WorldWideScience

Sample records for learning classifier system

  1. Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

    NARCIS (Netherlands)

    Simões, L.F.; Schut, M.C.; Haasdijk, E.W.

    2008-01-01

    An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory

  2. An Active Learning Classifier for Further Reducing Diabetic Retinopathy Screening System Cost

    Directory of Open Access Journals (Sweden)

    Yinan Zhang

    2016-01-01

    Full Text Available Diabetic retinopathy (DR screening system raises a financial problem. For further reducing DR screening cost, an active learning classifier is proposed in this paper. Our approach identifies retinal images based on features extracted by anatomical part recognition and lesion detection algorithms. Kernel extreme learning machine (KELM is a rapid classifier for solving classification problems in high dimensional space. Both active learning and ensemble technique elevate performance of KELM when using small training dataset. The committee only proposes necessary manual work to doctor for saving cost. On the publicly available Messidor database, our classifier is trained with 20%–35% of labeled retinal images and comparative classifiers are trained with 80% of labeled retinal images. Results show that our classifier can achieve better classification accuracy than Classification and Regression Tree, radial basis function SVM, Multilayer Perceptron SVM, Linear SVM, and K Nearest Neighbor. Empirical experiments suggest that our active learning classifier is efficient for further reducing DR screening cost.

  3. Learning classifier systems with memory condition to solve non-Markov problems

    OpenAIRE

    Zang, Zhaoxiang; Li, Dehua; Wang, Junying

    2012-01-01

    In the family of Learning Classifier Systems, the classifier system XCS has been successfully used for many applications. However, the standard XCS has no memory mechanism and can only learn optimal policy in Markov environments, where the optimal action is determined solely by the state of current sensory input. In practice, most environments are partially observable environments on agent's sensation, which are also known as non-Markov environments. Within these environments, XCS either fail...

  4. A neural learning classifier system with self-adaptive constructivism for mobile robot control.

    Science.gov (United States)

    Hurst, Jacob; Bull, Larry

    2006-01-01

    For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform.

  5. Statistical and Machine-Learning Classifier Framework to Improve Pulse Shape Discrimination System Design

    Energy Technology Data Exchange (ETDEWEB)

    Wurtz, R. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Kaplan, A. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

    2015-10-28

    Pulse shape discrimination (PSD) is a variety of statistical classifier. Fully-­realized statistical classifiers rely on a comprehensive set of tools for designing, building, and implementing. PSD advances rely on improvements to the implemented algorithm. PSD advances can be improved by using conventional statistical classifier or machine learning methods. This paper provides the reader with a glossary of classifier-­building elements and their functions in a fully-­designed and operational classifier framework that can be used to discover opportunities for improving PSD classifier projects. This paper recommends reporting the PSD classifier’s receiver operating characteristic (ROC) curve and its behavior at a gamma rejection rate (GRR) relevant for realistic applications.

  6. Learning from Multiple Classifier Systems: Perspectives for Improving Decision Making of QSAR Models in Medicinal Chemistry.

    Science.gov (United States)

    Pham-The, Hai; Nam, Nguyen-Hai; Nga, Doan-Viet; Hai, Dang Thanh; Dieguez-Santana, Karel; Marrero-Poncee, Yovani; Castillo-Garit, Juan A; Casanola-Martin, Gerardo M; Le-Thi-Thu, Huong

    2018-02-09

    Quantitative Structure - Activity Relationship (QSAR) modeling has been widely used in medicinal chemistry and computational toxicology for many years. Today, as the amount of chemicals is increasing dramatically, QSAR methods have become pivotal for the purpose of handling the data, identifying a decision, and gathering useful information from data processing. The advances in this field have paved a way for numerous alternative approaches that require deep mathematics in order to enhance the learning capability of QSAR models. One of these directions is the use of Multiple Classifier Systems (MCSs) that potentially provide a means to exploit the advantages of manifold learning through decomposition frameworks, while improving generalization and predictive performance. In this paper, we presented MCS as a next generation of QSAR modeling techniques and discuss the chance to mining the vast number of models already published in the literature. We systematically revisited the theoretical frameworks of MCS as well as current advances in MCS application for QSAR practice. Furthermore, we illustrated our idea by describing ensemble approaches on modeling histone deacetylase (HDACs) inhibitors. We expect that our analysis would contribute to a better understanding about MCS application and its future perspectives for improving the decision making of QSAR models. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  7. Reinforcement Learning Based Artificial Immune Classifier

    Directory of Open Access Journals (Sweden)

    Mehmet Karakose

    2013-01-01

    Full Text Available One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

  8. Classifying K-12 Blended Learning

    Science.gov (United States)

    Staker, Heather; Horn, Michael B.

    2012-01-01

    The growth of online learning in the K-12 sector is occurring both remotely through virtual schools and on campuses through blended learning. In emerging fields, definitions are important because they create a shared language that enables people to talk about the new phenomena. The blended-learning taxonomy and definitions presented in this paper…

  9. Detecting Dutch political tweets : A classifier based on voting system using supervised learning

    NARCIS (Netherlands)

    de Mello Araújo, Eric Fernandes; Ebbelaar, Dave

    The task of classifying political tweets has been shown to be very difficult, with controversial results in many works and with non-replicable methods. Most of the works with this goal use rule-based methods to identify political tweets. We propose here two methods, being one rule-based approach,

  10. Classifying smoking urges via machine learning.

    Science.gov (United States)

    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

  11. Logarithmic learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2014-12-01

    Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

  12. Search for an Appropriate Behavior within the Emotional Regulation in Virtual Creatures Using a Learning Classifier System.

    Science.gov (United States)

    Rosales, Jonathan-Hernando; Ramos, Félix; Ramos, Marco; Cervantes, José-Antonio

    2017-01-01

    Emotion regulation is a process by which human beings control emotional behaviors. From neuroscientific evidence, this mechanism is the product of conscious or unconscious processes. In particular, the mechanism generated by a conscious process needs a priori components to be computed. The behaviors generated by previous experiences are among these components. These behaviors need to be adapted to fulfill the objectives in a specific situation. The problem we address is how to endow virtual creatures with emotion regulation in order to compute an appropriate behavior in a specific emotional situation. This problem is clearly important and we have not identified ways to solve this problem in the current literature. In our proposal, we show a way to generate the appropriate behavior in an emotional situation using a learning classifier system (LCS). We illustrate the function of our proposal in unknown and known situations by means of two case studies. Our results demonstrate that it is possible to converge to the appropriate behavior even in the first case; that is, when the system does not have previous experiences and in situations where some previous information is available our proposal proves to be a very powerful tool.

  13. Search for an Appropriate Behavior within the Emotional Regulation in Virtual Creatures Using a Learning Classifier System

    Directory of Open Access Journals (Sweden)

    Jonathan-Hernando Rosales

    2017-01-01

    Full Text Available Emotion regulation is a process by which human beings control emotional behaviors. From neuroscientific evidence, this mechanism is the product of conscious or unconscious processes. In particular, the mechanism generated by a conscious process needs a priori components to be computed. The behaviors generated by previous experiences are among these components. These behaviors need to be adapted to fulfill the objectives in a specific situation. The problem we address is how to endow virtual creatures with emotion regulation in order to compute an appropriate behavior in a specific emotional situation. This problem is clearly important and we have not identified ways to solve this problem in the current literature. In our proposal, we show a way to generate the appropriate behavior in an emotional situation using a learning classifier system (LCS. We illustrate the function of our proposal in unknown and known situations by means of two case studies. Our results demonstrate that it is possible to converge to the appropriate behavior even in the first case; that is, when the system does not have previous experiences and in situations where some previous information is available our proposal proves to be a very powerful tool.

  14. Learning for VMM + WTA Embedded Classifiers

    Science.gov (United States)

    2016-03-31

    Learning for VMM + WTA Embedded Classifiers Jennifer Hasler and Sahil Shah Electrical and Computer Engineering Georgia Institute of Technology...enabling correct classification of each novel acoustic signal (generator, idle car, and idle truck ). The classification structure requires, after...measured on our SoC FPAA IC. The test input is composed of signals from urban environment for 3 objects (generator, idle car, and idle truck

  15. A Fuzzy Approach to Classify Learning Disability

    OpenAIRE

    Pooja Manghirmalani; Darshana More; Kavita Jain

    2012-01-01

    The endeavor of this work is to support the special education community in their quest to be with the mainstream. The initial segment of the paper gives an exhaustive study of the different mechanisms of diagnosing learning disability. After diagnosis of learning disability the further classification of learning disability that is dyslexia, dysgraphia or dyscalculia are fuzzy. Hence the paper proposes a model based on Fuzzy Expert System which enables the classification of learning disability...

  16. Deep Feature Learning and Cascaded Classifier for Large Scale Data

    DEFF Research Database (Denmark)

    Prasoon, Adhish

    from data rather than having a predefined feature set. We explore deep learning approach of convolutional neural network (CNN) for segmenting three dimensional medical images. We propose a novel system integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D......This thesis focuses on voxel/pixel classification based approaches for image segmentation. The main application is segmentation of articular cartilage in knee MRIs. The first major contribution of the thesis deals with large scale machine learning problems. Many medical imaging problems need huge...... amount of training data to cover sufficient biological variability. Learning methods scaling badly with number of training data points cannot be used in such scenarios. This may restrict the usage of many powerful classifiers having excellent generalization ability. We propose a cascaded classifier which...

  17. A Supervised Multiclass Classifier for an Autocoding System

    Directory of Open Access Journals (Sweden)

    Yukako Toko

    2017-11-01

    Full Text Available Classification is often required in various contexts, including in the field of official statistics. In the previous study, we have developed a multiclass classifier that can classify short text descriptions with high accuracy. The algorithm borrows the concept of the naïve Bayes classifier and is so simple that its structure is easily understandable. The proposed classifier has the following two advantages. First, the processing times for both learning and classifying are extremely practical. Second, the proposed classifier yields high-accuracy results for a large portion of a dataset. We have previously developed an autocoding system for the Family Income and Expenditure Survey in Japan that has a better performing classifier. While the original system was developed in Perl in order to improve the efficiency of the coding process of short Japanese texts, the proposed system is implemented in the R programming language in order to explore versatility and is modified to make the system easily applicable to English text descriptions, in consideration of the increasing number of R users in the field of official statistics. We are planning to publish the proposed classifier as an R-package. The proposed classifier would be generally applicable to other classification tasks including coding activities in the field of official statistics, and it would contribute greatly to improving their efficiency.

  18. A CLASSIFIER SYSTEM USING SMOOTH GRAPH COLORING

    Directory of Open Access Journals (Sweden)

    JORGE FLORES CRUZ

    2017-01-01

    Full Text Available Unsupervised classifiers allow clustering methods with less or no human intervention. Therefore it is desirable to group the set of items with less data processing. This paper proposes an unsupervised classifier system using the model of soft graph coloring. This method was tested with some classic instances in the literature and the results obtained were compared with classifications made with human intervention, yielding as good or better results than supervised classifiers, sometimes providing alternative classifications that considers additional information that humans did not considered.

  19. Classifying BCI signals from novice users with extreme learning machine

    Directory of Open Access Journals (Sweden)

    Rodríguez-Bermúdez Germán

    2017-07-01

    Full Text Available Brain computer interface (BCI allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.

  20. Ship localization in Santa Barbara Channel using machine learning classifiers.

    Science.gov (United States)

    Niu, Haiqiang; Ozanich, Emma; Gerstoft, Peter

    2017-11-01

    Machine learning classifiers are shown to outperform conventional matched field processing for a deep water (600 m depth) ocean acoustic-based ship range estimation problem in the Santa Barbara Channel Experiment when limited environmental information is known. Recordings of three different ships of opportunity on a vertical array were used as training and test data for the feed-forward neural network and support vector machine classifiers, demonstrating the feasibility of machine learning methods to locate unseen sources. The classifiers perform well up to 10 km range whereas the conventional matched field processing fails at about 4 km range without accurate environmental information.

  1. Machine Learning Based Classifier for Falsehood Detection

    Science.gov (United States)

    Mallikarjun, H. M.; Manimegalai, P., Dr.; Suresh, H. N., Dr.

    2017-08-01

    The investigation of physiological techniques for Falsehood identification tests utilizing the enthusiastic aggravations started as a part of mid 1900s. The need of Falsehood recognition has been a piece of our general public from hundreds of years back. Different requirements drifted over the general public raising the need to create trick evidence philosophies for Falsehood identification. The established similar addressing tests have been having a tendency to gather uncertain results against which new hearty strategies are being explored upon for acquiring more productive Falsehood discovery set up. Electroencephalography (EEG) is a non-obtrusive strategy to quantify the action of mind through the anodes appended to the scalp of a subject. Electroencephalogram is a record of the electric signs produced by the synchronous activity of mind cells over a timeframe. The fundamental goal is to accumulate and distinguish the important information through this action which can be acclimatized for giving surmising to Falsehood discovery in future analysis. This work proposes a strategy for Falsehood discovery utilizing EEG database recorded on irregular people of various age gatherings and social organizations. The factual investigation is directed utilizing MATLAB v-14. It is a superior dialect for specialized registering which spares a considerable measure of time with streamlined investigation systems. In this work center is made on Falsehood Classification by Support Vector Machine (SVM). 72 Samples are set up by making inquiries from standard poll with a Wright and wrong replies in a diverse era from the individual in wearable head unit. 52 samples are trained and 20 are tested. By utilizing Bluetooth based Neurosky’s Mindwave kit, brain waves are recorded and qualities are arranged appropriately. In this work confusion matrix is derived by matlab programs and accuracy of 56.25 % is achieved.

  2. Security Enrichment in Intrusion Detection System Using Classifier Ensemble

    Directory of Open Access Journals (Sweden)

    Uma R. Salunkhe

    2017-01-01

    Full Text Available In the era of Internet and with increasing number of people as its end users, a large number of attack categories are introduced daily. Hence, effective detection of various attacks with the help of Intrusion Detection Systems is an emerging trend in research these days. Existing studies show effectiveness of machine learning approaches in handling Intrusion Detection Systems. In this work, we aim to enhance detection rate of Intrusion Detection System by using machine learning technique. We propose a novel classifier ensemble based IDS that is constructed using hybrid approach which combines data level and feature level approach. Classifier ensembles combine the opinions of different experts and improve the intrusion detection rate. Experimental results show the improved detection rates of our system compared to reference technique.

  3. Nonparametric, Coupled ,Bayesian ,Dictionary ,and Classifier Learning for Hyperspectral Classification.

    Science.gov (United States)

    Akhtar, Naveed; Mian, Ajmal

    2017-10-03

    We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.

  4. Classifier-ensemble incremental-learning procedure for nuclear transient identification at different operational conditions

    Energy Technology Data Exchange (ETDEWEB)

    Baraldi, Piero, E-mail: piero.baraldi@polimi.i [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Razavi-Far, Roozbeh [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Zio, Enrico [Dipartimento di Energia - Sezione Ingegneria Nucleare, Politecnico di Milano, via Ponzio 34/3, 20133 Milano (Italy); Ecole Centrale Paris-Supelec, Paris (France)

    2011-04-15

    An important requirement for the practical implementation of empirical diagnostic systems is the capability of classifying transients in all plant operational conditions. The present paper proposes an approach based on an ensemble of classifiers for incrementally learning transients under different operational conditions. New classifiers are added to the ensemble where transients occurring in new operational conditions are not satisfactorily classified. The construction of the ensemble is made by bagging; the base classifier is a supervised Fuzzy C Means (FCM) classifier whose outcomes are combined by majority voting. The incremental learning procedure is applied to the identification of simulated transients in the feedwater system of a Boiling Water Reactor (BWR) under different reactor power levels.

  5. Classifier-ensemble incremental-learning procedure for nuclear transient identification at different operational conditions

    International Nuclear Information System (INIS)

    Baraldi, Piero; Razavi-Far, Roozbeh; Zio, Enrico

    2011-01-01

    An important requirement for the practical implementation of empirical diagnostic systems is the capability of classifying transients in all plant operational conditions. The present paper proposes an approach based on an ensemble of classifiers for incrementally learning transients under different operational conditions. New classifiers are added to the ensemble where transients occurring in new operational conditions are not satisfactorily classified. The construction of the ensemble is made by bagging; the base classifier is a supervised Fuzzy C Means (FCM) classifier whose outcomes are combined by majority voting. The incremental learning procedure is applied to the identification of simulated transients in the feedwater system of a Boiling Water Reactor (BWR) under different reactor power levels.

  6. A deep learning method for classifying mammographic breast density categories.

    Science.gov (United States)

    Mohamed, Aly A; Berg, Wendie A; Peng, Hong; Luo, Yahong; Jankowitz, Rachel C; Wu, Shandong

    2018-01-01

    Mammographic breast density is an established risk marker for breast cancer and is visually assessed by radiologists in routine mammogram image reading, using four qualitative Breast Imaging and Reporting Data System (BI-RADS) breast density categories. It is particularly difficult for radiologists to consistently distinguish the two most common and most variably assigned BI-RADS categories, i.e., "scattered density" and "heterogeneously dense". The aim of this work was to investigate a deep learning-based breast density classifier to consistently distinguish these two categories, aiming at providing a potential computerized tool to assist radiologists in assigning a BI-RADS category in current clinical workflow. In this study, we constructed a convolutional neural network (CNN)-based model coupled with a large (i.e., 22,000 images) digital mammogram imaging dataset to evaluate the classification performance between the two aforementioned breast density categories. All images were collected from a cohort of 1,427 women who underwent standard digital mammography screening from 2005 to 2016 at our institution. The truths of the density categories were based on standard clinical assessment made by board-certified breast imaging radiologists. Effects of direct training from scratch solely using digital mammogram images and transfer learning of a pretrained model on a large nonmedical imaging dataset were evaluated for the specific task of breast density classification. In order to measure the classification performance, the CNN classifier was also tested on a refined version of the mammogram image dataset by removing some potentially inaccurately labeled images. Receiver operating characteristic (ROC) curves and the area under the curve (AUC) were used to measure the accuracy of the classifier. The AUC was 0.9421 when the CNN-model was trained from scratch on our own mammogram images, and the accuracy increased gradually along with an increased size of training samples

  7. Silicon nanowire arrays as learning chemical vapour classifiers

    International Nuclear Information System (INIS)

    Niskanen, A O; Colli, A; White, R; Li, H W; Spigone, E; Kivioja, J M

    2011-01-01

    Nanowire field-effect transistors are a promising class of devices for various sensing applications. Apart from detecting individual chemical or biological analytes, it is especially interesting to use multiple selective sensors to look at their collective response in order to perform classification into predetermined categories. We show that non-functionalised silicon nanowire arrays can be used to robustly classify different chemical vapours using simple statistical machine learning methods. We were able to distinguish between acetone, ethanol and water with 100% accuracy while methanol, ethanol and 2-propanol were classified with 96% accuracy in ambient conditions.

  8. Defending Malicious Script Attacks Using Machine Learning Classifiers

    Directory of Open Access Journals (Sweden)

    Nayeem Khan

    2017-01-01

    Full Text Available The web application has become a primary target for cyber criminals by injecting malware especially JavaScript to perform malicious activities for impersonation. Thus, it becomes an imperative to detect such malicious code in real time before any malicious activity is performed. This study proposes an efficient method of detecting previously unknown malicious java scripts using an interceptor at the client side by classifying the key features of the malicious code. Feature subset was obtained by using wrapper method for dimensionality reduction. Supervised machine learning classifiers were used on the dataset for achieving high accuracy. Experimental results show that our method can efficiently classify malicious code from benign code with promising results.

  9. Learning to classify wakes from local sensory information

    Science.gov (United States)

    Alsalman, Mohamad; Colvert, Brendan; Kanso, Eva; Kanso Team

    2017-11-01

    Aquatic organisms exhibit remarkable abilities to sense local flow signals contained in their fluid environment and to surmise the origins of these flows. For example, fish can discern the information contained in various flow structures and utilize this information for obstacle avoidance and prey tracking. Flow structures created by flapping and swimming bodies are well characterized in the fluid dynamics literature; however, such characterization relies on classical methods that use an external observer to reconstruct global flow fields. The reconstructed flows, or wakes, are then classified according to the unsteady vortex patterns. Here, we propose a new approach for wake identification: we classify the wakes resulting from a flapping airfoil by applying machine learning algorithms to local flow information. In particular, we simulate the wakes of an oscillating airfoil in an incoming flow, extract the downstream vorticity information, and train a classifier to learn the different flow structures and classify new ones. This data-driven approach provides a promising framework for underwater navigation and detection in application to autonomous bio-inspired vehicles.

  10. Machine learning classifiers and fMRI: a tutorial overview.

    Science.gov (United States)

    Pereira, Francisco; Mitchell, Tom; Botvinick, Matthew

    2009-03-01

    Interpreting brain image experiments requires analysis of complex, multivariate data. In recent years, one analysis approach that has grown in popularity is the use of machine learning algorithms to train classifiers to decode stimuli, mental states, behaviours and other variables of interest from fMRI data and thereby show the data contain information about them. In this tutorial overview we review some of the key choices faced in using this approach as well as how to derive statistically significant results, illustrating each point from a case study. Furthermore, we show how, in addition to answering the question of 'is there information about a variable of interest' (pattern discrimination), classifiers can be used to tackle other classes of question, namely 'where is the information' (pattern localization) and 'how is that information encoded' (pattern characterization).

  11. Ensemble of classifiers based network intrusion detection system performance bound

    CSIR Research Space (South Africa)

    Mkuzangwe, Nenekazi NP

    2017-11-01

    Full Text Available This paper provides a performance bound of a network intrusion detection system (NIDS) that uses an ensemble of classifiers. Currently researchers rely on implementing the ensemble of classifiers based NIDS before they can determine the performance...

  12. Learning multiscale and deep representations for classifying remotely sensed imagery

    Science.gov (United States)

    Zhao, Wenzhi; Du, Shihong

    2016-03-01

    It is widely agreed that spatial features can be combined with spectral properties for improving interpretation performances on very-high-resolution (VHR) images in urban areas. However, many existing methods for extracting spatial features can only generate low-level features and consider limited scales, leading to unpleasant classification results. In this study, multiscale convolutional neural network (MCNN) algorithm was presented to learn spatial-related deep features for hyperspectral remote imagery classification. Unlike traditional methods for extracting spatial features, the MCNN first transforms the original data sets into a pyramid structure containing spatial information at multiple scales, and then automatically extracts high-level spatial features using multiscale training data sets. Specifically, the MCNN has two merits: (1) high-level spatial features can be effectively learned by using the hierarchical learning structure and (2) multiscale learning scheme can capture contextual information at different scales. To evaluate the effectiveness of the proposed approach, the MCNN was applied to classify the well-known hyperspectral data sets and compared with traditional methods. The experimental results shown a significant increase in classification accuracies especially for urban areas.

  13. Deep Learning to Classify Radiology Free-Text Reports.

    Science.gov (United States)

    Chen, Matthew C; Ball, Robyn L; Yang, Lingyao; Moradzadeh, Nathaniel; Chapman, Brian E; Larson, David B; Langlotz, Curtis P; Amrhein, Timothy J; Lungren, Matthew P

    2018-03-01

    Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. © RSNA, 2017 Online supplemental material is available for this article.

  14. Instance Selection for Classifier Performance Estimation in Meta Learning

    Directory of Open Access Journals (Sweden)

    Marcin Blachnik

    2017-11-01

    Full Text Available Building an accurate prediction model is challenging and requires appropriate model selection. This process is very time consuming but can be accelerated with meta-learning–automatic model recommendation by estimating the performances of given prediction models without training them. Meta-learning utilizes metadata extracted from the dataset to effectively estimate the accuracy of the model in question. To achieve that goal, metadata descriptors must be gathered efficiently and must be informative to allow the precise estimation of prediction accuracy. In this paper, a new type of metadata descriptors is analyzed. These descriptors are based on the compression level obtained from the instance selection methods at the data-preprocessing stage. To verify their suitability, two types of experiments on real-world datasets have been conducted. In the first one, 11 instance selection methods were examined in order to validate the compression–accuracy relation for three classifiers: k-nearest neighbors (kNN, support vector machine (SVM, and random forest. From this analysis, two methods are recommended (instance-based learning type 2 (IB2, and edited nearest neighbor (ENN which are then compared with the state-of-the-art metaset descriptors. The obtained results confirm that the two suggested compression-based meta-features help to predict accuracy of the base model much more accurately than the state-of-the-art solution.

  15. Machine learning algorithms to classify spinal muscular atrophy subtypes.

    Science.gov (United States)

    Srivastava, Tuhin; Darras, Basil T; Wu, Jim S; Rutkove, Seward B

    2012-07-24

    The development of better biomarkers for disease assessment remains an ongoing effort across the spectrum of neurologic illnesses. One approach for refining biomarkers is based on the concept of machine learning, in which individual, unrelated biomarkers are simultaneously evaluated. In this cross-sectional study, we assess the possibility of using machine learning, incorporating both quantitative muscle ultrasound (QMU) and electrical impedance myography (EIM) data, for classification of muscles affected by spinal muscular atrophy (SMA). Twenty-one normal subjects, 15 subjects with SMA type 2, and 10 subjects with SMA type 3 underwent EIM and QMU measurements of unilateral biceps, wrist extensors, quadriceps, and tibialis anterior. EIM and QMU parameters were then applied in combination using a support vector machine (SVM), a type of machine learning, in an attempt to accurately categorize 165 individual muscles. For all 3 classification problems, normal vs SMA, normal vs SMA 3, and SMA 2 vs SMA 3, use of SVM provided the greatest accuracy in discrimination, surpassing both EIM and QMU individually. For example, the accuracy, as measured by the receiver operating characteristic area under the curve (ROC-AUC) for the SVM discriminating SMA 2 muscles from SMA 3 muscles was 0.928; in comparison, the ROC-AUCs for EIM and QMU parameters alone were only 0.877 (p < 0.05) and 0.627 (p < 0.05), respectively. Combining EIM and QMU data categorizes individual SMA-affected muscles with very high accuracy. Further investigation of this approach for classifying and for following the progression of neuromuscular illness is warranted.

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

    Directory of Open Access Journals (Sweden)

    C. V. Subbulakshmi

    2015-01-01

    Full Text Available 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.

  17. REALM: an expert system for classifying emergencies

    International Nuclear Information System (INIS)

    Touchton, R.A.; Gunter, A.D.; Cain, D.G.

    1987-01-01

    In late 1983, EPRI began a program to encourage and stimulate the development of Artificial Intelligence Applications for the nuclear industry. As a part of that effort, EPRI has contracted Technology Applications, Inc., (TAI) to develop an artificially intelligent Emergency Classification system Prototype. This paper presents a description of and a status report on the recently completed prototype

  18. Implementation of a classifier didactical machine for learning mechatronic processes

    Directory of Open Access Journals (Sweden)

    Alex De La Cruz

    2017-06-01

    Full Text Available The present article shows the design and construction of a classifier didactical machine through artificial vision. The implementation of the machine is to be used as a learning module of mechatronic processes. In the project, it is described the theoretical aspects that relate concepts of mechanical design, electronic design and software management which constitute popular field in science and technology, which is mechatronics. The design of the machine was developed based on the requirements of the user, through the concurrent design methodology to define and materialize the appropriate hardware and software solutions. LabVIEW 2015 was implemented for high-speed image acquisition and analysis, as well as for the establishment of data communication with a programmable logic controller (PLC via Ethernet and an open communications platform known as Open Platform Communications - OPC. In addition, the Arduino MEGA 2560 platform was used to control the movement of the step motor and the servo motors of the module. Also, is used the Arduino MEGA 2560 to control the movement of the stepper motor and servo motors in the module. Finally, we assessed whether the equipment meets the technical specifications raised by running specific test protocols.

  19. Performance of classification confidence measures in dynamic classifier systems

    Czech Academy of Sciences Publication Activity Database

    Štefka, D.; Holeňa, Martin

    2013-01-01

    Roč. 23, č. 4 (2013), s. 299-319 ISSN 1210-0552 R&D Projects: GA ČR GA13-17187S Institutional support: RVO:67985807 Keywords : classifier combining * dynamic classifier systems * classification confidence Subject RIV: IN - Informatics, Computer Science Impact factor: 0.412, year: 2013

  20. Classification of EEG signals using a genetic-based machine learning classifier.

    Science.gov (United States)

    Skinner, B T; Nguyen, H T; Liu, D K

    2007-01-01

    This paper investigates the efficacy of the genetic-based learning classifier system XCS, for the classification of noisy, artefact-inclusive human electroencephalogram (EEG) signals represented using large condition strings (108bits). EEG signals from three participants were recorded while they performed four mental tasks designed to elicit hemispheric responses. Autoregressive (AR) models and Fast Fourier Transform (FFT) methods were used to form feature vectors with which mental tasks can be discriminated. XCS achieved a maximum classification accuracy of 99.3% and a best average of 88.9%. The relative classification performance of XCS was then compared against four non-evolutionary classifier systems originating from different learning techniques. The experimental results will be used as part of our larger research effort investigating the feasibility of using EEG signals as an interface to allow paralysed persons to control a powered wheelchair or other devices.

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

    Science.gov (United States)

    S K, Somasundaram; P, Alli

    2017-11-09

    of DR screening system using Bagging Ensemble Classifier (BEC) is investigated. With the help of voting the process in ML-BEC, bagging minimizes the error due to variance of the base classifier. With the publicly available retinal image databases, our classifier is trained with 25% of RI. Results show that the ensemble classifier can achieve better classification accuracy (CA) than single classification models. Empirical experiments suggest that the machine learning-based ensemble classifier is efficient for further reducing DR classification time (CT).

  2. Inter-Judge Agreement in Classifying Students as Learning Disabled.

    Science.gov (United States)

    Epps, Susan; And Others

    Eighteen judges with backgrounds in assessment, decision making, and learning disabilities were asked to use an array of information to differentiate learning disabled (LD) and non-learning disabled students. Each judge was provided with forms containing information on 42 test or subtest scores of 50 school-identified LD students and 49 non-LD…

  3. A Linguistic Image of Nature: The Burmese Numerative Classifier System

    Science.gov (United States)

    Becker, Alton L.

    1975-01-01

    The Burmese classifier system is coherent because it is based upon a single elementary semantic dimension: deixis. On that dimension, four distances are distinguished, distances which metaphorically substitute for other conceptual relations between people and other living beings, people and things, and people and concepts. (Author/RM)

  4. Generalization in the XCSF classifier system: analysis, improvement, and extension.

    Science.gov (United States)

    Lanzi, Pier Luca; Loiacono, Daniele; Wilson, Stewart W; Goldberg, David E

    2007-01-01

    We analyze generalization in XCSF and introduce three improvements. We begin by showing that the types of generalizations evolved by XCSF can be influenced by the input range. To explain these results we present a theoretical analysis of the convergence of classifier weights in XCSF which highlights a broader issue. In XCSF, because of the mathematical properties of the Widrow-Hoff update, the convergence of classifier weights in a given subspace can be slow when the spread of the eigenvalues of the autocorrelation matrix associated with each classifier is large. As a major consequence, the system's accuracy pressure may act before classifier weights are adequately updated, so that XCSF may evolve piecewise constant approximations, instead of the intended, and more efficient, piecewise linear ones. We propose three different ways to update classifier weights in XCSF so as to increase the generalization capabilities of XCSF: one based on a condition-based normalization of the inputs, one based on linear least squares, and one based on the recursive version of linear least squares. Through a series of experiments we show that while all three approaches significantly improve XCSF, least squares approaches appear to be best performing and most robust. Finally we show how XCSF can be extended to include polynomial approximations.

  5. Neural classifiers for learning higher-order correlations

    International Nuclear Information System (INIS)

    Gueler, M.

    1999-01-01

    Studies by various authors suggest that higher-order networks can be more powerful and biologically more plausible with respect to the more traditional multilayer networks. These architecture make explicit use of nonlinear interactions between input variables in the form of higher-order units or product units. If it is known a priori that the problem to be implemented possesses a given set of invariances like in the translation, rotation, and scale invariant recognition problems, those invariances can be encoded, thus eliminating all higher-order terms which are incompatible with the invariances. In general, however, it is a serious set-back that the complexity of learning increases exponentially with the size of inputs. This paper reviews higher-order networks and introduces an implicit representation in which learning complexity is mainly decided by the number of higher-order terms to be learned and increases only linearly with the input size

  6. Neural Classifiers for Learning Higher-Order Correlations

    Science.gov (United States)

    Güler, Marifi

    1999-01-01

    Studies by various authors suggest that higher-order networks can be more powerful and are biologically more plausible with respect to the more traditional multilayer networks. These architectures make explicit use of nonlinear interactions between input variables in the form of higher-order units or product units. If it is known a priori that the problem to be implemented possesses a given set of invariances like in the translation, rotation, and scale invariant pattern recognition problems, those invariances can be encoded, thus eliminating all higher-order terms which are incompatible with the invariances. In general, however, it is a serious set-back that the complexity of learning increases exponentially with the size of inputs. This paper reviews higher-order networks and introduces an implicit representation in which learning complexity is mainly decided by the number of higher-order terms to be learned and increases only linearly with the input size.

  7. A systems biology-based classifier for hepatocellular carcinoma diagnosis.

    Directory of Open Access Journals (Sweden)

    Yanqiong Zhang

    Full Text Available AIM: The diagnosis of hepatocellular carcinoma (HCC in the early stage is crucial to the application of curative treatments which are the only hope for increasing the life expectancy of patients. Recently, several large-scale studies have shed light on this problem through analysis of gene expression profiles to identify markers correlated with HCC progression. However, those marker sets shared few genes in common and were poorly validated using independent data. Therefore, we developed a systems biology based classifier by combining the differential gene expression with topological features of human protein interaction networks to enhance the ability of HCC diagnosis. METHODS AND RESULTS: In the Oncomine platform, genes differentially expressed in HCC tissues relative to their corresponding normal tissues were filtered by a corrected Q value cut-off and Concept filters. The identified genes that are common to different microarray datasets were chosen as the candidate markers. Then, their networks were analyzed by GeneGO Meta-Core software and the hub genes were chosen. After that, an HCC diagnostic classifier was constructed by Partial Least Squares modeling based on the microarray gene expression data of the hub genes. Validations of diagnostic performance showed that this classifier had high predictive accuracy (85.88∼92.71% and area under ROC curve (approximating 1.0, and that the network topological features integrated into this classifier contribute greatly to improving the predictive performance. Furthermore, it has been demonstrated that this modeling strategy is not only applicable to HCC, but also to other cancers. CONCLUSION: Our analysis suggests that the systems biology-based classifier that combines the differential gene expression and topological features of human protein interaction network may enhance the diagnostic performance of HCC classifier.

  8. Multiple-instance learning as a classifier combining problem

    DEFF Research Database (Denmark)

    Li, Yan; Tax, David M. J.; Duin, Robert P. W.

    2013-01-01

    In multiple-instance learning (MIL), an object is represented as a bag consisting of a set of feature vectors called instances. In the training set, the labels of bags are given, while the uncertainty comes from the unknown labels of instances in the bags. In this paper, we study MIL with the ass...

  9. Sentiment analysis system for movie review in Bahasa Indonesia using naive bayes classifier method

    Science.gov (United States)

    Nurdiansyah, Yanuar; Bukhori, Saiful; Hidayat, Rahmad

    2018-04-01

    There are many ways of implementing the use of sentiments often found in documents; one of which is the sentiments found on the product or service reviews. It is so important to be able to process and extract textual data from the documents. Therefore, we propose a system that is able to classify sentiments from review documents into two classes: positive sentiment and negative sentiment. We use Naive Bayes Classifier method in this document classification system that we build. We choose Movienthusiast, a movie reviews in Bahasa Indonesia website as the source of our review documents. From there, we were able to collect 1201 movie reviews: 783 positive reviews and 418 negative reviews that we use as the dataset for this machine learning classifier. The classifying accuracy yields an average of 88.37% from five times of accuracy measuring attempts using aforementioned dataset.

  10. Instance Selection for Classifier Performance Estimation in Meta Learning

    OpenAIRE

    Marcin Blachnik

    2017-01-01

    Building an accurate prediction model is challenging and requires appropriate model selection. This process is very time consuming but can be accelerated with meta-learning–automatic model recommendation by estimating the performances of given prediction models without training them. Meta-learning utilizes metadata extracted from the dataset to effectively estimate the accuracy of the model in question. To achieve that goal, metadata descriptors must be gathered efficiently and must be inform...

  11. BIOPHARMACEUTICS CLASSIFICATION SYSTEM: A STRATEGIC TOOL FOR CLASSIFYING DRUG SUBSTANCES

    OpenAIRE

    Rohilla Seema; Rohilla Ankur; Marwaha RK; Nanda Arun

    2011-01-01

    The biopharmaceutical classification system (BCS) is a scientific approach for classifying drug substances based on their dose/solubility ratio and intestinal permeability. The BCS has been developed to allow prediction of in vivo pharmacokinetic performance of drug products from measurements of permeability and solubility. Moreover, the drugs can be categorized into four classes of BCS on the basis of permeability and solubility namely; high permeability high solubility, high permeability lo...

  12. Classifying Structures in the ISM with Machine Learning Techniques

    Science.gov (United States)

    Beaumont, Christopher; Goodman, A. A.; Williams, J. P.

    2011-01-01

    The processes which govern molecular cloud evolution and star formation often sculpt structures in the ISM: filaments, pillars, shells, outflows, etc. Because of their morphological complexity, these objects are often identified manually. Manual classification has several disadvantages; the process is subjective, not easily reproducible, and does not scale well to handle increasingly large datasets. We have explored to what extent machine learning algorithms can be trained to autonomously identify specific morphological features in molecular cloud datasets. We show that the Support Vector Machine algorithm can successfully locate filaments and outflows blended with other emission structures. When the objects of interest are morphologically distinct from the surrounding emission, this autonomous classification achieves >90% accuracy. We have developed a set of IDL-based tools to apply this technique to other datasets.

  13. Lessons learned from different approaches towards classifying personal factors.

    Science.gov (United States)

    Müller, Rachel; Geyh, Szilvia

    2015-01-01

    To examine and compare existing suggestions towards a classification of Personal Factors (PF) of the International Classification of Functioning, Disability and Health (ICF). Qualitative and quantitative content analyses of available categorizations of PF are conducted. While the eight categorizations greatly differ in their background and structure, the broad content areas covered seem to be similar and reflect the ICF definition of PF. They cover to various degrees 12 broad content areas: socio-demographic factors, behavioral and lifestyle factors, cognitive psychological factors, social relationships, experiences and biography, coping, emotional factors, satisfaction, other health conditions, biological/physiological factors, personality, motives/motivation. In comparing these categorizations, a common core of content issues for a potential ICF PF classification could be identified and valuable lessons learned. This can contribute to future classification development activities in relation to PF.

  14. Using Machine Learning to classify the diffuse interstellar bands

    Science.gov (United States)

    Baron, Dalya; Poznanski, Dovi; Watson, Darach; Yao, Yushu; Cox, Nick L. J.; Prochaska, J. Xavier

    2015-07-01

    Using over a million and a half extragalactic spectra from the Sloan Digital Sky Survey we study the correlations of the diffuse interstellar bands (DIBs) in the Milky Way. We measure the correlation between DIB strength and dust extinction for 142 DIBs using 24 stacked spectra in the reddening range E(B - V) studied before. Most of the DIBs do not correlate with dust extinction. However, we find 10 weak and barely studied DIBs with correlations that are higher than 0.7 with dust extinction and confirm the high correlation of additional five strong DIBs. Furthermore, we find a pair of DIBs, 5925.9 and 5927.5 Å, which exhibits significant negative correlation with dust extinction, indicating that their carrier may be depleted on dust. We use Machine Learning algorithms to divide the DIBs to spectroscopic families based on 250 stacked spectra. By removing the dust dependence, we study how DIBs follow their local environment. We thus obtain six groups of weak DIBs, four of which are tightly associated with C2 or CN absorption lines.

  15. Insights from Classifying Visual Concepts with Multiple Kernel Learning

    Science.gov (United States)

    Binder, Alexander; Nakajima, Shinichi; Kloft, Marius; Müller, Christina; Samek, Wojciech; Brefeld, Ulf; Müller, Klaus-Robert; Kawanabe, Motoaki

    2012-01-01

    Combining information from various image features has become a standard technique in concept recognition tasks. However, the optimal way of fusing the resulting kernel functions is usually unknown in practical applications. Multiple kernel learning (MKL) techniques allow to determine an optimal linear combination of such similarity matrices. Classical approaches to MKL promote sparse mixtures. Unfortunately, 1-norm regularized MKL variants are often observed to be outperformed by an unweighted sum kernel. The main contributions of this paper are the following: we apply a recently developed non-sparse MKL variant to state-of-the-art concept recognition tasks from the application domain of computer vision. We provide insights on benefits and limits of non-sparse MKL and compare it against its direct competitors, the sum-kernel SVM and sparse MKL. We report empirical results for the PASCAL VOC 2009 Classification and ImageCLEF2010 Photo Annotation challenge data sets. Data sets (kernel matrices) as well as further information are available at http://doc.ml.tu-berlin.de/image_mkl/(Accessed 2012 Jun 25). PMID:22936970

  16. Stacking machine learning classifiers to identify Higgs bosons at the LHC

    International Nuclear Information System (INIS)

    Alves, A.

    2017-01-01

    Machine learning (ML) algorithms have been employed in the problem of classifying signal and background events with high accuracy in particle physics. In this paper, we compare the performance of a widespread ML technique, namely, stacked generalization , against the results of two state-of-art algorithms: (1) a deep neural network (DNN) in the task of discovering a new neutral Higgs boson and (2) a scalable machine learning system for tree boosting, in the Standard Model Higgs to tau leptons channel, both at the 8 TeV LHC. In a cut-and-count analysis, stacking three algorithms performed around 16% worse than DNN but demanding far less computation efforts, however, the same stacking outperforms boosted decision trees. Using the stacked classifiers in a multivariate statistical analysis (MVA), on the other hand, significantly enhances the statistical significance compared to cut-and-count in both Higgs processes, suggesting that combining an ensemble of simpler and faster ML algorithms with MVA tools is a better approach than building a complex state-of-art algorithm for cut-and-count.

  17. Classifier-Guided Sampling for Complex Energy System Optimization

    Energy Technology Data Exchange (ETDEWEB)

    Backlund, Peter B. [Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States); Eddy, John P. [Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

    2015-09-01

    This report documents the results of a Laboratory Directed Research and Development (LDRD) effort enti tled "Classifier - Guided Sampling for Complex Energy System Optimization" that was conducted during FY 2014 and FY 2015. The goal of this proj ect was to develop, implement, and test major improvements to the classifier - guided sampling (CGS) algorithm. CGS is type of evolutionary algorithm for perform ing search and optimization over a set of discrete design variables in the face of one or more objective functions. E xisting evolutionary algorithms, such as genetic algorithms , may require a large number of o bjecti ve function evaluations to identify optimal or near - optimal solutions . Reducing the number of evaluations can result in significant time savings, especially if the objective function is computationally expensive. CGS reduce s the evaluation count by us ing a Bayesian network classifier to filter out non - promising candidate designs , prior to evaluation, based on their posterior probabilit ies . In this project, b oth the single - objective and multi - objective version s of the CGS are developed and tested on a set of benchm ark problems. As a domain - specific case study, CGS is used to design a microgrid for use in islanded mode during an extended bulk power grid outage.

  18. Classifying cognitive profiles using machine learning with privileged information in Mild Cognitive Impairment

    Directory of Open Access Journals (Sweden)

    Hanin Hamdan Alahmadi

    2016-11-01

    Full Text Available Early diagnosis of dementia is critical for assessing disease progression and potential treatment. State-or-the-art machine learning techniques have been increasingly employed to take on this diagnostic task. In this study, we employed Generalised Matrix Learning Vector Quantization (GMLVQ classifiers to discriminate patients with Mild Cognitive Impairment (MCI from healthy controls based on their cognitive skills. Further, we adopted a ``Learning with privileged information'' approach to combine cognitive and fMRI data for the classification task. The resulting classifier operates solely on the cognitive data while it incorporates the fMRI data as privileged information (PI during training. This novel classifier is of practical use as the collection of brain imaging data is not always possible with patients and older participants.MCI patients and healthy age-matched controls were trained to extract structure from temporal sequences. We ask whether machine learning classifiers can be used to discriminate patients from controls based on the learning performance and whether differences between these groups relate to individual cognitive profiles. To this end, we tested participants in four cognitive tasks: working memory, cognitive inhibition, divided attention, and selective attention. We also collected fMRI data before and after training on the learning task and extracted fMRI responses and connectivity as features for machine learning classifiers. Our results show that the PI guided GMLVQ classifiers outperform the baseline classifier that only used the cognitive data. In addition, we found that for the baseline classifier, divided attention is the only relevant cognitive feature. When PI was incorporated, divided attention remained the most relevant feature while cognitive inhibition became also relevant for the task. Interestingly, this analysis for the fMRI GMLVQ classifier suggests that (1 when overall fMRI signal for structured stimuli is

  19. Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations.

    Science.gov (United States)

    Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

    2015-01-01

    Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

  20. Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations

    Directory of Open Access Journals (Sweden)

    Yi Zhang

    2015-01-01

    Full Text Available Maximum likelihood classifier (MLC and support vector machines (SVM are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

  1. Machine learning classifier using abnormal brain network topological metrics in major depressive disorder.

    Science.gov (United States)

    Guo, Hao; Cao, Xiaohua; Liu, Zhifen; Li, Haifang; Chen, Junjie; Zhang, Kerang

    2012-12-05

    Resting state functional brain networks have been widely studied in brain disease research. However, it is currently unclear whether abnormal resting state functional brain network metrics can be used with machine learning for the classification of brain diseases. Resting state functional brain networks were constructed for 28 healthy controls and 38 major depressive disorder patients by thresholding partial correlation matrices of 90 regions. Three nodal metrics were calculated using graph theory-based approaches. Nonparametric permutation tests were then used for group comparisons of topological metrics, which were used as classified features in six different algorithms. We used statistical significance as the threshold for selecting features and measured the accuracies of six classifiers with different number of features. A sensitivity analysis method was used to evaluate the importance of different features. The result indicated that some of the regions exhibited significantly abnormal nodal centralities, including the limbic system, basal ganglia, medial temporal, and prefrontal regions. Support vector machine with radial basis kernel function algorithm and neural network algorithm exhibited the highest average accuracy (79.27 and 78.22%, respectively) with 28 features (Pdisorder is associated with abnormal functional brain network topological metrics and statistically significant nodal metrics can be successfully used for feature selection in classification algorithms.

  2. A Learning Outcome-Oriented Approach towards Classifying Pervasive Games for Learning Using Game Design Patterns and Contextual Information

    Science.gov (United States)

    Schmitz, Birgit; Klemke, Roland; Specht, Marcus

    2013-01-01

    Mobile and in particular pervasive games are a strong component of future scenarios for teaching and learning. Based on results from a previous review of practical papers, this work explores the educational potential of pervasive games for learning by analysing underlying game mechanisms. In order to determine and classify cognitive and affective…

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

    Directory of Open Access Journals (Sweden)

    Deanna eGreenstein

    2012-06-01

    Full Text Available Introduction: 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. Methods: Using 74 anatomic brain MRI sub regions and Random Forest, we classified 98 COS patients and 99 age, sex, and ethnicity-matched healthy controls. We also used Random Forest to determine the likelihood 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 associated with schizophrenia. Results: 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 copy number variation (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. Conclusions: Schizophrenia and control groups can be well classified using Random Forest 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.

  4. Comparison of Shallow and Deep Learning Methods on Classifying the Regional Pattern of Diffuse Lung Disease.

    Science.gov (United States)

    Kim, Guk Bae; Jung, Kyu-Hwan; Lee, Yeha; Kim, Hyun-Jun; Kim, Namkug; Jun, Sanghoon; Seo, Joon Beom; Lynch, David A

    2017-10-17

    This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6-9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

  5. Feature weighting using particle swarm optimization for learning vector quantization classifier

    Science.gov (United States)

    Dongoran, A.; Rahmadani, S.; Zarlis, M.; Zakarias

    2018-03-01

    This paper discusses and proposes a method of feature weighting in classification assignments on competitive learning artificial neural network LVQ. The weighting feature method is the search for the weight of an attribute using the PSO so as to give effect to the resulting output. This method is then applied to the LVQ-Classifier and tested on the 3 datasets obtained from the UCI Machine Learning repository. Then an accuracy analysis will be generated by two approaches. The first approach using LVQ1, referred to as LVQ-Classifier and the second approach referred to as PSOFW-LVQ, is a proposed model. The result shows that the PSO algorithm is capable of finding attribute weights that increase LVQ-classifier accuracy.

  6. A comparative study of machine learning classifiers for modeling travel mode choice

    NARCIS (Netherlands)

    Hagenauer, J; Helbich, M

    2017-01-01

    The analysis of travel mode choice is an important task in transportation planning and policy making in order to understand and predict travel demands. While advances in machine learning have led to numerous powerful classifiers, their usefulness for modeling travel mode choice remains largely

  7. A Constrained Multi-Objective Learning Algorithm for Feed-Forward Neural Network Classifiers

    Directory of Open Access Journals (Sweden)

    M. Njah

    2017-06-01

    Full Text Available This paper proposes a new approach to address the optimal design of a Feed-forward Neural Network (FNN based classifier. The originality of the proposed methodology, called CMOA, lie in the use of a new constraint handling technique based on a self-adaptive penalty procedure in order to direct the entire search effort towards finding only Pareto optimal solutions that are acceptable. Neurons and connections of the FNN Classifier are dynamically built during the learning process. The approach includes differential evolution to create new individuals and then keeps only the non-dominated ones as the basis for the next generation. The designed FNN Classifier is applied to six binary classification benchmark problems, obtained from the UCI repository, and results indicated the advantages of the proposed approach over other existing multi-objective evolutionary neural networks classifiers reported recently in the literature.

  8. Ensemble Classifiers for Predicting HIV-1 Resistance from Three Rule-Based Genotypic Resistance Interpretation Systems.

    Science.gov (United States)

    Raposo, Letícia M; Nobre, Flavio F

    2017-08-30

    Resistance to antiretrovirals (ARVs) is a major problem faced by HIV-infected individuals. Different rule-based algorithms were developed to infer HIV-1 susceptibility to antiretrovirals from genotypic data. However, there is discordance between them, resulting in difficulties for clinical decisions about which treatment to use. Here, we developed ensemble classifiers integrating three interpretation algorithms: Agence Nationale de Recherche sur le SIDA (ANRS), Rega, and the genotypic resistance interpretation system from Stanford HIV Drug Resistance Database (HIVdb). Three approaches were applied to develop a classifier with a single resistance profile: stacked generalization, a simple plurality vote scheme and the selection of the interpretation system with the best performance. The strategies were compared with the Friedman's test and the performance of the classifiers was evaluated using the F-measure, sensitivity and specificity values. We found that the three strategies had similar performances for the selected antiretrovirals. For some cases, the stacking technique with naïve Bayes as the learning algorithm showed a statistically superior F-measure. This study demonstrates that ensemble classifiers can be an alternative tool for clinical decision-making since they provide a single resistance profile from the most commonly used resistance interpretation systems.

  9. Hierarchical Learning of Tree Classifiers for Large-Scale Plant Species Identification.

    Science.gov (United States)

    Fan, Jianping; Zhou, Ning; Peng, Jinye; Gao, Ling

    2015-11-01

    In this paper, a hierarchical multi-task structural learning algorithm is developed to support large-scale plant species identification, where a visual tree is constructed for organizing large numbers of plant species in a coarse-to-fine fashion and determining the inter-related learning tasks automatically. For a given parent node on the visual tree, it contains a set of sibling coarse-grained categories of plant species or sibling fine-grained plant species, and a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly for enhancing their discrimination power. The inter-level relationship constraint, e.g., a plant image must first be assigned to a parent node (high-level non-leaf node) correctly if it can further be assigned to the most relevant child node (low-level non-leaf node or leaf node) on the visual tree, is formally defined and leveraged to learn more discriminative tree classifiers over the visual tree. Our experimental results have demonstrated the effectiveness of our hierarchical multi-task structural learning algorithm on training more discriminative tree classifiers for large-scale plant species identification.

