WorldWideScience

Sample records for generative semi-supervised learning

  1. Semi-supervised Learning with Deep Generative Models

    NARCIS (Netherlands)

    Kingma, D.P.; Rezende, D.J.; Mohamed, S.; Welling, M.

    2014-01-01

    The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and

  2. Improving Semi-Supervised Learning with Auxiliary Deep Generative Models

    DEFF Research Database (Denmark)

    Maaløe, Lars; Sønderby, Casper Kaae; Sønderby, Søren Kaae

    Deep generative models based upon continuous variational distributions parameterized by deep networks give state-of-the-art performance. In this paper we propose a framework for extending the latent representation with extra auxiliary variables in order to make the variational distribution more...... expressive for semi-supervised learning. By utilizing the stochasticity of the auxiliary variable we demonstrate how to train discriminative classifiers resulting in state-of-the-art performance within semi-supervised learning exemplified by an 0.96% error on MNIST using 100 labeled data points. Furthermore...

  3. Generative Adversarial Networks-Based Semi-Supervised Learning for Hyperspectral Image Classification

    Directory of Open Access Journals (Sweden)

    Zhi He

    2017-10-01

    Full Text Available Classification of hyperspectral image (HSI is an important research topic in the remote sensing community. Significant efforts (e.g., deep learning have been concentrated on this task. However, it is still an open issue to classify the high-dimensional HSI with a limited number of training samples. In this paper, we propose a semi-supervised HSI classification method inspired by the generative adversarial networks (GANs. Unlike the supervised methods, the proposed HSI classification method is semi-supervised, which can make full use of the limited labeled samples as well as the sufficient unlabeled samples. Core ideas of the proposed method are twofold. First, the three-dimensional bilateral filter (3DBF is adopted to extract the spectral-spatial features by naturally treating the HSI as a volumetric dataset. The spatial information is integrated into the extracted features by 3DBF, which is propitious to the subsequent classification step. Second, GANs are trained on the spectral-spatial features for semi-supervised learning. A GAN contains two neural networks (i.e., generator and discriminator trained in opposition to one another. The semi-supervised learning is achieved by adding samples from the generator to the features and increasing the dimension of the classifier output. Experimental results obtained on three benchmark HSI datasets have confirmed the effectiveness of the proposed method , especially with a limited number of labeled samples.

  4. Human semi-supervised learning.

    Science.gov (United States)

    Gibson, Bryan R; Rogers, Timothy T; Zhu, Xiaojin

    2013-01-01

    Most empirical work in human categorization has studied learning in either fully supervised or fully unsupervised scenarios. Most real-world learning scenarios, however, are semi-supervised: Learners receive a great deal of unlabeled information from the world, coupled with occasional experiences in which items are directly labeled by a knowledgeable source. A large body of work in machine learning has investigated how learning can exploit both labeled and unlabeled data provided to a learner. Using equivalences between models found in human categorization and machine learning research, we explain how these semi-supervised techniques can be applied to human learning. A series of experiments are described which show that semi-supervised learning models prove useful for explaining human behavior when exposed to both labeled and unlabeled data. We then discuss some machine learning models that do not have familiar human categorization counterparts. Finally, we discuss some challenges yet to be addressed in the use of semi-supervised models for modeling human categorization. Copyright © 2013 Cognitive Science Society, Inc.

  5. A SURVEY OF SEMI-SUPERVISED LEARNING

    OpenAIRE

    Amrita Sadarangani *, Dr. Anjali Jivani

    2016-01-01

    Semi Supervised Learning involves using both labeled and unlabeled data to train a classifier or for clustering. Semi supervised learning finds usage in many applications, since labeled data can be hard to find in many cases. Currently, a lot of research is being conducted in this area. This paper discusses the different algorithms of semi supervised learning and then their advantages and limitations are compared. The differences between supervised classification and semi-supervised classific...

