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

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.

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.

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.

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.

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.

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.

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.

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.

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

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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).

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…

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.

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...

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.

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.

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.

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.

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.

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.

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

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

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.

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...

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.

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

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

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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...

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.

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

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.

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.

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

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

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...

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...

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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...

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.

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.

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…

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.

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

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.

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.

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.

A cascade of classifiers for extracting medication information from discharge summaries

Directory of Open Access Journals (Sweden)

Halgrim Scott

2011-07-01

Full Text Available Abstract Background Extracting medication information from clinical records has many potential applications, and recently published research, systems, and competitions reflect an interest therein. Much of the early extraction work involved rules and lexicons, but more recently machine learning has been applied to the task. Methods We present a hybrid system consisting of two parts. The first part, field detection, uses a cascade of statistical classifiers to identify medication-related named entities. The second part uses simple heuristics to link those entities into medication events. Results The system achieved performance that is comparable to other approaches to the same task. This performance is further improved by adding features that reference external medication name lists. Conclusions This study demonstrates that our hybrid approach outperforms purely statistical or rule-based systems. The study also shows that a cascade of classifiers works better than a single classifier in extracting medication information. The system is available as is upon request from the first author.

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.

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

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.

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.

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

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.

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.

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.

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.

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.

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

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.

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.

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.

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,

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.

Just-in-time adaptive classifiers-part II: designing the classifier.

Science.gov (United States)

Alippi, Cesare; Roveri, Manuel

2008-12-01

Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolution adaptive solutions must be envisaged to track its dynamics; in this direction, adaptive classifiers are generally designed by assuming the stationary hypothesis for the process generating the data with very few results addressing nonstationary environments. This paper proposes a methodology based on k-nearest neighbor (NN) classifiers for designing adaptive classification systems able to react to changing conditions just-in-time (JIT), i.e., exactly when it is needed. k-NN classifiers have been selected for their computational-free training phase, the possibility to easily estimate the model complexity k and keep under control the computational complexity of the classifier through suitable data reduction mechanisms. A JIT classifier requires a temporal detection of a (possible) process deviation (aspect tackled in a companion paper) followed by an adaptive management of the knowledge base (KB) of the classifier to cope with the process change. The novelty of the proposed approach resides in the general framework supporting the real-time update of the KB of the classification system in response to novel information coming from the process both in stationary conditions (accuracy improvement) and in nonstationary ones (process tracking) and in providing a suitable estimate of k. It is shown that the classification system grants consistency once the change targets the process generating the data in a new stationary state, as it is the case in many real applications.

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.

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.

Classifying seismic waveforms from scratch: a case study in the alpine environment

Science.gov (United States)

Hammer, C.; Ohrnberger, M.; Fäh, D.

2013-01-01

Nowadays, an increasing amount of seismic data is collected by daily observatory routines. The basic step for successfully analyzing those data is the correct detection of various event types. However, the visually scanning process is a time-consuming task. Applying standard techniques for detection like the STA/LTA trigger still requires the manual control for classification. Here, we present a useful alternative. The incoming data stream is scanned automatically for events of interest. A stochastic classifier, called hidden Markov model, is learned for each class of interest enabling the recognition of highly variable waveforms. In contrast to other automatic techniques as neural networks or support vector machines the algorithm allows to start the classification from scratch as soon as interesting events are identified. Neither the tedious process of collecting training samples nor a time-consuming configuration of the classifier is required. An approach originally introduced for the volcanic task force action allows to learn classifier properties from a single waveform example and some hours of background recording. Besides a reduction of required workload this also enables to detect very rare events. Especially the latter feature provides a milestone point for the use of seismic devices in alpine warning systems. Furthermore, the system offers the opportunity to flag new signal classes that have not been defined before. We demonstrate the application of the classification system using a data set from the Swiss Seismological Survey achieving very high recognition rates. In detail we document all refinements of the classifier providing a step-by-step guide for the fast set up of a well-working classification system.

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.

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.

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

Naive Bayes as opinion classifier to evaluate students satisfaction based on student sentiment in Twitter Social Media

Science.gov (United States)

Candra Permana, Fahmi; Rosmansyah, Yusep; Setiawan Abdullah, Atje

2017-10-01

Students activity on social media can provide implicit knowledge and new perspectives for an educational system. Sentiment analysis is a part of text mining that can help to analyze and classify the opinion data. This research uses text mining and naive Bayes method as opinion classifier, to be used as an alternative methods in the process of evaluating studentss satisfaction for educational institution. Based on test results, this system can determine the opinion classification in Bahasa Indonesia using naive Bayes as opinion classifier with accuracy level of 84% correct, and the comparison between the existing system and the proposed system to evaluate students satisfaction in learning process, there is only a difference of 16.49%.

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.

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.

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.

Reducing the Complexity of Genetic Fuzzy Classifiers in Highly-Dimensional Classification Problems

Directory of Open Access Journals (Sweden)

DimitrisG. Stavrakoudis

2012-04-01

Full Text Available This paper introduces the Fast Iterative Rule-based Linguistic Classifier (FaIRLiC, a Genetic Fuzzy Rule-Based Classification System (GFRBCS which targets at reducing the structural complexity of the resulting rule base, as well as its learning algorithm's computational requirements, especially when dealing with high-dimensional feature spaces. The proposed methodology follows the principles of the iterative rule learning (IRL approach, whereby a rule extraction algorithm (REA is invoked in an iterative fashion, producing one fuzzy rule at a time. The REA is performed in two successive steps: the first one selects the relevant features of the currently extracted rule, whereas the second one decides the antecedent part of the fuzzy rule, using the previously selected subset of features. The performance of the classifier is finally optimized through a genetic tuning post-processing stage. Comparative results in a hyperspectral remote sensing classification as well as in 12 real-world classification datasets indicate the effectiveness of the proposed methodology in generating high-performing and compact fuzzy rule-based classifiers, even for very high-dimensional feature spaces.

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.

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.

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.

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

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.

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.

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...

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.

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...

SAR Target Recognition Based on Multi-feature Multiple Representation Classifier Fusion

Directory of Open Access Journals (Sweden)

Zhang Xinzheng

2017-10-01

Full Text Available In this paper, we present a Synthetic Aperture Radar (SAR image target recognition algorithm based on multi-feature multiple representation learning classifier fusion. First, it extracts three features from the SAR images, namely principal component analysis, wavelet transform, and Two-Dimensional Slice Zernike Moments (2DSZM features. Second, we harness the sparse representation classifier and the cooperative representation classifier with the above-mentioned features to get six predictive labels. Finally, we adopt classifier fusion to obtain the final recognition decision. We researched three different classifier fusion algorithms in our experiments, and the results demonstrate thatusing Bayesian decision fusion gives thebest recognition performance. The method based on multi-feature multiple representation learning classifier fusion integrates the discrimination of multi-features and combines the sparse and cooperative representation classification performance to gain complementary advantages and to improve recognition accuracy. The experiments are based on the Moving and Stationary Target Acquisition and Recognition (MSTAR database,and they demonstrate the effectiveness of the proposed approach.

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

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.

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.

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.

Deep convolutional neural network for classifying Fusarium wilt of radish from unmanned aerial vehicles

Science.gov (United States)

Ha, Jin Gwan; Moon, Hyeonjoon; Kwak, Jin Tae; Hassan, Syed Ibrahim; Dang, Minh; Lee, O. New; Park, Han Yong

2017-10-01

Recently, unmanned aerial vehicles (UAVs) have gained much attention. In particular, there is a growing interest in utilizing UAVs for agricultural applications such as crop monitoring and management. We propose a computerized system that is capable of detecting Fusarium wilt of radish with high accuracy. The system adopts computer vision and machine learning techniques, including deep learning, to process the images captured by UAVs at low altitudes and to identify the infected radish. The whole radish field is first segmented into three distinctive regions (radish, bare ground, and mulching film) via a softmax classifier and K-means clustering. Then, the identified radish regions are further classified into healthy radish and Fusarium wilt of radish using a deep convolutional neural network (CNN). In identifying radish, bare ground, and mulching film from a radish field, we achieved an accuracy of ≥97.4%. In detecting Fusarium wilt of radish, the CNN obtained an accuracy of 93.3%. It also outperformed the standard machine learning algorithm, obtaining 82.9% accuracy. Therefore, UAVs equipped with computational techniques are promising tools for improving the quality and efficiency of agriculture today.

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.

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)

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.

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

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.

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.

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.

Stereo vision with texture learning for fault-tolerant automatic baling

DEFF Research Database (Denmark)

Blas, Morten Rufus; Blanke, Mogens

2010-01-01

This paper presents advances in using stereovision for automating baling. A robust classification scheme is demonstrated for learning and classifying based on texture and shape. Using a state-of-the-art texton approach a fast classifier is obtained that can handle non-linearities in the data....... The addition of shape information makes the method robust to large variations and greatly reduces false alarms by applying tight geometrical constraints. The classifier is tested on data from a stereovision guidance system on a tractor. The system is able to classify cut plant material (called swath......) by learning it's appearance. A 3D classifier is used to train and supervise the texture classifier....

An SVM classifier to separate false signals from microcalcifications in digital mammograms

Energy Technology Data Exchange (ETDEWEB)

Bazzani, Armando; Bollini, Dante; Brancaccio, Rosa; Campanini, Renato; Riccardi, Alessandro; Romani, Davide [Department of Physics, University of Bologna (Italy); INFN, Bologna (Italy); Lanconelli, Nico [Department of Physics, University of Bologna, and INFN, Bologna (Italy). E-mail: nico.lanconelli@bo.infn.it; Bevilacqua, Alessandro [Department of Electronics, Computer Science and Systems, University of Bologna, and INFN, Bologna (Italy)

2001-06-01

In this paper we investigate the feasibility of using an SVM (support vector machine) classifier in our automatic system for the detection of clustered microcalcifications in digital mammograms. SVM is a technique for pattern recognition which relies on the statistical learning theory. It minimizes a function of two terms: the number of misclassified vectors of the training set and a term regarding the generalization classifier capability. We compare the SVM classifier with an MLP (multi-layer perceptron) in the false-positive reduction phase of our detection scheme: a detected signal is considered either microcalcification or false signal, according to the value of a set of its features. The SVM classifier gets slightly better results than the MLP one (Az value of 0.963 against 0.958) in the presence of a high number of training data; the improvement becomes much more evident (Az value of 0.952 against 0.918) in training sets of reduced size. Finally, the setting of the SVM classifier is much easier than the MLP one. (author)

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)

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…

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

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.

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...

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.

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.

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.

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

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

Application of SVM classifier in thermographic image classification for early detection of breast cancer

Science.gov (United States)

Oleszkiewicz, Witold; Cichosz, Paweł; Jagodziński, Dariusz; Matysiewicz, Mateusz; Neumann, Łukasz; Nowak, Robert M.; Okuniewski, Rafał

2016-09-01

This article presents the application of machine learning algorithms for early detection of breast cancer on the basis of thermographic images. Supervised learning model: Support vector machine (SVM) and Sequential Minimal Optimization algorithm (SMO) for the training of SVM classifier were implemented. The SVM classifier was included in a client-server application which enables to create a training set of examinations and to apply classifiers (including SVM) for the diagnosis and early detection of the breast cancer. The sensitivity and specificity of SVM classifier were calculated based on the thermographic images from studies. Furthermore, the heuristic method for SVM's parameters tuning was proposed.

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.

Fusion of classifiers for REIS-based detection of suspicious breast lesions

Science.gov (United States)

Lederman, Dror; Wang, Xingwei; Zheng, Bin; Sumkin, Jules H.; Tublin, Mitchell; Gur, David

2011-03-01

After developing a multi-probe resonance-frequency electrical impedance spectroscopy (REIS) system aimed at detecting women with breast abnormalities that may indicate a developing breast cancer, we have been conducting a prospective clinical study to explore the feasibility of applying this REIS system to classify younger women (breast cancer. The system comprises one central probe placed in contact with the nipple, and six additional probes uniformly distributed along an outside circle to be placed in contact with six points on the outer breast skin surface. In this preliminary study, we selected an initial set of 174 examinations on participants that have completed REIS examinations and have clinical status verification. Among these, 66 examinations were recommended for biopsy due to findings of a highly suspicious breast lesion ("positives"), and 108 were determined as negative during imaging based procedures ("negatives"). A set of REIS-based features, extracted using a mirror-matched approach, was computed and fed into five machine learning classifiers. A genetic algorithm was used to select an optimal subset of features for each of the five classifiers. Three fusion rules, namely sum rule, weighted sum rule and weighted median rule, were used to combine the results of the classifiers. Performance evaluation was performed using a leave-one-case-out cross-validation method. The results indicated that REIS may provide a new technology to identify younger women with higher than average risk of having or developing breast cancer. Furthermore, it was shown that fusion rule, such as a weighted median fusion rule and a weighted sum fusion rule may improve performance as compared with the highest performing single classifier.