  10. Learning to Detect Traffic Incidents from Data Based on Tree Augmented Naive Bayesian Classifiers

    Directory of Open Access Journals (Sweden)

    Dawei Li

    2017-01-01

    Full Text Available This study develops a tree augmented naive Bayesian (TAN classifier based incident detection algorithm. Compared with the Bayesian networks based detection algorithms developed in the previous studies, this algorithm has less dependency on experts’ knowledge. The structure of TAN classifier for incident detection is learned from data. The discretization of continuous attributes is processed using an entropy-based method automatically. A simulation dataset on the section of the Ayer Rajah Expressway (AYE in Singapore is used to demonstrate the development of proposed algorithm, including wavelet denoising, normalization, entropy-based discretization, and structure learning. The performance of TAN based algorithm is evaluated compared with the previous developed Bayesian network (BN based and multilayer feed forward (MLF neural networks based algorithms with the same AYE data. The experiment results show that the TAN based algorithms perform better than the BN classifiers and have a similar performance to the MLF based algorithm. However, TAN based algorithm would have wider vista of applications because the theory of TAN classifiers is much less complicated than MLF. It should be found from the experiment that the TAN classifier based algorithm has a significant superiority over the speed of model training and calibration compared with MLF.

  11. Fuzzy prototype classifier based on items and its application in recommender system

    Directory of Open Access Journals (Sweden)

    Mei Cai

    2017-01-01

    Full Text Available Currently, recommender systems (RS are incorporating implicit information from social circle of the Internet. The implicit social information in human mind is not easy to reflect in appropriate decision making techniques. This paper consists of 2 contributions. First, we develop an item-based prototype classifier (IPC in which a prototype represents a social circlers preferences as a pattern classification technique. We assume the social circle which distinguishes with others by the items their members like. The prototype structure of the classifier is defined by two2-dimensional matrices. We use information gain and OWA aggregator to construct a feature space. The item-based classifier assigns a new item to some prototypes with different prototypicalities. We reform a typical data setmIris data set in UCI Machine Learning Repository to verify our fuzzy prototype classifier. The second proposition of this paper is to give the application of IPC in recommender system to solve new item cold-start problems. We modify the dataset of MovieLens to perform experimental demonstrations of the proposed ideas.

  12. Machine-learning classifiers applied to habitat and geological substrate mapping offshore South Carolina

    Science.gov (United States)

    White, S. M.; Maschmeyer, C.; Anderson, E.; Knapp, C. C.; Brantley, D.

    2017-12-01

    classification as the classifier confused flat parts with relatively flat sand data. 100% of testing data representing rocky portions of the seafloor were correctly classified. The use of machine-learning classifiers to determine seafloor-type provides a new solution to habitat mapping and offshore engineering problems.

  13. WEB-BASED ADAPTIVE TESTING SYSTEM (WATS FOR CLASSIFYING STUDENTS ACADEMIC ABILITY

    Directory of Open Access Journals (Sweden)

    Jaemu LEE,

    2012-08-01

    Full Text Available Computer Adaptive Testing (CAT has been highlighted as a promising assessment method to fulfill two testing purposes: estimating student academic ability and classifying student academic level. In this paper, we introduced the Web-based Adaptive Testing System (WATS developed to support a cost effective assessment for classifying students’ ability into different academic levels. Instead of using a traditional paper and pencil test, the WATS is expected to serve as an alternate method to promptly diagnosis and identify underachieving students through Web-based testing. The WATS can also help provide students with appropriate learning contents and necessary academic support in time. In this paper, theoretical background and structure of WATS, item construction process based upon item response theory, and user interfaces of WATS were discussed.

  14. Development of a skateboarding trick classifier using accelerometry and machine learning

    Directory of Open Access Journals (Sweden)

    Nicholas Kluge Corrêa

    Full Text Available Abstract Introduction Skateboarding is one of the most popular cultures in Brazil, with more than 8.5 million skateboarders. Nowadays, the discipline of street skating has gained recognition among other more classical sports and awaits its debut at the Tokyo 2020 Summer Olympic Games. This study aimed to explore the state-of-the-art for inertial measurement unit (IMU use in skateboarding trick detection, and to develop new classification methods using supervised machine learning and artificial neural networks (ANN. Methods State-of-the-art knowledge regarding motion detection in skateboarding was used to generate 543 artificial acceleration signals through signal modeling, corresponding to 181 flat ground tricks divided into five classes (NOLLIE, NSHOV, FLIP, SHOV, OLLIE. The classifier consisted of a multilayer feed-forward neural network created with three layers and a supervised learning algorithm (backpropagation. Results The use of ANNs trained specifically for each measured axis of acceleration resulted in error percentages inferior to 0.05%, with a computational efficiency that makes real-time application possible. Conclusion Machine learning can be a useful technique for classifying skateboarding flat ground tricks, assuming that the classifiers are properly constructed and trained, and the acceleration signals are preprocessed correctly.

  15. Evaluating the Performance of Multiple Classifier Systems: A Matrix Algebra Representation of Boolean Fusion Rules

    National Research Council Canada - National Science Library

    Hill, Justin

    2003-01-01

    ...., a logical OR, AND, or a majority vote of the classifiers in the system). An established method for evaluating a classifier is measuring some aspect of its Receiver Operating Characteristic (ROC...

  16. Using Experiential Learning Through Science Experiments to Increase the Motivation of Students Classified as Emotionally Disturbed

    Science.gov (United States)

    Crozier, Marisa

    When learning is an adventure rather than an exercise in memorization, students can enjoy the process and be motivated to participate in classroom activities (Clem, Mennicke, & Beasley, 2014). Students classified as emotionally disturbed are prone to disruptive behaviors and struggle learning in a traditional science classroom consisting of lecture and demonstrations. They cannot maintain the necessary level of attention nor have the strong reading, writing or memory skills needed to succeed. Therefore, this study examined whether the use of experiential learning would increase on-task behavior and improve the motivation of emotionally disturbed, middle school students in science. Students completed four hands-on experiments aligned with the science curriculum. The data collection methods implemented were an observation checklist with corresponding journal entries, a summative assessment in the form of lab sheets, and student interviews. Through triangulation and analysis, data revealed that the students had more on-task behaviors, were engaged in the lessons, and improved grades in science.

  17. Use of Machine Learning Classifiers and Sensor Data to Detect Neurological Deficit in Stroke Patients.

    Science.gov (United States)

    Park, Eunjeong; Chang, Hyuk-Jae; Nam, Hyo Suk

    2017-04-18

    The pronator drift test (PDT), a neurological examination, is widely used in clinics to measure motor weakness of stroke patients. The aim of this study was to develop a PDT tool with machine learning classifiers to detect stroke symptoms based on quantification of proximal arm weakness using inertial sensors and signal processing. We extracted features of drift and pronation from accelerometer signals of wearable devices on the inner wrists of 16 stroke patients and 10 healthy controls. Signal processing and feature selection approach were applied to discriminate PDT features used to classify stroke patients. A series of machine learning techniques, namely support vector machine (SVM), radial basis function network (RBFN), and random forest (RF), were implemented to discriminate stroke patients from controls with leave-one-out cross-validation. Signal processing by the PDT tool extracted a total of 12 PDT features from sensors. Feature selection abstracted the major attributes from the 12 PDT features to elucidate the dominant characteristics of proximal weakness of stroke patients using machine learning classification. Our proposed PDT classifiers had an area under the receiver operating characteristic curve (AUC) of .806 (SVM), .769 (RBFN), and .900 (RF) without feature selection, and feature selection improves the AUCs to .913 (SVM), .956 (RBFN), and .975 (RF), representing an average performance enhancement of 15.3%. Sensors and machine learning methods can reliably detect stroke signs and quantify proximal arm weakness. Our proposed solution will facilitate pervasive monitoring of stroke patients. ©Eunjeong Park, Hyuk-Jae Chang, Hyo Suk Nam. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 18.04.2017.

  18. Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features.

    Science.gov (United States)

    Szantoi, Zoltan; Escobedo, Francisco J; Abd-Elrahman, Amr; Pearlstine, Leonard; Dewitt, Bon; Smith, Scot

    2015-05-01

    Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge fromremotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using highspatial resolutionimagery and machine learning image classification algorithms for mapping heterogeneouswetland plantcommunities. This study addresses this void by analyzing whether machine learning classifierssuch as decisiontrees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedgecommunities usinghigh resolution aerial imagery and image texture data in the Everglades National Park, Florida.In addition tospectral bands, the normalized difference vegetation index, and first- and second-order texturefeatures derivedfrom the near-infrared band were analyzed. Classifier accuracies were assessed using confusiontablesand the calculated kappa coefficients of the resulting maps. The results indicated that an ANN(multilayerperceptron based on backpropagation) algorithm produced a statistically significantly higheraccuracy(82.04%) than the DT (QUEST) algorithm (80.48%) or the maximum likelihood (80.56%)classifier (αtexture features.

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

    Science.gov (United States)

    Yu, Hualong; Ni, Jun

    2014-01-01

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

  20. Performance of a Machine Learning Classifier of Knee MRI Reports in Two Large Academic Radiology Practices: A Tool to Estimate Diagnostic Yield.

    Science.gov (United States)

    Hassanpour, Saeed; Langlotz, Curtis P; Amrhein, Timothy J; Befera, Nicholas T; Lungren, Matthew P

    2017-04-01

    The purpose of this study is to evaluate the performance of a natural language processing (NLP) system in classifying a database of free-text knee MRI reports at two separate academic radiology practices. An NLP system that uses terms and patterns in manually classified narrative knee MRI reports was constructed. The NLP system was trained and tested on expert-classified knee MRI reports from two major health care organizations. Radiology reports were modeled in the training set as vectors, and a support vector machine framework was used to train the classifier. A separate test set from each organization was used to evaluate the performance of the system. We evaluated the performance of the system both within and across organizations. Standard evaluation metrics, such as accuracy, precision, recall, and F1 score (i.e., the weighted average of the precision and recall), and their respective 95% CIs were used to measure the efficacy of our classification system. The accuracy for radiology reports that belonged to the model's clinically significant concept classes after training data from the same institution was good, yielding an F1 score greater than 90% (95% CI, 84.6-97.3%). Performance of the classifier on cross-institutional application without institution-specific training data yielded F1 scores of 77.6% (95% CI, 69.5-85.7%) and 90.2% (95% CI, 84.5-95.9%) at the two organizations studied. The results show excellent accuracy by the NLP machine learning classifier in classifying free-text knee MRI reports, supporting the institution-independent reproducibility of knee MRI report classification. Furthermore, the machine learning classifier performed well on free-text knee MRI reports from another institution. These data support the feasibility of multiinstitutional classification of radiologic imaging text reports with a single machine learning classifier without requiring institution-specific training data.

  1. Super resolution reconstruction of infrared images based on classified dictionary learning

    Science.gov (United States)

    Liu, Fei; Han, Pingli; Wang, Yi; Li, Xuan; Bai, Lu; Shao, Xiaopeng

    2018-05-01

    Infrared images always suffer from low-resolution problems resulting from limitations of imaging devices. An economical approach to combat this problem involves reconstructing high-resolution images by reasonable methods without updating devices. Inspired by compressed sensing theory, this study presents and demonstrates a Classified Dictionary Learning method to reconstruct high-resolution infrared images. It classifies features of the samples into several reasonable clusters and trained a dictionary pair for each cluster. The optimal pair of dictionaries is chosen for each image reconstruction and therefore, more satisfactory results is achieved without the increase in computational complexity and time cost. Experiments and results demonstrated that it is a viable method for infrared images reconstruction since it improves image resolution and recovers detailed information of targets.

  2. A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier.

    Science.gov (United States)

    Chen, Yi; Shao, Ying; Yan, Jie; Yuan, Ti-Fei; Qu, Yanwen; Lee, Elizabeth; Wang, Shuihua

    2017-01-01

    Alzheimer's disease patients are increasing rapidly every year. Scholars tend to use computer vision methods to develop automatic diagnosis system. (Background) In 2015, Gorji et al. proposed a novel method using pseudo Zernike moment. They tested four classifiers: learning vector quantization neural network, pattern recognition neural network trained by Levenberg-Marquardt, by resilient backpropagation, and by scaled conjugate gradient. This study presents an improved method by introducing a relatively new classifier-linear regression classification. Our method selects one axial slice from 3D brain image, and employed pseudo Zernike moment with maximum order of 15 to extract 256 features from each image. Finally, linear regression classification was harnessed as the classifier. The proposed approach obtains an accuracy of 97.51%, a sensitivity of 96.71%, and a specificity of 97.73%. Our method performs better than Gorji's approach and five other state-of-the-art approaches. Therefore, it can be used to detect Alzheimer's disease. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  3. Use of a machine learning algorithm to classify expertise: analysis of hand motion patterns during a simulated surgical task.

    Science.gov (United States)

    Watson, Robert A

    2014-08-01

    To test the hypothesis that machine learning algorithms increase the predictive power to classify surgical expertise using surgeons' hand motion patterns. In 2012 at the University of North Carolina at Chapel Hill, 14 surgical attendings and 10 first- and second-year surgical residents each performed two bench model venous anastomoses. During the simulated tasks, the participants wore an inertial measurement unit on the dorsum of their dominant (right) hand to capture their hand motion patterns. The pattern from each bench model task performed was preprocessed into a symbolic time series and labeled as expert (attending) or novice (resident). The labeled hand motion patterns were processed and used to train a Support Vector Machine (SVM) classification algorithm. The trained algorithm was then tested for discriminative/predictive power against unlabeled (blinded) hand motion patterns from tasks not used in the training. The Lempel-Ziv (LZ) complexity metric was also measured from each hand motion pattern, with an optimal threshold calculated to separately classify the patterns. The LZ metric classified unlabeled (blinded) hand motion patterns into expert and novice groups with an accuracy of 70% (sensitivity 64%, specificity 80%). The SVM algorithm had an accuracy of 83% (sensitivity 86%, specificity 80%). The results confirmed the hypothesis. The SVM algorithm increased the predictive power to classify blinded surgical hand motion patterns into expert versus novice groups. With further development, the system used in this study could become a viable tool for low-cost, objective assessment of procedural proficiency in a competency-based curriculum.

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

    Science.gov (United States)

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

    2013-01-01

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

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

    Directory of Open Access Journals (Sweden)

    Meysam Bastani

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

  6. Hard-Rock Stability Analysis for Span Design in Entry-Type Excavations with Learning Classifiers

    Directory of Open Access Journals (Sweden)

    Esperanza García-Gonzalo

    2016-06-01

    Full Text Available The mining industry relies heavily on empirical analysis for design and prediction. An empirical design method, called the critical span graph, was developed specifically for rock stability analysis in entry-type excavations, based on an extensive case-history database of cut and fill mining in Canada. This empirical span design chart plots the critical span against rock mass rating for the observed case histories and has been accepted by many mining operations for the initial span design of cut and fill stopes. Different types of analysis have been used to classify the observed cases into stable, potentially unstable and unstable groups. The main purpose of this paper is to present a new method for defining rock stability areas of the critical span graph, which applies machine learning classifiers (support vector machine and extreme learning machine. The results show a reasonable correlation with previous guidelines. These machine learning methods are good tools for developing empirical methods, since they make no assumptions about the regression function. With this software, it is easy to add new field observations to a previous database, improving prediction output with the addition of data that consider the local conditions for each mine.

  7. Hard-Rock Stability Analysis for Span Design in Entry-Type Excavations with Learning Classifiers.

    Science.gov (United States)

    García-Gonzalo, Esperanza; Fernández-Muñiz, Zulima; García Nieto, Paulino José; Bernardo Sánchez, Antonio; Menéndez Fernández, Marta

    2016-06-29

    The mining industry relies heavily on empirical analysis for design and prediction. An empirical design method, called the critical span graph, was developed specifically for rock stability analysis in entry-type excavations, based on an extensive case-history database of cut and fill mining in Canada. This empirical span design chart plots the critical span against rock mass rating for the observed case histories and has been accepted by many mining operations for the initial span design of cut and fill stopes. Different types of analysis have been used to classify the observed cases into stable, potentially unstable and unstable groups. The main purpose of this paper is to present a new method for defining rock stability areas of the critical span graph, which applies machine learning classifiers (support vector machine and extreme learning machine). The results show a reasonable correlation with previous guidelines. These machine learning methods are good tools for developing empirical methods, since they make no assumptions about the regression function. With this software, it is easy to add new field observations to a previous database, improving prediction output with the addition of data that consider the local conditions for each mine.

  8. Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers

    Science.gov (United States)

    Mannini, Andrea; Sabatini, Angelo Maria

    2010-01-01

    The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series. PMID:22205862

  9. Using decision-tree classifier systems to extract knowledge from databases

    Science.gov (United States)

    St.clair, D. C.; Sabharwal, C. L.; Hacke, Keith; Bond, W. E.

    1990-01-01

    One difficulty in applying artificial intelligence techniques to the solution of real world problems is that the development and maintenance of many AI systems, such as those used in diagnostics, require large amounts of human resources. At the same time, databases frequently exist which contain information about the process(es) of interest. Recently, efforts to reduce development and maintenance costs of AI systems have focused on using machine learning techniques to extract knowledge from existing databases. Research is described in the area of knowledge extraction using a class of machine learning techniques called decision-tree classifier systems. Results of this research suggest ways of performing knowledge extraction which may be applied in numerous situations. In addition, a measurement called the concept strength metric (CSM) is described which can be used to determine how well the resulting decision tree can differentiate between the concepts it has learned. The CSM can be used to determine whether or not additional knowledge needs to be extracted from the database. An experiment involving real world data is presented to illustrate the concepts described.

  10. Training set optimization and classifier performance in a top-down diabetic retinopathy screening system

    Science.gov (United States)

    Wigdahl, J.; Agurto, C.; Murray, V.; Barriga, S.; Soliz, P.

    2013-03-01

    Diabetic retinopathy (DR) affects more than 4.4 million Americans age 40 and over. Automatic screening for DR has shown to be an efficient and cost-effective way to lower the burden on the healthcare system, by triaging diabetic patients and ensuring timely care for those presenting with DR. Several supervised algorithms have been developed to detect pathologies related to DR, but little work has been done in determining the size of the training set that optimizes an algorithm's performance. In this paper we analyze the effect of the training sample size on the performance of a top-down DR screening algorithm for different types of statistical classifiers. Results are based on partial least squares (PLS), support vector machines (SVM), k-nearest neighbor (kNN), and Naïve Bayes classifiers. Our dataset consisted of digital retinal images collected from a total of 745 cases (595 controls, 150 with DR). We varied the number of normal controls in the training set, while keeping the number of DR samples constant, and repeated the procedure 10 times using randomized training sets to avoid bias. Results show increasing performance in terms of area under the ROC curve (AUC) when the number of DR subjects in the training set increased, with similar trends for each of the classifiers. Of these, PLS and k-NN had the highest average AUC. Lower standard deviation and a flattening of the AUC curve gives evidence that there is a limit to the learning ability of the classifiers and an optimal number of cases to train on.

  11. Bias correction for selecting the minimal-error classifier from many machine learning models.

    Science.gov (United States)

    Ding, Ying; Tang, Shaowu; Liao, Serena G; Jia, Jia; Oesterreich, Steffi; Lin, Yan; Tseng, George C

    2014-11-15

    Supervised machine learning is commonly applied in genomic research to construct a classifier from the training data that is generalizable to predict independent testing data. When test datasets are not available, cross-validation is commonly used to estimate the error rate. Many machine learning methods are available, and it is well known that no universally best method exists in general. It has been a common practice to apply many machine learning methods and report the method that produces the smallest cross-validation error rate. Theoretically, such a procedure produces a selection bias. Consequently, many clinical studies with moderate sample sizes (e.g. n = 30-60) risk reporting a falsely small cross-validation error rate that could not be validated later in independent cohorts. In this article, we illustrated the probabilistic framework of the problem and explored the statistical and asymptotic properties. We proposed a new bias correction method based on learning curve fitting by inverse power law (IPL) and compared it with three existing methods: nested cross-validation, weighted mean correction and Tibshirani-Tibshirani procedure. All methods were compared in simulation datasets, five moderate size real datasets and two large breast cancer datasets. The result showed that IPL outperforms the other methods in bias correction with smaller variance, and it has an additional advantage to extrapolate error estimates for larger sample sizes, a practical feature to recommend whether more samples should be recruited to improve the classifier and accuracy. An R package 'MLbias' and all source files are publicly available. tsenglab.biostat.pitt.edu/software.htm. ctseng@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  12. Enhancing the Biological Relevance of Machine Learning Classifiers for Reverse Vaccinology

    Directory of Open Access Journals (Sweden)

    Ashley I. Heinson

    2017-02-01

    Full Text Available Reverse vaccinology (RV is a bioinformatics approach that can predict antigens with protective potential from the protein coding genomes of bacterial pathogens for subunit vaccine design. RV has become firmly established following the development of the BEXSERO® vaccine against Neisseria meningitidis serogroup B. RV studies have begun to incorporate machine learning (ML techniques to distinguish bacterial protective antigens (BPAs from non-BPAs. This research contributes significantly to the RV field by using permutation analysis to demonstrate that a signal for protective antigens can be curated from published data. Furthermore, the effects of the following on an ML approach to RV were also assessed: nested cross-validation, balancing selection of non-BPAs for subcellular localization, increasing the training data, and incorporating greater numbers of protein annotation tools for feature generation. These enhancements yielded a support vector machine (SVM classifier that could discriminate BPAs (n = 200 from non-BPAs (n = 200 with an area under the curve (AUC of 0.787. In addition, hierarchical clustering of BPAs revealed that intracellular BPAs clustered separately from extracellular BPAs. However, no immediate benefit was derived when training SVM classifiers on data sets exclusively containing intra- or extracellular BPAs. In conclusion, this work demonstrates that ML classifiers have great utility in RV approaches and will lead to new subunit vaccines in the future.

  13. Enhancing the Biological Relevance of Machine Learning Classifiers for Reverse Vaccinology

    KAUST Repository

    Heinson, Ashley

    2017-02-01

    Reverse vaccinology (RV) is a bioinformatics approach that can predict antigens with protective potential from the protein coding genomes of bacterial pathogens for subunit vaccine design. RV has become firmly established following the development of the BEXSERO® vaccine against Neisseria meningitidis serogroup B. RV studies have begun to incorporate machine learning (ML) techniques to distinguish bacterial protective antigens (BPAs) from non-BPAs. This research contributes significantly to the RV field by using permutation analysis to demonstrate that a signal for protective antigens can be curated from published data. Furthermore, the effects of the following on an ML approach to RV were also assessed: nested cross-validation, balancing selection of non-BPAs for subcellular localization, increasing the training data, and incorporating greater numbers of protein annotation tools for feature generation. These enhancements yielded a support vector machine (SVM) classifier that could discriminate BPAs (n = 200) from non-BPAs (n = 200) with an area under the curve (AUC) of 0.787. In addition, hierarchical clustering of BPAs revealed that intracellular BPAs clustered separately from extracellular BPAs. However, no immediate benefit was derived when training SVM classifiers on data sets exclusively containing intra- or extracellular BPAs. In conclusion, this work demonstrates that ML classifiers have great utility in RV approaches and will lead to new subunit vaccines in the future.

  14. Enhancing the Biological Relevance of Machine Learning Classifiers for Reverse Vaccinology

    KAUST Repository

    Heinson, Ashley; Gunawardana, Yawwani; Moesker, Bastiaan; Hume, Carmen; Vataga, Elena; Hall, Yper; Stylianou, Elena; McShane, Helen; Williams, Ann; Niranjan, Mahesan; Woelk, Christopher

    2017-01-01

    Reverse vaccinology (RV) is a bioinformatics approach that can predict antigens with protective potential from the protein coding genomes of bacterial pathogens for subunit vaccine design. RV has become firmly established following the development of the BEXSERO® vaccine against Neisseria meningitidis serogroup B. RV studies have begun to incorporate machine learning (ML) techniques to distinguish bacterial protective antigens (BPAs) from non-BPAs. This research contributes significantly to the RV field by using permutation analysis to demonstrate that a signal for protective antigens can be curated from published data. Furthermore, the effects of the following on an ML approach to RV were also assessed: nested cross-validation, balancing selection of non-BPAs for subcellular localization, increasing the training data, and incorporating greater numbers of protein annotation tools for feature generation. These enhancements yielded a support vector machine (SVM) classifier that could discriminate BPAs (n = 200) from non-BPAs (n = 200) with an area under the curve (AUC) of 0.787. In addition, hierarchical clustering of BPAs revealed that intracellular BPAs clustered separately from extracellular BPAs. However, no immediate benefit was derived when training SVM classifiers on data sets exclusively containing intra- or extracellular BPAs. In conclusion, this work demonstrates that ML classifiers have great utility in RV approaches and will lead to new subunit vaccines in the future.

  15. Discovering mammography-based machine learning classifiers for breast cancer diagnosis.

    Science.gov (United States)

    Ramos-Pollán, Raúl; Guevara-López, Miguel Angel; Suárez-Ortega, Cesar; Díaz-Herrero, Guillermo; Franco-Valiente, Jose Miguel; Rubio-Del-Solar, Manuel; González-de-Posada, Naimy; Vaz, Mario Augusto Pires; Loureiro, Joana; Ramos, Isabel

    2012-08-01

    This work explores the design of mammography-based machine learning classifiers (MLC) and proposes a new method to build MLC for breast cancer diagnosis. We massively evaluated MLC configurations to classify features vectors extracted from segmented regions (pathological lesion or normal tissue) on craniocaudal (CC) and/or mediolateral oblique (MLO) mammography image views, providing BI-RADS diagnosis. Previously, appropriate combinations of image processing and normalization techniques were applied to reduce image artifacts and increase mammograms details. The method can be used under different data acquisition circumstances and exploits computer clusters to select well performing MLC configurations. We evaluated 286 cases extracted from the repository owned by HSJ-FMUP, where specialized radiologists segmented regions on CC and/or MLO images (biopsies provided the golden standard). Around 20,000 MLC configurations were evaluated, obtaining classifiers achieving an area under the ROC curve of 0.996 when combining features vectors extracted from CC and MLO views of the same case.

  16. Interorganizational learning systems

    DEFF Research Database (Denmark)

    Hjalager, Anne-Mette

    1999-01-01

    The occurrence of organizational and interorganizational learning processes is not only the result of management endeavors. Industry structures and market related issues have substantial spill-over effects. The article reviews literature, and it establishes a learning model in which elements from...... organizational environments are included into a systematic conceptual framework. The model allows four types of learning to be identified: P-learning (professional/craft systems learning), T-learning (technology embedded learning), D-learning (dualistic learning systems, where part of the labor force is exclude...... from learning), and S-learning (learning in social networks or clans). The situation related to service industries illustrates the typology....

  17. ELM BASED CAD SYSTEM TO CLASSIFY MAMMOGRAMS BY THE COMBINATION OF CLBP AND CONTOURLET

    Directory of Open Access Journals (Sweden)

    S Venkatalakshmi

    2017-05-01

    Full Text Available Breast cancer is a serious life threat to the womanhood, worldwide. Mammography is the promising screening tool, which can show the abnormality being detected. However, the physicians find it difficult to detect the affected regions, as the size of microcalcifications is very small. Hence it would be better, if a CAD system can accompany the physician in detecting the malicious regions. Taking this as a challenge, this paper presents a CAD system for mammogram classification which is proven to be accurate and reliable. The entire work is decomposed into four different stages and the outcome of a phase is passed as the input of the following phase. Initially, the mammogram is pre-processed by adaptive median filter and the segmentation is done by GHFCM. The features are extracted by combining the texture feature descriptors Completed Local Binary Pattern (CLBP and contourlet to frame the feature sets. In the training phase, Extreme Learning Machine (ELM is trained with the feature sets. During the testing phase, the ELM can classify between normal, malignant and benign type of cancer. The performance of the proposed approach is analysed by varying the classifier, feature extractors and parameters of the feature extractor. From the experimental analysis, it is evident that the proposed work outperforms the analogous techniques in terms of accuracy, sensitivity and specificity.

  18. Classifying Microorganisms

    DEFF Research Database (Denmark)

    Sommerlund, Julie

    2006-01-01

    This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological characteris......This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological...... characteristics. The coexistence of the classification systems does not lead to a conflict between them. Rather, the systems seem to co-exist in different configurations, through which they are complementary, contradictory and inclusive in different situations-sometimes simultaneously. The systems come...

  19. Classifying snakebite in South Africa: Validating a scoring system

    African Journals Online (AJOL)

    In addition, coagulopathy may not be identified until the patient manifests with ... To develop and validate a scoring system for managing snakebites in South Africa (SA). Methods. ... that its greatest value is in identifying those patients who do ...

  20. A distributed approach for optimizing cascaded classifier topologies in real-time stream mining systems.

    Science.gov (United States)

    Foo, Brian; van der Schaar, Mihaela

    2010-11-01

    In this paper, we discuss distributed optimization techniques for configuring classifiers in a real-time, informationally-distributed stream mining system. Due to the large volume of streaming data, stream mining systems must often cope with overload, which can lead to poor performance and intolerable processing delay for real-time applications. Furthermore, optimizing over an entire system of classifiers is a difficult task since changing the filtering process at one classifier can impact both the feature values of data arriving at classifiers further downstream and thus, the classification performance achieved by an ensemble of classifiers, as well as the end-to-end processing delay. To address this problem, this paper makes three main contributions: 1) Based on classification and queuing theoretic models, we propose a utility metric that captures both the performance and the delay of a binary filtering classifier system. 2) We introduce a low-complexity framework for estimating the system utility by observing, estimating, and/or exchanging parameters between the inter-related classifiers deployed across the system. 3) We provide distributed algorithms to reconfigure the system, and analyze the algorithms based on their convergence properties, optimality, information exchange overhead, and rate of adaptation to non-stationary data sources. We provide results using different video classifier systems.

  1. Classifying snakebite in South Africa: Validating a scoring system ...

    African Journals Online (AJOL)

    Factors predictive of ATI and the optimal cut-off score for predicting an ATI were identified. These factors were then used to develop a standard scoring system. The score was then tested prospectively for accuracy in a new validation cohort consisting of 100 patients admitted for snakebite to our unit from 1 December 2014 to ...

  2. DL-ADR: a novel deep learning model for classifying genomic variants into adverse drug reactions.

    Science.gov (United States)

    Liang, Zhaohui; Huang, Jimmy Xiangji; Zeng, Xing; Zhang, Gang

    2016-08-10

    Genomic variations are associated with the metabolism and the occurrence of adverse reactions of many therapeutic agents. The polymorphisms on over 2000 locations of cytochrome P450 enzymes (CYP) due to many factors such as ethnicity, mutations, and inheritance attribute to the diversity of response and side effects of various drugs. The associations of the single nucleotide polymorphisms (SNPs), the internal pharmacokinetic patterns and the vulnerability of specific adverse reactions become one of the research interests of pharmacogenomics. The conventional genomewide association studies (GWAS) mainly focuses on the relation of single or multiple SNPs to a specific risk factors which are a one-to-many relation. However, there are no robust methods to establish a many-to-many network which can combine the direct and indirect associations between multiple SNPs and a serial of events (e.g. adverse reactions, metabolic patterns, prognostic factors etc.). In this paper, we present a novel deep learning model based on generative stochastic networks and hidden Markov chain to classify the observed samples with SNPs on five loci of two genes (CYP2D6 and CYP1A2) respectively to the vulnerable population of 14 types of adverse reactions. A supervised deep learning model is proposed in this study. The revised generative stochastic networks (GSN) model with transited by the hidden Markov chain is used. The data of the training set are collected from clinical observation. The training set is composed of 83 observations of blood samples with the genotypes respectively on CYP2D6*2, *10, *14 and CYP1A2*1C, *1 F. The samples are genotyped by the polymerase chain reaction (PCR) method. A hidden Markov chain is used as the transition operator to simulate the probabilistic distribution. The model can perform learning at lower cost compared to the conventional maximal likelihood method because the transition distribution is conditional on the previous state of the hidden Markov

  3. Deep learning classifier with optical coherence tomography images for early dental caries detection

    Science.gov (United States)

    Karimian, Nima; Salehi, Hassan S.; Mahdian, Mina; Alnajjar, Hisham; Tadinada, Aditya

    2018-02-01

    Dental caries is a microbial disease that results in localized dissolution of the mineral content of dental tissue. Despite considerable decline in the incidence of dental caries, it remains a major health problem in many societies. Early detection of incipient lesions at initial stages of demineralization can result in the implementation of non-surgical preventive approaches to reverse the demineralization process. In this paper, we present a novel approach combining deep convolutional neural networks (CNN) and optical coherence tomography (OCT) imaging modality for classification of human oral tissues to detect early dental caries. OCT images of oral tissues with various densities were input to a CNN classifier to determine variations in tissue densities resembling the demineralization process. The CNN automatically learns a hierarchy of increasingly complex features and a related classifier directly from training data sets. The initial CNN layer parameters were randomly selected. The training set is split into minibatches, with 10 OCT images per batch. Given a batch of training patches, the CNN employs two convolutional and pooling layers to extract features and then classify each patch based on the probabilities from the SoftMax classification layer (output-layer). Afterward, the CNN calculates the error between the classification result and the reference label, and then utilizes the backpropagation process to fine-tune all the layer parameters to minimize this error using batch gradient descent algorithm. We validated our proposed technique on ex-vivo OCT images of human oral tissues (enamel, cortical-bone, trabecular-bone, muscular-tissue, and fatty-tissue), which attested to effectiveness of our proposed method.

  4. Counting and classifying attractors in high dimensional dynamical systems.

    Science.gov (United States)

    Bagley, R J; Glass, L

    1996-12-07

    Randomly connected Boolean networks have been used as mathematical models of neural, genetic, and immune systems. A key quantity of such networks is the number of basins of attraction in the state space. The number of basins of attraction changes as a function of the size of the network, its connectivity and its transition rules. In discrete networks, a simple count of the number of attractors does not reveal the combinatorial structure of the attractors. These points are illustrated in a reexamination of dynamics in a class of random Boolean networks considered previously by Kauffman. We also consider comparisons between dynamics in discrete networks and continuous analogues. A continuous analogue of a discrete network may have a different number of attractors for many different reasons. Some attractors in discrete networks may be associated with unstable dynamics, and several different attractors in a discrete network may be associated with a single attractor in the continuous case. Special problems in determining attractors in continuous systems arise when there is aperiodic dynamics associated with quasiperiodicity of deterministic chaos.

  5. A comparison of rule-based and machine learning approaches for classifying patient portal messages.

    Science.gov (United States)

    Cronin, Robert M; Fabbri, Daniel; Denny, Joshua C; Rosenbloom, S Trent; Jackson, Gretchen Purcell

    2017-09-01

    Secure messaging through patient portals is an increasingly popular way that consumers interact with healthcare providers. The increasing burden of secure messaging can affect clinic staffing and workflows. Manual management of portal messages is costly and time consuming. Automated classification of portal messages could potentially expedite message triage and delivery of care. We developed automated patient portal message classifiers with rule-based and machine learning techniques using bag of words and natural language processing (NLP) approaches. To evaluate classifier performance, we used a gold standard of 3253 portal messages manually categorized using a taxonomy of communication types (i.e., main categories of informational, medical, logistical, social, and other communications, and subcategories including prescriptions, appointments, problems, tests, follow-up, contact information, and acknowledgement). We evaluated our classifiers' accuracies in identifying individual communication types within portal messages with area under the receiver-operator curve (AUC). Portal messages often contain more than one type of communication. To predict all communication types within single messages, we used the Jaccard Index. We extracted the variables of importance for the random forest classifiers. The best performing approaches to classification for the major communication types were: logistic regression for medical communications (AUC: 0.899); basic (rule-based) for informational communications (AUC: 0.842); and random forests for social communications and logistical communications (AUCs: 0.875 and 0.925, respectively). The best performing classification approach of classifiers for individual communication subtypes was random forests for Logistical-Contact Information (AUC: 0.963). The Jaccard Indices by approach were: basic classifier, Jaccard Index: 0.674; Naïve Bayes, Jaccard Index: 0.799; random forests, Jaccard Index: 0.859; and logistic regression, Jaccard

  6. Radiomic Machine Learning Classifiers for Prognostic Biomarkers of Head & Neck Cancer

    Directory of Open Access Journals (Sweden)

    Chintan eParmar

    2015-12-01

    Full Text Available Introduction: Radiomics extracts and mines large number of medical imaging features in a non-invasive and cost-effective way. The underlying assumption of radiomics is that these imaging features quantify phenotypic characteristics of entire tumor. In order to enhance applicability of radiomics in clinical oncology, highly accurate and reliable machine learning approaches are required. In this radiomic study, thirteen feature selection methods and eleven machine learning classification methods were evaluated in terms of their performance and stability for predicting overall survival in head and neck cancer patients. Methods: Two independent head and neck cancer cohorts were investigated. Training cohort HN1 consisted 101 HNSCC patients. Cohort HN2 (n=95 was used for validation. A total of 440 radiomic features were extracted from the segmented tumor regions in CT images. Feature selection and classification methods were compared using an unbiased evaluation framework. Results: We observed that the three feature selection methods MRMR (AUC = 0.69, Stability = 0.66, MIFS (AUC = 0.66, Stability = 0.69, and CIFE (AUC = 0.68, Stability = 0.7 had high prognostic performance and stability. The three classifiers BY (AUC = 0.67, RSD = 11.28, RF (AUC = 0.61, RSD = 7.36, and NN (AUC = 0.62, RSD = 10.52 also showed high prognostic performance and stability. Analysis investigating performance variability indicated that the choice of classification method is the major factor driving the performance variation (29.02% of total variance. Conclusions: Our study identified prognostic and reliable machine learning methods for the prediction of overall survival of head and neck cancer patients. Identification of optimal machine-learning methods for radiomics based prognostic analyses could broaden the scope of radiomics in precision oncology and cancer care.

  7. Learning to classify organic and conventional wheat - a machine-learning driven approach using the MeltDB 2.0 metabolomics analysis platform

    Directory of Open Access Journals (Sweden)

    Nikolas eKessler

    2015-03-01

    Full Text Available We present results of our machine learning approach to the problem of classifying GC-MS data originating from wheat grains of different farming systems. The aim is to investigate the potential of learning algorithms to classify GC-MS data to be either from conventionally grown or from organically grown samples and considering different cultivars. The motivation of our work is rather obvious on the background of nowadays increased demand for organic food in post-industrialized societies and the necessity to prove organic food authenticity. The background of our data set is given by up to eleven wheat cultivars that have been cultivated in both farming systems, organic and conventional, throughout three years. More than 300 GC-MS measurements were recorded and subsequently processed and analyzed in the MeltDB 2.0 metabolomics analysis platform, being briefly outlined in this paper. We further describe how unsupervised (t-SNE, PCA and supervised (RF, SVM methods can be applied for sample visualization and classification. Our results clearly show that years have most and wheat cultivars have second-most influence on the metabolic composition of a sample. We can also show, that for a given year and cultivar, organic and conventional cultivation can be distinguished by machine-learning algorithms.

  8. SpectraClassifier 1.0: a user friendly, automated MRS-based classifier-development system

    Directory of Open Access Journals (Sweden)

    Julià-Sapé Margarida

    2010-02-01

    Full Text Available Abstract Background SpectraClassifier (SC is a Java solution for designing and implementing Magnetic Resonance Spectroscopy (MRS-based classifiers. The main goal of SC is to allow users with minimum background knowledge of multivariate statistics to perform a fully automated pattern recognition analysis. SC incorporates feature selection (greedy stepwise approach, either forward or backward, and feature extraction (PCA. Fisher Linear Discriminant Analysis is the method of choice for classification. Classifier evaluation is performed through various methods: display of the confusion matrix of the training and testing datasets; K-fold cross-validation, leave-one-out and bootstrapping as well as Receiver Operating Characteristic (ROC curves. Results SC is composed of the following modules: Classifier design, Data exploration, Data visualisation, Classifier evaluation, Reports, and Classifier history. It is able to read low resolution in-vivo MRS (single-voxel and multi-voxel and high resolution tissue MRS (HRMAS, processed with existing tools (jMRUI, INTERPRET, 3DiCSI or TopSpin. In addition, to facilitate exchanging data between applications, a standard format capable of storing all the information needed for a dataset was developed. Each functionality of SC has been specifically validated with real data with the purpose of bug-testing and methods validation. Data from the INTERPRET project was used. Conclusions SC is a user-friendly software designed to fulfil the needs of potential users in the MRS community. It accepts all kinds of pre-processed MRS data types and classifies them semi-automatically, allowing spectroscopists to concentrate on interpretation of results with the use of its visualisation tools.

  9. Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors

    Directory of Open Access Journals (Sweden)

    Roland Zemp

    2016-01-01

    Full Text Available Occupational musculoskeletal disorders, particularly chronic low back pain (LBP, are ubiquitous due to prolonged static sitting or nonergonomic sitting positions. Therefore, the aim of this study was to develop an instrumented chair with force and acceleration sensors to determine the accuracy of automatically identifying the user’s sitting position by applying five different machine learning methods (Support Vector Machines, Multinomial Regression, Boosting, Neural Networks, and Random Forest. Forty-one subjects were requested to sit four times in seven different prescribed sitting positions (total 1148 samples. Sixteen force sensor values and the backrest angle were used as the explanatory variables (features for the classification. The different classification methods were compared by means of a Leave-One-Out cross-validation approach. The best performance was achieved using the Random Forest classification algorithm, producing a mean classification accuracy of 90.9% for subjects with which the algorithm was not familiar. The classification accuracy varied between 81% and 98% for the seven different sitting positions. The present study showed the possibility of accurately classifying different sitting positions by means of the introduced instrumented office chair combined with machine learning analyses. The use of such novel approaches for the accurate assessment of chair usage could offer insights into the relationships between sitting position, sitting behaviour, and the occurrence of musculoskeletal disorders.

  10. Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors.

    Science.gov (United States)

    Zemp, Roland; Tanadini, Matteo; Plüss, Stefan; Schnüriger, Karin; Singh, Navrag B; Taylor, William R; Lorenzetti, Silvio

    2016-01-01

    Occupational musculoskeletal disorders, particularly chronic low back pain (LBP), are ubiquitous due to prolonged static sitting or nonergonomic sitting positions. Therefore, the aim of this study was to develop an instrumented chair with force and acceleration sensors to determine the accuracy of automatically identifying the user's sitting position by applying five different machine learning methods (Support Vector Machines, Multinomial Regression, Boosting, Neural Networks, and Random Forest). Forty-one subjects were requested to sit four times in seven different prescribed sitting positions (total 1148 samples). Sixteen force sensor values and the backrest angle were used as the explanatory variables (features) for the classification. The different classification methods were compared by means of a Leave-One-Out cross-validation approach. The best performance was achieved using the Random Forest classification algorithm, producing a mean classification accuracy of 90.9% for subjects with which the algorithm was not familiar. The classification accuracy varied between 81% and 98% for the seven different sitting positions. The present study showed the possibility of accurately classifying different sitting positions by means of the introduced instrumented office chair combined with machine learning analyses. The use of such novel approaches for the accurate assessment of chair usage could offer insights into the relationships between sitting position, sitting behaviour, and the occurrence of musculoskeletal disorders.

  11. The immune system, adaptation, and machine learning

    Science.gov (United States)

    Farmer, J. Doyne; Packard, Norman H.; Perelson, Alan S.

    1986-10-01

    The immune system is capable of learning, memory, and pattern recognition. By employing genetic operators on a time scale fast enough to observe experimentally, the immune system is able to recognize novel shapes without preprogramming. Here we describe a dynamical model for the immune system that is based on the network hypothesis of Jerne, and is simple enough to simulate on a computer. This model has a strong similarity to an approach to learning and artificial intelligence introduced by Holland, called the classifier system. We demonstrate that simple versions of the classifier system can be cast as a nonlinear dynamical system, and explore the analogy between the immune and classifier systems in detail. Through this comparison we hope to gain insight into the way they perform specific tasks, and to suggest new approaches that might be of value in learning systems.

  12. Stable Sparse Classifiers Identify qEEG Signatures that Predict Learning Disabilities (NOS) Severity.

    Science.gov (United States)

    Bosch-Bayard, Jorge; Galán-García, Lídice; Fernandez, Thalia; Lirio, Rolando B; Bringas-Vega, Maria L; Roca-Stappung, Milene; Ricardo-Garcell, Josefina; Harmony, Thalía; Valdes-Sosa, Pedro A

    2017-01-01

    In this paper, we present a novel methodology to solve the classification problem, based on sparse (data-driven) regressions, combined with techniques for ensuring stability, especially useful for high-dimensional datasets and small samples number. The sensitivity and specificity of the classifiers are assessed by a stable ROC procedure, which uses a non-parametric algorithm for estimating the area under the ROC curve. This method allows assessing the performance of the classification by the ROC technique, when more than two groups are involved in the classification problem, i.e., when the gold standard is not binary. We apply this methodology to the EEG spectral signatures to find biomarkers that allow discriminating between (and predicting pertinence to) different subgroups of children diagnosed as Not Otherwise Specified Learning Disabilities (LD-NOS) disorder. Children with LD-NOS have notable learning difficulties, which affect education but are not able to be put into some specific category as reading (Dyslexia), Mathematics (Dyscalculia), or Writing (Dysgraphia). By using the EEG spectra, we aim to identify EEG patterns that may be related to specific learning disabilities in an individual case. This could be useful to develop subject-based methods of therapy, based on information provided by the EEG. Here we study 85 LD-NOS children, divided in three subgroups previously selected by a clustering technique over the scores of cognitive tests. The classification equation produced stable marginal areas under the ROC of 0.71 for discrimination between Group 1 vs. Group 2; 0.91 for Group 1 vs. Group 3; and 0.75 for Group 2 vs. Group1. A discussion of the EEG characteristics of each group related to the cognitive scores is also presented.

  13. Stable Sparse Classifiers Identify qEEG Signatures that Predict Learning Disabilities (NOS Severity

    Directory of Open Access Journals (Sweden)

    Jorge Bosch-Bayard

    2018-01-01

    Full Text Available In this paper, we present a novel methodology to solve the classification problem, based on sparse (data-driven regressions, combined with techniques for ensuring stability, especially useful for high-dimensional datasets and small samples number. The sensitivity and specificity of the classifiers are assessed by a stable ROC procedure, which uses a non-parametric algorithm for estimating the area under the ROC curve. This method allows assessing the performance of the classification by the ROC technique, when more than two groups are involved in the classification problem, i.e., when the gold standard is not binary. We apply this methodology to the EEG spectral signatures to find biomarkers that allow discriminating between (and predicting pertinence to different subgroups of children diagnosed as Not Otherwise Specified Learning Disabilities (LD-NOS disorder. Children with LD-NOS have notable learning difficulties, which affect education but are not able to be put into some specific category as reading (Dyslexia, Mathematics (Dyscalculia, or Writing (Dysgraphia. By using the EEG spectra, we aim to identify EEG patterns that may be related to specific learning disabilities in an individual case. This could be useful to develop subject-based methods of therapy, based on information provided by the EEG. Here we study 85 LD-NOS children, divided in three subgroups previously selected by a clustering technique over the scores of cognitive tests. The classification equation produced stable marginal areas under the ROC of 0.71 for discrimination between Group 1 vs. Group 2; 0.91 for Group 1 vs. Group 3; and 0.75 for Group 2 vs. Group1. A discussion of the EEG characteristics of each group related to the cognitive scores is also presented.

  14. Multiple classifier systems in texton-based approach for the classification of CT images of Lung

    DEFF Research Database (Denmark)

    Gangeh, Mehrdad J.; Sørensen, Lauge; Shaker, Saher B.

    2010-01-01

    In this paper, we propose using texton signatures based on raw pixel representation along with a parallel multiple classifier system for the classification of emphysema in computed tomography images of the lung. The multiple classifier system is composed of support vector machines on the texton.......e., texton size and k value in k-means. Our results show that while aggregation of single decisions by SVMs over various k values using multiple classifier systems helps to improve the results compared to single SVMs, combining over different texton sizes is not beneficial. The performance of the proposed...

  15. A novel approach for fire recognition using hybrid features and manifold learning-based classifier

    Science.gov (United States)

    Zhu, Rong; Hu, Xueying; Tang, Jiajun; Hu, Sheng

    2018-03-01

    Although image/video based fire recognition has received growing attention, an efficient and robust fire detection strategy is rarely explored. In this paper, we propose a novel approach to automatically identify the flame or smoke regions in an image. It is composed to three stages: (1) a block processing is applied to divide an image into several nonoverlapping image blocks, and these image blocks are identified as suspicious fire regions or not by using two color models and a color histogram-based similarity matching method in the HSV color space, (2) considering that compared to other information, the flame and smoke regions have significant visual characteristics, so that two kinds of image features are extracted for fire recognition, where local features are obtained based on the Scale Invariant Feature Transform (SIFT) descriptor and the Bags of Keypoints (BOK) technique, and texture features are extracted based on the Gray Level Co-occurrence Matrices (GLCM) and the Wavelet-based Analysis (WA) methods, and (3) a manifold learning-based classifier is constructed based on two image manifolds, which is designed via an improve Globular Neighborhood Locally Linear Embedding (GNLLE) algorithm, and the extracted hybrid features are used as input feature vectors to train the classifier, which is used to make decision for fire images or non fire images. Experiments and comparative analyses with four approaches are conducted on the collected image sets. The results show that the proposed approach is superior to the other ones in detecting fire and achieving a high recognition accuracy and a low error rate.

  16. Sensitivity and specificity of machine learning classifiers and spectral domain OCT for the diagnosis of glaucoma.

    Science.gov (United States)

    Vidotti, Vanessa G; Costa, Vital P; Silva, Fabrício R; Resende, Graziela M; Cremasco, Fernanda; Dias, Marcelo; Gomi, Edson S

    2012-06-15

    Purpose. To investigate the sensitivity and specificity of machine learning classifiers (MLC) and spectral domain optical coherence tomography (SD-OCT) for the diagnosis of glaucoma. Methods. Sixty-two patients with early to moderate glaucomatous visual field damage and 48 healthy individuals were included. All subjects underwent a complete ophthalmologic examination, achromatic standard automated perimetry, and RNFL imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec, Inc., Dublin, California, USA). Receiver operating characteristic (ROC) curves were obtained for all SD-OCT parameters. Subsequently, the following MLCs were tested: Classification Tree (CTREE), Random Forest (RAN), Bagging (BAG), AdaBoost M1 (ADA), Ensemble Selection (ENS), Multilayer Perceptron (MLP), Radial Basis Function (RBF), Naive-Bayes (NB), and Support Vector Machine (SVM). Areas under the ROC curves (aROCs) obtained for each parameter and each MLC were compared. Results. The mean age was 57.0±9.2 years for healthy individuals and 59.9±9.0 years for glaucoma patients (p=0.103). Mean deviation values were -4.1±2.4 dB for glaucoma patients and -1.5±1.6 dB for healthy individuals (pposition (0.765), and 6 o'clock position (0.754). The aROCs from classifiers varied from 0.785 (ADA) to 0.818 (BAG). The aROC obtained with BAG was not significantly different from the aROC obtained with the best single SD-OCT parameter (p=0.93). Conclusions. The SD-OCT showed good diagnostic accuracy in a group of patients with early glaucoma. In this series, MLCs did not improve the sensitivity and specificity of SD-OCT for the diagnosis of glaucoma.

  17. Can-Evo-Ens: Classifier stacking based evolutionary ensemble system for prediction of human breast cancer using amino acid sequences.

