed Central

    Stone, Bryan L; Johnson, Michael D; Tarczy-Hornoch, Peter; Wilcox, Adam B; Mooney, Sean D; Sheng, Xiaoming; Haug, Peter J; Nkoy, Flory L

    2017-01-01

    Background To improve health outcomes and cut health care costs, we often need to conduct prediction/classification using large clinical datasets (aka, clinical big data), for example, to identify high-risk patients for preventive interventions. Machine learning has been proposed as a key technology for doing this. Machine learning has won most data science competitions and could support many clinical activities, yet only 15% of hospitals use it for even limited purposes. Despite familiarity with data, health care researchers often lack machine learning expertise to directly use clinical big data, creating a hurdle in realizing value from their data. Health care researchers can work with data scientists with deep machine learning knowledge, but it takes time and effort for both parties to communicate effectively. Facing a shortage in the United States of data scientists and hiring competition from companies with deep pockets, health care systems have difficulty recruiting data scientists. Building and generalizing a machine learning model often requires hundreds to thousands of manual iterations by data scientists to select the following: (1) hyper-parameter values and complex algorithms that greatly affect model accuracy and (2) operators and periods for temporally aggregating clinical attributes (eg, whether a patient’s weight kept rising in the past year). This process becomes infeasible with limited budgets. Objective This study’s goal is to enable health care researchers to directly use clinical big data, make machine learning feasible with limited budgets and data scientist resources, and realize value from data. Methods This study will allow us to achieve the following: (1) finish developing the new software, Automated Machine Learning (Auto-ML), to automate model selection for machine learning with clinical big data and validate Auto-ML on seven benchmark modeling problems of clinical importance; (2) apply Auto-ML and novel methodology to two new

  16. Machine learning methods for the classification of gliomas: Initial results using features extracted from MR spectroscopy.

    PubMed

    Ranjith, G; Parvathy, R; Vikas, V; Chandrasekharan, Kesavadas; Nair, Suresh

    2015-04-01

    With the advent of new imaging modalities, radiologists are faced with handling increasing volumes of data for diagnosis and treatment planning. The use of automated and intelligent systems is becoming essential in such a scenario. Machine learning, a branch of artificial intelligence, is increasingly being used in medical image analysis applications such as image segmentation, registration and computer-aided diagnosis and detection. Histopathological analysis is currently the gold standard for classification of brain tumors. The use of machine learning algorithms along with extraction of relevant features from magnetic resonance imaging (MRI) holds promise of replacing conventional invasive methods of tumor classification. The aim of the study is to classify gliomas into benign and malignant types using MRI data. Retrospective data from 28 patients who were diagnosed with glioma were used for the analysis. WHO Grade II (low-grade astrocytoma) was classified as benign while Grade III (anaplastic astrocytoma) and Grade IV (glioblastoma multiforme) were classified as malignant. Features were extracted from MR spectroscopy. The classification was done using four machine learning algorithms: multilayer perceptrons, support vector machine, random forest and locally weighted learning. Three of the four machine learning algorithms gave an area under ROC curve in excess of 0.80. Random forest gave the best performance in terms of AUC (0.911) while sensitivity was best for locally weighted learning (86.1%). The performance of different machine learning algorithms in the classification of gliomas is promising. An even better performance may be expected by integrating features extracted from other MR sequences. © The Author(s) 2015 Reprints and permissions: sagepub.co.uk/journalsPermissions.nav.

  17. Feasibility of Machine Learning Methods for Separating Wood and Leaf Points from Terrestrial Laser Scanning Data

    NASA Astrophysics Data System (ADS)

    Wang, D.; Hollaus, M.; Pfeifer, N.

    2017-09-01

    Classification of wood and leaf components of trees is an essential prerequisite for deriving vital tree attributes, such as wood mass, leaf area index (LAI) and woody-to-total area. Laser scanning emerges to be a promising solution for such a request. Intensity based approaches are widely proposed, as different components of a tree can feature discriminatory optical properties at the operating wavelengths of a sensor system. For geometry based methods, machine learning algorithms are often used to separate wood and leaf points, by providing proper training samples. However, it remains unclear how the chosen machine learning classifier and features used would influence classification results. To this purpose, we compare four popular machine learning classifiers, namely Support Vector Machine (SVM), Na¨ıve Bayes (NB), Random Forest (RF), and Gaussian Mixture Model (GMM), for separating wood and leaf points from terrestrial laser scanning (TLS) data. Two trees, an Erytrophleum fordii and a Betula pendula (silver birch) are used to test the impacts from classifier, feature set, and training samples. Our results showed that RF is the best model in terms of accuracy, and local density related features are important. Experimental results confirmed the feasibility of machine learning algorithms for the reliable classification of wood and leaf points. It is also noted that our studies are based on isolated trees. Further tests should be performed on more tree species and data from more complex environments.

  18. Can Machine Learning Methods Predict Extubation Outcome in Premature Infants as well as Clinicians?

    PubMed Central

    Mueller, Martina; Almeida, Jonas S.; Stanislaus, Romesh; Wagner, Carol L.

    2014-01-01

    Rationale Though treatment of the prematurely born infant breathing with assistance of a mechanical ventilator has much advanced in the past decades, predicting extubation outcome at a given point in time remains challenging. Numerous studies have been conducted to identify predictors for extubation outcome; however, the rate of infants failing extubation attempts has not declined. Objective To develop a decision-support tool for the prediction of extubation outcome in premature infants using a set of machine learning algorithms Methods A dataset assembled from 486 premature infants on mechanical ventilation was used to develop predictive models using machine learning algorithms such as artificial neural networks (ANN), support vector machine (SVM), naïve Bayesian classifier (NBC), boosted decision trees (BDT), and multivariable logistic regression (MLR). Performance of all models was evaluated using area under the curve (AUC). Results For some of the models (ANN, MLR and NBC) results were satisfactory (AUC: 0.63–0.76); however, two algorithms (SVM and BDT) showed poor performance with AUCs of ~0.5. Conclusion Clinician's predictions still outperform machine learning due to the complexity of the data and contextual information that may not be captured in clinical data used as input for the development of the machine learning algorithms. Inclusion of preprocessing steps in future studies may improve the performance of prediction models. PMID:25419493

  19. Machine Methods for Acquiring, Learning, and Applying Knowledge.

    ERIC Educational Resources Information Center

    Hayes-Roth, Frederick; And Others

    A research plan for identifying and acting upon constraints that impede the development of knowledge-based intelligent systems is described. The two primary problems identified are knowledge programming, the task of which is to create an intelligent system that does what an expert says it should, and learning, the problem requiring the criticizing…

  20. A Review of Current Machine Learning Methods Used for Cancer Recurrence Modeling and Prediction

    SciTech Connect

    Hemphill, Geralyn M.

    2016-09-27

    Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type has become a necessity in cancer research. A major challenge in cancer management is the classification of patients into appropriate risk groups for better treatment and follow-up. Such risk assessment is critically important in order to optimize the patient’s health and the use of medical resources, as well as to avoid cancer recurrence. This paper focuses on the application of machine learning methods for predicting the likelihood of a recurrence of cancer. It is not meant to be an extensive review of the literature on the subject of machine learning techniques for cancer recurrence modeling. Other recent papers have performed such a review, and I will rely heavily on the results and outcomes from these papers. The electronic databases that were used for this review include PubMed, Google, and Google Scholar. Query terms used include “cancer recurrence modeling”, “cancer recurrence and machine learning”, “cancer recurrence modeling and machine learning”, and “machine learning for cancer recurrence and prediction”. The most recent and most applicable papers to the topic of this review have been included in the references. It also includes a list of modeling and classification methods to predict cancer recurrence.

  1. Solar Flare Predictions Using Time Series of SDO/HMI Observations and Machine Learning Methods

    NASA Astrophysics Data System (ADS)

    Ilonidis, Stathis; Bobra, Monica; Couvidat, Sebastien

    2015-08-01

    Solar active regions are dynamic systems that can rapidly evolve in time and produce flare eruptions. The temporal evolution of an active region can provide important information about its potential to produce major flares. In this study, we build a flare forecasting model using supervised machine learning methods and time series of SDO/HMI data for all the flaring regions with magnitude M1.0 or higher that have been observed with HMI and several thousand non-flaring regions. We define and compute hundreds of features that characterize the temporal evolution of physical properties related to the size, non-potentiality, and complexity of the active region, as well as its flaring history, for several days before the flare eruption. Using these features, we implement and test the performance of several machine learning algorithms, including support vector machines, neural networks, decision trees, discriminant analysis, and others. We also apply feature selection algorithms that aim to discard features with low predictive power and improve the performance of the machine learning methods. Our results show that support vector machines provide the best forecasts for the next 24 hours, achieving a True Skill Statistic of 0.923, an accuracy of 0.985, and a Heidke skill score of 0.861, which improve the scores obtained by Bobra and Couvidat (2015). The results of this study contribute to the development of a more reliable and fully automated data-driven flare forecasting system.

  2. Design method of machine-learning system used for autonomous land vehicle

    NASA Astrophysics Data System (ADS)

    He, Han-gen; Chang, Wensen

    1999-07-01

    The control of Autonomous Land Vehicle (ALV) is a kind of typical nonlinear control. Because the state of traffic and road are complex, so the control of ALV is complex and uncertain. Especially if the ALV runs in normal state of traffic, the control of ALV is becoming more complex and difficult. A good idea is that to let the control system of ALV to simulate human driver and develop a machine-leaning system in the control system of ALV. So that as the control system of ALV is driving ALV along road, the control system can learn from the experience of human driver according to the state of traffic and road. In other words, the control system of ALV is able to become more and more 'clever.' Of course it is a challenging and very difficult task. This paper analyzes the principle of machine-leaning system used for ALV and discusses the engineering method of developing a machine- leaning system used for ALV, when the ALV runs along highway in normal traffic. This paper advances the administrative levels of machine-leaning system and a method of fusing human intelligence into machine intelligence. This paper introduces our preliminary research on machine-leaning system used for ALV also, which is a kind of online machine-leaning system without teacher.

  3. Prediction of acetylcholinesterase inhibitors and characterization of correlative molecular descriptors by machine learning methods.

    PubMed

    Lv, Wei; Xue, Ying

    2010-03-01

    Acetylcholinesterase (AChE) has become an important drug target and its inhibitors have proved useful in the symptomatic treatment of Alzheimer's disease. This work explores several machine learning methods (support vector machine (SVM), k-nearest neighbor (k-NN), and C4.5 decision tree (C4.5 DT)) for predicting AChE inhibitors (AChEIs). A feature selection method is used for improving prediction accuracy and selecting molecular descriptors responsible for distinguishing AChEIs and non-AChEIs. The prediction accuracies are 76.3% approximately 88.0% for AChEIs and 74.3% approximately 79.6% for non-AChEIs based on the three kinds of machine learning methods. This work suggests that machine learning methods such as SVM are facilitating for predicting AChEIs potential of unknown sets of compounds and for exhibiting the molecular descriptors associated with AChEIs. Copyright (c) 2009 Elsevier Masson SAS. All rights reserved.

  4. Probability estimation with machine learning methods for dichotomous and multicategory outcome: theory.

    PubMed

    Kruppa, Jochen; Liu, Yufeng; Biau, Gérard; Kohler, Michael; König, Inke R; Malley, James D; Ziegler, Andreas

    2014-07-01

    Probability estimation for binary and multicategory outcome using logistic and multinomial logistic regression has a long-standing tradition in biostatistics. However, biases may occur if the model is misspecified. In contrast, outcome probabilities for individuals can be estimated consistently with machine learning approaches, including k-nearest neighbors (k-NN), bagged nearest neighbors (b-NN), random forests (RF), and support vector machines (SVM). Because machine learning methods are rarely used by applied biostatisticians, the primary goal of this paper is to explain the concept of probability estimation with these methods and to summarize recent theoretical findings. Probability estimation in k-NN, b-NN, and RF can be embedded into the class of nonparametric regression learning machines; therefore, we start with the construction of nonparametric regression estimates and review results on consistency and rates of convergence. In SVMs, outcome probabilities for individuals are estimated consistently by repeatedly solving classification problems. For SVMs we review classification problem and then dichotomous probability estimation. Next we extend the algorithms for estimating probabilities using k-NN, b-NN, and RF to multicategory outcomes and discuss approaches for the multicategory probability estimation problem using SVM. In simulation studies for dichotomous and multicategory dependent variables we demonstrate the general validity of the machine learning methods and compare it with logistic regression. However, each method fails in at least one simulation scenario. We conclude with a discussion of the failures and give recommendations for selecting and tuning the methods. Applications to real data and example code are provided in a companion article (doi:10.1002/bimj.201300077).

  5. Machine Learning for Medical Imaging

    PubMed Central

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

    2017-01-01

    Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. PMID:28212054

  6. Machine Learning for Medical Imaging.

    PubMed

    Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy L

    2017-01-01

    Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. (©)RSNA, 2017.

  7. e-Learning Application for Machine Maintenance Process using Iterative Method in XYZ Company

    NASA Astrophysics Data System (ADS)

    Nurunisa, Suaidah; Kurniawati, Amelia; Pramuditya Soesanto, Rayinda; Yunan Kurnia Septo Hediyanto, Umar

    2016-02-01

    XYZ Company is a company based on manufacturing part for airplane, one of the machine that is categorized as key facility in the company is Millac 5H6P. As a key facility, the machines should be assured to work well and in peak condition, therefore, maintenance process is needed periodically. From the data gathering, it is known that there are lack of competency from the maintenance staff to maintain different type of machine which is not assigned by the supervisor, this indicate that knowledge which possessed by maintenance staff are uneven. The purpose of this research is to create knowledge-based e-learning application as a realization from externalization process in knowledge transfer process to maintain the machine. The application feature are adjusted for maintenance purpose using e-learning framework for maintenance process, the content of the application support multimedia for learning purpose. QFD is used in this research to understand the needs from user. The application is built using moodle with iterative method for software development cycle and UML Diagram. The result from this research is e-learning application as sharing knowledge media for maintenance staff in the company. From the test, it is known that the application make maintenance staff easy to understand the competencies.

  8. An Overview and Evaluation of Recent Machine Learning Imputation Methods Using Cardiac Imaging Data.

    PubMed

    Liu, Yuzhe; Gopalakrishnan, Vanathi

    2017-03-01

    Many clinical research datasets have a large percentage of missing values that directly impacts their usefulness in yielding high accuracy classifiers when used for training in supervised machine learning. While missing value imputation methods have been shown to work well with smaller percentages of missing values, their ability to impute sparse clinical research data can be problem specific. We previously attempted to learn quantitative guidelines for ordering cardiac magnetic resonance imaging during the evaluation for pediatric cardiomyopathy, but missing data significantly reduced our usable sample size. In this work, we sought to determine if increasing the usable sample size through imputation would allow us to learn better guidelines. We first review several machine learning methods for estimating missing data. Then, we apply four popular methods (mean imputation, decision tree, k-nearest neighbors, and self-organizing maps) to a clinical research dataset of pediatric patients undergoing evaluation for cardiomyopathy. Using Bayesian Rule Learning (BRL) to learn ruleset models, we compared the performance of imputation-augmented models versus unaugmented models. We found that all four imputation-augmented models performed similarly to unaugmented models. While imputation did not improve performance, it did provide evidence for the robustness of our learned models.

  9. An Overview and Evaluation of Recent Machine Learning Imputation Methods Using Cardiac Imaging Data

    PubMed Central

    Liu, Yuzhe; Gopalakrishnan, Vanathi

    2017-01-01

    Many clinical research datasets have a large percentage of missing values that directly impacts their usefulness in yielding high accuracy classifiers when used for training in supervised machine learning. While missing value imputation methods have been shown to work well with smaller percentages of missing values, their ability to impute sparse clinical research data can be problem specific. We previously attempted to learn quantitative guidelines for ordering cardiac magnetic resonance imaging during the evaluation for pediatric cardiomyopathy, but missing data significantly reduced our usable sample size. In this work, we sought to determine if increasing the usable sample size through imputation would allow us to learn better guidelines. We first review several machine learning methods for estimating missing data. Then, we apply four popular methods (mean imputation, decision tree, k-nearest neighbors, and self-organizing maps) to a clinical research dataset of pediatric patients undergoing evaluation for cardiomyopathy. Using Bayesian Rule Learning (BRL) to learn ruleset models, we compared the performance of imputation-augmented models versus unaugmented models. We found that all four imputation-augmented models performed similarly to unaugmented models. While imputation did not improve performance, it did provide evidence for the robustness of our learned models. PMID:28243594

  10. A Distributed Learning Method for ℓ 1 -Regularized Kernel Machine over Wireless Sensor Networks.

    PubMed

    Ji, Xinrong; Hou, Cuiqin; Hou, Yibin; Gao, Fang; Wang, Shulong

    2016-07-01

    In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ 1 norm regularization ( ℓ 1 -regularized) is investigated, and a novel distributed learning algorithm for the ℓ 1 -regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost.

  11. A Distributed Learning Method for ℓ1-Regularized Kernel Machine over Wireless Sensor Networks

    PubMed Central

    Ji, Xinrong; Hou, Cuiqin; Hou, Yibin; Gao, Fang; Wang, Shulong

    2016-01-01

    In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ1 norm regularization (ℓ1-regularized) is investigated, and a novel distributed learning algorithm for the ℓ1-regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost. PMID:27376298

  12. Comparisons of likelihood and machine learning methods of individual classification

    USGS Publications Warehouse

    Guinand, B.; Topchy, A.; Page, K.S.; Burnham-Curtis, M. K.; Punch, W.F.; Scribner, K.T.

    2002-01-01

    “Assignment tests” are designed to determine population membership for individuals. One particular application based on a likelihood estimate (LE) was introduced by Paetkau et al. (1995; see also Vásquez-Domínguez et al. 2001) to assign an individual to the population of origin on the basis of multilocus genotype and expectations of observing this genotype in each potential source population. The LE approach can be implemented statistically in a Bayesian framework as a convenient way to evaluate hypotheses of plausible genealogical relationships (e.g., that an individual possesses an ancestor in another population) (Dawson and Belkhir 2001;Pritchard et al. 2000; Rannala and Mountain 1997). Other studies have evaluated the confidence of the assignment (Almudevar 2000) and characteristics of genotypic data (e.g., degree of population divergence, number of loci, number of individuals, number of alleles) that lead to greater population assignment (Bernatchez and Duchesne 2000; Cornuet et al. 1999; Haig et al. 1997; Shriver et al. 1997; Smouse and Chevillon 1998). Main statistical and conceptual differences between methods leading to the use of an assignment test are given in, for example,Cornuet et al. (1999) and Rosenberg et al. (2001). Howeve

  13. Machine Learning Method for Pattern Recognition in Volcano Seismic Spectra

    NASA Astrophysics Data System (ADS)

    Radic, V.; Unglert, K.; Jellinek, M.

    2016-12-01

    Variations in the spectral content of volcano seismicity related to changes in volcanic activity are commonly identified manually in spectrograms. However, long time series of monitoring data at volcano observatories require tools to facilitate automated and rapid processing. Techniques such as Self-Organizing Maps (SOM), Principal Component Analysis (PCA) and clustering methods can help to quickly and automatically identify important patterns related to impending eruptions. In this study we develop and evaluate an algorithm applied on a set of synthetic volcano seismic spectra as well as observed spectra from Kılauea Volcano, Hawai`i. Our goal is to retrieve a set of known spectral patterns that are associated with dominant phases of volcanic tremor before, during, and after periods of volcanic unrest. The algorithm is based on training a SOM on the spectra and then identifying local maxima and minima on the SOM 'topography'. The topography is derived from the first two PCA modes so that the maxima represent the SOM patterns that carry most of the variance in the spectra. Patterns identified in this way reproduce the known set of spectra. Our results show that, regardless of the level of white noise in the spectra, the algorithm can accurately reproduce the characteristic spectral patterns and their occurrence in time. The ability to rapidly classify spectra of volcano seismic data without prior knowledge of the character of the seismicity at a given volcanic system holds great potential for real time or near-real time applications, and thus ultimately for eruption forecasting.

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

    PubMed

    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.

  15. Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

    PubMed

    Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

    2017-03-01

    Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance.

  16. Detection of Periodic Leg Movements by Machine Learning Methods Using Polysomnographic Parameters Other Than Leg Electromyography.

    PubMed

    Umut, İlhan; Çentik, Güven

    2016-01-01

    The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, K-nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while K-nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present.

  17. Photometric classification of emission line galaxies with machine-learning methods

    NASA Astrophysics Data System (ADS)

    Cavuoti, Stefano; Brescia, Massimo; D'Abrusco, Raffaele; Longo, Giuseppe; Paolillo, Maurizio

    2014-01-01

    In this paper, we discuss an application of machine-learning-based methods to the identification of candidate active galactic nucleus (AGN) from optical survey data and to the automatic classification of AGNs in broad classes. We applied four different machine-learning algorithms, namely the Multi Layer Perceptron, trained, respectively, with the Conjugate Gradient, the Scaled Conjugate Gradient, the Quasi Newton learning rules and the Support Vector Machines, to tackle the problem of the classification of emission line galaxies in different classes, mainly AGNs versus non-AGNs, obtained using optical photometry in place of the diagnostics based on line intensity ratios which are classically used in the literature. Using the same photometric features, we discuss also the behaviour of the classifiers on finer AGN classification tasks, namely Seyfert I versus Seyfert II, and Seyfert versus LINER. Furthermore, we describe the algorithms employed, the samples of spectroscopically classified galaxies used to train the algorithms, the procedure followed to select the photometric parameters and the performances of our methods in terms of multiple statistical indicators. The results of the experiments show that the application of self-adaptive data mining algorithms trained on spectroscopic data sets and applied to carefully chosen photometric parameters represents a viable alternative to the classical methods that employ time-consuming spectroscopic observations.

  18. Machine Learning methods in fitting first-principles total energies for substitutionally disordered solid

    NASA Astrophysics Data System (ADS)

    Gao, Qin; Yao, Sanxi; Widom, Michael

    2015-03-01

    Density functional theory (DFT) provides an accurate and first-principles description of solid structures and total energies. However, it is highly time-consuming to calculate structures with hundreds of atoms in the unit cell and almost not possible to calculate thousands of atoms. We apply and adapt machine learning algorithms, including compressive sensing, support vector regression and artificial neural networks to fit the DFT total energies of substitutionally disordered boron carbide. The nonparametric kernel method is also included in our models. Our fitted total energy model reproduces the DFT energies with prediction error of around 1 meV/atom. The assumptions of these machine learning models and applications of the fitted total energies will also be discussed. Financial support from McWilliams Fellowship and the ONR-MURI under the Grant No. N00014-11-1-0678 is gratefully acknowledged.

  19. Recognizing Disjoint Clinical Concepts in Clinical Text Using Machine Learning-based Methods.

    PubMed

    Tang, Buzhou; Chen, Qingcai; Wang, Xiaolong; Wu, Yonghui; Zhang, Yaoyun; Jiang, Min; Wang, Jingqi; Xu, Hua

    2015-01-01

    Clinical concept recognition (CCR) is a fundamental task in clinical natural language processing (NLP) field. Almost all current machine learning-based CCR systems can only recognize clinical concepts of consecutive words (called consecutive clinical concepts, CCCs), but can do nothing about clinical concepts of disjoint words (called disjoint clinical concepts, DCCs), which widely exist in clinical text. In this paper, we proposed two novel types of representations for disjoint clinical concepts, and applied two state-of-the-art machine learning methods to recognizing consecutive and disjoint concepts. Experiments conducted on the 2013 ShARe/CLEF challenge corpus showed that our best system achieved a "strict" F-measure of 0.803 for CCCs, a "strict" F-measure of 0.477 for DCCs, and a "strict" F-measure of 0.783 for all clinical concepts, significantly higher than the baseline systems by 4.2% and 4.1% respectively.

  20. Machine learning methods enable predictive modeling of antibody feature:function relationships in RV144 vaccinees.

    PubMed

    Choi, Ickwon; Chung, Amy W; Suscovich, Todd J; Rerks-Ngarm, Supachai; Pitisuttithum, Punnee; Nitayaphan, Sorachai; Kaewkungwal, Jaranit; O'Connell, Robert J; Francis, Donald; Robb, Merlin L; Michael, Nelson L; Kim, Jerome H; Alter, Galit; Ackerman, Margaret E; Bailey-Kellogg, Chris

    2015-04-01

    The adaptive immune response to vaccination or infection can lead to the production of specific antibodies to neutralize the pathogen or recruit innate immune effector cells for help. The non-neutralizing role of antibodies in stimulating effector cell responses may have been a key mechanism of the protection observed in the RV144 HIV vaccine trial. In an extensive investigation of a rich set of data collected from RV144 vaccine recipients, we here employ machine learning methods to identify and model associations between antibody features (IgG subclass and antigen specificity) and effector function activities (antibody dependent cellular phagocytosis, cellular cytotoxicity, and cytokine release). We demonstrate via cross-validation that classification and regression approaches can effectively use the antibody features to robustly predict qualitative and quantitative functional outcomes. This integration of antibody feature and function data within a machine learning framework provides a new, objective approach to discovering and assessing multivariate immune correlates.

  1. Improved machine learning method for analysis of gas phase chemistry of peptides.

    PubMed

    Gehrke, Allison; Sun, Shaojun; Kurgan, Lukasz; Ahn, Natalie; Resing, Katheryn; Kafadar, Karen; Cios, Krzysztof

    2008-12-03

    Accurate peptide identification is important to high-throughput proteomics analyses that use mass spectrometry. Search programs compare fragmentation spectra (MS/MS) of peptides from complex digests with theoretically derived spectra from a database of protein sequences. Improved discrimination is achieved with theoretical spectra that are based on simulating gas phase chemistry of the peptides, but the limited understanding of those processes affects the accuracy of predictions from theoretical spectra. We employed a robust data mining strategy using new feature annotation functions of MAE software, which revealed under-prediction of the frequency of occurrence in fragmentation of the second peptide bond. We applied methods of exploratory data analysis to pre-process the information in the MS/MS spectra, including data normalization and attribute selection, to reduce the attributes to a smaller, less correlated set for machine learning studies. We then compared our rule building machine learning program, DataSqueezer, with commonly used association rules and decision tree algorithms. All used machine learning algorithms produced similar results that were consistent with expected properties for a second gas phase mechanism at the second peptide bond. The results provide compelling evidence that we have identified underlying chemical properties in the data that suggest the existence of an additional gas phase mechanism for the second peptide bond. Thus, the methods described in this study provide a valuable approach for analyses of this kind in the future.

  2. Improved machine learning method for analysis of gas phase chemistry of peptides

    PubMed Central

    Gehrke, Allison; Sun, Shaojun; Kurgan, Lukasz; Ahn, Natalie; Resing, Katheryn; Kafadar, Karen; Cios, Krzysztof

    2008-01-01

    Background Accurate peptide identification is important to high-throughput proteomics analyses that use mass spectrometry. Search programs compare fragmentation spectra (MS/MS) of peptides from complex digests with theoretically derived spectra from a database of protein sequences. Improved discrimination is achieved with theoretical spectra that are based on simulating gas phase chemistry of the peptides, but the limited understanding of those processes affects the accuracy of predictions from theoretical spectra. Results We employed a robust data mining strategy using new feature annotation functions of MAE software, which revealed under-prediction of the frequency of occurrence in fragmentation of the second peptide bond. We applied methods of exploratory data analysis to pre-process the information in the MS/MS spectra, including data normalization and attribute selection, to reduce the attributes to a smaller, less correlated set for machine learning studies. We then compared our rule building machine learning program, DataSqueezer, with commonly used association rules and decision tree algorithms. All used machine learning algorithms produced similar results that were consistent with expected properties for a second gas phase mechanism at the second peptide bond. Conclusion The results provide compelling evidence that we have identified underlying chemical properties in the data that suggest the existence of an additional gas phase mechanism for the second peptide bond. Thus, the methods described in this study provide a valuable approach for analyses of this kind in the future. PMID:19055745

  3. Machine Learning and Radiology

    PubMed Central

    Wang, Shijun; Summers, Ronald M.

    2012-01-01

    In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers. PMID:22465077

  4. Using machine learning methods to predict experimental high-throughput screening data.

    PubMed

    Mballo, Chérif; Makarenkov, Vladimir

    2010-06-01

    High-throughput screening (HTS) remains a very costly process notwithstanding many recent technological advances in the field of biotechnology. In this study we consider the application of machine learning methods for predicting experimental HTS measurements. Such a virtual HTS analysis can be based on the results of real HTS campaigns carried out with similar compounds libraries and similar drug targets. In this way, we analyzed Test assay from McMaster University Data Mining and Docking Competition using binary decision trees, neural networks, support vector machines (SVM), linear discriminant analysis, k-nearest neighbors and partial least squares. First, we studied separately the sets of molecular and atomic descriptors in order to establish which of them provides a better prediction. Then, the comparison of the six considered machine learning methods was made in terms of false positives and false negatives, method's sensitivity and enrichment factor. Finally, a variable selection procedure allowing one to improve the method's sensitivity was implemented and applied in the framework of polynomial SVM.

  5. Hippocampal shape analysis of Alzheimer disease based on machine learning methods.

    PubMed

    Li, S; Shi, F; Pu, F; Li, X; Jiang, T; Xie, S; Wang, Y

    2007-08-01

    Alzheimer disease (AD) is a neurodegenerative disease characterized by progressive dementia. The hippocampus is particularly vulnerable to damage at the very earliest stages of AD. This article seeks to evaluate critical AD-associated regional changes in the hippocampus using machine learning methods. High-resolution MR images were acquired from 19 patients with AD and 20 age- and sex-matched healthy control subjects. Regional changes of bilateral hippocampi were characterized using computational anatomic mapping methods. A feature selection method for support vector machine and leave-1-out cross-validation was introduced to determine regional shape differences that minimized the error rate in the datasets. Patients with AD showed significant deformations in the CA1 region of bilateral hippocampi, as well as the subiculum of the left hippocampus. There were also some changes in the CA2-4 subregions of the left hippocampus among patients with AD. Moreover, the left hippocampal surface showed greater variations than the right compared with those in healthy control subjects. The accuracies of leave-1-out cross-validation and 3-fold cross-validation experiments for assessing the reliability of these subregions were more than 80% in bilateral hippocampi. Subtle and spatially complex deformation patterns of hippocampus between patients with AD and healthy control subjects can be detected by machine learning methods.

  6. Application of machine learning methods to the solar disk state detection by all-sky images over the ocean

    NASA Astrophysics Data System (ADS)

    Krinitskiy, M. A.

    2017-03-01

    A new approach to automatic solar disk state detection by all-sky images using machine learning methods is developed and implemented. The efficiency of the most widely used machine learning algorithms is analyzed. The effect of reducing the dimensionality of the feature space on the classification accuracy is estimated. The multilayer artificial neural network model has shown the best accuracy in terms of the true score. The operation result demonstrates the effectiveness of machine learning methods applied to solar disk state detection by all-sky images.

  7. An iterative learning control method with application for CNC machine tools

    SciTech Connect

    Kim, D.I.; Kim, S.

    1996-01-01

    A proportional, integral, and derivative (PID) type iterative learning controller is proposed for precise tracking control of industrial robots and computer numerical controller (CNC) machine tools performing repetitive tasks. The convergence of the output error by the proposed learning controller is guaranteed under a certain condition even when the system parameters are not known exactly and unknown external disturbances exist. As the proposed learning controller is repeatedly applied to the industrial robot or the CNC machine tool with the path-dependent repetitive task, the distance difference between the desired path and the actual tracked or machined path, which is one of the most significant factors in the evaluation of control performance, is progressively reduced. The experimental results demonstrate that the proposed learning controller can improve machining accuracy when the CNC machine tool performs repetitive machining tasks.

  8. Learning thermodynamics with Boltzmann machines

    NASA Astrophysics Data System (ADS)

    Torlai, Giacomo; Melko, Roger G.

    2016-10-01

    A Boltzmann machine is a stochastic neural network that has been extensively used in the layers of deep architectures for modern machine learning applications. In this paper, we develop a Boltzmann machine that is capable of modeling thermodynamic observables for physical systems in thermal equilibrium. Through unsupervised learning, we train the Boltzmann machine on data sets constructed with spin configurations importance sampled from the partition function of an Ising Hamiltonian at different temperatures using Monte Carlo (MC) methods. The trained Boltzmann machine is then used to generate spin states, for which we compare thermodynamic observables to those computed by direct MC sampling. We demonstrate that the Boltzmann machine can faithfully reproduce the observables of the physical system. Further, we observe that the number of neurons required to obtain accurate results increases as the system is brought close to criticality.

  9. Probability estimation with machine learning methods for dichotomous and multicategory outcome: applications.

    PubMed

    Kruppa, Jochen; Liu, Yufeng; Diener, Hans-Christian; Holste, Theresa; Weimar, Christian; König, Inke R; Ziegler, Andreas

    2014-07-01

    Machine learning methods are applied to three different large datasets, all dealing with probability estimation problems for dichotomous or multicategory data. Specifically, we investigate k-nearest neighbors, bagged nearest neighbors, random forests for probability estimation trees, and support vector machines with the kernels of Bessel, linear, Laplacian, and radial basis type. Comparisons are made with logistic regression. The dataset from the German Stroke Study Collaboration with dichotomous and three-category outcome variables allows, in particular, for temporal and external validation. The other two datasets are freely available from the UCI learning repository and provide dichotomous outcome variables. One of them, the Cleveland Clinic Foundation Heart Disease dataset, uses data from one clinic for training and from three clinics for external validation, while the other, the thyroid disease dataset, allows for temporal validation by separating data into training and test data by date of recruitment into study. For dichotomous outcome variables, we use receiver operating characteristics, areas under the curve values with bootstrapped 95% confidence intervals, and Hosmer-Lemeshow-type figures as comparison criteria. For dichotomous and multicategory outcomes, we calculated bootstrap Brier scores with 95% confidence intervals and also compared them through bootstrapping. In a supplement, we provide R code for performing the analyses and for random forest analyses in Random Jungle, version 2.1.0. The learning machines show promising performance over all constructed models. They are simple to apply and serve as an alternative approach to logistic or multinomial logistic regression analysis.

  10. Model-based machine learning

    PubMed Central

    Bishop, Christopher M.

    2013-01-01

    Several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. To tackle a new application, a researcher typically tries to map their problem onto one of these existing methods, often influenced by their familiarity with specific algorithms and by the availability of corresponding software implementations. In this study, we describe an alternative methodology for applying machine learning, in which a bespoke solution is formulated for each new application. The solution is expressed through a compact modelling language, and the corresponding custom machine learning code is then generated automatically. This model-based approach offers several major advantages, including the opportunity to create highly tailored models for specific scenarios, as well as rapid prototyping and comparison of a range of alternative models. Furthermore, newcomers to the field of machine learning do not have to learn about the huge range of traditional methods, but instead can focus their attention on understanding a single modelling environment. In this study, we show how probabilistic graphical models, coupled with efficient inference algorithms, provide a very flexible foundation for model-based machine learning, and we outline a large-scale commercial application of this framework involving tens of millions of users. We also describe the concept of probabilistic programming as a powerful software environment for model-based machine learning, and we discuss a specific probabilistic programming language called Infer.NET, which has been widely used in practical applications. PMID:23277612

  11. Model-based machine learning.

    PubMed

    Bishop, Christopher M

    2013-02-13

    Several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. To tackle a new application, a researcher typically tries to map their problem onto one of these existing methods, often influenced by their familiarity with specific algorithms and by the availability of corresponding software implementations. In this study, we describe an alternative methodology for applying machine learning, in which a bespoke solution is formulated for each new application. The solution is expressed through a compact modelling language, and the corresponding custom machine learning code is then generated automatically. This model-based approach offers several major advantages, including the opportunity to create highly tailored models for specific scenarios, as well as rapid prototyping and comparison of a range of alternative models. Furthermore, newcomers to the field of machine learning do not have to learn about the huge range of traditional methods, but instead can focus their attention on understanding a single modelling environment. In this study, we show how probabilistic graphical models, coupled with efficient inference algorithms, provide a very flexible foundation for model-based machine learning, and we outline a large-scale commercial application of this framework involving tens of millions of users. We also describe the concept of probabilistic programming as a powerful software environment for model-based machine learning, and we discuss a specific probabilistic programming language called Infer.NET, which has been widely used in practical applications.

  12. [Quantitative retrieval of chlorophyll a concentration in Taihu Lake using machine learning methods].

    PubMed

    Zhang, Yu-Chao; Qian, Xin; Qian, Yu; Liu, Jian-Ping; Kong, Fan-Xiang

    2009-05-15

    We evaluated the performance of two machine learning methods, artificial neural net (ANN) and support vector machine (SVM), for estimation of chlorophyll a in Taihu Lake from remote sensing data. The theoretical analysis has been done from basic theory and learning target of these two methods first. Then two empirical algorithms have been developed to relate reflectance of MODIS to in situ concentrations of chlorophyll a. The performance of ANN and SVM is comparatively analyzed in terms of validation, stability and robustness assessment and chlorophyll a distribution of Taihu Lake from two algorithms. The root of mean square deviation (RMSE) and average relative error (ARE) of validation data is only 5.85 and 26.5% of SVM retrieval model, however, RMSE and ARE of ANN model is 13.04 and 46.8%. Stability and robustness assessment suggest that SVM provides the better performance than ANN. And the retrieval results show that the chlorophyll a distribution of the whole lake from two algorithms is similar, however, the chlorophyll a concentration in the eastern region and central region of Taihu Lake is distorted by ANN model because of the limitations, such as learning target setting and over-learning in net construction.

  13. The influence of the inactives subset generation on the performance of machine learning methods

    PubMed Central

    2013-01-01

    Background A growing popularity of machine learning methods application in virtual screening, in both classification and regression tasks, can be observed in the past few years. However, their effectiveness is strongly dependent on many different factors. Results In this study, the influence of the way of forming the set of inactives on the classification process was examined: random and diverse selection from the ZINC database, MDDR database and libraries generated according to the DUD methodology. All learning methods were tested in two modes: using one test set, the same for each method of inactive molecules generation and using test sets with inactives prepared in an analogous way as for training. The experiments were carried out for 5 different protein targets, 3 fingerprints for molecules representation and 7 classification algorithms with varying parameters. It appeared that the process of inactive set formation had a substantial impact on the machine learning methods performance. Conclusions The level of chemical space limitation determined the ability of tested classifiers to select potentially active molecules in virtual screening tasks, as for example DUDs (widely applied in docking experiments) did not provide proper selection of active molecules from databases with diverse structures. The study clearly showed that inactive compounds forming training set should be representative to the highest possible extent for libraries that undergo screening. PMID:23561266

  14. METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts

    NASA Astrophysics Data System (ADS)

    Cavuoti, S.; Amaro, V.; Brescia, M.; Vellucci, C.; Tortora, C.; Longo, G.

    2017-02-01

    A variety of fundamental astrophysical science topics require the determination of very accurate photometric redshifts (photo-z). A wide plethora of methods have been developed, based either on template models fitting or on empirical explorations of the photometric parameter space. Machine-learning-based techniques are not explicitly dependent on the physical priors and able to produce accurate photo-z estimations within the photometric ranges derived from the spectroscopic training set. These estimates, however, are not easy to characterize in terms of a photo-z probability density function (PDF), due to the fact that the analytical relation mapping the photometric parameters on to the redshift space is virtually unknown. We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method designed to provide a reliable PDF of the error distribution for empirical techniques. The method is implemented as a modular workflow, whose internal engine for photo-z estimation makes use of the MLPQNA neural network (Multi Layer Perceptron with Quasi Newton learning rule), with the possibility to easily replace the specific machine-learning model chosen to predict photo-z. We present a summary of results on SDSS-DR9 galaxy data, used also to perform a direct comparison with PDFs obtained by the LE PHARE spectral energy distribution template fitting. We show that METAPHOR is capable to estimate the precision and reliability of photometric redshifts obtained with three different self-adaptive techniques, i.e. MLPQNA, Random Forest and the standard K-Nearest Neighbors models.

  15. A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support.

    PubMed

    Connolly, Brian; Cohen, K Bretonnel; Santel, Daniel; Bayram, Ulya; Pestian, John

    2017-08-07

    Probabilistic assessments of clinical care are essential for quality care. Yet, machine learning, which supports this care process has been limited to categorical results. To maximize its usefulness, it is important to find novel approaches that calibrate the ML output with a likelihood scale. Current state-of-the-art calibration methods are generally accurate and applicable to many ML models, but improved granularity and accuracy of such methods would increase the information available for clinical decision making. This novel non-parametric Bayesian approach is demonstrated on a variety of data sets, including simulated classifier outputs, biomedical data sets from the University of California, Irvine (UCI) Machine Learning Repository, and a clinical data set built to determine suicide risk from the language of emergency department patients. The method is first demonstrated on support-vector machine (SVM) models, which generally produce well-behaved, well understood scores. The method produces calibrations that are comparable to the state-of-the-art Bayesian Binning in Quantiles (BBQ) method when the SVM models are able to effectively separate cases and controls. However, as the SVM models' ability to discriminate classes decreases, our approach yields more granular and dynamic calibrated probabilities comparing to the BBQ method. Improvements in granularity and range are even more dramatic when the discrimination between the classes is artificially degraded by replacing the SVM model with an ad hoc k-means classifier. The method allows both clinicians and patients to have a more nuanced view of the output of an ML model, allowing better decision making. The method is demonstrated on simulated data, various biomedical data sets and a clinical data set, to which diverse ML methods are applied. Trivially extending the method to (non-ML) clinical scores is also discussed.

  16. Identifying Structural Flow Defects in Disordered Solids Using Machine-Learning Methods

    NASA Astrophysics Data System (ADS)

    Cubuk, E. D.; Schoenholz, S. S.; Rieser, J. M.; Malone, B. D.; Rottler, J.; Durian, D. J.; Kaxiras, E.; Liu, A. J.

    2015-03-01

    We use machine-learning methods on local structure to identify flow defects—or particles susceptible to rearrangement—in jammed and glassy systems. We apply this method successfully to two very different systems: a two-dimensional experimental realization of a granular pillar under compression and a Lennard-Jones glass in both two and three dimensions above and below its glass transition temperature. We also identify characteristics of flow defects that differentiate them from the rest of the sample. Our results show it is possible to discern subtle structural features responsible for heterogeneous dynamics observed across a broad range of disordered materials.

  17. Briefing in application of machine learning methods in ion channel prediction.

    PubMed

    Lin, Hao; Chen, Wei

    2015-01-01

    In cells, ion channels are one of the most important classes of membrane proteins which allow inorganic ions to move across the membrane. A wide range of biological processes are involved and regulated by the opening and closing of ion channels. Ion channels can be classified into numerous classes and different types of ion channels exhibit different functions. Thus, the correct identification of ion channels and their types using computational methods will provide in-depth insights into their function in various biological processes. In this review, we will briefly introduce and discuss the recent progress in ion channel prediction using machine learning methods.

  18. A Critical Review for Developing Accurate and Dynamic Predictive Models Using Machine Learning Methods in Medicine and Health Care.

    PubMed

    Alanazi, Hamdan O; Abdullah, Abdul Hanan; Qureshi, Kashif Naseer

    2017-04-01

    Recently, Artificial Intelligence (AI) has been used widely in medicine and health care sector. In machine learning, the classification or prediction is a major field of AI. Today, the study of existing predictive models based on machine learning methods is extremely active. Doctors need accurate predictions for the outcomes of their patients' diseases. In addition, for accurate predictions, timing is another significant factor that influences treatment decisions. In this paper, existing predictive models in medicine and health care have critically reviewed. Furthermore, the most famous machine learning methods have explained, and the confusion between a statistical approach and machine learning has clarified. A review of related literature reveals that the predictions of existing predictive models differ even when the same dataset is used. Therefore, existing predictive models are essential, and current methods must be improved.

  19. An unsupervised machine learning method for assessing quality of tandem mass spectra

    PubMed Central

    2012-01-01

    Background In a single proteomic project, tandem mass spectrometers can produce hundreds of millions of tandem mass spectra. However, majority of tandem mass spectra are of poor quality, it wastes time to search them for peptides. Therefore, the quality assessment (before database search) is very useful in the pipeline of protein identification via tandem mass spectra, especially on the reduction of searching time and the decrease of false identifications. Most existing methods for quality assessment are supervised machine learning methods based on a number of features which describe the quality of tandem mass spectra. These methods need the training datasets with knowing the quality of all spectra, which are usually unavailable for the new datasets. Results This study proposes an unsupervised machine learning method for quality assessment of tandem mass spectra without any training dataset. This proposed method estimates the conditional probabilities of spectra being high quality from the quality assessments based on individual features. The probabilities are estimated through a constraint optimization problem. An efficient algorithm is developed to solve the constraint optimization problem and is proved to be convergent. Experimental results on two datasets illustrate that if we search only tandem spectra with the high quality determined by the proposed method, we can save about 56 % and 62% of database searching time while losing only a small amount of high-quality spectra. Conclusions Results indicate that the proposed method has a good performance for the quality assessment of tandem mass spectra and the way we estimate the conditional probabilities is effective. PMID:22759570

  20. Greedy and Linear Ensembles of Machine Learning Methods Outperform Single Approaches for QSPR Regression Problems.

    PubMed

    Kew, William; Mitchell, John B O

    2015-09-01

    The application of Machine Learning to cheminformatics is a large and active field of research, but there exist few papers which discuss whether ensembles of different Machine Learning methods can improve upon the performance of their component methodologies. Here we investigated a variety of methods, including kernel-based, tree, linear, neural networks, and both greedy and linear ensemble methods. These were all tested against a standardised methodology for regression with data relevant to the pharmaceutical development process. This investigation focused on QSPR problems within drug-like chemical space. We aimed to investigate which methods perform best, and how the 'wisdom of crowds' principle can be applied to ensemble predictors. It was found that no single method performs best for all problems, but that a dynamic, well-structured ensemble predictor would perform very well across the board, usually providing an improvement in performance over the best single method. Its use of weighting factors allows the greedy ensemble to acquire a bigger contribution from the better performing models, and this helps the greedy ensemble generally to outperform the simpler linear ensemble. Choice of data preprocessing methodology was found to be crucial to performance of each method too. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  1. Machine learning exciton dynamics

    SciTech Connect

    Häse, Florian; Valleau, Stéphanie; Pyzer-Knapp, Edward; Aspuru-Guzik, Alán

    2016-04-01

    Obtaining the exciton dynamics of large photosynthetic complexes by using mixed quantum mechanics/molecular mechanics (QM/MM) is computationally demanding. We propose a machine learning technique, multi-layer perceptrons, as a tool to reduce the time required to compute excited state energies. With this approach we predict time-dependent density functional theory (TDDFT) excited state energies of bacteriochlorophylls in the Fenna–Matthews–Olson (FMO) complex. Additionally we compute spectral densities and exciton populations from the predictions. Different methods to determine multi-layer perceptron training sets are introduced, leading to several initial data selections. In addition, we compute spectral densities and exciton populations. Once multi-layer perceptrons are trained, predicting excited state energies was found to be significantly faster than the corresponding QM/MM calculations. We showed that multi-layer perceptrons can successfully reproduce the energies of QM/MM calculations to a high degree of accuracy with prediction errors contained within 0.01 eV (0.5%). Spectral densities and exciton dynamics are also in agreement with the TDDFT results. The acceleration and accurate prediction of dynamics strongly encourage the combination of machine learning techniques with ab initio methods.

  2. Acceleration of ensemble machine learning methods using many-core devices

    NASA Astrophysics Data System (ADS)

    Tamerus, A.; Washbrook, A.; Wyeth, D.

    2015-12-01

    We present a case study into the acceleration of ensemble machine learning methods using many-core devices in collaboration with Toshiba Medical Visualisation Systems Europe (TMVSE). The adoption of GPUs to execute a key algorithm in the classification of medical image data was shown to significantly reduce overall processing time. Using a representative dataset and pre-trained decision trees as input we will demonstrate how the decision forest classification method can be mapped onto the GPU data processing model. It was found that a GPU-based version of the decision forest method resulted in over 138 times speed-up over a single-threaded CPU implementation with further improvements possible. The same GPU-based software was then directly applied to a suitably formed dataset to benefit supervised learning techniques applied in High Energy Physics (HEP) with similar improvements in performance.

  3. A Model-Free Machine Learning Method for Risk Classification and Survival Probability Prediction.

    PubMed

    Geng, Yuan; Lu, Wenbin; Zhang, Hao Helen

    2014-01-01

    Risk classification and survival probability prediction are two major goals in survival data analysis since they play an important role in patients' risk stratification, long-term diagnosis, and treatment selection. In this article, we propose a new model-free machine learning framework for risk classification and survival probability prediction based on weighted support vector machines. The new procedure does not require any specific parametric or semiparametric model assumption on data, and is therefore capable of capturing nonlinear covariate effects. We use numerous simulation examples to demonstrate finite sample performance of the proposed method under various settings. Applications to a glioma tumor data and a breast cancer gene expression survival data are shown to illustrate the new methodology in real data analysis.

  4. Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards.

    PubMed

    Churpek, Matthew M; Yuen, Trevor C; Winslow, Christopher; Meltzer, David O; Kattan, Michael W; Edelson, Dana P

    2016-02-01

    Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. Observational cohort study. Five hospitals, from November 2008 until January 2013. Hospitalized ward patients None Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score, a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC, 0.80 [95% CI, 0.80-0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC, 0.77 vs 0.74; p < 0.01), and all models were more accurate than the MEWS (AUC, 0.70 [95% CI, 0.70-0.70]). In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards.

  5. Multicenter Comparison of Machine Learning Methods and Conventional Regression for Predicting Clinical Deterioration on the Wards

    PubMed Central

    Churpek, Matthew M; Yuen, Trevor C; Winslow, Christopher; Meltzer, David O; Kattan, Michael W; Edelson, Dana P

    2016-01-01

    OBJECTIVE Machine learning methods are flexible prediction algorithms that may be more accurate than conventional regression. We compared the accuracy of different techniques for detecting clinical deterioration on the wards in a large, multicenter database. DESIGN Observational cohort study. SETTING Five hospitals, from November 2008 until January 2013. PATIENTS Hospitalized ward patients INTERVENTIONS None MEASUREMENTS AND MAIN RESULTS Demographic variables, laboratory values, and vital signs were utilized in a discrete-time survival analysis framework to predict the combined outcome of cardiac arrest, intensive care unit transfer, or death. Two logistic regression models (one using linear predictor terms and a second utilizing restricted cubic splines) were compared to several different machine learning methods. The models were derived in the first 60% of the data by date and then validated in the next 40%. For model derivation, each event time window was matched to a non-event window. All models were compared to each other and to the Modified Early Warning score (MEWS), a commonly cited early warning score, using the area under the receiver operating characteristic curve (AUC). A total of 269,999 patients were admitted, and 424 cardiac arrests, 13,188 intensive care unit transfers, and 2,840 deaths occurred in the study. In the validation dataset, the random forest model was the most accurate model (AUC 0.80 [95% CI 0.80–0.80]). The logistic regression model with spline predictors was more accurate than the model utilizing linear predictors (AUC 0.77 vs 0.74; p<0.01), and all models were more accurate than the MEWS (AUC 0.70 [95% CI 0.70–0.70]). CONCLUSIONS In this multicenter study, we found that several machine learning methods more accurately predicted clinical deterioration than logistic regression. Use of detection algorithms derived from these techniques may result in improved identification of critically ill patients on the wards. PMID:26771782

  6. Using multivariate machine learning methods and structural MRI to classify childhood onset schizophrenia and healthy controls.

    PubMed

    Greenstein, Deanna; Malley, James D; Weisinger, Brian; Clasen, Liv; Gogtay, Nitin

    2012-01-01

    Multivariate machine learning methods can be used to classify groups of schizophrenia patients and controls using structural magnetic resonance imaging (MRI). However, machine learning methods to date have not been extended beyond classification and contemporaneously applied in a meaningful way to clinical measures. We hypothesized that brain measures would classify groups, and that increased likelihood of being classified as a patient using regional brain measures would be positively related to illness severity, developmental delays, and genetic risk. Using 74 anatomic brain MRI sub regions and Random Forest (RF), a machine learning method, we classified 98 childhood onset schizophrenia (COS) patients and 99 age, sex, and ethnicity-matched healthy controls. We also used RF to estimate the probability of being classified as a schizophrenia patient based on MRI measures. We then explored relationships between brain-based probability of illness and symptoms, premorbid development, and presence of copy number variation (CNV) associated with schizophrenia. Brain regions jointly classified COS and control groups with 73.7% accuracy. Greater brain-based probability of illness was associated with worse functioning (p = 0.0004) and fewer developmental delays (p = 0.02). Presence of CNV was associated with lower probability of being classified as schizophrenia (p = 0.001). The regions that were most important in classifying groups included left temporal lobes, bilateral dorsolateral prefrontal regions, and left medial parietal lobes. Schizophrenia and control groups can be well classified using RF and anatomic brain measures, and brain-based probability of illness has a positive relationship with illness severity and a negative relationship with developmental delays/problems and CNV-based risk.