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.

Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers

OpenAIRE

Rosenberg, Ishai; Shabtai, Asaf; Rokach, Lior; Elovici, Yuval

2017-01-01

In this paper, we present a black-box attack against API call based machine learning malware classifiers, focusing on generating adversarial sequences combining API calls and static features (e.g., printable strings) that will be misclassified by the classifier without affecting the malware functionality. We show that this attack is effective against many classifiers due to the transferability principle between RNN variants, feed forward DNNs, and traditional machine learning classifiers such...

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.

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.

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.

Maximum margin classifier working in a set of strings.

Science.gov (United States)

Koyano, Hitoshi; Hayashida, Morihiro; Akutsu, Tatsuya

2016-03-01

Numbers and numerical vectors account for a large portion of data. However, recently, the amount of string data generated has increased dramatically. Consequently, classifying string data is a common problem in many fields. The most widely used approach to this problem is to convert strings into numerical vectors using string kernels and subsequently apply a support vector machine that works in a numerical vector space. However, this non-one-to-one conversion involves a loss of information and makes it impossible to evaluate, using probability theory, the generalization error of a learning machine, considering that the given data to train and test the machine are strings generated according to probability laws. In this study, we approach this classification problem by constructing a classifier that works in a set of strings. To evaluate the generalization error of such a classifier theoretically, probability theory for strings is required. Therefore, we first extend a limit theorem for a consensus sequence of strings demonstrated by one of the authors and co-workers in a previous study. Using the obtained result, we then demonstrate that our learning machine classifies strings in an asymptotically optimal manner. Furthermore, we demonstrate the usefulness of our machine in practical data analysis by applying it to predicting protein-protein interactions using amino acid sequences and classifying RNAs by the secondary structure using nucleotide sequences.

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.

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.

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.

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.

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....

Machine learning algorithms for the creation of clinical healthcare enterprise systems

Science.gov (United States)

Mandal, Indrajit

2017-10-01

Clinical recommender systems are increasingly becoming popular for improving modern healthcare systems. Enterprise systems are persuasively used for creating effective nurse care plans to provide nurse training, clinical recommendations and clinical quality control. A novel design of a reliable clinical recommender system based on multiple classifier system (MCS) is implemented. A hybrid machine learning (ML) ensemble based on random subspace method and random forest is presented. The performance accuracy and robustness of proposed enterprise architecture are quantitatively estimated to be above 99% and 97%, respectively (above 95% confidence interval). The study then extends to experimental analysis of the clinical recommender system with respect to the noisy data environment. The ranking of items in nurse care plan is demonstrated using machine learning algorithms (MLAs) to overcome the drawback of the traditional association rule method. The promising experimental results are compared against the sate-of-the-art approaches to highlight the advancement in recommendation technology. The proposed recommender system is experimentally validated using five benchmark clinical data to reinforce the research findings.

General and Local: Averaged k-Dependence Bayesian Classifiers

Directory of Open Access Journals (Sweden)

Limin Wang

2015-06-01

Full Text Available The inference of a general Bayesian network has been shown to be an NP-hard problem, even for approximate solutions. Although k-dependence Bayesian (KDB classifier can construct at arbitrary points (values of k along the attribute dependence spectrum, it cannot identify the changes of interdependencies when attributes take different values. Local KDB, which learns in the framework of KDB, is proposed in this study to describe the local dependencies implicated in each test instance. Based on the analysis of functional dependencies, substitution-elimination resolution, a new type of semi-naive Bayesian operation, is proposed to substitute or eliminate generalization to achieve accurate estimation of conditional probability distribution while reducing computational complexity. The final classifier, averaged k-dependence Bayesian (AKDB classifiers, will average the output of KDB and local KDB. Experimental results on the repository of machine learning databases from the University of California Irvine (UCI showed that AKDB has significant advantages in zero-one loss and bias relative to naive Bayes (NB, tree augmented naive Bayes (TAN, Averaged one-dependence estimators (AODE, and KDB. Moreover, KDB and local KDB show mutually complementary characteristics with respect to variance.

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...

Implications of physical symmetries in adaptive image classifiers

DEFF Research Database (Denmark)

Sams, Thomas; Hansen, Jonas Lundbek

2000-01-01

It is demonstrated that rotational invariance and reflection symmetry of image classifiers lead to a reduction in the number of free parameters in the classifier. When used in adaptive detectors, e.g. neural networks, this may be used to decrease the number of training samples necessary to learn...... a given classification task, or to improve generalization of the neural network. Notably, the symmetrization of the detector does not compromise the ability to distinguish objects that break the symmetry. (C) 2000 Elsevier Science Ltd. All rights reserved....

Feature extraction using convolutional neural network for classifying breast density in mammographic images

Science.gov (United States)

Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

2017-03-01

Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is

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

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.

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.

A Topic Model Approach to Representing and Classifying Football Plays

KAUST Repository

Varadarajan, Jagannadan

2013-09-09

We address the problem of modeling and classifying American Football offense teams’ plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more ef- ficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. To this end, we develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximiza- tion of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.

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

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...

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.

Reconfigurable support vector machine classifier with approximate computing

NARCIS (Netherlands)

van Leussen, M.J.; Huisken, J.; Wang, L.; Jiao, H.; De Gyvez, J.P.

2017-01-01

Support Vector Machine (SVM) is one of the most popular machine learning algorithms. An energy-efficient SVM classifier is proposed in this paper, where approximate computing is utilized to reduce energy consumption and silicon area. A hardware architecture with reconfigurable kernels and

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.

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

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.

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.

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.

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.

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.

Using Neural Networks to Classify Digitized Images of Galaxies

Science.gov (United States)

Goderya, S. N.; McGuire, P. C.

2000-12-01

Automated classification of Galaxies into Hubble types is of paramount importance to study the large scale structure of the Universe, particularly as survey projects like the Sloan Digital Sky Survey complete their data acquisition of one million galaxies. At present it is not possible to find robust and efficient artificial intelligence based galaxy classifiers. In this study we will summarize progress made in the development of automated galaxy classifiers using neural networks as machine learning tools. We explore the Bayesian linear algorithm, the higher order probabilistic network, the multilayer perceptron neural network and Support Vector Machine Classifier. The performance of any machine classifier is dependant on the quality of the parameters that characterize the different groups of galaxies. Our effort is to develop geometric and invariant moment based parameters as input to the machine classifiers instead of the raw pixel data. Such an approach reduces the dimensionality of the classifier considerably, and removes the effects of scaling and rotation, and makes it easier to solve for the unknown parameters in the galaxy classifier. To judge the quality of training and classification we develop the concept of Mathews coefficients for the galaxy classification community. Mathews coefficients are single numbers that quantify classifier performance even with unequal prior probabilities of the classes.

Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach.

Science.gov (United States)

Weng, Wei-Hung; Wagholikar, Kavishwar B; McCray, Alexa T; Szolovits, Peter; Chueh, Henry C

2017-12-01

The medical subdomain of a clinical note, such as cardiology or neurology, is useful content-derived metadata for developing machine learning downstream applications. To classify the medical subdomain of a note accurately, we have constructed a machine learning-based natural language processing (NLP) pipeline and developed medical subdomain classifiers based on the content of the note. We constructed the pipeline using the clinical NLP system, clinical Text Analysis and Knowledge Extraction System (cTAKES), the Unified Medical Language System (UMLS) Metathesaurus, Semantic Network, and learning algorithms to extract features from two datasets - clinical notes from Integrating Data for Analysis, Anonymization, and Sharing (iDASH) data repository (n = 431) and Massachusetts General Hospital (MGH) (n = 91,237), and built medical subdomain classifiers with different combinations of data representation methods and supervised learning algorithms. We evaluated the performance of classifiers and their portability across the two datasets. The convolutional recurrent neural network with neural word embeddings trained-medical subdomain classifier yielded the best performance measurement on iDASH and MGH datasets with area under receiver operating characteristic curve (AUC) of 0.975 and 0.991, and F1 scores of 0.845 and 0.870, respectively. Considering better clinical interpretability, linear support vector machine-trained medical subdomain classifier using hybrid bag-of-words and clinically relevant UMLS concepts as the feature representation, with term frequency-inverse document frequency (tf-idf)-weighting, outperformed other shallow learning classifiers on iDASH and MGH datasets with AUC of 0.957 and 0.964, and F1 scores of 0.932 and 0.934 respectively. We trained classifiers on one dataset, applied to the other dataset and yielded the threshold of F1 score of 0.7 in classifiers for half of the medical subdomains we studied. Our study shows that a supervised

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 .

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...

Differential profiling of volatile organic compound biomarker signatures utilizing a logical statistical filter-set and novel hybrid evolutionary classifiers

Science.gov (United States)

Grigsby, Claude C.; Zmuda, Michael A.; Boone, Derek W.; Highlander, Tyler C.; Kramer, Ryan M.; Rizki, Mateen M.

2012-06-01

A growing body of discoveries in molecular signatures has revealed that volatile organic compounds (VOCs), the small molecules associated with an individual's odor and breath, can be monitored to reveal the identity and presence of a unique individual, as well their overall physiological status. Given the analysis requirements for differential VOC profiling via gas chromatography/mass spectrometry, our group has developed a novel informatics platform, Metabolite Differentiation and Discovery Lab (MeDDL). In its current version, MeDDL is a comprehensive tool for time-series spectral registration and alignment, visualization, comparative analysis, and machine learning to facilitate the efficient analysis of multiple, large-scale biomarker discovery studies. The MeDDL toolset can therefore identify a large differential subset of registered peaks, where their corresponding intensities can be used as features for classification. This initial screening of peaks yields results sets that are typically too large for incorporation into a portable, electronic nose based system in addition to including VOCs that are not amenable to classification; consequently, it is also important to identify an optimal subset of these peaks to increase classification accuracy and to decrease the cost of the final system. MeDDL's learning tools include a classifier similar to a K-nearest neighbor classifier used in conjunction with a genetic algorithm (GA) that simultaneously optimizes the classifier and subset of features. The GA uses ROC curves to produce classifiers having maximal area under their ROC curve. Experimental results on over a dozen recognition problems show many examples of classifiers and feature sets that produce perfect ROC curves.

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...

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.

Learning based particle filtering object tracking for visible-light systems.

Science.gov (United States)

Sun, Wei

2015-10-01

We propose a novel object tracking framework based on online learning scheme that can work robustly in challenging scenarios. Firstly, a learning-based particle filter is proposed with color and edge-based features. We train a. support vector machine (SVM) classifier with object and background information and map the outputs into probabilities, then the weight of particles in a particle filter can be calculated by the probabilistic outputs to estimate the state of the object. Secondly, the tracking loop starts with Lucas-Kanade (LK) affine template matching and follows by learning-based particle filter tracking. Lucas-Kanade method estimates errors and updates object template in the positive samples dataset, and learning-based particle filter tracker will start if the LK tracker loses the object. Finally, SVM classifier evaluates every tracked appearance to update the training set or restart the tracking loop if necessary. Experimental results show that our method is robust to challenging light, scale and pose changing, and test on eButton image sequence also achieves satisfactory tracking performance.

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.

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…

Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies

Science.gov (United States)

Theis, Fabian J.

2017-01-01

Epidemiological studies often utilize stratified data in which rare outcomes or exposures are artificially enriched. This design can increase precision in association tests but distorts predictions when applying classifiers on nonstratified data. Several methods correct for this so-called sample selection bias, but their performance remains unclear especially for machine learning classifiers. With an emphasis on two-phase case-control studies, we aim to assess which corrections to perform in which setting and to obtain methods suitable for machine learning techniques, especially the random forest. We propose two new resampling-based methods to resemble the original data and covariance structure: stochastic inverse-probability oversampling and parametric inverse-probability bagging. We compare all techniques for the random forest and other classifiers, both theoretically and on simulated and real data. Empirical results show that the random forest profits from only the parametric inverse-probability bagging proposed by us. For other classifiers, correction is mostly advantageous, and methods perform uniformly. We discuss consequences of inappropriate distribution assumptions and reason for different behaviors between the random forest and other classifiers. In conclusion, we provide guidance for choosing correction methods when training classifiers on biased samples. For random forests, our method outperforms state-of-the-art procedures if distribution assumptions are roughly fulfilled. We provide our implementation in the R package sambia. PMID:29312464

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.

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.

A Nearest Neighbor Classifier Employing Critical Boundary Vectors for Efficient On-Chip Template Reduction.