    Science.gov (United States)

    Ali, Safdar; Majid, Abdul

    2015-04-01

    The diagnostic of human breast cancer is an intricate process and specific indicators may produce negative results. In order to avoid misleading results, accurate and reliable diagnostic system for breast cancer is indispensable. Recently, several interesting machine-learning (ML) approaches are proposed for prediction of breast cancer. To this end, we developed a novel classifier stacking based evolutionary ensemble system "Can-Evo-Ens" for predicting amino acid sequences associated with breast cancer. In this paper, first, we selected four diverse-type of ML algorithms of Naïve Bayes, K-Nearest Neighbor, Support Vector Machines, and Random Forest as base-level classifiers. These classifiers are trained individually in different feature spaces using physicochemical properties of amino acids. In order to exploit the decision spaces, the preliminary predictions of base-level classifiers are stacked. Genetic programming (GP) is then employed to develop a meta-classifier that optimal combine the predictions of the base classifiers. The most suitable threshold value of the best-evolved predictor is computed using Particle Swarm Optimization technique. Our experiments have demonstrated the robustness of Can-Evo-Ens system for independent validation dataset. The proposed system has achieved the highest value of Area Under Curve (AUC) of ROC Curve of 99.95% for cancer prediction. The comparative results revealed that proposed approach is better than individual ML approaches and conventional ensemble approaches of AdaBoostM1, Bagging, GentleBoost, and Random Subspace. It is expected that the proposed novel system would have a major impact on the fields of Biomedical, Genomics, Proteomics, Bioinformatics, and Drug Development. Copyright © 2015 Elsevier Inc. All rights reserved.

  18. A system for classifying wood-using industries and recording statistics for automatic data processing.

    Science.gov (United States)

    E.W. Fobes; R.W. Rowe

    1968-01-01

    A system for classifying wood-using industries and recording pertinent statistics for automatic data processing is described. Forms and coding instructions for recording data of primary processing plants are included.

  19. Learning Bayesian network classifiers for credit scoring using Markov Chain Monte Carlo search

    NARCIS (Netherlands)

    Baesens, B.; Egmont-Petersen, M.; Castelo, R.; Vanthienen, J.

    2001-01-01

    In this paper, we will evaluate the power and usefulness of Bayesian network classifiers for credit scoring. Various types of Bayesian network classifiers will be evaluated and contrasted including unrestricted Bayesian network classifiers learnt using Markov Chain Monte Carlo (MCMC) search.

  20. Possible world based consistency learning model for clustering and classifying uncertain data.

    Science.gov (United States)

    Liu, Han; Zhang, Xianchao; Zhang, Xiaotong

    2018-06-01

    Possible world has shown to be effective for handling various types of data uncertainty in uncertain data management. However, few uncertain data clustering and classification algorithms are proposed based on possible world. Moreover, existing possible world based algorithms suffer from the following issues: (1) they deal with each possible world independently and ignore the consistency principle across different possible worlds; (2) they require the extra post-processing procedure to obtain the final result, which causes that the effectiveness highly relies on the post-processing method and the efficiency is also not very good. In this paper, we propose a novel possible world based consistency learning model for uncertain data, which can be extended both for clustering and classifying uncertain data. This model utilizes the consistency principle to learn a consensus affinity matrix for uncertain data, which can make full use of the information across different possible worlds and then improve the clustering and classification performance. Meanwhile, this model imposes a new rank constraint on the Laplacian matrix of the consensus affinity matrix, thereby ensuring that the number of connected components in the consensus affinity matrix is exactly equal to the number of classes. This also means that the clustering and classification results can be directly obtained without any post-processing procedure. Furthermore, for the clustering and classification tasks, we respectively derive the efficient optimization methods to solve the proposed model. Experimental results on real benchmark datasets and real world uncertain datasets show that the proposed model outperforms the state-of-the-art uncertain data clustering and classification algorithms in effectiveness and performs competitively in efficiency. Copyright © 2018 Elsevier Ltd. All rights reserved.

  1. Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

    Science.gov (United States)

    Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

    2018-05-10

    The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

  2. An expert computer program for classifying stars on the MK spectral classification system

    International Nuclear Information System (INIS)

    Gray, R. O.; Corbally, C. J.

    2014-01-01

    This paper describes an expert computer program (MKCLASS) designed to classify stellar spectra on the MK Spectral Classification system in a way similar to humans—by direct comparison with the MK classification standards. Like an expert human classifier, the program first comes up with a rough spectral type, and then refines that spectral type by direct comparison with MK standards drawn from a standards library. A number of spectral peculiarities, including barium stars, Ap and Am stars, λ Bootis stars, carbon-rich giants, etc., can be detected and classified by the program. The program also evaluates the quality of the delivered spectral type. The program currently is capable of classifying spectra in the violet-green region in either the rectified or flux-calibrated format, although the accuracy of the flux calibration is not important. We report on tests of MKCLASS on spectra classified by human classifiers; those tests suggest that over the entire HR diagram, MKCLASS will classify in the temperature dimension with a precision of 0.6 spectral subclass, and in the luminosity dimension with a precision of about one half of a luminosity class. These results compare well with human classifiers.

  3. An expert computer program for classifying stars on the MK spectral classification system

    Energy Technology Data Exchange (ETDEWEB)

    Gray, R. O. [Department of Physics and Astronomy, Appalachian State University, Boone, NC 26808 (United States); Corbally, C. J. [Vatican Observatory Research Group, Tucson, AZ 85721-0065 (United States)

    2014-04-01

    This paper describes an expert computer program (MKCLASS) designed to classify stellar spectra on the MK Spectral Classification system in a way similar to humans—by direct comparison with the MK classification standards. Like an expert human classifier, the program first comes up with a rough spectral type, and then refines that spectral type by direct comparison with MK standards drawn from a standards library. A number of spectral peculiarities, including barium stars, Ap and Am stars, λ Bootis stars, carbon-rich giants, etc., can be detected and classified by the program. The program also evaluates the quality of the delivered spectral type. The program currently is capable of classifying spectra in the violet-green region in either the rectified or flux-calibrated format, although the accuracy of the flux calibration is not important. We report on tests of MKCLASS on spectra classified by human classifiers; those tests suggest that over the entire HR diagram, MKCLASS will classify in the temperature dimension with a precision of 0.6 spectral subclass, and in the luminosity dimension with a precision of about one half of a luminosity class. These results compare well with human classifiers.

  4. Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

    Science.gov (United States)

    Choi, Joon Yul; Yoo, Tae Keun; Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

    2017-01-01

    Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

  5. Panorama of recommender systems to support learning

    OpenAIRE

    Drachsler, Hendrik; Verbert, Katrien; Santos, Olga; Manouselis, Nikos

    2015-01-01

    This chapter presents an analysis of recommender systems in Technology-Enhanced Learning along their 15 years existence (2000-2014). All recommender systems considered for the review aim to support educational stakeholders by personalising the learning process. In this meta-review 82 recommender systems from 35 different countries have been investigated and categorised according to a given classification framework. The reviewed systems have been classified into 7 clusters according to their c...

  6. From Physiological data to Emotional States: Conducting a User Study and Comparing Machine Learning Classifiers

    Directory of Open Access Journals (Sweden)

    Ali Mehmood KHAN

    2016-06-01

    Full Text Available Recognizing emotional states is becoming a major part of a user's context for wearable computing applications. The system should be able to acquire a user's emotional states by using physiological sensors. We want to develop a personal emotional states recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the eHealth platform 1 which is a ready-made, light weight, small and easy to use device for recognizing a few emotional states like ‘Sad’, ‘Dislike’, ‘Joy’, ‘Stress’, ‘Normal’, ‘No-Idea’, ‘Positive’ and ‘Negative’ using decision tree (J48 and k-Nearest Neighbors (IBK classifiers. In this paper, we present an approach to build a system that exhibits this property and provides evidence based on data for 8 different emotional states collected from 24 different subjects. Our results indicate that the system has an accuracy rate of approximately 98 %. In our work, we used four physiological sensors i.e. ‘Blood Volume Pulse’ (BVP, ‘Electromyogram’ (EMG, ‘Galvanic Skin Response’ (GSR, and ‘Skin Temperature’ in order to recognize emotional states (i.e. Stress, Joy/Happy, Sad, Normal/Neutral, Dislike, No-idea, Positive and Negative.

  7. Nonlinear System Identification Using Quasi-ARX RBFN Models with a Parameter-Classified Scheme

    Directory of Open Access Journals (Sweden)

    Lan Wang

    2017-01-01

    Full Text Available Quasi-linear autoregressive with exogenous inputs (Quasi-ARX models have received considerable attention for their usefulness in nonlinear system identification and control. In this paper, identification methods of quasi-ARX type models are reviewed and categorized in three main groups, and a two-step learning approach is proposed as an extension of the parameter-classified methods to identify the quasi-ARX radial basis function network (RBFN model. Firstly, a clustering method is utilized to provide statistical properties of the dataset for determining the parameters nonlinear to the model, which are interpreted meaningfully in the sense of interpolation parameters of a local linear model. Secondly, support vector regression is used to estimate the parameters linear to the model; meanwhile, an explicit kernel mapping is given in terms of the nonlinear parameter identification procedure, in which the model is transformed from the nonlinear-in-nature to the linear-in-parameter. Numerical and real cases are carried out finally to demonstrate the effectiveness and generalization ability of the proposed method.

  8. Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers.

    Science.gov (United States)

    Bowd, Christopher; Weinreb, Robert N; Balasubramanian, Madhusudhanan; Lee, Intae; Jang, Giljin; Yousefi, Siamak; Zangwill, Linda M; Medeiros, Felipe A; Girkin, Christopher A; Liebmann, Jeffrey M; Goldbaum, Michael H

    2014-01-01

    The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters. FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age. FDT mean deviation was -1.00 dB (S.D. = 2.80 dB) and -5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G1 and G2 combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G1 and G2 the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity. VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

  9. Evaluating Machine Learning Classifiers for Hybrid Network Intrusion Detection Systems

    Science.gov (United States)

    2015-03-26

    and the value-focused method. Comparing results from the two evaluation methods, fallacies are revealed with 2 of the 5 notional weighting schemes...for them, because of their relentless support, love , and encouragement. I give a sincere thank you to my research advisor, Dr. Robert Mills, for his...though Ad- aBoost.BayesNet dominated the traditional PR space using a single curve approach. This evaluation fallacy has not been demonstrated prior to

  10. Constrained parameter estimation for semi-supervised learning : The case of the nearest mean classifier

    NARCIS (Netherlands)

    Loog, M.

    2011-01-01

    A rather simple semi-supervised version of the equally simple nearest mean classifier is presented. However simple, the proposed approach is of practical interest as the nearest mean classifier remains a relevant tool in biomedical applications or other areas dealing with relatively high-dimensional

  11. Label-Driven Learning Framework: Towards More Accurate Bayesian Network Classifiers through Discrimination of High-Confidence Labels

    Directory of Open Access Journals (Sweden)

    Yi Sun

    2017-12-01

    Full Text Available Bayesian network classifiers (BNCs have demonstrated competitive classification accuracy in a variety of real-world applications. However, it is error-prone for BNCs to discriminate among high-confidence labels. To address this issue, we propose the label-driven learning framework, which incorporates instance-based learning and ensemble learning. For each testing instance, high-confidence labels are first selected by a generalist classifier, e.g., the tree-augmented naive Bayes (TAN classifier. Then, by focusing on these labels, conditional mutual information is redefined to more precisely measure mutual dependence between attributes, thus leading to a refined generalist with a more reasonable network structure. To enable finer discrimination, an expert classifier is tailored for each high-confidence label. Finally, the predictions of the refined generalist and the experts are aggregated. We extend TAN to LTAN (Label-driven TAN by applying the proposed framework. Extensive experimental results demonstrate that LTAN delivers superior classification accuracy to not only several state-of-the-art single-structure BNCs but also some established ensemble BNCs at the expense of reasonable computation overhead.

  12. An improved early detection method of type-2 diabetes mellitus using multiple classifier system

    KAUST Repository

    Zhu, Jia

    2015-01-01

    The specific causes of complex diseases such as Type-2 Diabetes Mellitus (T2DM) have not yet been identified. Nevertheless, many medical science researchers believe that complex diseases are caused by a combination of genetic, environmental, and lifestyle factors. Detection of such diseases becomes an issue because it is not free from false presumptions and is accompanied by unpredictable effects. Given the greatly increased amount of data gathered in medical databases, data mining has been used widely in recent years to detect and improve the diagnosis of complex diseases. However, past research showed that no single classifier can be considered optimal for all problems. Therefore, in this paper, we focus on employing multiple classifier systems to improve the accuracy of detection for complex diseases, such as T2DM. We proposed a dynamic weighted voting scheme called multiple factors weighted combination for classifiers\\' decision combination. This method considers not only the local and global accuracy but also the diversity among classifiers and localized generalization error of each classifier. We evaluated our method on two real T2DM data sets and other medical data sets. The favorable results indicated that our proposed method significantly outperforms individual classifiers and other fusion methods.

  13. Gender and classifiers in concurrent systems: Refining the typology of nominal classification

    Directory of Open Access Journals (Sweden)

    Sebastian Fedden

    2017-04-01

    Full Text Available Some languages have both gender and classifiers, contrary to what was once believed possible. We use these interesting languages as a unique window onto nominal classification. They provide the impetus for a new typology, based on the degree of orthogonality of the semantic systems and the degree of difference of the forms realizing them. This nine-way typology integrates traditional gender, traditional classifiers and – importantly – the many recently attested phenomena lying between. Besides progress specifically in understanding nominal classification, our approach provides clarity on the wider theoretical issue of single versus concurrent featural systems.

  14. Learning in Artificial Neural Systems

    Science.gov (United States)

    Matheus, Christopher J.; Hohensee, William E.

    1987-01-01

    This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

  15. Study of Machine-Learning Classifier and Feature Set Selection for Intent Classification of Korean Tweets about Food Safety

    Directory of Open Access Journals (Sweden)

    Yeom, Ha-Neul

    2014-09-01

    Full Text Available In recent years, several studies have proposed making use of the Twitter micro-blogging service to track various trends in online media and discussion. In this study, we specifically examine the use of Twitter to track discussions of food safety in the Korean language. Given the irregularity of keyword use in most tweets, we focus on optimistic machine-learning and feature set selection to classify collected tweets. We build the classifier model using Naive Bayes & Naive Bayes Multinomial, Support Vector Machine, and Decision Tree Algorithms, all of which show good performance. To select an optimum feature set, we construct a basic feature set as a standard for performance comparison, so that further test feature sets can be evaluated. Experiments show that precision and F-measure performance are best when using a Naive Bayes Multinomial classifier model with a test feature set defined by extracting Substantive, Predicate, Modifier, and Interjection parts of speech.

  16. Voice of the Classified Employee: A Descriptive Study to Determine Degree of Job Satisfaction of Classified Employees and to Design Systems of Support by School District Leaders

    Science.gov (United States)

    Barakos-Cartwright, Rebekah B.

    2012-01-01

    Classified employees comprise thirty two percent of the educational workforce in school districts in the state of California. Acknowledging these employees as a viable and untapped resource within the educational system will enrich job satisfaction for these employees and benefit the operations in school sites. As acknowledged and valued…

  17. A Hierarchical Method for Transient Stability Prediction of Power Systems Using the Confidence of a SVM-Based Ensemble Classifier

    Directory of Open Access Journals (Sweden)

    Yanzhen Zhou

    2016-09-01

    Full Text Available Machine learning techniques have been widely used in transient stability prediction of power systems. When using the post-fault dynamic responses, it is difficult to draw a definite conclusion about how long the duration of response data used should be in order to balance the accuracy and speed. Besides, previous studies have the problem of lacking consideration for the confidence level. To solve these problems, a hierarchical method for transient stability prediction based on the confidence of ensemble classifier using multiple support vector machines (SVMs is proposed. Firstly, multiple datasets are generated by bootstrap sampling, then features are randomly picked up to compress the datasets. Secondly, the confidence indices are defined and multiple SVMs are built based on these generated datasets. By synthesizing the probabilistic outputs of multiple SVMs, the prediction results and confidence of the ensemble classifier will be obtained. Finally, different ensemble classifiers with different response times are built to construct different layers of the proposed hierarchical scheme. The simulation results show that the proposed hierarchical method can balance the accuracy and rapidity of the transient stability prediction. Moreover, the hierarchical method can reduce the misjudgments of unstable instances and cooperate with the time domain simulation to insure the security and stability of power systems.

  18. Classifying chemical mode of action using gene networks and machine learning: a case study with the herbicide linuron.

    Science.gov (United States)

    Ornostay, Anna; Cowie, Andrew M; Hindle, Matthew; Baker, Christopher J O; Martyniuk, Christopher J

    2013-12-01

    The herbicide linuron (LIN) is an endocrine disruptor with an anti-androgenic mode of action. The objectives of this study were to (1) improve knowledge of androgen and anti-androgen signaling in the teleostean ovary and to (2) assess the ability of gene networks and machine learning to classify LIN as an anti-androgen using transcriptomic data. Ovarian explants from vitellogenic fathead minnows (FHMs) were exposed to three concentrations of either 5α-dihydrotestosterone (DHT), flutamide (FLUT), or LIN for 12h. Ovaries exposed to DHT showed a significant increase in 17β-estradiol (E2) production while FLUT and LIN had no effect on E2. To improve understanding of androgen receptor signaling in the ovary, a reciprocal gene expression network was constructed for DHT and FLUT using pathway analysis and these data suggested that steroid metabolism, translation, and DNA replication are processes regulated through AR signaling in the ovary. Sub-network enrichment analysis revealed that FLUT and LIN shared more regulated gene networks in common compared to DHT. Using transcriptomic datasets from different fish species, machine learning algorithms classified LIN successfully with other anti-androgens. This study advances knowledge regarding molecular signaling cascades in the ovary that are responsive to androgens and anti-androgens and provides proof of concept that gene network analysis and machine learning can classify priority chemicals using experimental transcriptomic data collected from different fish species. © 2013.

  19. Combined Approach of PNN and Time-Frequency as the Classifier for Power System Transient Problems

    Directory of Open Access Journals (Sweden)

    Aslam Pervez Memon

    2013-04-01

    Full Text Available The transients in power system cause serious disturbances in the reliability, safety and economy of the system. The transient signals possess the nonstationary characteristics in which the frequency as well as varying time information is compulsory for the analysis. Hence, it is vital, first to detect and classify the type of transient fault and then to mitigate them. This article proposes time-frequency and FFNN (Feedforward Neural Network approach for the classification of power system transients problems. In this work it is suggested that all the major categories of transients are simulated, de-noised, and decomposed with DWT (Discrete Wavelet and MRA (Multiresolution Analysis algorithm and then distinctive features are extracted to get optimal vector as input for training of PNN (Probabilistic Neural Network classifier. The simulation results of proposed approach prove their simplicity, accurateness and effectiveness for the automatic detection and classification of PST (Power System Transient types

  20. Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy

    Science.gov (United States)

    2017-01-01

    Background Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor’s activity for the purposes of quality assurance, safety, and continuing professional development. Objective The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors’ professional performance in the United Kingdom. Methods We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians’ colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Results Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to “popular” (recall=.97), “innovator” (recall=.98), and “respected” (recall=.87) codes and was lower for the “interpersonal” (recall=.80) and “professional” (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as “respected,” “professional,” and “interpersonal” related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P.05). Conclusions Machine learning algorithms can classify open-text feedback

  1. Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy.

    Science.gov (United States)

    Gibbons, Chris; Richards, Suzanne; Valderas, Jose Maria; Campbell, John

    2017-03-15

    Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor's activity for the purposes of quality assurance, safety, and continuing professional development. The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors' professional performance in the United Kingdom. We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians' colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to "popular" (recall=.97), "innovator" (recall=.98), and "respected" (recall=.87) codes and was lower for the "interpersonal" (recall=.80) and "professional" (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as "respected," "professional," and "interpersonal" related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P.05). Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high

  2. Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal.

    Science.gov (United States)

    Hosseinifard, Behshad; Moradi, Mohammad Hassan; Rostami, Reza

    2013-03-01

    Diagnosing depression in the early curable stages is very important and may even save the life of a patient. In this paper, we study nonlinear analysis of EEG signal for discriminating depression patients and normal controls. Forty-five unmedicated depressed patients and 45 normal subjects were participated in this study. Power of four EEG bands and four nonlinear features including detrended fluctuation analysis (DFA), higuchi fractal, correlation dimension and lyapunov exponent were extracted from EEG signal. For discriminating the two groups, k-nearest neighbor, linear discriminant analysis and logistic regression as the classifiers are then used. Highest classification accuracy of 83.3% is obtained by correlation dimension and LR classifier among other nonlinear features. For further improvement, all nonlinear features are combined and applied to classifiers. A classification accuracy of 90% is achieved by all nonlinear features and LR classifier. In all experiments, genetic algorithm is employed to select the most important features. The proposed technique is compared and contrasted with the other reported methods and it is demonstrated that by combining nonlinear features, the performance is enhanced. This study shows that nonlinear analysis of EEG can be a useful method for discriminating depressed patients and normal subjects. It is suggested that this analysis may be a complementary tool to help psychiatrists for diagnosing depressed patients. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

  3. Recommender Systems for Learning

    CERN Document Server

    Manouselis, Nikos; Verbert, Katrien; Duval, Erik

    2013-01-01

    Technology enhanced learning (TEL) aims to design, develop and test sociotechnical innovations that will support and enhance learning practices of both individuals and organisations. It is therefore an application domain that generally covers technologies that support all forms of teaching and learning activities. Since information retrieval (in terms of searching for relevant learning resources to support teachers or learners) is a pivotal activity in TEL, the deployment of recommender systems has attracted increased interest. This brief attempts to provide an introduction to recommender systems for TEL settings, as well as to highlight their particularities compared to recommender systems for other application domains.

  4. iLoc-Animal: a multi-label learning classifier for predicting subcellular localization of animal proteins.

    Science.gov (United States)

    Lin, Wei-Zhong; Fang, Jian-An; Xiao, Xuan; Chou, Kuo-Chen

    2013-04-05

    Predicting protein subcellular localization is a challenging problem, particularly when query proteins have multi-label features meaning that they may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing methods can only be used to deal with the single-label proteins. Actually, multi-label proteins should not be ignored because they usually bear some special function worthy of in-depth studies. By introducing the "multi-label learning" approach, a new predictor, called iLoc-Animal, has been developed that can be used to deal with the systems containing both single- and multi-label animal (metazoan except human) proteins. Meanwhile, to measure the prediction quality of a multi-label system in a rigorous way, five indices were introduced; they are "Absolute-True", "Absolute-False" (or Hamming-Loss"), "Accuracy", "Precision", and "Recall". As a demonstration, the jackknife cross-validation was performed with iLoc-Animal on a benchmark dataset of animal proteins classified into the following 20 location sites: (1) acrosome, (2) cell membrane, (3) centriole, (4) centrosome, (5) cell cortex, (6) cytoplasm, (7) cytoskeleton, (8) endoplasmic reticulum, (9) endosome, (10) extracellular, (11) Golgi apparatus, (12) lysosome, (13) mitochondrion, (14) melanosome, (15) microsome, (16) nucleus, (17) peroxisome, (18) plasma membrane, (19) spindle, and (20) synapse, where many proteins belong to two or more locations. For such a complicated system, the outcomes achieved by iLoc-Animal for all the aforementioned five indices were quite encouraging, indicating that the predictor may become a useful tool in this area. It has not escaped our notice that the multi-label approach and the rigorous measurement metrics can also be used to investigate many other multi-label problems in molecular biology. As a user-friendly web-server, iLoc-Animal is freely accessible to the public at the web-site .

  5. A bench-top hyperspectral imaging system to classify beef from Nellore cattle based on tenderness

    Science.gov (United States)

    Nubiato, Keni Eduardo Zanoni; Mazon, Madeline Rezende; Antonelo, Daniel Silva; Calkins, Chris R.; Naganathan, Govindarajan Konda; Subbiah, Jeyamkondan; da Luz e Silva, Saulo

    2018-03-01

    The aim of this study was to evaluate the accuracy of classification of Nellore beef aged for 0, 7, 14, or 21 days and classification based on tenderness and aging period using a bench-top hyperspectral imaging system. A hyperspectral imaging system (λ = 928-2524 nm) was used to collect hyperspectral images of the Longissimus thoracis et lumborum (aging n = 376 and tenderness n = 345) of Nellore cattle. The image processing steps included selection of region of interest, extraction of spectra, and indentification and evalution of selected wavelengths for classification. Six linear discriminant models were developed to classify samples based on tenderness and aging period. The model using the first derivative of partial absorbance spectra (give wavelength range spectra) was able to classify steaks based on the tenderness with an overall accuracy of 89.8%. The model using the first derivative of full absorbance spectra was able to classify steaks based on aging period with an overall accuracy of 84.8%. The results demonstrate that the HIS may be a viable technology for classifying beef based on tenderness and aging period.

  6. Classifying threats with a 14-MeV neutron interrogation system.

    Science.gov (United States)

    Strellis, Dan; Gozani, Tsahi

    2005-01-01

    SeaPODDS (Sea Portable Drug Detection System) is a non-intrusive tool for detecting concealed threats in hidden compartments of maritime vessels. This system consists of an electronic neutron generator, a gamma-ray detector, a data acquisition computer, and a laptop computer user-interface. Although initially developed to detect narcotics, recent algorithm developments have shown that the system is capable of correctly classifying a threat into one of four distinct categories: narcotic, explosive, chemical weapon, or radiological dispersion device (RDD). Detection of narcotics, explosives, and chemical weapons is based on gamma-ray signatures unique to the chemical elements. Elements are identified by their characteristic prompt gamma-rays induced by fast and thermal neutrons. Detection of RDD is accomplished by detecting gamma-rays emitted by common radioisotopes and nuclear reactor fission products. The algorithm phenomenology for classifying threats into the proper categories is presented here.

  7. Detecting and Classifying Human Touches in a Social Robot Through Acoustic Sensing and Machine Learning.

    Science.gov (United States)

    Alonso-Martín, Fernando; Gamboa-Montero, Juan José; Castillo, José Carlos; Castro-González, Álvaro; Salichs, Miguel Ángel

    2017-05-16

    An important aspect in Human-Robot Interaction is responding to different kinds of touch stimuli. To date, several technologies have been explored to determine how a touch is perceived by a social robot, usually placing a large number of sensors throughout the robot's shell. In this work, we introduce a novel approach, where the audio acquired from contact microphones located in the robot's shell is processed using machine learning techniques to distinguish between different types of touches. The system is able to determine when the robot is touched (touch detection), and to ascertain the kind of touch performed among a set of possibilities: stroke , tap , slap , and tickle (touch classification). This proposal is cost-effective since just a few microphones are able to cover the whole robot's shell since a single microphone is enough to cover each solid part of the robot. Besides, it is easy to install and configure as it just requires a contact surface to attach the microphone to the robot's shell and plug it into the robot's computer. Results show the high accuracy scores in touch gesture recognition. The testing phase revealed that Logistic Model Trees achieved the best performance, with an F -score of 0.81. The dataset was built with information from 25 participants performing a total of 1981 touch gestures.

  8. Learning Content Management Systems

    Directory of Open Access Journals (Sweden)

    Tache JURUBESCU

    2008-01-01

    Full Text Available The paper explains the evolution of e-Learning and related concepts and tools and its connection with other concepts such as Knowledge Management, Human Resources Management, Enterprise Resource Planning, and Information Technology. The paper also distinguished Learning Content Management Systems from Learning Management Systems and Content Management Systems used for general web-based content. The newest Learning Content Management System, very expensive and yet very little implemented is one of the best tools that helps us to cope with the realities of the 21st Century in what learning concerns. The debates over how beneficial one or another system is for an organization, can be driven by costs involved, efficiency envisaged, and availability of the product on the market.

  9. Mapping Woodland Cover in the Miombo Ecosystem: A Comparison of Machine Learning Classifiers

    Directory of Open Access Journals (Sweden)

    Courage Kamusoko

    2014-06-01

    Full Text Available Miombo woodlands in Southern Africa are experiencing accelerated changes due to natural and anthropogenic disturbances. In order to formulate sustainable woodland management strategies in the Miombo ecosystem, timely and up-to-date land cover information is required. Recent advances in remote sensing technology have improved land cover mapping in tropical evergreen ecosystems. However, woodland cover mapping remains a challenge in the Miombo ecosystem. The objective of the study was to evaluate the performance of decision trees (DT, random forests (RF, and support vector machines (SVM in the context of improving woodland and non-woodland cover mapping in the Miombo ecosystem in Zimbabwe. We used Multidate Landsat 8 spectral and spatial dependence (Moran’s I variables to map woodland and non-woodland cover. Results show that RF classifier outperformed the SVM and DT classifiers by 4% and 15%, respectively. The RF importance measures show that multidate Landsat 8 spectral and spatial variables had the greatest influence on class-separability in the study area. Therefore, the RF classifier has potential to improve woodland cover mapping in the Miombo ecosystem.

  10. Computer vision system for on-line sorting of pot plants using artificial Neural Network Classifier

    NARCIS (Netherlands)

    Timmermans, A.J.M.

    1996-01-01

    A flexible grading system for pot plants is described. The system consists of a colour camera, an image processing system and specially developed software. It can be applied to several types of pot plants because of its implementation of learning techniques. Experiments are described for

  11. Promises, pitfalls, and basic guidelines for applying machine learning classifiers to psychiatric imaging data, with autism as an example

    Directory of Open Access Journals (Sweden)

    Pegah Kassraian Fard

    2016-12-01

    Full Text Available Most psychiatric disorders are associated with subtle alterations in brain function and are subject to large inter-individual differences. Typically the diagnosis of these disorders requires time-consuming behavioral assessments administered by a multi-disciplinary team with extensive experience. Whilst the application of machine learning classification methods (ML classifiers to neuroimaging data has the potential to speed and simplify diagnosis of psychiatric disorders, the methods, assumptions, and analytical steps are not currently opaque and accessible to researchers and clinicians outside the field. In this paper, we describe potential classification pipelines for Autism Spectrum Disorder, as an example of a psychiatric disorder. The analyses are based on resting-state fMRI data derived from a multi-site data repository (ABIDE. We compare several popular ML classifiers such as support vector machines, neural networks and regression approaches, among others. In a tutorial style, written to be equally accessible for researchers and clinicians, we explain the rationale of each classification approach, clarify the underlying assumptions, and discuss possible pitfalls and challenges. We also provide the data as well as the MATLAB code we used to achieve our results. We show that out-of-the-box ML classifiers can yield classification accuracies of about 60-70%. Finally, we discuss how classification accuracy can be further improved, and we mention methodological developments that are needed to pave the way for the use of ML classifiers in clinical practice.

  12. Multi-Range Conditional Random Field for Classifying Railway Electrification System Objects Using Mobile Laser Scanning Data

    Directory of Open Access Journals (Sweden)

    Jaewook Jung

    2016-12-01

    Full Text Available Railways have been used as one of the most crucial means of transportation in public mobility and economic development. For safe railway operation, the electrification system in the railway infrastructure, which supplies electric power to trains, is an essential facility for stable train operation. Due to its important role, the electrification system needs to be rigorously and regularly inspected and managed. This paper presents a supervised learning method to classify Mobile Laser Scanning (MLS data into ten target classes representing overhead wires, movable brackets and poles, which are key objects in the electrification system. In general, the layout of the railway electrification system shows strong spatial regularity relations among object classes. The proposed classifier is developed based on Conditional Random Field (CRF, which characterizes not only labeling homogeneity at short range, but also the layout compatibility between different object classes at long range in the probabilistic graphical model. This multi-range CRF model consists of a unary term and three pairwise contextual terms. In order to gain computational efficiency, MLS point clouds are converted into a set of line segments to which the labeling process is applied. Support Vector Machine (SVM is used as a local classifier considering only node features for producing the unary potentials of the CRF model. As the short-range pairwise contextual term, the Potts model is applied to enforce a local smoothness in the short-range graph; while long-range pairwise potentials are designed to enhance the spatial regularities of both horizontal and vertical layouts among railway objects. We formulate two long-range pairwise potentials as the log posterior probability obtained by the naive Bayes classifier. The directional layout compatibilities are characterized in probability look-up tables, which represent the co-occurrence rate of spatial relations in the horizontal and vertical

  13. Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers

    Directory of Open Access Journals (Sweden)

    Ryan Henderson

    2017-09-01

    Full Text Available Picasso is a free open-source (Eclipse Public License web application written in Python for rendering standard visualizations useful for analyzing convolutional neural networks. Picasso ships with occlusion maps and saliency maps, two visualizations which help reveal issues that evaluation metrics like loss and accuracy might hide: for example, learning a proxy classification task. Picasso works with the Tensorflow deep learning framework, and Keras (when the model can be loaded into the Tensorflow backend. Picasso can be used with minimal configuration by deep learning researchers and engineers alike across various neural network architectures. Adding new visualizations is simple: the user can specify their visualization code and HTML template separately from the application code.

  14. Comparing statistical and machine learning classifiers: alternatives for predictive modeling in human factors research.

    Science.gov (United States)

    Carnahan, Brian; Meyer, Gérard; Kuntz, Lois-Ann

    2003-01-01

    Multivariate classification models play an increasingly important role in human factors research. In the past, these models have been based primarily on discriminant analysis and logistic regression. Models developed from machine learning research offer the human factors professional a viable alternative to these traditional statistical classification methods. To illustrate this point, two machine learning approaches--genetic programming and decision tree induction--were used to construct classification models designed to predict whether or not a student truck driver would pass his or her commercial driver license (CDL) examination. The models were developed and validated using the curriculum scores and CDL exam performances of 37 student truck drivers who had completed a 320-hr driver training course. Results indicated that the machine learning classification models were superior to discriminant analysis and logistic regression in terms of predictive accuracy. Actual or potential applications of this research include the creation of models that more accurately predict human performance outcomes.

  15. Machine learning systems

    Energy Technology Data Exchange (ETDEWEB)

    Forsyth, R

    1984-05-01

    With the dramatic rise of expert systems has come a renewed interest in the fuel that drives them-knowledge. For it is specialist knowledge which gives expert systems their power. But extracting knowledge from human experts in symbolic form has proved arduous and labour-intensive. So the idea of machine learning is enjoying a renaissance. Machine learning is any automatic improvement in the performance of a computer system over time, as a result of experience. Thus a learning algorithm seeks to do one or more of the following: cover a wider range of problems, deliver more accurate solutions, obtain answers more cheaply, and simplify codified knowledge. 6 references.

  16. Classifying genes to the correct Gene Ontology Slim term in Saccharomyces cerevisiae using neighbouring genes with classification learning

    Directory of Open Access Journals (Sweden)

    Tsatsoulis Costas

    2010-05-01

    Full Text Available Abstract Background There is increasing evidence that gene location and surrounding genes influence the functionality of genes in the eukaryotic genome. Knowing the Gene Ontology Slim terms associated with a gene gives us insight into a gene's functionality by informing us how its gene product behaves in a cellular context using three different ontologies: molecular function, biological process, and cellular component. In this study, we analyzed if we could classify a gene in Saccharomyces cerevisiae to its correct Gene Ontology Slim term using information about its location in the genome and information from its nearest-neighbouring genes using classification learning. Results We performed experiments to establish that the MultiBoostAB algorithm using the J48 classifier could correctly classify Gene Ontology Slim terms of a gene given information regarding the gene's location and information from its nearest-neighbouring genes for training. Different neighbourhood sizes were examined to determine how many nearest neighbours should be included around each gene to provide better classification rules. Our results show that by just incorporating neighbour information from each gene's two-nearest neighbours, the percentage of correctly classified genes to their correct Gene Ontology Slim term for each ontology reaches over 80% with high accuracy (reflected in F-measures over 0.80 of the classification rules produced. Conclusions We confirmed that in classifying genes to their correct Gene Ontology Slim term, the inclusion of neighbour information from those genes is beneficial. Knowing the location of a gene and the Gene Ontology Slim information from neighbouring genes gives us insight into that gene's functionality. This benefit is seen by just including information from a gene's two-nearest neighbouring genes.

  17. Advanced recognition of explosives in traces on polymer surfaces using LIBS and supervised learning classifiers.

    Science.gov (United States)

    Serrano, Jorge; Moros, Javier; Sánchez, Carlos; Macías, Jorge; Laserna, J Javier

    2014-01-02

    The large similarity existing in the spectral emissions collected from organic compounds by laser-induced breakdown spectroscopy (LIBS) is a limiting factor for the use of this technology in the real world. Specifically, among the most ambitious challenges of today's LIBS involves the recognition of an organic residue when neglected on the surface of an object of identical nature. Under these circumstances, the development of an efficient algorithm to disclose the minute differences within this highly complex spectral information is crucial for a realistic application of LIBS in countering explosive threats. An approach cemented on scatter plots of characteristic emission features has been developed to identify organic explosives when located on polymeric surfaces (teflon, nylon and polyethylene). By using selected spectral variables, the approach allows to design a concise classifier for alerting when one of four explosives (DNT, TNT, RDX and PETN) is present on the surface of the polymer. Ordinary products (butter, fuel oil, hand cream, olive oil and motor oil) cause no confusion in the decisions taken by the classifier. With rates of false negatives and false positives below 5%, results demonstrate that the classification algorithm enables to label residues according to their harmful nature in the most demanding scenario for a LIBS sensor. Copyright © 2013 Elsevier B.V. All rights reserved.

  18. Using machine learning to classify image features from canine pelvic radiographs

    DEFF Research Database (Denmark)

    McEvoy, Fintan; Amigo Rubio, Jose Manuel

    2013-01-01

    As the number of images per study increases in the field of veterinary radiology, there is a growing need for computer-assisted diagnosis techniques. The purpose of this study was to evaluate two machine learning statistical models for automatically identifying image regions that contain the canine...

  19. Exploring Machine Learning Techniques Using Patient Interactions in Online Health Forums to Classify Drug Safety

    Science.gov (United States)

    Chee, Brant Wah Kwong

    2011-01-01

    This dissertation explores the use of personal health messages collected from online message forums to predict drug safety using natural language processing and machine learning techniques. Drug safety is defined as any drug with an active safety alert from the US Food and Drug Administration (FDA). It is believed that this is the first…

  20. Using supervised machine learning to code policy issues: Can classifiers generalize across contexts?

    NARCIS (Netherlands)

    Burscher, B.; Vliegenthart, R.; de Vreese, C.H.

    2015-01-01

    Content analysis of political communication usually covers large amounts of material and makes the study of dynamics in issue salience a costly enterprise. In this article, we present a supervised machine learning approach for the automatic coding of policy issues, which we apply to news articles

  1. Comparing Machine Learning Classifiers and Linear/Logistic Regression to Explore the Relationship between Hand Dimensions and Demographic Characteristics.

    Science.gov (United States)

    Miguel-Hurtado, Oscar; Guest, Richard; Stevenage, Sarah V; Neil, Greg J; Black, Sue

    2016-01-01

    Understanding the relationship between physiological measurements from human subjects and their demographic data is important within both the biometric and forensic domains. In this paper we explore the relationship between measurements of the human hand and a range of demographic features. We assess the ability of linear regression and machine learning classifiers to predict demographics from hand features, thereby providing evidence on both the strength of relationship and the key features underpinning this relationship. Our results show that we are able to predict sex, height, weight and foot size accurately within various data-range bin sizes, with machine learning classification algorithms out-performing linear regression in most situations. In addition, we identify the features used to provide these relationships applicable across multiple applications.

  2. Evaluating a k-nearest neighbours-based classifier for locating faulty areas in power systems

    Directory of Open Access Journals (Sweden)

    Juan José Mora Flórez

    2008-09-01

    Full Text Available This paper reports a strategy for identifying and locating faults in a power distribution system. The strategy was based on the K-nearest neighbours technique. This technique simply helps to estimate a distance from the features used for describing a particu-lar fault being classified to the faults presented during the training stage. If new data is presented to the proposed fault locator, it is classified according to the nearest example recovered. A characterisation of the voltage and current measurements obtained at one single line end is also presented in this document for assigning the area in the case of a fault in a power system. The pro-posed strategy was tested in a real power distribution system, average 93% confidence indexes being obtained which gives a good indicator of the proposal’s high performance. The results showed how a fault could be located by using features obtained from voltage and current, improving utility response and thereby improving system continuity indexes in power distribution sys-tems.

  3. Use of machine learning methods to classify Universities based on the income structure

    Science.gov (United States)

    Terlyga, Alexandra; Balk, Igor

    2017-10-01

    In this paper we discuss use of machine learning methods such as self organizing maps, k-means and Ward’s clustering to perform classification of universities based on their income. This classification will allow us to quantitate classification of universities as teaching, research, entrepreneur, etc. which is important tool for government, corporations and general public alike in setting expectation and selecting universities to achieve different goals.

  4. Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers.

    Directory of Open Access Journals (Sweden)

    Muhammad Ahmad

    Full Text Available Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF, in which we implement the idea of selecting optimal training samples to enhance generalization performance for two different kinds of classifiers, discriminative and generative (e.g. SVM and KNN. The optimal samples are selected by first estimating the boundary of each class and then calculating the fuzziness-based distance between each sample and the estimated class boundaries. Those samples that are at smaller distances from the boundaries and have higher fuzziness are chosen as target candidates for the training set. Through detailed experimentation on three publically available datasets, we showed that when trained with the proposed sample selection framework, both classifiers achieved higher classification accuracy and lower processing time with the small amount of training data as opposed to the case where the training samples were selected randomly. Our experiments demonstrate the effectiveness of our proposed method, which equates favorably with the state-of-the-art methods.

  5. MixDroid: A multi-features and multi-classifiers bagging system for Android malware detection

    Science.gov (United States)

    Huang, Weiqing; Hou, Erhang; Zheng, Liang; Feng, Weimiao

    2018-05-01

    In the past decade, Android platform has rapidly taken over the mobile market for its superior convenience and open source characteristics. However, with the popularity of Android, malwares targeting on Android devices are increasing rapidly, while the conventional rule-based and expert-experienced approaches are no longer able to handle such explosive growth. In this paper, combining with the theory of natural language processing and machine learning, we not only implement the basic feature extraction of permission application features, but also propose two innovative schemes of feature extraction: Dalvik opcode features and malicious code image, and implement an automatic Android malware detection system MixDroid which is based on multi-features and multi-classifiers. According to our experiment results on 20,000 Android applications, detection accuracy of MixDroid is 98.1%, which proves our schemes' effectiveness in Android malware detection.

  6. Evaluation of Stream Mining Classifiers for Real-Time Clinical Decision Support System: A Case Study of Blood Glucose Prediction in Diabetes Therapy

    Directory of Open Access Journals (Sweden)

    Simon Fong

    2013-01-01

    Full Text Available Earlier on, a conceptual design on the real-time clinical decision support system (rt-CDSS with data stream mining was proposed and published. The new system is introduced that can analyze medical data streams and can make real-time prediction. This system is based on a stream mining algorithm called VFDT. The VFDT is extended with the capability of using pointers to allow the decision tree to remember the mapping relationship between leaf nodes and the history records. In this paper, which is a sequel to the rt-CDSS design, several popular machine learning algorithms are investigated for their suitability to be a candidate in the implementation of classifier at the rt-CDSS. A classifier essentially needs to accurately map the events inputted to the system into one of the several predefined classes of assessments, such that the rt-CDSS can follow up with the prescribed remedies being recommended to the clinicians. For a real-time system like rt-CDSS, the major technological challenges lie in the capability of the classifier to process, analyze and classify the dynamic input data, quickly and upmost reliably. An experimental comparison is conducted. This paper contributes to the insight of choosing and embedding a stream mining classifier into rt-CDSS with a case study of diabetes therapy.

  7. The SNL/NM Classified Waste Landfill Excavation: Lessons Learned Moving from Planning to Implementation

    International Nuclear Information System (INIS)

    Galloway, Robert B; Slavin, Paula

    1999-01-01

    The Sandia National Laboratories/New Mexico (SNL/NM) Environmental Restoration Project is halfway through excavating the Classified Waste Landfill in Technical Area II, a disposal area for weapon components for approximately 40 years. While the planning phase of any project is important, it is only a means of getting to the field implementation phase where reality quickly sinks in. Documents outlining the general processes are developed, heavy equipment, supply needs, requisite skills, and staffing levels are anticipated, and contingencies for waste management are put in place. However, the nature of landfill excavation dictates that even the most detailed plans will probably change. This project is proving that trying to account for undefined variables and predicting the total cost of landfill remediation is very difficult if the contents are not well known. In landfill excavation, contingency cannot be minimized. During development of the waste management plan, it was recognized that even the best forecasting could not formulate the perfect cradle-to-grave processes because waste streams are rarely definable before excavation begins. Typically, as excavation progresses and waste streams are generated, new characterization information allows further definition of disposal options which, in turn, modify the generation/management process. A general plan combined with close involvement of waste management personnel to resolve characterization and packaging questions during generation has worked very well. And, as expected, each new pit excavated creates new waste management challenges. The material excavated consists primarily of classified weapon assemblies and related components, so disposition must include demilitarization and sanitization. The demilitarization task at the start of the project was provided by an SNL/NM group that has since lost their funding and operational capability. This project is having to take on the task of disassembly, destruction, and

  8. Advanced Cell Classifier: User-Friendly Machine-Learning-Based Software for Discovering Phenotypes in High-Content Imaging Data.

    Science.gov (United States)

    Piccinini, Filippo; Balassa, Tamas; Szkalisity, Abel; Molnar, Csaba; Paavolainen, Lassi; Kujala, Kaisa; Buzas, Krisztina; Sarazova, Marie; Pietiainen, Vilja; Kutay, Ulrike; Smith, Kevin; Horvath, Peter

    2017-06-28

    High-content, imaging-based screens now routinely generate data on a scale that precludes manual verification and interrogation. Software applying machine learning has become an essential tool to automate analysis, but these methods require annotated examples to learn from. Efficiently exploring large datasets to find relevant examples remains a challenging bottleneck. Here, we present Advanced Cell Classifier (ACC), a graphical software package for phenotypic analysis that addresses these difficulties. ACC applies machine-learning and image-analysis methods to high-content data generated by large-scale, cell-based experiments. It features methods to mine microscopic image data, discover new phenotypes, and improve recognition performance. We demonstrate that these features substantially expedite the training process, successfully uncover rare phenotypes, and improve the accuracy of the analysis. ACC is extensively documented, designed to be user-friendly for researchers without machine-learning expertise, and distributed as a free open-source tool at www.cellclassifier.org. Copyright © 2017 Elsevier Inc. All rights reserved.

  9. Defect characterization by an adaptive learning classifier in ultrasonic inspection of ferritic materials

    International Nuclear Information System (INIS)

    Grozellier, M.; Bieth, M.; Romy, D.

    1985-01-01

    The purpose of the work presented here is to determine the efficiency and reliability of the discrimination method ''Adapatative Learning Network''. This process is used to identify the nature of defects detected during Ultrasonic Testing (UT), by analysing some of the echo parameters calculated in temporal and frequency domains. The survey which dealt with several hundreds of echoes, revealed that the machined artificial reflectors, well defined geometrically, were identified with a probability exceeding 95 %. The fatigue cracks, producing less characteristic echoes, are identified with a slightly lower probability (90 % - 95 %)

  10. Simultaneous-Fault Diagnosis of Gas Turbine Generator Systems Using a Pairwise-Coupled Probabilistic Classifier

    Directory of Open Access Journals (Sweden)

    Zhixin Yang

    2013-01-01

    Full Text Available A reliable fault diagnostic system for gas turbine generator system (GTGS, which is complicated and inherent with many types of component faults, is essential to avoid the interruption of electricity supply. However, the GTGS diagnosis faces challenges in terms of the existence of simultaneous-fault diagnosis and high cost in acquiring the exponentially increased simultaneous-fault vibration signals for constructing the diagnostic system. This research proposes a new diagnostic framework combining feature extraction, pairwise-coupled probabilistic classifier, and decision threshold optimization. The feature extraction module adopts wavelet packet transform and time-domain statistical features to extract vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features. The features of single faults in a simultaneous-fault pattern are extracted and then detected using a probabilistic classifier, namely, pairwise-coupled relevance vector machine, which is trained with single-fault patterns only. Therefore, the training dataset of simultaneous-fault patterns is unnecessary. To optimize the decision threshold, this research proposes to use grid search method which can ensure a global solution as compared with traditional computational intelligence techniques. Experimental results show that the proposed framework performs well for both single-fault and simultaneous-fault diagnosis and is superior to the frameworks without feature extraction and pairwise coupling.

  11. Comparing classifiers for pronunciation error detection

    NARCIS (Netherlands)

    Strik, H.; Truong, K.; Wet, F. de; Cucchiarini, C.

    2007-01-01

    Providing feedback on pronunciation errors in computer assisted language learning systems requires that pronunciation errors be detected automatically. In the present study we compare four types of classifiers that can be used for this purpose: two acoustic-phonetic classifiers (one of which employs

  12. Sixty Percent Conceptual Design Report: Enterprise Accountability System for Classified Removable Electronic Media

    Energy Technology Data Exchange (ETDEWEB)

    B. Gardiner; L.Graton; J.Longo; T.Marks, Jr.; B.Martinez; R. Strittmatter; C.Woods; J. Joshua

    2003-05-03

    Classified removable electronic media (CREM) are tracked in several different ways at the Laboratory. To ensure greater security for CREM, we are creating a single, Laboratory-wide system to track CREM. We are researching technology that can be used to electronically tag and detect CREM, designing a database to track the movement of CREM, and planning to test the system at several locations around the Laboratory. We focus on affixing ''smart tags'' to items we want to track and installing gates at pedestrian portals to detect the entry or exit of tagged items. By means of an enterprise database, the system will track the entry and exit of tagged items into and from CREM storage vaults, vault-type rooms, access corridors, or boundaries of secure areas, as well as the identity of the person carrying an item. We are considering several options for tracking items that can give greater security, but at greater expense.

  13. Classifying bent radio galaxies from a mixture of point-like/extended images with Machine Learning.

    Science.gov (United States)

    Bastien, David; Oozeer, Nadeem; Somanah, Radhakrishna

    2017-05-01

    The hypothesis that bent radio sources are supposed to be found in rich, massive galaxy clusters and the avalibility of huge amount of data from radio surveys have fueled our motivation to use Machine Learning (ML) to identify bent radio sources and as such use them as tracers for galaxy clusters. The shapelet analysis allowed us to decompose radio images into 256 features that could be fed into the ML algorithm. Additionally, ideas from the field of neuro-psychology helped us to consider training the machine to identify bent galaxies at different orientations. From our analysis, we found that the Random Forest algorithm was the most effective with an accuracy rate of 92% for a classification of point and extended sources as well as an accuracy of 80% for bent and unbent classification.

  14. Artificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge Notes.

    Science.gov (United States)

    Lin, Chin; Hsu, Chia-Jung; Lou, Yu-Sheng; Yeh, Shih-Jen; Lee, Chia-Cheng; Su, Sui-Lung; Chen, Hsiang-Cheng

    2017-11-06

    Automated disease code classification using free-text medical information is important for public health surveillance. However, traditional natural language processing (NLP) pipelines are limited, so we propose a method combining word embedding with a convolutional neural network (CNN). Our objective was to compare the performance of traditional pipelines (NLP plus supervised machine learning models) with that of word embedding combined with a CNN in conducting a classification task identifying International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis codes in discharge notes. We used 2 classification methods: (1) extracting from discharge notes some features (terms, n-gram phrases, and SNOMED CT categories) that we used to train a set of supervised machine learning models (support vector machine, random forests, and gradient boosting machine), and (2) building a feature matrix, by a pretrained word embedding model, that we used to train a CNN. We used these methods to identify the chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. We conducted the evaluation using 103,390 discharge notes covering patients hospitalized from June 1, 2015 to January 31, 2017 in the Tri-Service General Hospital in Taipei, Taiwan. We used the receiver operating characteristic curve as an evaluation measure, and calculated the area under the curve (AUC) and F-measure as the global measure of effectiveness. In 5-fold cross-validation tests, our method had a higher testing accuracy (mean AUC 0.9696; mean F-measure 0.9086) than traditional NLP-based approaches (mean AUC range 0.8183-0.9571; mean F-measure range 0.5050-0.8739). A real-world simulation that split the training sample and the testing sample by date verified this result (mean AUC 0.9645; mean F-measure 0.9003 using the proposed method). Further analysis showed that the convolutional layers of the CNN effectively identified a large number of keywords and automatically

  15. Classifying injury narratives of large administrative databases for surveillance-A practical approach combining machine learning ensembles and human review.