  7. Drug name recognition in biomedical texts: a machine-learning-based method.

    PubMed

    He, Linna; Yang, Zhihao; Lin, Hongfei; Li, Yanpeng

    2014-05-01

    Currently, there is an urgent need to develop a technology for extracting drug information automatically from biomedical texts, and drug name recognition is an essential prerequisite for extracting drug information. This article presents a machine-learning-based approach to recognize drug names in biomedical texts. In this approach, a drug name dictionary is first constructed with the external resource of DrugBank and PubMed. Then a semi-supervised learning method, feature coupling generalization, is used to filter this dictionary. Finally, the dictionary look-up and the condition random field method are combined to recognize drug names. Experimental results show that our approach achieves an F-score of 92.54% on the test set of DDIExtraction2011.

  8. An Evaluation of Machine Learning Methods to Detect Malicious SCADA Communications

    SciTech Connect

    Beaver, Justin M; Borges, Raymond Charles; Buckner, Mark A

    2013-01-01

    Critical infrastructure Supervisory Control and Data Acquisition (SCADA) systems were designed to operate on closed, proprietary networks where a malicious insider posed the greatest threat potential. The centralization of control and the movement towards open systems and standards has improved the efficiency of industrial control, but has also exposed legacy SCADA systems to security threats that they were not designed to mitigate. This work explores the viability of machine learning methods in detecting the new threat scenarios of command and data injection. Similar to network intrusion detection systems in the cyber security domain, the command and control communications in a critical infrastructure setting are monitored, and vetted against examples of benign and malicious command traffic, in order to identify potential attack events. Multiple learning methods are evaluated using a dataset of Remote Terminal Unit communications, which included both normal operations and instances of command and data injection attack scenarios.

  9. A Machine Learning-based Method for Question Type Classification in Biomedical Question Answering.

    PubMed

    Sarrouti, Mourad; Ouatik El Alaoui, Said

    2017-05-18

    Biomedical question type classification is one of the important components of an automatic biomedical question answering system. The performance of the latter depends directly on the performance of its biomedical question type classification system, which consists of assigning a category to each question in order to determine the appropriate answer extraction algorithm. This study aims to automatically classify biomedical questions into one of the four categories: (1) yes/no, (2) factoid, (3) list, and (4) summary. In this paper, we propose a biomedical question type classification method based on machine learning approaches to automatically assign a category to a biomedical question. First, we extract features from biomedical questions using the proposed handcrafted lexico-syntactic patterns. Then, we feed these features for machine-learning algorithms. Finally, the class label is predicted using the trained classifiers. Experimental evaluations performed on large standard annotated datasets of biomedical questions, provided by the BioASQ challenge, demonstrated that our method exhibits significant improved performance when compared to four baseline systems. The proposed method achieves a roughly 10-point increase over the best baseline in terms of accuracy. Moreover, the obtained results show that using handcrafted lexico-syntactic patterns as features' provider of support vector machine (SVM) lead to the highest accuracy of 89.40 %. The proposed method can automatically classify BioASQ questions into one of the four categories: yes/no, factoid, list, and summary. Furthermore, the results demonstrated that our method produced the best classification performance compared to four baseline systems.

  10. Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods.

    PubMed

    Burlina, Philippe; Billings, Seth; Joshi, Neil; Albayda, Jemima

    2017-01-01

    To evaluate the use of ultrasound coupled with machine learning (ML) and deep learning (DL) techniques for automated or semi-automated classification of myositis. Eighty subjects comprised of 19 with inclusion body myositis (IBM), 14 with polymyositis (PM), 14 with dermatomyositis (DM), and 33 normal (N) subjects were included in this study, where 3214 muscle ultrasound images of 7 muscles (observed bilaterally) were acquired. We considered three problems of classification including (A) normal vs. affected (DM, PM, IBM); (B) normal vs. IBM patients; and (C) IBM vs. other types of myositis (DM or PM). We studied the use of an automated DL method using deep convolutional neural networks (DL-DCNNs) for diagnostic classification and compared it with a semi-automated conventional ML method based on random forests (ML-RF) and "engineered" features. We used the known clinical diagnosis as the gold standard for evaluating performance of muscle classification. The performance of the DL-DCNN method resulted in accuracies ± standard deviation of 76.2% ± 3.1% for problem (A), 86.6% ± 2.4% for (B) and 74.8% ± 3.9% for (C), while the ML-RF method led to accuracies of 72.3% ± 3.3% for problem (A), 84.3% ± 2.3% for (B) and 68.9% ± 2.5% for (C). This study demonstrates the application of machine learning methods for automatically or semi-automatically classifying inflammatory muscle disease using muscle ultrasound. Compared to the conventional random forest machine learning method used here, which has the drawback of requiring manual delineation of muscle/fat boundaries, DCNN-based classification by and large improved the accuracies in all classification problems while providing a fully automated approach to classification.

  11. Predicting obsessive-compulsive disorder severity combining neuroimaging and machine learning methods.

    PubMed

    Hoexter, Marcelo Q; Miguel, Euripedes C; Diniz, Juliana B; Shavitt, Roseli G; Busatto, Geraldo F; Sato, João R

    2013-09-25

    Recently, machine learning methods have been used to discriminate, on an individual basis, patients from healthy controls through brain structural magnetic resonance imaging (MRI). However, the application of these methods to predict the severity of psychiatric symptoms is less common. Herein, support vector regression (SVR) was employed to evaluate whether gray matter volumes encompassing cortical-subcortical loops contain discriminative information to predict obsessive-compulsive disorder (OCD) symptom severity in 37 treatment-naïve adult OCD patients. The Pearson correlation coefficient between predicted and observed symptom severity scores was 0.49 (p=0.002) for total Dimensional Yale-Brown Obsessive-Compulsive Scale (DY-BOCS) and 0.44 (p=0.006) for total Yale-Brown Obsessive-Compulsive Scale (Y-BOCS). The regions that contained the most discriminative information were the left medial orbitofrontal cortex and the left putamen for both scales. Our sample is relatively small and our results must be replicated with independent and larger samples. These results indicate that machine learning methods such as SVR analysis may identify neurobiological markers to predict OCD symptom severity based on individual structural MRI datasets. © 2013 Elsevier B.V. All rights reserved.

  12. NetiNeti: discovery of scientific names from text using machine learning methods.

    PubMed

    Akella, Lakshmi Manohar; Norton, Catherine N; Miller, Holly

    2012-08-22

    A scientific name for an organism can be associated with almost all biological data. Name identification is an important step in many text mining tasks aiming to extract useful information from biological, biomedical and biodiversity text sources. A scientific name acts as an important metadata element to link biological information. We present NetiNeti (Name Extraction from Textual Information-Name Extraction for Taxonomic Indexing), a machine learning based approach for recognition of scientific names including the discovery of new species names from text that will also handle misspellings, OCR errors and other variations in names. The system generates candidate names using rules for scientific names and applies probabilistic machine learning methods to classify names based on structural features of candidate names and features derived from their contexts. NetiNeti can also disambiguate scientific names from other names using the contextual information. We evaluated NetiNeti on legacy biodiversity texts and biomedical literature (MEDLINE). NetiNeti performs better (precision = 98.9% and recall = 70.5%) compared to a popular dictionary based approach (precision = 97.5% and recall = 54.3%) on a 600-page biodiversity book that was manually marked by an annotator. On a small set of PubMed Central's full text articles annotated with scientific names, the precision and recall values are 98.5% and 96.2% respectively. NetiNeti found more than 190,000 unique binomial and trinomial names in more than 1,880,000 PubMed records when used on the full MEDLINE database. NetiNeti also successfully identifies almost all of the new species names mentioned within web pages. We present NetiNeti, a machine learning based approach for identification and discovery of scientific names. The system implementing the approach can be accessed at http://namefinding.ubio.org.

  13. A New Automated Design Method Based on Machine Learning for CMOS Analog Circuits

    NASA Astrophysics Data System (ADS)

    Moradi, Behzad; Mirzaei, Abdolreza

    2016-11-01

    A new simulation based automated CMOS analog circuit design method which applies a multi-objective non-Darwinian-type evolutionary algorithm based on Learnable Evolution Model (LEM) is proposed in this article. The multi-objective property of this automated design of CMOS analog circuits is governed by a modified Strength Pareto Evolutionary Algorithm (SPEA) incorporated in the LEM algorithm presented here. LEM includes a machine learning method such as the decision trees that makes a distinction between high- and low-fitness areas in the design space. The learning process can detect the right directions of the evolution and lead to high steps in the evolution of the individuals. The learning phase shortens the evolution process and makes remarkable reduction in the number of individual evaluations. The expert designer's knowledge on circuit is applied in the design process in order to reduce the design space as well as the design time. The circuit evaluation is made by HSPICE simulator. In order to improve the design accuracy, bsim3v3 CMOS transistor model is adopted in this proposed design method. This proposed design method is tested on three different operational amplifier circuits. The performance of this proposed design method is verified by comparing it with the evolutionary strategy algorithm and other similar methods.

  14. A Machine Learning Method for the Prediction of Receptor Activation in the Simulation of Synapses

    PubMed Central

    Montes, Jesus; Gomez, Elena; Merchán-Pérez, Angel; DeFelipe, Javier; Peña, Jose-Maria

    2013-01-01

    Chemical synaptic transmission involves the release of a neurotransmitter that diffuses in the extracellular space and interacts with specific receptors located on the postsynaptic membrane. Computer simulation approaches provide fundamental tools for exploring various aspects of the synaptic transmission under different conditions. In particular, Monte Carlo methods can track the stochastic movements of neurotransmitter molecules and their interactions with other discrete molecules, the receptors. However, these methods are computationally expensive, even when used with simplified models, preventing their use in large-scale and multi-scale simulations of complex neuronal systems that may involve large numbers of synaptic connections. We have developed a machine-learning based method that can accurately predict relevant aspects of the behavior of synapses, such as the percentage of open synaptic receptors as a function of time since the release of the neurotransmitter, with considerably lower computational cost compared with the conventional Monte Carlo alternative. The method is designed to learn patterns and general principles from a corpus of previously generated Monte Carlo simulations of synapses covering a wide range of structural and functional characteristics. These patterns are later used as a predictive model of the behavior of synapses under different conditions without the need for additional computationally expensive Monte Carlo simulations. This is performed in five stages: data sampling, fold creation, machine learning, validation and curve fitting. The resulting procedure is accurate, automatic, and it is general enough to predict synapse behavior under experimental conditions that are different to the ones it has been trained on. Since our method efficiently reproduces the results that can be obtained with Monte Carlo simulations at a considerably lower computational cost, it is suitable for the simulation of high numbers of synapses and it is

  15. A machine learning method for the prediction of receptor activation in the simulation of synapses.

    PubMed

    Montes, Jesus; Gomez, Elena; Merchán-Pérez, Angel; Defelipe, Javier; Peña, Jose-Maria

    2013-01-01

    Chemical synaptic transmission involves the release of a neurotransmitter that diffuses in the extracellular space and interacts with specific receptors located on the postsynaptic membrane. Computer simulation approaches provide fundamental tools for exploring various aspects of the synaptic transmission under different conditions. In particular, Monte Carlo methods can track the stochastic movements of neurotransmitter molecules and their interactions with other discrete molecules, the receptors. However, these methods are computationally expensive, even when used with simplified models, preventing their use in large-scale and multi-scale simulations of complex neuronal systems that may involve large numbers of synaptic connections. We have developed a machine-learning based method that can accurately predict relevant aspects of the behavior of synapses, such as the percentage of open synaptic receptors as a function of time since the release of the neurotransmitter, with considerably lower computational cost compared with the conventional Monte Carlo alternative. The method is designed to learn patterns and general principles from a corpus of previously generated Monte Carlo simulations of synapses covering a wide range of structural and functional characteristics. These patterns are later used as a predictive model of the behavior of synapses under different conditions without the need for additional computationally expensive Monte Carlo simulations. This is performed in five stages: data sampling, fold creation, machine learning, validation and curve fitting. The resulting procedure is accurate, automatic, and it is general enough to predict synapse behavior under experimental conditions that are different to the ones it has been trained on. Since our method efficiently reproduces the results that can be obtained with Monte Carlo simulations at a considerably lower computational cost, it is suitable for the simulation of high numbers of synapses and it is

  16. Glucose Oxidase Biosensor Modeling and Predictors Optimization by Machine Learning Methods

    PubMed Central

    Gonzalez-Navarro, Felix F.; Stilianova-Stoytcheva, Margarita; Renteria-Gutierrez, Livier; Belanche-Muñoz, Lluís A.; Flores-Rios, Brenda L.; Ibarra-Esquer, Jorge E.

    2016-01-01

    Biosensors are small analytical devices incorporating a biological recognition element and a physico-chemical transducer to convert a biological signal into an electrical reading. Nowadays, their technological appeal resides in their fast performance, high sensitivity and continuous measuring capabilities; however, a full understanding is still under research. This paper aims to contribute to this growing field of biotechnology, with a focus on Glucose-Oxidase Biosensor (GOB) modeling through statistical learning methods from a regression perspective. We model the amperometric response of a GOB with dependent variables under different conditions, such as temperature, benzoquinone, pH and glucose concentrations, by means of several machine learning algorithms. Since the sensitivity of a GOB response is strongly related to these dependent variables, their interactions should be optimized to maximize the output signal, for which a genetic algorithm and simulated annealing are used. We report a model that shows a good generalization error and is consistent with the optimization. PMID:27792165

  17. Machine Learning in Medicine.

    PubMed

    Deo, Rahul C

    2015-11-17

    Spurred by advances in processing power, memory, storage, and an unprecedented wealth of data, computers are being asked to tackle increasingly complex learning tasks, often with astonishing success. Computers have now mastered a popular variant of poker, learned the laws of physics from experimental data, and become experts in video games - tasks that would have been deemed impossible not too long ago. In parallel, the number of companies centered on applying complex data analysis to varying industries has exploded, and it is thus unsurprising that some analytic companies are turning attention to problems in health care. The purpose of this review is to explore what problems in medicine might benefit from such learning approaches and use examples from the literature to introduce basic concepts in machine learning. It is important to note that seemingly large enough medical data sets and adequate learning algorithms have been available for many decades, and yet, although there are thousands of papers applying machine learning algorithms to medical data, very few have contributed meaningfully to clinical care. This lack of impact stands in stark contrast to the enormous relevance of machine learning to many other industries. Thus, part of my effort will be to identify what obstacles there may be to changing the practice of medicine through statistical learning approaches, and discuss how these might be overcome.

  18. Evaluation of machine-learning methods for ligand-based virtual screening

    NASA Astrophysics Data System (ADS)

    Chen, Beining; Harrison, Robert F.; Papadatos, George; Willett, Peter; Wood, David J.; Lewell, Xiao Qing; Greenidge, Paulette; Stiefl, Nikolaus

    2007-01-01

    Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier (NBC) methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of an NBC when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

  19. Machine learning for medical images analysis.

    PubMed

    Criminisi, A

    2016-10-01

    This article discusses the application of machine learning for the analysis of medical images. Specifically: (i) We show how a special type of learning models can be thought of as automatically optimized, hierarchically-structured, rule-based algorithms, and (ii) We discuss how the issue of collecting large labelled datasets applies to both conventional algorithms as well as machine learning techniques. The size of the training database is a function of model complexity rather than a characteristic of machine learning methods.

  20. Recognizing Disjoint Clinical Concepts in Clinical Text Using Machine Learning-based Methods

    PubMed Central

    Tang, Buzhou; Chen, Qingcai; Wang, Xiaolong; Wu, Yonghui; Zhang, Yaoyun; Jiang, Min; Wang, Jingqi; Xu, Hua

    2015-01-01

    Clinical concept recognition (CCR) is a fundamental task in clinical natural language processing (NLP) field. Almost all current machine learning-based CCR systems can only recognize clinical concepts of consecutive words (called consecutive clinical concepts, CCCs), but can do nothing about clinical concepts of disjoint words (called disjoint clinical concepts, DCCs), which widely exist in clinical text. In this paper, we proposed two novel types of representations for disjoint clinical concepts, and applied two state-of-the-art machine learning methods to recognizing consecutive and disjoint concepts. Experiments conducted on the 2013 ShARe/CLEF challenge corpus showed that our best system achieved a “strict” F-measure of 0.803 for CCCs, a “strict” F-measure of 0.477 for DCCs, and a “strict” F-measure of 0.783 for all clinical concepts, significantly higher than the baseline systems by 4.2% and 4.1% respectively. PMID:26958258

  1. Estimating the complexity of 3D structural models using machine learning methods

    NASA Astrophysics Data System (ADS)

    Mejía-Herrera, Pablo; Kakurina, Maria; Royer, Jean-Jacques

    2016-04-01

    Quantifying the complexity of 3D geological structural models can play a major role in natural resources exploration surveys, for predicting environmental hazards or for forecasting fossil resources. This paper proposes a structural complexity index which can be used to help in defining the degree of effort necessary to build a 3D model for a given degree of confidence, and also to identify locations where addition efforts are required to meet a given acceptable risk of uncertainty. In this work, it is considered that the structural complexity index can be estimated using machine learning methods on raw geo-data. More precisely, the metrics for measuring the complexity can be approximated as the difficulty degree associated to the prediction of the geological objects distribution calculated based on partial information on the actual structural distribution of materials. The proposed methodology is tested on a set of 3D synthetic structural models for which the degree of effort during their building is assessed using various parameters (such as number of faults, number of part in a surface object, number of borders, ...), the rank of geological elements contained in each model, and, finally, their level of deformation (folding and faulting). The results show how the estimated complexity in a 3D model can be approximated by the quantity of partial data necessaries to simulated at a given precision the actual 3D model without error using machine learning algorithms.

  2. Comparison and optimization of machine learning methods for automated classification of circulating tumor cells.

    PubMed

    Lannin, Timothy B; Thege, Fredrik I; Kirby, Brian J

    2016-10-01

    Advances in rare cell capture technology have made possible the interrogation of circulating tumor cells (CTCs) captured from whole patient blood. However, locating captured cells in the device by manual counting bottlenecks data processing by being tedious (hours per sample) and compromises the results by being inconsistent and prone to user bias. Some recent work has been done to automate the cell location and classification process to address these problems, employing image processing and machine learning (ML) algorithms to locate and classify cells in fluorescent microscope images. However, the type of machine learning method used is a part of the design space that has not been thoroughly explored. Thus, we have trained four ML algorithms on three different datasets. The trained ML algorithms locate and classify thousands of possible cells in a few minutes rather than a few hours, representing an order of magnitude increase in processing speed. Furthermore, some algorithms have a significantly (P < 0.05) higher area under the receiver operating characteristic curve than do other algorithms. Additionally, significant (P < 0.05) losses to performance occur when training on cell lines and testing on CTCs (and vice versa), indicating the need to train on a system that is representative of future unlabeled data. Optimal algorithm selection depends on the peculiarities of the individual dataset, indicating the need of a careful comparison and optimization of algorithms for individual image classification tasks. © 2016 International Society for Advancement of Cytometry. © 2016 International Society for Advancement of Cytometry.

  3. Benchmark of Machine Learning Methods for Classification of a SENTINEL-2 Image

    NASA Astrophysics Data System (ADS)

    Pirotti, F.; Sunar, F.; Piragnolo, M.

    2016-06-01

    Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. Validation is carried out using three different approaches: (i) using pixels from the training dataset (train), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (kfold) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (full) and with k-fold cross-validation (kfold) with ten folds. Results from validation of predictions of the whole dataset (full) show the random

  4. Logic Learning Machine and standard supervised methods for Hodgkin's lymphoma prognosis using gene expression data and clinical variables.

    PubMed

    Parodi, Stefano; Manneschi, Chiara; Verda, Damiano; Ferrari, Enrico; Muselli, Marco

    2016-06-27

    This study evaluates the performance of a set of machine learning techniques in predicting the prognosis of Hodgkin's lymphoma using clinical factors and gene expression data. Analysed samples from 130 Hodgkin's lymphoma patients included a small set of clinical variables and more than 54,000 gene features. Machine learning classifiers included three black-box algorithms (k-nearest neighbour, Artificial Neural Network, and Support Vector Machine) and two methods based on intelligible rules (Decision Tree and the innovative Logic Learning Machine method). Support Vector Machine clearly outperformed any of the other methods. Among the two rule-based algorithms, Logic Learning Machine performed better and identified a set of simple intelligible rules based on a combination of clinical variables and gene expressions. Decision Tree identified a non-coding gene (XIST) involved in the early phases of X chromosome inactivation that was overexpressed in females and in non-relapsed patients. XIST expression might be responsible for the better prognosis of female Hodgkin's lymphoma patients.

  5. MST-GEN: An Efficient Parameter Selection Method for One-Class Extreme Learning Machine.

    PubMed

    Wang, Siqi; Liu, Qiang; Zhu, En; Yin, Jianping; Zhao, Wentao

    2017-10-01

    One-class classification (OCC) models a set of target data from one class to detect outliers. OCC approaches like one-class support vector machine (OCSVM) and support vector data description (SVDD) have wide practical applications. Recently, one-class extreme learning machine (OCELM), which inherits the fast learning speed of original ELM and achieves equivalent or higher data description performance than OCSVM and SVDD, is proposed as a promising alternative. However, OCELM faces the same thorny parameter selection problem as OCSVM and SVDD. It significantly affects the performance of OCELM and remains under-explored. This paper proposes minimal spanning tree (MST)-GEN, an automatic way to select proper parameters for OCELM. Specifically, we first build a n -round MST to model the structure and distribution of the given target set. With information from n -round MST, a controllable number of pseudo outliers are generated by edge pattern detection and a novel "repelling" process, which readily overcomes two fundamental problems in previous outlier generation methods: where and how many pseudo outliers should be generated. Unlike previous methods that only generate pseudo outliers, we further exploit n -round MST to generate pseudo target data, so as to avoid the time-consuming cross-validation process and accelerate the parameter selection. Extensive experiments on various datasets suggest that the proposed method can select parameters for OCELM in a highly efficient and accurate manner when compared with existing methods, which enables OCELM to achieve better OCC performance in OCC applications. Furthermore, our experiments show that MST-GEN can also be favorably applied to other prevalent OCC methods like OCSVM and SVDD.

  6. Building blocks for automated elucidation of metabolites: Machine learning methods for NMR prediction

    PubMed Central

    Kuhn, Stefan; Egert, Björn; Neumann, Steffen; Steinbeck, Christoph

    2008-01-01

    Background Current efforts in Metabolomics, such as the Human Metabolome Project, collect structures of biological metabolites as well as data for their characterisation, such as spectra for identification of substances and measurements of their concentration. Still, only a fraction of existing metabolites and their spectral fingerprints are known. Computer-Assisted Structure Elucidation (CASE) of biological metabolites will be an important tool to leverage this lack of knowledge. Indispensable for CASE are modules to predict spectra for hypothetical structures. This paper evaluates different statistical and machine learning methods to perform predictions of proton NMR spectra based on data from our open database NMRShiftDB. Results A mean absolute error of 0.18 ppm was achieved for the prediction of proton NMR shifts ranging from 0 to 11 ppm. Random forest, J48 decision tree and support vector machines achieved similar overall errors. HOSE codes being a notably simple method achieved a comparatively good result of 0.17 ppm mean absolute error. Conclusion NMR prediction methods applied in the course of this work delivered precise predictions which can serve as a building block for Computer-Assisted Structure Elucidation for biological metabolites. PMID:18817546

  7. A machine learning approach to the potential-field method for implicit modeling of geological structures

    NASA Astrophysics Data System (ADS)

    Gonçalves, Ítalo Gomes; Kumaira, Sissa; Guadagnin, Felipe

    2017-06-01

    Implicit modeling has experienced a rise in popularity over the last decade due to its advantages in terms of speed and reproducibility in comparison with manual digitization of geological structures. The potential-field method consists in interpolating a scalar function that indicates to which side of a geological boundary a given point belongs to, based on cokriging of point data and structural orientations. This work proposes a vector potential-field solution from a machine learning perspective, recasting the problem as multi-class classification, which alleviates some of the original method's assumptions. The potentials related to each geological class are interpreted in a compositional data framework. Variogram modeling is avoided through the use of maximum likelihood to train the model, and an uncertainty measure is introduced. The methodology was applied to the modeling of a sample dataset provided with the software Move™. The calculations were implemented in the R language and 3D visualizations were prepared with the rgl package.

  8. Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances.

    PubMed

    Abut, Fatih; Akay, Mehmet Fatih

    2015-01-01

    Maximal oxygen uptake (VO2max) indicates how many milliliters of oxygen the body can consume in a state of intense exercise per minute. VO2max plays an important role in both sport and medical sciences for different purposes, such as indicating the endurance capacity of athletes or serving as a metric in estimating the disease risk of a person. In general, the direct measurement of VO2max provides the most accurate assessment of aerobic power. However, despite a high level of accuracy, practical limitations associated with the direct measurement of VO2max, such as the requirement of expensive and sophisticated laboratory equipment or trained staff, have led to the development of various regression models for predicting VO2max. Consequently, a lot of studies have been conducted in the last years to predict VO2max of various target audiences, ranging from soccer athletes, nonexpert swimmers, cross-country skiers to healthy-fit adults, teenagers, and children. Numerous prediction models have been developed using different sets of predictor variables and a variety of machine learning and statistical methods, including support vector machine, multilayer perceptron, general regression neural network, and multiple linear regression. The purpose of this study is to give a detailed overview about the data-driven modeling studies for the prediction of VO2max conducted in recent years and to compare the performance of various VO2max prediction models reported in related literature in terms of two well-known metrics, namely, multiple correlation coefficient (R) and standard error of estimate. The survey results reveal that with respect to regression methods used to develop prediction models, support vector machine, in general, shows better performance than other methods, whereas multiple linear regression exhibits the worst performance.

  9. Machine learning and statistical methods for the prediction of maximal oxygen uptake: recent advances

    PubMed Central

    Abut, Fatih; Akay, Mehmet Fatih

    2015-01-01

    Maximal oxygen uptake (VO2max) indicates how many milliliters of oxygen the body can consume in a state of intense exercise per minute. VO2max plays an important role in both sport and medical sciences for different purposes, such as indicating the endurance capacity of athletes or serving as a metric in estimating the disease risk of a person. In general, the direct measurement of VO2max provides the most accurate assessment of aerobic power. However, despite a high level of accuracy, practical limitations associated with the direct measurement of VO2max, such as the requirement of expensive and sophisticated laboratory equipment or trained staff, have led to the development of various regression models for predicting VO2max. Consequently, a lot of studies have been conducted in the last years to predict VO2max of various target audiences, ranging from soccer athletes, nonexpert swimmers, cross-country skiers to healthy-fit adults, teenagers, and children. Numerous prediction models have been developed using different sets of predictor variables and a variety of machine learning and statistical methods, including support vector machine, multilayer perceptron, general regression neural network, and multiple linear regression. The purpose of this study is to give a detailed overview about the data-driven modeling studies for the prediction of VO2max conducted in recent years and to compare the performance of various VO2max prediction models reported in related literature in terms of two well-known metrics, namely, multiple correlation coefficient (R) and standard error of estimate. The survey results reveal that with respect to regression methods used to develop prediction models, support vector machine, in general, shows better performance than other methods, whereas multiple linear regression exhibits the worst performance. PMID:26346869

  10. Automating Construction of Machine Learning Models With Clinical Big Data: Proposal Rationale and Methods.

    PubMed

    Luo, Gang; Stone, Bryan L; Johnson, Michael D; Tarczy-Hornoch, Peter; Wilcox, Adam B; Mooney, Sean D; Sheng, Xiaoming; Haug, Peter J; Nkoy, Flory L

    2017-08-29

    To improve health outcomes and cut health care costs, we often need to conduct prediction/classification using large clinical datasets (aka, clinical big data), for example, to identify high-risk patients for preventive interventions. Machine learning has been proposed as a key technology for doing this. Machine learning has won most data science competitions and could support many clinical activities, yet only 15% of hospitals use it for even limited purposes. Despite familiarity with data, health care researchers often lack machine learning expertise to directly use clinical big data, creating a hurdle in realizing value from their data. Health care researchers can work with data scientists with deep machine learning knowledge, but it takes time and effort for both parties to communicate effectively. Facing a shortage in the United States of data scientists and hiring competition from companies with deep pockets, health care systems have difficulty recruiting data scientists. Building and generalizing a machine learning model often requires hundreds to thousands of manual iterations by data scientists to select the following: (1) hyper-parameter values and complex algorithms that greatly affect model accuracy and (2) operators and periods for temporally aggregating clinical attributes (eg, whether a patient's weight kept rising in the past year). This process becomes infeasible with limited budgets. This study's goal is to enable health care researchers to directly use clinical big data, make machine learning feasible with limited budgets and data scientist resources, and realize value from data. This study will allow us to achieve the following: (1) finish developing the new software, Automated Machine Learning (Auto-ML), to automate model selection for machine learning with clinical big data and validate Auto-ML on seven benchmark modeling problems of clinical importance; (2) apply Auto-ML and novel methodology to two new modeling problems crucial for care

  11. Energy landscapes for machine learning.

    PubMed

    Ballard, Andrew J; Das, Ritankar; Martiniani, Stefano; Mehta, Dhagash; Sagun, Levent; Stevenson, Jacob D; Wales, David J

    2017-04-03

    Machine learning techniques are being increasingly used as flexible non-linear fitting and prediction tools in the physical sciences. Fitting functions that exhibit multiple solutions as local minima can be analysed in terms of the corresponding machine learning landscape. Methods to explore and visualise molecular potential energy landscapes can be applied to these machine learning landscapes to gain new insight into the solution space involved in training and the nature of the corresponding predictions. In particular, we can define quantities analogous to molecular structure, thermodynamics, and kinetics, and relate these emergent properties to the structure of the underlying landscape. This Perspective aims to describe these analogies with examples from recent applications, and suggest avenues for new interdisciplinary research.

  12. Applications of Machine Learning and Rule Induction,

    DTIC Science & Technology

    1995-02-15

    An important area of application for machine learning is in automating the acquisition of knowledge bases required for expert systems. In this paper...we review the major paradigms for machine learning , including neural networks, instance-based methods, genetic learning, rule induction, and analytic

  13. Machine learning control (MLC)---a novel method for optimal control of complex nonlinear systems

    NASA Astrophysics Data System (ADS)

    Noack, Bernd R.; Cordier, Laurent; Parezanovic, Vladimir; von Krbek, Kai; Segond, Marc; Abel, Markus W.; Brunton, Steven; Duriez, Thomas

    2014-11-01

    We propose a model-free closed-loop control strategy for complex nonlinear systems with a finite number of sensors and actuators (MIMO). This strategy yields a feedback law which optimizes a cost functional with machine learning methods. Thus, no dynamical model of the plant is required in contrast to model-based approaches, In addition, no working open-loop control is necessary in contrast to adaptive approaches. The approach is illustrated for strongly nonlinear dynamical systems which are not accessible to linear control design. Control studies of several shear-turbulence experiments will be presented in the talks of T. Duriez and V. Parezanović. Funding of the ANR Chair of Excellence TUCOROM, of the ANR Grant SepaCoDe, of the EC's Marie-Curie ITN program and of Ambrosys GmbH is acknowledged.

  14. Classifying Force Spectroscopy of DNA Pulling Measurements Using Supervised and Unsupervised Machine Learning Methods.

    PubMed

    Karatay, Durmus U; Zhang, Jie; Harrison, Jeffrey S; Ginger, David S

    2016-04-25

    Dynamic force spectroscopy (DFS) measurements on biomolecules typically require classifying thousands of repeated force spectra prior to data analysis. Here, we study classification of atomic force microscope-based DFS measurements using machine-learning algorithms in order to automate selection of successful force curves. Notably, we collect a data set that has a testable positive signal using photoswitch-modified DNA before and after illumination with UV (365 nm) light. We generate a feature set consisting of six properties of force-distance curves to train supervised models and use principal component analysis (PCA) for an unsupervised model. For supervised classification, we train random forest models for binary and multiclass classification of force-distance curves. Random forest models predict successful pulls with an accuracy of 94% and classify them into five classes with an accuracy of 90%. The unsupervised method using Gaussian mixture models (GMM) reaches an accuracy of approximately 80% for binary classification.

  15. Classifying spatial patterns of brain activity with machine learning methods: application to lie detection.

    PubMed

    Davatzikos, C; Ruparel, K; Fan, Y; Shen, D G; Acharyya, M; Loughead, J W; Gur, R C; Langleben, D D

    2005-11-15

    Patterns of brain activity during deception have recently been characterized with fMRI on the multi-subject average group level. The clinical value of fMRI in lie detection will be determined by the ability to detect deception in individual subjects, rather than group averages. High-dimensional non-linear pattern classification methods applied to functional magnetic resonance (fMRI) images were used to discriminate between the spatial patterns of brain activity associated with lie and truth. In 22 participants performing a forced-choice deception task, 99% of the true and false responses were discriminated correctly. Predictive accuracy, assessed by cross-validation in participants not included in training, was 88%. The results demonstrate the potential of non-linear machine learning techniques in lie detection and other possible clinical applications of fMRI in individual subjects, and indicate that accurate clinical tests could be based on measurements of brain function with fMRI.

  16. Can Machine Learning Methods Predict Extubation Outcome in Premature Infants as well as Clinicians?

    PubMed

    Mueller, Martina; Almeida, Jonas S; Stanislaus, Romesh; Wagner, Carol L

    2013-01-01

    Though treatment of the prematurely born infant breathing with assistance of a mechanical ventilator has much advanced in the past decades, predicting extubation outcome at a given point in time remains challenging. Numerous studies have been conducted to identify predictors for extubation outcome; however, the rate of infants failing extubation attempts has not declined. To develop a decision-support tool for the prediction of extubation outcome in premature infants using a set of machine learning algorithms. A dataset assembled from 486 premature infants on mechanical ventilation was used to develop predictive models using machine learning algorithms such as artificial neural networks (ANN), support vector machine (SVM), naïve Bayesian classifier (NBC), boosted decision trees (BDT), and multivariable logistic regression (MLR). Performance of all models was evaluated using area under the curve (AUC). For some of the models (ANN, MLR and NBC) results were satisfactory (AUC: 0.63-0.76); however, two algorithms (SVM and BDT) showed poor performance with AUCs of ~0.5. Clinician's predictions still outperform machine learning due to the complexity of the data and contextual information that may not be captured in clinical data used as input for the development of the machine learning algorithms. Inclusion of preprocessing steps in future studies may improve the performance of prediction models.

  17. Comparison of four statistical and machine learning methods for crash severity prediction.

    PubMed

    Iranitalab, Amirfarrokh; Khattak, Aemal

    2017-11-01

    Crash severity prediction models enable different agencies to predict the severity of a reported crash with unknown severity or the severity of crashes that may be expected to occur sometime in the future. This paper had three main objectives: comparison of the performance of four statistical and machine learning methods including Multinomial Logit (MNL), Nearest Neighbor Classification (NNC), Support Vector Machines (SVM) and Random Forests (RF), in predicting traffic crash severity; developing a crash costs-based approach for comparison of crash severity prediction methods; and investigating the effects of data clustering methods comprising K-means Clustering (KC) and Latent Class Clustering (LCC), on the performance of crash severity prediction models. The 2012-2015 reported crash data from Nebraska, United States was obtained and two-vehicle crashes were extracted as the analysis data. The dataset was split into training/estimation (2012-2014) and validation (2015) subsets. The four prediction methods were trained/estimated using the training/estimation dataset and the correct prediction rates for each crash severity level, overall correct prediction rate and a proposed crash costs-based accuracy measure were obtained for the validation dataset. The correct prediction rates and the proposed approach showed NNC had the best prediction performance in overall and in more severe crashes. RF and SVM had the next two sufficient performances and MNL was the weakest method. Data clustering did not affect the prediction results of SVM, but KC improved the prediction performance of MNL, NNC and RF, while LCC caused improvement in MNL and RF but weakened the performance of NNC. Overall correct prediction rate had almost the exact opposite results compared to the proposed approach, showing that neglecting the crash costs can lead to misjudgment in choosing the right prediction method. Copyright © 2017 Elsevier Ltd. All rights reserved.

  18. Propensity score estimation: machine learning and classification methods as alternatives to logistic regression

    PubMed Central

    Westreich, Daniel; Lessler, Justin; Funk, Michele Jonsson

    2010-01-01

    Summary Objective Propensity scores for the analysis of observational data are typically estimated using logistic regression. Our objective in this Review was to assess machine learning alternatives to logistic regression which may accomplish the same goals but with fewer assumptions or greater accuracy. Study Design and Setting We identified alternative methods for propensity score estimation and/or classification from the public health, biostatistics, discrete mathematics, and computer science literature, and evaluated these algorithms for applicability to the problem of propensity score estimation, potential advantages over logistic regression, and ease of use. Results We identified four techniques as alternatives to logistic regression: neural networks, support vector machines, decision trees (CART), and meta-classifiers (in particular, boosting). Conclusion While the assumptions of logistic regression are well understood, those assumptions are frequently ignored. All four alternatives have advantages and disadvantages compared with logistic regression. Boosting (meta-classifiers) and to a lesser extent decision trees (particularly CART) appear to be most promising for use in the context of propensity score analysis, but extensive simulation studies are needed to establish their utility in practice. PMID:20630332

  19. Classification of P-glycoprotein-interacting compounds using machine learning methods.

    PubMed

    Prachayasittikul, Veda; Worachartcheewan, Apilak; Shoombuatong, Watshara; Prachayasittikul, Virapong; Nantasenamat, Chanin

    2015-01-01

    P-glycoprotein (Pgp) is a drug transporter that plays important roles in multidrug resistance and drug pharmacokinetics. The inhibition of Pgp has become a notable strategy for combating multidrug-resistant cancers and improving therapeutic outcomes. However, the polyspecific nature of Pgp, together with inconsistent results in experimental assays, renders the determination of endpoints for Pgp-interacting compounds a great challenge. In this study, the classification of a large set of 2,477 Pgp-interacting compounds (i.e., 1341 inhibitors, 913 non-inhibitors, 197 substrates and 26 non-substrates) was performed using several machine learning methods (i.e., decision tree induction, artificial neural network modelling and support vector machine) as a function of their physicochemical properties. The models provided good predictive performance, producing MCC values in the range of 0.739-1 for internal cross-validation and 0.665-1 for external validation. The study provided simple and interpretable models for important properties that influence the activity of Pgp-interacting compounds, which are potentially beneficial for screening and rational design of Pgp inhibitors that are of clinical importance.

  20. Prediction and Identification of Krüppel-like transcription factors by machine learning method.

    PubMed

    Liao, Zhijun; Wang, Xinrui; Chend, Xingyong; Zoub, Quan

    2017-03-13

    The Krüppel-like factors (KLFs)are a family of containing zinc finger(ZF) motif transcription factors with 18 members in human genome.KLFs possess various physiological functionrelating withnumerous cancers and other diseases. Here we perform a binary-class classification of KLFs and non-KLFs and conserved motifs analysis of human KLFs. We search and cluster the protein sequences andseparate them into training datasetand test dataset(containing only negative samples), after extracting the 188-dimensional(188D) feature vectors we carry out category with four classifiers(GBDT, libSVM, RF, and k-NN), and use 10-fold cross-validation.On the human KLFs, we further explore the evolutionary relationship and motif distribution, and finally we analyze the conserved amino acid residues of three ZFs. The results show that classifier models of the training dataset were well constructed, and the highest specificity reached 99.83% from alibrary for support vector machine(libSVM)and the correctly classified rates were over 70% on test dataset. The 18 human KLFs can be further divided into 7 groups and the ZF domains were located at the C-terminus. Many conserved sequences,including Cys,His, the spanand interval, were consistent in the three ZF domains. In conclusion, we have built two-class classification models for KLFs prediction by novel machine learning methods.

  1. Classification of P-glycoprotein-interacting compounds using machine learning methods

    PubMed Central

    Prachayasittikul, Veda; Worachartcheewan, Apilak; Shoombuatong, Watshara; Prachayasittikul, Virapong; Nantasenamat, Chanin

    2015-01-01

    P-glycoprotein (Pgp) is a drug transporter that plays important roles in multidrug resistance and drug pharmacokinetics. The inhibition of Pgp has become a notable strategy for combating multidrug-resistant cancers and improving therapeutic outcomes. However, the polyspecific nature of Pgp, together with inconsistent results in experimental assays, renders the determination of endpoints for Pgp-interacting compounds a great challenge. In this study, the classification of a large set of 2,477 Pgp-interacting compounds (i.e., 1341 inhibitors, 913 non-inhibitors, 197 substrates and 26 non-substrates) was performed using several machine learning methods (i.e., decision tree induction, artificial neural network modelling and support vector machine) as a function of their physicochemical properties. The models provided good predictive performance, producing MCC values in the range of 0.739-1 for internal cross-validation and 0.665-1 for external validation. The study provided simple and interpretable models for important properties that influence the activity of Pgp-interacting compounds, which are potentially beneficial for screening and rational design of Pgp inhibitors that are of clinical importance. PMID:26862321

  2. A Novel Gravity Compensation Method for High Precision Free-INS Based on "Extreme Learning Machine".

    PubMed

    Zhou, Xiao; Yang, Gongliu; Cai, Qingzhong; Wang, Jing

    2016-11-29

    In recent years, with the emergency of high precision inertial sensors (accelerometers and gyros), gravity compensation has become a major source influencing the navigation accuracy in inertial navigation systems (INS), especially for high-precision INS. This paper presents preliminary results concerning the effect of gravity disturbance on INS. Meanwhile, this paper proposes a novel gravity compensation method for high-precision INS, which estimates the gravity disturbance on the track using the extreme learning machine (ELM) method based on measured gravity data on the geoid and processes the gravity disturbance to the height where INS has an upward continuation, then compensates the obtained gravity disturbance into the error equations of INS to restrain the INS error propagation. The estimation accuracy of the gravity disturbance data is verified by numerical tests. The root mean square error (RMSE) of the ELM estimation method can be improved by 23% and 44% compared with the bilinear interpolation method in plain and mountain areas, respectively. To further validate the proposed gravity compensation method, field experiments with an experimental vehicle were carried out in two regions. Test 1 was carried out in a plain area and Test 2 in a mountain area. The field experiment results also prove that the proposed gravity compensation method can significantly improve the positioning accuracy. During the 2-h field experiments, the positioning accuracy can be improved by 13% and 29% respectively, in Tests 1 and 2, when the navigation scheme is compensated by the proposed gravity compensation method.

  3. The Security of Machine Learning

    DTIC Science & Technology

    2008-04-24

    Machine learning has become a fundamental tool for computer security, since it can rapidly evolve to changing and complex situations. That...adaptability is also a vulnerability: attackers can exploit machine learning systems. We present a taxonomy identifying and analyzing attacks against machine ...We use our framework to survey and analyze the literature of attacks against machine learning systems. We also illustrate our taxonomy by showing

  4. Time and spectral analysis methods with machine learning for the authentication of digital audio recordings.

    PubMed

    Korycki, Rafal

    2013-07-10

    This paper addresses the problem of tampering detection and discusses new methods that can be used for authenticity analysis of digital audio recordings. Nowadays, the only method referred to digital audio files commonly approved by forensic experts is the ENF criterion. It consists in fluctuation analysis of the mains frequency induced in electronic circuits of recording devices. Therefore, its effectiveness is strictly dependent on the presence of mains signal in the recording, which is a rare occurrence. This article presents the existing methods of time and spectral analysis along with their modifications as proposed by the author involving spectral analysis of residual signal enhanced by machine learning algorithms. The effectiveness of tampering detection methods described in this paper is tested on a predefined music database. The results are compared graphically using ROC-like curves. Furthermore, time-frequency plots are presented and enhanced by reassignment method in purpose of visual inspection of modified recordings. Using this solution, enables analysis of minimal changes of background sounds, which may indicate tampering.

  5. Recent Progress in Machine Learning-Based Methods for Protein Fold Recognition

    PubMed Central

    Wei, Leyi; Zou, Quan

    2016-01-01

    Knowledge on protein folding has a profound impact on understanding the heterogeneity and molecular function of proteins, further facilitating drug design. Predicting the 3D structure (fold) of a protein is a key problem in molecular biology. Determination of the fold of a protein mainly relies on molecular experimental methods. With the development of next-generation sequencing techniques, the discovery of new protein sequences has been rapidly increasing. With such a great number of proteins, the use of experimental techniques to determine protein folding is extremely difficult because these techniques are time consuming and expensive. Thus, developing computational prediction methods that can automatically, rapidly, and accurately classify unknown protein sequences into specific fold categories is urgently needed. Computational recognition of protein folds has been a recent research hotspot in bioinformatics and computational biology. Many computational efforts have been made, generating a variety of computational prediction methods. In this review, we conduct a comprehensive survey of recent computational methods, especially machine learning-based methods, for protein fold recognition. This review is anticipated to assist researchers in their pursuit to systematically understand the computational recognition of protein folds. PMID:27999256

  6. A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease.

    PubMed

    Peng, Bo; Wang, Suhong; Zhou, Zhiyong; Liu, Yan; Tong, Baotong; Zhang, Tao; Dai, Yakang

    2017-06-09

    Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinson's disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinson's Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease. Copyright © 2017 Elsevier B.V. All rights reserved.

  7. Machine learning plus optical flow: a simple and sensitive method to detect cardioactive drugs.

    PubMed

    Lee, Eugene K; Kurokawa, Yosuke K; Tu, Robin; George, Steven C; Khine, Michelle

    2015-07-03

    Current preclinical screening methods do not adequately detect cardiotoxicity. Using human induced pluripotent stem cell-derived cardiomyocytes (iPS-CMs), more physiologically relevant preclinical or patient-specific screening to detect potential cardiotoxic effects of drug candidates may be possible. However, one of the persistent challenges for developing a high-throughput drug screening platform using iPS-CMs is the need to develop a simple and reliable method to measure key electrophysiological and contractile parameters. To address this need, we have developed a platform that combines machine learning paired with brightfield optical flow as a simple and robust tool that can automate the detection of cardiomyocyte drug effects. Using three cardioactive drugs of different mechanisms, including those with primarily electrophysiological effects, we demonstrate the general applicability of this screening method to detect subtle changes in cardiomyocyte contraction. Requiring only brightfield images of cardiomyocyte contractions, we detect changes in cardiomyocyte contraction comparable to - and even superior to - fluorescence readouts. This automated method serves as a widely applicable screening tool to characterize the effects of drugs on cardiomyocyte function.

  8. An Efficient Method for Traffic Sign Recognition Based on Extreme Learning Machine.

    PubMed

    Huang, Zhiyong; Yu, Yuanlong; Gu, Jason; Liu, Huaping

    2017-04-01

    This paper proposes a computationally efficient method for traffic sign recognition (TSR). This proposed method consists of two modules: 1) extraction of histogram of oriented gradient variant (HOGv) feature and 2) a single classifier trained by extreme learning machine (ELM) algorithm. The presented HOGv feature keeps a good balance between redundancy and local details such that it can represent distinctive shapes better. The classifier is a single-hidden-layer feedforward network. Based on ELM algorithm, the connection between input and hidden layers realizes the random feature mapping while only the weights between hidden and output layers are trained. As a result, layer-by-layer tuning is not required. Meanwhile, the norm of output weights is included in the cost function. Therefore, the ELM-based classifier can achieve an optimal and generalized solution for multiclass TSR. Furthermore, it can balance the recognition accuracy and computational cost. Three datasets, including the German TSR benchmark dataset, the Belgium traffic sign classification dataset and the revised mapping and assessing the state of traffic infrastructure (revised MASTIF) dataset, are used to evaluate this proposed method. Experimental results have shown that this proposed method obtains not only high recognition accuracy but also extremely high computational efficiency in both training and recognition processes in these three datasets.

  9. Comparison of Machine Learning methods for incipient motion in gravel bed rivers

    NASA Astrophysics Data System (ADS)

    Valyrakis, Manousos

    2013-04-01

    Soil erosion and sediment transport of natural gravel bed streams are important processes which affect both the morphology as well as the ecology of earth's surface. For gravel bed rivers at near incipient flow conditions, particle entrainment dynamics are highly intermittent. This contribution reviews the use of modern Machine Learning (ML) methods implemented for short term prediction of entrainment instances of individual grains exposed in fully developed near boundary turbulent flows. Results obtained by network architectures of variable complexity based on two different ML methods namely the Artificial Neural Network (ANN) and the Adaptive Neuro-Fuzzy Inference System (ANFIS) are compared in terms of different error and performance indices, computational efficiency and complexity as well as predictive accuracy and forecast ability. Different model architectures are trained and tested with experimental time series obtained from mobile particle flume experiments. The experimental setup consists of a Laser Doppler Velocimeter (LDV) and a laser optics system, which acquire data for the instantaneous flow and particle response respectively, synchronously. The first is used to record the flow velocity components directly upstream of the test particle, while the later tracks the particle's displacements. The lengthy experimental data sets (millions of data points) are split into the training and validation subsets used to perform the corresponding learning and testing of the models. It is demonstrated that the ANFIS hybrid model, which is based on neural learning and fuzzy inference principles, better predicts the critical flow conditions above which sediment transport is initiated. In addition, it is illustrated that empirical knowledge can be extracted, validating the theoretical assumption that particle ejections occur due to energetic turbulent flow events. Such a tool may find application in management and regulation of stream flows downstream of dams for stream

  10. On plant detection of intact tomato fruits using image analysis and machine learning methods.

    PubMed

    Yamamoto, Kyosuke; Guo, Wei; Yoshioka, Yosuke; Ninomiya, Seishi

    2014-07-09

    Fully automated yield estimation of intact fruits prior to harvesting provides various benefits to farmers. Until now, several studies have been conducted to estimate fruit yield using image-processing technologies. However, most of these techniques require thresholds for features such as color, shape and size. In addition, their performance strongly depends on the thresholds used, although optimal thresholds tend to vary with images. Furthermore, most of these techniques have attempted to detect only mature and immature fruits, although the number of young fruits is more important for the prediction of long-term fluctuations in yield. In this study, we aimed to develop a method to accurately detect individual intact tomato fruits including mature, immature and young fruits on a plant using a conventional RGB digital camera in conjunction with machine learning approaches. The developed method did not require an adjustment of threshold values for fruit detection from each image because image segmentation was conducted based on classification models generated in accordance with the color, shape, texture and size of the images. The results of fruit detection in the test images showed that the developed method achieved a recall of 0.80, while the precision was 0.88. The recall values of mature, immature and young fruits were 1.00, 0.80 and 0.78, respectively.

  11. Spectral methods in machine learning and new strategies for very large datasets.

    PubMed

    Belabbas, Mohamed-Ali; Wolfe, Patrick J

    2009-01-13

    Spectral methods are of fundamental importance in statistics and machine learning, because they underlie algorithms from classical principal components analysis to more recent approaches that exploit manifold structure. In most cases, the core technical problem can be reduced to computing a low-rank approximation to a positive-definite kernel. For the growing number of applications dealing with very large or high-dimensional datasets, however, the optimal approximation afforded by an exact spectral decomposition is too costly, because its complexity scales as the cube of either the number of training examples or their dimensionality. Motivated by such applications, we present here 2 new algorithms for the approximation of positive-semidefinite kernels, together with error bounds that improve on results in the literature. We approach this problem by seeking to determine, in an efficient manner, the most informative subset of our data relative to the kernel approximation task at hand. This leads to two new strategies based on the Nyström method that are directly applicable to massive datasets. The first of these-based on sampling-leads to a randomized algorithm whereupon the kernel induces a probability distribution on its set of partitions, whereas the latter approach-based on sorting-provides for the selection of a partition in a deterministic way. We detail their numerical implementation and provide simulation results for a variety of representative problems in statistical data analysis, each of which demonstrates the improved performance of our approach relative to existing methods.

  12. Comparison of Machine Learning Methods for the Purpose Of Human Fall Detection

    NASA Astrophysics Data System (ADS)

    Strémy, Maximilián; Peterková, Andrea

    2014-12-01

    According to several studies, the European population is rapidly aging far over last years. It is therefore important to ensure that aging population is able to live independently without the support of working-age population. In accordance with the studies, fall is the most dangerous and frequent accident in the everyday life of aging population. In our paper, we present a system to track the human fall by a visual detection, i.e. using no wearable equipment. For this purpose, we used a Kinect sensor, which provides the human body position in the Cartesian coordinates. It is possible to directly capture a human body because the Kinect sensor has a depth and also an infrared camera. The first step in our research was to detect postures and classify the fall accident. We experimented and compared the selected machine learning methods including Naive Bayes, decision trees and SVM method to compare the performance in recognizing the human postures (standing, sitting and lying). The highest classification accuracy of over 93.3% was achieved by the decision tree method.

  13. Machine Learning for the Knowledge Plane

    DTIC Science & Technology

    2006-06-01

    methods rely on careful engineering of the representation, the choice of algorithm, and so forth. The knowledge plane requires a more autonomous...learning capability that can operate in real time without continuous knowledge engineering . 2. Learning online. Most existing learning methods learn...detection and fault diagnosis. The central task of the knowledge plane is to detect anomalies and faults. Machine learning methods can be applied to learn

  14. Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours

    PubMed Central

    Slip, David J.; Hocking, David P.; Harcourt, Robert G.