  6. Coupled Semi-Supervised Learning

    Science.gov (United States)

    2010-05-01

    Additionally, specify the expected category of each relation argument to enable type-checking. Subsystem components and the KI can benefit from methods that...confirm that our coupled semi-supervised learning approaches can scale to hun- dreds of predicates and can benefit from using a diverse set of...organization yes California Institute of Technology vegetable food yes carrots vehicle item yes airplanes vertebrate animal yes videoGame product yes

  7. Cross-Domain Semi-Supervised Learning Using Feature Formulation.

    Science.gov (United States)

    Xingquan Zhu

    2011-12-01

    Semi-Supervised Learning (SSL) traditionally makes use of unlabeled samples by including them into the training set through an automated labeling process. Such a primitive Semi-Supervised Learning (pSSL) approach suffers from a number of disadvantages including false labeling and incapable of utilizing out-of-domain samples. In this paper, we propose a formative Semi-Supervised Learning (fSSL) framework which explores hidden features between labeled and unlabeled samples to achieve semi-supervised learning. fSSL regards that both labeled and unlabeled samples are generated from some hidden concepts with labeling information partially observable for some samples. The key of the fSSL is to recover the hidden concepts, and take them as new features to link labeled and unlabeled samples for semi-supervised learning. Because unlabeled samples are only used to generate new features, but not to be explicitly included in the training set like pSSL does, fSSL overcomes the inherent disadvantages of the traditional pSSL methods, especially for samples not within the same domain as the labeled instances. Experimental results and comparisons demonstrate that fSSL significantly outperforms pSSL-based methods for both within-domain and cross-domain semi-supervised learning.

  8. Semi-supervised Learning for Phenotyping Tasks.

    Science.gov (United States)

    Dligach, Dmitriy; Miller, Timothy; Savova, Guergana K

    2015-01-01

    Supervised learning is the dominant approach to automatic electronic health records-based phenotyping, but it is expensive due to the cost of manual chart review. Semi-supervised learning takes advantage of both scarce labeled and plentiful unlabeled data. In this work, we study a family of semi-supervised learning algorithms based on Expectation Maximization (EM) in the context of several phenotyping tasks. We first experiment with the basic EM algorithm. When the modeling assumptions are violated, basic EM leads to inaccurate parameter estimation. Augmented EM attenuates this shortcoming by introducing a weighting factor that downweights the unlabeled data. Cross-validation does not always lead to the best setting of the weighting factor and other heuristic methods may be preferred. We show that accurate phenotyping models can be trained with only a few hundred labeled (and a large number of unlabeled) examples, potentially providing substantial savings in the amount of the required manual chart review.

  9. Semi-supervised learning via regularized boosting working on multiple semi-supervised assumptions.

    Science.gov (United States)

    Chen, Ke; Wang, Shihai

    2011-01-01

    Semi-supervised learning concerns the problem of learning in the presence of labeled and unlabeled data. Several boosting algorithms have been extended to semi-supervised learning with various strategies. To our knowledge, however, none of them takes all three semi-supervised assumptions, i.e., smoothness, cluster, and manifold assumptions, together into account during boosting learning. In this paper, we propose a novel cost functional consisting of the margin cost on labeled data and the regularization penalty on unlabeled data based on three fundamental semi-supervised assumptions. Thus, minimizing our proposed cost functional with a greedy yet stagewise functional optimization procedure leads to a generic boosting framework for semi-supervised learning. Extensive experiments demonstrate that our algorithm yields favorite results for benchmark and real-world classification tasks in comparison to state-of-the-art semi-supervised learning algorithms, including newly developed boosting algorithms. Finally, we discuss relevant issues and relate our algorithm to the previous work.

  10. Graph-based semi-supervised learning

    CERN Document Server

    Subramanya, Amarnag

    2014-01-01

    While labeled data is expensive to prepare, ever increasing amounts of unlabeled data is becoming widely available. In order to adapt to this phenomenon, several semi-supervised learning (SSL) algorithms, which learn from labeled as well as unlabeled data, have been developed. In a separate line of work, researchers have started to realize that graphs provide a natural way to represent data in a variety of domains. Graph-based SSL algorithms, which bring together these two lines of work, have been shown to outperform the state-of-the-art in many applications in speech processing, computer visi

  11. Semi-Supervised Generation with Cluster-aware Generative Models

    DEFF Research Database (Denmark)

    Maaløe, Lars; Fraccaro, Marco; Winther, Ole

    2017-01-01

    Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically disregarded when training generative models. We propose the Clust...... a log-likelihood of −79.38 nats on permutation invariant MNIST, while also achieving competitive semi-supervised classification accuracies. The model can also be trained fully unsupervised, and still improve the log-likelihood performance with respect to related methods.......Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically disregarded when training generative models. We propose the Cluster...