    Science.gov (United States)

    Marucci-Wellman, Helen R; Corns, Helen L; Lehto, Mark R

    2017-01-01

    Injury narratives are now available real time and include useful information for injury surveillance and prevention. However, manual classification of the cause or events leading to injury found in large batches of narratives, such as workers compensation claims databases, can be prohibitive. In this study we compare the utility of four machine learning algorithms (Naïve Bayes, Single word and Bi-gram models, Support Vector Machine and Logistic Regression) for classifying narratives into Bureau of Labor Statistics Occupational Injury and Illness event leading to injury classifications for a large workers compensation database. These algorithms are known to do well classifying narrative text and are fairly easy to implement with off-the-shelf software packages such as Python. We propose human-machine learning ensemble approaches which maximize the power and accuracy of the algorithms for machine-assigned codes and allow for strategic filtering of rare, emerging or ambiguous narratives for manual review. We compare human-machine approaches based on filtering on the prediction strength of the classifier vs. agreement between algorithms. Regularized Logistic Regression (LR) was the best performing algorithm alone. Using this algorithm and filtering out the bottom 30% of predictions for manual review resulted in high accuracy (overall sensitivity/positive predictive value of 0.89) of the final machine-human coded dataset. The best pairings of algorithms included Naïve Bayes with Support Vector Machine whereby the triple ensemble NB SW =NB BI-GRAM =SVM had very high performance (0.93 overall sensitivity/positive predictive value and high accuracy (i.e. high sensitivity and positive predictive values)) across both large and small categories leaving 41% of the narratives for manual review. Integrating LR into this ensemble mix improved performance only slightly. For large administrative datasets we propose incorporation of methods based on human-machine pairings such as

  16. Data fusion and machine learning to identify threat vectors for the Zika virus and classify vulnerability

    Science.gov (United States)

    Gentle, J. N., Jr.; Kahn, A.; Pierce, S. A.; Wang, S.; Wade, C.; Moran, S.

    2016-12-01

    With the continued spread of the zika virus in the United States in both Florida and Virginia, increased public awareness, prevention and targeted prediction is necessary to effectively mitigate further infection and propagation of the virus throughout the human population. The goal of this project is to utilize publicly accessible data and HPC resources coupled with machine learning algorithms to identify potential threat vectors for the spread of the zika virus in Texas, the United States and globally by correlating available zika case data collected from incident reports in medical databases (e.g., CDC, Florida Department of Health) with known bodies of water in various earth science databases (e.g., USGS NAQWA Data, NASA ASTER Data, TWDB Data) and by using known mosquito population centers as a proxy for trends in population distribution (e.g., WHO, European CDC, Texas Data) while correlating historical trends in the spread of other mosquito borne diseases (e.g., chikungunya, malaria, dengue, yellow fever, west nile, etc.). The resulting analysis should refine the identification of the specific threat vectors for the spread of the virus which will correspondingly increase the effectiveness of the limited resources allocated towards combating the disease through better strategic implementation of defense measures. The minimal outcome of this research is a better understanding of the factors involved in the spread of the zika virus, with the greater potential to save additional lives through more effective resource utilization and public outreach.

  17. Design of a modified adaptive neuro fuzzy inference system classifier for medical diagnosis of Pima Indians Diabetes

    Science.gov (United States)

    Sagir, Abdu Masanawa; Sathasivam, Saratha

    2017-08-01

    Medical diagnosis is the process of determining which disease or medical condition explains a person's determinable signs and symptoms. Diagnosis of most of the diseases is very expensive as many tests are required for predictions. This paper aims to introduce an improved hybrid approach for training the adaptive network based fuzzy inference system with Modified Levenberg-Marquardt algorithm using analytical derivation scheme for computation of Jacobian matrix. The goal is to investigate how certain diseases are affected by patient's characteristics and measurement such as abnormalities or a decision about presence or absence of a disease. To achieve an accurate diagnosis at this complex stage of symptom analysis, the physician may need efficient diagnosis system to classify and predict patient condition by using an adaptive neuro fuzzy inference system (ANFIS) pre-processed by grid partitioning. The proposed hybridised intelligent system was tested with Pima Indian Diabetes dataset obtained from the University of California at Irvine's (UCI) machine learning repository. The proposed method's performance was evaluated based on training and test datasets. In addition, an attempt was done to specify the effectiveness of the performance measuring total accuracy, sensitivity and specificity. In comparison, the proposed method achieves superior performance when compared to conventional ANFIS based gradient descent algorithm and some related existing methods. The software used for the implementation is MATLAB R2014a (version 8.3) and executed in PC Intel Pentium IV E7400 processor with 2.80 GHz speed and 2.0 GB of RAM.

  18. Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry

    Directory of Open Access Journals (Sweden)

    Fabrício R. Silva

    2013-06-01

    Full Text Available PURPOSE: To evaluate the sensitivity and specificity of machine learning classifiers (MLCs for glaucoma diagnosis using Spectral Domain OCT (SD-OCT and standard automated perimetry (SAP. METHODS: Observational cross-sectional study. Sixty two glaucoma patients and 48 healthy individuals were included. All patients underwent a complete ophthalmologic examination, achromatic standard automated perimetry (SAP and retinal nerve fiber layer (RNFL imaging with SD-OCT (Cirrus HD-OCT; Carl Zeiss Meditec Inc., Dublin, California. Receiver operating characteristic (ROC curves were obtained for all SD-OCT parameters and global indices of SAP. Subsequently, the following MLCs were tested using parameters from the SD-OCT and SAP: Bagging (BAG, Naive-Bayes (NB, Multilayer Perceptron (MLP, Radial Basis Function (RBF, Random Forest (RAN, Ensemble Selection (ENS, Classification Tree (CTREE, Ada Boost M1(ADA,Support Vector Machine Linear (SVML and Support Vector Machine Gaussian (SVMG. Areas under the receiver operating characteristic curves (aROC obtained for isolated SAP and OCT parameters were compared with MLCs using OCT+SAP data. RESULTS: Combining OCT and SAP data, MLCs' aROCs varied from 0.777(CTREE to 0.946 (RAN.The best OCT+SAP aROC obtained with RAN (0.946 was significantly larger the best single OCT parameter (p<0.05, but was not significantly different from the aROC obtained with the best single SAP parameter (p=0.19. CONCLUSION: Machine learning classifiers trained on OCT and SAP data can successfully discriminate between healthy and glaucomatous eyes. The combination of OCT and SAP measurements improved the diagnostic accuracy compared with OCT data alone.

  19. An Unobtrusive Fall Detection and Alerting System Based on Kalman Filter and Bayes Network Classifier.

    Science.gov (United States)

    He, Jian; Bai, Shuang; Wang, Xiaoyi

    2017-06-16

    Falls are one of the main health risks among the elderly. A fall detection system based on inertial sensors can automatically detect fall event and alert a caregiver for immediate assistance, so as to reduce injuries causing by falls. Nevertheless, most inertial sensor-based fall detection technologies have focused on the accuracy of detection while neglecting quantization noise caused by inertial sensor. In this paper, an activity model based on tri-axial acceleration and gyroscope is proposed, and the difference between activities of daily living (ADLs) and falls is analyzed. Meanwhile, a Kalman filter is proposed to preprocess the raw data so as to reduce noise. A sliding window and Bayes network classifier are introduced to develop a wearable fall detection system, which is composed of a wearable motion sensor and a smart phone. The experiment shows that the proposed system distinguishes simulated falls from ADLs with a high accuracy of 95.67%, while sensitivity and specificity are 99.0% and 95.0%, respectively. Furthermore, the smart phone can issue an alarm to caregivers so as to provide timely and accurate help for the elderly, as soon as the system detects a fall.

  20. RUGs and "Medi-Cal" systems for classifying nursing home patients.

    Science.gov (United States)

    Grimaldi, P L

    1985-12-01

    Medicare and most state Medicaid programs currently use indirect case-mix measures to determine reimbursement for nursing home care. In the future, however, they probably will incorporate more direct case-mix measures into their payment systems. Care must be exercised in designing a case-based prospective payment system to ensure that its financial incentives motivate providers to expedite recovery, prevent deterioration, and admit heavy-care patients. For example, although use of a services-rendered approach helps guarantee that care will be provided when needed, it also offers providers an incentive to furnish a service regardless of whether it is in the patient's best interest. Consideration must be given to the frequency with which patients are reassessed. The implications of the timing of reassessments for quality of care also must be studied. Ideally, quality would be measured on an outcome basis--that is, payment would depend on whether targeted goals for individual patients are reached--rather than on structural or process measures alone. Two recent classification systems--Resource Utilization Groups and Medi-Cal groups--may serve as models for case-based prospective payment systems. Each method classifies patients into distinct, meaningful categories based on activities of daily living and services received.

  1. The Among System in the Senior High School History Learning

    Directory of Open Access Journals (Sweden)

    Nugraha Nugraha

    2018-05-01

    Full Text Available This study describes the theoretical and practical aspect of the Among - system in the modern historical learning. As a preliminary research, this article formulates a conceptual framework of the Among- system in the contemporary learning, especially modern history learning. This research used library research method that conducted in Dewantara Kirti Griya Library Yogyakarta. Data analysis was done by the descriptive method of collecting data, compiling or classifying, and interpreting.

  2. A decision support system using combined-classifier for high-speed data stream in smart grid

    Science.gov (United States)

    Yang, Hang; Li, Peng; He, Zhian; Guo, Xiaobin; Fong, Simon; Chen, Huajun

    2016-11-01

    Large volume of high-speed streaming data is generated by big power grids continuously. In order to detect and avoid power grid failure, decision support systems (DSSs) are commonly adopted in power grid enterprises. Among all the decision-making algorithms, incremental decision tree is the most widely used one. In this paper, we propose a combined classifier that is a composite of a cache-based classifier (CBC) and a main tree classifier (MTC). We integrate this classifier into a stream processing engine on top of the DSS such that high-speed steaming data can be transformed into operational intelligence efficiently. Experimental results show that our proposed classifier can return more accurate answers than other existing ones.

  3. Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

    Science.gov (United States)

    McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

    2018-04-01

    Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

  4. A FRAMEWORK FOR CLASSIFYING MISFITS BETWEEN ENTERPRISE RESOURCE PLANNING (ERP SYSTEMS AND BUSINESS STRATEGIES

    Directory of Open Access Journals (Sweden)

    Rosnah Idrus

    2011-07-01

    Full Text Available Enterprise resource planning (ERP is a broad set of activities that is supported by multi- module application software that helps manufacturers or other businesses manage their activities. ERP is more than a software package; it includes the efforts and activities to integrate internal and external management information, business process automation and reengineering, and organisation structure streamlining. Thus, ERP eventually leads to an efficient and competitive business. Despite the prominence of ERP systems, approximately three-quarters of ERP projects are deemed as failures. Most failures are attributed to the misfit between pre-loaded business models in the ERP system and business requirements in the real world. This paper introduces a framework to classify ERP misfits into logical categories that provide insights for solution derivation. Subsequently, the classification methods are applied to a case study. Practitioners can use the misfit classification method to derive corresponding actions as solutions for ERP misfits based on their nature or specificity. In addition, the theoretical contribution of the ERP misfit problem is explored to provide information for researchers to determine appropriate theories and concepts explaining this domain.

  5. Supervised Learning for Dynamical System Learning.

    Science.gov (United States)

    Hefny, Ahmed; Downey, Carlton; Gordon, Geoffrey J

    2015-01-01

    Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoff between computational and statistical efficiency. Unfortunately, they can be difficult to use and extend in practice: e.g., they can make it difficult to incorporate prior information such as sparsity or structure. To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L 1 regularization. Many existing spectral methods are special cases of this new framework, using linear regression as the supervised learner. We demonstrate the effectiveness of our framework by showing examples where nonlinear regression or lasso let us learn better state representations than plain linear regression does; the correctness of these instances follows directly from our general analysis.

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

    Energy Technology Data Exchange (ETDEWEB)

    Timofeev, Andrey V.; Egorov, Dmitry V. [LPP “EqualiZoom”, Astana, 010000 (Kazakhstan)

    2016-06-08

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

  7. An MR Brain Images Classifier System via Particle Swarm Optimization and Kernel Support Vector Machine

    Directory of Open Access Journals (Sweden)

    Yudong Zhang

    2013-01-01

    Full Text Available Automated abnormal brain detection is extremely of importance for clinical diagnosis. Over last decades numerous methods had been presented. In this paper, we proposed a novel hybrid system to classify a given MR brain image as either normal or abnormal. The proposed method first employed digital wavelet transform to extract features then used principal component analysis (PCA to reduce the feature space. Afterwards, we constructed a kernel support vector machine (KSVM with RBF kernel, using particle swarm optimization (PSO to optimize the parameters C and σ. Fivefold cross-validation was utilized to avoid overfitting. In the experimental procedure, we created a 90 images dataset brain downloaded from Harvard Medical School website. The abnormal brain MR images consist of the following diseases: glioma, metastatic adenocarcinoma, metastatic bronchogenic carcinoma, meningioma, sarcoma, Alzheimer, Huntington, motor neuron disease, cerebral calcinosis, Pick’s disease, Alzheimer plus visual agnosia, multiple sclerosis, AIDS dementia, Lyme encephalopathy, herpes encephalitis, Creutzfeld-Jakob disease, and cerebral toxoplasmosis. The 5-folded cross-validation classification results showed that our method achieved 97.78% classification accuracy, higher than 86.22% by BP-NN and 91.33% by RBF-NN. For the parameter selection, we compared PSO with those of random selection method. The results showed that the PSO is more effective to build optimal KSVM.

  8. Volume reduction system by soil classifying. Soil-washing system and problems to be solved

    International Nuclear Information System (INIS)

    Oshino, Yoshio

    2016-01-01

    Radioactive contamination of ground surfaces, buildings and forests in a broad area was caused by the accident at the Fukushima Daiichi Nuclear Power Plant in Japan. The national government and municipalities have still been carrying out the decontamination works for livelihood areas after five years from the accident. The government estimated that the amounts of soils and wastes removed by the decontamination works would be about 28,000,000 cubic meters maximum including 20,000,000 cubic meters maximum of soils. The removed soils will be stored in “Interim Storage Facility” then will be finally disposed outside of Fukushima prefecture within 30 years. On the other hand, shortage of the soils as materials needed for the revitalization in Fukushima prefecture is expected. Technical Advisory Council on Remediation and Waste Management, which consists of about 90 companies, started a working group to investigate solutions to these problems. The working group focused on the investigation of the possibility to recycle the soils by washing and classification to use them as the materials for civil engineering works, and to reduce the volume of the interim storage. In the first part of this report, we have evaluated the applicability of various technologies for purification and volume reduction of the removed soils, and have researched usages, required quantities and specifications of the recycled soils. In the second part, we have made trial calculations of the volume reduction effects and costs using the washing and classification system. The calculated results showed the possibilities of reducing the storage capacity of the interim storage facility, as well as the construction and the operation costs by recycling the removed soils with the washing and classification system inside the interim storage facility. At the end of this report, we proposed problems to be solved in order to adopt the washing and classification system. (author)

  9. [Application of classified protection of information security in the information system of air pollution and health impact monitoring].

    Science.gov (United States)

    Hao, Shuxin; Lü, Yiran; Liu, Jie; Liu, Yue; Xu, Dongqun

    2018-01-01

    To study the application of classified protection of information security in the information system of air pollution and health impact monitoring, so as to solve the possible safety risk of the information system. According to the relevant national standards and requirements for the information system security classified protection, and the professional characteristics of the information system, to design and implement the security architecture of information system, also to determine the protection level of information system. Basic security measures for the information system were developed in the technical safety and management safety aspects according to the protection levels, which effectively prevented the security risk of the information system. The information system established relatively complete information security protection measures, to enhanced the security of professional information and system service, and to ensure the safety of air pollution and health impact monitoring project carried out smoothly.

  10. A DNA-based pattern classifier with in vitro learning and associative recall for genomic characterization and biosensing without explicit sequence knowledge.

    Science.gov (United States)

    Lee, Ju Seok; Chen, Junghuei; Deaton, Russell; Kim, Jin-Woo

    2014-01-01

    Genetic material extracted from in situ microbial communities has high promise as an indicator of biological system status. However, the challenge is to access genomic information from all organisms at the population or community scale to monitor the biosystem's state. Hence, there is a need for a better diagnostic tool that provides a holistic view of a biosystem's genomic status. Here, we introduce an in vitro methodology for genomic pattern classification of biological samples that taps large amounts of genetic information from all genes present and uses that information to detect changes in genomic patterns and classify them. We developed a biosensing protocol, termed Biological Memory, that has in vitro computational capabilities to "learn" and "store" genomic sequence information directly from genomic samples without knowledge of their explicit sequences, and that discovers differences in vitro between previously unknown inputs and learned memory molecules. The Memory protocol was designed and optimized based upon (1) common in vitro recombinant DNA operations using 20-base random probes, including polymerization, nuclease digestion, and magnetic bead separation, to capture a snapshot of the genomic state of a biological sample as a DNA memory and (2) the thermal stability of DNA duplexes between new input and the memory to detect similarities and differences. For efficient read out, a microarray was used as an output method. When the microarray-based Memory protocol was implemented to test its capability and sensitivity using genomic DNA from two model bacterial strains, i.e., Escherichia coli K12 and Bacillus subtilis, results indicate that the Memory protocol can "learn" input DNA, "recall" similar DNA, differentiate between dissimilar DNA, and detect relatively small concentration differences in samples. This study demonstrated not only the in vitro information processing capabilities of DNA, but also its promise as a genomic pattern classifier that could

  11. Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the 'Extreme Learning Machine' Algorithm.

    Directory of Open Access Journals (Sweden)

    Mark D McDonnell

    Full Text Available Recent advances in training deep (multi-layer architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the 'Extreme Learning Machine' (ELM approach, which also enables a very rapid training time (∼ 10 minutes. Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random 'receptive field' sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.

  12. Carbon classified?

    DEFF Research Database (Denmark)

    Lippert, Ingmar

    2012-01-01

    . Using an actor- network theory (ANT) framework, the aim is to investigate the actors who bring together the elements needed to classify their carbon emission sources and unpack the heterogeneous relations drawn on. Based on an ethnographic study of corporate agents of ecological modernisation over...... a period of 13 months, this paper provides an exploration of three cases of enacting classification. Drawing on ANT, we problematise the silencing of a range of possible modalities of consumption facts and point to the ontological ethics involved in such performances. In a context of global warming...

  13. Learning to teach secondary mathematics using an online learning system

    Science.gov (United States)

    Cavanagh, Michael; Mitchelmore, Michael

    2011-12-01

    We report the results of a classroom study of three secondary mathematics teachers who had no prior experience teaching with technology as they began to use an online mathematics learning system in their lessons. We gave the teachers only basic instruction on how to operate the system and then observed them intensively over four school terms as they taught using it. We documented changes in the teachers' Pedagogical Technology Knowledge and subsequently classified their various roles as technology bystanders, adopters, adaptors and innovators. Results show that all teachers made some progress toward using the system in more sophisticated ways, but the improvements were not uniform across the teachers. We suggest possible reasons to explain the variation and discuss some implications for teacher professional development.

  14. Identification of Classified Information in Unclassified DoD Systems During the Audit of Internal Controls and Data Reliability in the Deployable Disbursing System

    Science.gov (United States)

    2009-02-17

    Identification of Classified Information in Unclassified DoD Systems During the Audit of Internal Controls and Data Reliability in the Deployable...TITLE AND SUBTITLE Identification of Classified Information in Unclassified DoD Systems During the Audit of Internal Controls and Data Reliability...Systems During the Audit ofInternal Controls and Data Reliability in the Deployable Disbursing System (Report No. D-2009-054) Weare providing this

  15. Modeling learning technology systems as business systems

    NARCIS (Netherlands)

    Avgeriou, Paris; Retalis, Symeon; Papaspyrou, Nikolaos

    2003-01-01

    The design of Learning Technology Systems, and the Software Systems that support them, is largely conducted on an intuitive, ad hoc basis, thus resulting in inefficient systems that defectively support the learning process. There is now justifiable, increasing effort in formalizing the engineering

  16. Network Intrusion Detection System (NIDS in Cloud Environment based on Hidden Naïve Bayes Multiclass Classifier

    Directory of Open Access Journals (Sweden)

    Hafza A. Mahmood

    2018-04-01

    Full Text Available Cloud Environment is next generation internet based computing system that supplies customiza-ble services to the end user to work or access to the various cloud applications. In order to provide security and decrease the damage of information system, network and computer system it is im-portant to provide intrusion detection system (IDS. Now Cloud environment are under threads from network intrusions, as one of most prevalent and offensive means Denial of Service (DoS attacks that cause dangerous impact on cloud computing systems. This paper propose Hidden naïve Bayes (HNB Classifier to handle DoS attacks which is a data mining (DM model used to relaxes the conditional independence assumption of Naïve Bayes classifier (NB, proposed sys-tem used HNB Classifier supported with discretization and feature selection where select the best feature enhance the performance of the system and reduce consuming time. To evaluate the per-formance of proposal system, KDD 99 CUP and NSL KDD Datasets has been used. The experi-mental results show that the HNB classifier improves the performance of NIDS in terms of accu-racy and detecting DoS attacks, where the accuracy of detect DoS is 100% in three test KDD cup 99 dataset by used only 12 feature that selected by use gain ratio while in NSL KDD Dataset the accuracy of detect DoS attack is 90 % in three Experimental NSL KDD dataset by select 10 fea-ture only.

  17. Toward A Dual-Learning Systems Model of Speech Category Learning

    Directory of Open Access Journals (Sweden)

    Bharath eChandrasekaran

    2014-07-01

    Full Text Available More than two decades of work in vision posits the existence of dual-learning systems of category learning. The reflective system uses working memory to develop and test rules for classifying in an explicit fashion, while the reflexive system operates by implicitly associating perception with actions that lead to reinforcement. Dual-learning systems models hypothesize that in learning natural categories, learners initially use the reflective system and, with practice, transfer control to the reflexive system. The role of reflective and reflexive systems in auditory category learning and more specifically in speech category learning has not been systematically examined. In this article we describe a neurobiologically-constrained dual-learning systems theoretical framework that is currently being developed in speech category learning and review recent applications of this framework. Using behavioral and computational modeling approaches, we provide evidence that speech category learning is predominantly mediated by the reflexive learning system. In one application, we explore the effects of normal aging on non-speech and speech category learning. We find an age related deficit in reflective-optimal but not reflexive-optimal auditory category learning. Prominently, we find a large age-related deficit in speech learning. The computational modeling suggests that older adults are less likely to transition from simple, reflective, uni-dimensional rules to more complex, reflexive, multi-dimensional rules. In a second application we summarize a recent study examining auditory category learning in individuals with elevated depressive symptoms. We find a deficit in reflective-optimal and an enhancement in reflexive-optimal auditory category learning. Interestingly, individuals with elevated depressive symptoms also show an advantage in learning speech categories. We end with a brief summary and description of a number of future directions.

  18. Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection

    International Nuclear Information System (INIS)

    Makili, L.; Vega, J.; Dormido-Canto, S.; Pastor, I.; Pereira, A.; Farias, G.; Portas, A.; Perez-Risco, D.; Rodriguez-Fernandez, M.C.; Busch, P.

    2010-01-01

    An automatic image classification system based on support vector machines (SVM) has been in operation for years in the TJ-II Thomson Scattering diagnostic. It recognizes five different types of images: CCD camera background, measurement of stray light without plasma or in a collapsed discharge, image during ECH phase, image during NBI phase and image after reaching the cut off density during ECH heating. Each kind of image implies the execution of different application software. Due to the fact that the recognition system is based on a learning system and major modifications have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid. A new SVM model has been developed with the current conditions. Also, specific error conditions in the data acquisition process can automatically be detected and managed now. The recovering process has been automated, thereby avoiding the loss of data in ensuing discharges.

  19. Upgrade of the automatic analysis system in the TJ-II Thomson Scattering diagnostic: New image recognition classifier and fault condition detection

    Energy Technology Data Exchange (ETDEWEB)

    Makili, L. [Dpto. Informatica y Automatica - UNED, Madrid (Spain); Vega, J. [Asociacion EURATOM/CIEMAT para Fusion, Madrid (Spain); Dormido-Canto, S., E-mail: sebas@dia.uned.e [Dpto. Informatica y Automatica - UNED, Madrid (Spain); Pastor, I.; Pereira, A. [Asociacion EURATOM/CIEMAT para Fusion, Madrid (Spain); Farias, G. [Dpto. Informatica y Automatica - UNED, Madrid (Spain); Portas, A.; Perez-Risco, D.; Rodriguez-Fernandez, M.C. [Asociacion EURATOM/CIEMAT para Fusion, Madrid (Spain); Busch, P. [FOM Institut voor PlasmaFysica Rijnhuizen, Nieuwegein (Netherlands)

    2010-07-15

    An automatic image classification system based on support vector machines (SVM) has been in operation for years in the TJ-II Thomson Scattering diagnostic. It recognizes five different types of images: CCD camera background, measurement of stray light without plasma or in a collapsed discharge, image during ECH phase, image during NBI phase and image after reaching the cut off density during ECH heating. Each kind of image implies the execution of different application software. Due to the fact that the recognition system is based on a learning system and major modifications have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid. A new SVM model has been developed with the current conditions. Also, specific error conditions in the data acquisition process can automatically be detected and managed now. The recovering process has been automated, thereby avoiding the loss of data in ensuing discharges.

  20. The Effectiveness of the Gesture-Based Learning System (GBLS and Its Impact on Learning Experience

    Directory of Open Access Journals (Sweden)

    Moamer Ali Shakroum

    2016-06-01

    Full Text Available Several studies and experiments have been conducted in recent years to examine the value and the advantage of using the Gesture-Based Learning System (GBLS.The investigation of the influence of the GBLS mode on the learning outcomes is still scarce. Most previous studies did not address more than one category of learning outcomes (cognitive, affective outcomes, etc. at the same time when used to understand the impact of GBLS. Moreover, none of these studies considered the difference in students’ characteristics such as learning styles and spatial abilities. Therefore, a comprehensive empirical research on the impact of the GBLS mode on learning outcomes is needed. The purpose of this paper is to fill in the gap and to investigate the effectiveness of the GBLS mode on learning using Technology Mediated Learning (TML models. This study revealed that the GBLS mode has greater positive impact on students’ learning outcomes (cognitive and affective outcomes when compared with other two learning modes that are classified as Computer Simulation Software Learning (CSSL mode and conventional learning mode. In addition, this study also found that the GBLS mode is capable of serving all students with different learning styles and spatial ability levels. The results of this study revealed that the GBLS mode outperformed the existing learning methods by providing a unique learning experience that considers the differences between students. The results have also shown that the Kinect user interface can create an interactive and an enjoyable learning experience.

  1. Upgrade of the Automatic Analysis System in the TJ-II Thomson Scattering Diagnostic: New Image Recognition Classifier and Fault Condition Detection

    Energy Technology Data Exchange (ETDEWEB)

    Makili, L.; Dormido-Canto, S. [UNED, Madrid (Spain); Vega, J.; Pastor, I.; Pereira, A.; Portas, A.; Perez-Risco, D.; Rodriguez-Fernandez, M. [Association EuratomCIEMAT para Fusion, Madrid (Spain); Busch, P. [FOM Instituut voor PlasmaFysica Rijnhuizen, Nieuwegein (Netherlands)

    2009-07-01

    Full text of publication follows: An automatic image classification system has been in operation for years in the TJ-II Thomson diagnostic. It recognizes five different types of images: CCD camera background, measurement of stray light without plasma or in a collapsed discharge, image during ECH phase, image during NBI phase and image after reaching the cut o density during ECH heating. Each kind of image implies the execution of different application software. Therefore, the classification system was developed to launch the corresponding software in an automatic way. The method to recognize the several classes was based on a learning system, in particular Support Vector Machines (SVM). Since the first implementation of the classifier, a relevant improvement has been accomplished in the diagnostic: a new notch filter is in operation, having a larger stray-light rejection at the ruby wavelength than the previous filter. On the other hand, its location in the optical system has been modified. As a consequence, the stray light pattern in the CCD image is located in a different position. In addition to these transformations, the power of neutral beams injected in the TJ-II plasma has been increased about a factor of 2. Due to the fact that the recognition system is based on a learning system and major modifications have been carried out in both the diagnostic (optics) and TJ-II plasmas (injected power), the classifier model is no longer valid. The creation of a new model (also based on SVM) under the present conditions has been necessary. Finally, specific error conditions in the data acquisition process can automatically be detected now. The recovering process can be automated, thereby avoiding the loss of data in ensuing discharges. (authors)

  2. Recommendation System for Adaptive Learning.

    Science.gov (United States)

    Chen, Yunxiao; Li, Xiaoou; Liu, Jingchen; Ying, Zhiliang

    2018-01-01

    An adaptive learning system aims at providing instruction tailored to the current status of a learner, differing from the traditional classroom experience. The latest advances in technology make adaptive learning possible, which has the potential to provide students with high-quality learning benefit at a low cost. A key component of an adaptive learning system is a recommendation system, which recommends the next material (video lectures, practices, and so on, on different skills) to the learner, based on the psychometric assessment results and possibly other individual characteristics. An important question then follows: How should recommendations be made? To answer this question, a mathematical framework is proposed that characterizes the recommendation process as a Markov decision problem, for which decisions are made based on the current knowledge of the learner and that of the learning materials. In particular, two plain vanilla systems are introduced, for which the optimal recommendation at each stage can be obtained analytically.

  3. Learning Companion Systems, Social Learning Systems, and the Global Social Learning Club.

    Science.gov (United States)

    Chan, Tak-Wai

    1996-01-01

    Describes the development of learning companion systems and their contributions to the class of social learning systems that integrate artificial intelligence agents and use machine learning to tutor and interact with students. Outlines initial social learning projects, their programming languages, and weakness. Future improvements will include…

  4. Prediction of Endocrine System Affectation in Fisher 344 Rats by Food Intake Exposed with Malathion, Applying Naïve Bayes Classifier and Genetic Algorithms.

    Science.gov (United States)

    Mora, Juan David Sandino; Hurtado, Darío Amaya; Sandoval, Olga Lucía Ramos

    2016-01-01

    Reported cases of uncontrolled use of pesticides and its produced effects by direct or indirect exposition, represent a high risk for human health. Therefore, in this paper, it is shown the results of the development and execution of an algorithm that predicts the possible effects in endocrine system in Fisher 344 (F344) rats, occasioned by ingestion of malathion. It was referred to ToxRefDB database in which different case studies in F344 rats exposed to malathion were collected. The experimental data were processed using Naïve Bayes (NB) machine learning classifier, which was subsequently optimized using genetic algorithms (GAs). The model was executed in an application with a graphical user interface programmed in C#. There was a tendency to suffer bigger alterations, increasing levels in the parathyroid gland in dosages between 4 and 5 mg/kg/day, in contrast to the thyroid gland for doses between 739 and 868 mg/kg/day. It was showed a greater resistance for females to contract effects on the endocrine system by the ingestion of malathion. Females were more susceptible to suffer alterations in the pituitary gland with exposure times between 3 and 6 months. The prediction model based on NB classifiers allowed to analyze all the possible combinations of the studied variables and improving its accuracy using GAs. Excepting the pituitary gland, females demonstrated better resistance to contract effects by increasing levels on the rest of endocrine system glands.

  5. CLASSIFICATION OF LEARNING MANAGEMENT SYSTEMS

    Directory of Open Access Journals (Sweden)

    Yu. B. Popova

    2016-01-01

    Full Text Available Using of information technologies and, in particular, learning management systems, increases opportunities of teachers and students in reaching their goals in education. Such systems provide learning content, help organize and monitor training, collect progress statistics and take into account the individual characteristics of each user. Currently, there is a huge inventory of both paid and free systems are physically located both on college servers and in the cloud, offering different features sets of different licensing scheme and the cost. This creates the problem of choosing the best system. This problem is partly due to the lack of comprehensive classification of such systems. Analysis of more than 30 of the most common now automated learning management systems has shown that a classification of such systems should be carried out according to certain criteria, under which the same type of system can be considered. As classification features offered by the author are: cost, functionality, modularity, keeping the customer’s requirements, the integration of content, the physical location of a system, adaptability training. Considering the learning management system within these classifications and taking into account the current trends of their development, it is possible to identify the main requirements to them: functionality, reliability, ease of use, low cost, support for SCORM standard or Tin Can API, modularity and adaptability. According to the requirements at the Software Department of FITR BNTU under the guidance of the author since 2009 take place the development, the use and continuous improvement of their own learning management system.

  6. Examining the Capability of Supervised Machine Learning Classifiers in Extracting Flooded Areas from Landsat TM Imagery: A Case Study from a Mediterranean Flood

    Directory of Open Access Journals (Sweden)

    Gareth Ireland

    2015-03-01

    Full Text Available This study explored the capability of Support Vector Machines (SVMs and regularised kernel Fisher’s discriminant analysis (rkFDA machine learning supervised classifiers in extracting flooded area from optical Landsat TM imagery. The ability of both techniques was evaluated using a case study of a riverine flood event in 2010 in a heterogeneous Mediterranean region, for which TM imagery acquired shortly after the flood event was available. For the two classifiers, both linear and non-linear (kernel versions were utilised in their implementation. The ability of the different classifiers to map the flooded area extent was assessed on the basis of classification accuracy assessment metrics. Results showed that rkFDA outperformed SVMs in terms of accurate flooded pixels detection, also producing fewer missed detections of the flooded area. Yet, SVMs showed less false flooded area detections. Overall, the non-linear rkFDA classification method was the more accurate of the two techniques (OA = 96.23%, K = 0.877. Both methods outperformed the standard Normalized Difference Water Index (NDWI thresholding (OA = 94.63, K = 0.818 by roughly 0.06 K points. Although overall accuracy results for the rkFDA and SVMs classifications only showed a somewhat minor improvement on the overall accuracy exhibited by the NDWI thresholding, notably both classifiers considerably outperformed the thresholding algorithm in other specific accuracy measures (e.g. producer accuracy for the “not flooded” class was ~10.5% less accurate for the NDWI thresholding algorithm in comparison to the classifiers, and average per-class accuracy was ~5% less accurate than the machine learning models. This study provides evidence of the successful application of supervised machine learning for classifying flooded areas in Landsat imagery, where few studies so far exist in this direction. Considering that Landsat data is open access and has global coverage, the results of this study

  7. Intelligent fractions learning system: implementation

    CSIR Research Space (South Africa)

    Smith, Andrew C

    2011-05-01

    Full Text Available Conference Proceedings Paul Cunningham and Miriam Cunningham (Eds) IIMC International Information Management Corporation, 2011 ISBN: 978-1-905824-24-3 An Intelligent Fractions Learning System: Implementation Andrew Cyrus SMITH1, Teemu H. LAINE2 1CSIR... to fractions. Our aim with the current research project is to extend the existing UFractions learning system to incorporate automatic data capturing. ?Intelligent UFractions? allows a teacher to remotely monitor the children?s progress during...

  8. Design of a Fuzzy Rule Base Expert System to Predict and Classify ...

    African Journals Online (AJOL)

    The main objective of design of a rule base expert system using fuzzy logic approach is to predict and forecast the risk level of cardiac patients to avoid sudden death. In this proposed system, uncertainty is captured using rule base and classification using fuzzy c-means clustering is discussed to overcome the risk level, ...

  9. Indirect Tire Monitoring System - Machine Learning Approach

    Science.gov (United States)

    Svensson, O.; Thelin, S.; Byttner, S.; Fan, Y.

    2017-10-01

    The heavy vehicle industry has today no requirement to provide a tire pressure monitoring system by law. This has created issues surrounding unknown tire pressure and thread depth during active service. There is also no standardization for these kind of systems which means that different manufacturers and third party solutions work after their own principles and it can be hard to know what works for a given vehicle type. The objective is to create an indirect tire monitoring system that can generalize a method that detect both incorrect tire pressure and thread depth for different type of vehicles within a fleet without the need for additional physical sensors or vehicle specific parameters. The existing sensors that are connected communicate through CAN and are interpreted by the Drivec Bridge hardware that exist in the fleet. By using supervised machine learning a classifier was created for each axle where the main focus was the front axle which had the most issues. The classifier will classify the vehicles tires condition and will be implemented in Drivecs cloud service where it will receive its data. The resulting classifier is a random forest implemented in Python. The result from the front axle with a data set consisting of 9767 samples of buses with correct tire condition and 1909 samples of buses with incorrect tire condition it has an accuracy of 90.54% (0.96%). The data sets are created from 34 unique measurements from buses between January and May 2017. This classifier has been exported and is used inside a Node.js module created for Drivecs cloud service which is the result of the whole implementation. The developed solution is called Indirect Tire Monitoring System (ITMS) and is seen as a process. This process will predict bad classes in the cloud which will lead to warnings. The warnings are defined as incidents. They contain only the information needed and the bandwidth of the incidents are also controlled so incidents are created within an

  10. Deep learning approach for classifying, detecting and predicting photometric redshifts of quasars in the Sloan Digital Sky Survey stripe 82

    Science.gov (United States)

    Pasquet-Itam, J.; Pasquet, J.

    2018-04-01

    We have applied a convolutional neural network (CNN) to classify and detect quasars in the Sloan Digital Sky Survey Stripe 82 and also to predict the photometric redshifts of quasars. The network takes the variability of objects into account by converting light curves into images. The width of the images, noted w, corresponds to the five magnitudes ugriz and the height of the images, noted h, represents the date of the observation. The CNN provides good results since its precision is 0.988 for a recall of 0.90, compared to a precision of 0.985 for the same recall with a random forest classifier. Moreover 175 new quasar candidates are found with the CNN considering a fixed recall of 0.97. The combination of probabilities given by the CNN and the random forest makes good performance even better with a precision of 0.99 for a recall of 0.90. For the redshift predictions, the CNN presents excellent results which are higher than those obtained with a feature extraction step and different classifiers (a K-nearest-neighbors, a support vector machine, a random forest and a Gaussian process classifier). Indeed, the accuracy of the CNN within |Δz| < 0.1 can reach 78.09%, within |Δz| < 0.2 reaches 86.15%, within |Δz| < 0.3 reaches 91.2% and the value of root mean square (rms) is 0.359. The performance of the KNN decreases for the three |Δz| regions, since within the accuracy of |Δz| < 0.1, |Δz| < 0.2, and |Δz| < 0.3 is 73.72%, 82.46%, and 90.09% respectively, and the value of rms amounts to 0.395. So the CNN successfully reduces the dispersion and the catastrophic redshifts of quasars. This new method is very promising for the future of big databases such as the Large Synoptic Survey Telescope. A table of the candidates is only available at the CDS via anonymous ftp to http://cdsarc.u-strasbg.fr (http://130.79.128.5) or via http://cdsarc.u-strasbg.fr/viz-bin/qcat?J/A+A/611/A97

  11. Studies on classifying Indian coals. Part II. A new system for grading and pricing

    Energy Technology Data Exchange (ETDEWEB)

    Tumuluri, S.G.; Shrikhande, S.K.; Rao, S.K.; Haque, R.

    1985-07-01

    The new system is self-complete through grading to pricing. It grades non-coking coal by moisture and ash contents. Coking coal is graded by GKLT coke type and ash content. Volatile matter content is used as a supporting indexer, where necessary. Through the grade data, a coal is evaluated into a single numeral which depicts the coaly matter content and its nature or effectiveness. This value, called effective coaly matter, is converted to a relative rupee value or price index/price. Pragmatics and versatility of the system are discussed.

  12. The Enhancement of Students’ Skill in Classifying and Concept Mastery in Salt Hydrolysis Material Through Problem Solving Learning Model

    OpenAIRE

    Safitri, Esty Indriyani; Rosilawati, Ila; Efkar, Tasviri

    2012-01-01

    The purpose of this research is to find out effectiveness of problem solving learning model on salt hydrolysis material in improve the skill of classifying and concept mastery. The population of the research was all students in XI science class in SMAN I Way Jepara number in 120 students. The samples were 30 students in XI science 3 class and 30 students in XI science 4 that have equal academic abilities. This research was a quasi experiment using non equivalent (pretest-postest) control grou...

  13. Considering Alternate Futures to Classify Off-Task Behavior as Emotion Self-Regulation: A Supervised Learning Approach

    Science.gov (United States)

    Sabourin, Jennifer L.; Rowe, Jonathan P.; Mott, Bradford W.; Lester, James C.

    2013-01-01

    Over the past decade, there has been growing interest in real-time assessment of student engagement and motivation during interactions with educational software. Detecting symptoms of disengagement, such as off-task behavior, has shown considerable promise for understanding students' motivational characteristics during learning. In this paper, we…

  14. Wearable kinesthetic system for capturing and classifying upper limb gesture in post-stroke rehabilitation.

    Science.gov (United States)

    Tognetti, Alessandro; Lorussi, Federico; Bartalesi, Raphael; Quaglini, Silvana; Tesconi, Mario; Zupone, Giuseppe; De Rossi, Danilo

    2005-03-02

    BACKGROUND: Monitoring body kinematics has fundamental relevance in several biological and technical disciplines. In particular the possibility to exactly know the posture may furnish a main aid in rehabilitation topics. In the present work an innovative and unobtrusive garment able to detect the posture and the movement of the upper limb has been introduced, with particular care to its application in post stroke rehabilitation field by describing the integration of the prototype in a healthcare service. METHODS: This paper deals with the design, the development and implementation of a sensing garment, from the characterization of innovative comfortable and diffuse sensors we used to the methodologies employed to gather information on the posture and movement which derive from the entire garments. Several new algorithms devoted to the signal acquisition, the treatment and posture and gesture reconstruction are introduced and tested. RESULTS: Data obtained by means of the sensing garment are analyzed and compared with the ones recorded using a traditional movement tracking system. CONCLUSION: The main results treated in this work are summarized and remarked. The system was compared with a commercial movement tracking system (a set of electrogoniometers) and it performed the same accuracy in detecting upper limb postures and movements.

  15. Wearable kinesthetic system for capturing and classifying upper limb gesture in post-stroke rehabilitation

    Directory of Open Access Journals (Sweden)

    Tesconi Mario

    2005-03-01

    Full Text Available Abstract Background Monitoring body kinematics has fundamental relevance in several biological and technical disciplines. In particular the possibility to exactly know the posture may furnish a main aid in rehabilitation topics. In the present work an innovative and unobtrusive garment able to detect the posture and the movement of the upper limb has been introduced, with particular care to its application in post stroke rehabilitation field by describing the integration of the prototype in a healthcare service. Methods This paper deals with the design, the development and implementation of a sensing garment, from the characterization of innovative comfortable and diffuse sensors we used to the methodologies employed to gather information on the posture and movement which derive from the entire garments. Several new algorithms devoted to the signal acquisition, the treatment and posture and gesture reconstruction are introduced and tested. Results Data obtained by means of the sensing garment are analyzed and compared with the ones recorded using a traditional movement tracking system. Conclusion The main results treated in this work are summarized and remarked. The system was compared with a commercial movement tracking system (a set of electrogoniometers and it performed the same accuracy in detecting upper limb postures and movements.

  16. LONS: Learning Object Negotiation System

    Science.gov (United States)

    García, Antonio; García, Eva; de-Marcos, Luis; Martínez, José-Javier; Gutiérrez, José-María; Gutiérrez, José-Antonio; Barchino, Roberto; Otón, Salvador; Hilera, José-Ramón

    This system comes up as a result of the increase of e-learning systems. It manages all relevant modules in this context, such as the association of digital rights with the contents (courses), management and payment processing on rights. There are three blocks:

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

    Science.gov (United States)

    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

  18. A new intelligent classifier for breast cancer diagnosis based on a rough set and extreme learning machine: RS + ELM

    OpenAIRE

    KAYA, Yılmaz

    2014-01-01

    Breast cancer is one of the leading causes of death among women all around the world. Therefore, true and early diagnosis of breast cancer is an important problem. The rough set (RS) and extreme learning machine (ELM) methods were used collectively in this study for the diagnosis of breast cancer. The unnecessary attributes were discarded from the dataset by means of the RS approach. The classification process by means of ELM was performed using the remaining attributes. The Wisconsin B...

  19. How to Diagnose and Classify Tattoo Complications in the Clinic: A System of Distinctive Patterns.

    Science.gov (United States)

    Serup, Jørgen

    2017-01-01

    Tattoo complications represent a broad spectrum of clinical entities and disease mechanisms. Infections are known, but chronic inflammatory reactions have hitherto been inconsistently reported and given many interpretations and terms. A clinical classification system of distinct patterns with emphasis on inflammatory tattoo reactions is introduced. Allergic reactions prevalent in red tattoos and often associated with azo pigments are manifested as the 'plaque elevation', 'excessive hyperkeratosis', and 'ulceronecrotic' patterns. The allergen is a hapten. Nonallergic reactions prevalent in black tattoos and associated with carbon black are manifested as the 'papulonodular' pattern. Carbon black nanoparticles agglomerate in the dermis over time forming foreign bodies that elicit reactions. Many black tattoos even develop sarcoid granuloma, and the 'papulonodular' pattern is strongly associated with sarcoidosis affecting other organs. Tattoo complications include a large group of less frequent but nevertheless specific entities, i.e. irritant and toxic local events, photosensitivity, urticaria, eczematous rash due to soluble allergen, neurosensitivity and pain syndrome, lymphopathies, pigment diffusion or fan, scars, and other sequels of tattooing or tattoo removal. Keratoacanthoma occurs in tattoos. Carcinoma and melanoma are rare and occur by coincidence only. Different tattoo complications require different therapeutic approaches, and precise diagnosis is thus important as a key to therapy. The proposed new classification with characteristic patterns relies on simple tools, namely patient history, objective findings, and supplementary punch biopsy. By virtue of simplicity and broad access, these methods make the proposed classification widely applicable in clinics and hospitals. The system is reported to the 11th revision of the WHO diagnosis classification used as international standard. © 2017 S. Karger AG, Basel.

  20. A Robust and Fast Computation Touchless Palm Print Recognition System Using LHEAT and the IFkNCN Classifier

    Directory of Open Access Journals (Sweden)

    Haryati Jaafar

    2015-01-01

    Full Text Available Mobile implementation is a current trend in biometric design. This paper proposes a new approach to palm print recognition, in which smart phones are used to capture palm print images at a distance. A touchless system was developed because of public demand for privacy and sanitation. Robust hand tracking, image enhancement, and fast computation processing algorithms are required for effective touchless and mobile-based recognition. In this project, hand tracking and the region of interest (ROI extraction method were discussed. A sliding neighborhood operation with local histogram equalization, followed by a local adaptive thresholding or LHEAT approach, was proposed in the image enhancement stage to manage low-quality palm print images. To accelerate the recognition process, a new classifier, improved fuzzy-based k nearest centroid neighbor (IFkNCN, was implemented. By removing outliers and reducing the amount of training data, this classifier exhibited faster computation. Our experimental results demonstrate that a touchless palm print system using LHEAT and IFkNCN achieves a promising recognition rate of 98.64%.

  1. Impact of epidural analgesia on cesarean and operative vaginal delivery rates classified by the Ten Groups Classification System.

    Science.gov (United States)

    Lucovnik, M; Blajic, I; Verdenik, I; Mirkovic, T; Stopar Pintaric, T

    2018-05-01

    The Ten Group Classification System (TGCS) allows critical analysis according to the obstetric characteristics of women in labor: singleton or multiple pregnancy, nulliparous, multiparous, or multiparous with a previous cesarean delivery, cephalic, breech presentation or other malpresentation, spontaneous or induced labor, and term or preterm births. Labor outcomes associated with epidural analgesia may be different among the different labor classification groups. The aim of this study was to explore associations between epidural analgesia and cesarean delivery, and epidural analgesia and assisted vaginal delivery, in women classified using the TGCS. Slovenian National Perinatal Information System data for the period 2007-2014 were analyzed. All women after spontaneous onset or induction of labor were classified according to the TGCS, within which cesarean and vaginal assisted delivery rates were investigated (P cesarean delivery rates. Women in group 1 (nulliparous term women with singleton fetuses in cephalic presentation in spontaneous labor) with epidural analgesia had a higher cesarean delivery rate. In most TGCS groups women with epidural analgesia had higher assisted vaginal delivery rates. Epidural analgesia is associated with different effects on cesarean delivery and assisted vaginal delivery rates in different TGCS groups. Copyright © 2018. Published by Elsevier Ltd.

  2. Classifying Natural Waters with the Forel-Ule Colour Index System: Results, Applications, Correlations and Crowdsourcing

    Directory of Open Access Journals (Sweden)

    Shungudzemwoyo P. Garaba

    2015-12-01

    Full Text Available Societal awareness of changes in the environment and climate has grown rapidly, and there is a need to engage citizens in gathering relevant scientific information to monitor environmental changes due to recognition that citizens are a potential source of critical information. The apparent colour of natural waters is one aspect of our aquatic environment that is easy to detect and an essential complementary optical water quality indicator. Here we present the results and explore the utility of the Forel-Ule colour index (FUI scale as a proxy for different properties of natural waters. A FUI scale is used to distinguish the apparent colours of different natural surface water masses. Correlation analysis was completed in an effort to determine the constituents of natural waters related to FUI. Strong correlations with turbidity, Secchi-disk depth, and coloured dissolved organic material suggest the FUI is a good indicator of changes related to other constituents of water. The increase in the number of tools capable of determining the FUI colours, (i ocean colour remote sensing products; (ii a handheld scale; and (iii a mobile device app, make it a versatile relative measure of water quality. It has the potential to provide higher spatial and temporal resolution of data for a modernized classification of optical water quality. This FUI colour system has been favoured by several scientists in the last century because it is affordable and easy to use and provides indicative information about the colour of water and the water constituents producing that colour. It is therefore within the scope of a growing interest in the application and usefulness of basic measurement methodologies with the potential to provide timely benchmark information about the environment to the public, scientists and policymakers.

  3. Classifying Natural Waters with the Forel-Ule Colour Index System: Results, Applications, Correlations and Crowdsourcing.

    Science.gov (United States)

    Garaba, Shungudzemwoyo P; Friedrichs, Anna; Voß, Daniela; Zielinski, Oliver

    2015-12-18

    Societal awareness of changes in the environment and climate has grown rapidly, and there is a need to engage citizens in gathering relevant scientific information to monitor environmental changes due to recognition that citizens are a potential source of critical information. The apparent colour of natural waters is one aspect of our aquatic environment that is easy to detect and an essential complementary optical water quality indicator. Here we present the results and explore the utility of the Forel-Ule colour index (FUI) scale as a proxy for different properties of natural waters. A FUI scale is used to distinguish the apparent colours of different natural surface water masses. Correlation analysis was completed in an effort to determine the constituents of natural waters related to FUI. Strong correlations with turbidity, Secchi-disk depth, and coloured dissolved organic material suggest the FUI is a good indicator of changes related to other constituents of water. The increase in the number of tools capable of determining the FUI colours, (i) ocean colour remote sensing products; (ii) a handheld scale; and (iii) a mobile device app, make it a versatile relative measure of water quality. It has the potential to provide higher spatial and temporal resolution of data for a modernized classification of optical water quality. This FUI colour system has been favoured by several scientists in the last century because it is affordable and easy to use and provides indicative information about the colour of water and the water constituents producing that colour. It is therefore within the scope of a growing interest in the application and usefulness of basic measurement methodologies with the potential to provide timely benchmark information about the environment to the public, scientists and policymakers.