    2016-01-01

    Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding—were all predicted with reasonable accuracy (52–81%) by the SVM while travelling was poorly categorised (31–41%). These results show that model selection is important when classifying behaviour and that by using animal

  15. A machine learning nowcasting method based on real-time reanalysis data

    NASA Astrophysics Data System (ADS)

    Han, Lei; Sun, Juanzhen; Zhang, Wei; Xiu, Yuanyuan; Feng, Hailei; Lin, Yinjing

    2017-04-01

    Despite marked progress over the past several decades, convective storm nowcasting remains a challenge because most nowcasting systems are based on linear extrapolation of radar reflectivity without much consideration for other meteorological fields. The variational Doppler radar analysis system (VDRAS) is an advanced convective-scale analysis system capable of providing analysis of 3-D wind, temperature, and humidity by assimilating Doppler radar observations. Although potentially useful, it is still an open question as to how to use these fields to improve nowcasting. In this study, we present results from our first attempt at developing a support vector machine (SVM) box-based nowcasting (SBOW) method under the machine learning framework using VDRAS analysis data. The key design points of SBOW are as follows: (1) The study domain is divided into many position-fixed small boxes, and the nowcasting problem is transformed into one question, i.e., will a radar echo > 35 dBZ appear in a box in 30 min? (2) Box-based temporal and spatial features, which include time trends and surrounding environmental information, are constructed. (3) And the box-based constructed features are used to first train the SVM classifier, and then the trained classifier is used to make predictions. Compared with complicated and expensive expert systems, the above design of SBOW allows the system to be small, compact, straightforward, and easy to maintain and expand at low cost. The experimental results show that although no complicated tracking algorithm is used, SBOW can predict the storm movement trend and storm growth with reasonable skill.

  16. Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours.

    PubMed

    Ladds, Monique A; Thompson, Adam P; Slip, David J; Hocking, David P; Harcourt, Robert G

    2016-01-01

    Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding-were all predicted with reasonable accuracy (52-81%) by the SVM while travelling was poorly categorised (31-41%). These results show that model selection is important when classifying behaviour and that by using animal

  17. Unsupervised nonlinear dimensionality reduction machine learning methods applied to multiparametric MRI in cerebral ischemia: preliminary results

    NASA Astrophysics Data System (ADS)

    Parekh, Vishwa S.; Jacobs, Jeremy R.; Jacobs, Michael A.

    2014-03-01

    The evaluation and treatment of acute cerebral ischemia requires a technique that can determine the total area of tissue at risk for infarction using diagnostic magnetic resonance imaging (MRI) sequences. Typical MRI data sets consist of T1- and T2-weighted imaging (T1WI, T2WI) along with advanced MRI parameters of diffusion-weighted imaging (DWI) and perfusion weighted imaging (PWI) methods. Each of these parameters has distinct radiological-pathological meaning. For example, DWI interrogates the movement of water in the tissue and PWI gives an estimate of the blood flow, both are critical measures during the evolution of stroke. In order to integrate these data and give an estimate of the tissue at risk or damaged; we have developed advanced machine learning methods based on unsupervised non-linear dimensionality reduction (NLDR) techniques. NLDR methods are a class of algorithms that uses mathematically defined manifolds for statistical sampling of multidimensional classes to generate a discrimination rule of guaranteed statistical accuracy and they can generate a two- or three-dimensional map, which represents the prominent structures of the data and provides an embedded image of meaningful low-dimensional structures hidden in their high-dimensional observations. In this manuscript, we develop NLDR methods on high dimensional MRI data sets of preclinical animals and clinical patients with stroke. On analyzing the performance of these methods, we observed that there was a high of similarity between multiparametric embedded images from NLDR methods and the ADC map and perfusion map. It was also observed that embedded scattergram of abnormal (infarcted or at risk) tissue can be visualized and provides a mechanism for automatic methods to delineate potential stroke volumes and early tissue at risk.

  18. A multi-label learning based kernel automatic recommendation method for support vector machine.

    PubMed

    Zhang, Xueying; Song, Qinbao

    2015-01-01

    Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance.

  19. A Multi-Label Learning Based Kernel Automatic Recommendation Method for Support Vector Machine

    PubMed Central

    Zhang, Xueying; Song, Qinbao

    2015-01-01

    Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance. PMID:25893896

  20. Big data analysis using modern statistical and machine learning methods in medicine.

    PubMed

    Yoo, Changwon; Ramirez, Luis; Liuzzi, Juan

    2014-06-01

    In this article we introduce modern statistical machine learning and bioinformatics approaches that have been used in learning statistical relationships from big data in medicine and behavioral science that typically include clinical, genomic (and proteomic) and environmental variables. Every year, data collected from biomedical and behavioral science is getting larger and more complicated. Thus, in medicine, we also need to be aware of this trend and understand the statistical tools that are available to analyze these datasets. Many statistical analyses that are aimed to analyze such big datasets have been introduced recently. However, given many different types of clinical, genomic, and environmental data, it is rather uncommon to see statistical methods that combine knowledge resulting from those different data types. To this extent, we will introduce big data in terms of clinical data, single nucleotide polymorphism and gene expression studies and their interactions with environment. In this article, we will introduce the concept of well-known regression analyses such as linear and logistic regressions that has been widely used in clinical data analyses and modern statistical models such as Bayesian networks that has been introduced to analyze more complicated data. Also we will discuss how to represent the interaction among clinical, genomic, and environmental data in using modern statistical models. We conclude this article with a promising modern statistical method called Bayesian networks that is suitable in analyzing big data sets that consists with different type of large data from clinical, genomic, and environmental data. Such statistical model form big data will provide us with more comprehensive understanding of human physiology and disease.

  1. Big Data Analysis Using Modern Statistical and Machine Learning Methods in Medicine

    PubMed Central

    Ramirez, Luis; Liuzzi, Juan

    2014-01-01

    In this article we introduce modern statistical machine learning and bioinformatics approaches that have been used in learning statistical relationships from big data in medicine and behavioral science that typically include clinical, genomic (and proteomic) and environmental variables. Every year, data collected from biomedical and behavioral science is getting larger and more complicated. Thus, in medicine, we also need to be aware of this trend and understand the statistical tools that are available to analyze these datasets. Many statistical analyses that are aimed to analyze such big datasets have been introduced recently. However, given many different types of clinical, genomic, and environmental data, it is rather uncommon to see statistical methods that combine knowledge resulting from those different data types. To this extent, we will introduce big data in terms of clinical data, single nucleotide polymorphism and gene expression studies and their interactions with environment. In this article, we will introduce the concept of well-known regression analyses such as linear and logistic regressions that has been widely used in clinical data analyses and modern statistical models such as Bayesian networks that has been introduced to analyze more complicated data. Also we will discuss how to represent the interaction among clinical, genomic, and environmental data in using modern statistical models. We conclude this article with a promising modern statistical method called Bayesian networks that is suitable in analyzing big data sets that consists with different type of large data from clinical, genomic, and environmental data. Such statistical model form big data will provide us with more comprehensive understanding of human physiology and disease. PMID:24987556

  2. Prediction of core cancer genes using a hybrid of feature selection and machine learning methods.

    PubMed

    Liu, Y X; Zhang, N N; He, Y; Lun, L J

    2015-08-03

    Machine learning techniques are of great importance in the analysis of microarray expression data, and provide a systematic and promising way to predict core cancer genes. In this study, a hybrid strategy was introduced based on machine learning techniques to select a small set of informative genes, which will lead to improving classification accuracy. First feature filtering algorithms were applied to select a set of top-ranked genes, and then hierarchical clustering and collapsing dense clusters were used to select core cancer genes. Through empirical study, our approach is capable of selecting relatively few core cancer genes while making high-accuracy predictions. The biological significance of these genes was evaluated using systems biology analysis. Extensive functional pathway and network analyses have confirmed findings in previous studies and can bring new insights into common cancer mechanisms.

  3. Quantum-Enhanced Machine Learning.

    PubMed

    Dunjko, Vedran; Taylor, Jacob M; Briegel, Hans J

    2016-09-23

    The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised, and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.

  4. Quantum-Enhanced Machine Learning

    NASA Astrophysics Data System (ADS)

    Dunjko, Vedran; Taylor, Jacob M.; Briegel, Hans J.

    2016-09-01

    The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised, and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.

  5. Estimating Corn Yield in the United States with Modis Evi and Machine Learning Methods

    NASA Astrophysics Data System (ADS)

    Kuwata, K.; Shibasaki, R.

    2016-06-01

    Satellite remote sensing is commonly used to monitor crop yield in wide areas. Because many parameters are necessary for crop yield estimation, modelling the relationships between parameters and crop yield is generally complicated. Several methodologies using machine learning have been proposed to solve this issue, but the accuracy of county-level estimation remains to be improved. In addition, estimating county-level crop yield across an entire country has not yet been achieved. In this study, we applied a deep neural network (DNN) to estimate corn yield. We evaluated the estimation accuracy of the DNN model by comparing it with other models trained by different machine learning algorithms. We also prepared two time-series datasets differing in duration and confirmed the feature extraction performance of models by inputting each dataset. As a result, the DNN estimated county-level corn yield for the entire area of the United States with a determination coefficient (R2) of 0.780 and a root mean square error (RMSE) of 18.2 bushels/acre. In addition, our results showed that estimation models that were trained by a neural network extracted features from the input data better than an existing machine learning algorithm.

  6. Classification of follicular lymphoma images: a holistic approach with symbol-based machine learning methods.

    PubMed

    Zorman, Milan; Sánchez de la Rosa, José Luis; Dinevski, Dejan

    2011-12-01

    It is not very often to see a symbol-based machine learning approach to be used for the purpose of image classification and recognition. In this paper we will present such an approach, which we first used on the follicular lymphoma images. Lymphoma is a broad term encompassing a variety of cancers of the lymphatic system. Lymphoma is differentiated by the type of cell that multiplies and how the cancer presents itself. It is very important to get an exact diagnosis regarding lymphoma and to determine the treatments that will be most effective for the patient's condition. Our work was focused on the identification of lymphomas by finding follicles in microscopy images provided by the Laboratory of Pathology in the University Hospital of Tenerife, Spain. We divided our work in two stages: in the first stage we did image pre-processing and feature extraction, and in the second stage we used different symbolic machine learning approaches for pixel classification. Symbolic machine learning approaches are often neglected when looking for image analysis tools. They are not only known for a very appropriate knowledge representation, but also claimed to lack computational power. The results we got are very promising and show that symbolic approaches can be successful in image analysis applications.

  7. Use of machine learning methods to reduce predictive error of groundwater models.

    PubMed

    Xu, Tianfang; Valocchi, Albert J; Choi, Jaesik; Amir, Eyal

    2014-01-01

    Quantitative analyses of groundwater flow and transport typically rely on a physically-based model, which is inherently subject to error. Errors in model structure, parameter and data lead to both random and systematic error even in the output of a calibrated model. We develop complementary data-driven models (DDMs) to reduce the predictive error of physically-based groundwater models. Two machine learning techniques, the instance-based weighting and support vector regression, are used to build the DDMs. This approach is illustrated using two real-world case studies of the Republican River Compact Administration model and the Spokane Valley-Rathdrum Prairie model. The two groundwater models have different hydrogeologic settings, parameterization, and calibration methods. In the first case study, cluster analysis is introduced for data preprocessing to make the DDMs more robust and computationally efficient. The DDMs reduce the root-mean-square error (RMSE) of the temporal, spatial, and spatiotemporal prediction of piezometric head of the groundwater model by 82%, 60%, and 48%, respectively. In the second case study, the DDMs reduce the RMSE of the temporal prediction of piezometric head of the groundwater model by 77%. It is further demonstrated that the effectiveness of the DDMs depends on the existence and extent of the structure in the error of the physically-based model. © 2013, National GroundWater Association.

  8. Comparison of machine-learning methods for above-ground biomass estimation based on Landsat imagery

    NASA Astrophysics Data System (ADS)

    Wu, Chaofan; Shen, Huanhuan; Shen, Aihua; Deng, Jinsong; Gan, Muye; Zhu, Jinxia; Xu, Hongwei; Wang, Ke

    2016-07-01

    Biomass is one significant biophysical parameter of a forest ecosystem, and accurate biomass estimation on the regional scale provides important information for carbon-cycle investigation and sustainable forest management. In this study, Landsat satellite imagery data combined with field-based measurements were integrated through comparisons of five regression approaches [stepwise linear regression, K-nearest neighbor, support vector regression, random forest (RF), and stochastic gradient boosting] with two different candidate variable strategies to implement the optimal spatial above-ground biomass (AGB) estimation. The results suggested that RF algorithm exhibited the best performance by 10-fold cross-validation with respect to R2 (0.63) and root-mean-square error (26.44 ton/ha). Consequently, the map of estimated AGB was generated with a mean value of 89.34 ton/ha in northwestern Zhejiang Province, China, with a similar pattern to the distribution mode of local forest species. This research indicates that machine-learning approaches associated with Landsat imagery provide an economical way for biomass estimation. Moreover, ensemble methods using all candidate variables, especially for Landsat images, provide an alternative for regional biomass simulation.

  9. Integrating Symbolic and Statistical Methods for Testing Intelligent Systems Applications to Machine Learning and Computer Vision

    SciTech Connect

    Jha, Sumit Kumar; Pullum, Laura L; Ramanathan, Arvind

    2016-01-01

    Embedded intelligent systems ranging from tiny im- plantable biomedical devices to large swarms of autonomous un- manned aerial systems are becoming pervasive in our daily lives. While we depend on the flawless functioning of such intelligent systems, and often take their behavioral correctness and safety for granted, it is notoriously difficult to generate test cases that expose subtle errors in the implementations of machine learning algorithms. Hence, the validation of intelligent systems is usually achieved by studying their behavior on representative data sets, using methods such as cross-validation and bootstrapping.In this paper, we present a new testing methodology for studying the correctness of intelligent systems. Our approach uses symbolic decision procedures coupled with statistical hypothesis testing to. We also use our algorithm to analyze the robustness of a human detection algorithm built using the OpenCV open-source computer vision library. We show that the human detection implementation can fail to detect humans in perturbed video frames even when the perturbations are so small that the corresponding frames look identical to the naked eye.

  10. An evaluation of machine-learning methods for predicting pneumonia mortality.

    PubMed

    Cooper, G F; Aliferis, C F; Ambrosino, R; Aronis, J; Buchanan, B G; Caruana, R; Fine, M J; Glymour, C; Gordon, G; Hanusa, B H; Janosky, J E; Meek, C; Mitchell, T; Richardson, T; Spirtes, P

    1997-02-01

    This paper describes the application of eight statistical and machine-learning methods to derive computer models for predicting mortality of hospital patients with pneumonia from their findings at initial presentation. The eight models were each constructed based on 9847 patient cases and they were each evaluated on 4352 additional cases. The primary evaluation metric was the error in predicted survival as a function of the fraction of patients predicted to survive. This metric is useful in assessing a model's potential to assist a clinician in deciding whether to treat a given patient in the hospital or at home. We examined the error rates of the models when predicting that a given fraction of patients will survive. We examined survival fractions between 0.1 and 0.6. Over this range, each model's predictive error rate was within 1% of the error rate of every other model. When predicting that approximately 30% of the patients will survive, all the models have an error rate of less than 1.5%. The models are distinguished more by the number of variables and parameters that they contain than by their error rates; these differences suggest which models may be the most amenable to future implementation as paper-based guidelines.

  11. Quantum adiabatic machine learning

    NASA Astrophysics Data System (ADS)

    Pudenz, Kristen L.; Lidar, Daniel A.

    2013-05-01

    We develop an approach to machine learning and anomaly detection via quantum adiabatic evolution. This approach consists of two quantum phases, with some amount of classical preprocessing to set up the quantum problems. In the training phase we identify an optimal set of weak classifiers, to form a single strong classifier. In the testing phase we adiabatically evolve one or more strong classifiers on a superposition of inputs in order to find certain anomalous elements in the classification space. Both the training and testing phases are executed via quantum adiabatic evolution. All quantum processing is strictly limited to two-qubit interactions so as to ensure physical feasibility. We apply and illustrate this approach in detail to the problem of software verification and validation, with a specific example of the learning phase applied to a problem of interest in flight control systems. Beyond this example, the algorithm can be used to attack a broad class of anomaly detection problems.

  12. Stacked Extreme Learning Machines.

    PubMed

    Zhou, Hongming; Huang, Guang-Bin; Lin, Zhiping; Wang, Han; Soh, Yeng Chai

    2015-09-01

    Extreme learning machine (ELM) has recently attracted many researchers' interest due to its very fast learning speed, good generalization ability, and ease of implementation. It provides a unified solution that can be used directly to solve regression, binary, and multiclass classification problems. In this paper, we propose a stacked ELMs (S-ELMs) that is specially designed for solving large and complex data problems. The S-ELMs divides a single large ELM network into multiple stacked small ELMs which are serially connected. The S-ELMs can approximate a very large ELM network with small memory requirement. To further improve the testing accuracy on big data problems, the ELM autoencoder can be implemented during each iteration of the S-ELMs algorithm. The simulation results show that the S-ELMs even with random hidden nodes can achieve similar testing accuracy to support vector machine (SVM) while having low memory requirements. With the help of ELM autoencoder, the S-ELMs can achieve much better testing accuracy than SVM and slightly better accuracy than deep belief network (DBN) with much faster training speed.

  13. Machine-learning in astronomy

    NASA Astrophysics Data System (ADS)

    Hobson, Michael; Graff, Philip; Feroz, Farhan; Lasenby, Anthony

    2014-05-01

    Machine-learning methods may be used to perform many tasks required in the analysis of astronomical data, including: data description and interpretation, pattern recognition, prediction, classification, compression, inference and many more. An intuitive and well-established approach to machine learning is the use of artificial neural networks (NNs), which consist of a group of interconnected nodes, each of which processes information that it receives and then passes this product on to other nodes via weighted connections. In particular, I discuss the first public release of the generic neural network training algorithm, called SkyNet, and demonstrate its application to astronomical problems focusing on its use in the BAMBI package for accelerated Bayesian inference in cosmology, and the identification of gamma-ray bursters. The SkyNet and BAMBI packages, which are fully parallelised using MPI, are available at http://www.mrao.cam.ac.uk/software/.

  14. Classification of lung cancer using ensemble-based feature selection and machine learning methods.

    PubMed

    Cai, Zhihua; Xu, Dong; Zhang, Qing; Zhang, Jiexia; Ngai, Sai-Ming; Shao, Jianlin

    2015-03-01

    Lung cancer is one of the leading causes of death worldwide. There are three major types of lung cancers, non-small cell lung cancer (NSCLC), small cell lung cancer (SCLC) and carcinoid. NSCLC is further classified into lung adenocarcinoma (LADC), squamous cell lung cancer (SQCLC) as well as large cell lung cancer. Many previous studies demonstrated that DNA methylation has emerged as potential lung cancer-specific biomarkers. However, whether there exists a set of DNA methylation markers simultaneously distinguishing such three types of lung cancers remains elusive. In the present study, ROC (Receiving Operating Curve), RFs (Random Forests) and mRMR (Maximum Relevancy and Minimum Redundancy) were proposed to capture the unbiased, informative as well as compact molecular signatures followed by machine learning methods to classify LADC, SQCLC and SCLC. As a result, a panel of 16 DNA methylation markers exhibits an ideal classification power with an accuracy of 86.54%, 84.6% and a recall 84.37%, 85.5% in the leave-one-out cross-validation (LOOCV) and independent data set test experiments, respectively. Besides, comparison results indicate that ensemble-based feature selection methods outperform individual ones when combined with the incremental feature selection (IFS) strategy in terms of the informative and compact property of features. Taken together, results obtained suggest the effectiveness of the ensemble-based feature selection approach and the possible existence of a common panel of DNA methylation markers among such three types of lung cancer tissue, which would facilitate clinical diagnosis and treatment.

  15. Recognition of Time Stamps on Full-Disk Hα Images Using Machine Learning Methods

    NASA Astrophysics Data System (ADS)

    Xu, Y.; Huang, N.; Jing, J.; Liu, C.; Wang, H.; Fu, G.

    2016-12-01

    Observation and understanding of the physics of the 11-year solar activity cycle and 22-year magnetic cycle are among the most important research topics in solar physics. The solar cycle is responsible for magnetic field and particle fluctuation in the near-earth environment that have been found increasingly important in affecting the living of human beings in the modern era. A systematic study of large-scale solar activities, as made possible by our rich data archive, will further help us to understand the global-scale magnetic fields that are closely related to solar cycles. The long-time-span data archive includes both full-disk and high-resolution Hα images. Prior to the widely use of CCD cameras in 1990s, 35-mm films were the major media to store images. The research group at NJIT recently finished the digitization of film data obtained by the National Solar Observatory (NSO) and Big Bear Solar Observatory (BBSO) covering the period of 1953 to 2000. The total volume of data exceeds 60 TB. To make this huge database scientific valuable, some processing and calibration are required. One of the most important steps is to read the time stamps on all of the 14 million images, which is almost impossible to be done manually. We implemented three different methods to recognize the time stamps automatically, including Optical Character Recognition (OCR), Classification Tree and TensorFlow. The latter two are known as machine learning algorithms which are very popular now a day in pattern recognition area. We will present some sample images and the results of clock recognition from all three methods.

  16. A Machine-learning Method to Infer Fundamental Stellar Parameters from Photometric Light Curves

    NASA Astrophysics Data System (ADS)

    Miller, A. A.; Bloom, J. S.; Richards, J. W.; Lee, Y. S.; Starr, D. L.; Butler, N. R.; Tokarz, S.; Smith, N.; Eisner, J. A.

    2015-01-01

    A fundamental challenge for wide-field imaging surveys is obtaining follow-up spectroscopic observations: there are >109 photometrically cataloged sources, yet modern spectroscopic surveys are limited to ~few× 106 targets. As we approach the Large Synoptic Survey Telescope era, new algorithmic solutions are required to cope with the data deluge. Here we report the development of a machine-learning framework capable of inferring fundamental stellar parameters (T eff, log g, and [Fe/H]) using photometric-brightness variations and color alone. A training set is constructed from a systematic spectroscopic survey of variables with Hectospec/Multi-Mirror Telescope. In sum, the training set includes ~9000 spectra, for which stellar parameters are measured using the SEGUE Stellar Parameters Pipeline (SSPP). We employed the random forest algorithm to perform a non-parametric regression that predicts T eff, log g, and [Fe/H] from photometric time-domain observations. Our final optimized model produces a cross-validated rms error (RMSE) of 165 K, 0.39 dex, and 0.33 dex for T eff, log g, and [Fe/H], respectively. Examining the subset of sources for which the SSPP measurements are most reliable, the RMSE reduces to 125 K, 0.37 dex, and 0.27 dex, respectively, comparable to what is achievable via low-resolution spectroscopy. For variable stars this represents a ≈12%-20% improvement in RMSE relative to models trained with single-epoch photometric colors. As an application of our method, we estimate stellar parameters for ~54,000 known variables. We argue that this method may convert photometric time-domain surveys into pseudo-spectrographic engines, enabling the construction of extremely detailed maps of the Milky Way, its structure, and history.

  17. A MACHINE-LEARNING METHOD TO INFER FUNDAMENTAL STELLAR PARAMETERS FROM PHOTOMETRIC LIGHT CURVES

    SciTech Connect

    Miller, A. A.; Bloom, J. S.; Richards, J. W.; Starr, D. L.; Lee, Y. S.; Butler, N. R.; Tokarz, S.; Smith, N.; Eisner, J. A.

    2015-01-10

    A fundamental challenge for wide-field imaging surveys is obtaining follow-up spectroscopic observations: there are >10{sup 9} photometrically cataloged sources, yet modern spectroscopic surveys are limited to ∼few× 10{sup 6} targets. As we approach the Large Synoptic Survey Telescope era, new algorithmic solutions are required to cope with the data deluge. Here we report the development of a machine-learning framework capable of inferring fundamental stellar parameters (T {sub eff}, log g, and [Fe/H]) using photometric-brightness variations and color alone. A training set is constructed from a systematic spectroscopic survey of variables with Hectospec/Multi-Mirror Telescope. In sum, the training set includes ∼9000 spectra, for which stellar parameters are measured using the SEGUE Stellar Parameters Pipeline (SSPP). We employed the random forest algorithm to perform a non-parametric regression that predicts T {sub eff}, log g, and [Fe/H] from photometric time-domain observations. Our final optimized model produces a cross-validated rms error (RMSE) of 165 K, 0.39 dex, and 0.33 dex for T {sub eff}, log g, and [Fe/H], respectively. Examining the subset of sources for which the SSPP measurements are most reliable, the RMSE reduces to 125 K, 0.37 dex, and 0.27 dex, respectively, comparable to what is achievable via low-resolution spectroscopy. For variable stars this represents a ≈12%-20% improvement in RMSE relative to models trained with single-epoch photometric colors. As an application of our method, we estimate stellar parameters for ∼54,000 known variables. We argue that this method may convert photometric time-domain surveys into pseudo-spectrographic engines, enabling the construction of extremely detailed maps of the Milky Way, its structure, and history.

  18. Prediction of Aerosol Optical Depth in West Asia: Machine Learning Methods versus Numerical Models

    NASA Astrophysics Data System (ADS)

    Omid Nabavi, Seyed; Haimberger, Leopold; Abbasi, Reyhaneh; Samimi, Cyrus

    2017-04-01

    Dust-prone areas of West Asia are releasing increasingly large amounts of dust particles during warm months. Because of the lack of ground-based observations in the region, this phenomenon is mainly monitored through remotely sensed aerosol products. The recent development of mesoscale Numerical Models (NMs) has offered an unprecedented opportunity to predict dust emission, and, subsequently Aerosol Optical Depth (AOD), at finer spatial and temporal resolutions. Nevertheless, the significant uncertainties in input data and simulations of dust activation and transport limit the performance of numerical models in dust prediction. The presented study aims to evaluate if machine-learning algorithms (MLAs), which require much less computational expense, can yield the same or even better performance than NMs. Deep blue (DB) AOD, which is observed by satellites but also predicted by MLAs and NMs, is used for validation. We concentrate our evaluations on the over dry Iraq plains, known as the main origin of recently intensified dust storms in West Asia. Here we examine the performance of four MLAs including Linear regression Model (LM), Support Vector Machine (SVM), Artificial Neural Network (ANN), Multivariate Adaptive Regression Splines (MARS). The Weather Research and Forecasting model coupled to Chemistry (WRF-Chem) and the Dust REgional Atmosphere Model (DREAM) are included as NMs. The MACC aerosol re-analysis of European Centre for Medium-range Weather Forecast (ECMWF) is also included, although it has assimilated satellite-based AOD data. Using the Recursive Feature Elimination (RFE) method, nine environmental features including soil moisture and temperature, NDVI, dust source function, albedo, dust uplift potential, vertical velocity, precipitation and 9-month SPEI drought index are selected for dust (AOD) modeling by MLAs. During the feature selection process, we noticed that NDVI and SPEI are of the highest importance in MLAs predictions. The data set was divided

  19. Approximate learning algorithm in Boltzmann machines.

    PubMed

    Yasuda, Muneki; Tanaka, Kazuyuki

    2009-11-01

    Boltzmann machines can be regarded as Markov random fields. For binary cases, they are equivalent to the Ising spin model in statistical mechanics. Learning systems in Boltzmann machines are one of the NP-hard problems. Thus, in general we have to use approximate methods to construct practical learning algorithms in this context. In this letter, we propose new and practical learning algorithms for Boltzmann machines by using the belief propagation algorithm and the linear response approximation, which are often referred as advanced mean field methods. Finally, we show the validity of our algorithm using numerical experiments.

  20. Use of a Machine-learning Method for Predicting Highly Cited Articles Within General Radiology Journals.

    PubMed

    Rosenkrantz, Andrew B; Doshi, Ankur M; Ginocchio, Luke A; Aphinyanaphongs, Yindalon

    2016-12-01

    This study aimed to assess the performance of a text classification machine-learning model in predicting highly cited articles within the recent radiological literature and to identify the model's most influential article features. We downloaded from PubMed the title, abstract, and medical subject heading terms for 10,065 articles published in 25 general radiology journals in 2012 and 2013. Three machine-learning models were applied to predict the top 10% of included articles in terms of the number of citations to the article in 2014 (reflecting the 2-year time window in conventional impact factor calculations). The model having the highest area under the curve was selected to derive a list of article features (words) predicting high citation volume, which was iteratively reduced to identify the smallest possible core feature list maintaining predictive power. Overall themes were qualitatively assigned to the core features. The regularized logistic regression (Bayesian binary regression) model had highest performance, achieving an area under the curve of 0.814 in predicting articles in the top 10% of citation volume. We reduced the initial 14,083 features to 210 features that maintain predictivity. These features corresponded with topics relating to various imaging techniques (eg, diffusion-weighted magnetic resonance imaging, hyperpolarized magnetic resonance imaging, dual-energy computed tomography, computed tomography reconstruction algorithms, tomosynthesis, elastography, and computer-aided diagnosis), particular pathologies (prostate cancer; thyroid nodules; hepatic adenoma, hepatocellular carcinoma, non-alcoholic fatty liver disease), and other topics (radiation dose, electroporation, education, general oncology, gadolinium, statistics). Machine learning can be successfully applied to create specific feature-based models for predicting articles likely to achieve high influence within the radiological literature. Copyright © 2016 The Association of University

  1. Extensions and applications of ensemble-of-trees methods in machine learning

    NASA Astrophysics Data System (ADS)

    Bleich, Justin

    Ensemble-of-trees algorithms have emerged to the forefront of machine learning due to their ability to generate high forecasting accuracy for a wide array of regression and classification problems. Classic ensemble methodologies such as random forests (RF) and stochastic gradient boosting (SGB) rely on algorithmic procedures to generate fits to data. In contrast, more recent ensemble techniques such as Bayesian Additive Regression Trees (BART) and Dynamic Trees (DT) focus on an underlying Bayesian probability model to generate the fits. These new probability model-based approaches show much promise versus their algorithmic counterparts, but also offer substantial room for improvement. The first part of this thesis focuses on methodological advances for ensemble-of-trees techniques with an emphasis on the more recent Bayesian approaches. In particular, we focus on extensions of BART in four distinct ways. First, we develop a more robust implementation of BART for both research and application. We then develop a principled approach to variable selection for BART as well as the ability to naturally incorporate prior information on important covariates into the algorithm. Next, we propose a method for handling missing data that relies on the recursive structure of decision trees and does not require imputation. Last, we relax the assumption of homoskedasticity in the BART model to allow for parametric modeling of heteroskedasticity. The second part of this thesis returns to the classic algorithmic approaches in the context of classification problems with asymmetric costs of forecasting errors. First we consider the performance of RF and SGB more broadly and demonstrate its superiority to logistic regression for applications in criminology with asymmetric costs. Next, we use RF to forecast unplanned hospital readmissions upon patient discharge with asymmetric costs taken into account. Finally, we explore the construction of stable decision trees for forecasts of

  2. Prediction of Interactions between Viral and Host Proteins Using Supervised Machine Learning Methods

    PubMed Central

    Barman, Ranjan Kumar; Saha, Sudipto; Das, Santasabuj

    2014-01-01

    Background Viral-host protein-protein interaction plays a vital role in pathogenesis, since it defines viral infection of the host and regulation of the host proteins. Identification of key viral-host protein-protein interactions (PPIs) has great implication for therapeutics. Methods In this study, a systematic attempt has been made to predict viral-host PPIs by integrating different features, including domain-domain association, network topology and sequence information using viral-host PPIs from VirusMINT. The three well-known supervised machine learning methods, such as SVM, Naïve Bayes and Random Forest, which are commonly used in the prediction of PPIs, were employed to evaluate the performance measure based on five-fold cross validation techniques. Results Out of 44 descriptors, best features were found to be domain-domain association and methionine, serine and valine amino acid composition of viral proteins. In this study, SVM-based method achieved better sensitivity of 67% over Naïve Bayes (37.49%) and Random Forest (55.66%). However the specificity of Naïve Bayes was the highest (99.52%) as compared with SVM (74%) and Random Forest (89.08%). Overall, the SVM and Random Forest achieved accuracy of 71% and 72.41%, respectively. The proposed SVM-based method was evaluated on blind dataset and attained a sensitivity of 64%, specificity of 83%, and accuracy of 74%. In addition, unknown potential targets of hepatitis B virus-human and hepatitis E virus-human PPIs have been predicted through proposed SVM model and validated by gene ontology enrichment analysis. Our proposed model shows that, hepatitis B virus “C protein” binds to membrane docking protein, while “X protein” and “P protein” interacts with cell-killing and metabolic process proteins, respectively. Conclusion The proposed method can predict large scale interspecies viral-human PPIs. The nature and function of unknown viral proteins (HBV and HEV), interacting partners of host protein

  3. Computer-Aided Diagnosis for Breast Ultrasound Using Computerized BI-RADS Features and Machine Learning Methods.

    PubMed

    Shan, Juan; Alam, S Kaisar; Garra, Brian; Zhang, Yingtao; Ahmed, Tahira

    2016-04-01

    This work identifies effective computable features from the Breast Imaging Reporting and Data System (BI-RADS), to develop a computer-aided diagnosis (CAD) system for breast ultrasound. Computerized features corresponding to ultrasound BI-RADs categories were designed and tested using a database of 283 pathology-proven benign and malignant lesions. Features were selected based on classification performance using a "bottom-up" approach for different machine learning methods, including decision tree, artificial neural network, random forest and support vector machine. Using 10-fold cross-validation on the database of 283 cases, the highest area under the receiver operating characteristic (ROC) curve (AUC) was 0.84 from a support vector machine with 77.7% overall accuracy; the highest overall accuracy, 78.5%, was from a random forest with the AUC 0.83. Lesion margin and orientation were optimum features common to all of the different machine learning methods. These features can be used in CAD systems to help distinguish benign from worrisome lesions.

  4. a Semi-Automatic Rule Set Building Method for Urban Land Cover Classification Based on Machine Learning and Human Knowledge

    NASA Astrophysics Data System (ADS)

    Gu, H. Y.; Li, H. T.; Liu, Z. Y.; Shao, C. Y.

    2017-09-01

    Classification rule set is important for Land Cover classification, which refers to features and decision rules. The selection of features and decision are based on an iterative trial-and-error approach that is often utilized in GEOBIA, however, it is time-consuming and has a poor versatility. This study has put forward a rule set building method for Land cover classification based on human knowledge and machine learning. The use of machine learning is to build rule sets effectively which will overcome the iterative trial-and-error approach. The use of human knowledge is to solve the shortcomings of existing machine learning method on insufficient usage of prior knowledge, and improve the versatility of rule sets. A two-step workflow has been introduced, firstly, an initial rule is built based on Random Forest and CART decision tree. Secondly, the initial rule is analyzed and validated based on human knowledge, where we use statistical confidence interval to determine its threshold. The test site is located in Potsdam City. We utilised the TOP, DSM and ground truth data. The results show that the method could determine rule set for Land Cover classification semi-automatically, and there are static features for different land cover classes.

  5. Multipolar electrostatics based on the Kriging machine learning method: an application to serine.

    PubMed

    Yuan, Yongna; Mills, Matthew J L; Popelier, Paul L A

    2014-04-01

    A multipolar, polarizable electrostatic method for future use in a novel force field is described. Quantum Chemical Topology (QCT) is used to partition the electron density of a chemical system into atoms, then the machine learning method Kriging is used to build models that relate the multipole moments of the atoms to the positions of their surrounding nuclei. The pilot system serine is used to study both the influence of the level of theory and the set of data generator methods used. The latter consists of: (i) sampling of protein structures deposited in the Protein Data Bank (PDB), or (ii) normal mode distortion along either (a) Cartesian coordinates, or (b) redundant internal coordinates. Wavefunctions for the sampled geometries were obtained at the HF/6-31G(d,p), B3LYP/apc-1, and MP2/cc-pVDZ levels of theory, prior to calculation of the atomic multipole moments by volume integration. The average absolute error (over an independent test set of conformations) in the total atom-atom electrostatic interaction energy of serine, using Kriging models built with the three data generator methods is 11.3 kJ mol⁻¹ (PDB), 8.2 kJ mol⁻¹ (Cartesian distortion), and 10.1 kJ mol⁻¹ (redundant internal distortion) at the HF/6-31G(d,p) level. At the B3LYP/apc-1 level, the respective errors are 7.7 kJ mol⁻¹, 6.7 kJ mol⁻¹, and 4.9 kJ mol⁻¹, while at the MP2/cc-pVDZ level they are 6.5 kJ mol⁻¹, 5.3 kJ mol⁻¹, and 4.0 kJ mol⁻¹. The ranges of geometries generated by the redundant internal coordinate distortion and by extraction from the PDB are much wider than the range generated by Cartesian distortion. The atomic multipole moment and electrostatic interaction energy predictions for the B3LYP/apc-1 and MP2/cc-pVDZ levels are similar, and both are better than the corresponding predictions at the HF/6-31G(d,p) level.

  6. Interpreting Medical Information Using Machine Learning and Individual Conditional Expectation.

    PubMed

    Nohara, Yasunobu; Wakata, Yoshifumi; Nakashima, Naoki

    2015-01-01

    Recently, machine-learning techniques have spread many fields. However, machine-learning is still not popular in medical research field due to difficulty of interpreting. In this paper, we introduce a method of interpreting medical information using machine learning technique. The method gave new explanation of partial dependence plot and individual conditional expectation plot from medical research field.

  7. Machine learning-based method for personalized and cost-effective detection of Alzheimer's disease.

    PubMed

    Escudero, Javier; Ifeachor, Emmanuel; Zajicek, John P; Green, Colin; Shearer, James; Pearson, Stephen

    2013-01-01

    Diagnosis of Alzheimer's disease (AD) is often difficult, especially early in the disease process at the stage of mild cognitive impairment (MCI). Yet, it is at this stage that treatment is most likely to be effective, so there would be great advantages in improving the diagnosis process. We describe and test a machine learning approach for personalized and cost-effective diagnosis of AD. It uses locally weighted learning to tailor a classifier model to each patient and computes the sequence of biomarkers most informative or cost-effective to diagnose patients. Using ADNI data, we classified AD versus controls and MCI patients who progressed to AD within a year, against those who did not. The approach performed similarly to considering all data at once, while significantly reducing the number (and cost) of the biomarkers needed to achieve a confident diagnosis for each patient. Thus, it may contribute to a personalized and effective detection of AD, and may prove useful in clinical settings.

  8. An EEG-based machine learning method to screen alcohol use disorder.

    PubMed

    Mumtaz, Wajid; Vuong, Pham Lam; Xia, Likun; Malik, Aamir Saeed; Rashid, Rusdi Bin Abd

    2017-04-01

    Screening alcohol use disorder (AUD) patients has been challenging due to the subjectivity involved in the process. Hence, robust and objective methods are needed to automate the screening of AUD patients. In this paper, a machine learning method is proposed that utilized resting-state electroencephalography (EEG)-derived features as input data to classify the AUD patients and healthy controls and to perform automatic screening of AUD patients. In this context, the EEG data were recorded during 5 min of eyes closed and 5 min of eyes open conditions. For this purpose, 30 AUD patients and 15 aged-matched healthy controls were recruited. After preprocessing the EEG data, EEG features such as inter-hemispheric coherences and spectral power for EEG delta, theta, alpha, beta and gamma bands were computed involving 19 scalp locations. The selection of most discriminant features was performed with a rank-based feature selection method assigning a weight value to each feature according to a criterion, i.e., receiver operating characteristics curve. For example, a feature with large weight was considered more relevant to the target labels than a feature with less weight. Therefore, a reduced set of most discriminant features was identified and further be utilized during classification of AUD patients and healthy controls. As results, the inter-hemispheric coherences between the brain regions were found significantly different between the study groups and provided high classification efficiency (Accuracy = 80.8, sensitivity = 82.5, and specificity = 80, F-Measure = 0.78). In addition, the power computed in different EEG bands were found significant and provided an overall classification efficiency as (Accuracy = 86.6, sensitivity = 95, specificity = 82.5, and F-Measure = 0.88). Further, the integration of these EEG feature resulted into even higher results (Accuracy = 89.3 %, sensitivity = 88.5 %, specificity = 91 %, and F-Measure = 0.90). Based

  9. In silico prediction of anti-malarial hit molecules based on machine learning methods.

    PubMed

    Kumari, Madhulata; Chandra, Subhash

    2015-01-01

    Machine learning techniques have been widely used in drug discovery and development in the areas of cheminformatics. Aspartyl aminopeptidase (M18AAP) of Plasmodium falciparum is crucial for survival of malaria parasite. We have created predictive models using weka and evaluated their performance based on various statistical parameters. Random Forest based model was found to be the most specificity (97.94%), with best accuracy (97.3%), MCC (0.306) as well as ROC (86.1%). The accuracy and MCC of these models indicated that they could be used to classify huge dataset of unknown compounds to predict their antimalarial compounds to develop effective drugs. Further, we deployed best predictive model on NCI diversity set IV. As result we found 59 bioactive anti-malarial molecules inhibiting M18AAP. Further, we obtained 18 non-toxic hit molecules out of 59 bioactive compounds. We suggest that such machine learning approaches could be applied to reduce the cost and length of time of drug discovery.

  10. High-accuracy automatic classification of Parkinsonian tremor severity using machine learning method.

    PubMed

    Jeon, Hyoseon; Lee, Woongwoo; Park, Hyeyoung; Lee, Hong Ji; Kim, Sang Kyong; Kim, Han Byul; Jeon, Beomseok; Park, Kwang Suk

    2017-09-21

    Although clinical aspirations for new technology to accurately measure and diagnose Parkinsonian tremors exist, automatic scoring of tremor severity using machine learning approaches has not yet been employed. Objective: This study aims to maximize the scientific validity of automatic tremor-severity classification using machine learning algorithms to score Parkinsonian tremor severity in the same manner as the Unified Parkinson's Disease Rating Scale (UPDRS) used to rate scores in real clinical practice. Approach: Eighty-five PD patients perform four tasks for severity assessment of their resting, resting with mental stress, postural, and intention tremors. The tremor signals are measured using a wristwatch-type wearable device with an accelerometer and gyroscope. Displacement and angle signals are obtained by integrating the acceleration and angular-velocity signals. Nineteen features are extracted from each of the four tremor signals. The optimal feature configuration is decided using the wrapper feature selection algorithm or principal component analysis, and decision tree, support vector machine, discriminant analysis, and k-nearest neighbour algorithms are considered to develop an automatic scoring system for UPDRS prediction. The results are compared to UPDRS ratings assigned by two neurologists. Main results: The highest accuracies are 92.3%, 86.2%, 92.1%, and 89.2% for resting, resting with mental stress, postural, and intention tremors, respectively. The weighted Cohen's kappa values are 0.745, 0.635 and 0.633 for resting, resting with mental stress, and postural tremors (almost perfect agreement), and 0.570 for intention tremors (moderate). Significance: These results indicate the feasibility of the proposed system as a clinical decision tool for Parkinsonian tremor-severity automatic scoring. . © 2017 Institute of Physics and Engineering in Medicine.

  11. Brief Review of Regression-Based and Machine Learning Methods in Genetic Epidemiology: The Genetic Analysis Workshop 17 Experience

    PubMed Central

    Dasgupta, Abhijit; Sun, Yan V.; König, Inke R.; Bailey-Wilson, Joan E.; Malley, James D.

    2012-01-01

    Genetics Analysis Workshop 17 provided common and rare genetic variants from exome sequencing data and simulated binary and quantitative traits in 200 replicates. We provide a brief review of the machine learning and regression-based methods used in the analyses of these data. Several regression and machine learning methods were used to address different problems inherent in the analyses of these data, which are high-dimension, low-sample-size data typical of many genetic association studies. Unsupervised methods, such as cluster analysis, were used for data segmentation and subset selection. Supervised learning methods, which include regression-based methods (e.g., generalized linear models, logic regression, and regularized regression) and tree-based methods (e.g., decision trees and random forests), were used for variable selection (selecting genetic and clinical features most associated or predictive of outcome) and prediction (developing models using common and rare genetic variants to accurately predict outcome), with the outcome being case-control status or quantitative trait value. We include a discussion of cross-validation for model selection and assessment and a description of available software resources for these methods. PMID:22128059

  12. A method based on machine learning using hand-crafted features for crack detection from asphalt pavement surface images

    NASA Astrophysics Data System (ADS)

    Fujita, Yusuke; Shimada, Koji; Ichihara, Manabu; Hamamoto, Yoshihiko

    2017-03-01

    Application of machine vision is expected for efficiency and objectivity of inspection in various fields. Automation of visual inspection for asphalt pavement surface images is also expected, but it is difficult because of unexpected objects, non-uniform illumination and irregularities in the pavement surface. Many of conventional approaches are based on state-of-the-arts. However, there is a problem that the application conditions of these is limited. In this article, we proposed a new method based on state-of-the-art and machine learning for crack detection from asphalt pavement surface images. The classifier of the proposed method is the linear support vector machine, and it uses features proposed in the conventional study that is one of the state-of-the-art approaches. The proposed system need not a large number of training data, unlike deep learning architectures. It is easy to train the classifier to detect cracks using a GUI tool developed by authors. Quantitative evaluation using 100 road surface images obtained by mobile mapping system was performed to compare with our conventional method as one of state-of-the-art approaches. Experiments show that our proposed method clearly outperforms the state-of-the-art approach.

  13. Probability Machines: Consistent Probability Estimation Using Nonparametric Learning Machines

    PubMed Central

    Malley, J. D.; Kruppa, J.; Dasgupta, A.; Malley, K. G.; Ziegler, A.

    2011-01-01

    Summary Background Most machine learning approaches only provide a classification for binary responses. However, probabilities are required for risk estimation using individual patient characteristics. It has been shown recently that every statistical learning machine known to be consistent for a nonparametric regression problem is a probability machine that is provably consistent for this estimation problem. Objectives The aim of this paper is to show how random forests and nearest neighbors can be used for consistent estimation of individual probabilities. Methods Two random forest algorithms and two nearest neighbor algorithms are described in detail for estimation of individual probabilities. We discuss the consistency of random forests, nearest neighbors and other learning machines in detail. We conduct a simulation study to illustrate the validity of the methods. We exemplify the algorithms by analyzing two well-known data sets on the diagnosis of appendicitis and the diagnosis of diabetes in Pima Indians. Results Simulations demonstrate the validity of the method. With the real data application, we show the accuracy and practicality of this approach. We provide sample code from R packages in which the probability estimation is already available. This means that all calculations can be performed using existing software. Conclusions Random forest algorithms as well as nearest neighbor approaches are valid machine learning methods for estimating individual probabilities for binary responses. Freely available implementations are available in R and may be used for applications. PMID:21915433

  14. Machine learning applications in genetics and genomics.

    PubMed

    Libbrecht, Maxwell W; Noble, William Stafford

    2015-06-01

    The field of machine learning, which aims to develop computer algorithms that improve with experience, holds promise to enable computers to assist humans in the analysis of large, complex data sets. Here, we provide an overview of machine learning applications for the analysis of genome sequencing data sets, including the annotation of sequence elements and epigenetic, proteomic or metabolomic data. We present considerations and recurrent challenges in the application of supervised, semi-supervised and unsupervised machine learning methods, as well as of generative and discriminative modelling approaches. We provide general guidelines to assist in the selection of these machine learning methods and their practical application for the analysis of genetic and genomic data sets.

  15. Designing Focused Chemical Libraries Enriched in Protein-Protein Interaction Inhibitors using Machine-Learning Methods

    PubMed Central

    Reynès, Christelle; Host, Hélène; Camproux, Anne-Claude; Laconde, Guillaume; Leroux, Florence; Mazars, Anne; Deprez, Benoit; Fahraeus, Robin; Villoutreix, Bruno O.; Sperandio, Olivier

    2010-01-01

    Protein-protein interactions (PPIs) may represent one of the next major classes of therapeutic targets. So far, only a minute fraction of the estimated 650,000 PPIs that comprise the human interactome are known with a tiny number of complexes being drugged. Such intricate biological systems cannot be cost-efficiently tackled using conventional high-throughput screening methods. Rather, time has come for designing new strategies that will maximize the chance for hit identification through a rationalization of the PPI inhibitor chemical space and the design of PPI-focused compound libraries (global or target-specific). Here, we train machine-learning-based models, mainly decision trees, using a dataset of known PPI inhibitors and of regular drugs in order to determine a global physico-chemical profile for putative PPI inhibitors. This statistical analysis unravels two important molecular descriptors for PPI inhibitors characterizing specific molecular shapes and the presence of a privileged number of aromatic bonds. The best model has been transposed into a computer program, PPI-HitProfiler, that can output from any drug-like compound collection a focused chemical library enriched in putative PPI inhibitors. Our PPI inhibitor profiler is challenged on the experimental screening results of 11 different PPIs among which the p53/MDM2 interaction screened within our own CDithem platform, that in addition to the validation of our concept led to the identification of 4 novel p53/MDM2 inhibitors. Collectively, our tool shows a robust behavior on the 11 experimental datasets by correctly profiling 70% of the experimentally identified hits while removing 52% of the inactive compounds from the initial compound collections. We strongly believe that this new tool can be used as a global PPI inhibitor profiler prior to screening assays to reduce the size of the compound collections to be experimentally screened while keeping most of the true PPI inhibitors. PPI-HitProfiler is

  16. Machine learning in virtual screening.

    PubMed

    Melville, James L; Burke, Edmund K; Hirst, Jonathan D

    2009-05-01

    In this review, we highlight recent applications of machine learning to virtual screening, focusing on the use of supervised techniques to train statistical learning algorithms to prioritize databases of molecules as active against a particular protein target. Both ligand-based similarity searching and structure-based docking have benefited from machine learning algorithms, including naïve Bayesian classifiers, support vector machines, neural networks, and decision trees, as well as more traditional regression techniques. Effective application of these methodologies requires an appreciation of data preparation, validation, optimization, and search methodologies, and we also survey developments in these areas.

  17. Constructing and validating readability models: the method of integrating multilevel linguistic features with machine learning.

    PubMed

    Sung, Yao-Ting; Chen, Ju-Ling; Cha, Ji-Her; Tseng, Hou-Chiang; Chang, Tao-Hsing; Chang, Kuo-En

    2015-06-01

    Multilevel linguistic features have been proposed for discourse analysis, but there have been few applications of multilevel linguistic features to readability models and also few validations of such models. Most traditional readability formulae are based on generalized linear models (GLMs; e.g., discriminant analysis and multiple regression), but these models have to comply with certain statistical assumptions about data properties and include all of the data in formulae construction without pruning the outliers in advance. The use of such readability formulae tends to produce a low text classification accuracy, while using a support vector machine (SVM) in machine learning can enhance the classification outcome. The present study constructed readability models by integrating multilevel linguistic features with SVM, which is more appropriate for text classification. Taking the Chinese language as an example, this study developed 31 linguistic features as the predicting variables at the word, semantic, syntax, and cohesion levels, with grade levels of texts as the criterion variable. The study compared four types of readability models by integrating unilevel and multilevel linguistic features with GLMs and an SVM. The results indicate that adopting a multilevel approach in readability analysis provides a better representation of the complexities of both texts and the reading comprehension process.

  18. Development of Machine Learning Tools in ROOT

    NASA Astrophysics Data System (ADS)

    Gleyzer, S. V.; Moneta, L.; Zapata, Omar A.

    2016-10-01

    ROOT is a framework for large-scale data analysis that provides basic and advanced statistical methods used by the LHC experiments. These include machine learning algorithms from the ROOT-integrated Toolkit for Multivariate Analysis (TMVA). We present several recent developments in TMVA, including a new modular design, new algorithms for variable importance and cross-validation, interfaces to other machine-learning software packages and integration of TMVA with Jupyter, making it accessible with a browser.

  19. Machine learning for precise quantum measurement.

    PubMed

    Hentschel, Alexander; Sanders, Barry C

    2010-02-12

    Adaptive feedback schemes are promising for quantum-enhanced measurements yet are complicated to design. Machine learning can autonomously generate algorithms in a classical setting. Here we adapt machine learning for quantum information and use our framework to generate autonomous adaptive feedback schemes for quantum measurement. In particular, our approach replaces guesswork in quantum measurement by a logical, fully automatic, programable routine. We show that our method yields schemes that outperform the best known adaptive scheme for interferometric phase estimation.

  20. Inhibitors for the hepatitis C virus RNA polymerase explored by SAR with advanced machine learning methods

    PubMed Central

    Weidlich, Iwona E.; Filippov, Igor V.; Brown, Jodian; Kaushik-Basu, Neerja; Krishnan, Ramalingam; Nicklaus, Marc C.; Thorpe, Ian F.