Science.gov (United States)

Xia, Wenjun; Mita, Yoshio; Shibata, Tadashi

2016-05-01

Aiming at efficient data condensation and improving accuracy, this paper presents a hardware-friendly template reduction (TR) method for the nearest neighbor (NN) classifiers by introducing the concept of critical boundary vectors. A hardware system is also implemented to demonstrate the feasibility of using an field-programmable gate array (FPGA) to accelerate the proposed method. Initially, k -means centers are used as substitutes for the entire template set. Then, to enhance the classification performance, critical boundary vectors are selected by a novel learning algorithm, which is completed within a single iteration. Moreover, to remove noisy boundary vectors that can mislead the classification in a generalized manner, a global categorization scheme has been explored and applied to the algorithm. The global characterization automatically categorizes each classification problem and rapidly selects the boundary vectors according to the nature of the problem. Finally, only critical boundary vectors and k -means centers are used as the new template set for classification. Experimental results for 24 data sets show that the proposed algorithm can effectively reduce the number of template vectors for classification with a high learning speed. At the same time, it improves the accuracy by an average of 2.17% compared with the traditional NN classifiers and also shows greater accuracy than seven other TR methods. We have shown the feasibility of using a proof-of-concept FPGA system of 256 64-D vectors to accelerate the proposed method on hardware. At a 50-MHz clock frequency, the proposed system achieves a 3.86 times higher learning speed than on a 3.4-GHz PC, while consuming only 1% of the power of that used by the PC.

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

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.

A Novel Cascade Classifier for Automatic Microcalcification Detection.

Directory of Open Access Journals (Sweden)

Seung Yeon Shin

Full Text Available In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC. Our framework comprises three classification stages: i a random forest (RF classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii a more complex discriminative restricted Boltzmann machine (DRBM classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC curve for detection of clustered μCs.

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.

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....

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.

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...

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.

Visual Thing Recognition with Binary Scale-Invariant Feature Transform and Support Vector Machine Classifiers Using Color Information

OpenAIRE

Wei-Jong Yang; Wei-Hau Du; Pau-Choo Chang; Jar-Ferr Yang; Pi-Hsia Hung

2017-01-01

The demands of smart visual thing recognition in various devices have been increased rapidly for daily smart production, living and learning systems in recent years. This paper proposed a visual thing recognition system, which combines binary scale-invariant feature transform (SIFT), bag of words model (BoW), and support vector machine (SVM) by using color information. Since the traditional SIFT features and SVM classifiers only use the gray information, color information is still an importan...

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.

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.

Feature selection and classification of mechanical fault of an induction motor using random forest classifier

OpenAIRE

Patel, Raj Kumar; Giri, V.K.

2016-01-01

Fault detection and diagnosis is the most important technology in condition-based maintenance (CBM) system for rotating machinery. This paper experimentally explores the development of a random forest (RF) classifier, a recently emerged machine learning technique, for multi-class mechanical fault diagnosis in bearing of an induction motor. Firstly, the vibration signals are collected from the bearing using accelerometer sensor. Parameters from the vibration signal are extracted in the form of...

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.

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.

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.

Building gene expression profile classifiers with a simple and efficient rejection option in R.

Science.gov (United States)

Benso, Alfredo; Di Carlo, Stefano; Politano, Gianfranco; Savino, Alessandro; Hafeezurrehman, Hafeez

2011-01-01

The collection of gene expression profiles from DNA microarrays and their analysis with pattern recognition algorithms is a powerful technology applied to several biological problems. Common pattern recognition systems classify samples assigning them to a set of known classes. However, in a clinical diagnostics setup, novel and unknown classes (new pathologies) may appear and one must be able to reject those samples that do not fit the trained model. The problem of implementing a rejection option in a multi-class classifier has not been widely addressed in the statistical literature. Gene expression profiles represent a critical case study since they suffer from the curse of dimensionality problem that negatively reflects on the reliability of both traditional rejection models and also more recent approaches such as one-class classifiers. This paper presents a set of empirical decision rules that can be used to implement a rejection option in a set of multi-class classifiers widely used for the analysis of gene expression profiles. In particular, we focus on the classifiers implemented in the R Language and Environment for Statistical Computing (R for short in the remaining of this paper). The main contribution of the proposed rules is their simplicity, which enables an easy integration with available data analysis environments. Since in the definition of a rejection model tuning of the involved parameters is often a complex and delicate task, in this paper we exploit an evolutionary strategy to automate this process. This allows the final user to maximize the rejection accuracy with minimum manual intervention. This paper shows how the use of simple decision rules can be used to help the use of complex machine learning algorithms in real experimental setups. The proposed approach is almost completely automated and therefore a good candidate for being integrated in data analysis flows in labs where the machine learning expertise required to tune traditional

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.

Joint Feature Extraction and Classifier Design for ECG-Based Biometric Recognition.

Science.gov (United States)

Gutta, Sandeep; Cheng, Qi

2016-03-01

Traditional biometric recognition systems often utilize physiological traits such as fingerprint, face, iris, etc. Recent years have seen a growing interest in electrocardiogram (ECG)-based biometric recognition techniques, especially in the field of clinical medicine. In existing ECG-based biometric recognition methods, feature extraction and classifier design are usually performed separately. In this paper, a multitask learning approach is proposed, in which feature extraction and classifier design are carried out simultaneously. Weights are assigned to the features within the kernel of each task. We decompose the matrix consisting of all the feature weights into sparse and low-rank components. The sparse component determines the features that are relevant to identify each individual, and the low-rank component determines the common feature subspace that is relevant to identify all the subjects. A fast optimization algorithm is developed, which requires only the first-order information. The performance of the proposed approach is demonstrated through experiments using the MIT-BIH Normal Sinus Rhythm database.

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.

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.

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.

Vandalism Detection in Wikipedia: a Bag-of-Words Classifier Approach

OpenAIRE

Belani, Amit

2010-01-01

A bag-of-words based probabilistic classifier is trained using regularized logistic regression to detect vandalism in the English Wikipedia. Isotonic regression is used to calibrate the class membership probabilities. Learning curve, reliability, ROC, and cost analysis are performed.

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.

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.

Algorithms for Image Analysis and Combination of Pattern Classifiers with Application to Medical Diagnosis

Science.gov (United States)

Georgiou, Harris

2009-10-01

Medical Informatics and the application of modern signal processing in the assistance of the diagnostic process in medical imaging is one of the more recent and active research areas today. This thesis addresses a variety of issues related to the general problem of medical image analysis, specifically in mammography, and presents a series of algorithms and design approaches for all the intermediate levels of a modern system for computer-aided diagnosis (CAD). The diagnostic problem is analyzed with a systematic approach, first defining the imaging characteristics and features that are relevant to probable pathology in mammo-grams. Next, these features are quantified and fused into new, integrated radio-logical systems that exhibit embedded digital signal processing, in order to improve the final result and minimize the radiological dose for the patient. In a higher level, special algorithms are designed for detecting and encoding these clinically interest-ing imaging features, in order to be used as input to advanced pattern classifiers and machine learning models. Finally, these approaches are extended in multi-classifier models under the scope of Game Theory and optimum collective deci-sion, in order to produce efficient solutions for combining classifiers with minimum computational costs for advanced diagnostic systems. The material covered in this thesis is related to a total of 18 published papers, 6 in scientific journals and 12 in international conferences.

Classification and learning using genetic algorithms applications in Bioinformatics and Web Intelligence

CERN Document Server

Bandyopadhyay, Sanghamitra

2007-01-01

This book provides a unified framework that describes how genetic learning can be used to design pattern recognition and learning systems. It examines how a search technique, the genetic algorithm, can be used for pattern classification mainly through approximating decision boundaries. Coverage also demonstrates the effectiveness of the genetic classifiers vis-à-vis several widely used classifiers, including neural networks.

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

Supervised machine learning and active learning in classification of radiology reports.

Science.gov (United States)

Nguyen, Dung H M; Patrick, Jon D

2014-01-01

This paper presents an automated system for classifying the results of imaging examinations (CT, MRI, positron emission tomography) into reportable and non-reportable cancer cases. This system is part of an industrial-strength processing pipeline built to extract content from radiology reports for use in the Victorian Cancer Registry. In addition to traditional supervised learning methods such as conditional random fields and support vector machines, active learning (AL) approaches were investigated to optimize training production and further improve classification performance. The project involved two pilot sites in Victoria, Australia (Lake Imaging (Ballarat) and Peter MacCallum Cancer Centre (Melbourne)) and, in collaboration with the NSW Central Registry, one pilot site at Westmead Hospital (Sydney). The reportability classifier performance achieved 98.25% sensitivity and 96.14% specificity on the cancer registry's held-out test set. Up to 92% of training data needed for supervised machine learning can be saved by AL. AL is a promising method for optimizing the supervised training production used in classification of radiology reports. When an AL strategy is applied during the data selection process, the cost of manual classification can be reduced significantly. The most important practical application of the reportability classifier is that it can dramatically reduce human effort in identifying relevant reports from the large imaging pool for further investigation of cancer. The classifier is built on a large real-world dataset and can achieve high performance in filtering relevant reports to support cancer registries. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

Use of information barriers to protect classified information

International Nuclear Information System (INIS)

MacArthur, D.; Johnson, M.W.; Nicholas, N.J.; Whiteson, R.

1998-01-01

This paper discusses the detailed requirements for an information barrier (IB) for use with verification systems that employ intrusive measurement technologies. The IB would protect classified information in a bilateral or multilateral inspection of classified fissile material. Such a barrier must strike a balance between providing the inspecting party the confidence necessary to accept the measurement while protecting the inspected party's classified information. The authors discuss the structure required of an IB as well as the implications of the IB on detector system maintenance. A defense-in-depth approach is proposed which would provide assurance to the inspected party that all sensitive information is protected and to the inspecting party that the measurements are being performed as expected. The barrier could include elements of physical protection (such as locks, surveillance systems, and tamper indicators), hardening of key hardware components, assurance of capabilities and limitations of hardware and software systems, administrative controls, validation and verification of the systems, and error detection and resolution. Finally, an unclassified interface could be used to display and, possibly, record measurement results. The introduction of an IB into an analysis system may result in many otherwise innocuous components (detectors, analyzers, etc.) becoming classified and unavailable for routine maintenance by uncleared personnel. System maintenance and updating will be significantly simplified if the classification status of as many components as possible can be made reversible (i.e. the component can become unclassified following the removal of classified objects)

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.

An automated, high-throughput plant phenotyping system using machine learning-based plant segmentation and image analysis.

Science.gov (United States)

Lee, Unseok; Chang, Sungyul; Putra, Gian Anantrio; Kim, Hyoungseok; Kim, Dong Hwan

2018-01-01

A high-throughput plant phenotyping system automatically observes and grows many plant samples. Many plant sample images are acquired by the system to determine the characteristics of the plants (populations). Stable image acquisition and processing is very important to accurately determine the characteristics. However, hardware for acquiring plant images rapidly and stably, while minimizing plant stress, is lacking. Moreover, most software cannot adequately handle large-scale plant imaging. To address these problems, we developed a new, automated, high-throughput plant phenotyping system using simple and robust hardware, and an automated plant-imaging-analysis pipeline consisting of machine-learning-based plant segmentation. Our hardware acquires images reliably and quickly and minimizes plant stress. Furthermore, the images are processed automatically. In particular, large-scale plant-image datasets can be segmented precisely using a classifier developed using a superpixel-based machine-learning algorithm (Random Forest), and variations in plant parameters (such as area) over time can be assessed using the segmented images. We performed comparative evaluations to identify an appropriate learning algorithm for our proposed system, and tested three robust learning algorithms. We developed not only an automatic analysis pipeline but also a convenient means of plant-growth analysis that provides a learning data interface and visualization of plant growth trends. Thus, our system allows end-users such as plant biologists to analyze plant growth via large-scale plant image data easily.

Auto-Encoder based Deep Learning for Surface Electromyography Signal Processing

Directory of Open Access Journals (Sweden)

Marwa Farouk Ibrahim Ibrahim

2018-01-01

Full Text Available Feature extraction is taking a very vital and essential part of bio-signal processing. We need to choose one of two paths to identify and select features in any system. The most popular track is engineering handcrafted, which mainly depends on the user experience and the field of application. While the other path is feature learning, which depends on training the system on recognising and picking the best features that match the application. The main concept of feature learning is to create a model that is expected to be able to learn the best features without any human intervention instead of recourse the traditional methods for feature extraction or reduction and avoid dealing with feature extraction that depends on researcher experience. In this paper, Auto-Encoder will be utilised as a feature learning algorithm to practice the recommended model to excerpt the useful features from the surface electromyography signal. Deep learning method will be suggested by using Auto-Encoder to learn features. Wavelet Packet, Spectrogram, and Wavelet will be employed to represent the surface electromyography signal in our recommended model. Then, the newly represented bio-signal will be fed to stacked autoencoder (2 stages to learn features and finally, the behaviour of the proposed algorithm will be estimated by hiring different classifiers such as Extreme Learning Machine, Support Vector Machine, and SoftMax Layer. The Rectified Linear Unit (ReLU will be created as an activation function for extreme learning machine classifier besides existing functions such as sigmoid and radial basis function. ReLU will show a better classification ability than sigmoid and Radial basis function (RBF for wavelet, Wavelet scale 5 and wavelet packet signal representations implemented techniques. ReLU will illustrate better classification ability, as an activation function, than sigmoid and poorer than RBF for spectrogram signal representation. Both confidence interval and

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…

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.