  4. An efficient word typing P300-BCI system using a modified T9 interface and random forest classifier.

    Science.gov (United States)

    Akram, Faraz; Han, Seung Moo; Kim, Tae-Seong

    2015-01-01

    A typical P300-based spelling brain computer interface (BCI) system types a single character with a character presentation paradigm and a P300 classification system. Lately, a few attempts have been made to type a whole word with the help of a smart dictionary that suggests some candidate words with the input of a few initial characters. In this paper, we propose a novel paradigm utilizing initial character typing with word suggestions and a novel P300 classifier to increase word typing speed and accuracy. The novel paradigm involves modifying the Text on 9 keys (T9) interface, which is similar to the keypad of a mobile phone used for text messaging. Users can type the initial characters using a 3×3 matrix interface and an integrated custom-built dictionary that suggests candidate words as the user types the initials. Then the user can select one of the given suggestions to complete word typing. We have adopted a random forest classifier, which significantly improves P300 classification accuracy by combining multiple decision trees. We conducted experiments with 10 subjects using the proposed BCI system. Our proposed paradigms significantly reduced word typing time and made word typing more convenient by outputting complete words with only a few initial character inputs. The conventional spelling system required an average time of 3.47 min per word while typing 10 random words, whereas our proposed system took an average time of 1.67 min per word, a 51.87% improvement, for the same words under the same conditions. Copyright © 2014 Elsevier Ltd. All rights reserved.

  5. Diversity of aging of the immune system classified in the cotton rat (Sigmodon hispidus) model of human infectious diseases.

    Science.gov (United States)

    Guichelaar, Teun; van Erp, Elisabeth A; Hoeboer, Jeroen; Smits, Noortje A M; van Els, Cécile A C M; Pieren, Daan K J; Luytjes, Willem

    2018-05-01

    Susceptibility and declined resistance to human pathogens like respiratory syncytial virus (RSV) at old age is well represented in the cotton rat (Sigmodon hispidus). Despite providing a preferred model of human infectious diseases, little is known about aging of its adaptive immune system. We aimed to define aging-related changes of the immune system of this species. Concomitantly, we asked whether the rate of immunological alterations may be stratified by physiological aberrations encountered during aging. With increasing age, cotton rats showed reduced frequencies of T cells, impaired induction of antibodies to RSV, higher incidence of aberrations of organs and signs of lipemia. Moreover, old animals expressed high biological heterogeneity, but the age-related reduction of T cell frequency was only observed in those specimens that displayed aberrant organs. Thus, cotton rats show age-related alterations of lymphocytes that can be classified by links with health status. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

  6. Social software: E-learning beyond learning management systems

    DEFF Research Database (Denmark)

    Dalsgaard, Christian

    2006-01-01

    The article argues that it is necessary to move e-learning beyond learning management systems and engage students in an active use of the web as a resource for their self-governed, problem-based and collaborative activities. The purpose of the article is to discuss the potential of social software...... to move e-learning beyond learning management systems. An approach to use of social software in support of a social constructivist approach to e-learning is presented, and it is argued that learning management systems do not support a social constructivist approach which emphasizes self-governed learning...... activities of students. The article suggests a limitation of the use of learning management systems to cover only administrative issues. Further, it is argued that students' self-governed learning processes are supported by providing students with personal tools and engaging them in different kinds of social...

  7. LCC: Light Curves Classifier

    Science.gov (United States)

    Vo, Martin

    2017-08-01

    Light Curves Classifier uses data mining and machine learning to obtain and classify desired objects. This task can be accomplished by attributes of light curves or any time series, including shapes, histograms, or variograms, or by other available information about the inspected objects, such as color indices, temperatures, and abundances. After specifying features which describe the objects to be searched, the software trains on a given training sample, and can then be used for unsupervised clustering for visualizing the natural separation of the sample. The package can be also used for automatic tuning parameters of used methods (for example, number of hidden neurons or binning ratio). Trained classifiers can be used for filtering outputs from astronomical databases or data stored locally. The Light Curve Classifier can also be used for simple downloading of light curves and all available information of queried stars. It natively can connect to OgleII, OgleIII, ASAS, CoRoT, Kepler, Catalina and MACHO, and new connectors or descriptors can be implemented. In addition to direct usage of the package and command line UI, the program can be used through a web interface. Users can create jobs for ”training” methods on given objects, querying databases and filtering outputs by trained filters. Preimplemented descriptors, classifier and connectors can be picked by simple clicks and their parameters can be tuned by giving ranges of these values. All combinations are then calculated and the best one is used for creating the filter. Natural separation of the data can be visualized by unsupervised clustering.

  8. A deep learning classifier for prediction of pathological complete response to neoadjuvant chemotherapy from baseline breast DCE-MRI

    Science.gov (United States)

    Ravichandran, Kavya; Braman, Nathaniel; Janowczyk, Andrew; Madabhushi, Anant

    2018-02-01

    Neoadjuvant chemotherapy (NAC) is routinely used to treat breast tumors before surgery to reduce tumor size and improve outcome. However, no current clinical or imaging metrics can effectively predict before treatment which NAC recipients will achieve pathological complete response (pCR), the absence of residual invasive disease in the breast or lymph nodes following surgical resection. In this work, we developed and applied a convolu- tional neural network (CNN) to predict pCR from pre-treatment dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) scans on a per-voxel basis. In this study, DCE-MRI data for a total of 166 breast cancer pa- tients from the ISPY1 Clinical Trial were split into a training set of 133 patients and a testing set of 33 patients. A CNN consisting of 6 convolutional blocks was trained over 30 epochs. The pre-contrast and post-contrast DCE-MRI phases were considered in isolation and conjunction. A CNN utilizing a combination of both pre- and post-contrast images best distinguished responders, with an AUC of 0.77; 82% of the patients in the testing set were correctly classified based on their treatment response. Within the testing set, the CNN was able to produce probability heatmaps that visualized tumor regions that most strongly predicted therapeutic response. Multi- variate analysis with prognostic clinical variables (age, largest diameter, hormone receptor and HER2 status), revealed that the network was an independent predictor of response (p=0.05), and that the inclusion of HER2 status could further improve capability to predict response (AUC = 0.85, accuracy = 85%).

  9. Composite Classifiers for Automatic Target Recognition

    National Research Council Canada - National Science Library

    Wang, Lin-Cheng

    1998-01-01

    ...) using forward-looking infrared (FLIR) imagery. Two existing classifiers, one based on learning vector quantization and the other on modular neural networks, are used as the building blocks for our composite classifiers...

  10. Prediction Models for Licensure Examination Performance using Data Mining Classifiers for Online Test and Decision Support System

    Directory of Open Access Journals (Sweden)

    Ivy M. Tarun

    2017-05-01

    Full Text Available This study focuse d on two main points: the generation of licensure examination performan ce prediction models; and the development of a Decision Support System. In this study, data mining classifiers were used to generate the models using WEKA (Waikato Environment for Knowledge Analysis. These models were integrated into the Decision Support System as default models to support decision making as far as appropriate interventions during review sessions are concerned. The system developed mainly involves the repeated generation of MR models for performance prediction and also provides a Mock Boar d Exam for the reviewees to take. From the models generated, it is established that the General Weighted Average of the reviewees in their General Education subjects, the result of the Mock Board Exam and the instance when the reviewee is conducting a sel f - review are good predictors of the licensure examination performance. Further , it is concluded that the General Weighted Average of the reviewees in their Major or Content courses is the best predictor of licensure examination performance. Based from the evaluation results of the system , the system satisfied its implied functions and is efficient, usable, reliable and portable. Hence, it can already be used not as a substitute to the face - to - face review sessions but to enhance the reviewees’ licensure exa mination review and allow initial identification of those who are likely to have difficulty in passing the licensure examination, therefore providing sufficient time and opportunities for appropriate interventions.

  11. Quantum ensembles of quantum classifiers.

    Science.gov (United States)

    Schuld, Maria; Petruccione, Francesco

    2018-02-09

    Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which - similar to Bayesian learning - the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.

  12. Stack filter classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Porter, Reid B [Los Alamos National Laboratory; Hush, Don [Los Alamos National Laboratory

    2009-01-01

    Just as linear models generalize the sample mean and weighted average, weighted order statistic models generalize the sample median and weighted median. This analogy can be continued informally to generalized additive modeels in the case of the mean, and Stack Filters in the case of the median. Both of these model classes have been extensively studied for signal and image processing but it is surprising to find that for pattern classification, their treatment has been significantly one sided. Generalized additive models are now a major tool in pattern classification and many different learning algorithms have been developed to fit model parameters to finite data. However Stack Filters remain largely confined to signal and image processing and learning algorithms for classification are yet to be seen. This paper is a step towards Stack Filter Classifiers and it shows that the approach is interesting from both a theoretical and a practical perspective.

  13. A web-based non-intrusive ambient system to measure and classify activities of daily living.

    Science.gov (United States)

    Stucki, Reto A; Urwyler, Prabitha; Rampa, Luca; Müri, René; Mosimann, Urs P; Nef, Tobias

    2014-07-21

    The number of older adults in the global population is increasing. This demographic shift leads to an increasing prevalence of age-associated disorders, such as Alzheimer's disease and other types of dementia. With the progression of the disease, the risk for institutional care increases, which contrasts with the desire of most patients to stay in their home environment. Despite doctors' and caregivers' awareness of the patient's cognitive status, they are often uncertain about its consequences on activities of daily living (ADL). To provide effective care, they need to know how patients cope with ADL, in particular, the estimation of risks associated with the cognitive decline. The occurrence, performance, and duration of different ADL are important indicators of functional ability. The patient's ability to cope with these activities is traditionally assessed with questionnaires, which has disadvantages (eg, lack of reliability and sensitivity). Several groups have proposed sensor-based systems to recognize and quantify these activities in the patient's home. Combined with Web technology, these systems can inform caregivers about their patients in real-time (e.g., via smartphone). We hypothesize that a non-intrusive system, which does not use body-mounted sensors, video-based imaging, and microphone recordings would be better suited for use in dementia patients. Since it does not require patient's attention and compliance, such a system might be well accepted by patients. We present a passive, Web-based, non-intrusive, assistive technology system that recognizes and classifies ADL. The components of this novel assistive technology system were wireless sensors distributed in every room of the participant's home and a central computer unit (CCU). The environmental data were acquired for 20 days (per participant) and then stored and processed on the CCU. In consultation with medical experts, eight ADL were classified. In this study, 10 healthy participants (6 women

  14. An Intelligent System for Determining Learning Style

    Science.gov (United States)

    Ozdemir, Ali; Alaybeyoglu, Aysegul; Mulayim, Naciye; Uysal, Muhammed

    2018-01-01

    In this study, an intelligent system which determines learning style of the students is developed to increase success in effective and easy learning. The importance of the proposed software system is to determine convenience degree of the student's learning style. Personal information form and Dunn Learning Style Preference Survey are used to…

  15. Intelligent Garbage Classifier

    Directory of Open Access Journals (Sweden)

    Ignacio Rodríguez Novelle

    2008-12-01

    Full Text Available IGC (Intelligent Garbage Classifier is a system for visual classification and separation of solid waste products. Currently, an important part of the separation effort is based on manual work, from household separation to industrial waste management. Taking advantage of the technologies currently available, a system has been built that can analyze images from a camera and control a robot arm and conveyor belt to automatically separate different kinds of waste.

  16. Learning Management Systems and Comparison of Open Source Learning Management Systems and Proprietary Learning Management Systems

    Directory of Open Access Journals (Sweden)

    Yücel Yılmaz

    2016-04-01

    Full Text Available The concept of learning has been increasingly gaining importance for individuals, businesses and communities in the age of information. On the other hand, developments in information and communication technologies take effect in the field of learning activities. With these technologies, barriers of time and space against the learning activities largely disappear and these technologies make it easier to carry out these activities more effectively. There remain a lot of questions regarding selection of learning management system (LMS to be used for the management of e-learning processes by all organizations conducing educational practices including universities, companies, non-profit organizations, etc. The main questions are as follows: Shall we choose open source LMS or commercial LMS? Can the selected LMS meet existing needs and future potential needs for the organization? What are the possibilities of technical support in the management of LMS? What kind of problems may be experienced in the use of LMS and how can these problems be solved? How much effective can officials in the organization be in the management of LMS? In this study, primarily e-learning and the concept of LMS will be discussed, and in the next section, as for answers to these questions, open source LMSs and centrally developed LMSs will be examined and their advantages and disadvantages relative to each other will be discussed.

  17. A deep-learning classifier identifies patients with clinical heart failure using whole-slide images of H&E tissue.

    Directory of Open Access Journals (Sweden)

    Jeffrey J Nirschl

    Full Text Available Over 26 million people worldwide suffer from heart failure annually. When the cause of heart failure cannot be identified, endomyocardial biopsy (EMB represents the gold-standard for the evaluation of disease. However, manual EMB interpretation has high inter-rater variability. Deep convolutional neural networks (CNNs have been successfully applied to detect cancer, diabetic retinopathy, and dermatologic lesions from images. In this study, we develop a CNN classifier to detect clinical heart failure from H&E stained whole-slide images from a total of 209 patients, 104 patients were used for training and the remaining 105 patients for independent testing. The CNN was able to identify patients with heart failure or severe pathology with a 99% sensitivity and 94% specificity on the test set, outperforming conventional feature-engineering approaches. Importantly, the CNN outperformed two expert pathologists by nearly 20%. Our results suggest that deep learning analytics of EMB can be used to predict cardiac outcome.

  18. A New Profile Learning Model for Recommendation System based on Machine Learning Technique

    Directory of Open Access Journals (Sweden)

    Shereen H. Ali

    2016-03-01

    Full Text Available Recommender systems (RSs have been used to successfully address the information overload problem by providing personalized and targeted recommendations to the end users. RSs are software tools and techniques providing suggestions for items to be of use to a user, hence, they typically apply techniques and methodologies from Data Mining. The main contribution of this paper is to introduce a new user profile learning model to promote the recommendation accuracy of vertical recommendation systems. The proposed profile learning model employs the vertical classifier that has been used in multi classification module of the Intelligent Adaptive Vertical Recommendation (IAVR system to discover the user’s area of interest, and then build the user’s profile accordingly. Experimental results have proven the effectiveness of the proposed profile learning model, which accordingly will promote the recommendation accuracy.

  19. VIRTUAL LABORATORY IN DISTANCE LEARNING SYSTEM

    Directory of Open Access Journals (Sweden)

    Е. Kozlovsky

    2011-11-01

    Full Text Available Questions of designing and a choice of technologies of creation of virtual laboratory for the distance learning system are considered. Distance learning system «Kherson Virtual University» is used as illustration.

  20. THEORETICAL AND EXPERIMENTAL INVESTIGATION OF THE MAGNETOELECTRIC SYSTEM, WHICH RECOGNIZES THE LARGE OF SUNS OF A SINGLE-SPIRAL CLASSIFIER

    Directory of Open Access Journals (Sweden)

    A. N. Matsui

    2018-02-01

    Full Text Available Purpose. The aim of the work is to create a magnetoelectric system with permanent magnets, which perceives the coarse size of the sand of a single-helix classifier, by establishing the connection of the output signal with the measured quantity, eliminating the effect of disturbances on the result and justifying its parameters. Methodology. The studies carried out on the basis of the use of methods of the theory of electrical engineering, magnetic systems with permanent magnets, galvanomagnetic transducers, probabilities, random processes, statistics, regression analysis, sensitivity, differential calculus, rock magnetism, determination of the physical properties of matrix material when impurities are added to it with others explicitly expressed properties, the classification of enrichment products. Findings. The process of the rate of change of the volume of solid in a controlled volume of space through which the sand material moves is described mathematically. The limits of the volume of the controlled volume at which the sensitivity is still sufficient are determined. The theoretical dependences of the rate of change of the solid volume in the controlled volume on the size of the sands at different speeds are obtained. It is established that the state of the controlled volume is best estimated by the magnetic method. A magnetoelectric system with permanent magnets has been developed, which has optimal parameter values and an induction winding containing up to 25,000 turns, and in one of the pole pieces of which a Hall transducer is installed in a continuous slot. The magnetic system near the air gap creates in the material a magnetic field 5 × 20 × 60 mm in size with almost the same intensity. Ed. The magnetoelectric system practically changes linearly with the increase in the size of the material. It depends on the content of magnetic iron in the solid, which is compensated by the use of the signal from the Hall converter. Correlation

  1. Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer's Disease Spectrum: Development of the Classifier and Longitudinal Evaluation.

    Science.gov (United States)

    Lee, Jin San; Kim, Changsoo; Shin, Jeong-Hyeon; Cho, Hanna; Shin, Dae-Seock; Kim, Nakyoung; Kim, Hee Jin; Kim, Yeshin; Lockhart, Samuel N; Na, Duk L; Seo, Sang Won; Seong, Joon-Kyung

    2018-03-07

    To develop a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject's cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

  2. Technological learning in bioenergy systems

    International Nuclear Information System (INIS)

    Junginger, Martin; Visser, Erika de; Hjort-Gregersen, Kurt; Koornneef, Joris; Raven, Rob; Faaij, Andre; Turkenburg, Wim

    2006-01-01

    The main goal of this article is to determine whether cost reductions in different bioenergy systems can be quantified using the experience curve approach, and how specific issues (arising from the complexity of biomass energy systems) can be addressed. This is pursued by case studies on biofuelled combined heat and power (CHP) plants in Sweden, global development of fluidized bed boilers and Danish biogas plants. As secondary goal, the aim is to identify learning mechanisms behind technology development and cost reduction for the biomass energy systems investigated. The case studies reveal large difficulties to devise empirical experience curves for investment costs of biomass-fuelled power plants. To some extent, this is due to lack of (detailed) data. The main reason, however, are varying plant costs due to differences in scale, fuel type, plant layout, region etc. For fluidized bed boiler plants built on a global level, progress ratios (PRs) for the price of entire plants lies approximately between 90-93% (which is typical for large plant-like technologies). The costs for the boiler section alone was found to decline much faster. The experience curve approach delivers better results, when the production costs of the final energy carrier are analyzed. Electricity from biofuelled CHP-plants yields PRs of 91-92%, i.e. an 8-9% reduction of electricity production costs with each cumulative doubling of electricity production. The experience curve for biogas production displays a PR of 85% from 1984 to the beginning of 1990, and then levels to approximately 100% until 2002. For technologies developed on a local level (e.g. biogas plants), learning-by-using and learning-by-interacting are important learning mechanism, while for CHP plants utilizing fluidized bed boilers, upscaling is probably one of the main mechanisms behind cost reductions

  3. Applying Rock Engineering Systems (RES approach to Evaluate and Classify the Coal Spontaneous Combustion Potential in Eastern Alborz Coal Mines

    Directory of Open Access Journals (Sweden)

    Amir Saffari

    2013-12-01

    Full Text Available Subject analysis of the potential of spontaneous combustion in coal layers with analytical and numerical methods has been always considered as a difficult task because of the complexity of the coal behavior and the number of factors influencing it. Empirical methods, due to accounting for certain and specific factors, have not accuracy and efficiency for all positions. The Rock Engineering Systems (RES approach as a systematic method for analyzing and classifying is proposed in engineering projects. The present study is concerned with employing the RES approach to categorize coal spontaneous combustion in coal regions. Using this approach, the interaction of parameters affecting each other in an equal scale on the coal spontaneous combustion was evaluated. The Intrinsic, geological and mining characteristics of coal seams were studied in order to identifying important parameters. Then, the main stages of implementation of the RES method i.e. interaction matrix formation, coding matrix and forming a list category were performed. Later, an index of Coal Spontaneous Combustion Potential (CSCPi was determined to format the mathematical equation. Then, the obtained data related to the intrinsic, geological and mining, and special index were calculated for each layer in the case study (Pashkalat coal region, Iran. So, the study offers a perfect and comprehensive classification of the layers. Finally, by using the event of spontaneous combustion occurred in Pashkalat coal region, an initial validation for this systematic approach in the study area was conducted, which suggested relatively good concordance in Pashkalat coal region.

  4. Learning Management Systems on Blended Learning Courses

    DEFF Research Database (Denmark)

    Kuran, Mehmet Şükrü; Pedersen, Jens Myrup; Elsner, Raphael

    2017-01-01

    LMSes, Moodle, Blackboard Learn, Canvas, and Stud.IP with respect to these. We explain how these features were utilized to increase the efficiency, tractability, and quality of experience of the course. We found that an LMS with advanced features such as progress tracking, modular course support...

  5. E-Learning Systems, Environments and Approaches

    OpenAIRE

    Isaias, P.; Spector, J.M.; Ifenthaler, D.; Sampson, D.G.

    2015-01-01

    The volume consists of twenty-five chapters selected from among peer-reviewed papers presented at the CELDA (Cognition and Exploratory Learning in the Digital Age) 2013 Conference held in Fort Worth, Texas, USA, in October 2013 and also from world class scholars in e-learning systems, environments and approaches. The following sub-topics are included: Exploratory Learning Technologies (Part I), e-Learning social web design (Part II), Learner communities through e-Learning implementations (Par...

  6. Localized thin-section CT with radiomics feature extraction and machine learning to classify early-detected pulmonary nodules from lung cancer screening

    Science.gov (United States)

    Tu, Shu-Ju; Wang, Chih-Wei; Pan, Kuang-Tse; Wu, Yi-Cheng; Wu, Chen-Te

    2018-03-01

    Lung cancer screening aims to detect small pulmonary nodules and decrease the mortality rate of those affected. However, studies from large-scale clinical trials of lung cancer screening have shown that the false-positive rate is high and positive predictive value is low. To address these problems, a technical approach is greatly needed for accurate malignancy differentiation among these early-detected nodules. We studied the clinical feasibility of an additional protocol of localized thin-section CT for further assessment on recalled patients from lung cancer screening tests. Our approach of localized thin-section CT was integrated with radiomics features extraction and machine learning classification which was supervised by pathological diagnosis. Localized thin-section CT images of 122 nodules were retrospectively reviewed and 374 radiomics features were extracted. In this study, 48 nodules were benign and 74 malignant. There were nine patients with multiple nodules and four with synchronous multiple malignant nodules. Different machine learning classifiers with a stratified ten-fold cross-validation were used and repeated 100 times to evaluate classification accuracy. Of the image features extracted from the thin-section CT images, 238 (64%) were useful in differentiating between benign and malignant nodules. These useful features include CT density (p  =  0.002 518), sigma (p  =  0.002 781), uniformity (p  =  0.032 41), and entropy (p  =  0.006 685). The highest classification accuracy was 79% by the logistic classifier. The performance metrics of this logistic classification model was 0.80 for the positive predictive value, 0.36 for the false-positive rate, and 0.80 for the area under the receiver operating characteristic curve. Our approach of direct risk classification supervised by the pathological diagnosis with localized thin-section CT and radiomics feature extraction may support clinical physicians in determining

  7. Accurate Traffic Flow Prediction in Heterogeneous Vehicular Networks in an Intelligent Transport System Using a Supervised Non-Parametric Classifier

    Directory of Open Access Journals (Sweden)

    Hesham El-Sayed

    2018-05-01

    Full Text Available Heterogeneous vehicular networks (HETVNETs evolve from vehicular ad hoc networks (VANETs, which allow vehicles to always be connected so as to obtain safety services within intelligent transportation systems (ITSs. The services and data provided by HETVNETs should be neither interrupted nor delayed. Therefore, Quality of Service (QoS improvement of HETVNETs is one of the topics attracting the attention of researchers and the manufacturing community. Several methodologies and frameworks have been devised by researchers to address QoS-prediction service issues. In this paper, to improve QoS, we evaluate various traffic characteristics of HETVNETs and propose a new supervised learning model to capture knowledge on all possible traffic patterns. This model is a refinement of support vector machine (SVM kernels with a radial basis function (RBF. The proposed model produces better results than SVMs, and outperforms other prediction methods used in a traffic context, as it has lower computational complexity and higher prediction accuracy.

  8. Fingerprint prediction using classifier ensembles

    CSIR Research Space (South Africa)

    Molale, P

    2011-11-01

    Full Text Available ); logistic discrimination (LgD), k-nearest neighbour (k-NN), artificial neural network (ANN), association rules (AR) decision tree (DT), naive Bayes classifier (NBC) and the support vector machine (SVM). The performance of several multiple classifier systems...

  9. IMPROVING CAUSE DETECTION SYSTEMS WITH ACTIVE LEARNING

    Data.gov (United States)

    National Aeronautics and Space Administration — IMPROVING CAUSE DETECTION SYSTEMS WITH ACTIVE LEARNING ISAAC PERSING AND VINCENT NG Abstract. Active learning has been successfully applied to many natural language...

  10. Acceptability and characteristics of 124 human bioequivalence studies with active substances classified according to the Biopharmaceutic Classification System

    Science.gov (United States)

    Ramirez, Elena; Laosa, Olga; Guerra, Pedro; Duque, Blanca; Mosquera, Beatriz; Borobia, Alberto M; Lei, Suhua H; Carcas, Antonio J; Frias, Jesus

    2010-01-01

    AIM The aim of this study was to evaluate the acceptability of 124 bioequivalence (BE) studies with 80 active substances categorized according to the Biopharmaceutics Classification System (BCS) in order to establish if there were different probabilities of proving BE between the different BCS classes. METHODS We evaluated the differences between pharmaceutical products with active substances from different BCS classes in terms of acceptability, number of subjects in the study (n), the point estimates, and intra- and inter-subject coefficients of variation data from BE studies with generic products. RESULTS Out of 124 BE studies 89 (71.77%) were performed with pharmaceutical products containing active substances classified by the BCS. In all BCS classes there were non-bioequivalent pharmaceutical products: 4 out of 26 (15.38%) in class 1, 14 out of 28 (50%) in class 2, 3 out of 22 (13.63%) in class 3 and 1 out of 13 (7.69%) in class 4. When we removed those pharmaceutical products in which intra-subject variability was higher than predicted (2 in class 1 active substances, 9 in class 2 and 2 in class 3) there were still non-BE pharmaceutical products in classes 1, 2 and 3. CONCLUSIONS Comparisons between pharmaceutical products with active substances from the four BCS classes have not allowed us to define differential characteristics of each class in terms of n, inter and intra-subject variability for Cmax or AUC. Despite the usually employed test dissolution methodology proposed as quality control, pharmaceutical products with active substances from the four classes of BCS showed non-BE studies. PMID:21039763

  11. Critical Points in Distance Learning System

    Directory of Open Access Journals (Sweden)

    Airina Savickaitė

    2013-08-01

    Full Text Available Purpose – This article presents the results of distance learning system analysis, i.e. the critical elements of the distance learning system. The critical points of distance learning are a part of distance education online environment interactivity/community process model. The most important is the fact that the critical point is associated with distance learning participants. Design/methodology/approach – Comparative review of articles and analysis of distance learning module. Findings – A modern man is a lifelong learner and distance learning is a way to be a modern person. The focus on a learner and feedback is the most important thing of learning distance system. Also, attention should be paid to the lecture-appropriate knowledge and ability to convey information. Distance system adaptation is the way to improve the learner’s learning outcomes. Research limitations/implications – Different learning disciplines and learning methods may have different critical points. Practical implications – The information of analysis could be important for both lecturers and students, who studies distance education systems. There are familiar critical points which may deteriorate the quality of learning. Originality/value – The study sought to develop remote systems for applications in order to improve the quality of knowledge. Keywords: distance learning, process model, critical points. Research type: review of literature and general overview.

  12. Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network.

    Science.gov (United States)

    Guo, Hao; Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

    2017-01-01

    High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

  13. Classifying objects in LWIR imagery via CNNs

    Science.gov (United States)

    Rodger, Iain; Connor, Barry; Robertson, Neil M.

    2016-10-01

    The aim of the presented work is to demonstrate enhanced target recognition and improved false alarm rates for a mid to long range detection system, utilising a Long Wave Infrared (LWIR) sensor. By exploiting high quality thermal image data and recent techniques in machine learning, the system can provide automatic target recognition capabilities. A Convolutional Neural Network (CNN) is trained and the classifier achieves an overall accuracy of > 95% for 6 object classes related to land defence. While the highly accurate CNN struggles to recognise long range target classes, due to low signal quality, robust target discrimination is achieved for challenging candidates. The overall performance of the methodology presented is assessed using human ground truth information, generating classifier evaluation metrics for thermal image sequences.

  14. A review and experimental study on the application of classifiers and evolutionary algorithms in EEG-based brain-machine interface systems

    Science.gov (United States)

    Tahernezhad-Javazm, Farajollah; Azimirad, Vahid; Shoaran, Maryam

    2018-04-01

    Objective. Considering the importance and the near-future development of noninvasive brain-machine interface (BMI) systems, this paper presents a comprehensive theoretical-experimental survey on the classification and evolutionary methods for BMI-based systems in which EEG signals are used. Approach. The paper is divided into two main parts. In the first part, a wide range of different types of the base and combinatorial classifiers including boosting and bagging classifiers and evolutionary algorithms are reviewed and investigated. In the second part, these classifiers and evolutionary algorithms are assessed and compared based on two types of relatively widely used BMI systems, sensory motor rhythm-BMI and event-related potentials-BMI. Moreover, in the second part, some of the improved evolutionary algorithms as well as bi-objective algorithms are experimentally assessed and compared. Main results. In this study two databases are used, and cross-validation accuracy (CVA) and stability to data volume (SDV) are considered as the evaluation criteria for the classifiers. According to the experimental results on both databases, regarding the base classifiers, linear discriminant analysis and support vector machines with respect to CVA evaluation metric, and naive Bayes with respect to SDV demonstrated the best performances. Among the combinatorial classifiers, four classifiers, Bagg-DT (bagging decision tree), LogitBoost, and GentleBoost with respect to CVA, and Bagging-LR (bagging logistic regression) and AdaBoost (adaptive boosting) with respect to SDV had the best performances. Finally, regarding the evolutionary algorithms, single-objective invasive weed optimization (IWO) and bi-objective nondominated sorting IWO algorithms demonstrated the best performances. Significance. We present a general survey on the base and the combinatorial classification methods for EEG signals (sensory motor rhythm and event-related potentials) as well as their optimization methods

  15. Authoring Systems Delivering Reusable Learning Objects

    Directory of Open Access Journals (Sweden)

    George Nicola Sammour

    2009-10-01

    Full Text Available A three layer e-learning course development model has been defined based on a conceptual model of learning content object. It starts by decomposing the learning content into small chunks which are initially placed in a hierarchic structure of units and blocks. The raw content components, being the atomic learning objects (ALO, were linked to the blocks and are structured in the database. We set forward a dynamic generation of LO's using re-usable e-learning raw materials or ALO’s In that view we need a LO authoring/ assembling system fitting the requirements of interoperability and reusability and starting from selecting the raw learning content from the learning materials content database. In practice authoring systems are used to develop e-learning courses. The company EDUWEST has developed an authoring system that is database based and will be SCORM compliant in the near future.

  16. Establishment of a Learning Management System

    International Nuclear Information System (INIS)

    Han, K. W.; Kim, Y. T.; Lee, E. J.; Min, B. J.

    2006-01-01

    A web-based learning management system (LMS) has been established to address the need of customized education and training of Nuclear Training Center (NTC) of KAERI. The LMS is designed to deal with various learning types (e.g. on-line, off-line and blended) and a practically comprehensive learning activity cycle (e.g. course preparation, registration, learning, and postlearning) as well as to be user-friendly. A test with an example course scenario on the established system has shown its satisfactory performance. This paper discusses details of the established webbased learning management system in terms of development approach and functions of the LMS

  17. Repetitive learning control of continuous chaotic systems

    International Nuclear Information System (INIS)

    Chen Maoyin; Shang Yun; Zhou Donghua

    2004-01-01

    Combining a shift method and the repetitive learning strategy, a repetitive learning controller is proposed to stabilize unstable periodic orbits (UPOs) within chaotic attractors in the sense of least mean square. If nonlinear parts in chaotic systems satisfy Lipschitz condition, the proposed controller can be simplified into a simple proportional repetitive learning controller

  18. Expert Students in Social Learning Management Systems

    Science.gov (United States)

    Avogadro, Paolo; Calegari, Silvia; Dominoni, Matteo Alessandro

    2016-01-01

    Purpose: A social learning management system (social LMS) is a tool which favors social interactions and allows scholastic institutions to supervise and guide the learning process. The inclusion of the social feature to a "normal" LMS leads to the creation of educational social networks (EduSN), where the students interact and learn. The…

  19. Modeling student's learning styles in web 2.0 learning systems

    Directory of Open Access Journals (Sweden)

    Ramon Cabada Zatarain Cabada, M. L. Barron Estrada, L. Zepeda Sanchez, Guillermo Sandoval, J.M. Osorio Velazquez, J.E. Urias Barrientos

    2009-12-01

    Full Text Available The identification of the best learning style in an Intelligent Tutoring System must be considered essential as part of thesuccess in the teaching process. In many implementations of automatic classifiers finding the right student learning styler e p r e s e n t s t h e h a r d e s t a s s i g n m e n t . T h e r e a s o n i s t h a t m o s t o f t h e t e c h n i q u e s w o r k u s i n g e x p e r t g r o u p s o r a s e t o fquestionnaires which define how the learning styles are assigned to students. This paper presents a novel approach forautomatic learning styles classification using a Kohonen network. The approach is used by an author tool for buildingIntelligent Tutoring Systems running under a Web 2.0 collaborative learning platform. The tutoring systems together withthe neural network can also be exported to mobile devices. We present different results to the approach working under theauthor tool.

  20. Linear System Control Using Stochastic Learning Automata

    Science.gov (United States)

    Ziyad, Nigel; Cox, E. Lucien; Chouikha, Mohamed F.

    1998-01-01

    This paper explains the use of a Stochastic Learning Automata (SLA) to control switching between three systems to produce the desired output response. The SLA learns the optimal choice of the damping ratio for each system to achieve a desired result. We show that the SLA can learn these states for the control of an unknown system with the proper choice of the error criteria. The results of using a single automaton are compared to using multiple automata.

  1. Micro Learning: A Modernized Education System

    Directory of Open Access Journals (Sweden)

    Omer Jomah

    2016-03-01

    Full Text Available Learning is an understanding of how the human brain is wired to learning rather than to an approach or a system. It is one of the best and most frequent approaches for the 21st century learners. Micro learning is more interesting due to its way of teaching and learning the content in a small, very specific burst. Here the learners decide what and when to learn. Content, time, curriculum, form, process, mediality, and learning type are the dimensions of micro learning. Our paper will discuss about micro learning and about the micro-content management system. The study will reflect the views of different users, and will analyze the collected data. Finally, it will be concluded with its pros and cons. 

  2. ENGINEERING OF UNIVERSITY INTELLIGENT LEARNING SYSTEMS

    Directory of Open Access Journals (Sweden)

    Vasiliy M. Trembach

    2016-01-01

    Full Text Available In the article issues of engineering intelligent tutoring systems of University with adaptation are considered. The article also dwells on some modern approaches to engineering of information systems. It shows the role of engineering e-learning devices (systems in system engineering. The article describes the basic principles of system engineering and these principles are expanded regarding to intelligent information systems. The structure of intelligent learning systems with adaptation of the individual learning environments based on services is represented in the article.

  3. Learning and the Instructional System

    Science.gov (United States)

    Kozma, Robert B.

    1977-01-01

    Faculty members can use information about six components of the learning situation to increase student learning. The nature, function, and interrelationships of the following elements are described: instructor, content, medium, student, evaluation, environment, and implementation. (Editor/LBH)

  4. THE RESTRICTED SURGICAL RELEVANCE OF MORPHOLOGIC CRITERIA TO CLASSIFY SYSTEMIC-PULMONARY COLLATERAL ARTERIES IN PULMONARY ATRESIA WITH VENTRICULAR SEPTAL-DEFECT

    NARCIS (Netherlands)

    DERUITER, MC; GITTENBERGERDEGROOT, AC; BOGERS, AJJC; ELZENGA, NJ

    1994-01-01

    Now that systemic-pulmonary collateral arteries are used for unifocalization in patients with pulmonary atresia and ventricular septal defect, the question arises whether morphologic criteria of these collateral arteries could help to provide better results. In an attempt to classify the morphologic

  5. Classifying Sluice Occurrences in Dialogue

    DEFF Research Database (Denmark)

    Baird, Austin; Hamza, Anissa; Hardt, Daniel

    2018-01-01

    perform manual annotation with acceptable inter-coder agreement. We build classifier models with Decision Trees and Naive Bayes, with accuracy of 67%. We deploy a classifier to automatically classify sluice occurrences in OpenSubtitles, resulting in a corpus with 1.7 million occurrences. This will support....... Despite this, the corpus can be of great use in research on sluicing and development of systems, and we are making the corpus freely available on request. Furthermore, we are in the process of improving the accuracy of sluice identification and annotation for the purpose of created a subsequent version...

  6. Recommender Systems in Technology Enhanced Learning

    NARCIS (Netherlands)

    Manouselis, Nikos; Drachsler, Hendrik; Verbert, Katrien; Santos, Olga

    2010-01-01

    Manouselis, N., Drachsler, H., Verbert, K., & Santos, C. S. (Eds.) (2010). Recommender System in Technology Enhanced Learning. Elsevier Procedia Computer Science: Volume 1, Issue 2. Proceedings of the 1st Workshop on Recommender Systems for Technology Enhanced Learning (RecSysTEL). September, 29-30,

  7. Panorama of Recommender Systems to Support Learning

    NARCIS (Netherlands)

    Drachsler, Hendrik; Verbert, Katrien; Santos, Olga C.; Manouselis, Nikos

    2015-01-01

    This chapter presents an analysis of recommender systems in TechnologyEnhanced Learning along their 15 years existence (2000-2014). All recommender systems considered for the review aim to support educational stakeholders by personalising the learning process. In this meta-review 82 recommender

  8. Reconceptualizing Learning as a Dynamical System.

    Science.gov (United States)

    Ennis, Catherine D.

    1992-01-01

    Dynamical systems theory can increase our understanding of the constantly evolving learning process. Current research using experimental and interpretive paradigms focuses on describing the attractors and constraints stabilizing the educational process. Dynamical systems theory focuses attention on critical junctures in the learning process as…

  9. Divulging Personal Information within Learning Analytics Systems

    Science.gov (United States)

    Ifenthaler, Dirk; Schumacher, Clara

    2015-01-01

    The purpose of this study was to investigate if students are prepared to release any personal data in order to inform learning analytics systems. Besides the well-documented benefits of learning analytics, serious concerns and challenges are associated with the application of these data driven systems. Most notably, empirical evidence regarding…

  10. Online reinforcement learning control for aerospace systems

    NARCIS (Netherlands)

    Zhou, Y.

    2018-01-01

    Reinforcement Learning (RL) methods are relatively new in the field of aerospace guidance, navigation, and control. This dissertation aims to exploit RL methods to improve the autonomy and online learning of aerospace systems with respect to the a priori unknown system and environment, dynamical

  11. Adaptive e-learning system using ontology

    OpenAIRE

    Yarandi, Maryam; Tawil, Abdel-Rahman; Jahankhani, Hossein

    2011-01-01

    This paper proposes an innovative ontological approach to design a personalised e-learning system which creates a tailored workflow for individual learner. Moreover, the learning content and sequencing logic is separated into content model and pedagogical model to increase the reusability and flexibility of the system.

  12. Recommender Systems in Technology Enhanced Learning

    NARCIS (Netherlands)

    Manouselis, Nikos; Drachsler, Hendrik; Vuorikari, Riina; Hummel, Hans; Koper, Rob

    2010-01-01

    Manouselis, N., Drachsler, H., Vuorikari, R., Hummel, H. G. K., & Koper, R. (2011). Recommender Systems in Technology Enhanced Learning. In P. B. Kantor, F. Ricci, L. Rokach, & B. Shapira (Eds.), Recommender Systems Handbook (pp. 387-415). Berlin: Springer.

  13. Learning Management Systems and E-Learning within Cyprus Universities

    Directory of Open Access Journals (Sweden)

    Amirkhanpour, Monaliz

    2011-01-01

    Full Text Available This paper presents an extensive research study and results on the use of existing open-source Learning Management Systems, or LMS within the public and private universities of Cyprus. The most significant objective of this research is the identification of the different types of E-Learning, i.e. Computer-Based Training (CBT, Technology-Based Learning (TBL, and Web-Based Training (WBT within Cyprus universities. The paper identifies the benefits and limitations of the main learning approaches used in higher educational institutions, i.e. synchronous and asynchronous learning, investigates the open-source LMS used in the Cypriot universities and compares their features with regards to students’ preferences for a collaborative E-Learning environment. The required data for this research study were collected from undergraduate and graduate students, alumni, faculty members, and IT professionals who currently work and/or study at the public and private universities of Cyprus. The most noteworthy recommendation of this study is the clear indication that most of the undergraduate students that extensively use the specific E-Learning platform of their university do not have a clear picture of the differences between an LMS and a VLE. This gap has to be gradually diminished in order to make optimum use of the different features offered by the specific E-Learning platform.

  14. Web-Based Learning Support System

    Science.gov (United States)

    Fan, Lisa

    Web-based learning support system offers many benefits over traditional learning environments and has become very popular. The Web is a powerful environment for distributing information and delivering knowledge to an increasingly wide and diverse audience. Typical Web-based learning environments, such as Web-CT, Blackboard, include course content delivery tools, quiz modules, grade reporting systems, assignment submission components, etc. They are powerful integrated learning management systems (LMS) that support a number of activities performed by teachers and students during the learning process [1]. However, students who study a course on the Internet tend to be more heterogeneously distributed than those found in a traditional classroom situation. In order to achieve optimal efficiency in a learning process, an individual learner needs his or her own personalized assistance. For a web-based open and dynamic learning environment, personalized support for learners becomes more important. This chapter demonstrates how to realize personalized learning support in dynamic and heterogeneous learning environments by utilizing Adaptive Web technologies. It focuses on course personalization in terms of contents and teaching materials that is according to each student's needs and capabilities. An example of using Rough Set to analyze student personal information to assist students with effective learning and predict student performance is presented.

  15. Hybrid Neuro-Fuzzy Classifier Based On Nefclass Model

    Directory of Open Access Journals (Sweden)

    Bogdan Gliwa

    2011-01-01

    Full Text Available The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which wasmodified. The presented classifier was compared to popular classifiers – neural networks andk-nearest neighbours. Efficiency of modifications in classifier was compared with methodsused in original model NEFCLASS (learning methods. Accuracy of classifier was testedusing 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wisconsin.Moreover, influence of ensemble classification methods on classification accuracy waspresented.

  16. Learning Markov models for stationary system behaviors

    DEFF Research Database (Denmark)

    Chen, Yingke; Mao, Hua; Jaeger, Manfred

    2012-01-01

    to a single long observation sequence, and in these situations existing automatic learning methods cannot be applied. In this paper, we adapt algorithms for learning variable order Markov chains from a single observation sequence of a target system, so that stationary system properties can be verified using......Establishing an accurate model for formal verification of an existing hardware or software system is often a manual process that is both time consuming and resource demanding. In order to ease the model construction phase, methods have recently been proposed for automatically learning accurate...... the learned model. Experiments demonstrate that system properties (formulated as stationary probabilities of LTL formulas) can be reliably identified using the learned model....

  17. Solution to Detect, Classify, and Report Illicit Online Marketing and Sales of Controlled Substances via Twitter: Using Machine Learning and Web Forensics to Combat Digital Opioid Access

    Science.gov (United States)

    Klugman, Josh; Kuzmenko, Ella; Gupta, Rashmi

    2018-01-01

    Background On December 6 and 7, 2017, the US Department of Health and Human Services (HHS) hosted its first Code-a-Thon event aimed at leveraging technology and data-driven solutions to help combat the opioid epidemic. The authors—an interdisciplinary team from academia, the private sector, and the US Centers for Disease Control and Prevention—participated in the Code-a-Thon as part of the prevention track. Objective The aim of this study was to develop and deploy a methodology using machine learning to accurately detect the marketing and sale of opioids by illicit online sellers via Twitter as part of participation at the HHS Opioid Code-a-Thon event. Methods Tweets were collected from the Twitter public application programming interface stream filtered for common prescription opioid keywords in conjunction with participation in the Code-a-Thon from November 15, 2017 to December 5, 2017. An unsupervised machine learning–based approach was developed and used during the Code-a-Thon competition (24 hours) to obtain a summary of the content of the tweets to isolate those clusters associated with illegal online marketing and sale using a biterm topic model (BTM). After isolating relevant tweets, hyperlinks associated with these tweets were reviewed to assess the characteristics of illegal online sellers. Results We collected and analyzed 213,041 tweets over the course of the Code-a-Thon containing keywords codeine, percocet, vicodin, oxycontin, oxycodone, fentanyl, and hydrocodone. Using BTM, 0.32% (692/213,041) tweets were identified as being associated with illegal online marketing and sale of prescription opioids. After removing duplicates and dead links, we identified 34 unique “live” tweets, with 44% (15/34) directing consumers to illicit online pharmacies, 32% (11/34) linked to individual drug sellers, and 21% (7/34) used by marketing affiliates. In addition to offering the “no prescription” sale of opioids, many of these vendors also sold other

  18. Intelligent and Adaptive Educational-Learning Systems Achievements and Trends

    CERN Document Server

    2013-01-01

    The Smart Innovation, Systems and Technologies book series encompasses the topics of knowledge, intelligence, innovation and sustainability. The aim of the series is to make available a platform for the publication of books on all aspects of single and multi-disciplinary research on these themes in order to make the latest results available in a readily-accessible form.  This book is devoted to the “Intelligent and Adaptive Educational-Learning Systems”. It privileges works that highlight key achievements and outline trends to inspire future research.  After a rigorous revision process twenty manuscripts were accepted and organized into four parts as follows: ·     Modeling: The first part embraces five chapters oriented to: 1) shape the affective behavior; 2) depict the adaptive learning curriculum; 3) predict learning achievements; 4) mine learner models to outcome optimized and adaptive e-learning objects; 5) classify learning preferences of learners. ·     Content: The second part encompas...

  19. Hybrid classifiers methods of data, knowledge, and classifier combination

    CERN Document Server

    Wozniak, Michal

    2014-01-01

    This book delivers a definite and compact knowledge on how hybridization can help improving the quality of computer classification systems. In order to make readers clearly realize the knowledge of hybridization, this book primarily focuses on introducing the different levels of hybridization and illuminating what problems we will face with as dealing with such projects. In the first instance the data and knowledge incorporated in hybridization were the action points, and then a still growing up area of classifier systems known as combined classifiers was considered. This book comprises the aforementioned state-of-the-art topics and the latest research results of the author and his team from Department of Systems and Computer Networks, Wroclaw University of Technology, including as classifier based on feature space splitting, one-class classification, imbalance data, and data stream classification.

  20. Hierarchical mixtures of naive Bayes classifiers

    NARCIS (Netherlands)

    Wiering, M.A.

    2002-01-01

    Naive Bayes classifiers tend to perform very well on a large number of problem domains, although their representation power is quite limited compared to more sophisticated machine learning algorithms. In this pa- per we study combining multiple naive Bayes classifiers by using the hierar- chical

  1. Feature extraction for dynamic integration of classifiers

    NARCIS (Netherlands)

    Pechenizkiy, M.; Tsymbal, A.; Puuronen, S.; Patterson, D.W.

    2007-01-01

    Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. In this paper, we present an algorithm for the dynamic integration of classifiers in the space of extracted features (FEDIC). It is based on the technique

  2. Neural network classifier of attacks in IP telephony

    Science.gov (United States)

    Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin

    2014-05-01

    Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.

  3. Protecting New Zealand children from exposure to the marketing of unhealthy foods and drinks: a comparison of three nutrient profiling systems to classify foods.

    Science.gov (United States)

    Mhurchu, Cliona Ni; Mackenzie, Tara; Vandevijvere, Stefanie

    2016-09-09

    Promotion of unhealthy foods and drinks is a significant, modifiable risk factor for child obesity and diet-related non-communicable diseases. We compared three accepted nutrient profiling systems: the Health Star Rating (HSR), the Ministry of Health Food and Beverage Classification System (FBCS) and the World Health Organization (WHO) Regional Office for Europe Nutrient Profiling Model, to identify the best system to protect New Zealand children from exposure to the marketing of unhealthy foods and beverages. 13,066 packaged foods from the 2014 New Zealand Nutritrack database were classified as 'restricted' or 'not restricted' as per the WHO model; 'everyday/sometimes' or 'occasional' as per the FBCS model; and 'foods that met the criteria for all three systems or none of the systems, and the types of food products classified as 'restricted' under the WHO model but classified as 'everyday/sometimes' (FBCS model) or as having >3.5 stars, were determined. Under any of the three nutrient profiling systems, approximately one-third (29-39%) of New Zealand packaged foods would be permitted to be marketed to children. The WHO Model would permit marketing of 29% of products; the HSR system would permit 36%; and the FBCS system would permit 39%. The WHO Model restricts marketing of unhealthy foods more effectively than the other two systems. The HSR and FBCS systems would permit marketing of a number of food products of concern, particularly high-sugar breakfast cereals, fruit juices and ready meals. The WHO Regional Office for Europe Nutrient Profiling Model should underpin the Advertising Standards Authority revised Children's Code for Advertising Food. The effectiveness of the new Code in reducing New Zealand children's exposure to marketing of unhealthy foods and drinks should be subject to evaluation by an independent body.

  4. In a secondary care setting, differences between neck pain subgroups classified using the Quebec task force classification system were typically small

    DEFF Research Database (Denmark)

    Rasmussen, Hanne; Kent, Peter; Kjaer, Per

    2015-01-01

    and patients with NP + NRI had experienced the largest improvements in pain intensity. Similar results were obtained for activity limitation. CONCLUSIONS: This study found baseline and outcome differences between neck pain subgroups classified using the Quebec Task Force Classification System. However......BACKGROUND: The component of the Quebec Task Force Classification System that subgroups patients based on the extent of their radiating pain and neurological signs has been demonstrated to have prognostic implications for patients with low back pain but has not been tested on patients with neck...... models. RESULTS: A total of 1,852 people were classified into subgroups (64 % females, mean age 49 years). Follow ups after 3, 6 and 12 months were available for 45 %, 32 % and 40 % of those invited to participate at each time point. A small improvement in pain was observed over time in all subgroups...

  5. Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Salahshoor, Karim [Department of Instrumentation and Automation, Petroleum University of Technology, Tehran (Iran, Islamic Republic of); Kordestani, Mojtaba; Khoshro, Majid S. [Department of Control Engineering, Islamic Azad University South Tehran branch (Iran, Islamic Republic of)

    2010-12-15

    The subject of FDD (fault detection and diagnosis) has gained widespread industrial interest in machine condition monitoring applications. This is mainly due to the potential advantage to be achieved from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a new FDD scheme for condition machinery of an industrial steam turbine using a data fusion methodology. Fusion of a SVM (support vector machine) classifier with an ANFIS (adaptive neuro-fuzzy inference system) classifier, integrated into a common framework, is utilized to enhance the fault detection and diagnostic tasks. For this purpose, a multi-attribute data is fused into aggregated values of a single attribute by OWA (ordered weighted averaging) operators. The simulation studies indicate that the resulting fusion-based scheme outperforms the individual SVM and ANFIS systems to detect and diagnose incipient steam turbine faults. (author)

  6. Adaptive polymeric system for Hebbian type learning

    OpenAIRE

    2011-01-01

    Abstract We present the experimental realization of an adaptive polymeric system displaying a ?learning behaviour?. The system consists on a statistically organized networks of memristive elements (memory-resitors) based on polyaniline. In a such network the path followed by the current increments its conductivity, a property which makes the system able to mimic Hebbian type learning and have application in hardware neural networks. After discussing the working principle of ...