    2013-01-01

    Hepatitis C virus (HCV) is a global health challenge, affecting approximately 200 million people worldwide. In this study we developed SAR models with advanced machine learning classifiers Random Forest and k Nearest Neighbor Simulated Annealing for 679 small molecules with measured inhibition activity for NS5B genotype 1b. The activity was expressed as a binary value (active/inactive), where actives were considered molecules with IC50 ≤ 0.95 μM. We applied our SAR models to various drug-like databases and identified novel chemical scaffolds for NS5B inhibitors. Subsequent in vitro antiviral assays suggested a new activity for an existing prodrug, Candesartan cilexetil, which is currently used to treat hypertension and heart failure but has not been previously tested for anti-HCV activity. We also identified NS5B inhibitors with two novel non-nucleoside chemical motifs. PMID:23608107

  1. Inhibitors for the hepatitis C virus RNA polymerase explored by SAR with advanced machine learning methods.

    PubMed

    Weidlich, Iwona E; Filippov, Igor V; Brown, Jodian; Kaushik-Basu, Neerja; Krishnan, Ramalingam; Nicklaus, Marc C; Thorpe, Ian F

    2013-06-01

    Hepatitis C virus (HCV) is a global health challenge, affecting approximately 200 million people worldwide. In this study we developed SAR models with advanced machine learning classifiers Random Forest and k Nearest Neighbor Simulated Annealing for 679 small molecules with measured inhibition activity for NS5B genotype 1b. The activity was expressed as a binary value (active/inactive), where actives were considered molecules with IC50 ≤0.95 μM. We applied our SAR models to various drug-like databases and identified novel chemical scaffolds for NS5B inhibitors. Subsequent in vitro antiviral assays suggested a new activity for an existing prodrug, Candesartan cilexetil, which is currently used to treat hypertension and heart failure but has not been previously tested for anti-HCV activity. We also identified NS5B inhibitors with two novel non-nucleoside chemical motifs. Copyright © 2013 Elsevier Ltd. All rights reserved.

  2. A Machine Learning Method for Power Prediction on the Mobile Devices.

    PubMed

    Chen, Da-Ren; Chen, You-Shyang; Chen, Lin-Chih; Hsu, Ming-Yang; Chiang, Kai-Feng

    2015-10-01

    Energy profiling and estimation have been popular areas of research in multicore mobile architectures. While short sequences of system calls have been recognized by machine learning as pattern descriptions for anomalous detection, power consumption of running processes with respect to system-call patterns are not well studied. In this paper, we propose a fuzzy neural network (FNN) for training and analyzing process execution behaviour with respect to series of system calls, parameters and their power consumptions. On the basis of the patterns of a series of system calls, we develop a power estimation daemon (PED) to analyze and predict the energy consumption of the running process. In the initial stage, PED categorizes sequences of system calls as functional groups and predicts their energy consumptions by FNN. In the operational stage, PED is applied to identify the predefined sequences of system calls invoked by running processes and estimates their energy consumption.

  3. Machine learning methods for anticipating the psychological distress in patients with Alzheimer's disease.

    PubMed

    Zhou, Xiaolin; Xu, Jie; Zhao, Yongbo

    2006-12-01

    Recent studies proved that psychological distress is an accelerator of Alzheimer disease (AD). However, the factors that affect the psychological distress of AD patients are still unknown. The aim of this study was to predict the incidence and identify the risk factors of psychological distress in AD patients. Artificial neural networks and Machine learning models were used to predict the incidence of psychological distress in AD patients. Linear regression and decision tree models were used to identify the factors of psychological distress in AD patients. Among all models for predicting the incidence of psychological distress in AD patients, the artificial neural networks with 8 hidden neurons achieved the highest predictive accuracy of 81.92%. In the five machine learning models, the ADTree algorithm made the highest Predictive Accuracy of 77.94%. As for risk factor analysis, the Linear Regression and Decision Tree models reported similar sets of variables that affect the psychological distress of AD patients. Three variables were reported by Linear Regression to be in negative correlation with psychological distress: the use of professional care service, caregiver consuming cigarette, and caregiver consuming alcohol. The incidence of psychological distress in AD patients can be predicted by artificial neural networks with an accuracy of 81.92%. There are four main risk factors for psychological distress of AD patients: "Caregiver experiencing psychological distress", "Caregiver suffering from chronic disease or cancer", "Care recipient's health status being serious or getting worse", and "Lack of professional care service". These findings are potentially helpful for the prediction, prevention and intervention of psychological distress in AD patients.

  4. Exploring the added value of machine learning methods in predicting flow duration curves: a comparative analysis for ungauged catchments

    NASA Astrophysics Data System (ADS)

    Kentel, E.; Dogulu, N.

    2016-12-01

    Understanding catchment hydrology is a fundamental concern for hydrologists and water resources planners. In this context, given the increasing demand for streamflow information at sparsely gauged or ungauged catchments, there has been great interest in estimating flow duration curve (FDC) due to its many practical applications. Statistical methods have been widely used for the modelling of FDCs at ungauged sites. These methods usually rely on estimation of flow quantiles, or quantitative characteristics of the FDCs representing their shape such as slope and parameters of statistical distribution, often in the context of regionalization. However, there are limited studies using methods of machine learning. Potential of various machine learning approaches for estimating FDCs is yet to be explored although these methods have successfully and extensively applied to solve various other water resources management and hydrological problems. This study addresses this gap by presenting a comparative performance evaluation of the methods: i) Multiple Linear Regression (MLR), ii) Regression Tree (RT), iii) Artificial Neural Network (ANN), iv) Adaptive Neuro-Fuzzy Inference System (ANFIS). Comparison of these methods is done for FDCs of the Western Black Sea catchment in Turkey modelled by relating flow quantiles to a number of variables representing catchment and climate characteristics. Accuracy of predicted FDCs is assessed by three different measures: the Root Mean Squared Error (RMSE), the Nash-Sutcliffe Efficiency (NSE) and the Percent Bias (PBIAS).

  5. A review of machine learning methods to predict the solubility of overexpressed recombinant proteins in Escherichia coli.

    PubMed

    Habibi, Narjeskhatoon; Mohd Hashim, Siti Z; Norouzi, Alireza; Samian, Mohammed Razip

    2014-05-08

    Over the last 20 years in biotechnology, the production of recombinant proteins has been a crucial bioprocess in both biopharmaceutical and research arena in terms of human health, scientific impact and economic volume. Although logical strategies of genetic engineering have been established, protein overexpression is still an art. In particular, heterologous expression is often hindered by low level of production and frequent fail due to opaque reasons. The problem is accentuated because there is no generic solution available to enhance heterologous overexpression. For a given protein, the extent of its solubility can indicate the quality of its function. Over 30% of synthesized proteins are not soluble. In certain experimental circumstances, including temperature, expression host, etc., protein solubility is a feature eventually defined by its sequence. Until now, numerous methods based on machine learning are proposed to predict the solubility of protein merely from its amino acid sequence. In spite of the 20 years of research on the matter, no comprehensive review is available on the published methods. This paper presents an extensive review of the existing models to predict protein solubility in Escherichia coli recombinant protein overexpression system. The models are investigated and compared regarding the datasets used, features, feature selection methods, machine learning techniques and accuracy of prediction. A discussion on the models is provided at the end. This study aims to investigate extensively the machine learning based methods to predict recombinant protein solubility, so as to offer a general as well as a detailed understanding for researches in the field. Some of the models present acceptable prediction performances and convenient user interfaces. These models can be considered as valuable tools to predict recombinant protein overexpression results before performing real laboratory experiments, thus saving labour, time and cost.

  6. Assessing Scientific Practices Using Machine-Learning Methods: How Closely Do They Match Clinical Interview Performance?

    NASA Astrophysics Data System (ADS)

    Beggrow, Elizabeth P.; Ha, Minsu; Nehm, Ross H.; Pearl, Dennis; Boone, William J.

    2013-07-01

    The landscape of science education is being transformed by the new Framework for Science Education (National Research Council, A framework for K-12 science education: practices, crosscutting concepts, and core ideas. The National Academies Press, Washington, DC, 2012), which emphasizes the centrality of scientific practices—such as explanation, argumentation, and communication—in science teaching, learning, and assessment. A major challenge facing the field of science education is developing assessment tools that are capable of validly and efficiently evaluating these practices. Our study examined the efficacy of a free, open-source machine-learning tool for evaluating the quality of students' written explanations of the causes of evolutionary change relative to three other approaches: (1) human-scored written explanations, (2) a multiple-choice test, and (3) clinical oral interviews. A large sample of undergraduates (n = 104) exposed to varying amounts of evolution content completed all three assessments: a clinical oral interview, a written open-response assessment, and a multiple-choice test. Rasch analysis was used to compute linear person measures and linear item measures on a single logit scale. We found that the multiple-choice test displayed poor person and item fit (mean square outfit >1.3), while both oral interview measures and computer-generated written response measures exhibited acceptable fit (average mean square outfit for interview: person 0.97, item 0.97; computer: person 1.03, item 1.06). Multiple-choice test measures were more weakly associated with interview measures (r = 0.35) than the computer-scored explanation measures (r = 0.63). Overall, Rasch analysis indicated that computer-scored written explanation measures (1) have the strongest correspondence to oral interview measures; (2) are capable of capturing students' normative scientific and naive ideas as accurately as human-scored explanations, and (3) more validly detect understanding

  7. Diagnosis of Dementia by Machine learning methods in Epidemiological studies: a pilot exploratory study from south India.

    PubMed

    Bhagyashree, Sheshadri Iyengar Raghavan; Nagaraj, Kiran; Prince, Martin; Fall, Caroline H D; Krishna, Murali

    2017-07-11

    There are limited data on the use of artificial intelligence methods for the diagnosis of dementia in epidemiological studies in low- and middle-income country (LMIC) settings. A culture and education fair battery of cognitive tests was developed and validated for population based studies in low- and middle-income countries including India by the 10/66 Dementia Research Group. We explored the machine learning methods based on the 10/66 battery of cognitive tests for the diagnosis of dementia based in a birth cohort study in South India. The data sets for 466 men and women for this study were obtained from the on-going Mysore Studies of Natal effect of Health and Ageing (MYNAH), in south India. The data sets included: demographics, performance on the 10/66 cognitive function tests, the 10/66 diagnosis of mental disorders and population based normative data for the 10/66 battery of cognitive function tests. Diagnosis of dementia from the rule based approach was compared against the 10/66 diagnosis of dementia. We have applied machine learning techniques to identify minimal number of the 10/66 cognitive function tests required for diagnosing dementia and derived an algorithm to improve the accuracy of dementia diagnosis. Of 466 subjects, 27 had 10/66 diagnosis of dementia, 19 of whom were correctly identified as having dementia by Jrip classification with 100% accuracy. This pilot exploratory study indicates that machine learning methods can help identify community dwelling older adults with 10/66 criterion diagnosis of dementia with good accuracy in a LMIC setting such as India. This should reduce the duration of the diagnostic assessment and make the process easier and quicker for clinicians, patients and will be useful for 'case' ascertainment in population based epidemiological studies.

  8. Comparison between Two Linear Supervised Learning Machines' Methods with Principle Component Based Methods for the Spectrofluorimetric Determination of Agomelatine and Its Degradants.

    PubMed

    Elkhoudary, Mahmoud M; Naguib, Ibrahim A; Abdel Salam, Randa A; Hadad, Ghada M

    2017-05-01

    Four accurate, sensitive and reliable stability indicating chemometric methods were developed for the quantitative determination of Agomelatine (AGM) whether in pure form or in pharmaceutical formulations. Two supervised learning machines' methods; linear artificial neural networks (PC-linANN) preceded by principle component analysis and linear support vector regression (linSVR), were compared with two principle component based methods; principle component regression (PCR) as well as partial least squares (PLS) for the spectrofluorimetric determination of AGM and its degradants. The results showed the benefits behind using linear learning machines' methods and the inherent merits of their algorithms in handling overlapped noisy spectral data especially during the challenging determination of AGM alkaline and acidic degradants (DG1 and DG2). Relative mean squared error of prediction (RMSEP) for the proposed models in the determination of AGM were 1.68, 1.72, 0.68 and 0.22 for PCR, PLS, SVR and PC-linANN; respectively. The results showed the superiority of supervised learning machines' methods over principle component based methods. Besides, the results suggested that linANN is the method of choice for determination of components in low amounts with similar overlapped spectra and narrow linearity range. Comparison between the proposed chemometric models and a reported HPLC method revealed the comparable performance and quantification power of the proposed models.

  9. Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data.

    PubMed

    Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

    2017-01-01

    Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

  10. Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data

    PubMed Central

    Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

    2017-01-01

    Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size. PMID:28045443

  11. Comparing machine learning and logistic regression methods for predicting hypertension using a combination of gene expression and next-generation sequencing data.

    PubMed

    Held, Elizabeth; Cape, Joshua; Tintle, Nathan

    2016-01-01

    Machine learning methods continue to show promise in the analysis of data from genetic association studies because of the high number of variables relative to the number of observations. However, few best practices exist for the application of these methods. We extend a recently proposed supervised machine learning approach for predicting disease risk by genotypes to be able to incorporate gene expression data and rare variants. We then apply 2 different versions of the approach (radial and linear support vector machines) to simulated data from Genetic Analysis Workshop 19 and compare performance to logistic regression. Method performance was not radically different across the 3 methods, although the linear support vector machine tended to show small gains in predictive ability relative to a radial support vector machine and logistic regression. Importantly, as the number of genes in the models was increased, even when those genes contained causal rare variants, model predictive ability showed a statistically significant decrease in performance for both the radial support vector machine and logistic regression. The linear support vector machine showed more robust performance to the inclusion of additional genes. Further work is needed to evaluate machine learning approaches on larger samples and to evaluate the relative improvement in model prediction from the incorporation of gene expression data.

  12. An introduction to quantum machine learning

    NASA Astrophysics Data System (ADS)

    Schuld, Maria; Sinayskiy, Ilya; Petruccione, Francesco

    2015-04-01

    Machine learning algorithms learn a desired input-output relation from examples in order to interpret new inputs. This is important for tasks such as image and speech recognition or strategy optimisation, with growing applications in the IT industry. In the last couple of years, researchers investigated if quantum computing can help to improve classical machine learning algorithms. Ideas range from running computationally costly algorithms or their subroutines efficiently on a quantum computer to the translation of stochastic methods into the language of quantum theory. This contribution gives a systematic overview of the emerging field of quantum machine learning. It presents the approaches as well as technical details in an accessible way, and discusses the potential of a future theory of quantum learning.

  13. Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

    PubMed Central

    2013-01-01

    Background Distinguishing cases from non-cases in free-text electronic medical records is an important initial step in observational epidemiological studies, but manual record validation is time-consuming and cumbersome. We compared different approaches to develop an automatic case identification system with high sensitivity to assist manual annotators. Methods We used four different machine-learning algorithms to build case identification systems for two data sets, one comprising hepatobiliary disease patients, the other acute renal failure patients. To improve the sensitivity of the systems, we varied the imbalance ratio between positive cases and negative cases using under- and over-sampling techniques, and applied cost-sensitive learning with various misclassification costs. Results For the hepatobiliary data set, we obtained a high sensitivity of 0.95 (on a par with manual annotators, as compared to 0.91 for a baseline classifier) with specificity 0.56. For the acute renal failure data set, sensitivity increased from 0.69 to 0.89, with specificity 0.59. Performance differences between the various machine-learning algorithms were not large. Classifiers performed best when trained on data sets with imbalance ratio below 10. Conclusions We were able to achieve high sensitivity with moderate specificity for automatic case identification on two data sets of electronic medical records. Such a high-sensitive case identification system can be used as a pre-filter to significantly reduce the burden of manual record validation. PMID:23452306

  14. Comparative analysis of expert and machine-learning methods for classification of body cavity effusions in companion animals.

    PubMed

    Hotz, Christine S; Templeton, Steven J; Christopher, Mary M

    2005-03-01

    A rule-based expert system using CLIPS programming language was created to classify body cavity effusions as transudates, modified transudates, exudates, chylous, and hemorrhagic effusions. The diagnostic accuracy of the rule-based system was compared with that produced by 2 machine-learning methods: Rosetta, a rough sets algorithm and RIPPER, a rule-induction method. Results of 508 body cavity fluid analyses (canine, feline, equine) obtained from the University of California-Davis Veterinary Medical Teaching Hospital computerized patient database were used to test CLIPS and to test and train RIPPER and Rosetta. The CLIPS system, using 17 rules, achieved an accuracy of 93.5% compared with pathologist consensus diagnoses. Rosetta accurately classified 91% of effusions by using 5,479 rules. RIPPER achieved the greatest accuracy (95.5%) using only 10 rules. When the original rules of the CLIPS application were replaced with those of RIPPER, the accuracy rates were identical. These results suggest that both rule-based expert systems and machine-learning methods hold promise for the preliminary classification of body fluids in the clinical laboratory.

  15. Machine Learning Methods for the Sampling of Chemical Space From First Principles

    NASA Astrophysics Data System (ADS)

    von Lilienfeld, Anatole

    2015-03-01

    Computational brute force high-throughput screening of compounds is beyond any capacity for all but the most restricted systems due to the combinatorial nature of chemical space, i.e. all the compositional, constitutional, and conformational isomers. Efficient computational materials design algorithms must therefore make good trade-offs between the accuracy of the applied model and computational speed. Overall, rapid convergence in terms of number of compounds visited is highly desirable. In this talk, I will describe recent contributions in this field based on statistical approaches that can serve as inexpensive surrogate models to reduce the computational load of quantum mechanical calculations. Such surrogate machine learning (ML) models infer quantum mechanical observables of novel materials, rather than solving approximate variants of Schroedinger's equation. We developed accurate ML models for the rapid prediction of atomization energies and enthalpies, cohesive energies, and electronic properties that conventionally can only be predicted using quantum mechanics. All our ML models have been trained using large data bases containing properties of thousands of chemical compounds and materials. I will exemplify our approach for the prediction of properties from scratch for out-of-sample compounds. These predictions reach quantum chemical accuracy and are basically instantaneous, i.e. at a computational cost reduced by several orders of magnitude.

  16. Comparison of machine learning methods for classifying aphasic and non-aphasic speakers.

    PubMed

    Järvelin, Antti; Juhola, Martti

    2011-12-01

    The performance of eight machine learning classifiers were compared with three aphasia related classification problems. The first problem contained naming data of aphasic and non-aphasic speakers tested with the Philadelphia Naming Test. The second problem included the naming data of Alzheimer and vascular disease patients tested with Finnish version of the Boston Naming Test. The third problem included aphasia test data of patients suffering from four different aphasic syndromes tested with the Aachen Aphasia Test. The first two data sets were small. Therefore, the data used in the tests were artificially generated from the original confrontation naming data of 23 and 22 subjects, respectively. The third set contained aphasia test data of 146 aphasic speakers and was used as such in the experiments. With the first and the third data set the classifiers could successfully be used for the task, while the results with the second data set were less encouraging. However, based on the results, no single classifier performed exceptionally well with all data sets, suggesting that the selection of the classifier used for classification of aphasic data should be based on the experiments performed with the data set at hand. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

  17. Machine Shop. Student Learning Guide.

    ERIC Educational Resources Information Center

    Palm Beach County Board of Public Instruction, West Palm Beach, FL.

    This student learning guide contains eight modules for completing a course in machine shop. It is designed especially for use in Palm Beach County, Florida. Each module covers one task, and consists of a purpose, performance objective, enabling objectives, learning activities and resources, information sheets, student self-check with answer key,…

  18. Machine Shop. Student Learning Guide.

    ERIC Educational Resources Information Center

    Palm Beach County Board of Public Instruction, West Palm Beach, FL.

    This student learning guide contains eight modules for completing a course in machine shop. It is designed especially for use in Palm Beach County, Florida. Each module covers one task, and consists of a purpose, performance objective, enabling objectives, learning activities and resources, information sheets, student self-check with answer key,…

  19. Data Processing And Machine Learning Methods For Multi-Modal Operator State Classification Systems

    NASA Technical Reports Server (NTRS)

    Hearn, Tristan A.

    2015-01-01

    This document is intended as an introduction to a set of common signal processing learning methods that may be used in the software portion of a functional crew state monitoring system. This includes overviews of both the theory of the methods involved, as well as examples of implementation. Practical considerations are discussed for implementing modular, flexible, and scalable processing and classification software for a multi-modal, multi-channel monitoring system. Example source code is also given for all of the discussed processing and classification methods.

  20. Oral cancer prognosis based on clinicopathologic and genomic markers using a hybrid of feature selection and machine learning methods

    PubMed Central

    2013-01-01

    Background Machine learning techniques are becoming useful as an alternative approach to conventional medical diagnosis or prognosis as they are good for handling noisy and incomplete data, and significant results can be attained despite a small sample size. Traditionally, clinicians make prognostic decisions based on clinicopathologic markers. However, it is not easy for the most skilful clinician to come out with an accurate prognosis by using these markers alone. Thus, there is a need to use genomic markers to improve the accuracy of prognosis. The main aim of this research is to apply a hybrid of feature selection and machine learning methods in oral cancer prognosis based on the parameters of the correlation of clinicopathologic and genomic markers. Results In the first stage of this research, five feature selection methods have been proposed and experimented on the oral cancer prognosis dataset. In the second stage, the model with the features selected from each feature selection methods are tested on the proposed classifiers. Four types of classifiers are chosen; these are namely, ANFIS, artificial neural network, support vector machine and logistic regression. A k-fold cross-validation is implemented on all types of classifiers due to the small sample size. The hybrid model of ReliefF-GA-ANFIS with 3-input features of drink, invasion and p63 achieved the best accuracy (accuracy = 93.81%; AUC = 0.90) for the oral cancer prognosis. Conclusions The results revealed that the prognosis is superior with the presence of both clinicopathologic and genomic markers. The selected features can be investigated further to validate the potential of becoming as significant prognostic signature in the oral cancer studies. PMID:23725313

  1. Game-powered machine learning

    PubMed Central

    Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

    2012-01-01

    Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the “wisdom of the crowds.” Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., “funky jazz with saxophone,” “spooky electronica,” etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data. PMID:22460786

  2. Game-powered machine learning.

    PubMed

    Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

    2012-04-24

    Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

  3. Recent Advances in Predictive (Machine) Learning

    SciTech Connect

    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.

  4. Machine Learning Based Malware Detection

    DTIC Science & Technology

    2015-05-18

    researchers have used machine learning to classify malware. Three types of features that have been popular in experiments to date are n- grams over machine...code instructions, API call sequences, and PE32 header data. N- gram analysis involves splitting a program’s code into chunks of size “n”—the n- grams ...File features are derived from frequencies of certain n- grams . Some studies have achieved modest success with this technique [6], [7]. However, it

  5. RED-ML: a novel, effective RNA editing detection method based on machine learning.

    PubMed

    Xiong, Heng; Liu, Dongbing; Li, Qiye; Lei, Mengyue; Xu, Liqin; Wu, Liang; Wang, Zongji; Ren, Shancheng; Li, Wangsheng; Xia, Min; Lu, Lihua; Lu, Haorong; Hou, Yong; Zhu, Shida; Liu, Xin; Sun, Yinghao; Wang, Jian; Yang, Huanming; Wu, Kui; Xu, Xun; Lee, Leo J

    2017-05-01

    With the advancement of second generation sequencing techniques, our ability to detect and quantify RNA editing on a global scale has been vastly improved. As a result, RNA editing is now being studied under a growing number of biological conditions so that its biochemical mechanisms and functional roles can be further understood. However, a major barrier that prevents RNA editing from being a routine RNA-seq analysis, similar to gene expression and splicing analysis, for example, is the lack of user-friendly and effective computational tools. Based on years of experience of analyzing RNA editing using diverse RNA-seq datasets, we have developed a software tool, RED-ML: RNA Editing Detection based on Machine learning (pronounced as "red ML"). The input to RED-ML can be as simple as a single BAM file, while it can also take advantage of matched genomic variant information when available. The output not only contains detected RNA editing sites, but also a confidence score to facilitate downstream filtering. We have carefully designed validation experiments and performed extensive comparison and analysis to show the efficiency and effectiveness of RED-ML under different conditions, and it can accurately detect novel RNA editing sites without relying on curated RNA editing databases. We have also made this tool freely available via GitHub . We have developed a highly accurate, speedy and general-purpose tool for RNA editing detection using RNA-seq data. With the availability of RED-ML, it is now possible to conveniently make RNA editing a routine analysis of RNA-seq. We believe this can greatly benefit the RNA editing research community and has profound impact to accelerate our understanding of this intriguing posttranscriptional modification process. © The Author 2017. Published by Oxford University Press.

  6. Machine learning: Trends, perspectives, and prospects.

    PubMed

    Jordan, M I; Mitchell, T M

    2015-07-17

    Machine learning addresses the question of how to build computers that improve automatically through experience. It is one of today's most rapidly growing technical fields, lying at the intersection of computer science and statistics, and at the core of artificial intelligence and data science. Recent progress in machine learning has been driven both by the development of new learning algorithms and theory and by the ongoing explosion in the availability of online data and low-cost computation. The adoption of data-intensive machine-learning methods can be found throughout science, technology and commerce, leading to more evidence-based decision-making across many walks of life, including health care, manufacturing, education, financial modeling, policing, and marketing.

  7. A comparison of machine learning methods for classification using simulation with multiple real data examples from mental health studies.

    PubMed

    Khondoker, Mizanur; Dobson, Richard; Skirrow, Caroline; Simmons, Andrew; Stahl, Daniel

    2016-10-01

    Recent literature on the comparison of machine learning methods has raised questions about the neutrality, unbiasedness and utility of many comparative studies. Reporting of results on favourable datasets and sampling error in the estimated performance measures based on single samples are thought to be the major sources of bias in such comparisons. Better performance in one or a few instances does not necessarily imply so on an average or on a population level and simulation studies may be a better alternative for objectively comparing the performances of machine learning algorithms. We compare the classification performance of a number of important and widely used machine learning algorithms, namely the Random Forests (RF), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA) and k-Nearest Neighbour (kNN). Using massively parallel processing on high-performance supercomputers, we compare the generalisation errors at various combinations of levels of several factors: number of features, training sample size, biological variation, experimental variation, effect size, replication and correlation between features. For smaller number of correlated features, number of features not exceeding approximately half the sample size, LDA was found to be the method of choice in terms of average generalisation errors as well as stability (precision) of error estimates. SVM (with RBF kernel) outperforms LDA as well as RF and kNN by a clear margin as the feature set gets larger provided the sample size is not too small (at least 20). The performance of kNN also improves as the number of features grows and outplays that of LDA and RF unless the data variability is too high and/or effect sizes are too small. RF was found to outperform only kNN in some instances where the data are more variable and have smaller effect sizes, in which cases it also provide more stable error estimates than kNN and LDA. Applications to a number of real datasets supported the findings from

  8. Machine learning phases of matter

    NASA Astrophysics Data System (ADS)

    Carrasquilla, Juan; Melko, Roger G.

    2017-02-01

    Condensed-matter physics is the study of the collective behaviour of infinitely complex assemblies of electrons, nuclei, magnetic moments, atoms or qubits. This complexity is reflected in the size of the state space, which grows exponentially with the number of particles, reminiscent of the `curse of dimensionality' commonly encountered in machine learning. Despite this curse, the machine learning community has developed techniques with remarkable abilities to recognize, classify, and characterize complex sets of data. Here, we show that modern machine learning architectures, such as fully connected and convolutional neural networks, can identify phases and phase transitions in a variety of condensed-matter Hamiltonians. Readily programmable through modern software libraries, neural networks can be trained to detect multiple types of order parameter, as well as highly non-trivial states with no conventional order, directly from raw state configurations sampled with Monte Carlo.

  9. Machine Learning Approaches in Cardiovascular Imaging.

    PubMed

    Henglin, Mir; Stein, Gillian; Hushcha, Pavel V; Snoek, Jasper; Wiltschko, Alexander B; Cheng, Susan

    2017-10-01

    Cardiovascular imaging technologies continue to increase in their capacity to capture and store large quantities of data. Modern computational methods, developed in the field of machine learning, offer new approaches to leveraging the growing volume of imaging data available for analyses. Machine learning methods can now address data-related problems ranging from simple analytic queries of existing measurement data to the more complex challenges involved in analyzing raw images. To date, machine learning has been used in 2 broad and highly interconnected areas: automation of tasks that might otherwise be performed by a human and generation of clinically important new knowledge. Most cardiovascular imaging studies have focused on task-oriented problems, but more studies involving algorithms aimed at generating new clinical insights are emerging. Continued expansion in the size and dimensionality of cardiovascular imaging databases is driving strong interest in applying powerful deep learning methods, in particular, to analyze these data. Overall, the most effective approaches will require an investment in the resources needed to appropriately prepare such large data sets for analyses. Notwithstanding current technical and logistical challenges, machine learning and especially deep learning methods have much to offer and will substantially impact the future practice and science of cardiovascular imaging. © 2017 American Heart Association, Inc.

  10. Blind steganalysis method for JPEG steganography combined with the semisupervised learning and soft margin support vector machine

    NASA Astrophysics Data System (ADS)

    Dong, Yu; Zhang, Tao; Xi, Ling

    2015-01-01

    Stego images embedded by unknown steganographic algorithms currently may not be detected by using steganalysis detectors based on binary classifier. However, it is difficult to obtain high detection accuracy by using universal steganalysis based on one-class classifier. For solving this problem, a blind detection method for JPEG steganography was proposed from the perspective of information theory. The proposed method combined the semisupervised learning and soft margin support vector machine with steganalysis detector based on one-class classifier to utilize the information in test data for improving detection performance. Reliable blind detection for JPEG steganography was realized only using cover images for training. The experimental results show that the proposed method can contribute to improving the detection accuracy of steganalysis detector based on one-class classifier and has good robustness under different source mismatch conditions.

  11. Machine learning in motion control

    NASA Technical Reports Server (NTRS)

    Su, Renjeng; Kermiche, Noureddine

    1989-01-01

    The existing methodologies for robot programming originate primarily from robotic applications to manufacturing, where uncertainties of the robots and their task environment may be minimized by repeated off-line modeling and identification. In space application of robots, however, a higher degree of automation is required for robot programming because of the desire of minimizing the human intervention. We discuss a new paradigm of robotic programming which is based on the concept of machine learning. The goal is to let robots practice tasks by themselves and the operational data are used to automatically improve their motion performance. The underlying mathematical problem is to solve the problem of dynamical inverse by iterative methods. One of the key questions is how to ensure the convergence of the iterative process. There have been a few small steps taken into this important approach to robot programming. We give a representative result on the convergence problem.

  12. Machine learning in sedimentation modelling.

    PubMed

    Bhattacharya, B; Solomatine, D P

    2006-03-01

    The paper presents machine learning (ML) models that predict sedimentation in the harbour basin of the Port of Rotterdam. The important factors affecting the sedimentation process such as waves, wind, tides, surge, river discharge, etc. are studied, the corresponding time series data is analysed, missing values are estimated and the most important variables behind the process are chosen as the inputs. Two ML methods are used: MLP ANN and M5 model tree. The latter is a collection of piece-wise linear regression models, each being an expert for a particular region of the input space. The models are trained on the data collected during 1992-1998 and tested by the data of 1999-2000. The predictive accuracy of the models is found to be adequate for the potential use in the operational decision making.

  13. Machine learning in motion control

    NASA Technical Reports Server (NTRS)

    Su, Renjeng; Kermiche, Noureddine

    1989-01-01

    The existing methodologies for robot programming originate primarily from robotic applications to manufacturing, where uncertainties of the robots and their task environment may be minimized by repeated off-line modeling and identification. In space application of robots, however, a higher degree of automation is required for robot programming because of the desire of minimizing the human intervention. We discuss a new paradigm of robotic programming which is based on the concept of machine learning. The goal is to let robots practice tasks by themselves and the operational data are used to automatically improve their motion performance. The underlying mathematical problem is to solve the problem of dynamical inverse by iterative methods. One of the key questions is how to ensure the convergence of the iterative process. There have been a few small steps taken into this important approach to robot programming. We give a representative result on the convergence problem.

  14. A Hybrid Machine Learning Method for Fusing fMRI and Genetic Data: Combining both Improves Classification of Schizophrenia

    PubMed Central

    Yang, Honghui; Liu, Jingyu; Sui, Jing; Pearlson, Godfrey; Calhoun, Vince D.

    2010-01-01

    We demonstrate a hybrid machine learning method to classify schizophrenia patients and healthy controls, using functional magnetic resonance imaging (fMRI) and single nucleotide polymorphism (SNP) data. The method consists of four stages: (1) SNPs with the most discriminating information between the healthy controls and schizophrenia patients are selected to construct a support vector machine ensemble (SNP-SVME). (2) Voxels in the fMRI map contributing to classification are selected to build another SVME (Voxel-SVME). (3) Components of fMRI activation obtained with independent component analysis (ICA) are used to construct a single SVM classifier (ICA-SVMC). (4) The above three models are combined into a single module using a majority voting approach to make a final decision (Combined SNP-fMRI). The method was evaluated by a fully validated leave-one-out method using 40 subjects (20 patients and 20 controls). The classification accuracy was: 0.74 for SNP-SVME, 0.82 for Voxel-SVME, 0.83 for ICA-SVMC, and 0.87 for Combined SNP-fMRI. Experimental results show that better classification accuracy was achieved by combining genetic and fMRI data than using either alone, indicating that genetic and brain function representing different, but partially complementary aspects, of schizophrenia etiopathology. This study suggests an effective way to reassess biological classification of individuals with schizophrenia, which is also potentially useful for identifying diagnostically important markers for the disorder. PMID:21119772

  15. Prediction of Backbreak in Open-Pit Blasting Operations Using the Machine Learning Method

    NASA Astrophysics Data System (ADS)

    Khandelwal, Manoj; Monjezi, M.

    2013-03-01

    Backbreak is an undesirable phenomenon in blasting operations. It can cause instability of mine walls, falling down of machinery, improper fragmentation, reduced efficiency of drilling, etc. The existence of various effective parameters and their unknown relationships are the main reasons for inaccuracy of the empirical models. Presently, the application of new approaches such as artificial intelligence is highly recommended. In this paper, an attempt has been made to predict backbreak in blasting operations of Soungun iron mine, Iran, incorporating rock properties and blast design parameters using the support vector machine (SVM) method. To investigate the suitability of this approach, the predictions by SVM have been compared with multivariate regression analysis (MVRA). The coefficient of determination (CoD) and the mean absolute error (MAE) were taken as performance measures. It was found that the CoD between measured and predicted backbreak was 0.987 and 0.89 by SVM and MVRA, respectively, whereas the MAE was 0.29 and 1.07 by SVM and MVRA, respectively.

  16. Applications of machine learning and data mining methods to detect associations of rare and common variants with complex traits.

    PubMed

    Lu, Ake Tzu-Hui; Austin, Erin; Bonner, Ashley; Huang, Hsin-Hsiung; Cantor, Rita M

    2014-09-01

    Machine learning methods (MLMs), designed to develop models using high-dimensional predictors, have been used to analyze genome-wide genetic and genomic data to predict risks for complex traits. We summarize the results from six contributions to our Genetic Analysis Workshop 18 working group; these investigators applied MLMs and data mining to analyses of rare and common genetic variants measured in pedigrees. To develop risk profiles, group members analyzed blood pressure traits along with single-nucleotide polymorphisms and rare variant genotypes derived from sequence and imputation analyses in large Mexican American pedigrees. Supervised MLMs included penalized regression with varying penalties, support vector machines, and permanental classification. Unsupervised MLMs included sparse principal components analysis and sparse graphical models. Entropy-based components analyses were also used to mine these data. None of the investigators fully capitalized on the genetic information provided by the complete pedigrees. Their approaches either corrected for the nonindependence of the individuals within the pedigrees or analyzed only those who were independent. Some methods allowed for covariate adjustment, whereas others did not. We evaluated these methods using a variety of metrics. Four contributors conducted primary analyses on the real data, and the other two research groups used the simulated data with and without knowledge of the underlying simulation model. One group used the answers to the simulated data to assess power and type I errors. Although the MLMs applied were substantially different, each research group concluded that MLMs have advantages over standard statistical approaches with these high-dimensional data.

  17. In silico prediction and screening of gamma-secretase inhibitors by molecular descriptors and machine learning methods.

    PubMed

    Yang, Xue-Gang; Lv, Wei; Chen, Yu-Zong; Xue, Ying

    2010-04-30

    Gamma-secretase inhibitors have been explored for the prevention and treatment of Alzheimer's disease (AD). Methods for prediction and screening of gamma-secretase inhibitors are highly desired for facilitating the design of novel therapeutic agents against AD, especially when incomplete knowledge about the mechanism and three-dimensional structure of gamma-secretase. We explored two machine learning methods, support vector machine (SVM) and random forest (RF), to develop models for predicting gamma-secretase inhibitors of diverse structures. Quantitative analysis of the receiver operating characteristic (ROC) curve was performed to further examine and optimize the models. Especially, the Youden index (YI) was initially introduced into the ROC curve of RF so as to obtain an optimal threshold of probability for prediction. The developed models were validated by an external testing set with the prediction accuracies of SVM and RF 96.48 and 98.83% for gamma-secretase inhibitors and 98.18 and 99.27% for noninhibitors, respectively. The different feature selection methods were used to extract the physicochemical features most relevant to gamma-secretase inhibition. To the best of our knowledge, the RF model developed in this work is the first model with a broad applicability domain, based on which the virtual screening of gamma-secretase inhibitors against the ZINC database was performed, resulting in 368 potential hit candidates. 2009 Wiley Periodicals, Inc.

  18. Remotely controlling of mobile robots using gesture captured by the Kinect and recognized by machine learning method

    NASA Astrophysics Data System (ADS)

    Hsu, Roy CHaoming; Jian, Jhih-Wei; Lin, Chih-Chuan; Lai, Chien-Hung; Liu, Cheng-Ting

    2013-01-01

    The main purpose of this paper is to use machine learning method and Kinect and its body sensation technology to design a simple, convenient, yet effective robot remote control system. In this study, a Kinect sensor is used to capture the human body skeleton with depth information, and a gesture training and identification method is designed using the back propagation neural network to remotely command a mobile robot for certain actions via the Bluetooth. The experimental results show that the designed mobile robots remote control system can achieve, on an average, more than 96% of accurate identification of 7 types of gestures and can effectively control a real e-puck robot for the designed commands.

  19. Integration of metabolomics, lipidomics and clinical data using a machine learning method.

    PubMed

    Acharjee, Animesh; Ament, Zsuzsanna; West, James A; Stanley, Elizabeth; Griffin, Julian L

    2016-11-22

    The recent pandemic of obesity and the metabolic syndrome (MetS) has led to the realisation that new drug targets are needed to either reduce obesity or the subsequent pathophysiological consequences associated with excess weight gain. Certain nuclear hormone receptors (NRs) play a pivotal role in lipid and carbohydrate metabolism and have been highlighted as potential treatments for obesity. This realisation started a search for NR agonists in order to understand and successfully treat MetS and associated conditions such as insulin resistance, dyslipidaemia, hypertension, hypertriglyceridemia, obesity and cardiovascular disease. The most studied NRs for treating metabolic diseases are the peroxisome proliferator-activated receptors (PPARs), PPAR-α, PPAR-γ, and PPAR-δ. However, prolonged PPAR treatment in animal models has led to adverse side effects including increased risk of a number of cancers, but how these receptors change metabolism long term in terms of pathology, despite many beneficial effects shorter term, is not fully understood. In the current study, changes in male Sprague Dawley rat liver caused by dietary treatment with a PPAR-pan (PPAR-α, -γ, and -δ) agonist were profiled by classical toxicology (clinical chemistry) and high throughput metabolomics and lipidomics approaches using mass spectrometry. In order to integrate an extensive set of nine different multivariate metabolic and lipidomics datasets with classical toxicological parameters we developed a hypotheses free, data driven machine learning approach. From the data analysis, we examined how the nine datasets were able to model dose and clinical chemistry results, with the different datasets having very different information content. We found lipidomics (Direct Infusion-Mass Spectrometry) data the most predictive for different dose responses. In addition, associations with the metabolic and lipidomic data with aspartate amino transaminase (AST), a hepatic leakage enzyme to assess organ

  20. Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds

    NASA Astrophysics Data System (ADS)

    Shortridge, Julie E.; Guikema, Seth D.; Zaitchik, Benjamin F.

    2016-07-01

    In the past decade, machine learning methods for empirical rainfall-runoff modeling have seen extensive development and been proposed as a useful complement to physical hydrologic models, particularly in basins where data to support process-based models are limited. However, the majority of research has focused on a small number of methods, such as artificial neural networks, despite the development of multiple other approaches for non-parametric regression in recent years. Furthermore, this work has often evaluated model performance based on predictive accuracy alone, while not considering broader objectives, such as model interpretability and uncertainty, that are important if such methods are to be used for planning and management decisions. In this paper, we use multiple regression and machine learning approaches (including generalized additive models, multivariate adaptive regression splines, artificial neural networks, random forests, and M5 cubist models) to simulate monthly streamflow in five highly seasonal rivers in the highlands of Ethiopia and compare their performance in terms of predictive accuracy, error structure and bias, model interpretability, and uncertainty when faced with extreme climate conditions. While the relative predictive performance of models differed across basins, data-driven approaches were able to achieve reduced errors when compared to physical models developed for the region. Methods such as random forests and generalized additive models may have advantages in terms of visualization and interpretation of model structure, which can be useful in providing insights into physical watershed function. However, the uncertainty associated with model predictions under extreme climate conditions should be carefully evaluated, since certain models (especially generalized additive models and multivariate adaptive regression splines) become highly variable when faced with high temperatures.

  1. Representational issues in machine learning

    SciTech Connect

    Liepins, G.E.; Hilliard, M.R.

    1986-10-25

    Classifier systems are numeric machine learning systems. They are machine counterparts to the natural genetic process and learn by reproduction, crossover, and mutation. Much publicity has been attended to their ability to demonstrate significant learning from a random start and without human intervention. Less well publicized is the considerable care that must be given to the choices of parameter settings and representation. Without the proper ''nurturing environment'' genetic algorithms are apt to learn very little. This infusion of human intelligence is often discounted, but the choice of appropriate representation forms the core of much of the current genetic algorithm research. This paper will address some of the representational issues from the perspective of two current experiments, one with scheduling and the other with a simulated robot. 10 refs., 7 figs.

  2. Language Acquisition and Machine Learning.

    DTIC Science & Technology

    1986-02-01

    This paper reviews recent progress in the field of machine learning and examine its implications for computational models of language acquisition . As...limitations of the earlier work and propose an alternative approach to modeling the mechanisms underlying language acquisition . (Author)

  3. A general procedure to generate models for urban environmental-noise pollution using feature selection and machine learning methods.

    PubMed

    Torija, Antonio J; Ruiz, Diego P

    2015-02-01

    The prediction of environmental noise in urban environments requires the solution of a complex and non-linear problem, since there are complex relationships among the multitude of variables involved in the characterization and modelling of environmental noise and environmental-noise magnitudes. Moreover, the inclusion of the great spatial heterogeneity characteristic of urban environments seems to be essential in order to achieve an accurate environmental-noise prediction in cities. This problem is addressed in this paper, where a procedure based on feature-selection techniques and machine-learning regression methods is proposed and applied to this environmental problem. Three machine-learning regression methods, which are considered very robust in solving non-linear problems, are used to estimate the energy-equivalent sound-pressure level descriptor (LAeq). These three methods are: (i) multilayer perceptron (MLP), (ii) sequential minimal optimisation (SMO), and (iii) Gaussian processes for regression (GPR). In addition, because of the high number of input variables involved in environmental-noise modelling and estimation in urban environments, which make LAeq prediction models quite complex and costly in terms of time and resources for application to real situations, three different techniques are used to approach feature selection or data reduction. The feature-selection techniques used are: (i) correlation-based feature-subset selection (CFS), (ii) wrapper for feature-subset selection (WFS), and the data reduction technique is principal-component analysis (PCA). The subsequent analysis leads to a proposal of different schemes, depending on the needs regarding data collection and accuracy. The use of WFS as the feature-selection technique with the implementation of SMO or GPR as regression algorithm provides the best LAeq estimation (R(2)=0.94 and mean absolute error (MAE)=1.14-1.16 dB(A)). Copyright © 2014 Elsevier B.V. All rights reserved.

  4. Workshop on Fielded Applications of Machine Learning

    DTIC Science & Technology

    1994-05-11

    This report summaries the talks presented at the Workshop on Fielded Applications of Machine Learning , and draws some initial conclusions about the state of machine learning and its potential for solving real-world problems.

  5. Applications of Machine Learning for Radiation Therapy.

    PubMed

    Arimura, Hidetaka; Nakamoto, Takahiro

    Radiation therapy has been highly advanced as image guided radiation therapy (IGRT) by making advantage of image engineering technologies. Recently, novel frameworks based on image engineering technologies as well as machine learning technologies have been studied for sophisticating the radiation therapy. In this review paper, the author introduces several researches of applications of machine learning for radiation therapy. For examples, a method to determine the threshold values for standardized uptake value (SUV) for estimation of gross tumor volume (GTV) in positron emission tomography (PET) images, an approach to estimate the multileaf collimator (MLC) position errors between treatment plans and radiation delivery time, and prediction frameworks for esophageal stenosis and radiation pneumonitis risk after radiation therapy are described. Finally, the author introduces seven issues that one should consider when applying machine learning models to radiation therapy.

  6. New Learning Method of a Lecture of ‘Machine Fabrication’ by Self-study with Investigation and Presentation Incorporated

    NASA Astrophysics Data System (ADS)

    Kasuga, Yukio

    A new teaching method was developed in learningmachine fabrication’ for the undergraduate students. This consists of a few times of lectures, grouping, decision of industrial products which each group wants to investigate, investigation work by library books and internet, arrangement of data containing characteristics of the products, employed materials and processing methods, presentation, discussions and revision followed by another presentation. This new method is derived from one of the Finland‧s way of primary school education. Their way of education is believed to have boosted up to the top ranking in PISA tests by OECD. After starting the new way of learning, students have fresh impressions on this lesson, especially for self-study, the way of investigation, collaborate work and presentation. Also, after four years of implementation, some improvements have been made including less use of internet, and determination of products and fabricating methods in advance which should be investigated. By this, students‧ lecture assessment shows further encouraging results.

  7. Machine Learning Methods to Predict Density Functional Theory B3LYP Energies of HOMO and LUMO Orbitals.

    PubMed

    Pereira, Florbela; Xiao, Kaixia; Latino, Diogo A R S; Wu, Chengcheng; Zhang, Qingyou; Aires-de-Sousa, Joao

    2017-01-23

    Machine learning algorithms were explored for the fast estimation of HOMO and LUMO orbital energies calculated by DFT B3LYP, on the basis of molecular descriptors exclusively based on connectivity. The whole project involved the retrieval and generation of molecular structures, quantum chemical calculations for a database with >111 000 structures, development of new molecular descriptors, and training/validation of machine learning models. Several machine learning algorithms were screened, and an applicability domain was defined based on Euclidean distances to the training set. Random forest models predicted an external test set of 9989 compounds achieving mean absolute error (MAE) up to 0.15 and 0.16 eV for the HOMO and LUMO orbitals, respectively. The impact of the quantum chemical calculation protocol was assessed with a subset of compounds. Inclusion of the orbital energy calculated by PM7 as an additional descriptor significantly improved the quality of estimations (reducing the MAE in >30%).

  8. New Theoretical Frameworks for Machine Learning

    DTIC Science & Technology

    2008-09-15

    is establishing new connections between Machine Learning and Algorithmic Game Theory. The formulation of the PAC learning model by Valiant [201] and...the Statistical Learning Theory framework by Vapnik [203] have been instrumental in the development of machine learning and the design and analysis of...theoretical results for Active Learning. Finally, this dissertation presents new applications of techniques from Machine Learning to Algorithmic Game

  9. Palate Shape and Depth: A Shape-Matching and Machine Learning Method for Estimating Ancestry from Human Skeletal Remains.

    PubMed

    Maier, Christopher A; Zhang, Kang; Manhein, Mary H; Li, Xin

    2015-09-01

    In the past, assessing ancestry relied on the naked eye and observer experience; however, replicability has become an important aspect of such analysis through the application of metric techniques. This study examines palate shape and assesses ancestry quantitatively using a 3D digitizer and shape-matching and machine learning methods. Palate curves and depths were recorded, processed, and tested for 376 individuals. Palate shape was an accurate indicator of ancestry in 58% of cases. Cluster analysis revealed that the parabolic, hyperbolic, and elliptical shapes are discrete from one another. Preliminary results indicate that palate depth in Hispanic individuals is greatest. Palate shape appears to be a useful indicator of ancestry, particularly when assessed by a computer. However, these data suggest that palate shape is not useful for assessing ancestry in Hispanic individuals. Although ancestry may be determined from palate shape, the use of multiple features is recommended and more reliable.

  10. Comparison between stochastic and machine learning methods for hydrological multi-step ahead forecasting: All forecasts are wrong!

    NASA Astrophysics Data System (ADS)

    Papacharalampous, Georgia; Tyralis, Hristos; Koutsoyiannis, Demetris

    2017-04-01

    Machine learning (ML) is considered to be a promising approach to hydrological processes forecasting. We conduct a comparison between several stochastic and ML point estimation methods by performing large-scale computational experiments based on simulations. The purpose is to provide generalized results, while the respective comparisons in the literature are usually based on case studies. The stochastic methods used include simple methods, models from the frequently used families of Autoregressive Moving Average (ARMA), Autoregressive Fractionally Integrated Moving Average (ARFIMA) and Exponential Smoothing models. The ML methods used are Random Forests (RF), Support Vector Machines (SVM) and Neural Networks (NN). The comparison refers to the multi-step ahead forecasting properties of the methods. A total of 20 methods are used, among which 9 are the ML methods. 12 simulation experiments are performed, while each of them uses 2 000 simulated time series of 310 observations. The time series are simulated using stochastic processes from the families of ARMA and ARFIMA models. Each time series is split into a fitting (first 300 observations) and a testing set (last 10 observations). The comparative assessment of the methods is based on 18 metrics, that quantify the methods' performance according to several criteria related to the accurate forecasting of the testing set, the capturing of its variation and the correlation between the testing and forecasted values. The most important outcome of this study is that there is not a uniformly better or worse method. However, there are methods that are regularly better or worse than others with respect to specific metrics. It appears that, although a general ranking of the methods is not possible, their classification based on their similar or contrasting performance in the various metrics is possible to some extent. Another important conclusion is that more sophisticated methods do not necessarily provide better forecasts

  11. An active role for machine learning in drug development

    PubMed Central

    Murphy, Robert F.

    2014-01-01

    Due to the complexity of biological systems, cutting-edge machine-learning methods will be critical for future drug development. In particular, machine-vision methods to extract detailed information from imaging assays and active-learning methods to guide experimentation will be required to overcome the dimensionality problem in drug development. PMID:21587249

  12. Walking speed estimation using foot-mounted inertial sensors: comparing machine learning and strap-down integration methods.

    PubMed

    Mannini, Andrea; Sabatini, Angelo Maria

    2014-10-01

    In this paper we implemented machine learning (ML) and strap-down integration (SDI) methods and analyzed them for their capability of estimating stride-by-stride walking speed. Walking speed was computed by dividing estimated stride length by stride time using data from a foot mounted inertial measurement unit. In SDI methods stride-by-stride walking speed estimation was driven by detecting gait events using a hidden Markov model (HMM) based method (HMM-based SDI); alternatively, a threshold-based gait event detector was investigated (threshold-based SDI). In the ML method a linear regression model was developed for stride length estimation. Whereas the gait event detectors were a priori fixed without training, the regression model was validated with leave-one-subject-out cross-validation. A subject-specific regression model calibration was also implemented to personalize the ML method. Healthy adults performed over-ground walking trials at natural, slower-than-natural and faster-than-natural speeds. The ML method achieved a root mean square estimation error of 2.0% and 4.2%, with and without personalization, against 2.0% and 3.1% by HMM-based SDI and threshold-based SDI. In spite that the results achieved by the two approaches were similar, the ML method, as compared with SDI methods, presented lower intra-subject variability and higher inter-subject variability, which was reduced by personalization. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

  13. Entanglement-Based Machine Learning on a Quantum Computer

    NASA Astrophysics Data System (ADS)

    Cai, X.-D.; Wu, D.; Su, Z.-E.; Chen, M.-C.; Wang, X.-L.; Li, Li; Liu, N.-L.; Lu, C.-Y.; Pan, J.-W.

    2015-03-01

    Machine learning, a branch of artificial intelligence, learns from previous experience to optimize performance, which is ubiquitous in various fields such as computer sciences, financial analysis, robotics, and bioinformatics. A challenge is that machine learning with the rapidly growing "big data" could become intractable for classical computers. Recently, quantum machine learning algorithms [Lloyd, Mohseni, and Rebentrost, arXiv.1307.0411] were proposed which could offer an exponential speedup over classical algorithms. Here, we report the first experimental entanglement-based classification of two-, four-, and eight-dimensional vectors to different clusters using a small-scale photonic quantum computer, which are then used to implement supervised and unsupervised machine learning. The results demonstrate the working principle of using quantum computers to manipulate and classify high-dimensional vectors, the core mathematical routine in machine learning. The method can, in principle, be scaled to larger numbers of qubits, and may provide a new route to accelerate machine learning.