On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation.

Directory of Open Access Journals (Sweden)

Sebastian Bach

Full Text Available Understanding and interpreting classification decisions of automated image classification systems is of high value in many applications, as it allows to verify the reasoning of the system and provides additional information to the human expert. Although machine learning methods are solving very successfully a plethora of tasks, they have in most cases the disadvantage of acting as a black box, not providing any information about what made them arrive at a particular decision. This work proposes a general solution to the problem of understanding classification decisions by pixel-wise decomposition of nonlinear classifiers. We introduce a methodology that allows to visualize the contributions of single pixels to predictions for kernel-based classifiers over Bag of Words features and for multilayered neural networks. These pixel contributions can be visualized as heatmaps and are provided to a human expert who can intuitively not only verify the validity of the classification decision, but also focus further analysis on regions of potential interest. We evaluate our method for classifiers trained on PASCAL VOC 2009 images, synthetic image data containing geometric shapes, the MNIST handwritten digits data set and for the pre-trained ImageNet model available as part of the Caffe open source package.

Symbol manipulation and rule learning in spiking neuronal networks.

Science.gov (United States)

Fernando, Chrisantha

2011-04-21

It has been claimed that the productivity, systematicity and compositionality of human language and thought necessitate the existence of a physical symbol system (PSS) in the brain. Recent discoveries about temporal coding suggest a novel type of neuronal implementation of a physical symbol system. Furthermore, learning classifier systems provide a plausible algorithmic basis by which symbol re-write rules could be trained to undertake behaviors exhibiting systematicity and compositionality, using a kind of natural selection of re-write rules in the brain, We show how the core operation of a learning classifier system, namely, the replication with variation of symbol re-write rules, can be implemented using spike-time dependent plasticity based supervised learning. As a whole, the aim of this paper is to integrate an algorithmic and an implementation level description of a neuronal symbol system capable of sustaining systematic and compositional behaviors. Previously proposed neuronal implementations of symbolic representations are compared with this new proposal. Copyright © 2011 Elsevier Ltd. All rights reserved.

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.

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.

Ensemble Clustering Classification Applied to Competing SVM and One-Class Classifiers Exemplified by Plant MicroRNAs Data

Directory of Open Access Journals (Sweden)

Yousef Malik

2016-12-01

Full Text Available The performance of many learning and data mining algorithms depends critically on suitable metrics to assess efficiency over the input space. Learning a suitable metric from examples may, therefore, be the key to successful application of these algorithms. We have demonstrated that the k-nearest neighbor (kNN classification can be significantly improved by learning a distance metric from labeled examples. The clustering ensemble is used to define the distance between points in respect to how they co-cluster. This distance is then used within the framework of the kNN algorithm to define a classifier named ensemble clustering kNN classifier (EC-kNN. In many instances in our experiments we achieved highest accuracy while SVM failed to perform as well. In this study, we compare the performance of a two-class classifier using EC-kNN with different one-class and two-class classifiers. The comparison was applied to seven different plant microRNA species considering eight feature selection methods. In this study, the averaged results show that EC-kNN outperforms all other methods employed here and previously published results for the same data. In conclusion, this study shows that the chosen classifier shows high performance when the distance metric is carefully chosen.

Analysis of applications suitable for mobile learning of preschool children

OpenAIRE

Stoimenovski, Aleksandar; Kraleva, Radoslava; Kralev, Velin

2016-01-01

This article considers the use of mobile learning in Bulgarian education by young children. The most used mobile operating systems are analyzed. Also some of the most used existing applications suitable for mobile learning of preschool children are presented and classified. Keywords: Mobile applications for preschool children, mobile learning.

Case base classification on digital mammograms: improving the performance of case base classifier

Science.gov (United States)

Raman, Valliappan; Then, H. H.; Sumari, Putra; Venkatesa Mohan, N.

2011-10-01

Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. The aim of the research presented here is in twofold. First stage of research involves machine learning techniques, which segments and extracts features from the mass of digital mammograms. Second level is on problem solving approach which includes classification of mass by performance based case base classifier. In this paper we build a case-based Classifier in order to diagnose mammographic images. We explain different methods and behaviors that have been added to the classifier to improve the performance of the classifier. Currently the initial Performance base Classifier with Bagging is proposed in the paper and it's been implemented and it shows an improvement in specificity and sensitivity.

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.

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

[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.

SVM classifier on chip for melanoma detection.

Science.gov (United States)

Afifi, Shereen; GholamHosseini, Hamid; Sinha, Roopak

2017-07-01

Support Vector Machine (SVM) is a common classifier used for efficient classification with high accuracy. SVM shows high accuracy for classifying melanoma (skin cancer) clinical images within computer-aided diagnosis systems used by skin cancer specialists to detect melanoma early and save lives. We aim to develop a medical low-cost handheld device that runs a real-time embedded SVM-based diagnosis system for use in primary care for early detection of melanoma. In this paper, an optimized SVM classifier is implemented onto a recent FPGA platform using the latest design methodology to be embedded into the proposed device for realizing online efficient melanoma detection on a single system on chip/device. The hardware implementation results demonstrate a high classification accuracy of 97.9% and a significant acceleration factor of 26 from equivalent software implementation on an embedded processor, with 34% of resources utilization and 2 watts for power consumption. Consequently, the implemented system meets crucial embedded systems constraints of high performance and low cost, resources utilization and power consumption, while achieving high classification accuracy.

Applied learning-based color tone mapping for face recognition in video surveillance system

Science.gov (United States)

Yew, Chuu Tian; Suandi, Shahrel Azmin

2012-04-01

In this paper, we present an applied learning-based color tone mapping technique for video surveillance system. This technique can be applied onto both color and grayscale surveillance images. The basic idea is to learn the color or intensity statistics from a training dataset of photorealistic images of the candidates appeared in the surveillance images, and remap the color or intensity of the input image so that the color or intensity statistics match those in the training dataset. It is well known that the difference in commercial surveillance cameras models, and signal processing chipsets used by different manufacturers will cause the color and intensity of the images to differ from one another, thus creating additional challenges for face recognition in video surveillance system. Using Multi-Class Support Vector Machines as the classifier on a publicly available video surveillance camera database, namely SCface database, this approach is validated and compared to the results of using holistic approach on grayscale images. The results show that this technique is suitable to improve the color or intensity quality of video surveillance system for face recognition.

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.

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

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.

Comparison of artificial intelligence classifiers for SIP attack data

Science.gov (United States)

Safarik, Jakub; Slachta, Jiri

2016-05-01

Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.

Classifying the molecular functions of Rab GTPases in membrane trafficking using deep convolutional neural networks.

Science.gov (United States)

Le, Nguyen-Quoc-Khanh; Ho, Quang-Thai; Ou, Yu-Yen

2018-06-13

Deep learning has been increasingly used to solve a number of problems with state-of-the-art performance in a wide variety of fields. In biology, deep learning can be applied to reduce feature extraction time and achieve high levels of performance. In our present work, we apply deep learning via two-dimensional convolutional neural networks and position-specific scoring matrices to classify Rab protein molecules, which are main regulators in membrane trafficking for transferring proteins and other macromolecules throughout the cell. The functional loss of specific Rab molecular functions has been implicated in a variety of human diseases, e.g., choroideremia, intellectual disabilities, cancer. Therefore, creating a precise model for classifying Rabs is crucial in helping biologists understand the molecular functions of Rabs and design drug targets according to such specific human disease information. We constructed a robust deep neural network for classifying Rabs that achieved an accuracy of 99%, 99.5%, 96.3%, and 97.6% for each of four specific molecular functions. Our approach demonstrates superior performance to traditional artificial neural networks. Therefore, from our proposed study, we provide both an effective tool for classifying Rab proteins and a basis for further research that can improve the performance of biological modeling using deep neural networks. Copyright © 2018 Elsevier Inc. All rights reserved.

Validation of an adaptation of the ICPS framework for classifying adverse events

DEFF Research Database (Denmark)

Thommesen, Jacob; Mikkelsen, Kim Lyngby; Siemsen, Inger Margrete

, mandatory and non-punitive incident reporting scheme in healthcare, and was explicitly defined to support learning from incidents. The number of reports received by the system has grown from 5,000 in 2004 to 34,000 in 2010. The update of the Danish system will include reporting not only from hospital staff......The Danish National Board of Health has adapted the World Health Organization´s International Classification for Patient Safety (ICPS) for classifying incidents reported to the national Danish Patient Safety Database (DPSD). Originally launched in January 2004, this was the first nationwide......, but also from the primary sector, clinics and nursing homes, and, later, patients and their relatives. In this paper we review some characteristics of the Danish incident reporting system and considerations before and following a validation of a pilot version in 2010...

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.

Personalised learning object based on multi-agent model and learners’ learning styles

Directory of Open Access Journals (Sweden)

Noppamas Pukkhem

2011-09-01

Full Text Available A multi-agent model is proposed in which learning styles and a word analysis technique to create a learning object recommendation system are used. On the basis of a learning style-based design, a concept map combination model is proposed to filter out unsuitable learning concepts from a given course. Our learner model classifies learners into eight styles and implements compatible computational methods consisting of three recommendations: i non-personalised, ii preferred feature-based, and iii neighbour-based collaborative filtering. The analysis of preference error (PE was performed by comparing the actual preferred learning object with the predicted one. In our experiments, the feature-based recommendation algorithm has the fewest PE.

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

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.

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...

Word2Vec inversion and traditional text classifiers for phenotyping lupus.

Science.gov (United States)

Turner, Clayton A; Jacobs, Alexander D; Marques, Cassios K; Oates, James C; Kamen, Diane L; Anderson, Paul E; Obeid, Jihad S

2017-08-22

Identifying patients with certain clinical criteria based on manual chart review of doctors' notes is a daunting task given the massive amounts of text notes in the electronic health records (EHR). This task can be automated using text classifiers based on Natural Language Processing (NLP) techniques along with pattern recognition machine learning (ML) algorithms. The aim of this research is to evaluate the performance of traditional classifiers for identifying patients with Systemic Lupus Erythematosus (SLE) in comparison with a newer Bayesian word vector method. We obtained clinical notes for patients with SLE diagnosis along with controls from the Rheumatology Clinic (662 total patients). Sparse bag-of-words (BOWs) and Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) matrices were produced using NLP pipelines. These matrices were subjected to several different NLP classifiers: neural networks, random forests, naïve Bayes, support vector machines, and Word2Vec inversion, a Bayesian inversion method. Performance was measured by calculating accuracy and area under the Receiver Operating Characteristic (ROC) curve (AUC) of a cross-validated (CV) set and a separate testing set. We calculated the accuracy of the ICD-9 billing codes as a baseline to be 90.00% with an AUC of 0.900, the shallow neural network with CUIs to be 92.10% with an AUC of 0.970, the random forest with BOWs to be 95.25% with an AUC of 0.994, the random forest with CUIs to be 95.00% with an AUC of 0.979, and the Word2Vec inversion to be 90.03% with an AUC of 0.905. Our results suggest that a shallow neural network with CUIs and random forests with both CUIs and BOWs are the best classifiers for this lupus phenotyping task. The Word2Vec inversion method failed to significantly beat the ICD-9 code classification, but yielded promising results. This method does not require explicit features and is more adaptable to non-binary classification tasks. The Word2Vec inversion is

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.

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.

Training Classifiers with Shadow Features for Sensor-Based Human Activity Recognition.

Science.gov (United States)

Fong, Simon; Song, Wei; Cho, Kyungeun; Wong, Raymond; Wong, Kelvin K L

2017-02-27

In this paper, a novel training/testing process for building/using a classification model based on human activity recognition (HAR) is proposed. Traditionally, HAR has been accomplished by a classifier that learns the activities of a person by training with skeletal data obtained from a motion sensor, such as Microsoft Kinect. These skeletal data are the spatial coordinates (x, y, z) of different parts of the human body. The numeric information forms time series, temporal records of movement sequences that can be used for training a classifier. In addition to the spatial features that describe current positions in the skeletal data, new features called 'shadow features' are used to improve the supervised learning efficacy of the classifier. Shadow features are inferred from the dynamics of body movements, and thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterising activities in the classification process, and thereby significantly improve the classification accuracy. Two cases of HAR are tested using a classification model trained with shadow features: one is by using wearable sensor and the other is by a Kinect-based remote sensor. Our experiments can demonstrate the advantages of the new method, which will have an impact on human activity detection research.