  7. Intelligent Web-Based Learning System with Personalized Learning Path Guidance

    Science.gov (United States)

    Chen, C. M.

    2008-01-01

    Personalized curriculum sequencing is an important research issue for web-based learning systems because no fixed learning paths will be appropriate for all learners. Therefore, many researchers focused on developing e-learning systems with personalized learning mechanisms to assist on-line web-based learning and adaptively provide learning paths…

  8. Patterns for Designing Learning Management Systems

    NARCIS (Netherlands)

    Avgeriou, Paris; Retalis, Symeon; Papasalouros, Andreas

    2003-01-01

    Learning Management Systems are sophisticated web-based applications that are being engineered today in increasing numbers by numerous institutions and companies that want to get involved in e-learning either for providing services to third parties, or for educating and training their own people.

  9. Process Systems Engineering Education: Learning by Research

    Science.gov (United States)

    Abbas, A.; Alhammadi, H. Y.; Romagnoli, J. A.

    2009-01-01

    In this paper, we discuss our approach in teaching the final-year course Process Systems Engineering. Students are given ownership of the course by transferring to them the responsibility of learning. A project-based group environment stimulates learning while solving a real engineering problem. We discuss postgraduate student involvement and how…

  10. Learning and Organizational Effectiveness: A Systems Perspective

    Science.gov (United States)

    Andreadis, Nicholas

    2009-01-01

    The challenge for leaders today is to create and develop the capability of their organization. Leaders must perceive and manage their organization as a dynamic, open system where learning is the core competence underlying innovation, growth, and sustainability. Creating a culture of learning is the first work of leadership. This article presents a…

  11. A Distributed Intelligent E-Learning System

    Science.gov (United States)

    Kristensen, Terje

    2016-01-01

    An E-learning system based on a multi-agent (MAS) architecture combined with the Dynamic Content Manager (DCM) model of E-learning, is presented. We discuss the benefits of using such a multi-agent architecture. Finally, the MAS architecture is compared with a pure service-oriented architecture (SOA). This MAS architecture may also be used within…

  12. Building machine learning systems with Python

    CERN Document Server

    Richert, Willi

    2013-01-01

    This is a tutorial-driven and practical, but well-grounded book showcasing good Machine Learning practices. There will be an emphasis on using existing technologies instead of showing how to write your own implementations of algorithms. This book is a scenario-based, example-driven tutorial. By the end of the book you will have learnt critical aspects of Machine Learning Python projects and experienced the power of ML-based systems by actually working on them.This book primarily targets Python developers who want to learn about and build Machine Learning into their projects, or who want to pro

  13. Automated gastric cancer diagnosis on H&E-stained sections; ltraining a classifier on a large scale with multiple instance machine learning

    Science.gov (United States)

    Cosatto, Eric; Laquerre, Pierre-Francois; Malon, Christopher; Graf, Hans-Peter; Saito, Akira; Kiyuna, Tomoharu; Marugame, Atsushi; Kamijo, Ken'ichi

    2013-03-01

    We present a system that detects cancer on slides of gastric tissue sections stained with hematoxylin and eosin (H&E). At its heart is a classi er trained using the semi-supervised multi-instance learning framework (MIL) where each tissue is represented by a set of regions-of-interest (ROI) and a single label. Such labels are readily obtained because pathologists diagnose each tissue independently as part of the normal clinical work ow. From a large dataset of over 26K gastric tissue sections from over 12K patients obtained from a clinical load spanning several months, we train a MIL classi er on a patient-level partition of the dataset (2/3 of the patients) and obtain a very high performance of 96% (AUC), tested on the remaining 1/3 never-seen before patients (over 8K tissues). We show this level of performance to match the more costly supervised approach where individual ROIs need to be labeled manually. The large amount of data used to train this system gives us con dence in its robustness and that it can be safely used in a clinical setting. We demonstrate how it can improve the clinical work ow when used for pre-screening or quality control. For pre-screening, the system can diagnose 47% of the tissues with a very low likelihood (cancers, thus halving the clinicians' caseload. For quality control, compared to random rechecking of 33% of the cases, the system achieves a three-fold increase in the likelihood of catching cancers missed by pathologists. The system is currently in regular use at independent pathology labs in Japan where it is used to double-check clinician's diagnoses. At the end of 2012 it will have analyzed over 80,000 slides of gastric and colorectal samples (200,000 tissues).

  14. SYSTEM APPROACH TO THE BLENDED LEARNING

    Directory of Open Access Journals (Sweden)

    Vladimir Kukharenko

    2015-10-01

    Full Text Available Currently, much attention is paid to the development of learning sour cream – a combination of traditional and distance (30-70% of training. Such training is sometimes called hybrid and referred to disruptive technologies. Purpose – to show that the use of systemic campaign in blended learning provides a high quality of education, and the technology can be devastating. The subject of the study – blended learning, object of study – Mixed learning process. The analysis results show that the combined training increases the motivation of students, qualification of teachers, personalized learning process. At the same time there are no reliable methods of assessing the quality of education and training standards. It is important that blended learning strategy to support the institutional goals and had an effective organizational model for support.

  15. Indirect learning control for nonlinear dynamical systems

    Science.gov (United States)

    Ryu, Yeong Soon; Longman, Richard W.

    1993-01-01

    In a previous paper, learning control algorithms were developed based on adaptive control ideas for linear time variant systems. The learning control methods were shown to have certain advantages over their adaptive control counterparts, such as the ability to produce zero tracking error in time varying systems, and the ability to eliminate repetitive disturbances. In recent years, certain adaptive control algorithms have been developed for multi-body dynamic systems such as robots, with global guaranteed convergence to zero tracking error for the nonlinear system euations. In this paper we study the relationship between such adaptive control methods designed for this specific class of nonlinear systems, and the learning control problem for such systems, seeking to converge to zero tracking error in following a specific command repeatedly, starting from the same initial conditions each time. The extension of these methods from the adaptive control problem to the learning control problem is seen to be trivial. The advantages and disadvantages of using learning control based on such adaptive control concepts for nonlinear systems, and the use of other currently available learning control algorithms are discussed.

  16. systemic approach to teaching and learning chemistry

    African Journals Online (AJOL)

    unesco

    2National Core Group in Chemistry, H.E.J Research Institute of Chemistry,. University of ... innovative way of teaching and learning through systemic approach (SATL) has been .... available to do useful work in a thermodynamic process.

  17. Balanced sensitivity functions for tuning multi-dimensional Bayesian network classifiers

    NARCIS (Netherlands)

    Bolt, J.H.; van der Gaag, L.C.

    Multi-dimensional Bayesian network classifiers are Bayesian networks of restricted topological structure, which are tailored to classifying data instances into multiple dimensions. Like more traditional classifiers, multi-dimensional classifiers are typically learned from data and may include

  18. Solution to Detect, Classify, and Report Illicit Online Marketing and Sales of Controlled Substances via Twitter: Using Machine Learning and Web Forensics to Combat Digital Opioid Access.

    Science.gov (United States)

    Mackey, Tim; Kalyanam, Janani; Klugman, Josh; Kuzmenko, Ella; Gupta, Rashmi

    2018-04-27

    On December 6 and 7, 2017, the US Department of Health and Human Services (HHS) hosted its first Code-a-Thon event aimed at leveraging technology and data-driven solutions to help combat the opioid epidemic. The authors—an interdisciplinary team from academia, the private sector, and the US Centers for Disease Control and Prevention—participated in the Code-a-Thon as part of the prevention track. The aim of this study was to develop and deploy a methodology using machine learning to accurately detect the marketing and sale of opioids by illicit online sellers via Twitter as part of participation at the HHS Opioid Code-a-Thon event. Tweets were collected from the Twitter public application programming interface stream filtered for common prescription opioid keywords in conjunction with participation in the Code-a-Thon from November 15, 2017 to December 5, 2017. An unsupervised machine learning–based approach was developed and used during the Code-a-Thon competition (24 hours) to obtain a summary of the content of the tweets to isolate those clusters associated with illegal online marketing and sale using a biterm topic model (BTM). After isolating relevant tweets, hyperlinks associated with these tweets were reviewed to assess the characteristics of illegal online sellers. We collected and analyzed 213,041 tweets over the course of the Code-a-Thon containing keywords codeine, percocet, vicodin, oxycontin, oxycodone, fentanyl, and hydrocodone. Using BTM, 0.32% (692/213,041) tweets were identified as being associated with illegal online marketing and sale of prescription opioids. After removing duplicates and dead links, we identified 34 unique “live” tweets, with 44% (15/34) directing consumers to illicit online pharmacies, 32% (11/34) linked to individual drug sellers, and 21% (7/34) used by marketing affiliates. In addition to offering the “no prescription” sale of opioids, many of these vendors also sold other controlled substances and illicit drugs

  19. Sitting Posture Monitoring System Based on a Low-Cost Load Cell Using Machine Learning

    Directory of Open Access Journals (Sweden)

    Jongryun Roh

    2018-01-01

    Full Text Available Sitting posture monitoring systems (SPMSs help assess the posture of a seated person in real-time and improve sitting posture. To date, SPMS studies reported have required many sensors mounted on the backrest plate and seat plate of a chair. The present study, therefore, developed a system that measures a total of six sitting postures including the posture that applied a load to the backrest plate, with four load cells mounted only on the seat plate. Various machine learning algorithms were applied to the body weight ratio measured by the developed SPMS to identify the method that most accurately classified the actual sitting posture of the seated person. After classifying the sitting postures using several classifiers, average and maximum classification rates of 97.20% and 97.94%, respectively, were obtained from nine subjects with a support vector machine using the radial basis function kernel; the results obtained by this classifier showed a statistically significant difference from the results of multiple classifications using other classifiers. The proposed SPMS was able to classify six sitting postures including the posture with loading on the backrest and showed the possibility of classifying the sitting posture even though the number of sensors is reduced.

  20. Transformative Learning: Patterns of Psychophysiologic Response and Technology-Enabled Learning and Intervention Systems

    Science.gov (United States)

    2008-09-01

    Psychophysiologic Response and Technology -Enabled Learning and Intervention Systems PRINCIPAL INVESTIGATOR: Leigh W. Jerome, Ph.D...NUMBER Transformative Learning : Patterns of Psychophysiologic Response and Technology - Enabled Learning and Intervention Systems 5b. GRANT NUMBER...project entitled “Transformative Learning : Patterns of Psychophysiologic Response in Technology Enabled Learning and Intervention Systems.” The

  1. Aggregation Operator Based Fuzzy Pattern Classifier Design

    DEFF Research Database (Denmark)

    Mönks, Uwe; Larsen, Henrik Legind; Lohweg, Volker

    2009-01-01

    This paper presents a novel modular fuzzy pattern classifier design framework for intelligent automation systems, developed on the base of the established Modified Fuzzy Pattern Classifier (MFPC) and allows designing novel classifier models which are hardware-efficiently implementable....... The performances of novel classifiers using substitutes of MFPC's geometric mean aggregator are benchmarked in the scope of an image processing application against the MFPC to reveal classification improvement potentials for obtaining higher classification rates....

  2. New designing of E-Learning systems with using network learning

    OpenAIRE

    Malayeri, Amin Daneshmand; Abdollahi, Jalal

    2010-01-01

    One of the most applied learning in virtual spaces is using E-Learning systems. Some E-Learning methodologies has been introduced, but the main subject is the most positive feedback from E-Learning systems. In this paper, we introduce a new methodology of E-Learning systems entitle "Network Learning" with review of another aspects of E-Learning systems. Also, we present benefits and advantages of using these systems in educating and fast learning programs. Network Learning can be programmable...

  3. Feedback Design Patterns for Math Online Learning Systems

    Science.gov (United States)

    Inventado, Paul Salvador; Scupelli, Peter; Heffernan, Cristina; Heffernan, Neil

    2017-01-01

    Increasingly, computer-based learning systems are used by educators to facilitate learning. Evaluations of several math learning systems show that they result in significant student learning improvements. Feedback provision is one of the key features in math learning systems that contribute to its success. We have recently been uncovering feedback…

  4. Systems Thinking, Lean Production and Action Learning

    Science.gov (United States)

    Seddon, John; Caulkin, Simon

    2007-01-01

    Systems thinking underpins "lean" management and is best understood through action-learning as the ideas are counter-intuitive. The Toyota Production System is just that--a system; the failure to appreciate that starting-place and the advocacy of "tools" leads many to fail to grasp what is, without doubt, a significant…

  5. The organization of an autonomous learning system

    Science.gov (United States)

    Kanerva, Pentti

    1988-01-01

    The organization of systems that learn from experience is examined, human beings and animals being prime examples of such systems. How is their information processing organized. They build an internal model of the world and base their actions on the model. The model is dynamic and predictive, and it includes the systems' own actions and their effects. In modeling such systems, a large pattern of features represents a moment of the system's experience. Some of the features are provided by the system's senses, some control the system's motors, and the rest have no immediate external significance. A sequence of such patterns then represents the system's experience over time. By storing such sequences appropriately in memory, the system builds a world model based on experience. In addition to the essential function of memory, fundamental roles are played by a sensory system that makes raw information about the world suitable for memory storage and by a motor system that affects the world. The relation of sensory and motor systems to the memory is discussed, together with how favorable actions can be learned and unfavorable actions can be avoided. Results in classical learning theory are explained in terms of the model, more advanced forms of learning are discussed, and the relevance of the model to the frame problem of robotics is examined.

  6. Method to classify the safety class of Structure, System and Components in a Defueled Condition of Nuclear Power Plant

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Dong-Hak; Jeon, Dang-Hee [KHNP CRI, Daejeon (Korea, Republic of)

    2016-10-15

    During pre-decommissioning phase, licensing and engineering work need to change the design basis of the plant such as safety analysis report, downgrade of systems, technical specifications and program and procedures to change of NPP condition from in an operation condition to in a defueled condition. The many systems to need to operate in an operational condition will not be operated during in a defueled condition and the function of systems will be changed from in an operation condition to in a defueled condition. So a downgrade of systems may be needed and reclassifying the safety class of structure, system and component (SSC) may be conducted. By the reclassification of SSC, activity related with quality assurance and maintenance of SSC is affected. In this paper, the method to reclassify SSC in a defueled condition is studied. The many systems to need to operate in an operational condition will not be operated during in a defueled condition and the function of systems will be changed from in an operation condition to in a defueled condition. The operation of NPP during a defueled condition need to conduct licensing and engineering work need to change the design basis of the plant optimize by downgrading systems and reclassifying the safety class of SSC. In this paper, the method to reclassify safety class for a defueled condition is studied.

  7. How Should Children with Speech Sound Disorders be Classified? A Review and Critical Evaluation of Current Classification Systems

    Science.gov (United States)

    Waring, R.; Knight, R.

    2013-01-01

    Background: Children with speech sound disorders (SSD) form a heterogeneous group who differ in terms of the severity of their condition, underlying cause, speech errors, involvement of other aspects of the linguistic system and treatment response. To date there is no universal and agreed-upon classification system. Instead, a number of…

  8. Are lung imaging reporting and data system categories clear to radiologists? A survey of the Korean Society of Thoracic Radiology members on ten difficult -to classify scenarios

    Energy Technology Data Exchange (ETDEWEB)

    Han, Dae Hee; Ahn, Myeong Im [Dept. of Radiology, Seoul St. Mary' s Hospital, College of Medicine, The Catholic University of Korea, Seoul (Korea, Republic of); Goo, Jin Mo [Dept. of Radiology, Seoul National University College of Medicine, Institute of Radiation Medicine, Seoul National University Medical Research Center, Seoul (Korea, Republic of); Chong, Se Min [Dept. of Radiology, Chung-Ang University Hospital, Chung-Ang University College of Medicine, Seoul (Korea, Republic of)

    2017-04-15

    To evaluate possible variability in chest radiologists' interpretations of the Lung Imaging Reporting and Data System (Lung-RADS) on difficult-to-classify scenarios. Ten scenarios of difficult-to-classify imaginary lung nodules were prepared as an online survey that targeted Korean Society of Thoracic Radiology members. In each question, a description was provided of the size, consistency, and interval change (new or growing) of a lung nodule observed using annual repeat computed tomography, and the respondent was instructed to choose one answer from five choices: category 2, 3, 4A, or 4B, or 'un-categorizable.' Consensus answers were established by members of the Korean Imaging Study Group for Lung Cancer. Of the 420 answers from 42 respondents (excluding multiple submissions), 310 (73.8%) agreed with the consensus answers; eleven (26.2%) respondents agreed with the consensus answers to six or fewer questions. Assigning the imaginary nodules to categories higher than the consensus answer was more frequent (16.0%) than assigning them to lower categories (5.5%), and the agreement rate was below 50% for two scenarios. When given difficult-to-classify scenarios, chest radiologists showed large variability in their interpretations of the Lung-RADS categories, with high frequencies of disagreement in some specific scenarios.

  9. Automatic Anthropometric System Development Using Machine Learning

    Directory of Open Access Journals (Sweden)

    Long The Nguyen

    2016-08-01

    Full Text Available The contactless automatic anthropometric system is proposed for the reconstruction of the 3D-model of the human body using the conventional smartphone. Our approach involves three main steps. The first step is the extraction of 12 anthropological features. Then we determine the most important features. Finally, we employ these features to build the 3D model of the human body and classify them according to gender and the commonly used sizes. 

  10. Classifying Transition Behaviour in Postural Activity Monitoring

    Directory of Open Access Journals (Sweden)

    James BRUSEY

    2009-10-01

    Full Text Available A few accelerometers positioned on different parts of the body can be used to accurately classify steady state behaviour, such as walking, running, or sitting. Such systems are usually built using supervised learning approaches. Transitions between postures are, however, difficult to deal with using posture classification systems proposed to date, since there is no label set for intermediary postures and also the exact point at which the transition occurs can sometimes be hard to pinpoint. The usual bypass when using supervised learning to train such systems is to discard a section of the dataset around each transition. This leads to poorer classification performance when the systems are deployed out of the laboratory and used on-line, particularly if the regimes monitored involve fast paced activity changes. Time-based filtering that takes advantage of sequential patterns is a potential mechanism to improve posture classification accuracy in such real-life applications. Also, such filtering should reduce the number of event messages needed to be sent across a wireless network to track posture remotely, hence extending the system’s life. To support time-based filtering, understanding transitions, which are the major event generators in a classification system, is a key. This work examines three approaches to post-process the output of a posture classifier using time-based filtering: a naïve voting scheme, an exponentially weighted voting scheme, and a Bayes filter. Best performance is obtained from the exponentially weighted voting scheme although it is suspected that a more sophisticated treatment of the Bayes filter might yield better results.

  11. A Mobile Gamification Learning System for Improving the Learning Motivation and Achievements

    Science.gov (United States)

    Su, C-H.; Cheng, C-H.

    2015-01-01

    This paper aims to investigate how a gamified learning approach influences science learning, achievement and motivation, through a context-aware mobile learning environment, and explains the effects on motivation and student learning. A series of gamified learning activities, based on MGLS (Mobile Gamification Learning System), was developed and…

  12. Beyond "objective" and "projective": a logical system for classifying psychological tests: comment on Meyer and Kurtz (2006).

    Science.gov (United States)

    Wagner, Edwin E

    2008-07-01

    I present a formal system that accounts for the misleading distinction between tests formerly termed objective and projective, duly noted by Meyer and Kurtz (2006). Three principles of Response Rightness, Response Latitude and Stimulus Ambiguity are shown to govern, in combination, the formal operating characteristics of tests, producing inevitable overlap between "objective" and "projective" tests and creating at least three "types" of tests historically regarded as being projective in nature. The system resolves many past issues regarding test classification and can be generalized to include all psychological tests.

  13. Diversity of aging of the immune system classified in the cotton rat (Sigmodon hispidus) model of human infectious diseases.

    NARCIS (Netherlands)

    Guichelaar, Teun; van Erp, Elisabeth A; Hoeboer, Jeroen; Smits, Noortje A M; van Els, Cécile A C M; Pieren, Daan K J; Luytjes, Willem

    2018-01-01

    Susceptibility and declined resistance to human pathogens like respiratory syncytial virus (RSV) at old age is well represented in the cotton rat (Sigmodon hispidus). Despite providing a preferred model of human infectious diseases, little is known about aging of its adaptive immune system. We aimed

  14. Classifying Pediatric Central Nervous System Tumors through near Optimal Feature Selection and Mutual Information: A Single Center Cohort

    Directory of Open Access Journals (Sweden)

    Mohammad Faranoush

    2013-10-01

    Full Text Available Background: Labeling, gathering mutual information, clustering and classificationof central nervous system tumors may assist in predicting not only distinct diagnosesbased on tumor-specific features but also prognosis. This study evaluates the epidemi-ological features of central nervous system tumors in children who referred to Mahak’sPediatric Cancer Treatment and Research Center in Tehran, Iran.Methods: This cohort (convenience sample study comprised 198 children (≤15years old with central nervous system tumors who referred to Mahak's PediatricCancer Treatment and Research Center from 2007 to 2010. In addition to the descriptiveanalyses on epidemiological features and mutual information, we used the LeastSquares Support Vector Machines method in MATLAB software to propose apreliminary predictive model of pediatric central nervous system tumor feature-labelanalysis. Results:Of patients, there were 63.1% males and 36.9% females. Patients' mean±SDage was 6.11±3.65 years. Tumor location was as follows: supra-tentorial (30.3%, infra-tentorial (67.7% and 2% (spinal. The most frequent tumors registered were: high-gradeglioma (supra-tentorial in 36 (59.99% patients and medulloblastoma (infra-tentorialin 65 (48.51% patients. The most prevalent clinical findings included vomiting,headache and impaired vision. Gender, age, ethnicity, tumor stage and the presence ofmetastasis were the features predictive of supra-tentorial tumor histology.Conclusion: Our data agreed with previous reports on the epidemiology of centralnervous system tumors. Our feature-label analysis has shown how presenting features maypartially predict diagnosis. Timely diagnosis and management of central nervous systemtumors can lead to decreased disease burden and improved survival. This may be furtherfacilitated through development of partitioning, risk prediction and prognostic models.

  15. Learning to Control Advanced Life Support Systems

    Science.gov (United States)

    Subramanian, Devika

    2004-01-01

    Advanced life support systems have many interacting processes and limited resources. Controlling and optimizing advanced life support systems presents unique challenges. In particular, advanced life support systems are nonlinear coupled dynamical systems and it is difficult for humans to take all interactions into account to design an effective control strategy. In this project. we developed several reinforcement learning controllers that actively explore the space of possible control strategies, guided by rewards from a user specified long term objective function. We evaluated these controllers using a discrete event simulation of an advanced life support system. This simulation, called BioSim, designed by Nasa scientists David Kortenkamp and Scott Bell has multiple, interacting life support modules including crew, food production, air revitalization, water recovery, solid waste incineration and power. They are implemented in a consumer/producer relationship in which certain modules produce resources that are consumed by other modules. Stores hold resources between modules. Control of this simulation is via adjusting flows of resources between modules and into/out of stores. We developed adaptive algorithms that control the flow of resources in BioSim. Our learning algorithms discovered several ingenious strategies for maximizing mission length by controlling the air and water recycling systems as well as crop planting schedules. By exploiting non-linearities in the overall system dynamics, the learned controllers easily out- performed controllers written by human experts. In sum, we accomplished three goals. We (1) developed foundations for learning models of coupled dynamical systems by active exploration of the state space, (2) developed and tested algorithms that learn to efficiently control air and water recycling processes as well as crop scheduling in Biosim, and (3) developed an understanding of the role machine learning in designing control systems for

  16. The Joint Lessons Learned System and Interoperability

    Science.gov (United States)

    1989-06-02

    Learned: 1988-1989 As mentioned in the introduction to this chaoter, the Organizacion of the JcinC Chiefs cf Staff .OJCS) ueren significant transformatioi...Organization and Functions Manual . Washington, D.C.: HQDA, Office of the Deputy Chief 0f Staff for Operations and Plans, June 1984. ’..S. Army. Concept...U.S. Department of Defense. Joint Universal Lessons Learned System (JULLS) User’s Manual . Orlando, Florida: University of Central Florida, Institute

  17. How Instructional Systems Will Manage Learning

    Science.gov (United States)

    Flanagan, John C.

    1970-01-01

    Discusses trends toward the systems approach in education including the development of effective instructional systems in government and industry; the introduction of teaching machines, programed learning, and computer- assisted instruction; and the increase in both the amount and sophistication of educational research and development. (JF)

  18. An Architecture for Open Learning Management Systems

    NARCIS (Netherlands)

    Avgeriou, Paris; Retalis, Simos; Skordalakis, Manolis

    2003-01-01

    There exists an urgent demand on defining architectures for Learning Management Systems, so that high-level frameworks for understanding these systems can be discovered, and quality attributes like portability, interoperability, reusability and modifiability can be achieved. In this paper we propose

  19. Transitioning from learning healthcare systems to learning health care communities.

    Science.gov (United States)

    Mullins, C Daniel; Wingate, La'Marcus T; Edwards, Hillary A; Tofade, Toyin; Wutoh, Anthony

    2018-02-26

    The learning healthcare system (LHS) model framework has three core, foundational components. These include an infrastructure for health-related data capture, care improvement targets and a supportive policy environment. Despite progress in advancing and implementing LHS approaches, low levels of participation from patients and the public have hampered the transformational potential of the LHS model. An enhanced vision of a community-engaged LHS redesign would focus on the provision of health care from the patient and community perspective to complement the healthcare system as the entity that provides the environment for care. Addressing the LHS framework implementation challenges and utilizing community levers are requisite components of a learning health care community model, version two of the LHS archetype.

  20. Evaluating Usability of E-Learning Systems in Universities

    OpenAIRE

    Nicholas Kipkurui Kiget; Professor G. Wanyembi; Anselemo Ikoha Peters

    2014-01-01

    The use of e-learning systems has increased significantly in the recent times. E-learning systems are supplementing teaching and learning in universities globally. Kenyan universities have adopted e-learning technologies as means for delivering course content. However despite adoption of these systems, there are considerable challenges facing the usability of the systems. Lecturers and students have different perceptions in regard to the usability of e-learning systems. The aim of this study ...

  1. CAD system for quantifying emphysema severity based on multi-class classifier using CT image and spirometry information

    International Nuclear Information System (INIS)

    Nimura, Yukitaka; Mori, Kensaku; Kitasaka, Takayuki; Honma, Hirotoshi; Takabatake, Hirotsugu; Mori, Masaki; Natori, Hiroshi

    2010-01-01

    Many diagnosis methods based on CT image processing are proposed for quantifying emphysema. The most of these diagnosis methods extract lesions as Low-Attenuation Areas (LAA) by simple threshold processing and evaluate their severity by calculating the LAA (LAA%) in the lung. However, pulmonary emphysema is diagnosed by not only the LAA but also the changes of pulmonary blood vessel and the spirometric measurements. This paper proposes a novel computer-aided detection (CAD) system for quantifying emphysema by combining spirometric measurements and results of CT image processing. The experimental results revealed that the accuracy rate of the proposed method was 78.3%. It is 13.1% improvement compared with the method based on only the LAA%. (author)

  2. Assisted Learning Systems in e-Education

    Directory of Open Access Journals (Sweden)

    Gabriel ZAMFIR

    2014-01-01

    Full Text Available Human society, analyzed as a learning environment, presumes different languages in order to know, to understand or to develop it. This statement results as a default application of the cog-nitive domain in the educational scientific research, and it highlights a key feature: each essen-tial discovery was available for the entire language compatible society. E-Society is constructed as an application of E-Science in social services, and it is going to reveal a learning system for each application of the information technology developed for a compatible society. This article is proposed as a conceptual one focused on scientific research and the interrelationship be-tween the building blocks of research, defined as an engine for any designed learning system applied in the cognitive domain. In this approach, educational research become a learning sys-tem in e-Education. The purpose of this analysis is to configure the teacher assisted learning system and to expose its main principles which could be integrated in standard assisted instruc-tion applications, available in e-Classroom, supporting the design of specific didactic activities.

  3. Machine learning paradigms applications in recommender systems

    CERN Document Server

    Lampropoulos, Aristomenis S

    2015-01-01

    This timely book presents Applications in Recommender Systems which are making recommendations using machine learning algorithms trained via examples of content the user likes or dislikes. Recommender systems built on the assumption of availability of both positive and negative examples do not perform well when negative examples are rare. It is exactly this problem that the authors address in the monograph at hand. Specifically, the books approach is based on one-class classification methodologies that have been appearing in recent machine learning research. The blending of recommender systems and one-class classification provides a new very fertile field for research, innovation and development with potential applications in “big data” as well as “sparse data” problems. The book will be useful to researchers, practitioners and graduate students dealing with problems of extensive and complex data. It is intended for both the expert/researcher in the fields of Pattern Recognition, Machine Learning and ...

  4. Multidimensional Learner Model In Intelligent Learning System

    Science.gov (United States)

    Deliyska, B.; Rozeva, A.

    2009-11-01

    The learner model in an intelligent learning system (ILS) has to ensure the personalization (individualization) and the adaptability of e-learning in an online learner-centered environment. ILS is a distributed e-learning system whose modules can be independent and located in different nodes (servers) on the Web. This kind of e-learning is achieved through the resources of the Semantic Web and is designed and developed around a course, group of courses or specialty. An essential part of ILS is learner model database which contains structured data about learner profile and temporal status in the learning process of one or more courses. In the paper a learner model position in ILS is considered and a relational database is designed from learner's domain ontology. Multidimensional modeling agent for the source database is designed and resultant learner data cube is presented. Agent's modules are proposed with corresponding algorithms and procedures. Multidimensional (OLAP) analysis guidelines on the resultant learner module for designing dynamic learning strategy have been highlighted.

  5. Classifying Returns as Extreme

    DEFF Research Database (Denmark)

    Christiansen, Charlotte

    2014-01-01

    I consider extreme returns for the stock and bond markets of 14 EU countries using two classification schemes: One, the univariate classification scheme from the previous literature that classifies extreme returns for each market separately, and two, a novel multivariate classification scheme tha...

  6. Multiple systems for motor skill learning.

    Science.gov (United States)

    Clark, Dav; Ivry, Richard B

    2010-07-01

    Motor learning is a ubiquitous feature of human competence. This review focuses on two particular classes of model tasks for studying skill acquisition. The serial reaction time (SRT) task is used to probe how people learn sequences of actions, while adaptation in the context of visuomotor or force field perturbations serves to illustrate how preexisting movements are recalibrated in novel environments. These tasks highlight important issues regarding the representational changes that occur during the course of motor learning. One important theme is that distinct mechanisms vary in their information processing costs during learning and performance. Fast learning processes may require few trials to produce large changes in performance but impose demands on cognitive resources. Slower processes are limited in their ability to integrate complex information but minimally demanding in terms of attention or processing resources. The representations derived from fast systems may be accessible to conscious processing and provide a relatively greater measure of flexibility, while the representations derived from slower systems are more inflexible and automatic in their behavior. In exploring these issues, we focus on how multiple neural systems may interact and compete during the acquisition and consolidation of new behaviors. Copyright © 2010 John Wiley & Sons, Ltd. This article is categorized under: Psychology > Motor Skill and Performance. Copyright © 2010 John Wiley & Sons, Ltd.

  7. Improvement of the Mair scoring system using structural equations modeling for classifying the diagnostic adequacy of cytology material from thyroid lesions.

    Science.gov (United States)

    Kulkarni, H R; Kamal, M M; Arjune, D G

    1999-12-01

    The scoring system developed by Mair et al. (Acta Cytol 1989;33:809-813) is frequently used to grade the quality of cytology smears. Using a one-factor analytic structural equations model, we demonstrate that the errors in measurement of the parameters used in the Mair scoring system are highly and significantly correlated. We recommend the use of either a multiplicative scoring system, using linear scores, or an additive scoring system, using exponential scores, to correct for the correlated errors. We suggest that the 0, 1, and 2 points used in the Mair scoring system be replaced by 1, 2, and 4, respectively. Using data on fine-needle biopsies of 200 thyroid lesions by both fine-needle aspiration (FNA) and fine-needle capillary sampling (FNC), we demonstrate that our modification of the Mair scoring system is more sensitive and more consistent with the structural equations model. Therefore, we recommend that the modified Mair scoring system be used for classifying the diagnostic adequacy of cytology smears. Diagn. Cytopathol. 1999;21:387-393. Copyright 1999 Wiley-Liss, Inc.

  8. 3D Game-Based Learning System for Improving Learning Achievement in Software Engineering Curriculum

    Science.gov (United States)

    Su,Chung-Ho; Cheng, Ching-Hsue

    2013-01-01

    The advancement of game-based learning has encouraged many related studies, such that students could better learn curriculum by 3-dimension virtual reality. To enhance software engineering learning, this paper develops a 3D game-based learning system to assist teaching and assess the students' motivation, satisfaction and learning achievement. A…

  9. Towards synergy between learning management systems and educational server applications

    OpenAIRE

    Hartog, R.J.M.; Schaaf, van der, H.; Kassahun, A.

    2008-01-01

    Most well-known Learning Management Systems (LMS) are based on a paradigm of learning objects to be uploaded into the system. Most formulations of this paradigm implicitly assume that the learning objects are self contained learning objects such as FLASH objects or JAVA applets or presentational learning objects such as slide presentations. These are typically client side objects. However, a demand for learning support that activates the student can often be satisfied better with a server app...

  10. An Instructional and Collaborative Learning System with Content Recommendation

    Science.gov (United States)

    Zheng, Xiang-wei; Ma, Hong-wei; Li, Yan

    2013-01-01

    With the rapid development of Internet, e-learning has become a new teaching and learning mode. However, lots of e-learning systems deployed on Internet are just electronic learning materials with very limited interactivity and diagnostic capability. This paper presents an integrated e-learning environment named iCLSR. Firstly, iCLSR provides an…

  11. Learning through the taste system

    Directory of Open Access Journals (Sweden)

    Thomas R. Scott

    2011-11-01

    Full Text Available Taste is the final arbiter of which chemicals from the environment will be admitted to the body. The action of swallowing a substance leads to a physiological consequence of which the taste system should be informed. Accordingly, taste neurons in the central nervous system are closely allied with those that receive input from the viscera so as to monitor the impact of a recently ingested substance. There is behavioral, anatomical, electrophysiological, gene expression, and neurochemical evidence that the consequences of ingestion influence subsequent food selection through development of either a conditioned taste aversion (if illness ensues or a conditioned taste preference (if satiety. This ongoing communication between taste and the viscera permits the animal to tailor its taste system to its individual needs over a lifetime.

  12. Information Systems in University Learning

    Directory of Open Access Journals (Sweden)

    Gheorghe SABAU

    2010-01-01

    Full Text Available The authors of this article are going to bring into light the significance, the place and the role of information systems in the university education process. At the same time they define the objectives and the target group of the subject named Economic Information Systems and state the competence gained by students by studying this subject. Special attention is given to the curriculum to be taught to students and to a suggestive enumeration of a series of economic applications that can be themes for laboratory practice and for students’ dissertation (graduation thesis.

  13. Classifying Linear Canonical Relations

    OpenAIRE

    Lorand, Jonathan

    2015-01-01

    In this Master's thesis, we consider the problem of classifying, up to conjugation by linear symplectomorphisms, linear canonical relations (lagrangian correspondences) from a finite-dimensional symplectic vector space to itself. We give an elementary introduction to the theory of linear canonical relations and present partial results toward the classification problem. This exposition should be accessible to undergraduate students with a basic familiarity with linear algebra.

  14. Deep learning-based Diabetic Retinopathy assessment on embedded system.

    Science.gov (United States)

    Ardiyanto, Igi; Nugroho, Hanung Adi; Buana, Ratna Lestari Budiani

    2017-07-01

    Diabetic Retinopathy (DR) is a disease which affect the vision ability. The observation by an ophthalmologist usually conducted by analyzing the retinal images of the patient which are marked by some DR features. However some misdiagnosis are usually found due to human error. Here, a deep learning-based low-cost embedded system is established to assist the doctor for grading the severity of the DR from the retinal images. A compact deep learning algorithm named Deep-DR-Net which fits on a small embedded board is afterwards proposed for such purposes. In the heart of Deep-DR-Net, a cascaded encoder-classifier network is arranged using residual style for ensuring the small model size. The usage of different types of convolutional layers subsequently guarantees the features richness of the network for differentiating the grade of the DR. Experimental results show the capability of the proposed system for detecting the existence as well as grading the severity of the DR symptomps.

  15. Implementing the learning health care system.

    NARCIS (Netherlands)

    Verheij, R.; Barten, D.J.; Hek, K.; Nielen, M.; Prins, M.; Zwaanswijk, M.; Bakker, D. de

    2014-01-01

    Background: As computerisation of primary care facilities is rapidly increasing, a wealth of data is created in routinely recorded electronic health records (EHRs). This data can be used to create a true learning health care system, in which routinely available data are processed and analysed in

  16. Distance Learning Delivery Systems: Instructional Options.

    Science.gov (United States)

    Steele, Ray L.

    1993-01-01

    Discusses the availability of satellite and cable programing to provide distance education opportunities in school districts. Various delivery systems are described, including telephones with speakers, personal computers, and satellite dishes; and a sidebar provides a directory of distance learning opportunities, including telecommunications…

  17. Learning System Center App Controller

    CERN Document Server

    Naeem, Nasir

    2015-01-01

    This book is intended for IT professionals working with Hyper-V, Azure cloud, VMM, and private cloud technologies who are looking for a quick way to get up and running with System Center 2012 R2 App Controller. To get the most out of this book, you should be familiar with Microsoft Hyper-V technology. Knowledge of Virtual Machine Manager is helpful but not mandatory.

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

    Directory of Open Access Journals (Sweden)

    Shehzad Khalid

    2014-01-01

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

  19. Principles of e-learning systems engineering

    CERN Document Server

    Gilbert, Lester

    2008-01-01

    The book integrates the principles of software engineering with the principles of educational theory, and applies them to the problems of e-learning development, thus establishing the discipline of E-learning systems engineering. For the first time, these principles are collected and organised into the coherent framework that this book provides. Both newcomers to and established practitioners in the field are provided with integrated and grounded advice on theory and practice. The book presents strong practical and theoretical frameworks for the design and development of technology-based mater

  20. Component-Based Approach in Learning Management System Development

    Science.gov (United States)

    Zaitseva, Larisa; Bule, Jekaterina; Makarov, Sergey

    2013-01-01

    The paper describes component-based approach (CBA) for learning management system development. Learning object as components of e-learning courses and their metadata is considered. The architecture of learning management system based on CBA being developed in Riga Technical University, namely its architecture, elements and possibilities are…

  1. A Situated Cultural Festival Learning System Based on Motion Sensing

    Science.gov (United States)

    Chang, Yi-Hsing; Lin, Yu-Kai; Fang, Rong-Jyue; Lu, You-Te

    2017-01-01

    A situated Chinese cultural festival learning system based on motion sensing is developed in this study. The primary design principle is to create a highly interactive learning environment, allowing learners to interact with Kinect through natural gestures in the designed learning situation to achieve efficient learning. The system has the…

  2. Pixel Classification of SAR ice images using ANFIS-PSO Classifier

    Directory of Open Access Journals (Sweden)

    G. Vasumathi

    2016-12-01

    Full Text Available Synthetic Aperture Radar (SAR is playing a vital role in taking extremely high resolution radar images. It is greatly used to monitor the ice covered ocean regions. Sea monitoring is important for various purposes which includes global climate systems and ship navigation. Classification on the ice infested area gives important features which will be further useful for various monitoring process around the ice regions. Main objective of this paper is to classify the SAR ice image that helps in identifying the regions around the ice infested areas. In this paper three stages are considered in classification of SAR ice images. It starts with preprocessing in which the speckled SAR ice images are denoised using various speckle removal filters; comparison is made on all these filters to find the best filter in speckle removal. Second stage includes segmentation in which different regions are segmented using K-means and watershed segmentation algorithms; comparison is made between these two algorithms to find the best in segmenting SAR ice images. The last stage includes pixel based classification which identifies and classifies the segmented regions using various supervised learning classifiers. The algorithms includes Back propagation neural networks (BPN, Fuzzy Classifier, Adaptive Neuro Fuzzy Inference Classifier (ANFIS classifier and proposed ANFIS with Particle Swarm Optimization (PSO classifier; comparison is made on all these classifiers to propose which classifier is best suitable for classifying the SAR ice image. Various evaluation metrics are performed separately at all these three stages.

  3. Genetic learning in rule-based and neural systems

    Science.gov (United States)

    Smith, Robert E.

    1993-01-01

    The design of neural networks and fuzzy systems can involve complex, nonlinear, and ill-conditioned optimization problems. Often, traditional optimization schemes are inadequate or inapplicable for such tasks. Genetic Algorithms (GA's) are a class of optimization procedures whose mechanics are based on those of natural genetics. Mathematical arguments show how GAs bring substantial computational leverage to search problems, without requiring the mathematical characteristics often necessary for traditional optimization schemes (e.g., modality, continuity, availability of derivative information, etc.). GA's have proven effective in a variety of search tasks that arise in neural networks and fuzzy systems. This presentation begins by introducing the mechanism and theoretical underpinnings of GA's. GA's are then related to a class of rule-based machine learning systems called learning classifier systems (LCS's). An LCS implements a low-level production-system that uses a GA as its primary rule discovery mechanism. This presentation illustrates how, despite its rule-based framework, an LCS can be thought of as a competitive neural network. Neural network simulator code for an LCS is presented. In this context, the GA is doing more than optimizing and objective function. It is searching for an ecology of hidden nodes with limited connectivity. The GA attempts to evolve this ecology such that effective neural network performance results. The GA is particularly well adapted to this task, given its naturally-inspired basis. The LCS/neural network analogy extends itself to other, more traditional neural networks. Conclusions to the presentation discuss the implications of using GA's in ecological search problems that arise in neural and fuzzy systems.

  4. DESIGNING MOTIVATIONAL LEARNING SYSTEMS IN DISTANCE EDUCATION

    Directory of Open Access Journals (Sweden)

    Jale BALABAN-SALI

    2008-07-01

    Full Text Available ABSTRACT The designing of instruction, when considered as a process, is the determination of instructional requirements of the learner and development of functional learning systems in order to meet these requirements. In fact, as a consequence of studies on the development of effective learning systems some instructional design theories have emerged. Among these theories the motivational design theory points out that instructional processes are required to be configured with the strategies which increases the attention, relevance, confidence and satisfaction of the students for an instructional design which ensures the continuity of learning motivation. The studies indicate that the systems which are developed on the basis of mentioned strategies raise the attention of the student during instruction, develop a relevance to the students’ requirements, create a positive expectation for success and help having a satisfaction by reinforcing success. In this article, the empirical studies related with this subject and the suggestions for presenting more effective motivational instructional designs in distance learning are summarized.

  5. A Tool for Creating Regionally Calibrated High-Resolution Land Cover Data Sets for the West African Sahel: Using Machine Learning to Scale Up Hand-Classified Maps in a Data-Sparse Environment

    Science.gov (United States)

    Van Gordon, M.; Van Gordon, S.; Min, A.; Sullivan, J.; Weiner, Z.; Tappan, G. G.

    2017-12-01

    Using support vector machine (SVM) learning and high-accuracy hand-classified maps, we have developed a publicly available land cover classification tool for the West African Sahel. Our classifier produces high-resolution and regionally calibrated land cover maps for the Sahel, representing a significant contribution to the data available for this region. Global land cover products are unreliable for the Sahel, and accurate land cover data for the region are sparse. To address this gap, the U.S. Geological Survey and the Regional Center for Agriculture, Hydrology and Meteorology (AGRHYMET) in Niger produced high-quality land cover maps for the region via hand-classification of Landsat images. This method produces highly accurate maps, but the time and labor required constrain the spatial and temporal resolution of the data products. By using these hand-classified maps alongside SVM techniques, we successfully increase the resolution of the land cover maps by 1-2 orders of magnitude, from 2km-decadal resolution to 30m-annual resolution. These high-resolution regionally calibrated land cover datasets, along with the classifier we developed to produce them, lay the foundation for major advances in studies of land surface processes in the region. These datasets will provide more accurate inputs for food security modeling, hydrologic modeling, analyses of land cover change and climate change adaptation efforts. The land cover classification tool we have developed will be publicly available for use in creating additional West Africa land cover datasets with future remote sensing data and can be adapted for use in other parts of the world.

  6. What Learning Systems do Intelligent Agents Need? Complementary Learning Systems Theory Updated.

    Science.gov (United States)

    Kumaran, Dharshan; Hassabis, Demis; McClelland, James L

    2016-07-01

    We update complementary learning systems (CLS) theory, which holds that intelligent agents must possess two learning systems, instantiated in mammalians in neocortex and hippocampus. The first gradually acquires structured knowledge representations while the second quickly learns the specifics of individual experiences. We broaden the role of replay of hippocampal memories in the theory, noting that replay allows goal-dependent weighting of experience statistics. We also address recent challenges to the theory and extend it by showing that recurrent activation of hippocampal traces can support some forms of generalization and that neocortical learning can be rapid for information that is consistent with known structure. Finally, we note the relevance of the theory to the design of artificial intelligent agents, highlighting connections between neuroscience and machine learning. Copyright © 2016 Elsevier Ltd. All rights reserved.

  7. Energy-Efficient Neuromorphic Classifiers.

    Science.gov (United States)

    Martí, Daniel; Rigotti, Mattia; Seok, Mingoo; Fusi, Stefano

    2016-10-01

    Neuromorphic engineering combines the architectural and computational principles of systems neuroscience with semiconductor electronics, with the aim of building efficient and compact devices that mimic the synaptic and neural machinery of the brain. The energy consumptions promised by neuromorphic engineering are extremely low, comparable to those of the nervous system. Until now, however, the neuromorphic approach has been restricted to relatively simple circuits and specialized functions, thereby obfuscating a direct comparison of their energy consumption to that used by conventional von Neumann digital machines solving real-world tasks. Here we show that a recent technology developed by IBM can be leveraged to realize neuromorphic circuits that operate as classifiers of complex real-world stimuli. Specifically, we provide a set of general prescriptions to enable the practical implementation of neural architectures that compete with state-of-the-art classifiers. We also show that the energy consumption of these architectures, realized on the IBM chip, is typically two or more orders of magnitude lower than that of conventional digital machines implementing classifiers with comparable performance. Moreover, the spike-based dynamics display a trade-off between integration time and accuracy, which naturally translates into algorithms that can be flexibly deployed for either fast and approximate classifications, or more accurate classifications at the mere expense of longer running times and higher energy costs. This work finally proves that the neuromorphic approach can be efficiently used in real-world applications and has significant advantages over conventional digital devices when energy consumption is considered.

  8. Multi-iPPseEvo: A Multi-label Classifier for Identifying Human Phosphorylated Proteins by Incorporating Evolutionary Information into Chou's General PseAAC via Grey System Theory.

    Science.gov (United States)

    Qiu, Wang-Ren; Zheng, Quan-Shu; Sun, Bi-Qian; Xiao, Xuan

    2017-03-01

    Predicting phosphorylation protein is a challenging problem, particularly when query proteins have multi-label features meaning that they may be phosphorylated at two or more different type amino acids. In fact, human protein usually be phosphorylated at serine, threonine and tyrosine. By introducing the "multi-label learning" approach, a novel predictor has been developed that can be used to deal with the systems containing both single- and multi-label phosphorylation protein. Here we proposed a predictor called Multi-iPPseEvo by (1) incorporating the protein sequence evolutionary information into the general pseudo amino acid composition (PseAAC) via the grey system theory, (2) balancing out the skewed training datasets by the asymmetric bootstrap approach, and (3) constructing an ensemble predictor by fusing an array of individual random forest classifiers thru a voting system. Rigorous cross-validations via a set of multi-label metrics indicate that the multi-label phosphorylation predictor is very promising and encouraging. The current approach represents a new strategy to deal with the multi-label biological problems, and the software is freely available for academic use at http://www.jci-bioinfo.cn/Multi-iPPseEvo. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

  9. Learning rates in supervised and unsupervised intelligent systems

    International Nuclear Information System (INIS)

    Hora, S.C.

    1986-01-01

    Classifying observations from a mixture distribution is considered a simple model for learning. Existing results are integrated to obtain asymptotically optimal estimators of the classification rule. The asymptotic relative efficiencies show that a tutored learner is considerably more efficient on difficult problems, but only slightly more efficient on easy problems. This suggests a combined method that seeks instruction on hard cases

  10. A system for learning statistical motion patterns.

    Science.gov (United States)

    Hu, Weiming; Xiao, Xuejuan; Fu, Zhouyu; Xie, Dan; Tan, Tieniu; Maybank, Steve

    2006-09-01

    Analysis of motion patterns is an effective approach for anomaly detection and behavior prediction. Current approaches for the analysis of motion patterns depend on known scenes, where objects move in predefined ways. It is highly desirable to automatically construct object motion patterns which reflect the knowledge of the scene. In this paper, we present a system for automatically learning motion patterns for anomaly detection and behavior prediction based on a proposed algorithm for robustly tracking multiple objects. In the tracking algorithm, foreground pixels are clustered using a fast accurate fuzzy K-means algorithm. Growing and prediction of the cluster centroids of foreground pixels ensure that each cluster centroid is associated with a moving object in the scene. In the algorithm for learning motion patterns, trajectories are clustered hierarchically using spatial and temporal information and then each motion pattern is represented with a chain of Gaussian distributions. Based on the learned statistical motion patterns, statistical methods are used to detect anomalies and predict behaviors. Our system is tested using image sequences acquired, respectively, from a crowded real traffic scene and a model traffic scene. Experimental results show the robustness of the tracking algorithm, the efficiency of the algorithm for learning motion patterns, and the encouraging performance of algorithms for anomaly detection and behavior prediction.

  11. Virk: An Active Learning-based System for Bootstrapping Knowledge Base Development in the Neurosciences

    Directory of Open Access Journals (Sweden)

    Kyle H. Ambert

    2013-12-01

    Full Text Available The frequency and volume of newly-published scientific literature is quickly making manual maintenance of publicly-available databases of primary data unrealistic and costly. Although machine learning can be useful for developing automated approaches to identifying scientific publications containing relevant information for a database, developing such tools necessitates manually annotating an unrealistic number of documents. One approach to this problem, active learning, builds classification models by iteratively identifying documents that provide the most information to a classifier. Although this approach has been shown to be effective for related problems, in the context of scientific databases curation, it falls short. We present Virk, an active learning system that, while being trained, simultaneously learns a classification model and identifies documents having information of interest for a knowledge base. Our approach uses a support vector machine classifier with input features derived from neuroscience-related publications from the primary literature. Using our approach, we were able to increase the size of the Neuron Registry, a knowledge base of neuron-related information, by a factor of 90%, a knowledge base of neuron-related information, in 3 months. Using standard biocuration methods, it would have taken between 1-2 years to make the same number of contributions to the Neuron Registry. Here, we describe the system pipeline in detail, and evaluate its performance against other approaches to sampling in active learning.

  12. A support vector machine (SVM) based voltage stability classifier

    Energy Technology Data Exchange (ETDEWEB)

    Dosano, R.D.; Song, H. [Kunsan National Univ., Kunsan, Jeonbuk (Korea, Republic of); Lee, B. [Korea Univ., Seoul (Korea, Republic of)

    2007-07-01

    Power system stability has become even more complex and critical with the advent of deregulated energy markets and the growing desire to completely employ existing transmission and infrastructure. The economic pressure on electricity markets forces the operation of power systems and components to their limit of capacity and performance. System conditions can be more exposed to instability due to greater uncertainty in day to day system operations and increase in the number of potential components for system disturbances potentially resulting in voltage stability. This paper proposed a support vector machine (SVM) based power system voltage stability classifier using local measurements of voltage and active power of load. It described the procedure for fast classification of long-term voltage stability using the SVM algorithm. The application of the SVM based voltage stability classifier was presented with reference to the choice of input parameters; input data preconditioning; moving window for feature vector; determination of learning samples; and other considerations in SVM applications. The paper presented a case study with numerical examples of an 11-bus test system. The test results for the feasibility study demonstrated that the classifier could offer an excellent performance in classification with time-series measurements in terms of long-term voltage stability. 9 refs., 14 figs.