  14. Entanglement-based machine learning on a quantum computer.

    PubMed

    Cai, X-D; Wu, D; Su, Z-E; Chen, M-C; Wang, X-L; Li, Li; Liu, N-L; Lu, C-Y; Pan, J-W

    2015-03-20

    Machine learning, a branch of artificial intelligence, learns from previous experience to optimize performance, which is ubiquitous in various fields such as computer sciences, financial analysis, robotics, and bioinformatics. A challenge is that machine learning with the rapidly growing "big data" could become intractable for classical computers. Recently, quantum machine learning algorithms [Lloyd, Mohseni, and Rebentrost, arXiv.1307.0411] were proposed which could offer an exponential speedup over classical algorithms. Here, we report the first experimental entanglement-based classification of two-, four-, and eight-dimensional vectors to different clusters using a small-scale photonic quantum computer, which are then used to implement supervised and unsupervised machine learning. The results demonstrate the working principle of using quantum computers to manipulate and classify high-dimensional vectors, the core mathematical routine in machine learning. The method can, in principle, be scaled to larger numbers of qubits, and may provide a new route to accelerate machine learning.

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

    ERIC Educational Resources Information Center

    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…

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

    ERIC Educational Resources Information Center

    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…

  17. Analysis of nanopore detector measurements using Machine-Learning methods, with application to single-molecule kinetic analysis

    PubMed Central

    Landry, Matthew; Winters-Hilt, Stephen

    2007-01-01

    Background A nanopore detector has a nanometer-scale trans-membrane channel across which a potential difference is established, resulting in an ionic current through the channel in the pA-nA range. A distinctive channel current blockade signal is created as individually "captured" DNA molecules interact with the channel and modulate the channel's ionic current. The nanopore detector is sensitive enough that nearly identical DNA molecules can be classified with very high accuracy using machine learning techniques such as Hidden Markov Models (HMMs) and Support Vector Machines (SVMs). Results A non-standard implementation of an HMM, emission inversion, is used for improved classification. Additional features are considered for the feature vector employed by the SVM for classification as well: The addition of a single feature representing spike density is shown to notably improve classification results. Another, much larger, feature set expansion was studied (2500 additional features instead of 1), deriving from including all the HMM's transition probabilities. The expanded features can introduce redundant, noisy information (as well as diagnostic information) into the current feature set, and thus degrade classification performance. A hybrid Adaptive Boosting approach was used for feature selection to alleviate this problem. Conclusion The methods shown here, for more informed feature extraction, improve both classification and provide biologists and chemists with tools for obtaining a better understanding of the kinetic properties of molecules of interest. PMID:18047711

  18. Vitrification: Machines learn to recognize glasses

    NASA Astrophysics Data System (ADS)

    Ceriotti, Michele; Vitelli, Vincenzo

    2016-05-01

    The dynamics of a viscous liquid undergo a dramatic slowdown when it is cooled to form a solid glass. Recognizing the structural changes across such a transition remains a major challenge. Machine-learning methods, similar to those Facebook uses to recognize groups of friends, have now been applied to this problem.

  19. A ternary classification using machine learning methods of distinct estrogen receptor activities within a large collection of environmental chemicals.

    PubMed

    Zhang, Quan; Yan, Lu; Wu, Yan; Ji, Li; Chen, Yuanchen; Zhao, Meirong; Dong, Xiaowu

    2017-02-15

    Endocrine-disrupting chemicals (EDCs), which can threaten ecological safety and be harmful to human beings, have been cause for wide concern. There is a high demand for efficient methodologies for evaluating potential EDCs in the environment. Herein an evaluation platform was developed using novel and statistically robust ternary models via different machine learning models (i.e., linear discriminant analysis, classification and regression tree, and support vector machines). The platform is aimed at effectively classifying chemicals with agonistic, antagonistic, or no estrogen receptor (ER) activities. A total of 440 chemicals from the literature were selected to derive and optimize the three-class model. One hundred and nine new chemicals appeared on the 2014 EPA list for EDC screening, which were used to assess the predictive performances by comparing the E-screen results with the predicted results of the classification models. The best model was obtained using support vector machines (SVM) which recognized agonists and antagonists with accuracies of 76.6% and 75.0%, respectively, on the test set (with an overall predictive accuracy of 75.2%), and achieved a 10-fold cross-validation (CV) of 73.4%. The external predicted accuracy validated by the E-screen assay was 87.5%, which demonstrated the application value for a virtual alert for EDCs with ER agonistic or antagonistic activities. It was demonstrated that the ternary computational model could be used as a faster and less expensive method to identify EDCs that act through nuclear receptors, and to classify these chemicals into different mechanism groups.

  20. Machine learning phases of matter

    NASA Astrophysics Data System (ADS)

    Carrasquilla, Juan; Stoudenmire, Miles; Melko, Roger

    We show how the technology that allows automatic teller machines read hand-written digits in cheques can be used to encode and recognize phases of matter and phase transitions in many-body systems. In particular, we analyze the (quasi-)order-disorder transitions in the classical Ising and XY models. Furthermore, we successfully use machine learning to study classical Z2 gauge theories that have important technological application in the coming wave of quantum information technologies and whose phase transitions have no conventional order parameter.

  1. Patient-centered yes/no prognosis using learning machines

    PubMed Central

    König, I.R.; Malley, J.D.; Pajevic, S.; Weimar, C.; Diener, H-C.

    2009-01-01

    In the last 15 years several machine learning approaches have been developed for classification and regression. In an intuitive manner we introduce the main ideas of classification and regression trees, support vector machines, bagging, boosting and random forests. We discuss differences in the use of machine learning in the biomedical community and the computer sciences. We propose methods for comparing machines on a sound statistical basis. Data from the German Stroke Study Collaboration is used for illustration. We compare the results from learning machines to those obtained by a published logistic regression and discuss similarities and differences. PMID:19216340

  2. Classifying smoking urges via machine learning.

    PubMed

    Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

    2016-12-01

    Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. Copyright © 2016 Elsevier Ireland Ltd. All rights

  3. Machine learning for neuroimaging with scikit-learn.

    PubMed

    Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

    2014-01-01

    Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.

  4. Machine learning for neuroimaging with scikit-learn

    PubMed Central

    Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

    2014-01-01

    Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain. PMID:24600388

  5. Learning Extended Finite State Machines

    NASA Technical Reports Server (NTRS)

    Cassel, Sofia; Howar, Falk; Jonsson, Bengt; Steffen, Bernhard

    2014-01-01

    We present an active learning algorithm for inferring extended finite state machines (EFSM)s, combining data flow and control behavior. Key to our learning technique is a novel learning model based on so-called tree queries. The learning algorithm uses the tree queries to infer symbolic data constraints on parameters, e.g., sequence numbers, time stamps, identifiers, or even simple arithmetic. We describe sufficient conditions for the properties that the symbolic constraints provided by a tree query in general must have to be usable in our learning model. We have evaluated our algorithm in a black-box scenario, where tree queries are realized through (black-box) testing. Our case studies include connection establishment in TCP and a priority queue from the Java Class Library.

  6. Machine learning methods predict locomotor response to MK-801 in mouse models of down syndrome.

    PubMed

    Nguyen, Cao D; Costa, Alberto C S; Cios, Krzysztof J; Gardiner, Katheleen J

    2011-03-01

    Down syndrome (DS), caused by trisomy of human chromosome 21 (HSA21), is a common genetic cause of cognitive impairment. This disorder results from the overexpression of HSA21 genes and the resulting perturbations in many molecular pathways and cellular processes. Knowledge-based identification of targets for pharmacotherapies will require defining the most critical protein abnormalities among these many perturbations. Here the authors show that using the Ts65Dn and Ts1Cje mouse models of DS, which are trisomic for 88 and 69 reference protein coding genes, respectively, a simple linear Naïve Bayes classifier successfully predicts behavioral outcome (level of locomotor activity) in response to treatment with the N-methyl-d-aspartate (NMDA) receptor antagonist MK-801. Input to the Naïve Bayes method were simple protein profiles generated from cortex and output was locomotor activity binned into three levels: low, medium, and high. When Feature Selection was used with the Naïve Bayes method, levels of three HSA21 and two non-HSA21 protein features were identified as making the most significant contributions to activity level. Using these five features, accuracies of up to 88% in prediction of locomotor activity were achieved. These predictions depend not only on genotype-specific differences but also on within-genotype individual variation in levels of molecular and behavioral parameters. With judicious choice of pathways and components, a similar approach may be useful in analysis of more complex behaviors, including those associated with learning and memory, and may facilitate identification of novel targets for pharmacotherapeutics.

  7. Identification of novel plant peroxisomal targeting signals by a combination of machine learning methods and in vivo subcellular targeting analyses.

    PubMed

    Lingner, Thomas; Kataya, Amr R; Antonicelli, Gerardo E; Benichou, Aline; Nilssen, Kjersti; Chen, Xiong-Yan; Siemsen, Tanja; Morgenstern, Burkhard; Meinicke, Peter; Reumann, Sigrun

    2011-04-01

    In the postgenomic era, accurate prediction tools are essential for identification of the proteomes of cell organelles. Prediction methods have been developed for peroxisome-targeted proteins in animals and fungi but are missing specifically for plants. For development of a predictor for plant proteins carrying peroxisome targeting signals type 1 (PTS1), we assembled more than 2500 homologous plant sequences, mainly from EST databases. We applied a discriminative machine learning approach to derive two different prediction methods, both of which showed high prediction accuracy and recognized specific targeting-enhancing patterns in the regions upstream of the PTS1 tripeptides. Upon application of these methods to the Arabidopsis thaliana genome, 392 gene models were predicted to be peroxisome targeted. These predictions were extensively tested in vivo, resulting in a high experimental verification rate of Arabidopsis proteins previously not known to be peroxisomal. The prediction methods were able to correctly infer novel PTS1 tripeptides, which even included novel residues. Twenty-three newly predicted PTS1 tripeptides were experimentally confirmed, and a high variability of the plant PTS1 motif was discovered. These prediction methods will be instrumental in identifying low-abundance and stress-inducible peroxisomal proteins and defining the entire peroxisomal proteome of Arabidopsis and agronomically important crop plants.

  8. Applying Sparse Machine Learning Methods to Twitter: Analysis of the 2012 Change in Pap Smear Guidelines. A Sequential Mixed-Methods Study

    PubMed Central

    Godbehere, Andrew; Le, Gem; El Ghaoui, Laurent; Sarkar, Urmimala

    2016-01-01

    Background It is difficult to synthesize the vast amount of textual data available from social media websites. Capturing real-world discussions via social media could provide insights into individuals’ opinions and the decision-making process. Objective We conducted a sequential mixed methods study to determine the utility of sparse machine learning techniques in summarizing Twitter dialogues. We chose a narrowly defined topic for this approach: cervical cancer discussions over a 6-month time period surrounding a change in Pap smear screening guidelines. Methods We applied statistical methodologies, known as sparse machine learning algorithms, to summarize Twitter messages about cervical cancer before and after the 2012 change in Pap smear screening guidelines by the US Preventive Services Task Force (USPSTF). All messages containing the search terms “cervical cancer,” “Pap smear,” and “Pap test” were analyzed during: (1) January 1–March 13, 2012, and (2) March 14–June 30, 2012. Topic modeling was used to discern the most common topics from each time period, and determine the singular value criterion for each topic. The results were then qualitatively coded from top 10 relevant topics to determine the efficiency of clustering method in grouping distinct ideas, and how the discussion differed before vs. after the change in guidelines . Results This machine learning method was effective in grouping the relevant discussion topics about cervical cancer during the respective time periods (~20% overall irrelevant content in both time periods). Qualitative analysis determined that a significant portion of the top discussion topics in the second time period directly reflected the USPSTF guideline change (eg, “New Screening Guidelines for Cervical Cancer”), and many topics in both time periods were addressing basic screening promotion and education (eg, “It is Cervical Cancer Awareness Month! Click the link to see where you can receive a free or low

  9. Learning Machine Learning: A Case Study

    ERIC Educational Resources Information Center

    Lavesson, N.

    2010-01-01

    This correspondence reports on a case study conducted in the Master's-level Machine Learning (ML) course at Blekinge Institute of Technology, Sweden. The students participated in a self-assessment test and a diagnostic test of prerequisite subjects, and their results on these tests are correlated with their achievement of the course's learning…

  10. Learning Machine Learning: A Case Study

    ERIC Educational Resources Information Center

    Lavesson, N.

    2010-01-01

    This correspondence reports on a case study conducted in the Master's-level Machine Learning (ML) course at Blekinge Institute of Technology, Sweden. The students participated in a self-assessment test and a diagnostic test of prerequisite subjects, and their results on these tests are correlated with their achievement of the course's learning…

  11. The Higgs Machine Learning Challenge

    NASA Astrophysics Data System (ADS)

    Adam-Bourdarios, C.; Cowan, G.; Germain-Renaud, C.; Guyon, I.; Kégl, B.; Rousseau, D.

    2015-12-01

    The Higgs Machine Learning Challenge was an open data analysis competition that took place between May and September 2014. Samples of simulated data from the ATLAS Experiment at the LHC corresponding to signal events with Higgs bosons decaying to τ+τ- together with background events were made available to the public through the website of the data science organization Kaggle (kaggle.com). Participants attempted to identify the search region in a space of 30 kinematic variables that would maximize the expected discovery significance of the signal process. One of the primary goals of the Challenge was to promote communication of new ideas between the Machine Learning (ML) and HEP communities. In this regard it was a resounding success, with almost 2,000 participants from HEP, ML and other areas. The process of understanding and integrating the new ideas, particularly from ML into HEP, is currently underway.

  12. Applying Sparse Machine Learning Methods to Twitter: Analysis of the 2012 Change in Pap Smear Guidelines. A Sequential Mixed-Methods Study.

    PubMed

    Lyles, Courtney Rees; Godbehere, Andrew; Le, Gem; El Ghaoui, Laurent; Sarkar, Urmimala

    2016-06-10

    It is difficult to synthesize the vast amount of textual data available from social media websites. Capturing real-world discussions via social media could provide insights into individuals' opinions and the decision-making process. We conducted a sequential mixed methods study to determine the utility of sparse machine learning techniques in summarizing Twitter dialogues. We chose a narrowly defined topic for this approach: cervical cancer discussions over a 6-month time period surrounding a change in Pap smear screening guidelines. We applied statistical methodologies, known as sparse machine learning algorithms, to summarize Twitter messages about cervical cancer before and after the 2012 change in Pap smear screening guidelines by the US Preventive Services Task Force (USPSTF). All messages containing the search terms "cervical cancer," "Pap smear," and "Pap test" were analyzed during: (1) January 1-March 13, 2012, and (2) March 14-June 30, 2012. Topic modeling was used to discern the most common topics from each time period, and determine the singular value criterion for each topic. The results were then qualitatively coded from top 10 relevant topics to determine the efficiency of clustering method in grouping distinct ideas, and how the discussion differed before vs. after the change in guidelines . This machine learning method was effective in grouping the relevant discussion topics about cervical cancer during the respective time periods (~20% overall irrelevant content in both time periods). Qualitative analysis determined that a significant portion of the top discussion topics in the second time period directly reflected the USPSTF guideline change (eg, "New Screening Guidelines for Cervical Cancer"), and many topics in both time periods were addressing basic screening promotion and education (eg, "It is Cervical Cancer Awareness Month! Click the link to see where you can receive a free or low cost Pap test.") It was demonstrated that machine learning

  13. Machine learning methods applied to pharmacokinetic modelling of remifentanil in healthy volunteers: a multi-method comparison.

    PubMed

    Poynton, M R; Choi, B M; Kim, Y M; Park, I S; Noh, G J; Hong, S O; Boo, Y K; Kang, S H

    2009-01-01

    This study compared the blood concentrations of remifentanil obtained in a previous clinical investigation with the predicted remifentanil concentrations produced by different pharmacokinetic models: a non-linear mixed effects model created by the software NONMEM; an artificial neural network (ANN) model; a support vector machine (SVM) model; and multi-method ensembles. The ensemble created from the mean of the ANN and the non-linear mixed effects model predictions achieved the smallest error and the highest correlation coefficient. The SVM model produced the highest error and the lowest correlation coefficient. Paired t-tests indicated that there was insufficient evidence that the predicted values of the ANN, SVM and two multi-method ensembles differed from the actual measured values at alpha = 0.05. The ensemble method combining the ANN and non-linear mixed effects model predictions outperformed either method alone. These results indicated a potential advantage of ensembles in improving the accuracy and reducing the variance of pharmacokinetic models.

  14. Galaxy Classification using Machine Learning

    NASA Astrophysics Data System (ADS)

    Fowler, Lucas; Schawinski, Kevin; Brandt, Ben-Elias; widmer, Nicole

    2017-01-01

    We present our current research into the use of machine learning to classify galaxy imaging data with various convolutional neural network configurations in TensorFlow. We are investigating how five-band Sloan Digital Sky Survey imaging data can be used to train on physical properties such as redshift, star formation rate, mass and morphology. We also investigate the performance of artificially redshifted images in recovering physical properties as image quality degrades.

  15. Potential of new machine learning methods for understanding long-term interannual variability of carbon and energy fluxes and states from site to global scale

    NASA Astrophysics Data System (ADS)

    Reichstein, M.; Jung, M.; Bodesheim, P.; Mahecha, M. D.; Gans, F.; Rodner, E.; Camps-Valls, G.; Papale, D.; Tramontana, G.; Denzler, J.; Baldocchi, D. D.

    2016-12-01

    Machine learning tools have been very successful in describing and predicting instantaneous climatic influences on the spatial and seasonal variability of biosphere-atmosphere exchange, while interannual variability is harder to model (e.g. Jung et al. 2011, JGR Biogeosciences). Here we hypothesize that innterannual variability is harder to describe for two reasons. 1) The signal-to-noise ratio in both, predictors (e.g. remote sensing) and target variables (e.g. net ecosystem exchange) is relatively weak, 2) The employed machine learning methods do not sufficiently account for dynamic lag and carry-over effects. In this presentation we can largely confirm both hypotheses: 1) We show that based on FLUXNET data and an ensemble of machine learning methods we can arrive at estimates of global NEE that correlate well with the residual land sink overall and CO2 flux inversions over latitudinal bands. Furthermore these results highlight the importance of variations in water availability for variations in carbon fluxes locally, while globally, as a scale-emergent property, tropical temperatures correlate well with the atmospheric CO2 growth rate, because of spatial anticorrelation and compensation of water availability. 2) We evidence with synthetic and real data that machine learning methods with embed dynamic memory effects of the system such as recurrent neural networks (RNNs) are able to better capture lag and carry-over effect which are caused by dynamic carbon pools in vegetation and soils. For these methods, long-term replicate observations are an essential asset.

  16. Fast, Continuous Audiogram Estimation Using Machine Learning.

    PubMed

    Song, Xinyu D; Wallace, Brittany M; Gardner, Jacob R; Ledbetter, Noah M; Weinberger, Kilian Q; Barbour, Dennis L

    2015-01-01

    Pure-tone audiometry has been a staple of hearing assessments for decades. Many different procedures have been proposed for measuring thresholds with pure tones by systematically manipulating intensity one frequency at a time until a discrete threshold function is determined. The authors have developed a novel nonparametric approach for estimating a continuous threshold audiogram using Bayesian estimation and machine learning classification. The objective of this study was to assess the accuracy and reliability of this new method relative to a commonly used threshold measurement technique. The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 18 and 90 years with varying degrees of hearing ability. Two repetitions of automated machine learning audiogram estimation and one repetition of conventional modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). The two threshold estimate methods delivered very similar estimates at standard audiogram frequencies. Specifically, the mean absolute difference between estimates was 4.16 ± 3.76 dB HL. The mean absolute difference between repeated measurements of the new machine learning procedure was 4.51 ± 4.45 dB HL. These values compare favorably with those of other threshold audiogram estimation procedures. Furthermore, the machine learning method generated threshold estimates from significantly fewer samples than the modified Hughson-Westlake procedure while returning a continuous threshold estimate as a function of frequency. The new machine learning audiogram estimation technique produces continuous threshold audiogram estimates accurately, reliably, and efficiently, making it a strong candidate for widespread application in clinical and research audiometry.

  17. Fast, Continuous Audiogram Estimation using Machine Learning

    PubMed Central

    Song, Xinyu D.; Wallace, Brittany M.; Gardner, Jacob R.; Ledbetter, Noah M.; Weinberger, Kilian Q.; Barbour, Dennis L.

    2016-01-01

    Objectives Pure-tone audiometry has been a staple of hearing assessments for decades. Many different procedures have been proposed for measuring thresholds with pure tones by systematically manipulating intensity one frequency at a time until a discrete threshold function is determined. The authors have developed a novel nonparametric approach for estimating a continuous threshold audiogram using Bayesian estimation and machine learning classification. The objective of this study is to assess the accuracy and reliability of this new method relative to a commonly used threshold measurement technique. Design The authors performed air conduction pure-tone audiometry on 21 participants between the ages of 18 and 90 years with varying degrees of hearing ability. Two repetitions of automated machine learning audiogram estimation and 1 repetition of conventional modified Hughson-Westlake ascending-descending audiogram estimation were acquired by an audiologist. The estimated hearing thresholds of these two techniques were compared at standard audiogram frequencies (i.e., 0.25, 0.5, 1, 2, 4, 8 kHz). Results The two threshold estimate methods delivered very similar estimates at standard audiogram frequencies. Specifically, the mean absolute difference between estimates was 4.16 ± 3.76 dB HL. The mean absolute difference between repeated measurements of the new machine learning procedure was 4.51 ± 4.45 dB HL. These values compare favorably to those of other threshold audiogram estimation procedures. Furthermore, the machine learning method generated threshold estimates from significantly fewer samples than the modified Hughson-Westlake procedure while returning a continuous threshold estimate as a function of frequency. Conclusions The new machine learning audiogram estimation technique produces continuous threshold audiogram estimates accurately, reliably, and efficiently, making it a strong candidate for widespread application in clinical and research audiometry. PMID

  18. Machine Learning in Intrusion Detection

    DTIC Science & Technology

    2005-07-01

    machine learning tasks. Anomaly detection provides the core technology for a broad spectrum of security-centric applications. In this dissertation, we examine various aspects of anomaly based intrusion detection in computer security. First, we present a new approach to learn program behavior for intrusion detection. Text categorization techniques are adopted to convert each process to a vector and calculate the similarity between two program activities. Then the k-nearest neighbor classifier is employed to classify program behavior as normal or intrusive. We demonstrate

  19. In silico prediction of spleen tyrosine kinase inhibitors using machine learning approaches and an optimized molecular descriptor subset generated by recursive feature elimination method.

    PubMed

    Li, Bing-Ke; Cong, Yong; Yang, Xue-Gang; Xue, Ying; Chen, Yi-Zong

    2013-05-01

    We tested four machine learning methods, support vector machine (SVM), k-nearest neighbor, back-propagation neural network and C4.5 decision tree for their capability in predicting spleen tyrosine kinase (Syk) inhibitors by using 2592 compounds which are more diverse than those in other studies. The recursive feature elimination method was used for improving prediction performance and selecting molecular descriptors responsible for distinguishing Syk inhibitors and non-inhibitors. Among four machine learning models, SVM produces the best performance at 99.18% for inhibitors and 98.82% for non-inhibitors, respectively, indicating that the SVM is potentially useful for facilitating the discovery of Syk inhibitors. Copyright © 2013 Elsevier Ltd. All rights reserved.

  20. Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning.

    PubMed

    Yang, Yimin; Wu, Q M Jonathan

    2015-10-09

    The extreme learning machine (ELM), which was originally proposed for ''generalized'' single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.

  1. Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning.

    PubMed

    Yang, Yimin; Wu, Q M Jonathan

    2016-11-01

    The extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.

  2. A machine learning method for identifying morphological patterns in reflectance confocal microscopy mosaics of melanocytic skin lesions in-vivo

    NASA Astrophysics Data System (ADS)

    Kose, Kivanc; Alessi-Fox, Christi; Gill, Melissa; Dy, Jennifer G.; Brooks, Dana H.; Rajadhyaksha, Milind

    2016-02-01

    We present a machine learning algorithm that can imitate the clinicians qualitative and visual process of analyzing reflectance confocal microscopy (RCM) mosaics at the dermal epidermal junction (DEJ) of skin. We divide the mosaics into localized areas of processing, and capture the textural appearance of each area using dense Speeded Up Robust Feature (SURF). Using these features, we train a support vector machine (SVM) classifier that can distinguish between meshwork, ring, clod, aspecific and background patterns in benign conditions and melanomas. Preliminary results on 20 RCM mosaics labeled by expert readers show classification with 55 - 81% sensitivity and 81 - 89% specificity in distinguishing these patterns.

  3. Fast linear algorithms for machine learning

    NASA Astrophysics Data System (ADS)

    Lu, Yichao

    Nowadays linear methods like Regression, Principal Component Analysis and Canonical Correlation Analysis are well understood and widely used by the machine learning community for predictive modeling and feature generation. Generally speaking, all these methods aim at capturing interesting subspaces in the original high dimensional feature space. Due to the simple linear structures, these methods all have a closed form solution which makes computation and theoretical analysis very easy for small datasets. However, in modern machine learning problems it's very common for a dataset to have millions or billions of features and samples. In these cases, pursuing the closed form solution for these linear methods can be extremely slow since it requires multiplying two huge matrices and computing inverse, inverse square root, QR decomposition or Singular Value Decomposition (SVD) of huge matrices. In this thesis, we consider three fast algorithms for computing Regression and Canonical Correlation Analysis approximate for huge datasets.

  4. Machine learning for autonomous crystal structure identification.

    PubMed

    Reinhart, Wesley F; Long, Andrew W; Howard, Michael P; Ferguson, Andrew L; Panagiotopoulos, Athanassios Z

    2017-07-21

    We present a machine learning technique to discover and distinguish relevant ordered structures from molecular simulation snapshots or particle tracking data. Unlike other popular methods for structural identification, our technique requires no a priori description of the target structures. Instead, we use nonlinear manifold learning to infer structural relationships between particles according to the topology of their local environment. This graph-based approach yields unbiased structural information which allows us to quantify the crystalline character of particles near defects, grain boundaries, and interfaces. We demonstrate the method by classifying particles in a simulation of colloidal crystallization, and show that our method identifies structural features that are missed by standard techniques.

  5. Accurate prediction of polarised high order electrostatic interactions for hydrogen bonded complexes using the machine learning method kriging

    NASA Astrophysics Data System (ADS)

    Hughes, Timothy J.; Kandathil, Shaun M.; Popelier, Paul L. A.

    2015-02-01

    As intermolecular interactions such as the hydrogen bond are electrostatic in origin, rigorous treatment of this term within force field methodologies should be mandatory. We present a method able of accurately reproducing such interactions for seven van der Waals complexes. It uses atomic multipole moments up to hexadecupole moment mapped to the positions of the nuclear coordinates by the machine learning method kriging. Models were built at three levels of theory: HF/6-31G**, B3LYP/aug-cc-pVDZ and M06-2X/aug-cc-pVDZ. The quality of the kriging models was measured by their ability to predict the electrostatic interaction energy between atoms in external test examples for which the true energies are known. At all levels of theory, >90% of test cases for small van der Waals complexes were predicted within 1 kJ mol-1, decreasing to 60-70% of test cases for larger base pair complexes. Models built on moments obtained at B3LYP and M06-2X level generally outperformed those at HF level. For all systems the individual interactions were predicted with a mean unsigned error of less than 1 kJ mol-1.

  6. Accurate prediction of polarised high order electrostatic interactions for hydrogen bonded complexes using the machine learning method kriging.

    PubMed

    Hughes, Timothy J; Kandathil, Shaun M; Popelier, Paul L A

    2015-02-05

    As intermolecular interactions such as the hydrogen bond are electrostatic in origin, rigorous treatment of this term within force field methodologies should be mandatory. We present a method able of accurately reproducing such interactions for seven van der Waals complexes. It uses atomic multipole moments up to hexadecupole moment mapped to the positions of the nuclear coordinates by the machine learning method kriging. Models were built at three levels of theory: HF/6-31G(**), B3LYP/aug-cc-pVDZ and M06-2X/aug-cc-pVDZ. The quality of the kriging models was measured by their ability to predict the electrostatic interaction energy between atoms in external test examples for which the true energies are known. At all levels of theory, >90% of test cases for small van der Waals complexes were predicted within 1 kJ mol(-1), decreasing to 60-70% of test cases for larger base pair complexes. Models built on moments obtained at B3LYP and M06-2X level generally outperformed those at HF level. For all systems the individual interactions were predicted with a mean unsigned error of less than 1 kJ mol(-1).

  7. Combining an Expert-Based Medical Entity Recognizer to a Machine-Learning System: Methods and a Case Study

    PubMed Central

    Zweigenbaum, Pierre; Lavergne, Thomas; Grabar, Natalia; Hamon, Thierry; Rosset, Sophie; Grouin, Cyril

    2013-01-01

    Medical entity recognition is currently generally performed by data-driven methods based on supervised machine learning. Expert-based systems, where linguistic and domain expertise are directly provided to the system are often combined with data-driven systems. We present here a case study where an existing expert-based medical entity recognition system, Ogmios, is combined with a data-driven system, Caramba, based on a linear-chain Conditional Random Field (CRF) classifier. Our case study specifically highlights the risk of overfitting incurred by an expert-based system. We observe that it prevents the combination of the 2 systems from obtaining improvements in precision, recall, or F-measure, and analyze the underlying mechanisms through a post-hoc feature-level analysis. Wrapping the expert-based system alone as attributes input to a CRF classifier does boost its F-measure from 0.603 to 0.710, bringing it on par with the data-driven system. The generalization of this method remains to be further investigated. PMID:24052691

  8. Stochastic weather inputs for improved urban water demand forecasting: application of nonlinear input variable selection and machine learning methods

    NASA Astrophysics Data System (ADS)

    Quilty, J.; Adamowski, J. F.

    2015-12-01

    Urban water supply systems are often stressed during seasonal outdoor water use as water demands related to the climate are variable in nature making it difficult to optimize the operation of the water supply system. Urban water demand forecasts (UWD) failing to include meteorological conditions as inputs to the forecast model may produce poor forecasts as they cannot account for the increase/decrease in demand related to meteorological conditions. Meteorological records stochastically simulated into the future can be used as inputs to data-driven UWD forecasts generally resulting in improved forecast accuracy. This study aims to produce data-driven UWD forecasts for two different Canadian water utilities (Montreal and Victoria) using machine learning methods by first selecting historical UWD and meteorological records derived from a stochastic weather generator using nonlinear input variable selection. The nonlinear input variable selection methods considered in this work are derived from the concept of conditional mutual information, a nonlinear dependency measure based on (multivariate) probability density functions and accounts for relevancy, conditional relevancy, and redundancy from a potential set of input variables. The results of our study indicate that stochastic weather inputs can improve UWD forecast accuracy for the two sites considered in this work. Nonlinear input variable selection is suggested as a means to identify which meteorological conditions should be utilized in the forecast.

  9. Preliminary study on wilcoxon learning machines.

    PubMed

    Hsieh, J G; Lin, Y L; Jeng, J H

    2008-02-01

    As is well known in statistics, the resulting linear regressors by using the rank-based Wilcoxon approach to linear regression problems are usually robust against (or insensitive to) outliers. This motivates us to introduce in this paper the Wilcoxon approach to the area of machine learning. Specifically, we investigate four new learning machines, namely Wilcoxon neural network (WNN), Wilcoxon generalized radial basis function network (WGRBFN), Wilcoxon fuzzy neural network (WFNN), and kernel-based Wilcoxon regressor (KWR). These provide alternative learning machines when faced with general nonlinear learning problems. Simple weights updating rules based on gradient descent will be derived. Some numerical examples will be provided to compare the robustness against outliers for various learning machines. Simulation results show that the Wilcoxon learning machines proposed in this paper have good robustness against outliers. We firmly believe that the Wilcoxon approach will provide a promising methodology for many machine learning problems.

  10. ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction.

    PubMed

    Hajiloo, Mohsen; Sapkota, Yadav; Mackey, John R; Robson, Paula; Greiner, Russell; Damaraju, Sambasivarao

    2013-02-22

    Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case-control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual's continental and sub-continental ancestry. To predict an individual's continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control's λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3

  11. ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction

    PubMed Central

    2013-01-01

    Background Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case–control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. Results We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual’s continental and sub-continental ancestry. To predict an individual’s continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control’s λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of

  12. Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods

    DOE PAGES

    Kolb, Brian; Lentz, Levi C.; Kolpak, Alexie M.

    2017-04-26

    Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. Themore » result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. Here, this work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet’s ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.« less

  13. Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods.

    PubMed

    Kolb, Brian; Lentz, Levi C; Kolpak, Alexie M

    2017-04-26

    Modern ab initio methods have rapidly increased our understanding of solid state materials properties, chemical reactions, and the quantum interactions between atoms. However, poor scaling often renders direct ab initio calculations intractable for large or complex systems. There are two obvious avenues through which to remedy this problem: (i) develop new, less expensive methods to calculate system properties, or (ii) make existing methods faster. This paper describes an open source framework designed to pursue both of these avenues. PROPhet (short for PROPerty Prophet) utilizes machine learning techniques to find complex, non-linear mappings between sets of material or system properties. The result is a single code capable of learning analytical potentials, non-linear density functionals, and other structure-property or property-property relationships. These capabilities enable highly accurate mesoscopic simulations, facilitate computation of expensive properties, and enable the development of predictive models for systematic materials design and optimization. This work explores the coupling of machine learning to ab initio methods through means both familiar (e.g., the creation of various potentials and energy functionals) and less familiar (e.g., the creation of density functionals for arbitrary properties), serving both to demonstrate PROPhet's ability to create exciting post-processing analysis tools and to open the door to improving ab initio methods themselves with these powerful machine learning techniques.

  14. Machine learning in computational docking.

    PubMed

    Khamis, Mohamed A; Gomaa, Walid; Ahmed, Walaa F

    2015-03-01

    The objective of this paper is to highlight the state-of-the-art machine learning (ML) techniques in computational docking. The use of smart computational methods in the life cycle of drug design is relatively a recent development that has gained much popularity and interest over the last few years. Central to this methodology is the notion of computational docking which is the process of predicting the best pose (orientation + conformation) of a small molecule (drug candidate) when bound to a target larger receptor molecule (protein) in order to form a stable complex molecule. In computational docking, a large number of binding poses are evaluated and ranked using a scoring function. The scoring function is a mathematical predictive model that produces a score that represents the binding free energy, and hence the stability, of the resulting complex molecule. Generally, such a function should produce a set of plausible ligands ranked according to their binding stability along with their binding poses. In more practical terms, an effective scoring function should produce promising drug candidates which can then be synthesized and physically screened using high throughput screening process. Therefore, the key to computer-aided drug design is the design of an efficient highly accurate scoring function (using ML techniques). The methods presented in this paper are specifically based on ML techniques. Despite many traditional techniques have been proposed, the performance was generally poor. Only in the last few years started the application of the ML technology in the design of scoring functions; and the results have been very promising. The ML-based techniques are based on various molecular features extracted from the abundance of protein-ligand information in the public molecular databases, e.g., protein data bank bind (PDBbind). In this paper, we present this paradigm shift elaborating on the main constituent elements of the ML approach to molecular docking along

  15. Food category consumption and obesity prevalence across countries: an application of Machine Learning method to big data analysis

    NASA Astrophysics Data System (ADS)

    Dunstan, Jocelyn; Fallah-Fini, Saeideh; Nau, Claudia; Glass, Thomas; Global Obesity Prevention Center Team

    The applications of sophisticated mathematical and numerical tools in public health has been demonstrated to be useful in predicting the outcome of public intervention as well as to study, for example, the main causes of obesity without doing experiments with the population. In this project we aim to understand which kind of food consumed in different countries over time best defines the rate of obesity in those countries. The use of Machine Learning is particularly useful because we do not need to create a hypothesis and test it with the data, but instead we learn from the data to find the groups of food that best describe the prevalence of obesity.

  16. Source localization in an ocean waveguide using supervised machine learning

    NASA Astrophysics Data System (ADS)

    Niu, Haiqiang; Reeves, Emma; Gerstoft, Peter

    2017-09-01

    Source localization in ocean acoustics is posed as a machine learning problem in which data-driven methods learn source ranges directly from observed acoustic data. The pressure received by a vertical linear array is preprocessed by constructing a normalized sample covariance matrix (SCM) and used as the input. Three machine learning methods (feed-forward neural networks (FNN), support vector machines (SVM) and random forests (RF)) are investigated in this paper, with focus on the FNN. The range estimation problem is solved both as a classification problem and as a regression problem by these three machine learning algorithms. The results of range estimation for the Noise09 experiment are compared for FNN, SVM, RF and conventional matched-field processing and demonstrate the potential of machine learning for underwater source localization..

  17. Visual human+machine learning.

    PubMed

    Fuchs, Raphael; Waser, Jürgen; Gröller, Meister Eduard

    2009-01-01

    In this paper we describe a novel method to integrate interactive visual analysis and machine learning to support the insight generation of the user. The suggested approach combines the vast search and processing power of the computer with the superior reasoning and pattern recognition capabilities of the human user. An evolutionary search algorithm has been adapted to assist in the fuzzy logic formalization of hypotheses that aim at explaining features inside multivariate, volumetric data. Up to now, users solely rely on their knowledge and expertise when looking for explanatory theories. However, it often remains unclear whether the selected attribute ranges represent the real explanation for the feature of interest. Other selections hidden in the large number of data variables could potentially lead to similar features. Moreover, as simulation complexity grows, users are confronted with huge multidimensional data sets making it almost impossible to find meaningful hypotheses at all. We propose an interactive cycle of knowledge-based analysis and automatic hypothesis generation. Starting from initial hypotheses, created with linking and brushing, the user steers a heuristic search algorithm to look for alternative or related hypotheses. The results are analyzed in information visualization views that are linked to the volume rendering. Individual properties as well as global aggregates are visually presented to provide insight into the most relevant aspects of the generated hypotheses. This novel approach becomes computationally feasible due to a GPU implementation of the time-critical parts in the algorithm. A thorough evaluation of search times and noise sensitivity as well as a case study on data from the automotive domain substantiate the usefulness of the suggested approach.

  18. Scaling up: Distributed machine learning with cooperation

    SciTech Connect

    Provost, F.J.; Hennessy, D.N.

    1996-12-31

    Machine-learning methods are becoming increasingly popular for automated data analysis. However, standard methods do not scale up to massive scientific and business data sets without expensive hardware. This paper investigates a practical alternative for scaling up: the use of distributed processing to take advantage of the often dormant PCs and workstations available on local networks. Each workstation runs a common rule-learning program on a subset of the data. We first show that for commonly used rule-evaluation criteria, a simple form of cooperation can guarantee that a rule will look good to the set of cooperating learners if and only if it would look good to a single learner operating with the entire data set. We then show how such a system can further capitalize on different perspectives by sharing learned knowledge for significant reduction in search effort. We demonstrate the power of the method by learning from a massive data set taken from the domain of cellular fraud detection. Finally, we provide an overview of other methods for scaling up machine learning.

  19. Introducing Machine Learning Concepts with WEKA.

    PubMed

    Smith, Tony C; Frank, Eibe

    2016-01-01

    This chapter presents an introduction to data mining with machine learning. It gives an overview of various types of machine learning, along with some examples. It explains how to download, install, and run the WEKA data mining toolkit on a simple data set, then proceeds to explain how one might approach a bioinformatics problem. Finally, it includes a brief summary of machine learning algorithms for other types of data mining problems, and provides suggestions about where to find additional information.

  20. WebWatcher: Machine Learning and Hypertext

    DTIC Science & Technology

    1995-05-29

    WebWatcher: Machine Learning and Hypertext Thorsten Joachims, Tom Mitchell, Dayne Freitag, and Robert Armstrong School of Computer Science Carnegie...HTML-page about machine learning in which we in- serted a hyperlink to WebWatcher (line 6). The user follows this hyperlink and gets to a page which...AND SUBTITLE WebWatcher: Machine Learning and Hypertext 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT

  1. Machine learning in genetics and genomics

    PubMed Central

    Libbrecht, Maxwell W.; Noble, William Stafford

    2016-01-01

    The field of machine learning promises to enable computers to assist humans in making sense of large, complex data sets. In this review, we outline some of the main applications of machine learning to genetic and genomic data. In the process, we identify some recurrent challenges associated with this type of analysis and provide general guidelines to assist in the practical application of machine learning to real genetic and genomic data. PMID:25948244

  2. Automatic diagnosis of melanoma using machine learning methods on a spectroscopic system.

    PubMed

    Li, Lin; Zhang, Qizhi; Ding, Yihua; Jiang, Huabei; Thiers, Bruce H; Wang, James Z

    2014-10-13

    Early and accurate diagnosis of melanoma, the deadliest type of skin cancer, has the potential to reduce morbidity and mortality rate. However, early diagnosis of melanoma is not trivial even for experienced dermatologists, as it needs sampling and laboratory tests which can be extremely complex and subjective. The accuracy of clinical diagnosis of melanoma is also an issue especially in distinguishing between melanoma and mole. To solve these problems, this paper presents an approach that makes non-subjective judgements based on quantitative measures for automatic diagnosis of melanoma. Our approach involves image acquisition, image processing, feature extraction, and classification. 187 images (19 malignant melanoma and 168 benign lesions) were collected in a clinic by a spectroscopic device that combines single-scattered, polarized light spectroscopy with multiple-scattered, un-polarized light spectroscopy. After noise reduction and image normalization, features were extracted based on statistical measurements (i.e. mean, standard deviation, mean absolute deviation, L1 norm, and L2 norm) of image pixel intensities to characterize the pattern of melanoma. Finally, these features were fed into certain classifiers to train learning models for classification. We adopted three classifiers - artificial neural network, naïve bayes, and k-nearest neighbour to evaluate our approach separately. The naive bayes classifier achieved the best performance - 89% accuracy, 89% sensitivity and 89% specificity, which was integrated with our approach in a desktop application running on the spectroscopic system for diagnosis of melanoma. Our work has two strengths. (1) We have used single scattered polarized light spectroscopy and multiple scattered unpolarized light spectroscopy to decipher the multilayered characteristics of human skin. (2) Our approach does not need image segmentation, as we directly probe tiny spots in the lesion skin and the image scans do not involve

  3. Quantum Machine Learning over Infinite Dimensions.

    PubMed

    Lau, Hoi-Kwan; Pooser, Raphael; Siopsis, George; Weedbrook, Christian

    2017-02-24

    Machine learning is a fascinating and exciting field within computer science. Recently, this excitement has been transferred to the quantum information realm. Currently, all proposals for the quantum version of machine learning utilize the finite-dimensional substrate of discrete variables. Here we generalize quantum machine learning to the more complex, but still remarkably practical, infinite-dimensional systems. We present the critical subroutines of quantum machine learning algorithms for an all-photonic continuous-variable quantum computer that can lead to exponential speedups in situations where classical algorithms scale polynomially. Finally, we also map out an experimental implementation which can be used as a blueprint for future photonic demonstrations.

  4. Quantum Machine Learning over Infinite Dimensions

    NASA Astrophysics Data System (ADS)

    Lau, Hoi-Kwan; Pooser, Raphael; Siopsis, George; Weedbrook, Christian

    2017-02-01

    Machine learning is a fascinating and exciting field within computer science. Recently, this excitement has been transferred to the quantum information realm. Currently, all proposals for the quantum version of machine learning utilize the finite-dimensional substrate of discrete variables. Here we generalize quantum machine learning to the more complex, but still remarkably practical, infinite-dimensional systems. We present the critical subroutines of quantum machine learning algorithms for an all-photonic continuous-variable quantum computer that can lead to exponential speedups in situations where classical algorithms scale polynomially. Finally, we also map out an experimental implementation which can be used as a blueprint for future photonic demonstrations.

  5. Harnessing the power of big data: infusing the scientific method with machine learning to transform ecology

    USDA-ARS?s Scientific Manuscript database

    Most efforts to harness the power of big data for ecology and environmental sciences focus on data and metadata sharing, standardization, and accuracy. However, many scientists have not accepted the data deluge as an integral part of their research because the current scientific method is not scalab...

  6. Machine Learning Methods for the Understanding and Prediction of Climate Systems: Tropical Pacific Ocean Thermocline and ENSO events

    NASA Astrophysics Data System (ADS)

    Lima, C. H.; Lall, U.

    2012-12-01

    In this work we explore recently developed methods from the machine learning community for dimensionality reduction and model selection of very large datasets. We apply the nonlinear maximum variance unfolding (MVU) method to find a short dimensional space for the thermocline of the Tropical Pacific Ocean as indicated by the ocean depth of the 200C isotherm from the NOAA/NCEP GODAS dataset. The leading modes are then used as covariates in an ENSO forecast model based on LASSO regression, where parameters are shrunk in order to find the best subset of predictors. A comparison with Principal Component Analysis (PCA) reveals that MVU is able to reduce the thermocline data from 21009 dimensions to three main components that collectively explain 77% of the system variance, whereas the first three PCs respond to 47% of the variance only. The series of the first three leading MVU and PCA based modes and their associated spatial patterns show also different features, including an enhanced monotonic upward trend in the first MVU mode that is hardly detected in the correspondent first PCA mode. Correlation analysis between the MVU components and the NINO3 index shows that each of the modes has peak correlations across different lag times, with statistically significant correlation coefficients up to two years. After combining the three MVU components across several lag times, a forecast model for NINO3 based on LASSO regression was built and tested using the ten-fold cross-validation method. Based on metrics such as the RMSE and correlation scores, the results show appreciable skills for lead times that go beyond ten months, particularly for the December NINO3, which is responsible for several floods and droughts across the globe.; Spatial signature of the first MVU mode. ; First MVU series featuring the upward trend.

  7. Graph Embedded Extreme Learning Machine.

    PubMed

    Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis

    2016-01-01

    In this paper, we propose a novel extension of the extreme learning machine (ELM) algorithm for single-hidden layer feedforward neural network training that is able to incorporate subspace learning (SL) criteria on the optimization process followed for the calculation of the network's output weights. The proposed graph embedded ELM (GEELM) algorithm is able to naturally exploit both intrinsic and penalty SL criteria that have been (or will be) designed under the graph embedding framework. In addition, we extend the proposed GEELM algorithm in order to be able to exploit SL criteria in arbitrary (even infinite) dimensional ELM spaces. We evaluate the proposed approach on eight standard classification problems and nine publicly available datasets designed for three problems related to human behavior analysis, i.e., the recognition of human face, facial expression, and activity. Experimental results denote the effectiveness of the proposed approach, since it outperforms other ELM-based classification schemes in all the cases.

  8. A Generalized Approach to Soil Strength Prediction With Machine Learning Methods

    DTIC Science & Technology

    2006-07-01

    describe the application of different prediction methods to the problem of estimating the 25 strength of lateritic soils, a material which forms...under the unique conditions found in the humid tropics [38–40]. The utility of laterites for paving applications can be tricky to assess, since the...practice for lateritic materials has focused on the direct measurement of strength as an acceptance criteria for construction applications. In order

  9. Applying GIS and Machine Learning Methods to Twitter Data for Multiscale Surveillance of Influenza.

    PubMed

    Allen, Chris; Tsou, Ming-Hsiang; Aslam, Anoshe; Nagel, Anna; Gawron, Jean-Mark

    2016-01-01

    Traditional methods for monitoring influenza are haphazard and lack fine-grained details regarding the spatial and temporal dynamics of outbreaks. Twitter gives researchers and public health officials an opportunity to examine the spread of influenza in real-time and at multiple geographical scales. In this paper, we introduce an improved framework for monitoring influenza outbreaks using the social media platform Twitter. Relying upon techniques from geographic information science (GIS) and data mining, Twitter messages were collected, filtered, and analyzed for the thirty most populated cities in the United States during the 2013-2014 flu season. The results of this procedure are compared with national, regional, and local flu outbreak reports, revealing a statistically significant correlation between the two data sources. The main contribution of this paper is to introduce a comprehensive data mining process that enhances previous attempts to accurately identify tweets related to influenza. Additionally, geographical information systems allow us to target, filter, and normalize Twitter messages.

  10. Applying GIS and Machine Learning Methods to Twitter Data for Multiscale Surveillance of Influenza

    PubMed Central

    Aslam, Anoshe; Nagel, Anna; Gawron, Jean-Mark

    2016-01-01

    Traditional methods for monitoring influenza are haphazard and lack fine-grained details regarding the spatial and temporal dynamics of outbreaks. Twitter gives researchers and public health officials an opportunity to examine the spread of influenza in real-time and at multiple geographical scales. In this paper, we introduce an improved framework for monitoring influenza outbreaks using the social media platform Twitter. Relying upon techniques from geographic information science (GIS) and data mining, Twitter messages were collected, filtered, and analyzed for the thirty most populated cities in the United States during the 2013–2014 flu season. The results of this procedure are compared with national, regional, and local flu outbreak reports, revealing a statistically significant correlation between the two data sources. The main contribution of this paper is to introduce a comprehensive data mining process that enhances previous attempts to accurately identify tweets related to influenza. Additionally, geographical information systems allow us to target, filter, and normalize Twitter messages. PMID:27455108

  11. Early identification of posttraumatic stress following military deployment: Application of machine learning methods to a prospective study of Danish soldiers.

    PubMed

    Karstoft, Karen-Inge; Statnikov, Alexander; Andersen, Søren B; Madsen, Trine; Galatzer-Levy, Isaac R

    2015-09-15

    Pre-deployment identification of soldiers at risk for long-term posttraumatic stress psychopathology after home coming is important to guide decisions about deployment. Early post-deployment identification can direct early interventions to those in need and thereby prevents the development of chronic psychopathology. Both hold significant public health benefits given large numbers of deployed soldiers, but has so far not been achieved. Here, we aim to assess the potential for pre- and early post-deployment prediction of resilience or posttraumatic stress development in soldiers by application of machine learning (ML) methods. ML feature selection and prediction algorithms were applied to a prospective cohort of 561 Danish soldiers deployed to Afghanistan in 2009 to identify unique risk indicators and forecast long-term posttraumatic stress responses. Robust pre- and early postdeployment risk indicators were identified, and included individual PTSD symptoms as well as total level of PTSD symptoms, previous trauma and treatment, negative emotions, and thought suppression. The predictive performance of these risk indicators combined was assessed by cross-validation. Together, these indicators forecasted long term posttraumatic stress responses with high accuracy (pre-deployment: AUC = 0.84 (95% CI = 0.81-0.87), post-deployment: AUC = 0.88 (95% CI = 0.85-0.91)). This study utilized a previously collected data set and was therefore not designed to exhaust the potential of ML methods. Further, the study relied solely on self-reported measures. Pre-deployment and early post-deployment identification of risk for long-term posttraumatic psychopathology are feasible and could greatly reduce the public health costs of war. Copyright © 2015 Elsevier B.V. All rights reserved.

  12. Predicting network of drug-enzyme interaction based on machine learning method.

    PubMed

    Niu, Bing; Zhang, Yuchao; Ding, Juan; Lu, Yin; Wang, Miao; Lu, Wencong; Yuan, Xiaochen; Yin, Jinyuan

    2014-01-01

    It is important to correctly and efficiently map drugs and enzymes to their possible interaction network in modern drug research. In this work, a novel approach was introduced to encode drug and enzyme molecules with physicochemical molecular descriptors and pseudo amino acid composition, respectively. Based on this encoding method, Random Forest was adopted to build the drug-enzyme interaction network. After selecting the optimal features that are able to represent the main factors of drug-enzyme interaction in our prediction, a total of 129 features were attained which can be clustered into nine categories: Elemental Analysis, Geometry, Chemistry, Amino Acid Composition, Secondary Structure, Polarity, Molecular Volume, Codon Diversity and Electrostatic Charge. It is further found that Geometry features were the most important of all the features. As a result, our predicting model achieved an MCC of 0.915 and a sensitivity of 87.9% at the specificity level of 99.8% for 10-fold cross-validation test, and achieved an MCC of 0.895 and a sensitivity of 95.7% at the specificity level of 95.4% for independent set test. This article is part of a Special Issue entitled: Computational Proteomics, Systems Biology & Clinical Implications. Guest Editor: Yudong Cai. © 2013.

  13. Rapid estimation of compost enzymatic activity by spectral analysis method combined with machine learning.

    PubMed

    Chakraborty, Somsubhra; Das, Bhabani S; Ali, Md Nasim; Li, Bin; Sarathjith, M C; Majumdar, K; Ray, D P

    2014-03-01

    The aim of this study was to investigate the feasibility of using visible near-infrared (VisNIR) diffuse reflectance spectroscopy (DRS) as an easy, inexpensive, and rapid method to predict compost enzymatic activity, which traditionally measured by fluorescein diacetate hydrolysis (FDA-HR) assay. Compost samples representative of five different compost facilities were scanned by DRS, and the raw reflectance spectra were preprocessed using seven spectral transformations for predicting compost FDA-HR with six multivariate algorithms. Although principal component analysis for all spectral pretreatments satisfactorily identified the clusters by compost types, it could not separate different FDA contents. Furthermore, the artificial neural network multilayer perceptron (residual prediction deviation=3.2, validation r(2)=0.91 and RMSE=13.38 μg g(-1) h(-1)) outperformed other multivariate models to capture the highly non-linear relationships between compost enzymatic activity and VisNIR reflectance spectra after Savitzky-Golay first derivative pretreatment. This work demonstrates the efficiency of VisNIR DRS for predicting compost enzymatic as well as microbial activity. Copyright © 2013 Elsevier Ltd. All rights reserved.