Training Classifiers with Shadow Features for Sensor-Based Human Activity Recognition

Directory of Open Access Journals (Sweden)

Simon Fong

2017-02-01

Full Text Available In this paper, a novel training/testing process for building/using a classification model based on human activity recognition (HAR is proposed. Traditionally, HAR has been accomplished by a classifier that learns the activities of a person by training with skeletal data obtained from a motion sensor, such as Microsoft Kinect. These skeletal data are the spatial coordinates (x, y, z of different parts of the human body. The numeric information forms time series, temporal records of movement sequences that can be used for training a classifier. In addition to the spatial features that describe current positions in the skeletal data, new features called ‘shadow features’ are used to improve the supervised learning efficacy of the classifier. Shadow features are inferred from the dynamics of body movements, and thereby modelling the underlying momentum of the performed activities. They provide extra dimensions of information for characterising activities in the classification process, and thereby significantly improve the classification accuracy. Two cases of HAR are tested using a classification model trained with shadow features: one is by using wearable sensor and the other is by a Kinect-based remote sensor. Our experiments can demonstrate the advantages of the new method, which will have an impact on human activity detection research.

Neuromodulatory Adaptive Combination of Correlation-based Learning in Cerebellum and Reward-based Learning in Basal Ganglia for Goal-directed Behavior Control

DEFF Research Database (Denmark)

Dasgupta, Sakyasingha; Wörgötter, Florentin; Manoonpong, Poramate

2014-01-01

Goal-directed decision making in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). A number of computational...... and experimental studies have well established the role of the basal ganglia in reward-based learning, where as the cerebellum plays an important role in developing specific conditioned responses. Although viewed as distinct learning systems, recent animal experiments point toward their complementary role...... in behavioral learning, and also show the existence of substantial two-way communication between these two brain structures. Based on this notion of co-operative learning, in this paper we hypothesize that the basal ganglia and cerebellar learning systems work in parallel and interact with each other. We...

Current Directional Protection of Series Compensated Line Using Intelligent Classifier

Directory of Open Access Journals (Sweden)

M. Mollanezhad Heydarabadi

2016-12-01

Full Text Available Current inversion condition leads to incorrect operation of current based directional relay in power system with series compensated device. Application of the intelligent system for fault direction classification has been suggested in this paper. A new current directional protection scheme based on intelligent classifier is proposed for the series compensated line. The proposed classifier uses only half cycle of pre-fault and post fault current samples at relay location to feed the classifier. A lot of forward and backward fault simulations under different system conditions upon a transmission line with a fixed series capacitor are carried out using PSCAD/EMTDC software. The applicability of decision tree (DT, probabilistic neural network (PNN and support vector machine (SVM are investigated using simulated data under different system conditions. The performance comparison of the classifiers indicates that the SVM is a best suitable classifier for fault direction discriminating. The backward faults can be accurately distinguished from forward faults even under current inversion without require to detect of the current inversion condition.

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

Directory of Open Access Journals (Sweden)

Guofeng Wang

2014-11-01

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

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

Directory of Open Access Journals (Sweden)

Runtao Yang

2015-09-01

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

Nonlinear Knowledge in Kernel-Based Multiple Criteria Programming Classifier

Science.gov (United States)

Zhang, Dongling; Tian, Yingjie; Shi, Yong

Kernel-based Multiple Criteria Linear Programming (KMCLP) model is used as classification methods, which can learn from training examples. Whereas, in traditional machine learning area, data sets are classified only by prior knowledge. Some works combine the above two classification principle to overcome the defaults of each approach. In this paper, we propose a model to incorporate the nonlinear knowledge into KMCLP in order to solve the problem when input consists of not only training example, but also nonlinear prior knowledge. In dealing with real world case breast cancer diagnosis, the model shows its better performance than the model solely based on training data.

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…

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

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.

Identification and optimization of classifier genes from multi-class earthworm microarray dataset.

Directory of Open Access Journals (Sweden)

Ying Li

Full Text Available Monitoring, assessment and prediction of environmental risks that chemicals pose demand rapid and accurate diagnostic assays. A variety of toxicological effects have been associated with explosive compounds TNT and RDX. One important goal of microarray experiments is to discover novel biomarkers for toxicity evaluation. We have developed an earthworm microarray containing 15,208 unique oligo probes and have used it to profile gene expression in 248 earthworms exposed to TNT, RDX or neither. We assembled a new machine learning pipeline consisting of several well-established feature filtering/selection and classification techniques to analyze the 248-array dataset in order to construct classifier models that can separate earthworm samples into three groups: control, TNT-treated, and RDX-treated. First, a total of 869 genes differentially expressed in response to TNT or RDX exposure were identified using a univariate statistical algorithm of class comparison. Then, decision tree-based algorithms were applied to select a subset of 354 classifier genes, which were ranked by their overall weight of significance. A multiclass support vector machine (MC-SVM method and an unsupervised K-mean clustering method were applied to independently refine the classifier, producing a smaller subset of 39 and 30 classifier genes, separately, with 11 common genes being potential biomarkers. The combined 58 genes were considered the refined subset and used to build MC-SVM and clustering models with classification accuracy of 83.5% and 56.9%, respectively. This study demonstrates that the machine learning approach can be used to identify and optimize a small subset of classifier/biomarker genes from high dimensional datasets and generate classification models of acceptable precision for multiple classes.

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.

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.

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.

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.

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.

BEBP: An Poisoning Method Against Machine Learning Based IDSs

OpenAIRE

Li, Pan; Liu, Qiang; Zhao, Wentao; Wang, Dongxu; Wang, Siqi

2018-01-01

In big data era, machine learning is one of fundamental techniques in intrusion detection systems (IDSs). However, practical IDSs generally update their decision module by feeding new data then retraining learning models in a periodical way. Hence, some attacks that comprise the data for training or testing classifiers significantly challenge the detecting capability of machine learning-based IDSs. Poisoning attack, which is one of the most recognized security threats towards machine learning...

Intelligent systems

CERN Document Server

Irwin, J David

2011-01-01

Technology has now progressed to the point that intelligent systems are replacing humans in the decision making processes as well as aiding in the solution of very complex problems. In many cases intelligent systems are already outperforming human activities. Artificial neural networks are not only capable of learning how to classify patterns, such images or sequence of events, but they can also effectively model complex nonlinear systems. Their ability to classify sequences of events is probably more popular in industrial applications where there is an inherent need to model nonlinear system

Development and Experimental Evaluation of Machine-Learning Techniques for an Intelligent Hairy Scalp Detection System

Directory of Open Access Journals (Sweden)

Wei-Chien Wang

2018-05-01

Full Text Available Deep learning has become the most popular research subject in the fields of artificial intelligence (AI and machine learning. In October 2013, MIT Technology Review commented that deep learning was a breakthrough technology. Deep learning has made progress in voice and image recognition, image classification, and natural language processing. Prior to deep learning, decision tree, linear discriminant analysis (LDA, support vector machines (SVM, k-nearest neighbors algorithm (K-NN, and ensemble learning were popular in solving classification problems. In this paper, we applied the previously mentioned and deep learning techniques to hairy scalp images. Hairy scalp problems are usually diagnosed by non-professionals in hair salons, and people with such problems may be advised by these non-professionals. Additionally, several common scalp problems are similar; therefore, non-experts may provide incorrect diagnoses. Hence, scalp problems have worsened. In this work, we implemented and compared the deep-learning method, the ImageNet-VGG-f model Bag of Words (BOW, with machine-learning classifiers, and histogram of oriented gradients (HOG/pyramid histogram of oriented gradients (PHOG with machine-learning classifiers. The tools from the classification learner apps were used for hairy scalp image classification. The results indicated that deep learning can achieve an accuracy of 89.77% when the learning rate is 1 × 10−4, and this accuracy is far higher than those achieved by BOW with SVM (80.50% and PHOG with SVM (53.0%.

Construction of a system using a deep learning algorithm to count cell numbers in nanoliter wells for viable single-cell experiments.

Science.gov (United States)

Kamatani, Takashi; Fukunaga, Koichi; Miyata, Kaede; Shirasaki, Yoshitaka; Tanaka, Junji; Baba, Rie; Matsusaka, Masako; Kamatani, Naoyuki; Moro, Kazuyo; Betsuyaku, Tomoko; Uemura, Sotaro

2017-12-04

For single-cell experiments, it is important to accurately count the number of viable cells in a nanoliter well. We used a deep learning-based convolutional neural network (CNN) on a large amount of digital data obtained as microscopic images. The training set consisted of 103 019 samples, each representing a microscopic grayscale image. After extensive training, the CNN was able to classify the samples into four categories, i.e., 0, 1, 2, and more than 2 cells per well, with an accuracy of 98.3% when compared to determination by two trained technicians. By analyzing the samples for which judgments were discordant, we found that the judgment by technicians was relatively correct although cell counting was often difficult by the images of discordant samples. Based on the results, the system was further enhanced by introducing a new algorithm in which the highest outputs from CNN were used, increasing the accuracy to higher than 99%. Our system was able to classify the data even from wells with a different shape. No other tested machine learning algorithm showed a performance higher than that of our system. The presented CNN system is expected to be useful for various single-cell experiments, and for high-throughput and high-content screening.

Ask-the-expert: Active Learning Based Knowledge Discovery Using the Expert

Science.gov (United States)

Das, Kamalika; Avrekh, Ilya; Matthews, Bryan; Sharma, Manali; Oza, Nikunj

2017-01-01

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the backend. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

Science.gov (United States)

Zhang, Ce; Pan, Xin; Li, Huapeng; Gardiner, Andy; Sargent, Isabel; Hare, Jonathon; Atkinson, Peter M.

2018-06-01

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

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.

Hospitals as learning organizations: fostering innovation through interactive learning.

Science.gov (United States)

Dias, Casimiro; Escoval, Ana

2015-01-01

The article aims to provide an analytical understanding of hospitals as "learning organizations." It further analyzes the development of learning organizations as a way to enhance innovation and performance in the hospital sector. The article pulls together primary data on organizational flexibility, innovation, and performance from 95 administrators from hospital boards in Portugal, collected through a survey, interviews with hospital's boards, and a nominal group technique with a panel of experts on health systems. Results show that a combination of several organizational traits of the learning organization enhances its capacity for innovation development. The logistic model presented reveals that hospitals classified as "advanced learning organizations" have 5 times more chance of developing innovation than "basic learning organizations." Empirical findings further pointed out incentives, standards, and measurement requirements as key elements for integration of service delivery systems and expansion of the current capacity for structured and real-time learning in the hospital sector. The major implication arising from this study is that policy needs to combine instruments that promote innovation opportunities and incentives, with instruments stimulating the further development of the core components of learning organizations. Such a combination of policy instruments has the potential to ensure a wide external cooperation through a learning infrastructure.

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.

Supervised Learning for Visual Pattern Classification

Science.gov (United States)

Zheng, Nanning; Xue, Jianru

This chapter presents an overview of the topics and major ideas of supervised learning for visual pattern classification. Two prevalent algorithms, i.e., the support vector machine (SVM) and the boosting algorithm, are briefly introduced. SVMs and boosting algorithms are two hot topics of recent research in supervised learning. SVMs improve the generalization of the learning machine by implementing the rule of structural risk minimization (SRM). It exhibits good generalization even when little training data are available for machine training. The boosting algorithm can boost a weak classifier to a strong classifier by means of the so-called classifier combination. This algorithm provides a general way for producing a classifier with high generalization capability from a great number of weak classifiers.

Zooniverse: Combining Human and Machine Classifiers for the Big Survey Era

Science.gov (United States)

Fortson, Lucy; Wright, Darryl; Beck, Melanie; Lintott, Chris; Scarlata, Claudia; Dickinson, Hugh; Trouille, Laura; Willi, Marco; Laraia, Michael; Boyer, Amy; Veldhuis, Marten; Zooniverse

2018-01-01

Many analyses of astronomical data sets, ranging from morphological classification of galaxies to identification of supernova candidates, have relied on humans to classify data into distinct categories. Crowdsourced galaxy classifications via the Galaxy Zoo project provided a solution that scaled visual classification for extant surveys by harnessing the combined power of thousands of volunteers. However, the much larger data sets anticipated from upcoming surveys will require a different approach. Automated classifiers using supervised machine learning have improved considerably over the past decade but their increasing sophistication comes at the expense of needing ever more training data. Crowdsourced classification by human volunteers is a critical technique for obtaining these training data. But several improvements can be made on this zeroth order solution. Efficiency gains can be achieved by implementing a “cascade filtering” approach whereby the task structure is reduced to a set of binary questions that are more suited to simpler machines while demanding lower cognitive loads for humans.Intelligent subject retirement based on quantitative metrics of volunteer skill and subject label reliability also leads to dramatic improvements in efficiency. We note that human and machine classifiers may retire subjects differently leading to trade-offs in performance space. Drawing on work with several Zooniverse projects including Galaxy Zoo and Supernova Hunter, we will present recent findings from experiments that combine cohorts of human and machine classifiers. We show that the most efficient system results when appropriate subsets of the data are intelligently assigned to each group according to their particular capabilities.With sufficient online training, simple machines can quickly classify “easy” subjects, leaving more difficult (and discovery-oriented) tasks for volunteers. We also find humans achieve higher classification purity while samples

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...

Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.

Science.gov (United States)

Luo, Yuan; Cheng, Yu; Uzuner, Özlem; Szolovits, Peter; Starren, Justin

2018-01-01

We propose Segment Convolutional Neural Networks (Seg-CNNs) for classifying relations from clinical notes. Seg-CNNs use only word-embedding features without manual feature engineering. Unlike typical CNN models, relations between 2 concepts are identified by simultaneously learning separate representations for text segments in a sentence: preceding, concept1, middle, concept2, and succeeding. We evaluate Seg-CNN on the i2b2/VA relation classification challenge dataset. We show that Seg-CNN achieves a state-of-the-art micro-average F-measure of 0.742 for overall evaluation, 0.686 for classifying medical problem-treatment relations, 0.820 for medical problem-test relations, and 0.702 for medical problem-medical problem relations. We demonstrate the benefits of learning segment-level representations. We show that medical domain word embeddings help improve relation classification. Seg-CNNs can be trained quickly for the i2b2/VA dataset on a graphics processing unit (GPU) platform. These results support the use of CNNs computed over segments of text for classifying medical relations, as they show state-of-the-art performance while requiring no manual feature engineering. © The Author 2017. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

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.

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.

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

Classifying and scoring of molecules with the NGN: new datasets, significance tests, and generalization

Directory of Open Access Journals (Sweden)

Cameron Christopher JF

2010-10-01

Full Text Available Abstract This paper demonstrates how a Neural Grammar Network learns to classify and score molecules for a variety of tasks in chemistry and toxicology. In addition to a more detailed analysis on datasets previously studied, we introduce three new datasets (BBB, FXa, and toxicology to show the generality of the approach. A new experimental methodology is developed and applied to both the new datasets as well as previously studied datasets. This methodology is rigorous and statistically grounded, and ultimately culminates in a Wilcoxon significance test that proves the effectiveness of the system. We further include a complete generalization of the specific technique to arbitrary grammars and datasets using a mathematical abstraction that allows researchers in different domains to apply the method to their own work. Background Our work can be viewed as an alternative to existing methods to solve the quantitative structure-activity relationship (QSAR problem. To this end, we review a number approaches both from a methodological and also a performance perspective. In addition to these approaches, we also examined a number of chemical properties that can be used by generic classifier systems, such as feed-forward artificial neural networks. In studying these approaches, we identified a set of interesting benchmark problem sets to which many of the above approaches had been applied. These included: ACE, AChE, AR, BBB, BZR, Cox2, DHFR, ER, FXa, GPB, Therm, and Thr. Finally, we developed our own benchmark set by collecting data on toxicology. Results Our results show that our system performs better than, or comparatively to, the existing methods over a broad range of problem types. Our method does not require the expert knowledge that is necessary to apply the other methods to novel problems. Conclusions We conclude that our success is due to the ability of our system to: 1 encode molecules losslessly before presentation to the learning system, and 2

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

Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers

Directory of Open Access Journals (Sweden)

M. Al-Rousan

2005-08-01

Full Text Available Building an accurate automatic sign language recognition system is of great importance in facilitating efficient communication with deaf people. In this paper, we propose the use of polynomial classifiers as a classification engine for the recognition of Arabic sign language (ArSL alphabet. Polynomial classifiers have several advantages over other classifiers in that they do not require iterative training, and that they are highly computationally scalable with the number of classes. Based on polynomial classifiers, we have built an ArSL system and measured its performance using real ArSL data collected from deaf people. We show that the proposed system provides superior recognition results when compared with previously published results using ANFIS-based classification on the same dataset and feature extraction methodology. The comparison is shown in terms of the number of misclassified test patterns. The reduction in the rate of misclassified patterns was very significant. In particular, we have achieved a 36% reduction of misclassifications on the training data and 57% on the test data.

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.

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.

Hybrid Collaborative Learning for Classification and Clustering in Sensor Networks

Science.gov (United States)

Wagstaff, Kiri L.; Sosnowski, Scott; Lane, Terran

2012-01-01

. The new capability has the potential to greatly expand the in situ analysis abilities of sensor networks. Classifiers seeking to categorize incoming data into different types of events can operate in tandem with clusterers that are sensitive to the occurrence of new kinds of events not known to the classifiers. In contrast to current approaches that treat these operations as independent components, a hybrid collaborative learning system can enable them to learn from each other.

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.

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.

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

Directory of Open Access Journals (Sweden)

Salah Bouktif

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

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.

Localizing genes to cerebellar layers by classifying ISH images.

Directory of Open Access Journals (Sweden)

Lior Kirsch

Full Text Available Gene expression controls how the brain develops and functions. Understanding control processes in the brain is particularly hard since they involve numerous types of neurons and glia, and very little is known about which genes are expressed in which cells and brain layers. Here we describe an approach to detect genes whose expression is primarily localized to a specific brain layer and apply it to the mouse cerebellum. We learn typical spatial patterns of expression from a few markers that are known to be localized to specific layers, and use these patterns to predict localization for new genes. We analyze images of in-situ hybridization (ISH experiments, which we represent using histograms of local binary patterns (LBP and train image classifiers and gene classifiers for four layers of the cerebellum: the Purkinje, granular, molecular and white matter layer. On held-out data, the layer classifiers achieve accuracy above 94% (AUC by representing each image at multiple scales and by combining multiple image scores into a single gene-level decision. When applied to the full mouse genome, the classifiers predict specific layer localization for hundreds of new genes in the Purkinje and granular layers. Many genes localized to the Purkinje layer are likely to be expressed in astrocytes, and many others are involved in lipid metabolism, possibly due to the unusual size of Purkinje cells.

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.

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.

Solving a Higgs optimization problem with quantum annealing for machine learning.

Science.gov (United States)

Mott, Alex; Job, Joshua; Vlimant, Jean-Roch; Lidar, Daniel; Spiropulu, Maria

2017-10-18

The discovery of Higgs-boson decays in a background of standard-model processes was assisted by machine learning methods. The classifiers used to separate signals such as these from background are trained using highly unerring but not completely perfect simulations of the physical processes involved, often resulting in incorrect labelling of background processes or signals (label noise) and systematic errors. Here we use quantum and classical annealing (probabilistic techniques for approximating the global maximum or minimum of a given function) to solve a Higgs-signal-versus-background machine learning optimization problem, mapped to a problem of finding the ground state of a corresponding Ising spin model. We build a set of weak classifiers based on the kinematic observables of the Higgs decay photons, which we then use to construct a strong classifier. This strong classifier is highly resilient against overtraining and against errors in the correlations of the physical observables in the training data. We show that the resulting quantum and classical annealing-based classifier systems perform comparably to the state-of-the-art machine learning methods that are currently used in particle physics. However, in contrast to these methods, the annealing-based classifiers are simple functions of directly interpretable experimental parameters with clear physical meaning. The annealer-trained classifiers use the excited states in the vicinity of the ground state and demonstrate some advantage over traditional machine learning methods for small training datasets. Given the relative simplicity of the algorithm and its robustness to error, this technique may find application in other areas of experimental particle physics, such as real-time decision making in event-selection problems and classification in neutrino physics.

Classifying Radio Galaxies with the Convolutional Neural Network

Energy Technology Data Exchange (ETDEWEB)

Aniyan, A. K.; Thorat, K. [Department of Physics and Electronics, Rhodes University, Grahamstown (South Africa)

2017-06-01

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff–Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ∼200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

Classifying Radio Galaxies with the Convolutional Neural Network

Science.gov (United States)

Aniyan, A. K.; Thorat, K.

2017-06-01

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff-Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ˜200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

Classifying Radio Galaxies with the Convolutional Neural Network

International Nuclear Information System (INIS)

Aniyan, A. K.; Thorat, K.

2017-01-01

We present the application of a deep machine learning technique to classify radio images of extended sources on a morphological basis using convolutional neural networks (CNN). In this study, we have taken the case of the Fanaroff–Riley (FR) class of radio galaxies as well as radio galaxies with bent-tailed morphology. We have used archival data from the Very Large Array (VLA)—Faint Images of the Radio Sky at Twenty Centimeters survey and existing visually classified samples available in the literature to train a neural network for morphological classification of these categories of radio sources. Our training sample size for each of these categories is ∼200 sources, which has been augmented by rotated versions of the same. Our study shows that CNNs can classify images of the FRI and FRII and bent-tailed radio galaxies with high accuracy (maximum precision at 95%) using well-defined samples and a “fusion classifier,” which combines the results of binary classifications, while allowing for a mechanism to find sources with unusual morphologies. The individual precision is highest for bent-tailed radio galaxies at 95% and is 91% and 75% for the FRI and FRII classes, respectively, whereas the recall is highest for FRI and FRIIs at 91% each, while the bent-tailed class has a recall of 79%. These results show that our results are comparable to that of manual classification, while being much faster. Finally, we discuss the computational and data-related challenges associated with the morphological classification of radio galaxies with CNNs.

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. 

Machine learning vortices at the Kosterlitz-Thouless transition

Science.gov (United States)

Beach, Matthew J. S.; Golubeva, Anna; Melko, Roger G.

2018-01-01

Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed-matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further show a single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.

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.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

Science.gov (United States)

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K; Jacobs, Colin; Scholten, Ernst Th; Schaefer-Prokop, Cornelia; Wille, Mathilde M W; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-04-19

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

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.…

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 ...

Effects of cultural characteristics on building an emotion classifier through facial expression analysis

Science.gov (United States)

da Silva, Flávio Altinier Maximiano; Pedrini, Helio

2015-03-01

Facial expressions are an important demonstration of humanity's humors and emotions. Algorithms capable of recognizing facial expressions and associating them with emotions were developed and employed to compare the expressions that different cultural groups use to show their emotions. Static pictures of predominantly occidental and oriental subjects from public datasets were used to train machine learning algorithms, whereas local binary patterns, histogram of oriented gradients (HOGs), and Gabor filters were employed to describe the facial expressions for six different basic emotions. The most consistent combination, formed by the association of HOG filter and support vector machines, was then used to classify the other cultural group: there was a strong drop in accuracy, meaning that the subtle differences of facial expressions of each culture affected the classifier performance. Finally, a classifier was trained with images from both occidental and oriental subjects and its accuracy was higher on multicultural data, evidencing the need of a multicultural training set to build an efficient classifier.

Robust Visual Knowledge Transfer via Extreme Learning Machine Based Domain Adaptation.

Science.gov (United States)

Zhang, Lei; Zhang, David

2016-08-10

We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme learning machine based cross-domain network learning framework, that is called Extreme Learning Machine (ELM) based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the -norm of the network output weights and the learning error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross domain learning. It minimizes the matching error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as base classifiers. The network output weights cannot only be analytically determined, but also transferrable. Additionally, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semi-supervised learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition, demonstrate that our EDA methods outperform existing cross-domain learning methods.

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…

Multiobjective optimization of classifiers by means of 3D convex-hull-based evolutionary algorithms

NARCIS (Netherlands)

Zhao, J.; Basto, Fernandes V.; Jiao, L.; Yevseyeva, I.; Asep, Maulana A.; Li, R.; Bäck, T.H.W.; Tang, T.; Michael, Emmerich T. M.

2016-01-01

The receiver operating characteristic (ROC) and detection error tradeoff(DET) curves are frequently used in the machine learning community to analyze the performance of binary classifiers. Recently, the convex-hull-based multiobjective genetic programming algorithm was proposed and successfully

Incremental Learning of Perceptual Categories for Open-Domain Sketch Recognition

National Research Council Canada - National Science Library

Lovett, Andrew; Dehghani, Morteza; Forbus, Kenneth

2007-01-01

.... This paper describes an incremental learning technique for opendomain recognition. Our system builds generalizations for categories of objects based upon previous sketches of those objects and uses those generalizations to classify new sketches...

Local-global classifier fusion for screening chest radiographs

Science.gov (United States)

Ding, Meng; Antani, Sameer; Jaeger, Stefan; Xue, Zhiyun; Candemir, Sema; Kohli, Marc; Thoma, George

2017-03-01

Tuberculosis (TB) is a severe comorbidity of HIV and chest x-ray (CXR) analysis is a necessary step in screening for the infective disease. Automatic analysis of digital CXR images for detecting pulmonary abnormalities is critical for population screening, especially in medical resource constrained developing regions. In this article, we describe steps that improve previously reported performance of NLM's CXR screening algorithms and help advance the state of the art in the field. We propose a local-global classifier fusion method where two complementary classification systems are combined. The local classifier focuses on subtle and partial presentation of the disease leveraging information in radiology reports that roughly indicates locations of the abnormalities. In addition, the global classifier models the dominant spatial structure in the gestalt image using GIST descriptor for the semantic differentiation. Finally, the two complementary classifiers are combined using linear fusion, where the weight of each decision is calculated by the confidence probabilities from the two classifiers. We evaluated our method on three datasets in terms of the area under the Receiver Operating Characteristic (ROC) curve, sensitivity, specificity and accuracy. The evaluation demonstrates the superiority of our proposed local-global fusion method over any single classifier.