  13. Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey.

    Science.gov (United States)

    Huang, Qinghua; Zhang, Fan; Li, Xuelong

    2018-01-01

    The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.

  14. Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey

    Directory of Open Access Journals (Sweden)

    Qinghua Huang

    2018-01-01

    Full Text Available The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.

  15. Extensible Adaptive System for STEM Learning

    Science.gov (United States)

    2013-07-16

    Copyright 2013 Raytheon BBN Technologies Corp. All Rights Reserved ONR STEM Grand Challenge Extensible Adaptive System for STEM Learning ...Contract # N00014-12-C-0535 Raytheon BBN Technologies Corp. (BBN) Reference # 14217 In partial fulfillment of contract deliverable item # A001...Quarterly Progress Report #2 April 7, 2013 –July 6, 2013 Submitted July 16, 2013 BBN Technical POC: John Makhoul Raytheon BBN Technologies

  16. Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture.

    Science.gov (United States)

    Chen, C L Philip; Liu, Zhulin

    2018-01-01

    Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.

  17. Supporting Teachers in Identifying Students' Learning Styles in Learning Management Systems: An Automatic Student Modelling Approach

    Science.gov (United States)

    Graf, Sabine; Kinshuk; Liu, Tzu-Chien

    2009-01-01

    In learning management systems (LMSs), teachers have more difficulties to notice and know how individual students behave and learn in a course, compared to face-to-face education. Enabling teachers to know their students' learning styles and making students aware of their own learning styles increases teachers' and students' understanding about…

  18. Lessons learned on digital systems safety

    International Nuclear Information System (INIS)

    Sivertsen, Terje

    2005-06-01

    A decade ago, in 1994, lessons learned from Halden research activities on digital systems safety were summarized in the reports HWR-374 and HWR-375, under the title 'A Lessons Learned Report on Software Dependability'. The reports reviewed all activities made at the Halden Project in this field since 1977. As such, the reports provide a wealth of information on Halden research. At the same time, the lessons learned from the different activities are made more accessible to the reader by being summarized in terms of results, conclusions and recommendations. The present report provides a new lessons learned report, covering the Halden Project research activities in this area from 1994 to medio 2005. As before, the emphasis is on the results, conclusions and recommendations made from these activities, in particular how they can be utilized by different types of organisations, such as licensing authorities, safety assessors, power companies, and software developers. The contents of the report have been edited on the basis of input from a large number of Halden work reports, involving many different authors. Brief summaries of these reports are included in the last part of the report. (Author)

  19. A Machine Learning Approach to Automated Gait Analysis for the Noldus Catwalk System.

    Science.gov (United States)

    Frohlich, Holger; Claes, Kasper; De Wolf, Catherine; Van Damme, Xavier; Michel, Anne

    2018-05-01

    Gait analysis of animal disease models can provide valuable insights into in vivo compound effects and thus help in preclinical drug development. The purpose of this paper is to establish a computational gait analysis approach for the Noldus Catwalk system, in which footprints are automatically captured and stored. We present a - to our knowledge - first machine learning based approach for the Catwalk system, which comprises a step decomposition, definition and extraction of meaningful features, multivariate step sequence alignment, feature selection, and training of different classifiers (gradient boosting machine, random forest, and elastic net). Using animal-wise leave-one-out cross validation we demonstrate that with our method we can reliable separate movement patterns of a putative Parkinson's disease animal model and several control groups. Furthermore, we show that we can predict the time point after and the type of different brain lesions and can even forecast the brain region, where the intervention was applied. We provide an in-depth analysis of the features involved into our classifiers via statistical techniques for model interpretation. A machine learning method for automated analysis of data from the Noldus Catwalk system was established. Our works shows the ability of machine learning to discriminate pharmacologically relevant animal groups based on their walking behavior in a multivariate manner. Further interesting aspects of the approach include the ability to learn from past experiments, improve with more data arriving and to make predictions for single animals in future studies.

  20. An Architecture for Online Laboratory E-Learning System

    Science.gov (United States)

    Duan, Bing; Hosseini, Habib Mir M.; Ling, Keck Voon; Gay, Robert Kheng Leng

    2006-01-01

    Internet-based learning systems, or e-learning, are widely available in institutes, universities, and industrial companies, hosting regular or continuous education programs. The dream of teaching and learning from anywhere and at anytime becomes a reality due to the construction of e-learning infrastructure. Traditional teaching materials and…

  1. Systemic Assessment as a new tool for assessing students learning ...

    African Journals Online (AJOL)

    Systemic Assessment [SA] has been shown to be highly effective new tool in raising the level of students academic achievements, improve their ability to learn by enhancing the process of teaching and learning, and converts students from surface to deep learning. It also allow teacher to monitor students learning ...

  2. INFORMATION-ANALYTICAL LEARNING MANAGEMENT SYSTEM UNIVERSITIES

    Directory of Open Access Journals (Sweden)

    Yu. Tryus

    2016-12-01

    Full Text Available We consider conceptual approaches to creation of information systems, learning management school, which uses modern methods of decision-making and simulational modeling, web-technologies. The main criteria for the selection of development tools of the system are: openness, free of charge, easy to use and independence from system software and hardware. The chosen technology and the system itself satisfies such requirements as: focus on national and international standards in the field of higher education, adherence to service-oriented architecture, ensuring stable operation with a large number of users, support for a clear division of user rights to obtain and change information resources, software modularity the final product and its ability to integrate into the corporate information system of the university

  3. The use of hyperspectral data for tree species discrimination: Combining binary classifiers

    CSIR Research Space (South Africa)

    Dastile, X

    2010-11-01

    Full Text Available classifier Classification system 7 class 1 class 2 new sample For 5-nearest neighbour classification: assign new sample to class 1. RU SASA 2010 ? Given learning task {(x1,t1),(x 2,t2),?,(x p,tp)} (xi ? Rn feature vectors, ti ? {?1,?, ?c...). A review on the combination of binary classifiers in multiclass problems. Springer science and Business Media B.V [7] Dietterich T.G and Bakiri G.(1995). Solving Multiclass Learning Problem via Error-Correcting Output Codes. AI Access Foundation...

  4. Learning towards system innovation: Evaluating a systemic instrument

    NARCIS (Netherlands)

    Mierlo, B. van; Leeuwis, C.; Smits, R.; Klein Woolthuis, R.J.A.

    2010-01-01

    In this paper we develop an analytical framework for studying learning processes in the context of efforts to bring about system innovation by building new networks of actors who are willing to work on a change towards sustainable development. We then use it to evaluate two specific intervention

  5. A Novel Approach for Enhancing Lifelong Learning Systems by Using Hybrid Recommender System

    Science.gov (United States)

    Kardan, Ahmad A.; Speily, Omid R. B.; Modaberi, Somayyeh

    2011-01-01

    The majority of current web-based learning systems are closed learning environments where courses and learning materials are fixed, and the only dynamic aspect is the organization of the material that can be adapted to allow a relatively individualized learning environment. In this paper, we propose an evolving web-based learning system which can…

  6. Classifying Adverse Events in the Dental Office.

    Science.gov (United States)

    Kalenderian, Elsbeth; Obadan-Udoh, Enihomo; Maramaldi, Peter; Etolue, Jini; Yansane, Alfa; Stewart, Denice; White, Joel; Vaderhobli, Ram; Kent, Karla; Hebballi, Nutan B; Delattre, Veronique; Kahn, Maria; Tokede, Oluwabunmi; Ramoni, Rachel B; Walji, Muhammad F

    2017-06-30

    Dentists strive to provide safe and effective oral healthcare. However, some patients may encounter an adverse event (AE) defined as "unnecessary harm due to dental treatment." In this research, we propose and evaluate two systems for categorizing the type and severity of AEs encountered at the dental office. Several existing medical AE type and severity classification systems were reviewed and adapted for dentistry. Using data collected in previous work, two initial dental AE type and severity classification systems were developed. Eight independent reviewers performed focused chart reviews, and AEs identified were used to evaluate and modify these newly developed classifications. A total of 958 charts were independently reviewed. Among the reviewed charts, 118 prospective AEs were found and 101 (85.6%) were verified as AEs through a consensus process. At the end of the study, a final AE type classification comprising 12 categories, and an AE severity classification comprising 7 categories emerged. Pain and infection were the most common AE types representing 73% of the cases reviewed (56% and 17%, respectively) and 88% were found to cause temporary, moderate to severe harm to the patient. Adverse events found during the chart review process were successfully classified using the novel dental AE type and severity classifications. Understanding the type of AEs and their severity are important steps if we are to learn from and prevent patient harm in the dental office.

  7. A Temporal Mining Framework for Classifying Un-Evenly Spaced Clinical Data: An Approach for Building Effective Clinical Decision-Making System.

    Science.gov (United States)

    Jane, Nancy Yesudhas; Nehemiah, Khanna Harichandran; Arputharaj, Kannan

    2016-01-01

    Clinical time-series data acquired from electronic health records (EHR) are liable to temporal complexities such as irregular observations, missing values and time constrained attributes that make the knowledge discovery process challenging. This paper presents a temporal rough set induced neuro-fuzzy (TRiNF) mining framework that handles these complexities and builds an effective clinical decision-making system. TRiNF provides two functionalities namely temporal data acquisition (TDA) and temporal classification. In TDA, a time-series forecasting model is constructed by adopting an improved double exponential smoothing method. The forecasting model is used in missing value imputation and temporal pattern extraction. The relevant attributes are selected using a temporal pattern based rough set approach. In temporal classification, a classification model is built with the selected attributes using a temporal pattern induced neuro-fuzzy classifier. For experimentation, this work uses two clinical time series dataset of hepatitis and thrombosis patients. The experimental result shows that with the proposed TRiNF framework, there is a significant reduction in the error rate, thereby obtaining the classification accuracy on an average of 92.59% for hepatitis and 91.69% for thrombosis dataset. The obtained classification results prove the efficiency of the proposed framework in terms of its improved classification accuracy.

  8. A Studi on High Plant Systems Course with Active Learning in Higher Education Through Outdoor Learning to Increase Student Learning Activities

    OpenAIRE

    Nur Rokhimah Hanik, Anwari Adi Nugroho

    2015-01-01

    Biology learning especially high plant system courses needs to be applied to active learning centered on the student (Active Learning In Higher Education) to enhance the students' learning activities so that the quality of learning for the better. Outdoor Learning is one of the active learning invites students to learn outside of the classroom by exploring the surrounding environment. This research aims to improve the students' learning activities in the course of high plant systems through t...

  9. Harnessing the Power of Learning Management Systems: An E-Learning Approach for Professional Development.

    Science.gov (United States)

    White, Meagan; Shellenbarger, Teresa

    E-learning provides an alternative approach to traditional professional development activities. A learning management system may help nursing professional development practitioners deliver content more efficiently and effectively; however, careful consideration is needed during planning and implementation. This article provides essential information in the selection and use of a learning management system for professional development.

  10. Resolving the Problem of Intelligent Learning Content in Learning Management Systems

    Science.gov (United States)

    Rey-Lopez, Marta; Brusilovsky, Peter; Meccawy, Maram; Diaz-Redondo, Rebeca; Fernandez-Vilas, Ana; Ashman, Helen

    2008-01-01

    Current e-learning standardization initiatives have put much effort into easing interoperability between systems and the reusability of contents. For this to be possible, one of the most relevant areas is the definition of a run-time environment, which allows Learning Management Systems to launch, track and communicate with learning objects.…

  11. Cultural impacts on e-learning systems' success

    OpenAIRE

    Aparicio, M.; Bação, F.; Oliveira, T.

    2016-01-01

    WOS:000383295100007 (Nº de Acesso Web of Science) E-learning systems are enablers in the learning process, strengthening their importance as part of the educational strategy. Understanding the determinants of e-learning success is crucial for defining instructional strategies. Several authors have studied e-learning implementation and adoption, and various studies have addressed e-learning success from different perspectives. However, none of these studies have verified whether students' c...

  12. Framework for Designing Context-Aware Learning Systems

    Science.gov (United States)

    Tortorella, Richard A. W.; Kinshuk; Chen, Nian-Shing

    2018-01-01

    Today people learn in many diverse locations and contexts, beyond the confines of classical brick and mortar classrooms. This trend is ever increasing, progressing hand-in-hand with the progress of technology. Context-aware learning systems are systems which adapt to the learner's context, providing tailored learning for a particular learning…

  13. An Intelligent Computer Assisted Language Learning System for Arabic Learners

    Science.gov (United States)

    Shaalan, Khaled F.

    2005-01-01

    This paper describes the development of an intelligent computer-assisted language learning (ICALL) system for learning Arabic. This system could be used for learning Arabic by students at primary schools or by learners of Arabic as a second or foreign language. It explores the use of Natural Language Processing (NLP) techniques for learning…

  14. Which Recommender System Can Best Fit Social Learning Platforms?

    NARCIS (Netherlands)

    Fazeli, Soude; Loni, Babak; Drachsler, Hendrik; Sloep, Peter

    2014-01-01

    This study aims to develop a recommender system for social learning platforms that combine traditional learning management systems with commercial social networks like Facebook. We therefore take into account social interactions of users to make recommendations on learning resources. We propose to

  15. Digital case-based learning system in school.

    Science.gov (United States)

    Gu, Peipei; Guo, Jiayang

    2017-01-01

    With the continuing growth of multi-media learning resources, it is important to offer methods helping learners to explore and acquire relevant learning information effectively. As services that organize multi-media learning materials together to support programming learning, the digital case-based learning system is needed. In order to create a case-oriented e-learning system, this paper concentrates on the digital case study of multi-media resources and learning processes with an integrated framework. An integration of multi-media resources, testing and learning strategies recommendation as the learning unit is proposed in the digital case-based learning framework. The learning mechanism of learning guidance, multi-media materials learning and testing feedback is supported in our project. An improved personalized genetic algorithm which incorporates preference information and usage degree into the crossover and mutation process is proposed to assemble the personalized test sheet for each learner. A learning strategies recommendation solution is proposed to recommend learning strategies for learners to help them to learn. The experiments are conducted to prove that the proposed approaches are capable of constructing personalized sheets and the effectiveness of the framework.

  16. Digital case-based learning system in school.

    Directory of Open Access Journals (Sweden)

    Peipei Gu

    Full Text Available With the continuing growth of multi-media learning resources, it is important to offer methods helping learners to explore and acquire relevant learning information effectively. As services that organize multi-media learning materials together to support programming learning, the digital case-based learning system is needed. In order to create a case-oriented e-learning system, this paper concentrates on the digital case study of multi-media resources and learning processes with an integrated framework. An integration of multi-media resources, testing and learning strategies recommendation as the learning unit is proposed in the digital case-based learning framework. The learning mechanism of learning guidance, multi-media materials learning and testing feedback is supported in our project. An improved personalized genetic algorithm which incorporates preference information and usage degree into the crossover and mutation process is proposed to assemble the personalized test sheet for each learner. A learning strategies recommendation solution is proposed to recommend learning strategies for learners to help them to learn. The experiments are conducted to prove that the proposed approaches are capable of constructing personalized sheets and the effectiveness of the framework.

  17. A Web-Based Learning Support System for Inquiry-Based Learning

    Science.gov (United States)

    Kim, Dong Won; Yao, Jingtao

    The emergence of the Internet and Web technology makes it possible to implement the ideals of inquiry-based learning, in which students seek truth, information, or knowledge by questioning. Web-based learning support systems can provide a good framework for inquiry-based learning. This article presents a study on a Web-based learning support system called Online Treasure Hunt. The Web-based learning support system mainly consists of a teaching support subsystem, a learning support subsystem, and a treasure hunt game. The teaching support subsystem allows instructors to design their own inquiry-based learning environments. The learning support subsystem supports students' inquiry activities. The treasure hunt game enables students to investigate new knowledge, develop ideas, and review their findings. Online Treasure Hunt complies with a treasure hunt model. The treasure hunt model formalizes a general treasure hunt game to contain the learning strategies of inquiry-based learning. This Web-based learning support system empowered with the online-learning game and founded on the sound learning strategies furnishes students with the interactive and collaborative student-centered learning environment.

  18. A Teaching System To Learn Programming: the Programmer's Learning Machine

    OpenAIRE

    Quinson , Martin; Oster , Gérald

    2015-01-01

    International audience; The Programmer's Learning Machine (PLM) is an interactive exerciser for learning programming and algorithms. Using an integrated and graphical environment that provides a short feedback loop, it allows students to learn in a (semi)-autonomous way. This generic platform also enables teachers to create specific programming microworlds that match their teaching goals. This paper discusses our design goals and motivations, introduces the existing material and the proposed ...

  19. Towards an intelligent learning management system under blended learning trends, profiles and modeling perspectives

    CERN Document Server

    Dias, Sofia B; Hadjileontiadis, Leontios J

    2013-01-01

    This book offers useful information that evokes initiatives towards rethinking of the value, efficiency, inclusiveness, effectiveness and personalization of the intelligent learning management systems-based blended-learning environment.

  20. Intelligent data analysis for e-learning enhancing security and trustworthiness in online learning systems

    CERN Document Server

    Miguel, Jorge; Xhafa, Fatos

    2016-01-01

    Intelligent Data Analysis for e-Learning: Enhancing Security and Trustworthiness in Online Learning Systems addresses information security within e-Learning based on trustworthiness assessment and prediction. Over the past decade, many learning management systems have appeared in the education market. Security in these systems is essential for protecting against unfair and dishonest conduct-most notably cheating-however, e-Learning services are often designed and implemented without considering security requirements. This book provides functional approaches of trustworthiness analysis, modeling, assessment, and prediction for stronger security and support in online learning, highlighting the security deficiencies found in most online collaborative learning systems. The book explores trustworthiness methodologies based on collective intelligence than can overcome these deficiencies. It examines trustworthiness analysis that utilizes the large amounts of data-learning activities generate. In addition, as proc...

  1. Differentiation of Enhancing Glioma and Primary Central Nervous System Lymphoma by Texture-Based Machine Learning.

    Science.gov (United States)

    Alcaide-Leon, P; Dufort, P; Geraldo, A F; Alshafai, L; Maralani, P J; Spears, J; Bharatha, A

    2017-06-01

    Accurate preoperative differentiation of primary central nervous system lymphoma and enhancing glioma is essential to avoid unnecessary neurosurgical resection in patients with primary central nervous system lymphoma. The purpose of the study was to evaluate the diagnostic performance of a machine-learning algorithm by using texture analysis of contrast-enhanced T1-weighted images for differentiation of primary central nervous system lymphoma and enhancing glioma. Seventy-one adult patients with enhancing gliomas and 35 adult patients with primary central nervous system lymphomas were included. The tumors were manually contoured on contrast-enhanced T1WI, and the resulting volumes of interest were mined for textural features and subjected to a support vector machine-based machine-learning protocol. Three readers classified the tumors independently on contrast-enhanced T1WI. Areas under the receiver operating characteristic curves were estimated for each reader and for the support vector machine classifier. A noninferiority test for diagnostic accuracy based on paired areas under the receiver operating characteristic curve was performed with a noninferiority margin of 0.15. The mean areas under the receiver operating characteristic curve were 0.877 (95% CI, 0.798-0.955) for the support vector machine classifier; 0.878 (95% CI, 0.807-0.949) for reader 1; 0.899 (95% CI, 0.833-0.966) for reader 2; and 0.845 (95% CI, 0.757-0.933) for reader 3. The mean area under the receiver operating characteristic curve of the support vector machine classifier was significantly noninferior to the mean area under the curve of reader 1 ( P = .021), reader 2 ( P = .035), and reader 3 ( P = .007). Support vector machine classification based on textural features of contrast-enhanced T1WI is noninferior to expert human evaluation in the differentiation of primary central nervous system lymphoma and enhancing glioma. © 2017 by American Journal of Neuroradiology.

  2. Cognitive Models for Learning to Control Dynamic Systems

    National Research Council Canada - National Science Library

    Eberhart, Russ; Hu, Xiaohui; Chen, Yaobin

    2008-01-01

    Report developed under STTR contract for topic "Cognitive models for learning to control dynamic systems" demonstrated a swarm intelligence learning algorithm and its application in unmanned aerial vehicle (UAV) mission planning...

  3. Introduction of a learning management system at the Kilimanjaro ...

    African Journals Online (AJOL)

    Background. Medical schools in Africa face daunting challenges including faculty shortages, growing class sizes, and inadequate resources. Learning management systems (LMS) may be powerful tools for organising and presenting curricular learning materials, with the potential for monitoring and evaluation functions.

  4. Computation in the Learning System of Cephalopods.

    Science.gov (United States)

    Young, J Z

    1991-04-01

    The memory mechanisms of cephalopods consist of a series of matrices of intersecting axes, which find associations between the signals of input events and their consequences. The tactile memory is distributed among eight such matrices, and there is also some suboesophageal learning capacity. The visual memory lies in the optic lobe and four matrices, with some re-exciting pathways. In both systems, damage to any part reduces proportionally the effectiveness of the whole memory. These matrices are somewhat like those in mammals, for instance those in the hippocampus. The first matrix in both visual and tactile systems receives signals of vision and taste, and its output serves to increase the tendency to attack or to take with the arms. The second matrix provides for the correlation of groups of signals on its neurons, which pass signals to the third matrix. Here large cells find clusters in the sets of signals. Their output re-excites those of the first lobe, unless pain occurs. In that case, this set of cells provides a record that ensures retreat. There is experimental evidence that these distributed memory systems allow for the identification of categories of visual and tactile inputs, for generalization, and for decision on appropriate behavior in the light of experience. The evidence suggests that learning in cephalopods is not localized to certain layers or "grandmother cells" but is distributed with high redundance in serial networks, with recurrent circuits.

  5. Classifier fusion for VoIP attacks classification

    Science.gov (United States)

    Safarik, Jakub; Rezac, Filip

    2017-05-01

    SIP is one of the most successful protocols in the field of IP telephony communication. It establishes and manages VoIP calls. As the number of SIP implementation rises, we can expect a higher number of attacks on the communication system in the near future. This work aims at malicious SIP traffic classification. A number of various machine learning algorithms have been developed for attack classification. The paper presents a comparison of current research and the use of classifier fusion method leading to a potential decrease in classification error rate. Use of classifier combination makes a more robust solution without difficulties that may affect single algorithms. Different voting schemes, combination rules, and classifiers are discussed to improve the overall performance. All classifiers have been trained on real malicious traffic. The concept of traffic monitoring depends on the network of honeypot nodes. These honeypots run in several networks spread in different locations. Separation of honeypots allows us to gain an independent and trustworthy attack information.

  6. An ensemble self-training protein interaction article classifier.

    Science.gov (United States)

    Chen, Yifei; Hou, Ping; Manderick, Bernard

    2014-01-01

    Protein-protein interaction (PPI) is essential to understand the fundamental processes governing cell biology. The mining and curation of PPI knowledge are critical for analyzing proteomics data. Hence it is desired to classify articles PPI-related or not automatically. In order to build interaction article classification systems, an annotated corpus is needed. However, it is usually the case that only a small number of labeled articles can be obtained manually. Meanwhile, a large number of unlabeled articles are available. By combining ensemble learning and semi-supervised self-training, an ensemble self-training interaction classifier called EST_IACer is designed to classify PPI-related articles based on a small number of labeled articles and a large number of unlabeled articles. A biological background based feature weighting strategy is extended using the category information from both labeled and unlabeled data. Moreover, a heuristic constraint is put forward to select optimal instances from unlabeled data to improve the performance further. Experiment results show that the EST_IACer can classify the PPI related articles effectively and efficiently.

  7. Adaptive Hypermedia Systems for E-Learning

    Directory of Open Access Journals (Sweden)

    Aammou Souhaib

    2010-11-01

    Full Text Available The domain of traditional hypermedia is revolutionized by the arrival of the concept of adaptation. Currently the domain of Adaptive Hypermedia Systems (AHS is constantly growing. A major goal of current research is to provide a personalized educational experience that meets the needs specific to each learner (knowledge level, goals, motivation etc.... In this article we have studied the possibility of implementing traditional features of adaptive hypermedia in an open environment, and discussed the standards for describing learning objects and architectural models based on the use of ontologies as a prerequisite for such an adaptation.

  8. System of Consciousness Contextual as Learning Support

    Directory of Open Access Journals (Sweden)

    Jorge Eliseo Gómez Gómez

    2016-08-01

    Full Text Available With the inclusion of ubiquitous computing in education, it is intended that the student is an active agent in its formation process and interacts with its context. This paper presents the design and implementation of architecture for ubiquitous learning environments in which they integrate physical spaces with applications which are then executed by users. The system supports objects augmented with RFID tags, NFC and QR Code. Each tag contains data that uniquely identifies the resource. To validate the proposed architecture is developed experimentally tested a prototype at the end of it is done to verify that the proposed architecture improves the academic performance of students.

  9. Recommender systems for technology enhanced learning research trends and applications

    CERN Document Server

    Manouselis, Nikos; Verbert, Katrien

    2014-01-01

    Presents cutting edge research from leading experts in the growing field of Recommender Systems for Technology Enhanced Learning (RecSys TEL) International contributions are included to demonstrate the merging of various efforts and communities Topics include: Linked Data and the Social Web as Facilitators for TEL Recommender Systems in Research and Practice, Personalised Learning-Plan Recommendations in Game-Based Learning and Recommendations from Heterogeneous Sources in a Technology Enhanced Learning Ecosystem

  10. The Office Software Learning and Examination System Design Based on Fragmented Learning Idea

    Directory of Open Access Journals (Sweden)

    Xu Ling

    2016-01-01

    Full Text Available Fragmented learning is that through the segmentation of learning content or learning time, make learners can use the fragmented time for learning fragmentated content, have the characteristics of time flexibility, learning targeted and high learning efficiency. Based on the fragmented learning ideas, combined with the teaching idea of micro class and interactive teaching, comprehensive utilization of flash animation design software, .NET development platform, VSTO technology, multimedia development technology and so on, design and develop a system integrated with learning, practice and examination of the Office software, which is not only conducive to the effective and personalized learning of students, but also conducive to the understanding the students’ situation of teachers, and liberate teachers from the heavy labor of mechanical, focus on promoting the formation of students’ knowledge system.

  11. Application of a naive Bayesians classifiers in assessing the supplier

    Directory of Open Access Journals (Sweden)

    Mijailović Snežana

    2017-01-01

    Full Text Available The paper considers the class of interactive knowledge based systems whose main purpose of making proposals and assisting customers in making decisions. The mathematical model provides a set of examples of learning about the delivered series of outflows from three suppliers, as well as an analysis of an illustrative example for assessing the supplier using a naive Bayesian classifier. The model was developed on the basis of the analysis of subjective probabilities, which are later revised with the help of new empirical information and Bayesian theorem on a posterior probability, i.e. combining of subjective and objective conditional probabilities in the choice of a reliable supplier.

  12. STRATEGY FOR EVALUATION AND SELECTION OF SYSTEMS FOR ELECTRONIC LEARNING

    OpenAIRE

    Dubravka Mandušić; Lucija Blašković

    2012-01-01

    Today`s technology supported and accelerated learning time requires constant and continuous acquisition of new knowledge. On the other hand, it does not leave enough time for additional education. Increasing number of E-learning systems, withdraws a need for precise evaluation of functionality that those systems provide; so they could be reciprocally compared. While implementing new systems for electronic learning, it is very important to pre-evaluate existing systems in order to ...

  13. Development of a Relational Database for Learning Management Systems

    Science.gov (United States)

    Deperlioglu, Omer; Sarpkaya, Yilmaz; Ergun, Ertugrul

    2011-01-01

    In today's world, Web-Based Distance Education Systems have a great importance. Web-based Distance Education Systems are usually known as Learning Management Systems (LMS). In this article, a database design, which was developed to create an educational institution as a Learning Management System, is described. In this sense, developed Learning…

  14. Adaptive Learning Systems: Beyond Teaching Machines

    Science.gov (United States)

    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…

  15. Sensorimotor learning configures the human mirror system.

    Science.gov (United States)

    Catmur, Caroline; Walsh, Vincent; Heyes, Cecilia

    2007-09-04

    Cells in the "mirror system" fire not only when an individual performs an action but also when one observes the same action performed by another agent [1-4]. The mirror system, found in premotor and parietal cortices of human and monkey brains, is thought to provide the foundation for social understanding and to enable the development of theory of mind and language [5-9]. However, it is unclear how mirror neurons acquire their mirror properties -- how they derive the information necessary to match observed with executed actions [10]. We address this by showing that it is possible to manipulate the selectivity of the human mirror system, and thereby make it operate as a countermirror system, by giving participants training to perform one action while observing another. Before this training, participants showed event-related muscle-specific responses to transcranial magnetic stimulation over motor cortex during observation of little- and index-finger movements [11-13]. After training, this normal mirror effect was reversed. These results indicate that the mirror properties of the mirror system are neither wholly innate [14] nor fixed once acquired; instead they develop through sensorimotor learning [15, 16]. Our findings indicate that the human mirror system is, to some extent, both a product and a process of social interaction.

  16. Learning modalities in artificial intelligence systems: a framework and review

    Energy Technology Data Exchange (ETDEWEB)

    Araya, A A

    1982-01-01

    Intelligent systems should possess two fundamental capabilities: problem solving and learning. Problem solving capabilities allow an intelligent system to cope with problems in a given domain. Learning capabilities make possible for an intelligent system to improve the solution to the problems within its current reach or to cope with new problems. This paper examines research in artificial intelligence from the perspective of learning with the purpose of: 1) developing and understanding of the problem of learning from the AI point of view, and II) characterizing the current state of the art on learning in AI. 35 references.

  17. Classifying Planets: Nature vs. Nurture

    Science.gov (United States)

    Beichman, Charles A.

    2009-05-01

    The idea of a planet was so simple when we learned about the solar system in elementary school. Now students and professional s alike are faced with confusing array of definitions --- from "Brown Dwarfs” to "Super Jupiters", from "Super Earths” to "Terrestrial Planets", and from "Planets” to "Small, Sort-of Round Things That Aren't Really Planets". I will discuss how planets might be defined by how they formed, where they are found, or by the life they might support.

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

    Science.gov (United States)

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

    2018-01-01

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

  19. Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features.

    Science.gov (United States)

    Zhang, Xin; Yan, Lin-Feng; Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

    2017-07-18

    Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

  20. A new system to reduce formaldehyde levels improves safety conditions during gross veterinary anatomy learning.

    Science.gov (United States)

    Nacher, Víctor; Llombart, Cristina; Carretero, Ana; Navarro, Marc; Ysern, Pere; Calero, Sebastián; Fígols, Enric; Ruberte, Jesús

    2007-01-01

    Dissection is a very useful method of learning veterinary anatomy. However, formaldehyde, which is widely used to preserve cadavers, is an irritant, and it has recently been classified as a carcinogen. In 1997, the Instituto Nacional de Seguridad e Higiene en el Trabajo [National Institute of Workplace Security and Hygiene] found that the levels of formaldehyde in our dissection room were above the threshold limit values. Unfortunately, no optimal substitute for formaldehyde is currently available. Therefore, we designed a new ventilation system that combines slow propulsion of fresh air from above the dissection table and rapid aspiration of polluted air from the perimeter. Formaldehyde measurements performed in 2004, after the introduction of this new system into our dissection laboratory, showed a dramatic reduction (about tenfold, or 0.03 ppm). A suitable propelling/aspirating air system successfully reduces the concentration of formaldehyde in the dissection room, significantly improving safety conditions for students, instructors, and technical staff during gross anatomy learning.

  1. Learning Analytics for Supporting Seamless Language Learning Using E-Book with Ubiquitous Learning System

    Science.gov (United States)

    Mouri, Kousuke; Uosaki, Noriko; Ogata, Hiroaki

    2018-01-01

    Seamless learning has been recognized as an effective learning approach across various dimensions including formal and informal learning contexts, individual and social learning, and physical world and cyberspace. With the emergence of seamless learning, the majority of the current research focuses on realizing a seamless learning environment at…

  2. Adaptive E- Learning System Based on Personalized Learning Style

    African Journals Online (AJOL)

    pc

    2018-03-05

    Mar 5, 2018 ... motivation to this research is to improve the learner performance and achieve the ... valuable factor for enhancing learning process by adopting an effective .... Video. Reflective Intuitive. Primer Test. Verbal Sequential. Tutorial.

  3. Learning to Support Learning Together: An Experience with the Soft Systems Methodology

    Science.gov (United States)

    Sanchez, Adolfo; Mejia, Andres

    2008-01-01

    An action research approach called soft systems methodology (SSM) was used to foster organisational learning in a school regarding the role of the learning support department within the school and its relation with the normal teaching-learning activities. From an initial situation of lack of coordination as well as mutual misunderstanding and…

  4. Courseware Development with Animated Pedagogical Agents in Learning System to Improve Learning Motivation

    Science.gov (United States)

    Chin, Kai-Yi; Hong, Zeng-Wei; Huang, Yueh-Min; Shen, Wei-Wei; Lin, Jim-Min

    2016-01-01

    The addition of animated pedagogical agents (APAs) in computer-assisted learning (CAL) systems could successfully enhance students' learning motivation and engagement in learning activities. Conventionally, the APA incorporated multimedia materials are constructed through the cooperation of teachers and software programmers. However, the thinking…

  5. The Impacts of System and Human Factors on Online Learning Systems Use and Learner Satisfaction

    Science.gov (United States)

    Alshare, Khaled A.; Freeze, Ronald D.; Lane, Peggy L.; Wen, H. Joseph

    2011-01-01

    Success in an online learning environment is tied to both human and system factors. This study illuminates the unique contributions of human factors (comfort with online learning, self-management of learning, and perceived Web self-efficacy) to online learning system success, which is measured in terms of usage and satisfaction. The research model…

  6. DIDACTIC ENGINEERING: DESIGNING NEW GENERATION LEARNING SYSTEMS

    Directory of Open Access Journals (Sweden)

    Nail K. Nuriyev

    2016-09-01

    Full Text Available Introduction: the article deals with the organisation of training activities in the man-made environment. Didactic engineering is seen as a methodology within which problems of didactics are solved with application of pedagogical, psychological, engineering methods. It is obvious that in order to implement the training of future engineers in a competence-based format (according to educational standard a new type of teaching system is needed, with new capacities (properties. These systems should set each student towards the development of professionally significant (key abilities, taking into account his/her psychological characteristics; ensure training on the verge of permissible difficulties (developing training, and thereby achieve rapid development of key skills, through his/her zone of “immediate development”; to diagnose the quality of possession of a competence in the academic sense. For the objectivity and reliability of assessment of the level and depth of learned knowledge it is necessary to generate this evaluation in a metric format. As a result, we created a didactic system, which combines all the listed properties and the properties of classical systems. This allowed us to construct a new generation of didactic systems. Materials and Methods: the research is based on a systematic analysis of the activity of an engineer; on models of “zones of immediate development” by L. S. Vygotsky; on “developmental education” by L. N. Zankova; on the use of pedagogical and psychological patterns as well as taxonomic methods, didactic engineering, theory of probability and mathematical statistics. Results: constructed is a model for training engineers in the metric format of competence, which envisages a rapid development of students project and constructive abilit ies based on their knowledge learned. Discussion and Conclusions: the parameters defining the probability of engineer’s success have been described; the taxonomic scale

  7. Inclusive E-Learning - Towards an Integrated System Design.

    Science.gov (United States)

    Patzer, Yasmin; Pinkwart, Niels

    2017-01-01

    At first sight there seem to be issues combining technical accessibility guidelines and educational needs when designing inclusive E-Learning. Furthermore Universal Design for Learning seems to contradict individualization. In this paper we address both issues with an inclusive E-Learning design for the LAYA system, which targets disabled and non-disabled learners.

  8. Collaborative Learning in Advanced Supply Systems: The KLASS Pilot Project.

    Science.gov (United States)

    Rhodes, Ed; Carter, Ruth

    2003-01-01

    The Knowledge and Learning in Advanced Supply Systems (KLASS) project developed collaborative learning networks of suppliers in the British automotive and aerospace industries. Methods included face-to-face and distance learning, work toward National Vocational Qualifications, and diagnostic workshops for senior managers on improving quality,…

  9. Collaborative Learning Framework in Business Management Systems

    Directory of Open Access Journals (Sweden)

    Vladimir GRIGORE

    2008-01-01

    Full Text Available This paper presents a solution based on collaboration with experts and practitioner from university and ERP companies involved in process learning by training and learning by working. The solution uses CPI test to establish proper team for framework modules: Real-Time Chat Room, Discussion Forum, E-mail Support and Learning through Training. We define novice, practitioner and expert competence level based on CORONET train methodology. ERP companies have own roles for mentoring services to knowledge workers and evaluate the performance of learning process with teachers’ cooperation in learning by teaching and learning by working module.

  10. White blood cells identification system based on convolutional deep neural learning networks.

    Science.gov (United States)

    Shahin, A I; Guo, Yanhui; Amin, K M; Sharawi, Amr A

    2017-11-16

    White blood cells (WBCs) differential counting yields valued information about human health and disease. The current developed automated cell morphology equipments perform differential count which is based on blood smear image analysis. Previous identification systems for WBCs consist of successive dependent stages; pre-processing, segmentation, feature extraction, feature selection, and classification. There is a real need to employ deep learning methodologies so that the performance of previous WBCs identification systems can be increased. Classifying small limited datasets through deep learning systems is a major challenge and should be investigated. In this paper, we propose a novel identification system for WBCs based on deep convolutional neural networks. Two methodologies based on transfer learning are followed: transfer learning based on deep activation features and fine-tuning of existed deep networks. Deep acrivation featues are extracted from several pre-trained networks and employed in a traditional identification system. Moreover, a novel end-to-end convolutional deep architecture called "WBCsNet" is proposed and built from scratch. Finally, a limited balanced WBCs dataset classification is performed through the WBCsNet as a pre-trained network. During our experiments, three different public WBCs datasets (2551 images) have been used which contain 5 healthy WBCs types. The overall system accuracy achieved by the proposed WBCsNet is (96.1%) which is more than different transfer learning approaches or even the previous traditional identification system. We also present features visualization for the WBCsNet activation which reflects higher response than the pre-trained activated one. a novel WBCs identification system based on deep learning theory is proposed and a high performance WBCsNet can be employed as a pre-trained network. Copyright © 2017. Published by Elsevier B.V.

  11. Intelligent e-Learning Systems: An Educational Paradigm Shift

    Directory of Open Access Journals (Sweden)

    Suman Bhattacharya

    2016-12-01

    Full Text Available Learning is the long process of transforming information as well as experience into knowledge, skills, attitude and behaviors. To make up the wide gap between the demand of increasing higher education and comparatively limited resources, more and more educational institutes are looking into instructional technology. Use of online resources not only reduces the cost of education but also meet the needs of society. Intelligent e-learning has become one of the important channels to reach out to students exceeding geographic boundaries. Besides this, the characteristics of e-learning have complicated the process of education, and have brought challenges to both instructors and students. This paper will focus on the discussion of different discipline of intelligent e-learning like scaffolding based e-learning, personalized e-learning, confidence based e-learning, intelligent tutoring system, etc. to illuminate the educational paradigm shift in intelligent e-learning system.

  12. System Quality Characteristics for Selecting Mobile Learning Applications

    Directory of Open Access Journals (Sweden)

    Mohamed SARRAB

    2015-10-01

    Full Text Available The majority of M-learning (Mobile learning applications available today are developed for the formal learning and education environment. These applications are characterized by the improvement in the interaction between learners and instructors to provide high interaction and flexibility to the learning process. M-learning is gaining increased recognition and adoption by different organizations. With the high number of M-learning applications available today, making the right decision about which, application to choose can be quite challenging. To date there is no complete and well defined set of system characteristics for such M-learning applications. This paper presents system quality characteristics for selecting M-learning applications based on the result of a systematic review conducted in this domain.

  13. Teach Them How They Learn: Learning Styles and Information Systems Education

    Science.gov (United States)

    Cegielski, Casey G.; Hazen, Benjamin T.; Rainer, R. Kelly

    2011-01-01

    The rich, interdisciplinary tradition of learning styles is markedly absent in information systems-related research. The current study applies the framework of learning styles to a common educational component of many of today's information systems curricula--object-oriented systems development--in an effort to answer the question as to whether…

  14. The Development of Inquiry Learning Materials to Complete Content Life System Organization in Junior High School Students

    Science.gov (United States)

    Mayasari, F.; Raharjo; Supardi, Z. A. I.

    2018-01-01

    This research aims to develop the material eligibility to complete the inquiry learning of student in the material organization system of junior high school students. Learning materials developed include syllabi, lesson plans, students’ textbook, worksheets, and learning achievement test. This research is the developmental research which employ Dick and Carey model to develop learning material. The experiment was done in Junior High School 4 Lamongan regency using One Group Pretest-Posttest Design. The data collection used validation, observation, achievement test, questionnaire administration, and documentation. Data analysis techniques used quantitative and qualitative descriptive.The results showed that the developed learning material was valid and can be used. Learning activity accomplished with good category, where student activities were observed. The aspects of attitudes were observed during the learning process are honest, responsible, and confident. Student learning achievement gained an average of 81, 85 in complete category, with N-Gain 0, 75 for a high category. The activities and student response to learning was very well categorized. Based on the results, this researcher concluded that the device classified as feasible of inquiry-based learning (valid, practical, and effective) system used on the material organization of junior high school students.

  15. Evaluating Recommender Systems for Technology Enhanced Learning: A Quantitative Survey

    Science.gov (United States)

    Erdt, Mojisola; Fernandez, Alejandro; Rensing, Christoph

    2015-01-01

    The increasing number of publications on recommender systems for Technology Enhanced Learning (TEL) evidence a growing interest in their development and deployment. In order to support learning, recommender systems for TEL need to consider specific requirements, which differ from the requirements for recommender systems in other domains like…

  16. A Simple and Effective Remedial Learning System with a Fuzzy Expert System

    Science.gov (United States)

    Lin, C.-C.; Guo, K.-H.; Lin, Y.-C.

    2016-01-01

    This study aims at implementing a simple and effective remedial learning system. Based on fuzzy inference, a remedial learning material selection system is proposed for a digital logic course. Two learning concepts of the course have been used in the proposed system: number systems and combinational logic. We conducted an experiment to validate…

  17. MOODLE – COMPUTERIZED DISTANT LEARNING SUPPORT SYSTEM

    Directory of Open Access Journals (Sweden)

    V. A. Tunda

    2014-01-01

    Full Text Available Moodle (Modular Object-Oriented Dynamic Learning Environment is the system developed by the English-speaking community around the world for more than 10 years, supports both, offline and online training. In most cases, Moodle is used to support and connect learning face-to-face with online training, as well as with other types of learning. Moodle allows you to ask all sorts of questions and assess responses in a variety of ways. The central concept of Moodle is a course in which one or more teachers offer students resources (such as files, folders, Web pages and participate in interactive activities (such as forums, wikis, blogging, lessons, seminars, assignments, examinations. Students and teachers can change roles, mutually assess each other, share knowledge on the topics of study in the glossary and database system.In the English-speaking world, there are public sites with detailed documentation on Moodle, which is constantly verified and modified in accordance with emerging new versions of the system; Russian versions do not have public sites with detailed translation of the English-language documentation. On what and to whom you want to perform actions in the daily practice of the modern versions, only the barest of outlines on paid seminars and presentations to those who started the implementation of Moodle in your organization are given. And this despite the fact that the system has a great variety of Moodle (over 500 settings with different levels of functionality to be performed, to maintain and develop specially organized by the team of specialists. The question is not only about creating a training course in Moodle. It's about maintaining the health of the system within the institution, such as a University. Under the "health maintenance" means: availability and preservation of up-to-date documentation on system and manuals on Moodle separately for administrators, managers, teachers and students at their level, training consultants

  18. The Role of a Commander in Military Lessons Learned Systems

    Directory of Open Access Journals (Sweden)

    Zenon Waliński

    2015-06-01

    Full Text Available The aim of the paper is to investigate the role of a commander in military Lessons Learned systems. In order to achieve the aim, the paper presents (1 the architecture of the Lessons Learned capabilities in the U.S. Army, NATO and the Polish Armed Forces, (2 the commander’s role in the Lessons Learned process (3 the commander’s role in fostering Lessons Learned organisation culture. The paper is based on multiple case study analysis including Lessons Learned systems in NATO, the U.S. Army and the Polish Armed Forces.

  19. Intensitas Perilaku Pengguna E-learning System dengan Model Utaut

    OpenAIRE

    Sari, Fatma; Purnamasari, Susan Dian

    2013-01-01

    This study aims to determine behavioral intention in the use of e-learning system using models UTAUT. The phenomenon underlying the research is: It is not yet optimal use of e-learning by students information systems in the learning process, not yet optimal socialization of the existence of e-learning, so that is not maximized and yet utilization measurability of the impact of using e-learning for lecturers.This study is limited in its scope: analysis of the influence of performance expectanc...

  20. ABOUT SYSTEM OF DISTANCE LEARNING IN OPEN ONLINE COURSE

    Directory of Open Access Journals (Sweden)

    V.М. Kukharenko

    2012-03-01

    Full Text Available This paper describes the first part of the open online course "E-Learning from A to Z", dedicated to the creation and development of system of distance learning (university or corporation. The results of the learning process and discussion on the workshop at NTU "KPI" in 2012 is shown the interest of teachers in a new form of online course and lack of development of personal learning environment. The open online courses can contribute to society practice.

  1. Implementation of standards within eLearning information systems

    OpenAIRE

    Roman Malo

    2007-01-01

    Nowadays, eLearning standards' support within eLearning systems is much discussed problem. In this problem domain especially the reference model SCORM must be considered. This de-facto standard is a package of common standards and specifications used for the standardization of eLearning activities as eLearning content preparation, using e-course, communication etc. Implementation of standards itself is a process with great difficulty and time requests. Interesting and considerable approach to...

  2. Building machine learning systems with Python

    CERN Document Server

    Coelho, Luis Pedro

    2015-01-01

    This book primarily targets Python developers who want to learn and use Python's machine learning capabilities and gain valuable insights from data to develop effective solutions for business problems.

  3. Personalized E- learning System Based on Intelligent Agent

    Science.gov (United States)

    Duo, Sun; Ying, Zhou Cai

    Lack of personalized learning is the key shortcoming of traditional e-Learning system. This paper analyzes the personal characters in e-Learning activity. In order to meet the personalized e-learning, a personalized e-learning system based on intelligent agent was proposed and realized in the paper. The structure of system, work process, the design of intelligent agent and the realization of intelligent agent were introduced in the paper. After the test use of the system by certain network school, we found that the system could improve the learner's initiative participation, which can provide learners with personalized knowledge service. Thus, we thought it might be a practical solution to realize self- learning and self-promotion in the lifelong education age.

  4. Dynamic integration of classifiers in the space of principal components

    NARCIS (Netherlands)

    Tsymbal, A.; Pechenizkiy, M.; Puuronen, S.; Patterson, D.W.; Kalinichenko, L.A.; Manthey, R.; Thalheim, B.; Wloka, U.

    2003-01-01

    Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. It was shown that, for an ensemble to be successful, it should consist of accurate and diverse base classifiers. However, it is also important that the

  5. Building Artificial Vision Systems with Machine Learning

    Energy Technology Data Exchange (ETDEWEB)

    LeCun, Yann [New York University

    2011-02-23

    Three questions pose the next challenge for Artificial Intelligence (AI), robotics, and neuroscience. How do we learn perception (e.g. vision)? How do we learn representations of the perceptual world? How do we learn visual categories from just a few examples?

  6. Learning Analytics across a Statewide System

    Science.gov (United States)

    Buyarski, Catherine; Murray, Jim; Torstrick, Rebecca

    2017-01-01

    This chapter explores lessons learned from two different learning analytics efforts at a large, public, multicampus university--one internally developed and one vended platform. It raises questions about how to best use analytics to support students while keeping students responsible for their own learning and success.

  7. Review of Recommender Systems Algorithms Utilized in Social Networks based e-Learning Systems & Neutrosophic System

    Directory of Open Access Journals (Sweden)

    A. A. Salama

    2015-03-01

    Full Text Available In this paper, we present a review of different recommender system algorithms that are utilized in social networks based e-Learning systems. Future research will include our proposed our e-Learning system that utilizes Recommender System and Social Network. Since the world is full of indeterminacy, the neutrosophics found their place into contemporary research. The fundamental concepts of neutrosophic set, introduced by Smarandache in [21, 22, 23] and Salama et al. in [24-66].The purpose of this paper is to utilize a neutrosophic set to analyze social networks data conducted through learning activities.

  8. Personalised Learning Object System Based on Self-Regulated Learning Theories

    Directory of Open Access Journals (Sweden)

    Ali Alharbi

    2014-06-01

    Full Text Available Self-regulated learning has become an important construct in education research in the last few years. Selfregulated learning in its simple form is the learner’s ability to monitor and control the learning process. There is increasing research in the literature on how to support students become more self-regulated learners. However, the advancement in the information technology has led to paradigm changes in the design and development of educational content. The concept of learning object instructional technology has emerged as a result of this shift in educational technology paradigms. This paper presents the results of a study that investigated the potential educational effectiveness of a pedagogical framework based on the self-regulated learning theories to support the design of learning object systems to help computer science students. A prototype learning object system was developed based on the contemporary research on self-regulated learning. The system was educationally evaluated in a quasi-experimental study over two semesters in a core programming languages concepts course. The evaluation revealed that a learning object system that takes into consideration contemporary research on self-regulated learning can be an effective learning environment to support computer science education.

  9. Statistical model for classifying the feeding systems of Iberian pigs through Gas Chromatography (GC-FID and Isotope Ratio Mass Spectrometry (GC-C-IRMS

    Directory of Open Access Journals (Sweden)

    García-Casco, J. M.

    2013-04-01

    Full Text Available In the present work we have analyzed a total of 734 subcutaneous fat samples from Iberian pigs with different feeding systems for fattening (“Bellota”, “Recebo”, “Campo” and “Cebo” over three consecutive years, 2009-2011. Lipids were extracted from the subcutaneous fat on the rump, and after esterification, they were analyzed by Gas Chromatography (GC-FID and Gas Chromatography- Combustion-Isotope Ratio Mass Spectrometry (GC-C-IRMS. Mean fatty acids and isotope ratios show that there are differences according to the year and feeding systems, two factors that should be taken into account when classifying the animals. The application of different prediction models based on Discriminant analysis has allowed us to establish a method for the classification of animals according to the feeding system type, with a correct percentage of 85% using three or four classification categories (Bellota, Recebo, Campo and/or Cebo and 91% using only two categories, Cebo and Bellota. This model could provide the basis for appropriate classification of Iberian pigs according to their feeding regime.En el presente trabajo se han analizado un total de 734 muestras de tejido subcutáneo de cerdos ibéricos con distintos tipos de alimentación de engorde (Bellota, Recebo, Cebo y Campo a lo largo de tres años consecutivos, 2009-2011. Se han extraído los lípidos de la grasa subcutánea de rabadilla, y después de su esterificación, se han analizado por Cromatografía de gases (GC-FID y por Espectrometría de masas de relaciones isotópicas (GC-C-IRMS. Las medias de los ácidos grasos y de las relaciones isotópicas muestran que existen diferencias según el año y tipo de alimentación, factores que deberían tenerse en cuenta a la hora de clasificar los animales. La aplicación de distintos modelos de predicción basados en análisis discriminante permite establecer un método para la clasificación de los animales según el tipo de alimentación, con

  10. Proactive learning for artificial cognitive systems

    Science.gov (United States)

    Lee, Soo-Young

    2010-04-01

    The Artificial Cognitive Systems (ACS) will be developed for human-like functions such as vision, auditory, inference, and behavior. Especially, computational models and artificial HW/SW systems will be devised for Proactive Learning (PL) and Self-Identity (SI). The PL model provides bilateral interactions between robot and unknown environment (people, other robots, cyberspace). For the situation awareness in unknown environment it is required to receive audiovisual signals and to accumulate knowledge. If the knowledge is not enough, the PL should improve by itself though internet and others. For human-oriented decision making it is also required for the robot to have self-identify and emotion. Finally, the developed models and system will be mounted on a robot for the human-robot co-existing society. The developed ACS will be tested against the new Turing Test for the situation awareness. The Test problems will consist of several video clips, and the performance of the ACSs will be compared against those of human with several levels of cognitive ability.