  14. Analysis and Prediction of Myristoylation Sites Using the mRMR Method, the IFS Method and an Extreme Learning Machine Algorithm.

    PubMed

    Wang, ShaoPeng; Zhang, Yu-Hang; Huang, GuoHua; Chen, Lei; Cai, Yu-Dong

    2017-01-01

    Myristoylation is an important hydrophobic post-translational modification that is covalently bound to the amino group of Gly residues on the N-terminus of proteins. The many diverse functions of myristoylation on proteins, such as membrane targeting, signal pathway regulation and apoptosis, are largely due to the lipid modification, whereas abnormal or irregular myristoylation on proteins can lead to several pathological changes in the cell. To better understand the function of myristoylated sites and to correctly identify them in protein sequences, this study conducted a novel computational investigation on identifying myristoylation sites in protein sequences. A training dataset with 196 positive and 84 negative peptide segments were obtained. Four types of features derived from the peptide segments following the myristoylation sites were used to specify myristoylatedand non-myristoylated sites. Then, feature selection methods including maximum relevance and minimum redundancy (mRMR), incremental feature selection (IFS), and a machine learning algorithm (extreme learning machine method) were adopted to extract optimal features for the algorithm to identify myristoylation sites in protein sequences, thereby building an optimal prediction model. As a result, 41 key features were extracted and used to build an optimal prediction model. The effectiveness of the optimal prediction model was further validated by its performance on a test dataset. Furthermore, detailed analyses were also performed on the extracted 41 features to gain insight into the mechanism of myristoylation modification. This study provided a new computational method for identifying myristoylation sites in protein sequences. We believe that it can be a useful tool to predict myristoylation sites from protein sequences. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  15. Using Machine learning method to estimate Air Temperature from MODIS over Berlin

    NASA Astrophysics Data System (ADS)

    Marzban, F.; Preusker, R.; Sodoudi, S.; Taheri, H.; Allahbakhshi, M.

    2015-12-01

    Land Surface Temperature (LST) is defined as the temperature of the interface between the Earth's surface and its atmosphere and thus it is a critical variable to understand land-atmosphere interactions and a key parameter in meteorological and hydrological studies, which is involved in energy fluxes. Air temperature (Tair) is one of the most important input variables in different spatially distributed hydrological, ecological models. The estimation of near surface air temperature is useful for a wide range of applications. Some applications from traffic or energy management, require Tair data in high spatial and temporal resolution at two meters height above the ground (T2m), sometimes in near-real-time. Thus, a parameterization based on boundary layer physical principles was developed that determines the air temperature from remote sensing data (MODIS). Tair is commonly obtained from synoptic measurements in weather stations. However, the derivation of near surface air temperature from the LST derived from satellite is far from straight forward. T2m is not driven directly by the sun, but indirectly by LST, thus T2m can be parameterized from the LST and other variables such as Albedo, NDVI, Water vapor and etc. Most of the previous studies have focused on estimating T2m based on simple and advanced statistical approaches, Temperature-Vegetation index and energy-balance approaches but the main objective of this research is to explore the relationships between T2m and LST in Berlin by using Artificial intelligence method with the aim of studying key variables to allow us establishing suitable techniques to obtain Tair from satellite Products and ground data. Secondly, an attempt was explored to identify an individual mix of attributes that reveals a particular pattern to better understanding variation of T2m during day and nighttime over the different area of Berlin. For this reason, a three layer Feedforward neural networks is considered with LMA algorithm

  16. Feature engineering combined with machine learning and rule-based methods for structured information extraction from narrative clinical discharge summaries.

    PubMed

    Xu, Yan; Hong, Kai; Tsujii, Junichi; Chang, Eric I-Chao

    2012-01-01

    A system that translates narrative text in the medical domain into structured representation is in great demand. The system performs three sub-tasks: concept extraction, assertion classification, and relation identification. The overall system consists of five steps: (1) pre-processing sentences, (2) marking noun phrases (NPs) and adjective phrases (APs), (3) extracting concepts that use a dosage-unit dictionary to dynamically switch two models based on Conditional Random Fields (CRF), (4) classifying assertions based on voting of five classifiers, and (5) identifying relations using normalized sentences with a set of effective discriminating features. Macro-averaged and micro-averaged precision, recall and F-measure were used to evaluate results. The performance is competitive with the state-of-the-art systems with micro-averaged F-measure of 0.8489 for concept extraction, 0.9392 for assertion classification and 0.7326 for relation identification. The system exploits an array of common features and achieves state-of-the-art performance. Prudent feature engineering sets the foundation of our systems. In concept extraction, we demonstrated that switching models, one of which is especially designed for telegraphic sentences, improved extraction of the treatment concept significantly. In assertion classification, a set of features derived from a rule-based classifier were proven to be effective for the classes such as conditional and possible. These classes would suffer from data scarcity in conventional machine-learning methods. In relation identification, we use two-staged architecture, the second of which applies pairwise classifiers to possible candidate classes. This architecture significantly improves performance.

  17. Learning as a Machine: Crossovers between Humans and Machines

    ERIC Educational Resources Information Center

    Hildebrandt, Mireille

    2017-01-01

    This article is a revised version of the keynote presented at LAK '16 in Edinburgh. The article investigates some of the assumptions of learning analytics, notably those related to behaviourism. Building on the work of Ivan Pavlov, Herbert Simon, and James Gibson as ways of "learning as a machine," the article then develops two levels of…

  18. Medical Dataset Classification: A Machine Learning Paradigm Integrating Particle Swarm Optimization with Extreme Learning Machine Classifier.

    PubMed

    Subbulakshmi, C V; Deepa, S N

    2015-01-01

    Medical data classification is a prime data mining problem being discussed about for a decade that has attracted several researchers around the world. Most classifiers are designed so as to learn from the data itself using a training process, because complete expert knowledge to determine classifier parameters is impracticable. This paper proposes a hybrid methodology based on machine learning paradigm. This paradigm integrates the successful exploration mechanism called self-regulated learning capability of the particle swarm optimization (PSO) algorithm with the extreme learning machine (ELM) classifier. As a recent off-line learning method, ELM is a single-hidden layer feedforward neural network (FFNN), proved to be an excellent classifier with large number of hidden layer neurons. In this research, PSO is used to determine the optimum set of parameters for the ELM, thus reducing the number of hidden layer neurons, and it further improves the network generalization performance. The proposed method is experimented on five benchmarked datasets of the UCI Machine Learning Repository for handling medical dataset classification. Simulation results show that the proposed approach is able to achieve good generalization performance, compared to the results of other classifiers.

  19. Medical Dataset Classification: A Machine Learning Paradigm Integrating Particle Swarm Optimization with Extreme Learning Machine Classifier

    PubMed Central

    Subbulakshmi, C. V.; Deepa, S. N.

    2015-01-01

    Medical data classification is a prime data mining problem being discussed about for a decade that has attracted several researchers around the world. Most classifiers are designed so as to learn from the data itself using a training process, because complete expert knowledge to determine classifier parameters is impracticable. This paper proposes a hybrid methodology based on machine learning paradigm. This paradigm integrates the successful exploration mechanism called self-regulated learning capability of the particle swarm optimization (PSO) algorithm with the extreme learning machine (ELM) classifier. As a recent off-line learning method, ELM is a single-hidden layer feedforward neural network (FFNN), proved to be an excellent classifier with large number of hidden layer neurons. In this research, PSO is used to determine the optimum set of parameters for the ELM, thus reducing the number of hidden layer neurons, and it further improves the network generalization performance. The proposed method is experimented on five benchmarked datasets of the UCI Machine Learning Repository for handling medical dataset classification. Simulation results show that the proposed approach is able to achieve good generalization performance, compared to the results of other classifiers. PMID:26491713

  20. Defect Classification Using Machine Learning

    SciTech Connect

    Carr, A; Kegelmeyer, L; Liao, Z M; Abdulla, G; Cross, D; Kegelmeyer, W P; Raviza, F; Carr, C W

    2008-10-24

    Laser-induced damage growth on the surface of fused silica optics has been extensively studied and has been found to depend on a number of factors including fluence and the surface on which the damage site resides. It has been demonstrated that damage sites as small as a few tens of microns can be detected and tracked on optics installed a fusion-class laser, however, determining the surface of an optic on which a damage site resides in situ can be a significant challenge. In this work demonstrate that a machine-learning algorithm can successfully predict the surface location of the damage site using an expanded set of characteristics for each damage site, some of which are not historically associated with growth rate.

  1. Discriminative clustering via extreme learning machine.

    PubMed

    Huang, Gao; Liu, Tianchi; Yang, Yan; Lin, Zhiping; Song, Shiji; Wu, Cheng

    2015-10-01

    Discriminative clustering is an unsupervised learning framework which introduces the discriminative learning rule of supervised classification into clustering. The underlying assumption is that a good partition (clustering) of the data should yield high discrimination, namely, the partitioned data can be easily classified by some classification algorithms. In this paper, we propose three discriminative clustering approaches based on Extreme Learning Machine (ELM). The first algorithm iteratively trains weighted ELM (W-ELM) classifier to gradually maximize the data discrimination. The second and third methods are both built on Fisher's Linear Discriminant Analysis (LDA); but one approach adopts alternative optimization, while the other leverages kernel k-means. We show that the proposed algorithms can be easily implemented, and yield competitive clustering accuracy on real world data sets compared to state-of-the-art clustering methods.

  2. Machine learning applications in cell image analysis.

    PubMed

    Kan, Andrey

    2017-04-04

    Machine learning (ML) refers to a set of automatic pattern recognition methods that have been successfully applied across various problem domains, including biomedical image analysis. This review focuses on ML applications for image analysis in light microscopy experiments with typical tasks of segmenting and tracking individual cells, and modelling of reconstructed lineage trees. After describing a typical image analysis pipeline and highlighting challenges of automatic analysis (for example, variability in cell morphology, tracking in presence of clutters) this review gives a brief historical outlook of ML, followed by basic concepts and definitions required for understanding examples. This article then presents several example applications at various image processing stages, including the use of supervised learning methods for improving cell segmentation, and the application of active learning for tracking. The review concludes with remarks on parameter setting and future directions.Immunology and Cell Biology advance online publication, 4 April 2017; doi:10.1038/icb.2017.16.

  3. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from (18)F-FDG PET/CT images.

    PubMed

    Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

    2017-12-01

    This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from (18)F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images

  4. Toward Harnessing User Feedback For Machine Learning

    DTIC Science & Technology

    2006-10-02

    machine learning systems. If this resource-the users themselves-could somehow work hand-in-hand with machine learning systems, the accuracy of learning systems could be improved and the users? understanding and trust of the system could improve as well. We conducted a think-aloud study to see how willing users were to provide feedback and to understand what kinds of feedback users could give. Users were shown explanations of machine learning predictions and asked to provide feedback to improve the predictions. We found that users

  5. Probabilistic machine learning and artificial intelligence.

    PubMed

    Ghahramani, Zoubin

    2015-05-28

    How can a machine learn from experience? Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The probabilistic framework, which describes how to represent and manipulate uncertainty about models and predictions, has a central role in scientific data analysis, machine learning, robotics, cognitive science and artificial intelligence. This Review provides an introduction to this framework, and discusses some of the state-of-the-art advances in the field, namely, probabilistic programming, Bayesian optimization, data compression and automatic model discovery.

  6. Probabilistic machine learning and artificial intelligence

    NASA Astrophysics Data System (ADS)

    Ghahramani, Zoubin

    2015-05-01

    How can a machine learn from experience? Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The probabilistic framework, which describes how to represent and manipulate uncertainty about models and predictions, has a central role in scientific data analysis, machine learning, robotics, cognitive science and artificial intelligence. This Review provides an introduction to this framework, and discusses some of the state-of-the-art advances in the field, namely, probabilistic programming, Bayesian optimization, data compression and automatic model discovery.

  7. Machine learning: An artificial intelligence approach

    SciTech Connect

    Michalski, R.S.; Carbonell, J.G.; Mitchell, T.M.

    1983-01-01

    This book contains tutorial overviews and research papers on contemporary trends in the area of machine learning viewed from an AI perspective. Research directions covered include: learning from examples, modeling human learning strategies, knowledge acquisition for expert systems, learning heuristics, discovery systems, and conceptual data analysis.

  8. Adaptive Learning Systems: Beyond Teaching Machines

    ERIC Educational Resources Information Center

    Kara, Nuri; Sevim, Nese

    2013-01-01

    Since 1950s, teaching machines have changed a lot. Today, we have different ideas about how people learn, what instructor should do to help students during their learning process. We have adaptive learning technologies that can create much more student oriented learning environments. The purpose of this article is to present these changes and its…

  9. Sparse extreme learning machine for classification.

    PubMed

    Bai, Zuo; Huang, Guang-Bin; Wang, Danwei; Wang, Han; Westover, M Brandon

    2014-10-01

    Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least square support vector machines, proximal support vector machines, and so on. However, the solution of unified ELM is dense, and thus, usually plenty of storage space and testing time are required for large-scale applications. In this paper, a sparse ELM is proposed as an alternative solution for classification, reducing storage space and testing time. In addition, unified ELM obtains the solution by matrix inversion, whose computational complexity is between quadratic and cubic with respect to the training size. It still requires plenty of training time for large-scale problems, even though it is much faster than many other traditional methods. In this paper, an efficient training algorithm is specifically developed for sparse ELM. The quadratic programming problem involved in sparse ELM is divided into a series of smallest possible sub-problems, each of which are solved analytically. Compared with SVM, sparse ELM obtains better generalization performance with much faster training speed. Compared with unified ELM, sparse ELM achieves similar generalization performance for binary classification applications, and when dealing with large-scale binary classification problems, sparse ELM realizes even faster training speed than unified ELM.

  10. Sparse Extreme Learning Machine for Classification

    PubMed Central

    Bai, Zuo; Huang, Guang-Bin; Wang, Danwei; Wang, Han; Westover, M. Brandon

    2016-01-01

    Extreme learning machine (ELM) was initially proposed for single-hidden-layer feedforward neural networks (SLFNs). In the hidden layer (feature mapping), nodes are randomly generated independently of training data. Furthermore, a unified ELM was proposed, providing a single framework to simplify and unify different learning methods, such as SLFNs, least square support vector machines, proximal support vector machines, and so on. However, the solution of unified ELM is dense, and thus, usually plenty of storage space and testing time are required for large-scale applications. In this paper, a sparse ELM is proposed as an alternative solution for classification, reducing storage space and testing time. In addition, unified ELM obtains the solution by matrix inversion, whose computational complexity is between quadratic and cubic with respect to the training size. It still requires plenty of training time for large-scale problems, even though it is much faster than many other traditional methods. In this paper, an efficient training algorithm is specifically developed for sparse ELM. The quadratic programming problem involved in sparse ELM is divided into a series of smallest possible sub-problems, each of which are solved analytically. Compared with SVM, sparse ELM obtains better generalization performance with much faster training speed. Compared with unified ELM, sparse ELM achieves similar generalization performance for binary classification applications, and when dealing with large-scale binary classification problems, sparse ELM realizes even faster training speed than unified ELM. PMID:25222727

  11. Scalable Machine Learning for Massive Astronomical Datasets

    NASA Astrophysics Data System (ADS)

    Ball, Nicholas M.; Gray, A.

    2014-04-01

    We present the ability to perform data mining and machine learning operations on a catalog of half a billion astronomical objects. This is the result of the combination of robust, highly accurate machine learning algorithms with linear scalability that renders the applications of these algorithms to massive astronomical data tractable. We demonstrate the core algorithms kernel density estimation, K-means clustering, linear regression, nearest neighbors, random forest and gradient-boosted decision tree, singular value decomposition, support vector machine, and two-point correlation function. Each of these is relevant for astronomical applications such as finding novel astrophysical objects, characterizing artifacts in data, object classification (including for rare objects), object distances, finding the important features describing objects, density estimation of distributions, probabilistic quantities, and exploring the unknown structure of new data. The software, Skytree Server, runs on any UNIX-based machine, a virtual machine, or cloud-based and distributed systems including Hadoop. We have integrated it on the cloud computing system of the Canadian Astronomical Data Centre, the Canadian Advanced Network for Astronomical Research (CANFAR), creating the world's first cloud computing data mining system for astronomy. We demonstrate results showing the scaling of each of our major algorithms on large astronomical datasets, including the full 470,992,970 objects of the 2 Micron All-Sky Survey (2MASS) Point Source Catalog. We demonstrate the ability to find outliers in the full 2MASS dataset utilizing multiple methods, e.g., nearest neighbors. This is likely of particular interest to the radio astronomy community given, for example, that survey projects contain groups dedicated to this topic. 2MASS is used as a proof-of-concept dataset due to its convenience and availability. These results are of interest to any astronomical project with large and/or complex

  12. Modeling quantum physics with machine learning

    NASA Astrophysics Data System (ADS)

    Lopez-Bezanilla, Alejandro; Arsenault, Louis-Francois; Millis, Andrew; Littlewood, Peter; von Lilienfeld, Anatole

    2014-03-01

    Machine Learning (ML) is a systematic way of inferring new results from sparse information. It directly allows for the resolution of computationally expensive sets of equations by making sense of accumulated knowledge and it is therefore an attractive method for providing computationally inexpensive 'solvers' for some of the important systems of condensed matter physics. In this talk a non-linear regression statistical model is introduced to demonstrate the utility of ML methods in solving quantum physics related problem, and is applied to the calculation of electronic transport in 1D channels. DOE contract number DE-AC02-06CH11357.

  13. Hierarchical extreme learning machine based reinforcement learning for goal localization

    NASA Astrophysics Data System (ADS)

    AlDahoul, Nouar; Zaw Htike, Zaw; Akmeliawati, Rini

    2017-03-01

    The objective of goal localization is to find the location of goals in noisy environments. Simple actions are performed to move the agent towards the goal. The goal detector should be capable of minimizing the error between the predicted locations and the true ones. Few regions need to be processed by the agent to reduce the computational effort and increase the speed of convergence. In this paper, reinforcement learning (RL) method was utilized to find optimal series of actions to localize the goal region. The visual data, a set of images, is high dimensional unstructured data and needs to be represented efficiently to get a robust detector. Different deep Reinforcement models have already been used to localize a goal but most of them take long time to learn the model. This long learning time results from the weights fine tuning stage that is applied iteratively to find an accurate model. Hierarchical Extreme Learning Machine (H-ELM) was used as a fast deep model that doesn’t fine tune the weights. In other words, hidden weights are generated randomly and output weights are calculated analytically. H-ELM algorithm was used in this work to find good features for effective representation. This paper proposes a combination of Hierarchical Extreme learning machine and Reinforcement learning to find an optimal policy directly from visual input. This combination outperforms other methods in terms of accuracy and learning speed. The simulations and results were analysed by using MATLAB.

  14. Accelerating materials property predictions using machine learning.

    PubMed

    Pilania, Ghanshyam; Wang, Chenchen; Jiang, Xun; Rajasekaran, Sanguthevar; Ramprasad, Ramamurthy

    2013-09-30

    The materials discovery process can be significantly expedited and simplified if we can learn effectively from available knowledge and data. In the present contribution, we show that efficient and accurate prediction of a diverse set of properties of material systems is possible by employing machine (or statistical) learning methods trained on quantum mechanical computations in combination with the notions of chemical similarity. Using a family of one-dimensional chain systems, we present a general formalism that allows us to discover decision rules that establish a mapping between easily accessible attributes of a system and its properties. It is shown that fingerprints based on either chemo-structural (compositional and configurational information) or the electronic charge density distribution can be used to make ultra-fast, yet accurate, property predictions. Harnessing such learning paradigms extends recent efforts to systematically explore and mine vast chemical spaces, and can significantly accelerate the discovery of new application-specific materials.

  15. A new method for species identification via protein-coding and non-coding DNA barcodes by combining machine learning with bioinformatic methods.

    PubMed

    Zhang, Ai-bing; Feng, Jie; Ward, Robert D; Wan, Ping; Gao, Qiang; Wu, Jun; Zhao, Wei-zhong

    2012-01-01

    Species identification via DNA barcodes is contributing greatly to current bioinventory efforts. The initial, and widely accepted, proposal was to use the protein-coding cytochrome c oxidase subunit I (COI) region as the standard barcode for animals, but recently non-coding internal transcribed spacer (ITS) genes have been proposed as candidate barcodes for both animals and plants. However, achieving a robust alignment for non-coding regions can be problematic. Here we propose two new methods (DV-RBF and FJ-RBF) to address this issue for species assignment by both coding and non-coding sequences that take advantage of the power of machine learning and bioinformatics. We demonstrate the value of the new methods with four empirical datasets, two representing typical protein-coding COI barcode datasets (neotropical bats and marine fish) and two representing non-coding ITS barcodes (rust fungi and brown algae). Using two random sub-sampling approaches, we demonstrate that the new methods significantly outperformed existing Neighbor-joining (NJ) and Maximum likelihood (ML) methods for both coding and non-coding barcodes when there was complete species coverage in the reference dataset. The new methods also out-performed NJ and ML methods for non-coding sequences in circumstances of potentially incomplete species coverage, although then the NJ and ML methods performed slightly better than the new methods for protein-coding barcodes. A 100% success rate of species identification was achieved with the two new methods for 4,122 bat queries and 5,134 fish queries using COI barcodes, with 95% confidence intervals (CI) of 99.75-100%. The new methods also obtained a 96.29% success rate (95%CI: 91.62-98.40%) for 484 rust fungi queries and a 98.50% success rate (95%CI: 96.60-99.37%) for 1094 brown algae queries, both using ITS barcodes.

  16. Photonic Neurocomputers And Learning Machines

    NASA Astrophysics Data System (ADS)

    Farhat, Nabil H.

    1990-05-01

    The study of complex multidimensional nonlinear dynamical systems and the modeling and emulation of cognitive brain-like processing of sensory information (neural network research), including the study of chaos and its role in such systems would benefit immensely from the development of a new generation of programmable analog computers capable of carrying out collective, nonlinear and iterative computations at very high speed. The massive interconnectivity and nonlinearity needed in such analog computing structures indicate that a mix of optics and electronics mediated by judicial choice of device physics offer benefits for realizing networks with the following desirable properties: (a) large scale nets, i.e. nets with high number of decision making elements (neurons), (b) modifiable structure, i.e. ability to partition the net into any desired number of layers of prescribed size (number of neurons per layer) with any prescribed pattern of communications between them (e.g. feed forward or feedback (recurrent)), (c) programmable and/or adaptive connectivity weights between the neurons for self-organization and learning, (d) both synchroneous or asynchroneous update rules be possible, (e) high speed update i.e. neurons with lisec response time to enable rapid iteration and convergence, (f) can be used in the study and evaluation of a variety of adaptive learning algorithms, (g) can be used in rapid solution by fast simulated annealing of complex optimization problems of the kind encountered in adaptive learning, pattern recognition, and image processing. The aim of this paper is to describe recent efforts and progress made towards achieving these desirable attributes in analog photonic (optoelectronic and/or electron optical) hardware that utilizes primarily incoherent light. A specific example, hardware implementation of a stochastic Boltzmann learning machine, is used as vehicle for identifying generic issues and clarify research and development areas for further

  17. Galaxy morphology - An unsupervised machine learning approach

    NASA Astrophysics Data System (ADS)

    Schutter, A.; Shamir, L.

    2015-09-01

    Structural properties poses valuable information about the formation and evolution of galaxies, and are important for understanding the past, present, and future universe. Here we use unsupervised machine learning methodology to analyze a network of similarities between galaxy morphological types, and automatically deduce a morphological sequence of galaxies. Application of the method to the EFIGI catalog show that the morphological scheme produced by the algorithm is largely in agreement with the De Vaucouleurs system, demonstrating the ability of computer vision and machine learning methods to automatically profile galaxy morphological sequences. The unsupervised analysis method is based on comprehensive computer vision techniques that compute the visual similarities between the different morphological types. Rather than relying on human cognition, the proposed system deduces the similarities between sets of galaxy images in an automatic manner, and is therefore not limited by the number of galaxies being analyzed. The source code of the method is publicly available, and the protocol of the experiment is included in the paper so that the experiment can be replicated, and the method can be used to analyze user-defined datasets of galaxy images.

  18. Using Machine Learning in Adversarial Environments.

    SciTech Connect

    Warren Leon Davis

    2016-02-01

    Intrusion/anomaly detection systems are among the first lines of cyber defense. Commonly, they either use signatures or machine learning (ML) to identify threats, but fail to account for sophisticated attackers trying to circumvent them. We propose to embed machine learning within a game theoretic framework that performs adversarial modeling, develops methods for optimizing operational response based on ML, and integrates the resulting optimization codebase into the existing ML infrastructure developed by the Hybrid LDRD. Our approach addresses three key shortcomings of ML in adversarial settings: 1) resulting classifiers are typically deterministic and, therefore, easy to reverse engineer; 2) ML approaches only address the prediction problem, but do not prescribe how one should operationalize predictions, nor account for operational costs and constraints; and 3) ML approaches do not model attackers’ response and can be circumvented by sophisticated adversaries. The principal novelty of our approach is to construct an optimization framework that blends ML, operational considerations, and a model predicting attackers reaction, with the goal of computing optimal moving target defense. One important challenge is to construct a realistic model of an adversary that is tractable, yet realistic. We aim to advance the science of attacker modeling by considering game-theoretic methods, and by engaging experimental subjects with red teaming experience in trying to actively circumvent an intrusion detection system, and learning a predictive model of such circumvention activities. In addition, we will generate metrics to test that a particular model of an adversary is consistent with available data.

  19. Applying Machine Learning to Star Cluster Classification

    NASA Astrophysics Data System (ADS)

    Fedorenko, Kristina; Grasha, Kathryn; Calzetti, Daniela; Mahadevan, Sridhar

    2016-01-01

    Catalogs describing populations of star clusters are essential in investigating a range of important issues, from star formation to galaxy evolution. Star cluster catalogs are typically created in a two-step process: in the first step, a catalog of sources is automatically produced; in the second step, each of the extracted sources is visually inspected by 3-to-5 human classifiers and assigned a category. Classification by humans is labor-intensive and time consuming, thus it creates a bottleneck, and substantially slows down progress in star cluster research.We seek to automate the process of labeling star clusters (the second step) through applying supervised machine learning techniques. This will provide a fast, objective, and reproducible classification. Our data is HST (WFC3 and ACS) images of galaxies in the distance range of 3.5-12 Mpc, with a few thousand star clusters already classified by humans as a part of the LEGUS (Legacy ExtraGalactic UV Survey) project. The classification is based on 4 labels (Class 1 - symmetric, compact cluster; Class 2 - concentrated object with some degree of asymmetry; Class 3 - multiple peak system, diffuse; and Class 4 - spurious detection). We start by looking at basic machine learning methods such as decision trees. We then proceed to evaluate performance of more advanced techniques, focusing on convolutional neural networks and other Deep Learning methods. We analyze the results, and suggest several directions for further improvement.

  20. Machine Learning for Computer-aided Diagnosis.

    PubMed

    Nemoto, Mitsutaka; Masutani, Yoshitaka; Nomura, Yukihiro; Hanaoka, Shohei; Miki, Soichiro; Yoshikawa, Takeharu; Hayashi, Naoto; Ootomo, Kuni

    Machine learning algorithms are to analyze any dataset to extract data-driven model, prediction rule, or decision rule from the dataset. Various machine learning algorithms are now used to develop high-performance medical image processing systems such as computer-aided detection (CADe) system which detects clinically significant objects from medical images and computer-aided diagnosis (CADx) system which quantifies malignancy of manually or automatically detected clinical objects. In this paper, we introduce some applications of machine learning algorithms to the development of medical image processing system.

  1. Classification of collective behavior: a comparison of tracking and machine learning methods to study the effect of ambient light on fish shoaling.

    PubMed

    Butail, Sachit; Salerno, Philip; Bollt, Erik M; Porfiri, Maurizio

    2015-12-01

    Traditional approaches for the analysis of collective behavior entail digitizing the position of each individual, followed by evaluation of pertinent group observables, such as cohesion and polarization. Machine learning may enable considerable advancements in this area by affording the classification of these observables directly from images. While such methods have been successfully implemented in the classification of individual behavior, their potential in the study collective behavior is largely untested. In this paper, we compare three methods for the analysis of collective behavior: simple tracking (ST) without resolving occlusions, machine learning with real data (MLR), and machine learning with synthetic data (MLS). These methods are evaluated on videos recorded from an experiment studying the effect of ambient light on the shoaling tendency of Giant danios. In particular, we compute average nearest-neighbor distance (ANND) and polarization using the three methods and compare the values with manually-verified ground-truth data. To further assess possible dependence on sampling rate for computing ANND, the comparison is also performed at a low frame rate. Results show that while ST is the most accurate at higher frame rate for both ANND and polarization, at low frame rate for ANND there is no significant difference in accuracy between the three methods. In terms of computational speed, MLR and MLS take significantly less time to process an image, with MLS better addressing constraints related to generation of training data. Finally, all methods are able to successfully detect a significant difference in ANND as the ambient light intensity is varied irrespective of the direction of intensity change.

  2. Machine Learning Techniques in Clinical Vision Sciences.

    PubMed

    Caixinha, Miguel; Nunes, Sandrina

    2017-01-01

    This review presents and discusses the contribution of machine learning techniques for diagnosis and disease monitoring in the context of clinical vision science. Many ocular diseases leading to blindness can be halted or delayed when detected and treated at its earliest stages. With the recent developments in diagnostic devices, imaging and genomics, new sources of data for early disease detection and patients' management are now available. Machine learning techniques emerged in the biomedical sciences as clinical decision-support techniques to improve sensitivity and specificity of disease detection and monitoring, increasing objectively the clinical decision-making process. This manuscript presents a review in multimodal ocular disease diagnosis and monitoring based on machine learning approaches. In the first section, the technical issues related to the different machine learning approaches will be present. Machine learning techniques are used to automatically recognize complex patterns in a given dataset. These techniques allows creating homogeneous groups (unsupervised learning), or creating a classifier predicting group membership of new cases (supervised learning), when a group label is available for each case. To ensure a good performance of the machine learning techniques in a given dataset, all possible sources of bias should be removed or minimized. For that, the representativeness of the input dataset for the true population should be confirmed, the noise should be removed, the missing data should be treated and the data dimensionally (i.e., the number of parameters/features and the number of cases in the dataset) should be adjusted. The application of machine learning techniques in ocular disease diagnosis and monitoring will be presented and discussed in the second section of this manuscript. To show the clinical benefits of machine learning in clinical vision sciences, several examples will be presented in glaucoma, age-related macular degeneration

  3. Fusion of HJ1B and ALOS PALSAR data for land cover classification using machine learning methods

    NASA Astrophysics Data System (ADS)

    Wang, X. Y.; Guo, Y. G.; He, J.; Du, L. T.

    2016-10-01

    Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier.

  4. Alternating minimization and Boltzmann machine learning.

    PubMed

    Byrne, W

    1992-01-01

    Training a Boltzmann machine with hidden units is appropriately treated in information geometry using the information divergence and the technique of alternating minimization. The resulting algorithm is shown to be closely related to gradient descent Boltzmann machine learning rules, and the close relationship of both to the EM algorithm is described. An iterative proportional fitting procedure for training machines without hidden units is described and incorporated into the alternating minimization algorithm.

  5. The application of discriminant analysis and Machine Learning methods as tools to identify and classify compounds with potential as transdermal enhancers.

    PubMed

    Moss, G P; Shah, A J; Adams, R G; Davey, N; Wilkinson, S C; Pugh, W J; Sun, Y

    2012-01-23

    Discriminant analysis (DA) has previously been shown to allow the proposal of simple guidelines for the classification of 73 chemical enhancers of percutaneous absorption. Pugh et al. employed DA to classify such enhancers into simple categories, based on the physicochemical properties of the enhancer molecules (Pugh et al., 2005). While this approach provided a reasonable accuracy of classification it was unable to provide a consistently reliable estimate of enhancement ratio (ER, defined as the amount of hydrocortisone transferred after 24h, relative to control). Machine Learning methods, including Gaussian process (GP) regression, have recently been employed in the prediction of percutaneous absorption of exogenous chemicals (Moss et al., 2009; Lam et al., 2010; Sun et al., 2011). They have shown that they provide more accurate predictions of these phenomena. In this study several Machine Learning methods, including the K-nearest-neighbour (KNN) regression, single layer networks, radial basis function networks and the SVM classifier were applied to an enhancer dataset reported previously. The SMOTE sampling method was used to oversample chemical compounds with ER>10 in each training set in order to improve estimation of GP and KNN. Results show that models using five physicochemical descriptors exhibit better performance than those with three features. The best classification result was obtained by using the SVM method without dealing with imbalanced data. Following over-sampling, GP gives the best result. It correctly assigned 8 of the 12 "good" (ER>10) enhancers and 56 of the 59 "poor" enhancers (ER<10). Overall success rates were similar. However, the pharmaceutical advantages of the Machine Learning methods are that they can provide more accurate classification of enhancer type with fewer false-positive results and that, unlike discriminant analysis, they are able to make predictions of enhancer ability.

  6. Machine Learning and Cosmological Simulations

    NASA Astrophysics Data System (ADS)

    Kamdar, Harshil; Turk, Matthew; Brunner, Robert

    2016-01-01

    We explore the application of machine learning (ML) to the problem of galaxy formation and evolution in a hierarchical universe. Our motivations are two-fold: (1) presenting a new, promising technique to study galaxy formation, and (2) quantitatively evaluating the extent of the influence of dark matter halo properties on small-scale structure formation. For our analyses, we use both semi-analytical models (Millennium simulation) and N-body + hydrodynamical simulations (Illustris simulation). The ML algorithms are trained on important dark matter halo properties (inputs) and galaxy properties (outputs). The trained models are able to robustly predict the gas mass, stellar mass, black hole mass, star formation rate, $g-r$ color, and stellar metallicity. Moreover, the ML simulated galaxies obey fundamental observational constraints implying that the population of ML predicted galaxies is physically and statistically robust. Next, ML algorithms are trained on an N-body + hydrodynamical simulation and applied to an N-body only simulation (Dark Sky simulation, Illustris Dark), populating this new simulation with galaxies. We can examine how structure formation changes with different cosmological parameters and are able to mimic a full-blown hydrodynamical simulation in a computation time that is orders of magnitude smaller. We find that the set of ML simulated galaxies in Dark Sky obey the same observational constraints, further solidifying ML's place as an intriguing and promising technique in future galaxy formation studies and rapid mock galaxy catalog creation.

  7. Machine learning techniques and drug design.

    PubMed

    Gertrudes, J C; Maltarollo, V G; Silva, R A; Oliveira, P R; Honório, K M; da Silva, A B F

    2012-01-01

    The interest in the application of machine learning techniques (MLT) as drug design tools is growing in the last decades. The reason for this is related to the fact that the drug design is very complex and requires the use of hybrid techniques. A brief review of some MLT such as self-organizing maps, multilayer perceptron, bayesian neural networks, counter-propagation neural network and support vector machines is described in this paper. A comparison between the performance of the described methods and some classical statistical methods (such as partial least squares and multiple linear regression) shows that MLT have significant advantages. Nowadays, the number of studies in medicinal chemistry that employ these techniques has considerably increased, in particular the use of support vector machines. The state of the art and the future trends of MLT applications encompass the use of these techniques to construct more reliable QSAR models. The models obtained from MLT can be used in virtual screening studies as well as filters to develop/discovery new chemicals. An important challenge in the drug design field is the prediction of pharmacokinetic and toxicity properties, which can avoid failures in the clinical phases. Therefore, this review provides a critical point of view on the main MLT and shows their potential ability as a valuable tool in drug design.

  8. Predicting fecal sources in waters with diverse pollution loads using general and molecular host-specific indicators and applying machine learning methods.

    PubMed

    Casanovas-Massana, Arnau; Gómez-Doñate, Marta; Sánchez, David; Belanche-Muñoz, Lluís A; Muniesa, Maite; Blanch, Anicet R

    2015-03-15

    In this study we use a machine learning software (Ichnaea) to generate predictive models for water samples with different concentrations of fecal contamination (point source, moderate and low). We applied several MST methods (host-specific Bacteroides phages, mitochondrial DNA genetic markers, Bifidobacterium adolescentis and Bifidobacterium dentium markers, and bifidobacterial host-specific qPCR), and general indicators (Escherichia coli, enterococci and somatic coliphages) to evaluate the source of contamination in the samples. The results provided data to the Ichnaea software, that evaluated the performance of each method in the different scenarios and determined the source of the contamination. Almost all MST methods in this study determined correctly the origin of fecal contamination at point source and in moderate concentration samples. When the dilution of the fecal pollution increased (below 3 log10 CFU E. coli/100 ml) some of these indicators (bifidobacterial host-specific qPCR, some mitochondrial markers or B. dentium marker) were not suitable because their concentrations decreased below the detection limit. Using the data from source point samples, the software Ichnaea produced models for waters with low levels of fecal pollution. These models included some MST methods, on the basis of their best performance, that were used to determine the source of pollution in this area. Regardless the methods selected, that could vary depending on the scenario, inductive machine learning methods are a promising tool in MST studies and may represent a leap forward in solving MST cases.

  9. Machine learning: an indispensable tool in bioinformatics.

    PubMed

    Inza, Iñaki; Calvo, Borja; Armañanzas, Rubén; Bengoetxea, Endika; Larrañaga, Pedro; Lozano, José A

    2010-01-01

    The increase in the number and complexity of biological databases has raised the need for modern and powerful data analysis tools and techniques. In order to fulfill these requirements, the machine learning discipline has become an everyday tool in bio-laboratories. The use of machine learning techniques has been extended to a wide spectrum of bioinformatics applications. It is broadly used to investigate the underlying mechanisms and interactions between biological molecules in many diseases, and it is an essential tool in any biomarker discovery process. In this chapter, we provide a basic taxonomy of machine learning algorithms, and the characteristics of main data preprocessing, supervised classification, and clustering techniques are shown. Feature selection, classifier evaluation, and two supervised classification topics that have a deep impact on current bioinformatics are presented. We make the interested reader aware of a set of popular web resources, open source software tools, and benchmarking data repositories that are frequently used by the machine learning community.

  10. Extreme Learning Machine for Multilayer Perceptron.

    PubMed

    Tang, Jiexiong; Deng, Chenwei; Huang, Guang-Bin

    2016-04-01

    Extreme learning machine (ELM) is an emerging learning algorithm for the generalized single hidden layer feedforward neural networks, of which the hidden node parameters are randomly generated and the output weights are analytically computed. However, due to its shallow architecture, feature learning using ELM may not be effective for natural signals (e.g., images/videos), even with a large number of hidden nodes. To address this issue, in this paper, a new ELM-based hierarchical learning framework is proposed for multilayer perceptron. The proposed architecture is divided into two main components: 1) self-taught feature extraction followed by supervised feature classification and 2) they are bridged by random initialized hidden weights. The novelties of this paper are as follows: 1) unsupervised multilayer encoding is conducted for feature extraction, and an ELM-based sparse autoencoder is developed via l1 constraint. By doing so, it achieves more compact and meaningful feature representations than the original ELM; 2) by exploiting the advantages of ELM random feature mapping, the hierarchically encoded outputs are randomly projected before final decision making, which leads to a better generalization with faster learning speed; and 3) unlike the greedy layerwise training of deep learning (DL), the hidden layers of the proposed framework are trained in a forward manner. Once the previous layer is established, the weights of the current layer are fixed without fine-tuning. Therefore, it has much better learning efficiency than the DL. Extensive experiments on various widely used classification data sets show that the proposed algorithm achieves better and faster convergence than the existing state-of-the-art hierarchical learning methods. Furthermore, multiple applications in computer vision further confirm the generality and capability of the proposed learning scheme.

  11. Implementing Machine Learning in the PCWG Tool

    SciTech Connect

    Clifton, Andrew; Ding, Yu; Stuart, Peter

    2016-12-13

    The Power Curve Working Group (www.pcwg.org) is an ad-hoc industry-led group to investigate the performance of wind turbines in real-world conditions. As part of ongoing experience-sharing exercises, machine learning has been proposed as a possible way to predict turbine performance. This presentation provides some background information about machine learning and how it might be implemented in the PCWG exercises.

  12. Acceleration of saddle-point searches with machine learning.

    PubMed

    Peterson, Andrew A

    2016-08-21

    In atomistic simulations, the location of the saddle point on the potential-energy surface (PES) gives important information on transitions between local minima, for example, via transition-state theory. However, the search for saddle points often involves hundreds or thousands of ab initio force calls, which are typically all done at full accuracy. This results in the vast majority of the computational effort being spent calculating the electronic structure of states not important to the researcher, and very little time performing the calculation of the saddle point state itself. In this work, we describe how machine learning (ML) can reduce the number of intermediate ab initio calculations needed to locate saddle points. Since machine-learning models can learn from, and thus mimic, atomistic simulations, the saddle-point search can be conducted rapidly in the machine-learning representation. The saddle-point prediction can then be verified by an ab initio calculation; if it is incorrect, this strategically has identified regions of the PES where the machine-learning representation has insufficient training data. When these training data are used to improve the machine-learning model, the estimates greatly improve. This approach can be systematized, and in two simple example problems we demonstrate a dramatic reduction in the number of ab initio force calls. We expect that this approach and future refinements will greatly accelerate searches for saddle points, as well as other searches on the potential energy surface, as machine-learning methods see greater adoption by the atomistics community.

  13. Addressing uncertainty in atomistic machine learning.

    PubMed

    Peterson, Andrew A; Christensen, Rune; Khorshidi, Alireza

    2017-05-10

    Machine-learning regression has been demonstrated to precisely emulate the potential energy and forces that are output from more expensive electronic-structure calculations. However, to predict new regions of the potential energy surface, an assessment must be made of the credibility of the predictions. In this perspective, we address the types of errors that might arise in atomistic machine learning, the unique aspects of atomistic simulations that make machine-learning challenging, and highlight how uncertainty analysis can be used to assess the validity of machine-learning predictions. We suggest this will allow researchers to more fully use machine learning for the routine acceleration of large, high-accuracy, or extended-time simulations. In our demonstrations, we use a bootstrap ensemble of neural network-based calculators, and show that the width of the ensemble can provide an estimate of the uncertainty when the width is comparable to that in the training data. Intriguingly, we also show that the uncertainty can be localized to specific atoms in the simulation, which may offer hints for the generation of training data to strategically improve the machine-learned representation.

  14. Infection status outcome, machine learning method and virus type interact to affect the optimised prediction of hepatitis virus immunoassay results from routine pathology laboratory assays in unbalanced data.

    PubMed

    Richardson, Alice M; Lidbury, Brett A

    2013-06-25

    Advanced data mining techniques such as decision trees have been successfully used to predict a variety of outcomes in complex medical environments. Furthermore, previous research has shown that combining the results of a set of individually trained trees into an ensemble-based classifier can improve overall classification accuracy. This paper investigates the effect of data pre-processing, the use of ensembles constructed by bagging, and a simple majority vote to combine classification predictions from routine pathology laboratory data, particularly to overcome a large imbalance of negative Hepatitis B virus (HBV) and Hepatitis C virus (HCV) cases versus HBV or HCV immunoassay positive cases. These methods were illustrated using a never before analysed data set from ACT Pathology (Canberra, Australia) relating to HBV and HCV patients. It was easier to predict immunoassay positive cases than negative cases of HBV or HCV. While applying an ensemble-based approach rather than a single classifier had a small positive effect on the accuracy rate, this also varied depending on the virus under analysis. Finally, scaling data before prediction also has a small positive effect on the accuracy rate for this dataset. A graphical analysis of the distribution of accuracy rates across ensembles supports these findings. Laboratories looking to include machine learning as part of their decision support processes need to be aware that the infection outcome, the machine learning method used and the virus type interact to affect the enhanced laboratory diagnosis of hepatitis virus infection, as determined by primary immunoassay data in concert with multiple routine pathology laboratory variables. This awareness will lead to the informed use of existing machine learning methods, thus improving the quality of laboratory diagnosis via informatics analyses.

  15. Machine learning for biomedical literature triage.

    PubMed

    Almeida, Hayda; Meurs, Marie-Jean; Kosseim, Leila; Butler, Greg; Tsang, Adrian

    2014-01-01

    This paper presents a machine learning system for supporting the first task of the biological literature manual curation process, called triage. We compare the performance of various classification models, by experimenting with dataset sampling factors and a set of features, as well as three different machine learning algorithms (Naive Bayes, Support Vector Machine and Logistic Model Trees). The results show that the most fitting model to handle the imbalanced datasets of the triage classification task is obtained by using domain relevant features, an under-sampling technique, and the Logistic Model Trees algorithm.

  16. Producing landslide susceptibility maps by utilizing machine learning methods. The case of Finikas catchment basin, North Peloponnese, Greece.

    NASA Astrophysics Data System (ADS)

    Tsangaratos, Paraskevas; Ilia, Ioanna; Loupasakis, Constantinos; Papadakis, Michalis; Karimalis, Antonios

    2017-04-01

    The main objective of the present study was to apply two machine learning methods for the production of a landslide susceptibility map in the Finikas catchment basin, located in North Peloponnese, Greece and to compare their results. Specifically, Logistic Regression and Random Forest were utilized, based on a database of 40 sites classified into two categories, non-landslide and landslide areas that were separated into a training dataset (70% of the total data) and a validation dataset (remaining 30%). The identification of the areas was established by analyzing airborne imagery, extensive field investigation and the examination of previous research studies. Six landslide related variables were analyzed, namely: lithology, elevation, slope, aspect, distance to rivers and distance to faults. Within the Finikas catchment basin most of the reported landslides were located along the road network and within the residential complexes, classified as rotational and translational slides, and rockfalls, mainly caused due to the physical conditions and the general geotechnical behavior of the geological formation that cover the area. Each landslide susceptibility map was reclassified by applying the Geometric Interval classification technique into five classes, namely: very low susceptibility, low susceptibility, moderate susceptibility, high susceptibility, and very high susceptibility. The comparison and validation of the outcomes of each model were achieved using statistical evaluation measures, the receiving operating characteristic and the area under the success and predictive rate curves. The computation process was carried out using RStudio an integrated development environment for R language and ArcGIS 10.1 for compiling the data and producing the landslide susceptibility maps. From the outcomes of the Logistic Regression analysis it was induced that the highest b coefficient is allocated to lithology and slope, which was 2.8423 and 1.5841, respectively. From the

  17. Targeting Plague Virulence Factors: A Combined Machine Learning Method and Multiple Conformational Virtual Screening for the Discovery of Yersinia Protein Kinase A Inhibitors

    PubMed Central

    Hu, Xin; Prehna, Gerd; Stebbins, C. Erec

    2008-01-01

    Yersinia spp, is currently an antibiotic resistance concern and a re-emerging disease. An essential virulence factor YpkA, contains a Ser/Thr kinase domain whose activity modulates pathogenicity. Here we present an approach integrating a machine learning method, homology modeling, and multiple conformational high throughput docking for the discovery of YpkA inhibitors. These first reported inhibitors of YpkA may facilitate studies of pathogenic mechanism of YpkA, and serve as a starting point for development of anti-plague drugs. PMID:17676727

  18. Simple and efficient machine learning frameworks for identifying protein-protein interaction relevant articles and experimental methods used to study the interactions.

    PubMed

    Agarwal, Shashank; Liu, Feifan; Yu, Hong

    2011-10-03

    Protein-protein interaction (PPI) is an important biomedical phenomenon. Automatically detecting PPI-relevant articles and identifying methods that are used to study PPI are important text mining tasks. In this study, we have explored domain independent features to develop two open source machine learning frameworks. One performs binary classification to determine whether the given article is PPI relevant or not, named "Simple Classifier", and the other one maps the PPI relevant articles with corresponding interaction method nodes in a standardized PSI-MI (Proteomics Standards Initiative-Molecular Interactions) ontology, named "OntoNorm". We evaluated our system in the context of BioCreative challenge competition using the standardized data set. Our systems are amongst the top systems reported by the organizers, attaining 60.8% F1-score for identifying relevant documents, and 52.3% F1-score for mapping articles to interaction method ontology. Our results show that domain-independent machine learning frameworks can perform competitively well at the tasks of detecting PPI relevant articles and identifying the methods that were used to study the interaction in such articles. Simple Classifier is available at http://sourceforge.net/p/simpleclassify/home/ and OntoNorm at http://sourceforge.net/p/ontonorm/home/.

  19. A fast hybrid methodology based on machine learning, quantum methods, and experimental measurements for evaluating material properties

    NASA Astrophysics Data System (ADS)

    Kong, Chang Sun; Haverty, Michael; Simka, Harsono; Shankar, Sadasivan; Rajan, Krishna

    2017-09-01

    We present a hybrid approach based on both machine learning and targeted ab-initio calculations to determine adhesion energies between dissimilar materials. The goals of this approach are to complement experimental and/or all ab-initio computational efforts, to identify promising materials rapidly and identify in a quantitative manner the relative contributions of the different material attributes affecting adhesion. Applications of the methodology to predict bulk modulus, yield strength, adhesion and wetting properties of copper (Cu) with other materials including metals, nitrides and oxides is discussed in this paper. In the machine learning component of this methodology, the parameters that were chosen can be roughly divided into four types: atomic and crystalline parameters (which are related to specific elements such as electronegativities, electron densities in Wigner-Seitz cells); bulk material properties (e.g. melting point), mechanical properties (e.g. modulus) and those representing atomic characteristics in ab-initio formalisms (e.g. pseudopotentials). The atomic parameters are defined over one dataset to determine property correlation with published experimental data. We then develop a semi-empirical model across multiple datasets to predict adhesion in material interfaces outside the original datasets. Since adhesion is between two materials, we appropriately use parameters which indicate differences between the elements that comprise the materials. These semi-empirical predictions agree reasonably with the trend in chemical work of adhesion predicted using ab-initio techniques and are used for fast materials screening. For the screened candidates, the ab-initio modeling component provides fundamental understanding of the chemical interactions at the interface, and explains the wetting thermodynamics of thin Cu layers on various substrates. Comparison against ultra-high vacuum (UHV) experiments for well-characterized Cu/Ta and Cu/α-Al2O3 interfaces is

  20. Application of machine learning methods to describe the effects of conjugated equine estrogens therapy on region-specific brain volumes.

    PubMed

    Casanova, Ramon; Espeland, Mark A; Goveas, Joseph S; Davatzikos, Christos; Gaussoin, Sarah A; Maldjian, Joseph A; Brunner, Robert L; Kuller, Lewis H; Johnson, Karen C; Mysiw, W Jerry; Wagner, Benjamin; Resnick, Susan M

    2011-05-01

    Use of conjugated equine estrogens (CEE) has been linked to smaller regional brain volumes in women aged ≥65 years; however, it is unknown whether this results in a broad-based characteristic pattern of effects. Structural magnetic resonance imaging was used to assess regional volumes of normal tissue and ischemic lesions among 513 women who had been enrolled in a randomized clinical trial of CEE therapy for an average of 6.6 years, beginning at ages 65-80 years. A multivariate pattern analysis, based on a machine learning technique that combined Random Forest and logistic regression with L(1) penalty, was applied to identify patterns among regional volumes associated with therapy and whether patterns discriminate between treatment groups. The multivariate pattern analysis detected smaller regional volumes of normal tissue within the limbic and temporal lobes among women that had been assigned to CEE therapy. Mean decrements ranged as high as 7% in the left entorhinal cortex and 5% in the left perirhinal cortex, which exceeded the effect sizes reported previously in frontal lobe and hippocampus. Overall accuracy of classification based on these patterns, however, was projected to be only 54.5%. Prescription of CEE therapy for an average of 6.6 years is associated with lower regional brain volumes, but it does not induce a characteristic spatial pattern of changes in brain volumes of sufficient magnitude to discriminate users and nonusers.

  1. Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction

    NASA Astrophysics Data System (ADS)

    Belayneh, A.; Adamowski, J.; Khalil, B.; Quilty, J.

    2016-05-01

    This study explored the ability of coupled machine learning models and ensemble techniques to predict drought conditions in the Awash River Basin of Ethiopia. The potential of wavelet transforms coupled with the bootstrap and boosting ensemble techniques to develop reliable artificial neural network (ANN) and support vector regression (SVR) models was explored in this study for drought prediction. Wavelet analysis was used as a pre-processing tool and was shown to improve drought predictions. The Standardized Precipitation Index (SPI) (in this case SPI 3, SPI 12 and SPI 24) is a meteorological drought index that was forecasted using the aforementioned models and these SPI values represent short and long-term drought conditions. The performances of all models were compared using RMSE, MAE, and R2. The prediction results indicated that the use of the boosting ensemble technique consistently improved the correlation between observed and predicted SPIs. In addition, the use of wavelet analysis improved the prediction results of all models. Overall, the wavelet boosting ANN (WBS-ANN) and wavelet boosting SVR (WBS-SVR) models provided better prediction results compared to the other model types evaluated.