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.

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.

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…

Machine-Learning Research

OpenAIRE

Dietterich, Thomas G.

1997-01-01

Machine-learning research has been making great progress in many directions. This article summarizes four of these directions and discusses some current open problems. The four directions are (1) the improvement of classification accuracy by learning ensembles of classifiers, (2) methods for scaling up supervised learning algorithms, (3) reinforcement learning, and (4) the learning of complex stochastic models.

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....

Can single classifiers be as useful as model ensembles to produce benthic seabed substratum maps?

Science.gov (United States)

Turner, Joseph A.; Babcock, Russell C.; Hovey, Renae; Kendrick, Gary A.

2018-05-01

Numerous machine-learning classifiers are available for benthic habitat map production, which can lead to different results. This study highlights the performance of the Random Forest (RF) classifier, which was significantly better than Classification Trees (CT), Naïve Bayes (NB), and a multi-model ensemble in terms of overall accuracy, Balanced Error Rate (BER), Kappa, and area under the curve (AUC) values. RF accuracy was often higher than 90% for each substratum class, even at the most detailed level of the substratum classification and AUC values also indicated excellent performance (0.8-1). Total agreement between classifiers was high at the broadest level of classification (75-80%) when differentiating between hard and soft substratum. However, this sharply declined as the number of substratum categories increased (19-45%) including a mix of rock, gravel, pebbles, and sand. The model ensemble, produced from the results of all three classifiers by majority voting, did not show any increase in predictive performance when compared to the single RF classifier. This study shows how a single classifier may be sufficient to produce benthic seabed maps and model ensembles of multiple classifiers.

Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers.

Science.gov (United States)

Siuly; Yin, Xiaoxia; Hadjiloucas, Sillas; Zhang, Yanchun

2016-04-01

This work provides a performance comparison of four different machine learning classifiers: multinomial logistic regression with ridge estimators (MLR) classifier, k-nearest neighbours (KNN), support vector machine (SVM) and naïve Bayes (NB) as applied to terahertz (THz) transient time domain sequences associated with pixelated images of different powder samples. The six substances considered, although have similar optical properties, their complex insertion loss at the THz part of the spectrum is significantly different because of differences in both their frequency dependent THz extinction coefficient as well as differences in their refractive index and scattering properties. As scattering can be unquantifiable in many spectroscopic experiments, classification solely on differences in complex insertion loss can be inconclusive. The problem is addressed using two-dimensional (2-D) cross-correlations between background and sample interferograms, these ensure good noise suppression of the datasets and provide a range of statistical features that are subsequently used as inputs to the above classifiers. A cross-validation procedure is adopted to assess the performance of the classifiers. Firstly the measurements related to samples that had thicknesses of 2mm were classified, then samples at thicknesses of 4mm, and after that 3mm were classified and the success rate and consistency of each classifier was recorded. In addition, mixtures having thicknesses of 2 and 4mm as well as mixtures of 2, 3 and 4mm were presented simultaneously to all classifiers. This approach provided further cross-validation of the classification consistency of each algorithm. The results confirm the superiority in classification accuracy and robustness of the MLR (least accuracy 88.24%) and KNN (least accuracy 90.19%) algorithms which consistently outperformed the SVM (least accuracy 74.51%) and NB (least accuracy 56.86%) classifiers for the same number of feature vectors across all studies

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.

Web-Based Evaluation System to Measure Learning Effectiveness in Kampo Medicine

Directory of Open Access Journals (Sweden)

Norio Iizuka

2016-01-01

Full Text Available Measuring the learning effectiveness of Kampo Medicine (KM education is challenging. The aim of this study was to develop a web-based test to measure the learning effectiveness of KM education among medical students (MSs. We used an open-source Moodle platform to test 30 multiple-choice questions classified into 8-type fields (eight basic concepts of KM including “qi-blood-fluid” and “five-element” theories, on 117 fourth-year MSs. The mean (±standard deviation [SD] score on the web-based test was 30.2±11.9 (/100. The correct answer rate ranged from 17% to 36%. A pattern-based portfolio enabled these rates to be individualized in terms of KM proficiency. MSs with scores higher (n=19 or lower (n=14 than mean ± 1SD were defined as high or low achievers, respectively. Cluster analysis using the correct answer rates for the 8-type field questions revealed clear divisions between high and low achievers. Interestingly, each high achiever had a different proficiency pattern. In contrast, three major clusters were evident among low achievers, all of whom responded with a low percentage of or no correct answers. In addition, a combination of three questions accurately classified high and low achievers. These findings suggest that our web-based test allows individual quantitative assessment of the learning effectiveness of KM education among MSs.

Classifying images using restricted Boltzmann machines and convolutional neural networks

Science.gov (United States)

Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

2017-07-01

To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

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

Science.gov (United States)

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

2016-01-01

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

Evaluating Classifiers in Detecting 419 Scams in Bilingual Cybercriminal Communities

OpenAIRE

Mbaziira, Alex V.; Abozinadah, Ehab; Jones Jr, James H.

2015-01-01

Incidents of organized cybercrime are rising because of criminals are reaping high financial rewards while incurring low costs to commit crime. As the digital landscape broadens to accommodate more internet-enabled devices and technologies like social media, more cybercriminals who are not native English speakers are invading cyberspace to cash in on quick exploits. In this paper we evaluate the performance of three machine learning classifiers in detecting 419 scams in a bilingual Nigerian c...

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.

Proposed hybrid-classifier ensemble algorithm to map snow cover area

Science.gov (United States)

Nijhawan, Rahul; Raman, Balasubramanian; Das, Josodhir

2018-01-01

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

Enhancing interpretability of automatically extracted machine learning features: application to a RBM-Random Forest system on brain lesion segmentation.

Science.gov (United States)

Pereira, Sérgio; Meier, Raphael; McKinley, Richard; Wiest, Roland; Alves, Victor; Silva, Carlos A; Reyes, Mauricio

2018-02-01

Machine learning systems are achieving better performances at the cost of becoming increasingly complex. However, because of that, they become less interpretable, which may cause some distrust by the end-user of the system. This is especially important as these systems are pervasively being introduced to critical domains, such as the medical field. Representation Learning techniques are general methods for automatic feature computation. Nevertheless, these techniques are regarded as uninterpretable "black boxes". In this paper, we propose a methodology to enhance the interpretability of automatically extracted machine learning features. The proposed system is composed of a Restricted Boltzmann Machine for unsupervised feature learning, and a Random Forest classifier, which are combined to jointly consider existing correlations between imaging data, features, and target variables. We define two levels of interpretation: global and local. The former is devoted to understanding if the system learned the relevant relations in the data correctly, while the later is focused on predictions performed on a voxel- and patient-level. In addition, we propose a novel feature importance strategy that considers both imaging data and target variables, and we demonstrate the ability of the approach to leverage the interpretability of the obtained representation for the task at hand. We evaluated the proposed methodology in brain tumor segmentation and penumbra estimation in ischemic stroke lesions. We show the ability of the proposed methodology to unveil information regarding relationships between imaging modalities and extracted features and their usefulness for the task at hand. In both clinical scenarios, we demonstrate that the proposed methodology enhances the interpretability of automatically learned features, highlighting specific learning patterns that resemble how an expert extracts relevant data from medical images. Copyright © 2017 Elsevier B.V. All rights reserved.

Assessing the Impact of IT Competency on Organizational Learning Capability of Indonesian Manufacturing Firms

Directory of Open Access Journals (Sweden)

Alizar Hasan

2010-01-01

Full Text Available This paper attempt to assessing the impact of IT competency on organizational learning capability by using the measurement scale that have been developed by Tippins et al. and Gomes et al. These studies cover a sample of 192 manufacturing firms. IT competencies are classified into three dimensions: IT knowledge, IT operations, and IT objects, and organizational learning capability are classified into four dimensions: Managerial commitment, System perspec-tive, Openness and experimentation, and Knowledge transfer and integration. The result of factor analysis on IT competency and Organizational learning capability show that all items have high loading only on a single factor with ranging from .60 to .84. The findings revealed that IT competency positively and significantly influences the organizational learning capability of Indonesian manufacturing firms.

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…

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...

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…

Personalized Resource Recommendations using Learning from Positive and Unlabeled Examples

Directory of Open Access Journals (Sweden)

Priyank Thakkar

2016-08-01

Full Text Available This paper proposes a novel approach for recommending social resources using learning from positive and unlabeled examples. Bookmarks submitted on social bookmarking system delicious1 and artists on online music system last.fm2 are considered as social resources. The foremost feature of this problem is that there are no labeled negative resources/examples available for learning a recommender/classifier. The memory based collaborative filtering has served as the most widely used algorithm for social resource recommendation. However, its predictions are based on some ad hoc heuristic rules and its success depends on the availability of a critical mass of users. This paper proposes model based two-step techniques to learn a classifier using positive and unlabeled examples to address personalized resource recommendations. In the first step of these techniques, naïve Bayes classifier is employed to identify reliable negative resources. In the second step, to generate effective resource recommender, classification and regression tree and least square support vector machine (LS-SVM are exercised. A direct method based on LS-SVM is also put forward to realize the recommendation task. LS-SVM is customized for learning from positive and unlabeled data. Furthermore, the impact of feature selection on our proposed techniques is also studied. Memory based collaborative filtering as well as our proposed techniques exploit usage data to generate personalized recommendations. Experimental results show that the proposed techniques outperform existing method appreciably.

Feature and score fusion based multiple classifier selection for iris recognition.

Science.gov (United States)

Islam, Md Rabiul

2014-01-01

The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

Feature and Score Fusion Based Multiple Classifier Selection for Iris Recognition

Directory of Open Access Journals (Sweden)

Md. Rabiul Islam

2014-01-01

Full Text Available The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

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. .

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.

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

A novel deep learning approach for classification of EEG motor imagery signals.

Science.gov (United States)

Tabar, Yousef Rezaei; Halici, Ugur

2017-02-01

Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

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.

Application of the Naive Bayesian Classifier to optimize treatment decisions

International Nuclear Information System (INIS)

Kazmierska, Joanna; Malicki, Julian

2008-01-01

Background and purpose: To study the accuracy, specificity and sensitivity of the Naive Bayesian Classifier (NBC) in the assessment of individual risk of cancer relapse or progression after radiotherapy (RT). Materials and methods: Data of 142 brain tumour patients irradiated from 2000 to 2005 were analyzed. Ninety-six attributes related to disease, patient and treatment were chosen. Attributes in binary form consisted of the training set for NBC learning. NBC calculated an individual conditional probability of being assigned to: relapse or progression (1), or no relapse or progression (0) group. Accuracy, attribute selection and quality of classifier were determined by comparison with actual treatment results, leave-one-out and cross validation methods, respectively. Clinical setting test utilized data of 35 patients. Treatment results at classification were unknown and were compared with classification results after 3 months. Results: High classification accuracy (84%), specificity (0.87) and sensitivity (0.80) were achieved, both for classifier training and in progressive clinical evaluation. Conclusions: NBC is a useful tool to support the assessment of individual risk of relapse or progression in patients diagnosed with brain tumour undergoing RT postoperatively

A web-based neurological pain classifier tool utilizing Bayesian decision theory for pain classification in spinal cord injury patients

Science.gov (United States)

Verma, Sneha K.; Chun, Sophia; Liu, Brent J.

2014-03-01

Pain is a common complication after spinal cord injury with prevalence estimates ranging 77% to 81%, which highly affects a patient's lifestyle and well-being. In the current clinical setting paper-based forms are used to classify pain correctly, however, the accuracy of diagnoses and optimal management of pain largely depend on the expert reviewer, which in many cases is not possible because of very few experts in this field. The need for a clinical decision support system that can be used by expert and non-expert clinicians has been cited in literature, but such a system has not been developed. We have designed and developed a stand-alone tool for correctly classifying pain type in spinal cord injury (SCI) patients, using Bayesian decision theory. Various machine learning simulation methods are used to verify the algorithm using a pilot study data set, which consists of 48 patients data set. The data set consists of the paper-based forms, collected at Long Beach VA clinic with pain classification done by expert in the field. Using the WEKA as the machine learning tool we have tested on the 48 patient dataset that the hypothesis that attributes collected on the forms and the pain location marked by patients have very significant impact on the pain type classification. This tool will be integrated with an imaging informatics system to support a clinical study that will test the effectiveness of using Proton Beam radiotherapy for treating spinal cord injury (SCI) related neuropathic pain as an alternative to invasive surgical lesioning.