  11. Intelligent Image Recognition System for Marine Fouling Using Softmax Transfer Learning and Deep Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    C. S. Chin

    2017-01-01

    Full Text Available The control of biofouling on marine vessels is challenging and costly. Early detection before hull performance is significantly affected is desirable, especially if “grooming” is an option. Here, a system is described to detect marine fouling at an early stage of development. In this study, an image of fouling can be transferred wirelessly via a mobile network for analysis. The proposed system utilizes transfer learning and deep convolutional neural network (CNN to perform image recognition on the fouling image by classifying the detected fouling species and the density of fouling on the surface. Transfer learning using Google’s Inception V3 model with Softmax at last layer was carried out on a fouling database of 10 categories and 1825 images. Experimental results gave acceptable accuracies for fouling detection and recognition.

  12. Data Mining Learning Models and Algorithms on a Scada System Data Repository

    Directory of Open Access Journals (Sweden)

    Mircea Rîşteiu

    2010-06-01

    Full Text Available This paper presents three data mining techniques applied
    on a SCADA system data repository: Naijve Bayes, k-Nearest Neighbor and Decision Trees. A conclusion that k-Nearest Neighbor is a suitable method to classify the large amount of data considered is made finally according to the mining result and its reasonable explanation. The experiments are built on the training data set and evaluated using the new test set with machine learning tool WEKA.

  13. Machine-learning approach for local classification of crystalline structures in multiphase systems

    Science.gov (United States)

    Dietz, C.; Kretz, T.; Thoma, M. H.

    2017-07-01

    Machine learning is one of the most popular fields in computer science and has a vast number of applications. In this work we will propose a method that will use a neural network to locally identify crystal structures in a mixed phase Yukawa system consisting of fcc, hcp, and bcc clusters and disordered particles similar to plasma crystals. We compare our approach to already used methods and show that the quality of identification increases significantly. The technique works very well for highly disturbed lattices and shows a flexible and robust way to classify crystalline structures that can be used by only providing particle positions. This leads to insights into highly disturbed crystalline structures.

  14. An E-learning System based on Affective Computing

    Science.gov (United States)

    Duo, Sun; Song, Lu Xue

    In recent years, e-learning as a learning system is very popular. But the current e-learning systems cannot instruct students effectively since they do not consider the emotional state in the context of instruction. The emergence of the theory about "Affective computing" can solve this question. It can make the computer's intelligence no longer be a pure cognitive one. In this paper, we construct an emotional intelligent e-learning system based on "Affective computing". A dimensional model is put forward to recognize and analyze the student's emotion state and a virtual teacher's avatar is offered to regulate student's learning psychology with consideration of teaching style based on his personality trait. A "man-to-man" learning environment is built to simulate the traditional classroom's pedagogy in the system.

  15. Reinforcement and Systemic Machine Learning for Decision Making

    CERN Document Server

    Kulkarni, Parag

    2012-01-01

    Reinforcement and Systemic Machine Learning for Decision Making There are always difficulties in making machines that learn from experience. Complete information is not always available-or it becomes available in bits and pieces over a period of time. With respect to systemic learning, there is a need to understand the impact of decisions and actions on a system over that period of time. This book takes a holistic approach to addressing that need and presents a new paradigm-creating new learning applications and, ultimately, more intelligent machines. The first book of its kind in this new an

  16. Estimating Students’ Satisfaction with Web Based Learning System in Blended Learning Environment

    Directory of Open Access Journals (Sweden)

    Sanja Bauk

    2014-01-01

    Full Text Available Blended learning became the most popular educational model that universities apply for teaching and learning. This model combines online and face-to-face learning environments, in order to enhance learning with implementation of new web technologies and tools in learning process. In this paper principles of DeLone and Mclean success model for information system are applied to Kano two-dimensional model, for categorizing quality attributes related to satisfaction of students with web based learning system used in blended learning model. Survey results are obtained among the students at “Mediterranean” University in Montenegro. The (dysfunctional dimensions of Kano model, including Kano basic matrix for assessment of the degree of students’ satisfaction level, have been considered in some more detail through corresponding numerical, graphical, and statistical analysis.

  17. Which Recommender System Can Best Fit Social Learning Platforms?

    OpenAIRE

    Fazeli, Soude; Loni, Babak; Drachsler, Hendrik; Sloep, Peter

    2014-01-01

    In this presentation, we present a study that aims to develop a recommender system for social learning platforms that combine traditional learning management systems with commercial social networks like Facebook. We therefore take into account social interactions of users to make recommendations on learning resources. We propose to make use of graph-walking methods for improving performance of the well-known baseline algorithms. We evaluate the proposed graph-based approach in terms of their ...

  18. Active Learning of Markov Decision Processes for System Verification

    DEFF Research Database (Denmark)

    Chen, Yingke; Nielsen, Thomas Dyhre

    2012-01-01

    deterministic Markov decision processes from data by actively guiding the selection of input actions. The algorithm is empirically analyzed by learning system models of slot machines, and it is demonstrated that the proposed active learning procedure can significantly reduce the amount of data required...... demanding process, and this shortcoming has motivated the development of algorithms for automatically learning system models from observed system behaviors. Recently, algorithms have been proposed for learning Markov decision process representations of reactive systems based on alternating sequences...... of input/output observations. While alleviating the problem of manually constructing a system model, the collection/generation of observed system behaviors can also prove demanding. Consequently we seek to minimize the amount of data required. In this paper we propose an algorithm for learning...

  19. Recommendation System Based On Association Rules For Distributed E-Learning Management Systems

    Science.gov (United States)

    Mihai, Gabroveanu

    2015-09-01

    Traditional Learning Management Systems are installed on a single server where learning materials and user data are kept. To increase its performance, the Learning Management System can be installed on multiple servers; learning materials and user data could be distributed across these servers obtaining a Distributed Learning Management System. In this paper is proposed the prototype of a recommendation system based on association rules for Distributed Learning Management System. Information from LMS databases is analyzed using distributed data mining algorithms in order to extract the association rules. Then the extracted rules are used as inference rules to provide personalized recommendations. The quality of provided recommendations is improved because the rules used to make the inferences are more accurate, since these rules aggregate knowledge from all e-Learning systems included in Distributed Learning Management System.

  20. Integrated Programme Control Systems: Lessons Learned

    Energy Technology Data Exchange (ETDEWEB)

    Brown, C. W. [Babcock International Group PLC (formerly UKAEA Ltd) B21 Forss, Thurso, Caithness, Scotland (United Kingdom)

    2013-08-15

    Dounreay was the UK's centre of fast reactor research and development from 1955 until 1994 and is now Scotland's largest nuclear clean up and demolition project. After four decades of research, Dounreay is now a site of construction, demolition and waste management, designed to return the site to as near as practicable to its original condition. Dounreay has a turnover in the region of Pounds 150 million a year and employs approximately 900 people. It subcontracts work to 50 or so companies in the supply chain and this provides employment for a similar number of people. The plan for decommissioning the site anticipates all redundant buildings will be cleared in the short term. The target date to achieve interim end state by 2039 is being reviewed in light of Government funding constraints, and will be subject to change through the NDA led site management competition. In the longer term, controls will be put in place on the use of contaminated land until 2300. In supporting the planning, management and organisational aspects for this complex decommissioning programme an integrated programme controls system has been developed and deployed. This consists of a combination of commercial and bespoke tools integrated to support all aspects of programme management, namely scope, schedule, cost, estimating and risk in order to provide baseline and performance management data based upon the application of earned value management principles. Through system evolution and lessons learned, the main benefits of this approach are management data consistency, rapid communication of live information, and increased granularity of data providing summary and detailed reports which identify performance trends that lead to corrective actions. The challenges of such approach are effective use of the information to realise positive changes, balancing the annual system support and development costs against the business needs, and maximising system performance. (author)

  1. Conceptualizing Debates in Learning and Educational Research: Toward a Complex Systems Conceptual Framework of Learning

    Science.gov (United States)

    Jacobson, Michael J.; Kapur, Manu; Reimann, Peter

    2016-01-01

    This article proposes a conceptual framework of learning based on perspectives and methodologies being employed in the study of complex physical and social systems to inform educational research. We argue that the contexts in which learning occurs are complex systems with elements or agents at different levels--including neuronal, cognitive,…

  2. Could a Mobile-Assisted Learning System Support Flipped Classrooms for Classical Chinese Learning?

    Science.gov (United States)

    Wang, Y.-H.

    2016-01-01

    In this study, the researcher aimed to develop a mobile-assisted learning system and to investigate whether it could promote teenage learners' classical Chinese learning through the flipped classroom approach. The researcher first proposed the structure of the Cross-device Mobile-Assisted Classical Chinese (CMACC) system according to the pilot…

  3. Learner Open Modeling in Adaptive Mobile Learning System for Supporting Student to Learn English

    Directory of Open Access Journals (Sweden)

    Van Cong Pham

    2011-10-01

    Full Text Available This paper represents a personalized context-aware mobile learning architecture for supporting student to learn English as foreign language in order to prepare for TOEFL test. We consider how to apply open learner modeling techniques to adapt contents for different learners based on context, which includes location, amount of time to learn, the manner as well as learner's knowledge in learning progress. Through negotiation with system, the editable learner model will be updated to support adaptive engine to select adaptive contents meeting learner's demands. Empirical testing results for students who used application prototype indicate that interaction user modeling is helpful in supporting learner to learn adaptive materials.

  4. Thai Finger-Spelling Recognition Using a Cascaded Classifier Based on Histogram of Orientation Gradient Features

    Directory of Open Access Journals (Sweden)

    Kittasil Silanon

    2017-01-01

    Full Text Available Hand posture recognition is an essential module in applications such as human-computer interaction (HCI, games, and sign language systems, in which performance and robustness are the primary requirements. In this paper, we proposed automatic classification to recognize 21 hand postures that represent letters in Thai finger-spelling based on Histogram of Orientation Gradient (HOG feature (which is applied with more focus on the information within certain region of the image rather than each single pixel and Adaptive Boost (i.e., AdaBoost learning technique to select the best weak classifier and to construct a strong classifier that consists of several weak classifiers to be cascaded in detection architecture. We collected 21 static hand posture images from 10 subjects for testing and training in Thai letters finger-spelling. The parameters for the training process have been adjusted in three experiments, false positive rates (FPR, true positive rates (TPR, and number of training stages (N, to achieve the most suitable training model for each hand posture. All cascaded classifiers are loaded into the system simultaneously to classify different hand postures. A correlation coefficient is computed to distinguish the hand postures that are similar. The system achieves approximately 78% accuracy on average on all classifier experiments.

  5. The Role of Corticostriatal Systems in Speech Category Learning.

    Science.gov (United States)

    Yi, Han-Gyol; Maddox, W Todd; Mumford, Jeanette A; Chandrasekaran, Bharath

    2016-04-01

    One of the most difficult category learning problems for humans is learning nonnative speech categories. While feedback-based category training can enhance speech learning, the mechanisms underlying these benefits are unclear. In this functional magnetic resonance imaging study, we investigated neural and computational mechanisms underlying feedback-dependent speech category learning in adults. Positive feedback activated a large corticostriatal network including the dorsolateral prefrontal cortex, inferior parietal lobule, middle temporal gyrus, caudate, putamen, and the ventral striatum. Successful learning was contingent upon the activity of domain-general category learning systems: the fast-learning reflective system, involving the dorsolateral prefrontal cortex that develops and tests explicit rules based on the feedback content, and the slow-learning reflexive system, involving the putamen in which the stimuli are implicitly associated with category responses based on the reward value in feedback. Computational modeling of response strategies revealed significant use of reflective strategies early in training and greater use of reflexive strategies later in training. Reflexive strategy use was associated with increased activation in the putamen. Our results demonstrate a critical role for the reflexive corticostriatal learning system as a function of response strategy and proficiency during speech category learning. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

  6. Assessing the Value of E-Learning Systems

    Science.gov (United States)

    Levy, Yair

    2006-01-01

    "Assessing the Value of E-Learning Systems" provides an extensive literature review pulling theories from the field of information systems, psychology and cognitive sciences, distance and online learning, as well as marketing and decision sciences. This book provides empirical evidence for the power of measuring value in the context of e-learning…

  7. PERSO: Towards an Adaptive e-Learning System

    Science.gov (United States)

    Chorfi, Henda; Jemni, Mohamed

    2004-01-01

    In today's information technology society, members are increasingly required to be up to date on new technologies, particularly for computers, regardless of their background social situation. In this context, our aim is to design and develop an adaptive hypermedia e-learning system, called PERSO (PERSOnalizing e-learning system), where learners…

  8. Computerized adaptive testing item selection in computerized adaptive learning systems

    NARCIS (Netherlands)

    Eggen, Theodorus Johannes Hendrikus Maria; Eggen, T.J.H.M.; Veldkamp, B.P.

    2012-01-01

    Item selection methods traditionally developed for computerized adaptive testing (CAT) are explored for their usefulness in item-based computerized adaptive learning (CAL) systems. While in CAT Fisher information-based selection is optimal, for recovering learning populations in CAL systems item

  9. Learning from the Field : Innovating China's Higher Education System

    International Development Research Centre (IDRC) Digital Library (Canada)

    2008-04-15

    Learning from the Field : Innovating China's Higher Education System. Couverture du livre Learning from the Field : Innovating China's Higher Education System. Editor(s):. Ronnie Vernooy, Li Xiaoyun, Xu Xiuli, Lu Min, et Qi Gubo. Publisher(s):. Foundation Book, CRDI. April 15, 2008. ISBN: 9788175966017. 260 pages.

  10. Which recommender system can best fit social learning platforms?

    NARCIS (Netherlands)

    Fazeli, Soude; Loni, Babak; Drachsler, Hendrik; Sloep, Peter

    2014-01-01

    In this presentation, we present a study that aims to develop a recommender system for social learning platforms that combine traditional learning management systems with commercial social networks like Facebook. We therefore take into account social interactions of users to make recommendations on

  11. Systems control with generalized probabilistic fuzzy-reinforcement learning

    NARCIS (Netherlands)

    Hinojosa, J.; Nefti, S.; Kaymak, U.

    2011-01-01

    Reinforcement learning (RL) is a valuable learning method when the systems require a selection of control actions whose consequences emerge over long periods for which input-output data are not available. In most combinations of fuzzy systems and RL, the environment is considered to be

  12. Natural Interaction Based Online Military Boxing Learning System

    Science.gov (United States)

    Yang, Chenglei; Wang, Lu; Sun, Bing; Yin, Xu; Wang, Xiaoting; Liu, Li; Lu, Lin

    2013-01-01

    Military boxing, a kind of Chinese martial arts, is widespread and health beneficial. In this paper, the authors introduce a military boxing learning system realized by 3D motion capture, Web3D and 3D interactive technologies. The interactions with the system are natural and intuitive. Users can observe and learn the details of each action of the…

  13. Adaptive Landmark-Based Navigation System Using Learning Techniques

    DEFF Research Database (Denmark)

    Zeidan, Bassel; Dasgupta, Sakyasingha; Wörgötter, Florentin

    2014-01-01

    The goal-directed navigational ability of animals is an essential prerequisite for them to survive. They can learn to navigate to a distal goal in a complex environment. During this long-distance navigation, they exploit environmental features, like landmarks, to guide them towards their goal. In...... hexapod robots. As a result, it allows the robots to successfully learn to navigate to distal goals in complex environments.......The goal-directed navigational ability of animals is an essential prerequisite for them to survive. They can learn to navigate to a distal goal in a complex environment. During this long-distance navigation, they exploit environmental features, like landmarks, to guide them towards their goal....... Inspired by this, we develop an adaptive landmark-based navigation system based on sequential reinforcement learning. In addition, correlation-based learning is also integrated into the system to improve learning performance. The proposed system has been applied to simulated simple wheeled and more complex...

  14. LBS Mobile Learning System Based on Android Platform

    Directory of Open Access Journals (Sweden)

    Zhang Ya-Li

    2017-01-01

    Full Text Available In the era of mobile internet, PC-end internet services can no long satisfy people’s demands, needs for App and services on mobile phones are more urgent than ever. With increasing social competition, the concept of lifelong learning becomes more and more popular and accepted, making full use of spare time to learn at any time and any place meets updating knowledge desires of modern people, Location Based System (LBS mobile learning system based on Android platform was created under such background. In this Paper, characteristics of mobile location technology and intelligent terminal were introduced and analyzed, mobile learning system which will fulfill personalized needs of mobile learners was designed and developed on basis of location information, mobile learning can be greatly promoted and new research ideas can be expanded for mobile learning.

  15. Parameterization of a fuzzy classifier for the diagnosis of an industrial process

    International Nuclear Information System (INIS)

    Toscano, R.; Lyonnet, P.

    2002-01-01

    The aim of this paper is to present a classifier based on a fuzzy inference system. For this classifier, we propose a parameterization method, which is not necessarily based on an iterative training. This approach can be seen as a pre-parameterization, which allows the determination of the rules base and the parameters of the membership functions. We also present a continuous and derivable version of the previous classifier and suggest an iterative learning algorithm based on a gradient method. An example using the learning basis IRIS, which is a benchmark for classification problems, is presented showing the performances of this classifier. Finally this classifier is applied to the diagnosis of a DC motor showing the utility of this method. However in many cases the total knowledge necessary to the synthesis of the fuzzy diagnosis system (FDS) is not, in general, directly available. It must be extracted from an often-considerable mass of information. For this reason, a general methodology for the design of a FDS is presented and illustrated on a non-linear plant

  16. Classified

    CERN Multimedia

    Computer Security Team

    2011-01-01

    In the last issue of the Bulletin, we have discussed recent implications for privacy on the Internet. But privacy of personal data is just one facet of data protection. Confidentiality is another one. However, confidentiality and data protection are often perceived as not relevant in the academic environment of CERN.   But think twice! At CERN, your personal data, e-mails, medical records, financial and contractual documents, MARS forms, group meeting minutes (and of course your password!) are all considered to be sensitive, restricted or even confidential. And this is not all. Physics results, in particular when being preliminary and pending scrutiny, are sensitive, too. Just recently, an ATLAS collaborator copy/pasted the abstract of an ATLAS note onto an external public blog, despite the fact that this document was clearly marked as an "Internal Note". Such an act was not only embarrassing to the ATLAS collaboration, and had negative impact on CERN’s reputation --- i...

  17. e-Learning Management System (eLMS) -

    Data.gov (United States)

    Department of Transportation — DOT's electronic Learning Management System (eLMS) is a state-of-the-art web-based system that meets the needs of training administrators, learners, and managers and...

  18. Three data partitioning strategies for building local classifiers (Chapter 14)

    NARCIS (Netherlands)

    Zliobaite, I.; Okun, O.; Valentini, G.; Re, M.

    2011-01-01

    Divide-and-conquer approach has been recognized in multiple classifier systems aiming to utilize local expertise of individual classifiers. In this study we experimentally investigate three strategies for building local classifiers that are based on different routines of sampling data for training.

  19. MACHINE LEARNING IMPLEMENTATION FOR THE CLASSIFICATION OF ATTACKS ON WEB SYSTEMS. PART 1

    Directory of Open Access Journals (Sweden)

    K. Smirnova

    2017-08-01

    Full Text Available The possibility of applying machine learning is considered for the classification of malicious requests to a Web application. This approach excludes the use of deterministic analysis systems (for example, expert systems, and based on the application of a cascade of neural networks or perceptrons on an approximate model to the real human brain. The main idea of the work is to enable to describe complex attack vectors consisting of feature sets, abstract terms for compiling a training sample, controlling the quality of recognition and classifying each of the layers (networks participating in the work, with the ability to adjust not the entire network, But only a small part of it, in the training of which a mistake or inaccuracy crept in.  The design of the developed network can be described as a cascaded, scalable neural network.  The developed system of intrusion detection uses a three-layer neural network. Layers can be built independently of each other by cascades. In the first layer, for each class of attack recognition, there is a corresponding network and correctness is checked on this network. To learn this layer, we have chosen classes of things that can be classified uniquely as yes or no, that is, they are linearly separable. Thus, a layer is obtained not just of neurons, but of their microsets, which can best determine whether is there some data class in the query or not. The following layers are not trained to recognize the attacks themselves, they are trained that a set of attacks creates certain threats. This allows you to more accurately recognize the attacker's attempts to bypass the defense system, as well as classify the target of the attack, and not just its fact. Simple layering allows you to minimize the percentage of false positives.

  20. A service based adaptive U-learning system using UX.

    Science.gov (United States)

    Jeong, Hwa-Young; Yi, Gangman

    2014-01-01

    In recent years, traditional development techniques for e-learning systems have been changing to become more convenient and efficient. One new technology in the development of application systems includes both cloud and ubiquitous computing. Cloud computing can support learning system processes by using services while ubiquitous computing can provide system operation and management via a high performance technical process and network. In the cloud computing environment, a learning service application can provide a business module or process to the user via the internet. This research focuses on providing the learning material and processes of courses by learning units using the services in a ubiquitous computing environment. And we also investigate functions that support users' tailored materials according to their learning style. That is, we analyzed the user's data and their characteristics in accordance with their user experience. We subsequently applied the learning process to fit on their learning performance and preferences. Finally, we demonstrate how the proposed system outperforms learning effects to learners better than existing techniques.

  1. A Service Based Adaptive U-Learning System Using UX

    Directory of Open Access Journals (Sweden)

    Hwa-Young Jeong

    2014-01-01

    Full Text Available In recent years, traditional development techniques for e-learning systems have been changing to become more convenient and efficient. One new technology in the development of application systems includes both cloud and ubiquitous computing. Cloud computing can support learning system processes by using services while ubiquitous computing can provide system operation and management via a high performance technical process and network. In the cloud computing environment, a learning service application can provide a business module or process to the user via the internet. This research focuses on providing the learning material and processes of courses by learning units using the services in a ubiquitous computing environment. And we also investigate functions that support users’ tailored materials according to their learning style. That is, we analyzed the user’s data and their characteristics in accordance with their user experience. We subsequently applied the learning process to fit on their learning performance and preferences. Finally, we demonstrate how the proposed system outperforms learning effects to learners better than existing techniques.

  2. LEARNING STYLES BASED ADAPTIVE INTELLIGENT TUTORING SYSTEMS: DOCUMENT ANALYSIS OF ARTICLES PUBLISHED BETWEEN 2001. AND 2016.

    Directory of Open Access Journals (Sweden)

    Amit Kumar

    2017-12-01

    Full Text Available Actualizing instructional intercessions to suit learner contrasts has gotten extensive consideration. Among these individual contrast factors, the observational confirmation in regards to the academic benefit of learning styles has been addressed, yet the examination on the issue proceeds. Late improvements in web-based executions have driven researchers to re-examine the learning styles in adaptive tutoring frameworks. Adaptivity in intelligent tutoring systems is strongly influenced by the learning style of a learner. This study involved extensive document analysis of adaptive tutoring systems based on learning styles. Seventy-eight studies in literature from 2001 to 2016 were collected and classified under select parameters such as main focus, purpose, research types, methods, types and levels of participants, field/area of application, learner modelling, data gathering tools used and research findings. The current studies reveal that majority of the studies defined a framework or architecture of adaptive intelligent tutoring system (AITS while others focused on impact of AITS on learner satisfaction and academic outcomes. Currents trends, gaps in literature and ications were discussed.

  3. The Design and Analysis of Learning Effects for a Game-based Learning System

    OpenAIRE

    Wernhuar Tarng; Weichian Tsai

    2010-01-01

    The major purpose of this study is to use network and multimedia technologies to build a game-based learning system for junior high school students to apply in learning “World Geography" through the “role-playing" game approaches. This study first investigated the motivation and habits of junior high school students to use the Internet and online games, and then designed a game-based learning system according to situated and game-based learning theories. A teaching experiment was conducted to...

  4. Learning in tele-autonomous systems using Soar

    Science.gov (United States)

    Laird, John E.; Yager, Eric S.; Tuck, Christopher M.; Hucka, Michael

    1989-01-01

    Robo-Soar is a high-level robot arm control system implemented in Soar. Robo-Soar learns to perform simple block manipulation tasks using advice from a human. Following learning, the system is able to perform similar tasks without external guidance. It can also learn to correct its knowledge, using its own problem solving in addition to outside guidance. Robo-Soar corrects its knowledge by accepting advice about relevance of features in its domain, using a unique integration of analytic and empirical learning techniques.

  5. Designing E-learning Model to Learn About Transportation Management System to Support Supply Chain Management with Simulation Problems

    OpenAIRE

    Wiyono, Didiek Sri; Pribadi, Sidigdoyo; Permana, Ryan

    2011-01-01

    Focus of this research is designing Transportation Management System (TMS) as e-learning media for logistic education. E-learning is the use of Internet technologies to enhance knowledge and performance. E-learning technologies offer learners control over content, learning sequence, pace of learning, time, and often media, allowing them to tailor their experiences to meet their personal learning objectives. E-learning appears to be at least as effective as classical lectures. Students do not ...

  6. Learning management system and e-learning tools: an experience of medical students' usage and expectations.

    Science.gov (United States)

    Back, David A; Behringer, Florian; Haberstroh, Nicole; Ehlers, Jan P; Sostmann, Kai; Peters, Harm

    2016-08-20

    To investigate medical students´ utilization of and problems with a learning management system and its e-learning tools as well as their expectations on future developments. A single-center online survey has been carried out to investigate medical students´ (n = 505) usage and perception concerning the learning management system Blackboard, and provided e-learning tools. Data were collected with a standardized questionnaire consisting of 70 items and analyzed by quantitative and qualitative methods. The participants valued lecture notes (73.7%) and Wikipedia (74%) as their most important online sources for knowledge acquisition. Missing integration of e-learning into teaching was seen as the major pitfall (58.7%). The learning management system was mostly used for study information (68.3%), preparation of exams (63.3%) and lessons (54.5%). Clarity (98.3%), teaching-related contexts (92.5%) and easy use of e-learning offers (92.5%) were rated highest. Interactivity was most important in free-text comments (n = 123). It is desired that contents of a learning management system support an efficient learning. Interactivity of tools and their conceptual integration into face-to-face teaching are important for students. The learning management system was especially important for organizational purposes and the provision of learning materials. Teachers should be aware that free online sources such as Wikipedia enjoy a high approval as source of knowledge acquisition. This study provides an empirical basis for medical schools and teachers to improve their offerings in the field of digital learning for their students.

  7. Evaluating Web-Based Learning Systems

    Science.gov (United States)

    Pergola, Teresa M.; Walters, L. Melissa

    2011-01-01

    Accounting educators continuously seek ways to effectively integrate instructional technology into accounting coursework as a means to facilitate active learning environments and address the technology-driven learning preferences of the current generation of students. Most accounting textbook publishers now provide interactive, web-based learning…

  8. Soft Systems Methodology for Personalized Learning Environment

    Science.gov (United States)

    Nair, Uday

    2015-01-01

    There are two sides to a coin when it comes to implementing technology at universities; on one side, there is the university using technologies via the virtual learning environment that seems to be outdated with the digital needs of the students, and on the other side, while implementing technology at the university learning environment the focus…

  9. Games as Distributed Teaching and Learning Systems

    Science.gov (United States)

    Gee, Elisabeth; Gee, James Paul

    2017-01-01

    Background: Videogames and virtual worlds have frequently been studied as learning environments in isolation; that is, scholars have focused on understanding the features of games or virtual worlds as separate from or different than "real world" environments for learning. Although more recently, scholars have explored the teaching and…

  10. Intelligent fractions learning system: conceptual design

    CSIR Research Space (South Africa)

    Laine, TH

    2010-01-01

    Full Text Available UFractions is a ubiquitous learning environment which combines mobile technology, tangible fraction blocks and a story-based game into a mathematical learning experience. In this paper the authors present a novel concept for monitoring a user’s...

  11. Moving towards Virtual Learning Clouds from Traditional Learning: Higher Educational Systems in India

    Directory of Open Access Journals (Sweden)

    Vasanthi Muniasamy

    2014-10-01

    Full Text Available E-Learning has become an increasingly popular learning approach in higher Education institutions due to the rapid growth of Communication and Information Technology (CIT. In recent years, it has been integrated in many university programs and it is one of the new learning trends. But in many Indian Universities did not implement this novel technology in their Educational Systems. E-Learning is not intended to replace the traditional classroom setting, but to provide new opportunities and new virtual environment for interaction and communication between the students and teacher. E-Learning through Cloud is now becoming an interesting and very useful revolutionary technology in the field of education. E-Learning system usually requires huge amount of hardware and software resources. Due to the cost, many universities in India do not want to implement the E-Learning technology in their Educational system and they cannot afford such investments. Cloud Virtual Learning is the only solution for this problem. This paper presents the benefits of using cloud technology in E-Learning system, working mode, Services, Models. And also we discuss the cloud computing educational environment and how higher education may take advantage of clouds not only in terms of cost but also in terms of Security, flexibility, portability, efficiency and reliability. And also we present some educational clouds introduced by popular cloud providers.

  12. Learning object repositories as knowledge management systems

    Directory of Open Access Journals (Sweden)

    Demetrios G. Sampson

    2013-06-01

    Full Text Available Over the past years, a number of international initiatives that recognize the importance of sharing and reusing digital educational resources among educational communities through the use of Learning Object Repositories (LORs have emerged. Typically, these initiatives focus on collecting digital educational resources that are offered by their creators for open access and potential reuse. Nevertheless, most of the existing LORs are designed more as digital repositories, rather than as Knowledge Management Systems (KMS. By exploiting KMSs functionalities in LORs would bare the potential to support the organization and sharing of educational communities’ explicit knowledge (depicted in digital educational resources constructed by teachers and/or instructional designers and tacit knowledge (depicted in teachers’ and students’ experiences and interactions of using digital educational resources available in LORs. Within this context, in this paper we study the design and the implementation of fourteen operating LORs from the KMSs’ perspective, so as to identify additional functionalities that can support the management of educational communities’ explicit and tacit knowledge. Thus, we propose a list of essential LORs’ functionalities, which aim to facilitate the organization and sharing of educational communities’ knowledge. Finally, we present the added value of these functionalities by identifying their importance towards addressing the current demands of web-facilitated educational communities, as well as the knowledge management activities that they execute.

  13. STRATEGY FOR EVALUATION AND SELECTION OF SYSTEMS FOR ELECTRONIC LEARNING

    Directory of Open Access Journals (Sweden)

    Dubravka Mandušić

    2012-12-01

    Full Text Available Today`s technology supported and accelerated learning time requires constant and continuous acquisition of new knowledge. On the other hand, it does not leave enough time for additional education. Increasing number of E-learning systems, withdraws a need for precise evaluation of functionality that those systems provide; so they could be reciprocally compared. While implementing new systems for electronic learning, it is very important to pre-evaluate existing systems in order to select the one that meets all defined parameters, with low costs/investment. Proper evaluation can save time and money.

  14. Generalized projective synchronization of chaotic systems via adaptive learning control

    International Nuclear Information System (INIS)

    Yun-Ping, Sun; Jun-Min, Li; Hui-Lin, Wang; Jiang-An, Wang

    2010-01-01

    In this paper, a learning control approach is applied to the generalized projective synchronisation (GPS) of different chaotic systems with unknown periodically time-varying parameters. Using the Lyapunov–Krasovskii functional stability theory, a differential-difference mixed parametric learning law and an adaptive learning control law are constructed to make the states of two different chaotic systems asymptotically synchronised. The scheme is successfully applied to the generalized projective synchronisation between the Lorenz system and Chen system. Moreover, numerical simulations results are used to verify the effectiveness of the proposed scheme. (general)

  15. Client Mobile Software Design Principles for Mobile Learning Systems

    Directory of Open Access Journals (Sweden)

    Qing Tan

    2009-01-01

    Full Text Available In a client-server mobile learning system, client mobile software must run on the mobile phone to acquire, package, and send student’s interaction data via the mobile communications network to the connected mobile application server. The server will receive and process the client data in order to offer appropriate content and learning activities. To develop the mobile learning systems there are a number of very important issues that must be addressed. Mobile phones have scarce computing resources. They consist of heterogeneous devices and use various mobile operating systems, they have limitations with their user/device interaction capabilities, high data communications cost, and must provide for device mobility and portability. In this paper we propose five principles for designing Client mobile learning software. A location-based adaptive mobile learning system is presented as a proof of concept to demonstrate the applicability of these design principles.

  16. Student Modelling in Adaptive E-Learning Systems

    Directory of Open Access Journals (Sweden)

    Clemens Bechter

    2011-09-01

    Full Text Available Most e-Learning systems provide web-based learning so that students can access the same online courses via the Internet without adaptation, based on each student's profile and behavior. In an e-Learning system, one size does not fit all. Therefore, it is a challenge to make e-Learning systems that are suitably “adaptive”. The aim of adaptive e-Learning is to provide the students the appropriate content at the right time, means that the system is able to determine the knowledge level, keep track of usage, and arrange content automatically for each student for the best learning result. This study presents a proposed system which includes major adaptive features based on a student model. The proposed system is able to initialize the student model for determining the knowledge level of a student when the student registers for the course. After a student starts learning the lessons and doing many activities, the system can track information of the student until he/she takes a test. The student’s knowledge level, based on the test scores, is updated into the system for use in the adaptation process, which combines the student model with the domain model in order to deliver suitable course contents to the students. In this study, the proposed adaptive e-Learning system is implemented on an “Introduction to Java Programming Language” course, using LearnSquare software. After the system was tested, the results showed positive feedback towards the proposed system, especially in its adaptive capability.

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

    Directory of Open Access Journals (Sweden)

    Yanjun Zhang

    2015-01-01

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

  18. IAEA safeguards and classified materials

    International Nuclear Information System (INIS)

    Pilat, J.F.; Eccleston, G.W.; Fearey, B.L.; Nicholas, N.J.; Tape, J.W.; Kratzer, M.

    1997-01-01

    The international community in the post-Cold War period has suggested that the International Atomic Energy Agency (IAEA) utilize its expertise in support of the arms control and disarmament process in unprecedented ways. The pledges of the US and Russian presidents to place excess defense materials, some of which are classified, under some type of international inspections raises the prospect of using IAEA safeguards approaches for monitoring classified materials. A traditional safeguards approach, based on nuclear material accountancy, would seem unavoidably to reveal classified information. However, further analysis of the IAEA's safeguards approaches is warranted in order to understand fully the scope and nature of any problems. The issues are complex and difficult, and it is expected that common technical understandings will be essential for their resolution. Accordingly, this paper examines and compares traditional safeguards item accounting of fuel at a nuclear power station (especially spent fuel) with the challenges presented by inspections of classified materials. This analysis is intended to delineate more clearly the problems as well as reveal possible approaches, techniques, and technologies that could allow the adaptation of safeguards to the unprecedented task of inspecting classified materials. It is also hoped that a discussion of these issues can advance ongoing political-technical debates on international inspections of excess classified materials

  19. E-learning systems intelligent techniques for personalization

    CERN Document Server

    Klašnja-Milićević, Aleksandra; Ivanović, Mirjana; Budimac, Zoran; Jain, Lakhmi C

    2017-01-01

    This monograph provides a comprehensive research review of intelligent techniques for personalisation of e-learning systems. Special emphasis is given to intelligent tutoring systems as a particular class of e-learning systems, which support and improve the learning and teaching of domain-specific knowledge. A new approach to perform effective personalization based on Semantic web technologies achieved in a tutoring system is presented. This approach incorporates a recommender system based on collaborative tagging techniques that adapts to the interests and level of students' knowledge. These innovations are important contributions of this monograph. Theoretical models and techniques are illustrated on a real personalised tutoring system for teaching Java programming language. The monograph is directed to, students and researchers interested in the e-learning and personalization techniques. .

  20. Classifying web pages with visual features

    NARCIS (Netherlands)

    de Boer, V.; van Someren, M.; Lupascu, T.; Filipe, J.; Cordeiro, J.

    2010-01-01

    To automatically classify and process web pages, current systems use the textual content of those pages, including both the displayed content and the underlying (HTML) code. However, a very important feature of a web page is its visual appearance. In this paper, we show that using generic visual

  1. A survey of decision tree classifier methodology

    Science.gov (United States)

    Safavian, S. R.; Landgrebe, David

    1991-01-01

    Decision tree classifiers (DTCs) are used successfully in many diverse areas such as radar signal classification, character recognition, remote sensing, medical diagnosis, expert systems, and speech recognition. Perhaps the most important feature of DTCs is their capability to break down a complex decision-making process into a collection of simpler decisions, thus providing a solution which is often easier to interpret. A survey of current methods is presented for DTC designs and the various existing issues. After considering potential advantages of DTCs over single-state classifiers, subjects of tree structure design, feature selection at each internal node, and decision and search strategies are discussed.

  2. Applications of learning based systems at AREVA group

    International Nuclear Information System (INIS)

    Jeanmart, F.; Leclerc, C.

    2006-01-01

    As part of its work on advanced information systems, AREVA is exploring the use of computerized tools based on 'machine learning' techniques. Some of these studies are being carried out by EURIWARE - continuing on from previous work done by AREVA NC - focused on the supervision of complex systems. Systems based on machine learning techniques are one of the possible solutions being investigated by AREVA: knowing that the stakes are high and involve better anticipation and control and high financial considerations. (authors)

  3. Detection of Fundus Lesions Using Classifier Selection

    Science.gov (United States)

    Nagayoshi, Hiroto; Hiramatsu, Yoshitaka; Sako, Hiroshi; Himaga, Mitsutoshi; Kato, Satoshi

    A system for detecting fundus lesions caused by diabetic retinopathy from fundus images is being developed. The system can screen the images in advance in order to reduce the inspection workload on doctors. One of the difficulties that must be addressed in completing this system is how to remove false positives (which tend to arise near blood vessels) without decreasing the detection rate of lesions in other areas. To overcome this difficulty, we developed classifier selection according to the position of a candidate lesion, and we introduced new features that can distinguish true lesions from false positives. A system incorporating classifier selection and these new features was tested in experiments using 55 fundus images with some lesions and 223 images without lesions. The results of the experiments confirm the effectiveness of the proposed system, namely, degrees of sensitivity and specificity of 98% and 81%, respectively.

  4. Variations in oxygen and ellagitannins, and organoleptic properties of red wine aged in French oak barrels classified by a near infrared system.

    Science.gov (United States)

    Michel, Julien; Albertin, Warren; Jourdes, Michael; Le Floch, Alexandra; Giordanengo, Thomas; Mourey, Nicolas; Teissedre, Pierre-Louis

    2016-08-01

    During wine aging in barrels, antioxidant molecules from wood, such as ellagitannins, are solubilized and react with wine molecules and oxygen. However, their concentrations are highly variable. Oxygen is an important factor, as it plays a role in wine parameters and organoleptic perceptions. Five barrel modalities were used; three polyphenol indices (IP), classified using the NIRS procedure, and three grain qualities. Barrels were equipped with windows to measure the oxygen using luminescence technology. The ellagitannin concentrations in the wine and its organoleptic properties were monitored. Oxygen concentrations decreased quickly during the first 8days of aging and this phenomenon was significantly more marked in barrels with a higher IP and medium grain. The ellagitannin concentrations were believed to be correlated with wood classification and oxygen consumption. Furthermore, the organoleptic properties were significantly impacted, as the wine with the lowest ellagitannin level was described as less astringent, bitter, woody, and smoky/toasty. Copyright © 2016 Elsevier Ltd. All rights reserved.

  5. An informal summary of a new formalism for classifying spin-orbit systems using tools distilled from the theory of bundles

    International Nuclear Information System (INIS)

    Heinemann, K.; Ellison, J.A.

    2015-02-01

    We give an informal summary of ongoing work which uses tools distilled from the theory of fibre bundles to classify and connect invariant fields associated with spin motion in storage rings. We mention four major theorems. One ties invariant fields with the notion of normal form, the second allows comparison of different invariant fields and the two others tie the existence of invariant fields to the existence of certain invariant sets. We explain how the theorems apply to the spin dynamics of spin-1/2 and spin-1 particles. Our approach elegantly unifies the spin-vector dynamics from the T-BMT equation with the spin-tensor dynamics and other dynamics and suggests an avenue for addressing the question of the existence of the invariant spin field.

  6. Enhancing Collaborative Learning in Web 2.0-Based E-Learning Systems: A Design Framework for Building Collaborative E-Learning Contents

    Science.gov (United States)

    El Mhouti, Abderrahim; Nasseh, Azeddine; Erradi, Mohamed; Vasquèz, José Marfa

    2017-01-01

    Today, the implication of Web 2.0 technologies in e-learning allows envisaging new teaching and learning forms, advocating an important place to the collaboration and social interaction. However, in e-learning systems, learn in a collaborative way is not always so easy because one of the difficulties when arranging e-learning courses can be that…

  7. Performance evaluation of various classifiers for color prediction of rice paddy plant leaf

    Science.gov (United States)

    Singh, Amandeep; Singh, Maninder Lal

    2016-11-01

    The food industry is one of the industries that uses machine vision for a nondestructive quality evaluation of the produce. These quality measuring systems and softwares are precalculated on the basis of various image-processing algorithms which generally use a particular type of classifier. These classifiers play a vital role in making the algorithms so intelligent that it can contribute its best while performing the said quality evaluations by translating the human perception into machine vision and hence machine learning. The crop of interest is rice, and the color of this crop indicates the health status of the plant. An enormous number of classifiers are available to solve the purpose of color prediction, but choosing the best among them is the focus of this paper. Performance of a total of 60 classifiers has been analyzed from the application point of view, and the results have been discussed. The motivation comes from the idea of providing a set of classifiers with excellent performance and implementing them on a single algorithm for the improvement of machine vision learning and, hence, associated applications.

  8. Biomechanical Reconstruction Using the Tacit Learning System: Intuitive Control of Prosthetic Hand Rotation.

    Science.gov (United States)

    Oyama, Shintaro; Shimoda, Shingo; Alnajjar, Fady S K; Iwatsuki, Katsuyuki; Hoshiyama, Minoru; Tanaka, Hirotaka; Hirata, Hitoshi

    2016-01-01

    Background: For mechanically reconstructing human biomechanical function, intuitive proportional control, and robustness to unexpected situations are required. Particularly, creating a functional hand prosthesis is a typical challenge in the reconstruction of lost biomechanical function. Nevertheless, currently available control algorithms are in the development phase. The most advanced algorithms for controlling multifunctional prosthesis are machine learning and pattern recognition of myoelectric signals. Despite the increase in computational speed, these methods cannot avoid the requirement of user consciousness and classified separation errors. "Tacit Learning System" is a simple but novel adaptive control strategy that can self-adapt its posture to environment changes. We introduced the strategy in the prosthesis rotation control to achieve compensatory reduction, as well as evaluated the system and its effects on the user. Methods: We conducted a non-randomized study involving eight prosthesis users to perform a bar relocation task with/without Tacit Learning System support. Hand piece and body motions were recorded continuously with goniometers, videos, and a motion-capture system. Findings: Reduction in the participants' upper extremity rotatory compensation motion was monitored during the relocation task in all participants. The estimated profile of total body energy consumption improved in five out of six participants. Interpretation: Our system rapidly accomplished nearly natural motion without unexpected errors. The Tacit Learning System not only adapts human motions but also enhances the human ability to adapt to the system quickly, while the system amplifies compensation generated by the residual limb. The concept can be extended to various situations for reconstructing lost functions that can be compensated.

  9. Multiple systems for motor skill learning

    OpenAIRE

    Clark, Dav; Ivry, Richard B.

    2010-01-01

    Motor learning is a ubiquitous feature of human competence. This review focuses on two particular classes of model tasks for studying skill acquisition. The serial reaction time (SRT) task is used to probe how people learn sequences of actions, while adaptation in the context of visuomotor or force field perturbations serves to illustrate how preexisting movements are recalibrated in novel environments. These tasks highlight important issues regarding the representational changes that occur d...

  10. Using Information Technology in the Navy Lessons Learned System to Improve Organizational Learning

    National Research Council Canada - National Science Library

    Garvey, Michael

    2001-01-01

    ... to support or enhance organizational learning in the Navy. The research concludes that NLLS has improved organizational learning but has not attained as widespread use as is possible. Recommendations are provide to improve the program and increase NLLS exposure to the fleet and to the potential users of the system.

  11. Effective Trust-Aware E-learning Recommender System Based on Learning Styles and Knowledge Levels

    Science.gov (United States)

    Dwivedi, Pragya; Bharadwaj, Kamal K.

    2013-01-01

    In the age of information explosion, e-learning recommender systems (ELRSs) have emerged as the most essential tool to deliver personalized learning resources to learners. Due to enormous amount of information on the web, learner faces problem in searching right information. ELRSs deal with the problem of information overload effectively and…

  12. Student and Staff Perceptions of a Learning Management System for Blended Learning in Teacher Education

    Science.gov (United States)

    Holmes, Kathryn A.; Prieto-Rodriguez, Elena

    2018-01-01

    Higher education institutions routinely use Learning Management Systems (LMS) for multiple purposes; to organise coursework and assessment, to facilitate staff and student interactions, and to act as repositories of learning objects. The analysis reported here involves staff (n = 46) and student (n = 470) responses to surveys as well as data…

  13. Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems

    Science.gov (United States)

    Gifford, Christopher M.

    2009-01-01

    This dissertation focuses on the collaboration of multiple heterogeneous, intelligent agents (hardware or software) which collaborate to learn a task and are capable of sharing knowledge. The concept of collaborative learning in multi-agent and multi-robot systems is largely under studied, and represents an area where further research is needed to…

  14. Learning by Doing: Twenty Successful Active Learning Exercises for Information Systems Courses

    Science.gov (United States)

    Mitchell, Alanah; Petter, Stacie; Harris, Albert L.

    2017-01-01

    Aim/Purpose: This paper provides a review of previously published work related to active learning in information systems (IS) courses. Background: There are a rising number of strategies in higher education that offer promise in regards to getting students' attention and helping them learn, such as flipped classrooms and offering courses online.…

  15. Design and Implementation of a Cooperative Learning System for Digital Content Design Curriculum: Investigation on Learning Effectiveness and Social Presence

    Science.gov (United States)

    Huang, Ming-Shang; Hsiao, Wei-Hung; Chang, Tsung-Sheng; Hu, Mei-Huei

    2012-01-01

    The purpose of this paper is to investigate the learning effectiveness of cooperative learning system based on social presence theory. We develop a web-based cooperative learning system which contains personal module, admin module, course module, communication module, and learning records module to support the implementation of cooperative…

  16. The endocannabinoid system and associative learning and memory in zebrafish.

    Science.gov (United States)

    Ruhl, Tim; Moesbauer, Kirstin; Oellers, Nadine; von der Emde, Gerhard

    2015-09-01

    In zebrafish the medial pallium of the dorsal telencephalon represents an amygdala homolog structure, which is crucially involved in emotional associative learning and memory. Similar to the mammalian amygdala, the medial pallium contains a high density of endocannabinoid receptor CB1. To elucidate the role of the zebrafish endocannabinoid system in associative learning, we tested the influence of acute and chronic administration of receptor agonists (THC, WIN55,212-2) and antagonists (Rimonabant, AM-281) on two different learning paradigms. In an appetitively motivated two-alternative choice paradigm, animals learned to associate a certain color with a food reward. In a second set-up, a fish shuttle-box, animals associated the onset of a light stimulus with the occurrence of a subsequent electric shock (avoidance conditioning). Once fish successfully had learned to solve these behavioral tasks, acute receptor activation or inactivation had no effect on memory retrieval, suggesting that established associative memories were stable and not alterable by the endocannabinoid system. In both learning tasks, chronic treatment with receptor antagonists improved acquisition learning, and additionally facilitated reversal learning during color discrimination. In contrast, chronic CB1 activation prevented aversively motivated acquisition learning, while different effects were found on appetitively motivated acquisition learning. While THC significantly improved behavioral performance, WIN55,212-2 significantly impaired color association. Our findings suggest that the zebrafish endocannabinoid system can modulate associative learning and memory. Stimulation of the CB1 receptor might play a more specific role in acquisition and storage of aversive learning and memory, while CB1 blocking induces general enhancement of cognitive functions. Copyright © 2015 Elsevier B.V. All rights reserved.

  17. IDOCS: intelligent distributed ontology consensus system--the use of machine learning in retinal drusen phenotyping.

    Science.gov (United States)

    Thomas, George; Grassi, Michael A; Lee, John R; Edwards, Albert O; Gorin, Michael B; Klein, Ronald; Casavant, Thomas L; Scheetz, Todd E; Stone, Edwin M; Williams, Andrew B

    2007-05-01

    To use the power of knowledge acquisition and machine learning in the development of a collaborative computer classification system based on the features of age-related macular degeneration (AMD). A vocabulary was acquired from four AMD experts who examined 100 ophthalmoscopic images. The vocabulary was analyzed, hierarchically structured, and incorporated into a collaborative computer classification system called IDOCS. Using this system, three of the experts examined images from a second set of digital images compiled from more than 1000 patients with AMD. Images were annotated, and features were identified and defined. Decision trees, a machine learning method, were trained on the data collected and used to extract patterns. Interrelationships between the data from the different clinicians were investigated. Six drusen classes in the structured vocabulary were largely sufficient to describe all the identified features. The decision trees classified the data with 76.86% to 88.5% accuracy and distilled patterns in the form of hierarchical trees composed of 5 to 15 nodes. Experts were largely consistent in their characterization of soft, and to a lesser extent, hard drusen, but diverge in definition of other drusen. Size and crystalline morphology were the main determinants of drusen type across all experts. Machine learning is a powerful tool for the characterization of disease phenotypes. The creation of a defined feature set for AMD will facilitate the development of an IDOCS-based classification system.

  18. Towards a Pattern Language for Learning Management Systems

    NARCIS (Netherlands)

    Avgeriou, Paris; Papasalouros, Andreas; Retalis, Symeon; Skordalakis, Manolis

    2003-01-01

    Learning Management Systems are sophisticated web-based applications that are being engineered today in increasing numbers by numerous institutions and companies that want to get involved in e-learning either for providing services to third parties, or for educating and training their own people.

  19. Recommender Systems for Technology Enhanced Learning: Research Trends & Applications

    NARCIS (Netherlands)

    Manouselis, Nikos; Verbert, Katrien; Drachsler, Hendrik; Santos, Olga

    2014-01-01

    As an area, Technology Enhanced Learning (TEL) aims to design, develop and test socio-technical innovations that will support and enhance learning practices of individuals and organizations. Information retrieval is a pivotal activity in TEL and the deployment of recommender systems has attracted

  20. Dataset-driven research for improving recommender systems for learning

    NARCIS (Netherlands)

    Verbert, Katrien; Drachsler, Hendrik; Manouselis, Nikos; Wolpers, Martin; Vuorikari, Riina; Duval, Erik

    2011-01-01

    Verbert, K., Drachsler, H., Manouselis, N., Wolpers, M., Vuorikari, R., & Duval, E. (2011). Dataset-driven research for improving recommender systems for learning. In Ph. Long, & G. Siemens (Eds.), Proceedings of 1st International Conference Learning Analytics & Knowledge (pp. 44-53). February,