  2. Applications of Machine Learning in Cancer Prediction and Prognosis

    PubMed Central

    Cruz, Joseph A.; Wishart, David S.

    2006-01-01

    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. PMID:19458758

  3. A strategy for quantum algorithm design assisted by machine learning

    NASA Astrophysics Data System (ADS)

    Bang, Jeongho; Ryu, Junghee; Yoo, Seokwon; Pawłowski, Marcin; Lee, Jinhyoung

    2014-07-01

    We propose a method for quantum algorithm design assisted by machine learning. The method uses a quantum-classical hybrid simulator, where a ‘quantum student’ is being taught by a ‘classical teacher’. In other words, in our method, the learning system is supposed to evolve into a quantum algorithm for a given problem, assisted by a classical main-feedback system. Our method is applicable for designing quantum oracle-based algorithms. We chose, as a case study, an oracle decision problem, called a Deutsch-Jozsa problem. We showed by using Monte Carlo simulations that our simulator can faithfully learn a quantum algorithm for solving the problem for a given oracle. Remarkably, the learning time is proportional to the square root of the total number of parameters, rather than showing the exponential dependence found in the classical machine learning-based method.

  4. Photometric Supernova Classification with Machine Learning

    NASA Astrophysics Data System (ADS)

    Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.

    2016-08-01

    Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

  5. Machine Learning Phases of Strongly Correlated Fermions

    NASA Astrophysics Data System (ADS)

    Ch'ng, Kelvin; Carrasquilla, Juan; Melko, Roger G.; Khatami, Ehsan

    2017-07-01

    Machine learning offers an unprecedented perspective for the problem of classifying phases in condensed matter physics. We employ neural-network machine learning techniques to distinguish finite-temperature phases of the strongly correlated fermions on cubic lattices. We show that a three-dimensional convolutional network trained on auxiliary field configurations produced by quantum Monte Carlo simulations of the Hubbard model can correctly predict the magnetic phase diagram of the model at the average density of one (half filling). We then use the network, trained at half filling, to explore the trend in the transition temperature as the system is doped away from half filling. This transfer learning approach predicts that the instability to the magnetic phase extends to at least 5% doping in this region. Our results pave the way for other machine learning applications in correlated quantum many-body systems.

  6. Machine Learning, deep learning and optimization in computer vision

    NASA Astrophysics Data System (ADS)

    Canu, Stéphane

    2017-03-01

    As quoted in the Large Scale Computer Vision Systems NIPS workshop, computer vision is a mature field with a long tradition of research, but recent advances in machine learning, deep learning, representation learning and optimization have provided models with new capabilities to better understand visual content. The presentation will go through these new developments in machine learning covering basic motivations, ideas, models and optimization in deep learning for computer vision, identifying challenges and opportunities. It will focus on issues related with large scale learning that is: high dimensional features, large variety of visual classes, and large number of examples.

  7. Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes.

    PubMed

    Austin, Peter C; Tu, Jack V; Ho, Jennifer E; Levy, Daniel; Lee, Douglas S

    2013-04-01

    Physicians classify patients into those with or without a specific disease. Furthermore, there is often interest in classifying patients according to disease etiology or subtype. Classification trees are frequently used to classify patients according to the presence or absence of a disease. However, classification trees can suffer from limited accuracy. In the data-mining and machine-learning literature, alternate classification schemes have been developed. These include bootstrap aggregation (bagging), boosting, random forests, and support vector machines. We compared the performance of these classification methods with that of conventional classification trees to classify patients with heart failure (HF) according to the following subtypes: HF with preserved ejection fraction (HFPEF) and HF with reduced ejection fraction. We also compared the ability of these methods to predict the probability of the presence of HFPEF with that of conventional logistic regression. We found that modern, flexible tree-based methods from the data-mining literature offer substantial improvement in prediction and classification of HF subtype compared with conventional classification and regression trees. However, conventional logistic regression had superior performance for predicting the probability of the presence of HFPEF compared with the methods proposed in the data-mining literature. The use of tree-based methods offers superior performance over conventional classification and regression trees for predicting and classifying HF subtypes in a population-based sample of patients from Ontario, Canada. However, these methods do not offer substantial improvements over logistic regression for predicting the presence of HFPEF. Copyright © 2013 Elsevier Inc. All rights reserved.

  8. A method for the evaluation of image quality according to the recognition effectiveness of objects in the optical remote sensing image using machine learning algorithm.

    PubMed

    Yuan, Tao; Zheng, Xinqi; Hu, Xuan; Zhou, Wei; Wang, Wei

    2014-01-01

    Objective and effective image quality assessment (IQA) is directly related to the application of optical remote sensing images (ORSI). In this study, a new IQA method of standardizing the target object recognition rate (ORR) is presented to reflect quality. First, several quality degradation treatments with high-resolution ORSIs are implemented to model the ORSIs obtained in different imaging conditions; then, a machine learning algorithm is adopted for recognition experiments on a chosen target object to obtain ORRs; finally, a comparison with commonly used IQA indicators was performed to reveal their applicability and limitations. The results showed that the ORR of the original ORSI was calculated to be up to 81.95%, whereas the ORR ratios of the quality-degraded images to the original images were 65.52%, 64.58%, 71.21%, and 73.11%. The results show that these data can more accurately reflect the advantages and disadvantages of different images in object identification and information extraction when compared with conventional digital image assessment indexes. By recognizing the difference in image quality from the application effect perspective, using a machine learning algorithm to extract regional gray scale features of typical objects in the image for analysis, and quantitatively assessing quality of ORSI according to the difference, this method provides a new approach for objective ORSI assessment.

  9. Hypervelocity cutting machine and method

    DOEpatents

    Powell, James R.; Reich, Morris

    1996-11-12

    A method and machine 14 are provided for cutting a workpiece 12 such as concrete. A gun barrel 16 is provided for repetitively loading projectiles 22 therein and is supplied with a pressurized propellant from a storage tank 28. A thermal storage tank 32,32A is disposed between the propellant storage tank 28 and the gun barrel 16 for repetitively receiving and heating propellant charges which are released in the gun barrel 16 for repetitively firing projectiles 22 therefrom toward the workpiece 12. In a preferred embodiment, hypervelocity of the projectiles 22 is obtained for cutting the concrete workpiece 12 by fracturing thereof.

  10. Hypervelocity cutting machine and method

    DOEpatents

    Powell, J.R.; Reich, M.

    1996-11-12

    A method and machine are provided for cutting a workpiece such as concrete. A gun barrel is provided for repetitively loading projectiles therein and is supplied with a pressurized propellant from a storage tank. A thermal storage tank is disposed between the propellant storage tank and the gun barrel for repetitively receiving and heating propellant charges which are released in the gun barrel for repetitively firing projectiles therefrom toward the workpiece. In a preferred embodiment, hypervelocity of the projectiles is obtained for cutting the concrete workpiece by fracturing thereof. 10 figs.

  11. A study of the effectiveness of machine learning methods for classification of clinical interview fragments into a large number of categories.

    PubMed

    Hasan, Mehedi; Kotov, Alexander; Idalski Carcone, April; Dong, Ming; Naar, Sylvie; Brogan Hartlieb, Kathryn

    2016-08-01

    This study examines the effectiveness of state-of-the-art supervised machine learning methods in conjunction with different feature types for the task of automatic annotation of fragments of clinical text based on codebooks with a large number of categories. We used a collection of motivational interview transcripts consisting of 11,353 utterances, which were manually annotated by two human coders as the gold standard, and experimented with state-of-art classifiers, including Naïve Bayes, J48 Decision Tree, Support Vector Machine (SVM), Random Forest (RF), AdaBoost, DiscLDA, Conditional Random Fields (CRF) and Convolutional Neural Network (CNN) in conjunction with lexical, contextual (label of the previous utterance) and semantic (distribution of words in the utterance across the Linguistic Inquiry and Word Count dictionaries) features. We found out that, when the number of classes is large, the performance of CNN and CRF is inferior to SVM. When only lexical features were used, interview transcripts were automatically annotated by SVM with the highest classification accuracy among all classifiers of 70.8%, 61% and 53.7% based on the codebooks consisting of 17, 20 and 41 codes, respectively. Using contextual and semantic features, as well as their combination, in addition to lexical ones, improved the accuracy of SVM for annotation of utterances in motivational interview transcripts with a codebook consisting of 17 classes to 71.5%, 74.2%, and 75.1%, respectively. Our results demonstrate the potential of using machine learning methods in conjunction with lexical, semantic and contextual features for automatic annotation of clinical interview transcripts with near-human accuracy.

  12. Feasibility of Active Machine Learning for Multiclass Compound Classification.

    PubMed

    Lang, Tobias; Flachsenberg, Florian; von Luxburg, Ulrike; Rarey, Matthias

    2016-01-25

    A common task in the hit-to-lead process is classifying sets of compounds into multiple, usually structural classes, which build the groundwork for subsequent SAR studies. Machine learning techniques can be used to automate this process by learning classification models from training compounds of each class. Gathering class information for compounds can be cost-intensive as the required data needs to be provided by human experts or experiments. This paper studies whether active machine learning can be used to reduce the required number of training compounds. Active learning is a machine learning method which processes class label data in an iterative fashion. It has gained much attention in a broad range of application areas. In this paper, an active learning method for multiclass compound classification is proposed. This method selects informative training compounds so as to optimally support the learning progress. The combination with human feedback leads to a semiautomated interactive multiclass classification procedure. This method was investigated empirically on 15 compound classification tasks containing 86-2870 compounds in 3-38 classes. The empirical results show that active learning can solve these classification tasks using 10-80% of the data which would be necessary for standard learning techniques.

  13. Machine Learning for Biological Trajectory Classification Applications

    NASA Technical Reports Server (NTRS)

    Sbalzarini, Ivo F.; Theriot, Julie; Koumoutsakos, Petros

    2002-01-01

    Machine-learning techniques, including clustering algorithms, support vector machines and hidden Markov models, are applied to the task of classifying trajectories of moving keratocyte cells. The different algorithms axe compared to each other as well as to expert and non-expert test persons, using concepts from signal-detection theory. The algorithms performed very well as compared to humans, suggesting a robust tool for trajectory classification in biological applications.

  14. Extreme Learning Machines for spatial environmental data

    NASA Astrophysics Data System (ADS)

    Leuenberger, Michael; Kanevski, Mikhail

    2015-12-01

    The use of machine learning algorithms has increased in a wide variety of domains (from finance to biocomputing and astronomy), and nowadays has a significant impact on the geoscience community. In most real cases geoscience data modelling problems are multivariate, high dimensional, variable at several spatial scales, and are generated by non-linear processes. For such complex data, the spatial prediction of continuous (or categorical) variables is a challenging task. The aim of this paper is to investigate the potential of the recently developed Extreme Learning Machine (ELM) for environmental data analysis, modelling and spatial prediction purposes. An important contribution of this study deals with an application of a generic self-consistent methodology for environmental data driven modelling based on Extreme Learning Machine. Both real and simulated data are used to demonstrate applicability of ELM at different stages of the study to understand and justify the results.

  15. Introduction to machine learning for brain imaging.

    PubMed

    Lemm, Steven; Blankertz, Benjamin; Dickhaus, Thorsten; Müller, Klaus-Robert

    2011-05-15

    Machine learning and pattern recognition algorithms have in the past years developed to become a working horse in brain imaging and the computational neurosciences, as they are instrumental for mining vast amounts of neural data of ever increasing measurement precision and detecting minuscule signals from an overwhelming noise floor. They provide the means to decode and characterize task relevant brain states and to distinguish them from non-informative brain signals. While undoubtedly this machinery has helped to gain novel biological insights, it also holds the danger of potential unintentional abuse. Ideally machine learning techniques should be usable for any non-expert, however, unfortunately they are typically not. Overfitting and other pitfalls may occur and lead to spurious and nonsensical interpretation. The goal of this review is therefore to provide an accessible and clear introduction to the strengths and also the inherent dangers of machine learning usage in the neurosciences.

  16. A Machine-Learning-Driven Sky Model.

    PubMed

    Satylmys, Pynar; Bashford-Rogers, Thomas; Chalmers, Alan; Debattista, Kurt

    2017-01-01

    Sky illumination is responsible for much of the lighting in a virtual environment. A machine-learning-based approach can compactly represent sky illumination from both existing analytic sky models and from captured environment maps. The proposed approach can approximate the captured lighting at a significantly reduced memory cost and enable smooth transitions of sky lighting to be created from a small set of environment maps captured at discrete times of day. The author's results demonstrate accuracy close to the ground truth for both analytical and capture-based methods. The approach has a low runtime overhead, so it can be used as a generic approach for both offline and real-time applications.

  17. Machine Learning for Dynamical Mean Field Theory

    NASA Astrophysics Data System (ADS)

    Arsenault, Louis-Francois; Lopez-Bezanilla, Alejandro; von Lilienfeld, O. Anatole; Littlewood, P. B.; Millis, Andy

    2014-03-01

    Machine Learning (ML), an approach that infers new results from accumulated knowledge, is in use for a variety of tasks ranging from face and voice recognition to internet searching and has recently been gaining increasing importance in chemistry and physics. In this talk, we investigate the possibility of using ML to solve the equations of dynamical mean field theory which otherwise requires the (numerically very expensive) solution of a quantum impurity model. Our ML scheme requires the relation between two functions: the hybridization function describing the bare (local) electronic structure of a material and the self-energy describing the many body physics. We discuss the parameterization of the two functions for the exact diagonalization solver and present examples, beginning with the Anderson Impurity model with a fixed bath density of states, demonstrating the advantages and the pitfalls of the method. DOE contract DE-AC02-06CH11357.

  18. Machine learning in cell biology - teaching computers to recognize phenotypes.

    PubMed

    Sommer, Christoph; Gerlich, Daniel W

    2013-12-15

    Recent advances in microscope automation provide new opportunities for high-throughput cell biology, such as image-based screening. High-complex image analysis tasks often make the implementation of static and predefined processing rules a cumbersome effort. Machine-learning methods, instead, seek to use intrinsic data structure, as well as the expert annotations of biologists to infer models that can be used to solve versatile data analysis tasks. Here, we explain how machine-learning methods work and what needs to be considered for their successful application in cell biology. We outline how microscopy images can be converted into a data representation suitable for machine learning, and then introduce various state-of-the-art machine-learning algorithms, highlighting recent applications in image-based screening. Our Commentary aims to provide the biologist with a guide to the application of machine learning to microscopy assays and we therefore include extensive discussion on how to optimize experimental workflow as well as the data analysis pipeline.

  19. SAR ATR using genetics based machine learning

    NASA Astrophysics Data System (ADS)

    Ravichandran, B.; Gandhe, Avinash; Smith, Robert; Mehra, Raman

    2005-05-01

    Addressing the challenge of robust ATR, this paper describes the development and demonstration of Machine Learning for Robust ATR. The primary innovation of this work is the development of an automated way of developing heuristic inference rules that can draw on multiple models and multiple feature types to make more robust ATR decisions. The key realization is that this meta learning problem is one of structural learning; that can be conducted independently of parameter learning associated with each model and feature based technique, and more effectively draw on the strengths of all such techniques, and even information from unforeseen techniques. This is accomplished by using robust, genetics-based machine learning for the ill conditioned combinatorial problem of structural rule learning, while using statistical and mathematical techniques for parameter learning. This paper describes a learning classifier system approach (with evolutionary computation for structural learning) for robust ATR and points to a promising solution to the structural learning problem, across multiple feature types (which we will refer to as the meta-learning problem), for ATR with EOCs. This system was tested on MSTAR Public Release SAR data using nominal and extended operation conditions. These results were also compared against two baseline classifiers, a PCA based distance classifier and a MSE classifier. The systems were evaluated for accuracy (via training set classification) and robustness (via testing set classification). In both cases, the LCS based robust ATR system performed very well with accuracy over 99% and robustness over 80%.

  20. Paradigms for Realizing Machine Learning Algorithms.

    PubMed

    Agneeswaran, Vijay Srinivas; Tonpay, Pranay; Tiwary, Jayati

    2013-12-01

    The article explains the three generations of machine learning algorithms-with all three trying to operate on big data. The first generation tools are SAS, SPSS, etc., while second generation realizations include Mahout and RapidMiner (that work over Hadoop), and the third generation paradigms include Spark and GraphLab, among others. The essence of the article is that for a number of machine learning algorithms, it is important to look beyond the Hadoop's Map-Reduce paradigm in order to make them work on big data. A number of promising contenders have emerged in the third generation that can be exploited to realize deep analytics on big data.

  1. 3D Visualization of Machine Learning Algorithms with Astronomical Data

    NASA Astrophysics Data System (ADS)

    Kent, Brian R.

    2016-01-01

    We present innovative machine learning (ML) methods using unsupervised clustering with minimum spanning trees (MSTs) to study 3D astronomical catalogs. Utilizing Python code to build trees based on galaxy catalogs, we can render the results with the visualization suite Blender to produce interactive 360 degree panoramic videos. The catalogs and their ML results can be explored in a 3D space using mobile devices, tablets or desktop browsers. We compare the statistics of the MST results to a number of machine learning methods relating to optimization and efficiency.

  2. Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology.

    PubMed

    Zhang, Jieru; Ju, Ying; Lu, Huijuan; Xuan, Ping; Zou, Quan

    2016-01-01

    Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.

  3. Machine Learning: A Crucial Tool for Sensor Design

    PubMed Central

    Zhao, Weixiang; Bhushan, Abhinav; Santamaria, Anthony D.; Simon, Melinda G.; Davis, Cristina E.

    2009-01-01

    Sensors have been widely used for disease diagnosis, environmental quality monitoring, food quality control, industrial process analysis and control, and other related fields. As a key tool for sensor data analysis, machine learning is becoming a core part of novel sensor design. Dividing a complete machine learning process into three steps: data pre-treatment, feature extraction and dimension reduction, and system modeling, this paper provides a review of the methods that are widely used for each step. For each method, the principles and the key issues that affect modeling results are discussed. After reviewing the potential problems in machine learning processes, this paper gives a summary of current algorithms in this field and provides some feasible directions for future studies. PMID:20191110

  4. Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology

    PubMed Central

    Ju, Ying

    2016-01-01

    Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics. PMID:27478823

  5. Machine Learning: A Crucial Tool for Sensor Design.

    PubMed

    Zhao, Weixiang; Bhushan, Abhinav; Santamaria, Anthony D; Simon, Melinda G; Davis, Cristina E

    2008-12-01

    Sensors have been widely used for disease diagnosis, environmental quality monitoring, food quality control, industrial process analysis and control, and other related fields. As a key tool for sensor data analysis, machine learning is becoming a core part of novel sensor design. Dividing a complete machine learning process into three steps: data pre-treatment, feature extraction and dimension reduction, and system modeling, this paper provides a review of the methods that are widely used for each step. For each method, the principles and the key issues that affect modeling results are discussed. After reviewing the potential problems in machine learning processes, this paper gives a summary of current algorithms in this field and provides some feasible directions for future studies.

  6. Biochemical Profile of Heritage and Modern Apple Cultivars and Application of Machine Learning Methods To Predict Usage, Age, and Harvest Season.

    PubMed

    Anastasiadi, Maria; Mohareb, Fady; Redfern, Sally P; Berry, Mark; Simmonds, Monique S J; Terry, Leon A

    2017-07-05

    The present study represents the first major attempt to characterize the biochemical profile in different tissues of a large selection of apple cultivars sourced from the United Kingdom's National Fruit Collection comprising dessert, ornamental, cider, and culinary apples. Furthermore, advanced machine learning methods were applied with the objective to identify whether the phenolic and sugar composition of an apple cultivar could be used as a biomarker fingerprint to differentiate between heritage and mainstream commercial cultivars as well as govern the separation among primary usage groups and harvest season. A prediction accuracy of >90% was achieved with the random forest method for all three models. The results highlighted the extraordinary phytochemical potency and unique profile of some heritage, cider, and ornamental apple cultivars, especially in comparison to more mainstream apple cultivars. Therefore, these findings could guide future cultivar selection on the basis of health-promoting phytochemical content.

  7. A Machine Learning Based Framework for Adaptive Mobile Learning

    NASA Astrophysics Data System (ADS)

    Al-Hmouz, Ahmed; Shen, Jun; Yan, Jun

    Advances in wireless technology and handheld devices have created significant interest in mobile learning (m-learning) in recent years. Students nowadays are able to learn anywhere and at any time. Mobile learning environments must also cater for different user preferences and various devices with limited capability, where not all of the information is relevant and critical to each learning environment. To address this issue, this paper presents a framework that depicts the process of adapting learning content to satisfy individual learner characteristics by taking into consideration his/her learning style. We use a machine learning based algorithm for acquiring, representing, storing, reasoning and updating each learner acquired profile.

  8. Distributed fuzzy learning using the MULTISOFT machine.

    PubMed

    Russo, M

    2001-01-01

    Describes PARGEFREX, a distributed approach to genetic-neuro-fuzzy learning which has been implemented using the MULTISOFT machine, a low-cost form of personal computers built at the University of Messina. The performance of the serial version is hugely enhanced with the simple parallelization scheme described in the paper. Once a learning dataset is fixed, there is a very high super linear speedup in the average time needed to reach a prefixed learning error, i.e., if the number of personal computers increases by n times, the mean learning time becomes less than 1/n times.

  9. Application of advanced machine learning methods on resting-state fMRI network for identification of mild cognitive impairment and Alzheimer's disease.

    PubMed

    Khazaee, Ali; Ebrahimzadeh, Ata; Babajani-Feremi, Abbas

    2016-09-01

    The study of brain networks by resting-state functional magnetic resonance imaging (rs-fMRI) is a promising method for identifying patients with dementia from healthy controls (HC). Using graph theory, different aspects of the brain network can be efficiently characterized by calculating measures of integration and segregation. In this study, we combined a graph theoretical approach with advanced machine learning methods to study the brain network in 89 patients with mild cognitive impairment (MCI), 34 patients with Alzheimer's disease (AD), and 45 age-matched HC. The rs-fMRI connectivity matrix was constructed using a brain parcellation based on a 264 putative functional areas. Using the optimal features extracted from the graph measures, we were able to accurately classify three groups (i.e., HC, MCI, and AD) with accuracy of 88.4 %. We also investigated performance of our proposed method for a binary classification of a group (e.g., MCI) from two other groups (e.g., HC and AD). The classification accuracies for identifying HC from AD and MCI, AD from HC and MCI, and MCI from HC and AD, were 87.3, 97.5, and 72.0 %, respectively. In addition, results based on the parcellation of 264 regions were compared to that of the automated anatomical labeling atlas (AAL), consisted of 90 regions. The accuracy of classification of three groups using AAL was degraded to 83.2 %. Our results show that combining the graph measures with the machine learning approach, on the basis of the rs-fMRI connectivity analysis, may assist in diagnosis of AD and MCI.

  10. A machine learning-based method to improve docking scoring functions and its application to drug repurposing.

    PubMed

    Kinnings, Sarah L; Liu, Nina; Tonge, Peter J; Jackson, Richard M; Xie, Lei; Bourne, Philip E

    2011-02-28

    Docking scoring functions are notoriously weak predictors of binding affinity. They typically assign a common set of weights to the individual energy terms that contribute to the overall energy score; however, these weights should be gene family dependent. In addition, they incorrectly assume that individual interactions contribute toward the total binding affinity in an additive manner. In reality, noncovalent interactions often depend on one another in a nonlinear manner. In this paper, we show how the use of support vector machines (SVMs), trained by associating sets of individual energy terms retrieved from molecular docking with the known binding affinity of each compound from high-throughput screening experiments, can be used to improve the correlation between known binding affinities and those predicted by the docking program eHiTS. We construct two prediction models: a regression model trained using IC(50) values from BindingDB, and a classification model trained using active and decoy compounds from the Directory of Useful Decoys (DUD). Moreover, to address the issue of overrepresentation of negative data in high-throughput screening data sets, we have designed a multiple-planar SVM training procedure for the classification model. The increased performance that both SVMs give when compared with the original eHiTS scoring function highlights the potential for using nonlinear methods when deriving overall energy scores from their individual components. We apply the above methodology to train a new scoring function for direct inhibitors of Mycobacterium tuberculosis (M.tb) InhA. By combining ligand binding site comparison with the new scoring function, we propose that phosphodiesterase inhibitors can potentially be repurposed to target M.tb InhA. Our methodology may be applied to other gene families for which target structures and activity data are available, as demonstrated in the work presented here.

  11. Movement error rate for evaluation of machine learning methods for sEMG-based hand movement classification.

    PubMed

    Gijsberts, Arjan; Atzori, Manfredo; Castellini, Claudio; Muller, Henning; Caputo, Barbara

    2014-07-01

    There has been increasing interest in applying learning algorithms to improve the dexterity of myoelectric prostheses. In this work, we present a large-scale benchmark evaluation on the second iteration of the publicly released NinaPro database, which contains surface electromyography data for 6 DOF force activations as well as for 40 discrete hand movements. The evaluation involves a modern kernel method and compares performance of three feature representations and three kernel functions. Both the force regression and movement classification problems can be learned successfully when using a nonlinear kernel function, while the exp- χ(2) kernel outperforms the more popular radial basis function kernel in all cases. Furthermore, combining surface electromyography and accelerometry in a multimodal classifier results in significant increases in accuracy as compared to when either modality is used individually. Since window-based classification accuracy should not be considered in isolation to estimate prosthetic controllability, we also provide results in terms of classification mistakes and prediction delay. To this extent, we propose the movement error rate as an alternative to the standard window-based accuracy. This error rate is insensitive to prediction delays and it allows us therefore to quantify mistakes and delays as independent performance characteristics. This type of analysis confirms that the inclusion of accelerometry is superior, as it results in fewer mistakes while at the same time reducing prediction delay.

  12. Machine Learning Toolkit for Extreme Scale

    SciTech Connect

    2014-03-31

    Support Vector Machines (SVM) is a popular machine learning technique, which has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. MaTEx undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Several techniques are proposed for improved speed and memory space usage including adaptive and aggressive elimination of samples for faster convergence , and sparse format representation of data samples. Several heuristics for earliest possible to lazy elimination of non-contributing samples are considered in MaTEx. In many cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The proposed algorithm and heuristics are implemented and evaluated on various publicly available datasets

  13. Machine Learning Toolkit for Extreme Scale

    SciTech Connect

    2014-03-31

    Support Vector Machines (SVM) is a popular machine learning technique, which has been applied to a wide range of domains such as science, finance, and social networks for supervised learning. MaTEx undertakes the challenge of designing a scalable parallel SVM training algorithm for large scale systems, which includes commodity multi-core machines, tightly connected supercomputers and cloud computing systems. Several techniques are proposed for improved speed and memory space usage including adaptive and aggressive elimination of samples for faster convergence , and sparse format representation of data samples. Several heuristics for earliest possible to lazy elimination of non-contributing samples are considered in MaTEx. In many cases, where an early sample elimination might result in a false positive, low overhead mechanisms for reconstruction of key data structures are proposed. The proposed algorithm and heuristics are implemented and evaluated on various publicly available datasets

  14. Machine Learning Applications to Resting-State Functional MR Imaging Analysis.

    PubMed

    Billings, John M; Eder, Maxwell; Flood, William C; Dhami, Devendra Singh; Natarajan, Sriraam; Whitlow, Christopher T

    2017-11-01

    Machine learning is one of the most exciting and rapidly expanding fields within computer science. Academic and commercial research entities are investing in machine learning methods, especially in personalized medicine via patient-level classification. There is great promise that machine learning methods combined with resting state functional MR imaging will aid in diagnosis of disease and guide potential treatment for conditions thought to be impossible to identify based on imaging alone, such as psychiatric disorders. We discuss machine learning methods and explore recent advances. Copyright © 2017 Elsevier Inc. All rights reserved.

  15. Dimension Reduction with Extreme Learning Machine.

    PubMed

    Liyanaarachchi Lekamalage, Chamara; Yang, Yan; Huang, Guang-Bin; Zhang, Zhengyou

    2016-05-18

    Data may often contain noise or irrelevant information which negatively affect the generalization capability of machine learning algorithms. The objective of dimension reduction algorithms such as Principal Component Analysis (PCA), Non-negative Matrix Factorization (NMF), random projection (RP) and auto-encoder (AE) is to reduce the noise or irrelevant information of the data. The features of PCA (eigenvectors) and linear AE is not able to represent data as parts (e.g. nose in a face image); On the other hand, NMF and non-linear AE is maimed by slow learning speed and RP only represents a subspace of original data. This paper introduces a dimension reduction framework which to some extend represents data as parts, has fast learning speed and learns the between-class scatter subspace. To this end, this paper investigates a linear and nonlinear dimension reduction framework referred to as Extreme Learning Machine Auto-Encoder (ELM-AE) and Sparse Extreme Learning Machine Auto-Encoder (SELM-AE). In contrast to tied weight auto-encoder (TAE), the hidden neurons in ELMAE and SELM-AE need not be tuned, their parameters (e.g, input weights in additive neurons) are initialized using orthogonal and sparse random weights respectively. Experimental results on USPS handwritten digit recognition dataset, CIFAR-10 object recognition and NORB object recognition data set show the efficacy of linear and non-linear ELM-AE and SELM-AE in terms of discriminative capability, sparsity, training time and Normalized Mean Square Error (NMSE).

  16. Using Simple Machines to Leverage Learning

    ERIC Educational Resources Information Center

    Dotger, Sharon

    2008-01-01

    What would your students say if you told them they could lift you off the ground using a block and a board? Using a simple machine, they'll find out they can, and they'll learn about work, energy, and motion in the process! In addition, this integrated lesson gives students the opportunity to investigate variables while practicing measurement…

  17. Using Simple Machines to Leverage Learning

    ERIC Educational Resources Information Center

    Dotger, Sharon

    2008-01-01

    What would your students say if you told them they could lift you off the ground using a block and a board? Using a simple machine, they'll find out they can, and they'll learn about work, energy, and motion in the process! In addition, this integrated lesson gives students the opportunity to investigate variables while practicing measurement…

  18. Machine learning and computer vision approaches for phenotypic profiling.

    PubMed

    Grys, Ben T; Lo, Dara S; Sahin, Nil; Kraus, Oren Z; Morris, Quaid; Boone, Charles; Andrews, Brenda J

    2017-01-02

    With recent advances in high-throughput, automated microscopy, there has been an increased demand for effective computational strategies to analyze large-scale, image-based data. To this end, computer vision approaches have been applied to cell segmentation and feature extraction, whereas machine-learning approaches have been developed to aid in phenotypic classification and clustering of data acquired from biological images. Here, we provide an overview of the commonly used computer vision and machine-learning methods for generating and categorizing phenotypic profiles, highlighting the general biological utility of each approach. © 2017 Grys et al.

  19. The Efficacy of Machine Learning Programs for Navy Manpower Analysis

    DTIC Science & Technology

    1993-03-01

    This thesis investigated the efficacy of two machine learning programs for Navy manpower analysis. Two machine learning programs, AIM and IXL, were...to generate models from the two commercial machine learning programs. Using a held out sub-set of the data the capabilities of the three models were...partial effects. The author recommended further investigation of AIM’s capabilities, and testing in an operational environment.... Machine learning , AIM, IXL.

  20. Machine learning for real time remote detection

    NASA Astrophysics Data System (ADS)

    Labbé, Benjamin; Fournier, Jérôme; Henaff, Gilles; Bascle, Bénédicte; Canu, Stéphane

    2010-10-01

    Infrared systems are key to providing enhanced capability to military forces such as automatic control of threats and prevention from air, naval and ground attacks. Key requirements for such a system to produce operational benefits are real-time processing as well as high efficiency in terms of detection and false alarm rate. These are serious issues since the system must deal with a large number of objects and categories to be recognized (small vehicles, armored vehicles, planes, buildings, etc.). Statistical learning based algorithms are promising candidates to meet these requirements when using selected discriminant features and real-time implementation. This paper proposes a new decision architecture benefiting from recent advances in machine learning by using an effective method for level set estimation. While building decision function, the proposed approach performs variable selection based on a discriminative criterion. Moreover, the use of level set makes it possible to manage rejection of unknown or ambiguous objects thus preserving the false alarm rate. Experimental evidences reported on real world infrared images demonstrate the validity of our approach.

  1. Improving propensity score weighting using machine learning

    PubMed Central

    Lee, Brian K.; Lessler, Justin; Stuart, Elizabeth A.

    2009-01-01

    Machine learning techniques such as classification and regression trees (CART) have been suggested as promising alternatives to logistic regression for the estimation of propensity scores. The authors examined the performance of various CART-based propensity score models using simulated data. Hypothetical studies of varying sample sizes (n=500, 1000, 2000) with a binary exposure, continuous outcome, and ten covariates were simulated under seven scenarios differing by degree of non-linear and non-additive associations between covariates and the exposure. Propensity score weights were estimated using logistic regression (all main effects), CART, pruned CART, and the ensemble methods of bagged CART, random forests, and boosted CART. Performance metrics included covariate balance, standard error, percent absolute bias, and 95% confidence interval coverage. All methods displayed generally acceptable performance under conditions of either non-linearity or non-additivity alone. However, under conditions of both moderate non-additivity and moderate non-linearity, logistic regression had subpar performance, while ensemble methods provided substantially better bias reduction and more consistent 95% CI coverage. The results suggest that ensemble methods, especially boosted CART, may be useful for propensity score weighting. PMID:19960510

  2. Machine Learning and Quantum Mechanics

    NASA Astrophysics Data System (ADS)

    Chapline, George

    The author has previously pointed out some similarities between selforganizing neural networks and quantum mechanics. These types of neural networks were originally conceived of as away of emulating the cognitive capabilities of the human brain. Recently extensions of these networks, collectively referred to as deep learning networks, have strengthened the connection between self-organizing neural networks and human cognitive capabilities. In this note we consider whether hardware quantum devices might be useful for emulating neural networks with human-like cognitive capabilities, or alternatively whether implementations of deep learning neural networks using conventional computers might lead to better algorithms for solving the many body Schrodinger equation.

  3. Noninvasive Intracranial Pressure Monitoring Using Advanced Machine Learning Techniques

    DTIC Science & Technology

    2013-11-01

    This project explored the use of advanced machine learning techniques to noninvasively estimate real-time intracranial pressure (ICP) in traumatic...brain injury patients from continuous electronic physiological monitoring data. We hypothesized that advanced machine learning techniques could process...provide a valid analytic platform for the noninvasive monitoring of ICP for defined periods and clinical needs. We developed a machine learning algorithm

  4. Learning algorithms for human-machine interfaces.

    PubMed

    Danziger, Zachary; Fishbach, Alon; Mussa-Ivaldi, Ferdinando A

    2009-05-01

    The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore-Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction.

  5. Learning Algorithms for Human–Machine Interfaces

    PubMed Central

    Fishbach, Alon; Mussa-Ivaldi, Ferdinando A.

    2012-01-01

    The goal of this study is to create and examine machine learning algorithms that adapt in a controlled and cadenced way to foster a harmonious learning environment between the user and the controlled device. To evaluate these algorithms, we have developed a simple experimental framework. Subjects wear an instrumented data glove that records finger motions. The high-dimensional glove signals remotely control the joint angles of a simulated planar two-link arm on a computer screen, which is used to acquire targets. A machine learning algorithm was applied to adaptively change the transformation between finger motion and the simulated robot arm. This algorithm was either LMS gradient descent or the Moore–Penrose (MP) pseudoinverse transformation. Both algorithms modified the glove-to-joint angle map so as to reduce the endpoint errors measured in past performance. The MP group performed worse than the control group (subjects not exposed to any machine learning), while the LMS group outperformed the control subjects. However, the LMS subjects failed to achieve better generalization than the control subjects, and after extensive training converged to the same level of performance as the control subjects. These results highlight the limitations of coadaptive learning using only endpoint error reduction. PMID:19203886

  6. The Learning Machine: Home Remedies.

    ERIC Educational Resources Information Center

    Huntington, Fred

    1984-01-01

    Presents a list of Apple software that helps students develop specific skills through supplemental learning at home. Software, including program, manufacturer, grade level(s), and price, is provided for: writing; spelling; grammar; vocabulary; reading comprehension; computational mathematics; and mathematics concepts/applications. Also provides…

  7. Machine learning techniques for fault isolation and sensor placement

    NASA Technical Reports Server (NTRS)

    Carnes, James R.; Fisher, Douglas H.

    1993-01-01

    Fault isolation and sensor placement are vital for monitoring and diagnosis. A sensor conveys information about a system's state that guides troubleshooting if problems arise. We are using machine learning methods to uncover behavioral patterns over snapshots of system simulations that will aid fault isolation and sensor placement, with an eye towards minimality, fault coverage, and noise tolerance.

  8. Research on knowledge representation, machine learning, and knowledge acquisition

    NASA Technical Reports Server (NTRS)

    Buchanan, Bruce G.

    1987-01-01

    Research in knowledge representation, machine learning, and knowledge acquisition performed at Knowledge Systems Lab. is summarized. The major goal of the research was to develop flexible, effective methods for representing the qualitative knowledge necessary for solving large problems that require symbolic reasoning as well as numerical computation. The research focused on integrating different representation methods to describe different kinds of knowledge more effectively than any one method can alone. In particular, emphasis was placed on representing and using spatial information about three dimensional objects and constraints on the arrangement of these objects in space. Another major theme is the development of robust machine learning programs that can be integrated with a variety of intelligent systems. To achieve this goal, learning methods were designed, implemented and experimented within several different problem solving environments.

  9. Combining data mining and machine learning for effective user profiling

    SciTech Connect

    Fawcett, T.; Provost, F.

    1996-12-31

    This paper describes the automatic design of methods for detecting fraudulent behavior. Much of the design is accomplished using a series of machine learning methods. In particular, we combine data mining and constructive induction with more standard machine learning techniques to design methods for detecting fraudulent usage of cellular telephones based on profiling customer behavior. Specifically, we use a rule-learning program to uncover indicators of fraudulent behavior from a large database of cellular calls. These indicators are used to create profilers, which then serve as features to a system that combines evidence from multiple profilers to generate high-confidence alarms. Experiments indicate that this automatic approach performs nearly as well as the best hand-tuned methods for detecting fraud.

  10. Optimal interference code based on machine learning

    NASA Astrophysics Data System (ADS)

    Qian, Ye; Chen, Qian; Hu, Xiaobo; Cao, Ercong; Qian, Weixian; Gu, Guohua

    2016-10-01

    In this paper, we analyze the characteristics of pseudo-random code, by the case of m sequence. Depending on the description of coding theory, we introduce the jamming methods. We simulate the interference effect or probability model by the means of MATLAB to consolidate. In accordance with the length of decoding time the adversary spends, we find out the optimal formula and optimal coefficients based on machine learning, then we get the new optimal interference code. First, when it comes to the phase of recognition, this study judges the effect of interference by the way of simulating the length of time over the decoding period of laser seeker. Then, we use laser active deception jamming simulate interference process in the tracking phase in the next block. In this study we choose the method of laser active deception jamming. In order to improve the performance of the interference, this paper simulates the model by MATLAB software. We find out the least number of pulse intervals which must be received, then we can make the conclusion that the precise interval number of the laser pointer for m sequence encoding. In order to find the shortest space, we make the choice of the greatest common divisor method. Then, combining with the coding regularity that has been found before, we restore pulse interval of pseudo-random code, which has been already received. Finally, we can control the time period of laser interference, get the optimal interference code, and also increase the probability of interference as well.

  11. Modeling electronic quantum transport with machine learning

    NASA Astrophysics Data System (ADS)

    Lopez-Bezanilla, Alejandro; von Lilienfeld, O. Anatole

    2014-06-01

    We present a machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test data sets to the machine. The system's representation encodes energetic as well as geometrical information to characterize similarities between disordered configurations, while the Euclidean norm is used as a measure of similarity. Errors for out-of-sample predictions systematically decrease with training set size, enabling the accurate and fast prediction of new transmission coefficients. The remarkable performance of our model to capture the complexity of interference phenomena lends further support to its viability in dealing with transport problems of undulatory nature.

  12. From machine learning to deep learning: progress in machine intelligence for rational drug discovery.

    PubMed

    Zhang, Lu; Tan, Jianjun; Han, Dan; Zhu, Hao

    2017-09-04

    Machine intelligence, which is normally presented as artificial intelligence, refers to the intelligence exhibited by computers. In the history of rational drug discovery, various machine intelligence approaches have been applied to guide traditional experiments, which are expensive and time-consuming. Over the past several decades, machine-learning tools, such as quantitative structure-activity relationship (QSAR) modeling, were developed that can identify potential biological active molecules from millions of candidate compounds quickly and cheaply. However, when drug discovery moved into the era of 'big' data, machine learning approaches evolved into deep learning approaches, which are a more powerful and efficient way to deal with the massive amounts of data generated from modern drug discovery approaches. Here, we summarize the history of machine learning and provide insight into recently developed deep learning approaches and their applications in rational drug discovery. We suggest that this evolution of machine intelligence now provides a guide for early-stage drug design and discovery in the current big data era. Copyright © 2017 Elsevier Ltd. All rights reserved.

  13. Many-body physics via machine learning

    NASA Astrophysics Data System (ADS)

    Arsenault, Louis-Francois; von Lilienfeld, O. Anatole; Millis, Andrew J.

    We demonstrate a method for the use of machine learning (ML) to solve the equations of many-body physics, which are functional equations linking a bare to an interacting Green's function (or self-energy) offering transferable power of prediction for physical quantities for both the forward and the reverse engineering problem of materials. Functions are represented by coefficients in an orthogonal polynomial expansion and kernel ridge regression is used. The method is demonstrated using as an example a database built from Dynamical Mean Field theory (DMFT) calculations on the three dimensional Hubbard model. We discuss the extension to a database for real materials. We also discuss some new area of investigation concerning high throughput predictions for real materials by offering a perspective of how our scheme is general enough for applications to other problems involving the inversion of integral equations from the integrated knowledge such as the analytical continuation of the Green's function and the reconstruction of lattice structures from X-ray spectra. Office of Science of the U.S. Department of Energy under SubContract DOE No. 3F-3138 and FG-ER04169.

  14. Outsmarting neural networks: an alternative paradigm for machine learning

    SciTech Connect

    Protopopescu, V.; Rao, N.S.V.

    1996-10-01

    We address three problems in machine learning, namely: (i) function learning, (ii) regression estimation, and (iii) sensor fusion, in the Probably and Approximately Correct (PAC) framework. We show that, under certain conditions, one can reduce the three problems above to the regression estimation. The latter is usually tackled with artificial neural networks (ANNs) that satisfy the PAC criteria, but have high computational complexity. We propose several computationally efficient PAC alternatives to ANNs to solve the regression estimation. Thereby we also provide efficient PAC solutions to the function learning and sensor fusion problems. The approach is based on cross-fertilizing concepts and methods from statistical estimation, nonlinear algorithms, and the theory of computational complexity, and is designed as part of a new, coherent paradigm for machine learning.

  15. Machine learning for science: state of the art and future prospects.

    PubMed

    Mjolsness, E; DeCoste, D

    2001-09-14

    Recent advances in machine learning methods, along with successful applications across a wide variety of fields such as planetary science and bioinformatics, promise powerful new tools for practicing scientists. This viewpoint highlights some useful characteristics of modern machine learning methods and their relevance to scientific applications. We conclude with some speculations on near-term progress and promising directions.

  16. Committee of machine learning predictors of hydrological models uncertainty

    NASA Astrophysics Data System (ADS)

    Kayastha, Nagendra; Solomatine, Dimitri

    2014-05-01

    In prediction of uncertainty based on machine learning methods, the results of various sampling schemes namely, Monte Carlo sampling (MCS), generalized likelihood uncertainty estimation (GLUE), Markov chain Monte Carlo (MCMC), shuffled complex evolution metropolis algorithm (SCEMUA), differential evolution adaptive metropolis (DREAM), particle swarm optimization (PSO) and adaptive cluster covering (ACCO)[1] used to build a predictive models. These models predict the uncertainty (quantiles of pdf) of a deterministic output from hydrological model [2]. Inputs to these models are the specially identified representative variables (past events precipitation and flows). The trained machine learning models are then employed to predict the model output uncertainty which is specific for the new input data. For each sampling scheme three machine learning methods namely, artificial neural networks, model tree, locally weighted regression are applied to predict output uncertainties. The problem here is that different sampling algorithms result in different data sets used to train different machine learning models which leads to several models (21 predictive uncertainty models). There is no clear evidence which model is the best since there is no basis for comparison. A solution could be to form a committee of all models and to sue a dynamic averaging scheme to generate the final output [3]. This approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model HBV in the Nzoia catchment in Kenya. [1] N. Kayastha, D. L. Shrestha and D. P. Solomatine. Experiments with several methods of parameter uncertainty estimation in hydrological modeling. Proc. 9th Intern. Conf. on Hydroinformatics, Tianjin, China, September 2010. [2] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press

  17. Manifold learning in machine vision and robotics

    NASA Astrophysics Data System (ADS)

    Bernstein, Alexander

    2017-02-01

    Smart algorithms are used in Machine vision and Robotics to organize or extract high-level information from the available data. Nowadays, Machine learning is an essential and ubiquitous tool to automate extraction patterns or regularities from data (images in Machine vision; camera, laser, and sonar sensors data in Robotics) in order to solve various subject-oriented tasks such as understanding and classification of images content, navigation of mobile autonomous robot in uncertain environments, robot manipulation in medical robotics and computer-assisted surgery, and other. Usually such data have high dimensionality, however, due to various dependencies between their components and constraints caused by physical reasons, all "feasible and usable data" occupy only a very small part in high dimensional "observation space" with smaller intrinsic dimensionality. Generally accepted model of such data is manifold model in accordance with which the data lie on or near an unknown manifold (surface) of lower dimensionality embedded in an ambient high dimensional observation space; real-world high-dimensional data obtained from "natural" sources meet, as a rule, this model. The use of Manifold learning technique in Machine vision and Robotics, which discovers a low-dimensional structure of high dimensional data and results in effective algorithms for solving of a large number of various subject-oriented tasks, is the content of the conference plenary speech some topics of which are in the paper.

  18. AstroML: Python-powered Machine Learning for Astronomy

    NASA Astrophysics Data System (ADS)

    Vander Plas, Jake; Connolly, A. J.; Ivezic, Z.

    2014-01-01

    As astronomical data sets grow in size and complexity, automated machine learning and data mining methods are becoming an increasingly fundamental component of research in the field. The astroML project (http://astroML.org) provides a common repository for practical examples of the data mining and machine learning tools used and developed by astronomical researchers, written in Python. The astroML module contains a host of general-purpose data analysis and machine learning routines, loaders for openly-available astronomical datasets, and fast implementations of specific computational methods often used in astronomy and astrophysics. The associated website features hundreds of examples of these routines being used for analysis of real astronomical datasets, while the associated textbook provides a curriculum resource for graduate-level courses focusing on practical statistics, machine learning, and data mining approaches within Astronomical research. This poster will highlight several of the more powerful and unique examples of analysis performed with astroML, all of which can be reproduced in their entirety on any computer with the proper packages installed.

  19. Machine-Learning Algorithms to Code Public Health Spending Accounts.

    PubMed

    Brady, Eoghan S; Leider, Jonathon P; Resnick, Beth A; Alfonso, Y Natalia; Bishai, David

    Government public health expenditure data sets require time- and labor-intensive manipulation to summarize results that public health policy makers can use. Our objective was to compare the performances of machine-learning algorithms with manual classification of public health expenditures to determine if machines could provide a faster, cheaper alternative to manual classification. We used machine-learning algorithms to replicate the process of manually classifying state public health expenditures, using the standardized public health spending categories from the Foundational Public Health Services model and a large data set from the US Census Bureau. We obtained a data set of 1.9 million individual expenditure items from 2000 to 2013. We collapsed these data into 147 280 summary expenditure records, and we followed a standardized method of manually classifying each expenditure record as public health, maybe public health, or not public health. We then trained 9 machine-learning algorithms to replicate the manual process. We calculated recall, precision, and coverage rates to measure the performance of individual and ensembled algorithms. Compared with manual classification, the machine-learning random forests algorithm produced 84% recall and 91% precision. With algorithm ensembling, we achieved our target criterion of 90% recall by using a consensus ensemble of ≥6 algorithms while still retaining 93% coverage, leaving only 7% of the summary expenditure records unclassified. Machine learning can be a time- and cost-saving tool for estimating public health spending in the United States. It can be used with standardized public health spending categories based on the Foundational Public Health Services model to help parse public health expenditure information from other types of health-related spending, provide data that are more comparable across public health organizations, and evaluate the impact of evidence-based public health resource allocation.

  20. Research on machine learning framework based on random forest algorithm

    NASA Astrophysics Data System (ADS)

    Ren, Qiong; Cheng, Hui; Han, Hai

    2017-03-01

    With the continuous development of machine learning, industry and academia have released a lot of machine learning frameworks based on distributed computing platform, and have been widely used. However, the existing framework of machine learning is limited by the limitations of machine learning algorithm itself, such as the choice of parameters and the interference of noises, the high using threshold and so on. This paper introduces the research background of machine learning framework, and combined with the commonly used random forest algorithm in machine learning classification algorithm, puts forward the research objectives and content, proposes an improved adaptive random forest algorithm (referred to as ARF), and on the basis of ARF, designs and implements the machine learning framework.

  1. Radio Frequency Interference Detection using Machine Learning.

    NASA Astrophysics Data System (ADS)

    Mosiane, Olorato; Oozeer, Nadeem; Aniyan, Arun; Bassett, Bruce A.

    2017-05-01

    Radio frequency interference (RFI) has plagued radio astronomy which potentially might be as bad or worse by the time the Square Kilometre Array (SKA) comes up. RFI can be either internal (generated by instruments) or external that originates from intentional or unintentional radio emission generated by man. With the huge amount of data that will be available with up coming radio telescopes, an automated aproach will be required to detect RFI. In this paper to try automate this process we present the result of applying machine learning techniques to cross match RFI from the Karoo Array Telescope (KAT-7) data. We found that not all the features selected to characterise RFI are always important. We further investigated 3 machine learning techniques and conclude that the Random forest classifier performs with a 98% Area Under Curve and 91% recall in detecting RFI.

  2. Machine learning: how to get more out of HEP data and the Higgs Boson Machine Learning Challenge

    NASA Astrophysics Data System (ADS)

    Wolter, Marcin

    2015-09-01

    Multivariate techniques using machine learning algorithms have become an integral part in many High Energy Physics (HEP) data analyses. The article shows the gain in physics reach of the physics experiments due to the adaptation of machine learning techniques. Rapid development in the field of machine learning in the last years is a challenge for the HEP community. The open competition for machine learning experts "Higgs Boson Machine Learning Challenge" shows, that the modern techniques developed outside HEP can significantly improve the analysis of data from HEP experiments and improve the sensitivity of searches for new particles and processes.

  3. Learning in higher order Boltzmann machines using linear response.

    PubMed

    Leisink, M A; Kappen, H J

    2000-04-01

    We introduce an efficient method for learning and inference in higher order Boltzmann machines. The method is based on mean field theory with the linear response correction. We compute the correlations using the exact and the approximated method for a fully connected third order network of ten neurons. In addition, we compare the results of the exact and approximate learning algorithm. Finally we use the presented method to solve the shifter problem. We conclude that the linear response approximation gives good results as long as the couplings are not too large.

  4. A Machine Learning Approach to Student Modeling.

    DTIC Science & Technology

    1984-05-01

    machine learning , and describe ACN, a student modeling system that incorporates this approach. This system begins with a set of overly general rules, which it uses to search a problem space until it arrives at the same answer as the student. The ACM computer program then uses the solution path it has discovered to determine positive and negative instances of its initial rules, and employs a discrimination learning mechanism to place additional conditions on these rules. The revised rules will reproduce the solution path without search, and constitute a cognitive model of

  5. Quantum Loop Topography for Machine Learning.

    PubMed

    Zhang, Yi; Kim, Eun-Ah

    2017-05-26

    Despite rapidly growing interest in harnessing machine learning in the study of quantum many-body systems, training neural networks to identify quantum phases is a nontrivial challenge. The key challenge is in efficiently extracting essential information from the many-body Hamiltonian or wave function and turning the information into an image that can be fed into a neural network. When targeting topological phases, this task becomes particularly challenging as topological phases are defined in terms of nonlocal properties. Here, we introduce quantum loop topography (QLT): a procedure of constructing a multidimensional image from the "sample" Hamiltonian or wave function by evaluating two-point operators that form loops at independent Monte Carlo steps. The loop configuration is guided by the characteristic response for defining the phase, which is Hall conductivity for the cases at hand. Feeding QLT to a fully connected neural network with a single hidden layer, we demonstrate that the architecture can be effectively trained to distinguish the Chern insulator and the fractional Chern insulator from trivial insulators with high fidelity. In addition to establishing the first case of obtaining a phase diagram with a topological quantum phase transition with machine learning, the perspective of bridging traditional condensed matter theory with machine learning will be broadly valuable.