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…

Comparisons and Selections of Features and Classifiers for Short Text Classification

Science.gov (United States)

Wang, Ye; Zhou, Zhi; Jin, Shan; Liu, Debin; Lu, Mi

2017-10-01

Short text is considerably different from traditional long text documents due to its shortness and conciseness, which somehow hinders the applications of conventional machine learning and data mining algorithms in short text classification. According to traditional artificial intelligence methods, we divide short text classification into three steps, namely preprocessing, feature selection and classifier comparison. In this paper, we have illustrated step-by-step how we approach our goals. Specifically, in feature selection, we compared the performance and robustness of the four methods of one-hot encoding, tf-idf weighting, word2vec and paragraph2vec, and in the classification part, we deliberately chose and compared Naive Bayes, Logistic Regression, Support Vector Machine, K-nearest Neighbor and Decision Tree as our classifiers. Then, we compared and analysed the classifiers horizontally with each other and vertically with feature selections. Regarding the datasets, we crawled more than 400,000 short text files from Shanghai and Shenzhen Stock Exchanges and manually labeled them into two classes, the big and the small. There are eight labels in the big class, and 59 labels in the small class.

Exploring nursing e-learning systems success based on information system success model.

Science.gov (United States)

Chang, Hui-Chuan; Liu, Chung-Feng; Hwang, Hsin-Ginn

2011-12-01

E-learning is thought of as an innovative approach to enhance nurses' care service knowledge. Extensive research has provided rich information toward system development, courses design, and nurses' satisfaction with an e-learning system. However, a comprehensive view in understanding nursing e-learning system success is an important but less focused-on topic. The purpose of this research was to explore net benefits of nursing e-learning systems based on the updated DeLone and McLean's Information System Success Model. The study used a self-administered questionnaire to collected 208 valid nurses' responses from 21 of Taiwan's medium- and large-scale hospitals that have implemented nursing e-learning systems. The result confirms that the model is sufficient to explore the nurses' use of e-learning systems in terms of intention to use, user satisfaction, and net benefits. However, while the three exogenous quality factors (system quality, information quality, and service quality) were all found to be critical factors affecting user satisfaction, only information quality showed a direct effect on the intention to use. This study provides useful insights for evaluating nursing e-learning system qualities as well as an understanding of nurses' intentions and satisfaction related to performance benefits.

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

A systematic comparison of supervised classifiers.

Directory of Open Access Journals (Sweden)

Diego Raphael Amancio

Full Text Available Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM. In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.

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.

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

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,

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…

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.

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation.

Science.gov (United States)

Hohman, Fred; Hodas, Nathan; Chau, Duen Horng

2017-05-01

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as "black-boxes" due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user's data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation

Energy Technology Data Exchange (ETDEWEB)

Hohman, Frederick M.; Hodas, Nathan O.; Chau, Duen Horng

2017-05-30

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as “black-boxes” due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user’s data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

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

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…

Supervised Learning Applied to Air Traffic Trajectory Classification

Science.gov (United States)

Bosson, Christabelle; Nikoleris, Tasos

2018-01-01

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

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.

MACHINE LEARNING IMPLEMENTATION FOR THE CLASSIFICATION OF ATTACKS ON WEB SYSTEMS. PART 2

Directory of Open Access Journals (Sweden)

K. Smirnova

2017-11-01

Full Text Available The possibility of applying machine learning for the classification of malicious requests to aWeb application is considered. This approach excludes the use of deterministic analysis systems (for example, expert systems,and is based on the application of a cascade of neural networks or perceptrons on an approximate model to the real humanbrain. The main idea of the work is to enable to describe complex attack vectors consisting of feature sets, abstract terms forcompiling a training sample, controlling the quality of recognition and classifying each of the layers (networks participatingin 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 orinaccuracy crept in. The design of the developed network can be described as a cascaded, scalable neural network.When using neural networks to detect attacks on web systems, the issue of vectorization and normalization of features isacute. The most commonly used methods for solving these problems are not designed for the case of deliberate distortion ofthe signs of an attack.The proposed approach makes it possible to obtain a neural network that has been studied in more detail by small features,and also to eliminate the normalization issues in order to avoid deliberately bypassing the intrusion detection system. Byisolating one more group of neurons in the network and teaching it to samples containing various variants of circumvention ofthe attack classification, the developed intrusion detection system remains able to classify any types of attacks as well as theiraggregates, putting forward more stringent measures to counteract attacks. This allows you to follow the life cycle of theattack in more detail: from the starting trial attack to deliberate sophisticated attempts to bypass the system and introducemore decisive measures to actively counteract the attack, eliminating the chances of a false alarm system.

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.

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.

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.

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.

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…

Active Learning with Irrelevant Examples

Science.gov (United States)

Wagstaff, Kiri; Mazzoni, Dominic

2009-01-01

An improved active learning method has been devised for training data classifiers. One example of a data classifier is the algorithm used by the United States Postal Service since the 1960s to recognize scans of handwritten digits for processing zip codes. Active learning algorithms enable rapid training with minimal investment of time on the part of human experts to provide training examples consisting of correctly classified (labeled) input data. They function by identifying which examples would be most profitable for a human expert to label. The goal is to maximize classifier accuracy while minimizing the number of examples the expert must label. Although there are several well-established methods for active learning, they may not operate well when irrelevant examples are present in the data set. That is, they may select an item for labeling that the expert simply cannot assign to any of the valid classes. In the context of classifying handwritten digits, the irrelevant items may include stray marks, smudges, and mis-scans. Querying the expert about these items results in wasted time or erroneous labels, if the expert is forced to assign the item to one of the valid classes. In contrast, the new algorithm provides a specific mechanism for avoiding querying the irrelevant items. This algorithm has two components: an active learner (which could be a conventional active learning algorithm) and a relevance classifier. The combination of these components yields a method, denoted Relevance Bias, that enables the active learner to avoid querying irrelevant data so as to increase its learning rate and efficiency when irrelevant items are present. The algorithm collects irrelevant data in a set of rejected examples, then trains the relevance classifier to distinguish between labeled (relevant) training examples and the rejected ones. The active learner combines its ranking of the items with the probability that they are relevant to yield a final decision about which item

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.

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...

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...

Multi-label classifier based on histogram of gradients for predicting the anatomical therapeutic chemical class/classes of a given compound.

Science.gov (United States)

Nanni, Loris; Brahnam, Sheryl

2017-09-15

Given an unknown compound, is it possible to predict its Anatomical Therapeutic Chemical class/classes? This is a challenging yet important problem since such a prediction could be used to deduce not only a compound's possible active ingredients but also its therapeutic, pharmacological and chemical properties, thereby substantially expediting the pace of drug development. The problem is challenging because some drugs and compounds belong to two or more ATC classes, making machine learning extremely difficult. In this article a multi-label classifier system is proposed that incorporates information about a compound's chemical-chemical interaction and its structural and fingerprint similarities to other compounds belonging to the different ATC classes. The proposed system reshapes a 1D feature vector to obtain a 2D matrix representation of the compound. This matrix is then described by a histogram of gradients that is fed into a Multi-Label Learning with Label-Specific Features classifier. Rigorous cross-validations demonstrate the superior prediction quality of this method compared with other state-of-the-art approaches developed for this problem, a superiority that is reflected particularly in the absolute true rate, the most important and harshest metric for assessing multi-label systems. The MATLAB code for replicating the experiments presented in this article is available at https://www.dropbox.com/s/7v1mey48tl9bfgz/ToolPaperATC.rar?dl=0 . loris.nanni@unipd.it. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Co-Labeling for Multi-View Weakly Labeled Learning.

Science.gov (United States)

Xu, Xinxing; Li, Wen; Xu, Dong; Tsang, Ivor W

2016-06-01

It is often expensive and time consuming to collect labeled training samples in many real-world applications. To reduce human effort on annotating training samples, many machine learning techniques (e.g., semi-supervised learning (SSL), multi-instance learning (MIL), etc.) have been studied to exploit weakly labeled training samples. Meanwhile, when the training data is represented with multiple types of features, many multi-view learning methods have shown that classifiers trained on different views can help each other to better utilize the unlabeled training samples for the SSL task. In this paper, we study a new learning problem called multi-view weakly labeled learning, in which we aim to develop a unified approach to learn robust classifiers by effectively utilizing different types of weakly labeled multi-view data from a broad range of tasks including SSL, MIL and relative outlier detection (ROD). We propose an effective approach called co-labeling to solve the multi-view weakly labeled learning problem. Specifically, we model the learning problem on each view as a weakly labeled learning problem, which aims to learn an optimal classifier from a set of pseudo-label vectors generated by using the classifiers trained from other views. Unlike traditional co-training approaches using a single pseudo-label vector for training each classifier, our co-labeling approach explores different strategies to utilize the predictions from different views, biases and iterations for generating the pseudo-label vectors, making our approach more robust for real-world applications. Moreover, to further improve the weakly labeled learning on each view, we also exploit the inherent group structure in the pseudo-label vectors generated from different strategies, which leads to a new multi-layer multiple kernel learning problem. Promising results for text-based image retrieval on the NUS-WIDE dataset as well as news classification and text categorization on several real-world multi

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.

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.

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.

Interpreting Black-Box Classifiers Using Instance-Level Visual Explanations

Energy Technology Data Exchange (ETDEWEB)

Tamagnini, Paolo; Krause, Josua W.; Dasgupta, Aritra; Bertini, Enrico

2017-05-14

To realize the full potential of machine learning in diverse real- world domains, it is necessary for model predictions to be readily interpretable and actionable for the human in the loop. Analysts, who are the users but not the developers of machine learning models, often do not trust a model because of the lack of transparency in associating predictions with the underlying data space. To address this problem, we propose Rivelo, a visual analytic interface that enables analysts to understand the causes behind predictions of binary classifiers by interactively exploring a set of instance-level explanations. These explanations are model-agnostic, treating a model as a black box, and they help analysts in interactively probing the high-dimensional binary data space for detecting features relevant to predictions. We demonstrate the utility of the interface with a case study analyzing a random forest model on the sentiment of Yelp reviews about doctors.

Oblique decision trees using embedded support vector machines in classifier ensembles

NARCIS (Netherlands)

Menkovski, V.; Christou, I.; Efremidis, S.

2008-01-01

Classifier ensembles have emerged in recent years as a promising research area for boosting pattern recognition systems' performance. We present a new base classifier that utilizes oblique decision tree technology based on support vector machines for the construction of oblique (non-axis parallel)

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%.

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.

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…

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.

Informed Systems: Enabling Collaborative Evidence Based Organizational Learning

Directory of Open Access Journals (Sweden)

Mary M. Somerville

2015-12-01

Full Text Available Objective – In response to unrelenting disruptions in academic publishing and higher education ecosystems, the Informed Systems approach supports evidence based professional activities to make decisions and take actions. This conceptual paper presents two core models, Informed Systems Leadership Model and Collaborative Evidence-Based Information Process Model, whereby co-workers learn to make informed decisions by identifying the decisions to be made and the information required for those decisions. This is accomplished through collaborative design and iterative evaluation of workplace systems, relationships, and practices. Over time, increasingly effective and efficient structures and processes for using information to learn further organizational renewal and advance nimble responsiveness amidst dynamically changing circumstances. Methods – The integrated Informed Systems approach to fostering persistent workplace inquiry has its genesis in three theories that together activate and enable robust information usage and organizational learning. The information- and learning-intensive theories of Peter Checkland in England, which advance systems design, stimulate participants’ appreciation during the design process of the potential for using information to learn. Within a co-designed environment, intentional social practices continue workplace learning, described by Christine Bruce in Australia as informed learning enacted through information experiences. In addition, in Japan, Ikujiro Nonaka’s theories foster information exchange processes and knowledge creation activities within and across organizational units. In combination, these theories promote the kind of learning made possible through evolving and transferable capacity to use information to learn through design and usage of collaborative communication systems with associated professional practices. Informed Systems therein draws from three antecedent theories to create an original

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.

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...

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.

A Novel Approach for Multi Class Fault Diagnosis in Induction Machine Based on Statistical Time Features and Random Forest Classifier

Science.gov (United States)

Sonje, M. Deepak; Kundu, P.; Chowdhury, A.

2017-08-01

Fault diagnosis and detection is the important area in health monitoring of electrical machines. This paper proposes the recently developed machine learning classifier for multi class fault diagnosis in induction machine. The classification is based on random forest (RF) algorithm. Initially, stator currents are acquired from the induction machine under various conditions. After preprocessing the currents, fourteen statistical time features are estimated for each phase of the current. These parameters are considered as inputs to the classifier. The main scope of the paper is to evaluate effectiveness of RF classifier for individual and mixed fault diagnosis in induction machine. The stator, rotor and mixed faults (stator and rotor faults) are classified using the proposed classifier. The obtained performance measures are compared with the multilayer perceptron neural network (MLPNN) classifier. The results show the much better performance measures and more accurate than MLPNN classifier. For demonstration of planned fault diagnosis algorithm, experimentally obtained results are considered to build the classifier more practical.

Integrating machine learning and physician knowledge to improve the accuracy of breast biopsy.

Science.gov (United States)