  6. Quantum Loop Topography for Machine Learning

    NASA Astrophysics Data System (ADS)

    Zhang, Yi; Kim, Eun-Ah

    2017-05-01

    Despite rapidly growing interest in harnessing machine learning in the study of quantum many-body systems, training neural networks to identify quantum phases is a nontrivial challenge. The key challenge is in efficiently extracting essential information from the many-body Hamiltonian or wave function and turning the information into an image that can be fed into a neural network. When targeting topological phases, this task becomes particularly challenging as topological phases are defined in terms of nonlocal properties. Here, we introduce quantum loop topography (QLT): a procedure of constructing a multidimensional image from the "sample" Hamiltonian or wave function by evaluating two-point operators that form loops at independent Monte Carlo steps. The loop configuration is guided by the characteristic response for defining the phase, which is Hall conductivity for the cases at hand. Feeding QLT to a fully connected neural network with a single hidden layer, we demonstrate that the architecture can be effectively trained to distinguish the Chern insulator and the fractional Chern insulator from trivial insulators with high fidelity. In addition to establishing the first case of obtaining a phase diagram with a topological quantum phase transition with machine learning, the perspective of bridging traditional condensed matter theory with machine learning will be broadly valuable.

  7. Stochastic subset selection for learning with kernel machines.

    PubMed

    Rhinelander, Jason; Liu, Xiaoping P

    2012-06-01

    Kernel machines have gained much popularity in applications of machine learning. Support vector machines (SVMs) are a subset of kernel machines and generalize well for classification, regression, and anomaly detection tasks. The training procedure for traditional SVMs involves solving a quadratic programming (QP) problem. The QP problem scales super linearly in computational effort with the number of training samples and is often used for the offline batch processing of data. Kernel machines operate by retaining a subset of observed data during training. The data vectors contained within this subset are referred to as support vectors (SVs). The work presented in this paper introduces a subset selection method for the use of kernel machines in online, changing environments. Our algorithm works by using a stochastic indexing technique when selecting a subset of SVs when computing the kernel expansion. The work described here is novel because it separates the selection of kernel basis functions from the training algorithm used. The subset selection algorithm presented here can be used in conjunction with any online training technique. It is important for online kernel machines to be computationally efficient due to the real-time requirements of online environments. Our algorithm is an important contribution because it scales linearly with the number of training samples and is compatible with current training techniques. Our algorithm outperforms standard techniques in terms of computational efficiency and provides increased recognition accuracy in our experiments. We provide results from experiments using both simulated and real-world data sets to verify our algorithm.

  8. Machine learning optimization of cross docking accuracy.

    PubMed

    Bjerrum, Esben J

    2016-06-01

    Performance of small molecule automated docking programs has conceptually been divided into docking -, scoring -, ranking - and screening power, which focuses on the crystal pose prediction, affinity prediction, ligand ranking and database screening capabilities of the docking program, respectively. Benchmarks show that different docking programs can excel in individual benchmarks which suggests that the scoring function employed by the programs can be optimized for a particular task. Here the scoring function of Smina is re-optimized towards enhancing the docking power using a supervised machine learning approach and a manually curated database of ligands and cross docking receptor pairs. The optimization method does not need associated binding data for the receptor-ligand examples used in the data set and works with small train sets. The re-optimization of the weights for the scoring function results in a similar docking performance with regard to docking power towards a cross docking test set. A ligand decoy based benchmark indicates a better discrimination between poses with high and low RMSD. The reported parameters for Smina are compatible with Autodock Vina and represent ready-to-use alternative parameters for researchers who aim at pose prediction rather than affinity prediction. Copyright © 2016 Elsevier Ltd. All rights reserved.

  9. Perspective: Machine learning potentials for atomistic simulations

    NASA Astrophysics Data System (ADS)

    Behler, Jörg

    2016-11-01

    Nowadays, computer simulations have become a standard tool in essentially all fields of chemistry, condensed matter physics, and materials science. In order to keep up with state-of-the-art experiments and the ever growing complexity of the investigated problems, there is a constantly increasing need for simulations of more realistic, i.e., larger, model systems with improved accuracy. In many cases, the availability of sufficiently efficient interatomic potentials providing reliable energies and forces has become a serious bottleneck for performing these simulations. To address this problem, currently a paradigm change is taking place in the development of interatomic potentials. Since the early days of computer simulations simplified potentials have been derived using physical approximations whenever the direct application of electronic structure methods has been too demanding. Recent advances in machine learning (ML) now offer an alternative approach for the representation of potential-energy surfaces by fitting large data sets from electronic structure calculations. In this perspective, the central ideas underlying these ML potentials, solved problems and remaining challenges are reviewed along with a discussion of their current applicability and limitations.

  10. Dimension Reduction With Extreme Learning Machine.

    PubMed

    Kasun, Liyanaarachchi Lekamalage Chamara; Yang, Yan; Huang, Guang-Bin; Zhang, Zhengyou

    2016-08-01

    Data may often contain noise or irrelevant information, which negatively affect the generalization capability of machine learning algorithms. The objective of dimension reduction algorithms, such as principal component analysis (PCA), non-negative matrix factorization (NMF), random projection (RP), and auto-encoder (AE), is to reduce the noise or irrelevant information of the data. The features of PCA (eigenvectors) and linear AE are not able to represent data as parts (e.g. nose in a face image). On the other hand, NMF and non-linear AE are maimed by slow learning speed and RP only represents a subspace of original data. This paper introduces a dimension reduction framework which to some extend represents data as parts, has fast learning speed, and learns the between-class scatter subspace. To this end, this paper investigates a linear and non-linear dimension reduction framework referred to as extreme learning machine AE (ELM-AE) and sparse ELM-AE (SELM-AE). In contrast to tied weight AE, the hidden neurons in ELM-AE and SELM-AE need not be tuned, and their parameters (e.g, input weights in additive neurons) are initialized using orthogonal and sparse random weights, respectively. Experimental results on USPS handwritten digit recognition data set, CIFAR-10 object recognition, and NORB object recognition data set show the efficacy of linear and non-linear ELM-AE and SELM-AE in terms of discriminative capability, sparsity, training time, and normalized mean square error.

  11. A novel class of machine-learning-driven real-time 2D/3D tracking methods: texture model registration (TMR)

    NASA Astrophysics Data System (ADS)

    Steininger, Philipp; Neuner, Markus; Fritscher, Karl; Sedlmayer, Felix; Deutschmann, Heinrich

    2011-03-01

    We present a novel view on 2D/3D image registration by introducing a generic algorithmic framework that is based on supervised machine learning (SML). First and foremost, this class of algorithms, referred to as texture model registration (TMR), aims at making 2D/3D registration applicable for time-critical image guided medical procedures. TMR methods are two-stage. In a first offline pre-computational stage, a prediction rule is derived from a pre-interventional 3D image and according geometric constraints. This is achieved by computing digitally reconstructed radiographs, pre-processing them, extracting their texture, and applying SML methods. In a second online stage, the inferred rule is used for predicting the spatial rigid transformation of unseen intrainterventional 2D images. A first simple concrete TMR implementation, referred to as TMR-PCR, is introduced. This approach involves principal component regression (PCR) and simple intermediate pre-processing steps. Using TMR-PCR, first experimental results on five clinical IGRT 3D data sets and synthetic intra-interventional images are presented. The implementation showed an average registration rate of 48 Hz over 40000 registrations, and succeeded in the majority of cases with a mean target registration error smaller than 2 mm. Finally, the potential and characteristics of the proposed methodical framework are discussed.

  12. Binary classification of a large collection of environmental chemicals from estrogen receptor assays by quantitative structure-activity relationship and machine learning methods.

    PubMed

    Zang, Qingda; Rotroff, Daniel M; Judson, Richard S

    2013-12-23

    There are thousands of environmental chemicals subject to regulatory decisions for endocrine disrupting potential. The ToxCast and Tox21 programs have tested ∼8200 chemicals in a broad screening panel of in vitro high-throughput screening (HTS) assays for estrogen receptor (ER) agonist and antagonist activity. The present work uses this large data set to develop in silico quantitative structure-activity relationship (QSAR) models using machine learning (ML) methods and a novel approach to manage the imbalanced data distribution. Training compounds from the ToxCast project were categorized as active or inactive (binding or nonbinding) classes based on a composite ER Interaction Score derived from a collection of 13 ER in vitro assays. A total of 1537 chemicals from ToxCast were used to derive and optimize the binary classification models while 5073 additional chemicals from the Tox21 project, evaluated in 2 of the 13 in vitro assays, were used to externally validate the model performance. In order to handle the imbalanced distribution of active and inactive chemicals, we developed a cluster-selection strategy to minimize information loss and increase predictive performance and compared this strategy to three currently popular techniques: cost-sensitive learning, oversampling of the minority class, and undersampling of the majority class. QSAR classification models were built to relate the molecular structures of chemicals to their ER activities using linear discriminant analysis (LDA), classification and regression trees (CART), and support vector machines (SVM) with 51 molecular descriptors from QikProp and 4328 bits of structural fingerprints as explanatory variables. A random forest (RF) feature selection method was employed to extract the structural features most relevant to the ER activity. The best model was obtained using SVM in combination with a subset of descriptors identified from a large set via the RF algorithm, which recognized the active and

  13. Testing and Validating Machine Learning Classifiers by Metamorphic Testing☆

    PubMed Central

    Xie, Xiaoyuan; Ho, Joshua W. K.; Murphy, Christian; Kaiser, Gail; Xu, Baowen; Chen, Tsong Yueh

    2011-01-01

    Machine Learning algorithms have provided core functionality to many application domains - such as bioinformatics, computational linguistics, etc. However, it is difficult to detect faults in such applications because often there is no “test oracle” to verify the correctness of the computed outputs. To help address the software quality, in this paper we present a technique for testing the implementations of machine learning classification algorithms which support such applications. Our approach is based on the technique “metamorphic testing”, which has been shown to be effective to alleviate the oracle problem. Also presented include a case study on a real-world machine learning application framework, and a discussion of how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also conduct mutation analysis and cross-validation, which reveal that our method has high effectiveness in killing mutants, and that observing expected cross-validation result alone is not sufficiently effective to detect faults in a supervised classification program. The effectiveness of metamorphic testing is further confirmed by the detection of real faults in a popular open-source classification program. PMID:21532969

  14. Relative optical navigation around small bodies via Extreme Learning Machine

    NASA Astrophysics Data System (ADS)

    Law, Andrew M.

    To perform close proximity operations under a low-gravity environment, relative and absolute positions are vital information to the maneuver. Hence navigation is inseparably integrated in space travel. Extreme Learning Machine (ELM) is presented as an optical navigation method around small celestial bodies. Optical Navigation uses visual observation instruments such as a camera to acquire useful data and determine spacecraft position. The required input data for operation is merely a single image strip and a nadir image. ELM is a machine learning Single Layer feed-Forward Network (SLFN), a type of neural network (NN). The algorithm is developed on the predicate that input weights and biases can be randomly assigned and does not require back-propagation. The learned model is the output layer weights which are used to calculate a prediction. Together, Extreme Learning Machine Optical Navigation (ELM OpNav) utilizes optical images and ELM algorithm to train the machine to navigate around a target body. In this thesis the asteroid, Vesta, is the designated celestial body. The trained ELMs estimate the position of the spacecraft during operation with a single data set. The results show the approach is promising and potentially suitable for on-board navigation.

  15. Machine Learning Capabilities of a Simulated Cerebellum.

    PubMed

    Hausknecht, Matthew; Li, Wen-Ke; Mauk, Michael; Stone, Peter

    2017-03-01

    This paper describes the learning and control capabilities of a biologically constrained bottom-up model of the mammalian cerebellum. Results are presented from six tasks: 1) eyelid conditioning; 2) pendulum balancing; 3) proportional-integral-derivative control; 4) robot balancing; 5) pattern recognition; and 6) MNIST handwritten digit recognition. These tasks span several paradigms of machine learning, including supervised learning, reinforcement learning, control, and pattern recognition. Results over these six domains indicate that the cerebellar simulation is capable of robustly identifying static input patterns even when randomized across the sensory apparatus. This capability allows the simulated cerebellum to perform several different supervised learning and control tasks. On the other hand, both reinforcement learning and temporal pattern recognition prove problematic due to the delayed nature of error signals and the simulator's inability to solve the credit assignment problem. These results are consistent with previous findings which hypothesize that in the human brain, the basal ganglia is responsible for reinforcement learning, while the cerebellum handles supervised learning.

  16. In Silico Calculation of Infinite Dilution Activity Coefficients of Molecular Solutes in Ionic Liquids: Critical Review of Current Methods and New Models Based on Three Machine Learning Algorithms.

    PubMed

    Paduszyński, Kamil

    2016-08-22

    The aim of the paper is to address all the disadvantages of currently available models for calculating infinite dilution activity coefficients (γ(∞)) of molecular solutes in ionic liquids (ILs)-a relevant property from the point of view of many applications of ILs, particularly in separations. Three new models are proposed, each of them based on distinct machine learning algorithm: stepwise multiple linear regression (SWMLR), feed-forward artificial neural network (FFANN), and least-squares support vector machine (LSSVM). The models were established based on the most comprehensive γ(∞) data bank reported so far (>34 000 data points for 188 ILs and 128 solutes). Following the paper published previously [J. Chem. Inf. Model 2014, 54, 1311-1324], the ILs were treated in terms of group contributions, whereas the Abraham solvation parameters were used to quantify an impact of solute structure. Temperature is also included in the input data of the models so that they can be utilized to obtain temperature-dependent data and thus related thermodynamic functions. Both internal and external validation techniques were applied to assess the statistical significance and explanatory power of the final correlations. A comparative study of the overall performance of the investigated SWMLR/FFANN/LSSVM approaches is presented in terms of root-mean-square error and average absolute relative deviation between calculated and experimental γ(∞), evaluated for different families of ILs and solutes, as well as between calculated and experimental infinite dilution selectivity for separation problems benzene from n-hexane and thiophene from n-heptane. LSSVM is shown to be a method with the lowest values of both training and generalization errors. It is finally demonstrated that the established models exhibit an improved accuracy compared to the state-of-the-art model, namely, temperature-dependent group contribution linear solvation energy relationship, published in 2011 [J. Chem

  17. Machine Learning. Part 1. A Historical and Methodological Analysis.

    DTIC Science & Technology

    1983-05-31

    Machine learning has always been an integral part of artificial intelligence, and its methodology has evolved in concert with the major concerns of the field. In response to the difficulties of encoding ever-increasing volumes of knowledge in modern Al systems, many researchers have recently turned their attention to machine learning as a means to overcome the knowledge acquisition bottleneck. Part 1 of this paper presents a taxonomic analysis of machine learning organized primarily by learning strategies and secondarily by

  18. Stacking for machine learning redshifts applied to SDSS galaxies

    NASA Astrophysics Data System (ADS)

    Zitlau, Roman; Hoyle, Ben; Paech, Kerstin; Weller, Jochen; Rau, Markus Michael; Seitz, Stella

    2016-08-01

    We present an analysis of a general machine learning technique called `stacking' for the estimation of photometric redshifts. Stacking techniques can feed the photometric redshift estimate, as output by a base algorithm, back into the same algorithm as an additional input feature in a subsequent learning round. We show how all tested base algorithms benefit from at least one additional stacking round (or layer). To demonstrate the benefit of stacking, we apply the method to both unsupervised machine learning techniques based on self-organizing maps (SOMs), and supervised machine learning methods based on decision trees. We explore a range of stacking architectures, such as the number of layers and the number of base learners per layer. Finally we explore the effectiveness of stacking even when using a successful algorithm such as AdaBoost. We observe a significant improvement of between 1.9 per cent and 21 per cent on all computed metrics when stacking is applied to weak learners (such as SOMs and decision trees). When applied to strong learning algorithms (such as AdaBoost) the ratio of improvement shrinks, but still remains positive and is between 0.4 per cent and 2.5 per cent for the explored metrics and comes at almost no additional computational cost.

  19. Estimating extinction using unsupervised machine learning

    NASA Astrophysics Data System (ADS)

    Meingast, Stefan; Lombardi, Marco; Alves, João

    2017-05-01

    Dust extinction is the most robust tracer of the gas distribution in the interstellar medium, but measuring extinction is limited by the systematic uncertainties involved in estimating the intrinsic colors to background stars. In this paper we present a new technique, Pnicer, that estimates intrinsic colors and extinction for individual stars using unsupervised machine learning algorithms. This new method aims to be free from any priors with respect to the column density and intrinsic color distribution. It is applicable to any combination of parameters and works in arbitrary numbers of dimensions. Furthermore, it is not restricted to color space. Extinction toward single sources is determined by fitting Gaussian mixture models along the extinction vector to (extinction-free) control field observations. In this way it becomes possible to describe the extinction for observed sources with probability densities, rather than a single value. Pnicer effectively eliminates known biases found in similar methods and outperforms them in cases of deep observational data where the number of background galaxies is significant, or when a large number of parameters is used to break degeneracies in the intrinsic color distributions. This new method remains computationally competitive, making it possible to correctly de-redden millions of sources within a matter of seconds. With the ever-increasing number of large-scale high-sensitivity imaging surveys, Pnicer offers a fast and reliable way to efficiently calculate extinction for arbitrary parameter combinations without prior information on source characteristics. The Pnicer software package also offers access to the well-established Nicer technique in a simple unified interface and is capable of building extinction maps including the Nicest correction for cloud substructure. Pnicer is offered to the community as an open-source software solution and is entirely written in Python.

  20. Prediction of drug-induced nephrotoxicity and injury mechanisms with human induced pluripotent stem cell-derived cells and machine learning methods

    PubMed Central

    Kandasamy, Karthikeyan; Chuah, Jacqueline Kai Chin; Su, Ran; Huang, Peng; Eng, Kim Guan; Xiong, Sijing; Li, Yao; Chia, Chun Siang; Loo, Lit-Hsin; Zink, Daniele

    2015-01-01

    The renal proximal tubule is a main target for drug-induced toxicity. The prediction of proximal tubular toxicity during drug development remains difficult. Any in vitro methods based on induced pluripotent stem cell-derived renal cells had not been developed, so far. Here, we developed a rapid 1-step protocol for the differentiation of human induced pluripotent stem cells (hiPSC) into proximal tubular-like cells. These proximal tubular-like cells had a purity of >90% after 8 days of differentiation and could be directly applied for compound screening. The nephrotoxicity prediction performance of the cells was determined by evaluating their responses to 30 compounds. The results were automatically determined using a machine learning algorithm called random forest. In this way, proximal tubular toxicity in humans could be predicted with 99.8% training accuracy and 87.0% test accuracy. Further, we studied the underlying mechanisms of injury and drug-induced cellular pathways in these hiPSC-derived renal cells, and the results were in agreement with human and animal data. Our methods will enable the development of personalized or disease-specific hiPSC-based renal in vitro models for compound screening and nephrotoxicity prediction. PMID:26212763

  1. Improved machine learning models for predicting selective compounds.

    PubMed

    Ning, Xia; Walters, Michael; Karypis, George; Karypisxy, George

    2012-01-23

    The identification of small potent compounds that selectively bind to the target under consideration with high affinities is a critical step toward successful drug discovery. However, there is still a lack of efficient and accurate computational methods to predict compound selectivity properties. In this paper, we propose a set of machine learning methods to do compound selectivity prediction. In particular, we propose a novel cascaded learning method and a multitask learning method. The cascaded method decomposes the selectivity prediction into two steps, one model for each step, so as to effectively filter out nonselective compounds. The multitask method incorporates both activity and selectivity models into one multitask model so as to better differentiate compound selectivity properties. We conducted a comprehensive set of experiments and compared the results with those of other conventional selectivity prediction methods, and our results demonstrated that the cascaded and multitask methods significantly improve the selectivity prediction performance.

  2. Finding New Perovskite Halides via Machine learning

    NASA Astrophysics Data System (ADS)

    Pilania, Ghanshyam; Balachandran, Prasanna V.; Kim, Chiho; Lookman, Turab

    2016-04-01

    Advanced materials with improved properties have the potential to fuel future technological advancements. However, identification and discovery of these optimal materials for a specific application is a non-trivial task, because of the vastness of the chemical search space with enormous compositional and configurational degrees of freedom. Materials informatics provides an efficient approach towards rational design of new materials, via learning from known data to make decisions on new and previously unexplored compounds in an accelerated manner. Here, we demonstrate the power and utility of such statistical learning (or machine learning) via building a support vector machine (SVM) based classifier that uses elemental features (or descriptors) to predict the formability of a given ABX3 halide composition (where A and B represent monovalent and divalent cations, respectively, and X is F, Cl, Br or I anion) in the perovskite crystal structure. The classification model is built by learning from a dataset of 181 experimentally known ABX3 compounds. After exploring a wide range of features, we identify ionic radii, tolerance factor and octahedral factor to be the most important factors for the classification, suggesting that steric and geometric packing effects govern the stability of these halides. The trained and validated models then predict, with a high degree of confidence, several novel ABX3 compositions with perovskite crystal structure.

  3. Finding new perovskite halides via machine learning

    DOE PAGES

    Pilania, Ghanshyam; Balachandran, Prasanna V.; Kim, Chiho; ...

    2016-04-26

    Advanced materials with improved properties have the potential to fuel future technological advancements. However, identification and discovery of these optimal materials for a specific application is a non-trivial task, because of the vastness of the chemical search space with enormous compositional and configurational degrees of freedom. Materials informatics provides an efficient approach toward rational design of new materials, via learning from known data to make decisions on new and previously unexplored compounds in an accelerated manner. Here, we demonstrate the power and utility of such statistical learning (or machine learning, henceforth referred to as ML) via building a support vectormore » machine (SVM) based classifier that uses elemental features (or descriptors) to predict the formability of a given ABX3 halide composition (where A and B represent monovalent and divalent cations, respectively, and X is F, Cl, Br, or I anion) in the perovskite crystal structure. The classification model is built by learning from a dataset of 185 experimentally known ABX3 compounds. After exploring a wide range of features, we identify ionic radii, tolerance factor, and octahedral factor to be the most important factors for the classification, suggesting that steric and geometric packing effects govern the stability of these halides. As a result, the trained and validated models then predict, with a high degree of confidence, several novel ABX3 compositions with perovskite crystal structure.« less

  4. Finding new perovskite halides via machine learning

    SciTech Connect

    Pilania, Ghanshyam; Balachandran, Prasanna V.; Kim, Chiho; Lookman, Turab

    2016-04-26

    Advanced materials with improved properties have the potential to fuel future technological advancements. However, identification and discovery of these optimal materials for a specific application is a non-trivial task, because of the vastness of the chemical search space with enormous compositional and configurational degrees of freedom. Materials informatics provides an efficient approach toward rational design of new materials, via learning from known data to make decisions on new and previously unexplored compounds in an accelerated manner. Here, we demonstrate the power and utility of such statistical learning (or machine learning, henceforth referred to as ML) via building a support vector machine (SVM) based classifier that uses elemental features (or descriptors) to predict the formability of a given ABX3 halide composition (where A and B represent monovalent and divalent cations, respectively, and X is F, Cl, Br, or I anion) in the perovskite crystal structure. The classification model is built by learning from a dataset of 185 experimentally known ABX3 compounds. After exploring a wide range of features, we identify ionic radii, tolerance factor, and octahedral factor to be the most important factors for the classification, suggesting that steric and geometric packing effects govern the stability of these halides. As a result, the trained and validated models then predict, with a high degree of confidence, several novel ABX3 compositions with perovskite crystal structure.

  5. Machine learning for detection and diagnosis of disease.

    PubMed

    Sajda, Paul

    2006-01-01

    Machine learning offers a principled approach for developing sophisticated, automatic, and objective algorithms for analysis of high-dimensional and multimodal biomedical data. This review focuses on several advances in the state of the art that have shown promise in improving detection, diagnosis, and therapeutic monitoring of disease. Key in the advancement has been the development of a more in-depth understanding and theoretical analysis of critical issues related to algorithmic construction and learning theory. These include trade-offs for maximizing generalization performance, use of physically realistic constraints, and incorporation of prior knowledge and uncertainty. The review describes recent developments in machine learning, focusing on supervised and unsupervised linear methods and Bayesian inference, which have made significant impacts in the detection and diagnosis of disease in biomedicine. We describe the different methodologies and, for each, provide examples of their application to specific domains in biomedical diagnostics.

  6. Hydrological data assimilation using Extreme Learning Machines

    NASA Astrophysics Data System (ADS)

    Boucher, Marie-Amélie; Quilty, John; Adamowski, Jan

    2017-04-01

    Data assimilation refers to any process that allows for updating state variables in a model to represent reality more accurately than the initial (open loop) simulation. In hydrology, data assimilation is often a pre-requisite for forecasting. In practice, many operational agencies rely on "manual" data assimilation: perturbations are added manually to meteorological inputs or directly to state variables based on "expert knowledge" until the simulated streamflow matches the observed streamflow closely. The corrected state variables are then considered as representative of the "true", unknown, state of the watershed just before the forecasting period. However, manual data assimilation raises concerns, mainly regarding reproducibility and high reliance on "expert knowledge". For those reasons, automatic data assimilation methods have been proposed in the literature. Automatic data assimilation also allows for the assessment and reduction of state variable uncertainty, which is predominant for short-term streamflow forecasts (e.g. Thiboult et al. 2016). The goal of this project is to explore the potential of Extreme Learning Machines (ELM, Zang and Liu 2015) for data assimilation. ELMs are an emerging type of neural network that does not require iterative optimisation of their weights and biases and therefore are much faster to calibrate than typical feed-forward backpropagation neural networks. We explore ELM for updating state variables of the lumped conceptual hydrological model GR4J. The GR4J model has two state variables: the level of water in the production and routing reservoirs. Although these two variables are sufficient to describe the state of a snow-free watershed, they are modelling artifices that are not measurable. Consequently, their "true" values can only be verified indirectly through a comparison of simulated and observed streamflow and their values are highly uncertain. GR4J can also be coupled with the snow model CemaNeige, which adds two other

  7. Machine learning in genome-wide association studies.

    PubMed

    Szymczak, Silke; Biernacka, Joanna M; Cordell, Heather J; González-Recio, Oscar; König, Inke R; Zhang, Heping; Sun, Yan V

    2009-01-01

    Recently, genome-wide association studies have substantially expanded our knowledge about genetic variants that influence the susceptibility to complex diseases. Although standard statistical tests for each single-nucleotide polymorphism (SNP) separately are able to capture main genetic effects, different approaches are necessary to identify SNPs that influence disease risk jointly or in complex interactions. Experimental and simulated genome-wide SNP data provided by the Genetic Analysis Workshop 16 afforded an opportunity to analyze the applicability and benefit of several machine learning methods. Penalized regression, ensemble methods, and network analyses resulted in several new findings while known and simulated genetic risk variants were also identified. In conclusion, machine learning approaches are promising complements to standard single-and multi-SNP analysis methods for understanding the overall genetic architecture of complex human diseases. However, because they are not optimized for genome-wide SNP data, improved implementations and new variable selection procedures are required. (c) 2009 Wiley-Liss, Inc.

  8. A duct mapping method using least squares support vector machines

    NASA Astrophysics Data System (ADS)

    Douvenot, RéMi; Fabbro, Vincent; Gerstoft, Peter; Bourlier, Christophe; Saillard, Joseph

    2008-12-01

    This paper introduces a "refractivity from clutter" (RFC) approach with an inversion method based on a pregenerated database. The RFC method exploits the information contained in the radar sea clutter return to estimate the refractive index profile. Whereas initial efforts are based on algorithms giving a good accuracy involving high computational needs, the present method is based on a learning machine algorithm in order to obtain a real-time system. This paper shows the feasibility of a RFC technique based on the least squares support vector machine inversion method by comparing it to a genetic algorithm on simulated and noise-free data, at 1 and 5 GHz. These data are simulated in the presence of ideal trilinear surface-based ducts. The learning machine is based on a pregenerated database computed using Latin hypercube sampling to improve the efficiency of the learning. The results show that little accuracy is lost compared to a genetic algorithm approach. The computational time of a genetic algorithm is very high, whereas the learning machine approach is real time. The advantage of a real-time RFC system is that it could work on several azimuths in near real time.

  9. Machine learning strategies for systems with invariance properties

    NASA Astrophysics Data System (ADS)

    Ling, Julia; Jones, Reese; Templeton, Jeremy

    2016-08-01

    In many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds Averaged Navier Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high performance computing has led to a growing availability of high fidelity simulation data. These data open up the possibility of using machine learning algorithms, such as random forests or neural networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these empirical models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first method, a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance at significantly reduced computational training costs.

  10. Programmed Learning, Programmed Textbooks, Teaching Machines.

    ERIC Educational Resources Information Center

    Prokof'yev, A. V.

    The overall idea of programed learning plays an important role in the learning process, but it does not contain any sensational discoveries or unusual points. Importance resides in the perfection of the existing systems and methods of learning with the use of the achievements of modern science, and particularly of radio electronics and…

  11. Pulsar Search Using Supervised Machine Learning

    NASA Astrophysics Data System (ADS)

    Ford, John M.

    2017-05-01

    Pulsars are rapidly rotating neutron stars which emit a strong beam of energy through mechanisms that are not entirely clear to physicists. These very dense stars are used by astrophysicists to study many basic physical phenomena, such as the behavior of plasmas in extremely dense environments, behavior of pulsar-black hole pairs, and tests of general relativity. Many of these tasks require a large ensemble of pulsars to provide enough statistical information to answer the scientific questions posed by physicists. In order to provide more pulsars to study, there are several large-scale pulsar surveys underway, which are generating a huge backlog of unprocessed data. Searching for pulsars is a very labor-intensive process, currently requiring skilled people to examine and interpret plots of data output by analysis programs. An automated system for screening the plots will speed up the search for pulsars by a very large factor. Research to date on using machine learning and pattern recognition has not yielded a completely satisfactory system, as systems with the desired near 100% recall have false positive rates that are higher than desired, causing more manual labor in the classification of pulsars. This work proposed to research, identify, propose and develop methods to overcome the barriers to building an improved classification system with a false positive rate of less than 1% and a recall of near 100% that will be useful for the current and next generation of large pulsar surveys. The results show that it is possible to generate classifiers that perform as needed from the available training data. While a false positive rate of 1% was not reached, recall of over 99% was achieved with a false positive rate of less than 2%. Methods of mitigating the imbalanced training and test data were explored and found to be highly effective in enhancing classification accuracy.

  12. Modeling Electronic Quantum Transport with Machine Learning

    DOE PAGES

    Lopez Bezanilla, Alejandro; von Lilienfeld Toal, Otto A.

    2014-06-11

    We present a machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test data sets to the machine. The system’s representation encodes energetic as well as geometrical information to characterize similarities between disordered configurations, while the Euclidean norm is used as a measure of similarity. Errors for out-of-sample predictions systematically decrease with training set size, enabling the accurate and fast prediction of new transmission coefficients. The remarkable performance of our model to capture the complexity of interference phenomena lends further support to its viability inmore » dealing with transport problems of undulatory nature.« less

  13. Modeling Electronic Quantum Transport with Machine Learning

    SciTech Connect

    Lopez Bezanilla, Alejandro; von Lilienfeld Toal, Otto A.

    2014-06-11

    We present a machine learning approach to solve electronic quantum transport equations of one-dimensional nanostructures. The transmission coefficients of disordered systems were computed to provide training and test data sets to the machine. The system’s representation encodes energetic as well as geometrical information to characterize similarities between disordered configurations, while the Euclidean norm is used as a measure of similarity. Errors for out-of-sample predictions systematically decrease with training set size, enabling the accurate and fast prediction of new transmission coefficients. The remarkable performance of our model to capture the complexity of interference phenomena lends further support to its viability in dealing with transport problems of undulatory nature.

  14. Normal tissue complication probability (NTCP) modelling using spatial dose metrics and machine learning methods for severe acute oral mucositis resulting from head and neck radiotherapy

    PubMed Central

    Dean, Jamie A; Wong, Kee H; Welsh, Liam C; Jones, Ann-Britt; Schick, Ulrike; Newbold, Kate L; Bhide, Shreerang A; Harrington, Kevin J; Nutting, Christopher M; Gulliford, Sarah L

    2016-01-01

    Background and Purpose Severe acute mucositis commonly results from head and neck (chemo)radiotherapy. A predictive model of mucositis could guide clinical decision-making and inform treatment planning. We aimed to generate such a model using spatial dose metrics and machine learning. Material and Methods Predictive models of severe acute mucositis were generated using radiotherapy dose (dose-volume and spatial dose metrics) and clinical data. Penalised logistic regression, support vector classification and random forest classification (RFC) models were generated and compared. Internal validation was performed (with 100-iteration cross-validation), using multiple metrics, including area under the receiver operating characteristic curve (AUC) and calibration slope, to assess performance. Associations between covariates and severe mucositis were explored using the models. Results The dose-volume-based models (standard) performed equally to those incorporating spatial information. Discrimination was similar between models, but the RFCstandard had the best calibration. The mean AUC and calibration slope for this model were 0.71 (s.d.=0.09) and 3.9 (s.d.=2.2), respectively. The volumes of oral cavity receiving intermediate and high doses were associated with severe mucositis. Conclusions The RFCstandard model performance is modest-to-good, but should be improved, and requires external validation. Reducing the volumes of oral cavity receiving intermediate and high doses may reduce mucositis incidence. PMID:27240717

  15. AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment

    PubMed Central

    2011-01-01

    Background Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. Results This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. Conclusions AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of

  16. Toward accelerating landslide mapping with interactive machine learning techniques

    NASA Astrophysics Data System (ADS)

    Stumpf, André; Lachiche, Nicolas; Malet, Jean-Philippe; Kerle, Norman; Puissant, Anne

    2013-04-01

    Despite important advances in the development of more automated methods for landslide mapping from optical remote sensing images, the elaboration of inventory maps after major triggering events still remains a tedious task. Image classification with expert defined rules typically still requires significant manual labour for the elaboration and adaption of rule sets for each particular case. Machine learning algorithm, on the contrary, have the ability to learn and identify complex image patterns from labelled examples but may require relatively large amounts of training data. In order to reduce the amount of required training data active learning has evolved as key concept to guide the sampling for applications such as document classification, genetics and remote sensing. The general underlying idea of most active learning approaches is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and/or the data structure to iteratively select the most valuable samples that should be labelled by the user and added in the training set. With relatively few queries and labelled samples, an active learning strategy should ideally yield at least the same accuracy than an equivalent classifier trained with many randomly selected samples. Our study was dedicated to the development of an active learning approach for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. The developed approach is a region-based query heuristic that enables to guide the user attention towards few compact spatial batches rather than distributed points resulting in time savings of 50% and more compared to standard active learning techniques. The approach was tested with multi-temporal and multi-sensor satellite images capturing recent large scale triggering events in Brazil and China and demonstrated balanced user's and producer's accuracies between 74% and 80%. The assessment also

  17. Machine learning: An artificial intelligence approach. Vol. II

    SciTech Connect

    Michalski, R.S.; Carbonell, J.G.; Mitchell, T.M.

    1986-01-01

    This book reflects the expansion of machine learning research through presentation of recent advances in the field. The book provides an account of current research directions. Major topics covered include the following: learning concepts and rules from examples; cognitive aspects of learning; learning by analogy; learning by observation and discovery; and an exploration of general aspects of learning.

  18. Machine learning strategies for systems with invariance properties

    DOE PAGES

    Ling, Julia; Jones, Reese E.; Templeton, Jeremy Alan

    2016-05-06

    Here, in many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds-Averaged Navier-Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high-performance computing has led to a growing availability of high-fidelity simulation data, which open up the possibility of using machine learning algorithms, such as random forests or neuralmore » networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first , a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance with significantly reduced computational training costs.« less

  19. Machine learning strategies for systems with invariance properties

    SciTech Connect

    Ling, Julia; Jones, Reese E.; Templeton, Jeremy Alan

    2016-05-06

    Here, in many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds-Averaged Navier-Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high-performance computing has led to a growing availability of high-fidelity simulation data, which open up the possibility of using machine learning algorithms, such as random forests or neural networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first , a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance with significantly reduced computational training costs.

  20. Machine learning strategies for systems with invariance properties

    SciTech Connect

    Ling, Julia; Jones, Reese E.; Templeton, Jeremy Alan

    2016-05-06

    Here, in many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds-Averaged Navier-Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high-performance computing has led to a growing availability of high-fidelity simulation data, which open up the possibility of using machine learning algorithms, such as random forests or neural networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first , a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance with significantly reduced computational training costs.

  1. Scalable Low-Power Deep Machine Learning with Analog Computation

    DTIC Science & Technology

    2013-07-19

    machine learning . We have performed extensive simulations investigating the magnitude of errors expected from analog computational elements and their...unsupervised machine learning task. We have further designed a second more complex learning chip. We have made significant innovations to the algorithm to

  2. An Evolutionary Machine Learning Framework for Big Data Sequence Mining

    ERIC Educational Resources Information Center

    Kamath, Uday Krishna

    2014-01-01

    Sequence classification is an important problem in many real-world applications. Unlike other machine learning data, there are no "explicit" features or signals in sequence data that can help traditional machine learning algorithms learn and predict from the data. Sequence data exhibits inter-relationships in the elements that are…

  3. An Evolutionary Machine Learning Framework for Big Data Sequence Mining

    ERIC Educational Resources Information Center

    Kamath, Uday Krishna

    2014-01-01

    Sequence classification is an important problem in many real-world applications. Unlike other machine learning data, there are no "explicit" features or signals in sequence data that can help traditional machine learning algorithms learn and predict from the data. Sequence data exhibits inter-relationships in the elements that are…

  4. Recognition of explosives fingerprints on objects for courier services using machine learning methods and laser-induced breakdown spectroscopy.

    PubMed

    Moros, J; Serrano, J; Gallego, F J; Macías, J; Laserna, J J

    2013-06-15

    During recent years laser-induced breakdown spectroscopy (LIBS) has been considered one of the techniques with larger ability for trace detection of explosives. However, despite of the high sensitivity exhibited for this application, LIBS suffers from a limited selectivity due to difficulties in assigning the molecular origin of the spectral emissions observed. This circumstance makes the recognition of fingerprints a latent challenging problem. In the present manuscript the sorting of six explosives (chloratite, ammonal, DNT, TNT, RDX and PETN) against a broad list of potential harmless interferents (butter, fuel oil, hand cream, olive oil, …), all of them in the form of fingerprints deposited on the surfaces of objects for courier services, has been carried out. When LIBS information is processed through a multi-stage architecture algorithm built from a suitable combination of 3 learning classifiers, an unknown fingerprint may be labeled into a particular class. Neural network classifiers trained by the Levenberg-Marquardt rule were decided within 3D scatter plots projected onto the subspace of the most useful features extracted from the LIBS spectra. Experimental results demonstrate that the presented algorithm sorts fingerprints according to their hazardous character, although its spectral information is virtually identical in appearance, with rates of false negatives and false positives not beyond of 10%. These reported achievements mean a step forward in the technology readiness level of LIBS for this complex application related to defense, homeland security and force protection. Copyright © 2013 Elsevier B.V. All rights reserved.

  5. Machine learning models in breast cancer survival prediction.

    PubMed

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

    2016-01-01

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

  6. Machine learning: novel bioinformatics approaches for combating antimicrobial resistance.

    PubMed

    Macesic, Nenad; Polubriaginof, Fernanda; Tatonetti, Nicholas P

    2017-09-12

    Antimicrobial resistance (AMR) is a threat to global health and new approaches to combating AMR are needed. Use of machine learning in addressing AMR is in its infancy but has made promising steps. We reviewed the current literature on the use of machine learning for studying bacterial AMR. The advent of large-scale data sets provided by next-generation sequencing and electronic health records make applying machine learning to the study and treatment of AMR possible. To date, it has been used for antimicrobial susceptibility genotype/phenotype prediction, development of AMR clinical decision rules, novel antimicrobial agent discovery and antimicrobial therapy optimization. Application of machine learning to studying AMR is feasible but remains limited. Implementation of machine learning in clinical settings faces barriers to uptake with concerns regarding model interpretability and data quality.Future applications of machine learning to AMR are likely to be laboratory-based, such as antimicrobial susceptibility phenotype prediction.

  7. Machine Learning Interface for Medical Image Analysis.

    PubMed

    Zhang, Yi C; Kagen, Alexander C

    2016-10-11

    TensorFlow is a second-generation open-source machine learning software library with a built-in framework for implementing neural networks in wide variety of perceptual tasks. Although TensorFlow usage is well established with computer vision datasets, the TensorFlow interface with DICOM formats for medical imaging remains to be established. Our goal is to extend the TensorFlow API to accept raw DICOM images as input; 1513 DaTscan DICOM images were obtained from the Parkinson's Progression Markers Initiative (PPMI) database. DICOM pixel intensities were extracted and shaped into tensors, or n-dimensional arrays, to populate the training, validation, and test input datasets for machine learning. A simple neural network was constructed in TensorFlow to classify images into normal or Parkinson's disease groups. Training was executed over 1000 iterations for each cross-validation set. The gradient descent optimization and Adagrad optimization algorithms were used to minimize cross-entropy between the predicted and ground-truth labels. Cross-validation was performed ten times to produce a mean accuracy of 0.938 ± 0.047 (95 % CI 0.908-0.967). The mean sensitivity was 0.974 ± 0.043 (95 % CI 0.947-1.00) and mean specificity was 0.822 ± 0.207 (95 % CI 0.694-0.950). We extended the TensorFlow API to enable DICOM compatibility in the context of DaTscan image analysis. We implemented a neural network classifier that produces diagnostic accuracies on par with excellent results from previous machine learning models. These results indicate the potential role of TensorFlow as a useful adjunct diagnostic tool in the clinical setting.

  8. Machine Learning Predictions of Flash Floods

    NASA Astrophysics Data System (ADS)

    Clark, R. A., III; Flamig, Z.; Gourley, J. J.; Hong, Y.

    2016-12-01

    This study concerns the development, assessment, and use of machine learning (ML) algorithms to automatically generate predictions of flash floods around the world from numerical weather prediction (NWP) output. Using an archive of NWP outputs from the Global Forecast System (GFS) model and a historical archive of reports of flash floods across the U.S. and Europe, we developed a set of ML models that output forecasts of the probability of a flash flood given a certain set of atmospheric conditions. Using these ML models, real-time global flash flood predictions from NWP data have been generated in research mode since February 2016. These ML models provide information about which atmospheric variables are most important in the flash flood prediction process. The raw ML predictions can be calibrated against historical events to generate reliable flash flood probabilities. The automatic system was tested in a research-to-operations testbed enviroment with National Weather Service forecasters. The ML models are quite successful at incorporating large amounts of information in a computationally-efficient manner and and result in reasonably skillful predictions. The system is largely successful at identifying flash floods resulting from synoptically-forced events, but struggles with isolated flash floods that arise as a result of weather systems largely unresolvable by the coarse resolution of a global NWP system. The results from this collection of studies suggest that automatic probabilistic predictions of flash floods are a plausible way forward in operational forecasting, but that future research could focus upon applying these methods to finer-scale NWP guidance, to NWP ensembles, and to forecast lead times beyond 24 hours.

  9. Formation enthalpies for transition metal alloys using machine learning

    NASA Astrophysics Data System (ADS)

    Ubaru, Shashanka; Miedlar, Agnieszka; Saad, Yousef; Chelikowsky, James R.

    2017-06-01

    The enthalpy of formation is an important thermodynamic property. Developing fast and accurate methods for its prediction is of practical interest in a variety of applications. Material informatics techniques based on machine learning have recently been introduced in the literature as an inexpensive means of exploiting materials data, and can be used to examine a variety of thermodynamics properties. We investigate the use of such machine learning tools for predicting the formation enthalpies of binary intermetallic compounds that contain at least one transition metal. We consider certain easily available properties of the constituting elements complemented by some basic properties of the compounds, to predict the formation enthalpies. We show how choosing these properties (input features) based on a literature study (using prior physics knowledge) seems to outperform machine learning based feature selection methods such as sensitivity analysis and LASSO (least absolute shrinkage and selection operator) based methods. A nonlinear kernel based support vector regression method is employed to perform the predictions. The predictive ability of our model is illustrated via several experiments on a dataset containing 648 binary alloys. We train and validate the model using the formation enthalpies calculated using a model by Miedema, which is a popular semiempirical model used for the prediction of formation enthalpies of metal alloys.

  10. Application of Machine Learning to Rotorcraft Health Monitoring

    NASA Technical Reports Server (NTRS)

    Cody, Tyler; Dempsey, Paula J.

    2017-01-01

    Machine learning is a powerful tool for data exploration and model building with large data sets. This project aimed to use machine learning techniques to explore the inherent structure of data from rotorcraft gear tests, relationships between features and damage states, and to build a system for predicting gear health for future rotorcraft transmission applications. Classical machine learning techniques are difficult, if not irresponsible to apply to time series data because many make the assumption of independence between samples. To overcome this, Hidden Markov Models were used to create a binary classifier for identifying scuffing transitions and Recurrent Neural Networks were used to leverage long distance relationships in predicting discrete damage states. When combined in a workflow, where the binary classifier acted as a filter for the fatigue monitor, the system was able to demonstrate accuracy in damage state prediction and scuffing identification. The time dependent nature of the data restricted data exploration to collecting and analyzing data from the model selection process. The limited amount of available data was unable to give useful information, and the division of training and testing sets tended to heavily influence the scores of the models across combinations of features and hyper-parameters. This work built a framework for tracking scuffing and fatigue on streaming data and demonstrates that machine learning has much to offer rotorcraft health monitoring by using Bayesian learning and deep learning methods to capture the time dependent nature of the data. Suggested future work is to implement the framework developed in this project using a larger variety of data sets to test the generalization capabilities of the models and allow for data exploration.

  11. Classification of Encrypted Web Traffic Using Machine Learning Algorithms

    DTIC Science & Technology

    2013-06-01

    CLASSIFICATION OF ENCRYPTED WEB TRAFFIC USING MACHINE LEARNING ALGORITHMS THESIS William Charles Barto AFIT-ENG-13-J-11 DEPARTMENT OF THE AIR FORCE...copyright protection in the United States. AFIT-ENG-13-J-11 CLASSIFICATION OF ENCRYPTED WEB TRAFFIC USING MACHINE LEARNING ALGORITHMS THESIS Presented to...ENCRYPTED WEB TRAFFIC USING MACHINE LEARNING ALGORITHMS William Charles Barto, B.S.C.E. Approved: AFIT-ENG-13-J-11 Abstract The increase in secure web

  12. Statistical Machine Learning for Structured and High Dimensional Data

    DTIC Science & Technology

    2014-09-17

    AFRL-OSR-VA-TR-2014-0234 STATISTICAL MACHINE LEARNING FOR STRUCTURED AND HIGH DIMENSIONAL DATA Larry Wasserman CARNEGIE MELLON UNIVERSITY Final...Re . 8-98) v Prescribed by ANSI Std. Z39.18 14-06-2014 Final Dec 2009 - Aug 2014 Statistical Machine Learning for Structured and High Dimensional...area of resource-constrained statistical estimation. machine learning , high-dimensional statistics U U U UU John Lafferty 773-702-3813 > Research under

  13. Estimation of octanol/water partition coefficient and aqueous solubility of environmental chemicals using molecular fingerprints and machine learning methods

    EPA Science Inventory

    Octanol/water partition coefficient (logP) and aqueous solubility (logS) are two important parameters in pharmacology and toxicology studies, and experimental measurements are usually time-consuming and expensive. In the present research, novel methods are presented for the estim...

  14. Estimation of octanol/water partition coefficient and aqueous solubility of environmental chemicals using molecular fingerprints and machine learning methods

    EPA Science Inventory

    Octanol/water partition coefficient (logP) and aqueous solubility (logS) are two important parameters in pharmacology and toxicology studies, and experimental measurements are usually time-consuming and expensive. In the present research, novel methods are presented for the estim...

  15. A study of machine learning regression methods for major elemental analysis of rocks using laser-induced breakdown spectroscopy

    NASA Astrophysics Data System (ADS)

    Boucher, Thomas F.; Ozanne, Marie V.; Carmosino, Marco L.; Dyar, M. Darby; Mahadevan, Sridhar; Breves, Elly A.; Lepore, Kate H.; Clegg, Samuel M.

    2015-05-01

    The ChemCam instrument on the Mars Curiosity rover is generating thousands of LIBS spectra and bringing interest in this technique to public attention. The key to interpreting Mars or any other types of LIBS data are calibrations that relate laboratory standards to unknowns examined in other settings and enable predictions of chemical composition. Here, LIBS spectral data are analyzed using linear regression methods including partial least squares (PLS-1 and PLS-2), principal component regression (PCR), least absolute shrinkage and selection operator (lasso), elastic net, and linear support vector regression (SVR-Lin). These were compared against results from nonlinear regression methods including kernel principal component regression (K-PCR), polynomial kernel support vector regression (SVR-Py) and k-nearest neighbor (kNN) regression to discern the most effective models for interpreting chemical abundances from LIBS spectra of geological samples. The results were evaluated for 100 samples analyzed with 50 laser pulses at each of five locations averaged together. Wilcoxon signed-rank tests were employed to evaluate the statistical significance of differences among the nine models using their predicted residual sum of squares (PRESS) to make comparisons. For MgO, SiO2, Fe2O3, CaO, and MnO, the sparse models outperform all the others except for linear SVR, while for Na2O, K2O, TiO2, and P2O5, the sparse methods produce inferior results, likely because their emission lines in this energy range have lower transition probabilities. The strong performance of the sparse methods in this study suggests that use of dimensionality-reduction techniques as a preprocessing step may improve the performance of the linear models. Nonlinear methods tend to overfit the data and predict less accurately, while the linear methods proved to be more generalizable with better predictive performance. These results are attributed to the high dimensionality of the data (6144 channels

  16. Acoustic detection and classification of Microchiroptera using machine learning: lessons learned from automatic speech recognition.

    PubMed

    Skowronski, Mark D; Harris, John G

    2006-03-01

    Current automatic acoustic detection and classification of microchiroptera utilize global features of individual calls (i.e., duration, bandwidth, frequency extrema), an approach that stems from expert knowledge of call sonograms. This approach parallels the acoustic phonetic paradigm of human automatic speech recognition (ASR), which relied on expert knowledge to account for variations in canonical linguistic units. ASR research eventually shifted from acoustic phonetics to machine learning, primarily because of the superior ability of machine learning to account for signal variation. To compare machine learning with conventional methods of detection and classification, nearly 3000 search-phase calls were hand labeled from recordings of five species: Pipistrellus bodenheimeri, Molossus molossus, Lasiurus borealis, L. cinereus semotus, and Tadarida brasiliensis. The hand labels were used to train two machine learning models: a Gaussian mixture model (GMM) for detection and classification and a hidden Markov model (HMM) for classification. The GMM detector produced 4% error compared to 32% error for a baseline broadband energy detector, while the GMM and HMM classifiers produced errors of 0.6 +/- 0.2% compared to 16.9 +/- 1.1% error for a baseline discriminant function analysis classifier. The experiments showed that machine learning algorithms produced errors an order of magnitude smaller than those for conventional methods.

  17. Analysis of Machine Learning Techniques for Heart Failure Readmissions.

    PubMed

    Mortazavi, Bobak J; Downing, Nicholas S; Bucholz, Emily M; Dharmarajan, Kumar; Manhapra, Ajay; Li, Shu-Xia; Negahban, Sahand N; Krumholz, Harlan M

    2016-11-01

    The current ability to predict readmissions in patients with heart failure is modest at best. It is unclear whether machine learning techniques that address higher dimensional, nonlinear relationships among variables would enhance prediction. We sought to compare the effectiveness of several machine learning algorithms for predicting readmissions. Using data from the Telemonitoring to Improve Heart Failure Outcomes trial, we compared the effectiveness of random forests, boosting, random forests combined hierarchically with support vector machines or logistic regression (LR), and Poisson regression against traditional LR to predict 30- and 180-day all-cause readmissions and readmissions because of heart failure. We randomly selected 50% of patients for a derivation set, and a validation set comprised the remaining patients, validated using 100 bootstrapped iterations. We compared C statistics for discrimination and distributions of observed outcomes in risk deciles for predictive range. In 30-day all-cause readmission prediction, the best performing machine learning model, random forests, provided a 17.8% improvement over LR (mean C statistics, 0.628 and 0.533, respectively). For readmissions because of heart failure, boosting improved the C statistic by 24.9% over LR (mean C statistic 0.678 and 0.543, respectively). For 30-day all-cause readmission, the observed readmission rates in the lowest and highest deciles of predicted risk with random forests (7.8% and 26.2%, respectively) showed a much wider separation than LR (14.2% and 16.4%, respectively). Machine learning methods improved the prediction of readmission after hospitalization for heart failure compared with LR and provided the greatest predictive range in observed readmission rates. © 2016 American Heart Association, Inc.

  18. Automated assessment of joint synovitis activity from medical ultrasound and power doppler examinations using image processing and machine learning methods

    PubMed Central

    Ziębiński, Adam

    2016-01-01

    Objectives Rheumatoid arthritis is the most common rheumatic disease with arthritis, and causes substantial functional disability in approximately 50% patients after 10 years. Accurate measurement of the disease activity is crucial to provide an adequate treatment and care to the patients. The aim of this study is focused on a computer aided diagnostic system that support