  12. SemiBoost: boosting for semi-supervised learning.

    Science.gov (United States)

    Mallapragada, Pavan Kumar; Jin, Rong; Jain, Anil K; Liu, Yi

    2009-11-01

    Semi-supervised learning has attracted a significant amount of attention in pattern recognition and machine learning. Most previous studies have focused on designing special algorithms to effectively exploit the unlabeled data in conjunction with labeled data. Our goal is to improve the classification accuracy of any given supervised learning algorithm by using the available unlabeled examples. We call this as the Semi-supervised improvement problem, to distinguish the proposed approach from the existing approaches. We design a metasemi-supervised learning algorithm that wraps around the underlying supervised algorithm and improves its performance using unlabeled data. This problem is particularly important when we need to train a supervised learning algorithm with a limited number of labeled examples and a multitude of unlabeled examples. We present a boosting framework for semi-supervised learning, termed as SemiBoost. The key advantages of the proposed semi-supervised learning approach are: 1) performance improvement of any supervised learning algorithm with a multitude of unlabeled data, 2) efficient computation by the iterative boosting algorithm, and 3) exploiting both manifold and cluster assumption in training classification models. An empirical study on 16 different data sets and text categorization demonstrates that the proposed framework improves the performance of several commonly used supervised learning algorithms, given a large number of unlabeled examples. We also show that the performance of the proposed algorithm, SemiBoost, is comparable to the state-of-the-art semi-supervised learning algorithms.

  13. Robust Semi-Supervised Manifold Learning Algorithm for Classification

    Directory of Open Access Journals (Sweden)

    Mingxia Chen

    2018-01-01

    Full Text Available In the recent years, manifold learning methods have been widely used in data classification to tackle the curse of dimensionality problem, since they can discover the potential intrinsic low-dimensional structures of the high-dimensional data. Given partially labeled data, the semi-supervised manifold learning algorithms are proposed to predict the labels of the unlabeled points, taking into account label information. However, these semi-supervised manifold learning algorithms are not robust against noisy points, especially when the labeled data contain noise. In this paper, we propose a framework for robust semi-supervised manifold learning (RSSML to address this problem. The noisy levels of the labeled points are firstly predicted, and then a regularization term is constructed to reduce the impact of labeled points containing noise. A new robust semi-supervised optimization model is proposed by adding the regularization term to the traditional semi-supervised optimization model. Numerical experiments are given to show the improvement and efficiency of RSSML on noisy data sets.

  14. Label Information Guided Graph Construction for Semi-Supervised Learning.

    Science.gov (United States)

    Zhuang, Liansheng; Zhou, Zihan; Gao, Shenghua; Yin, Jingwen; Lin, Zhouchen; Ma, Yi

    2017-09-01

    In the literature, most existing graph-based semi-supervised learning methods only use the label information of observed samples in the label propagation stage, while ignoring such valuable information when learning the graph. In this paper, we argue that it is beneficial to consider the label information in the graph learning stage. Specifically, by enforcing the weight of edges between labeled samples of different classes to be zero, we explicitly incorporate the label information into the state-of-the-art graph learning methods, such as the low-rank representation (LRR), and propose a novel semi-supervised graph learning method called semi-supervised low-rank representation. This results in a convex optimization problem with linear constraints, which can be solved by the linearized alternating direction method. Though we take LRR as an example, our proposed method is in fact very general and can be applied to any self-representation graph learning methods. Experiment results on both synthetic and real data sets demonstrate that the proposed graph learning method can better capture the global geometric structure of the data, and therefore is more effective for semi-supervised learning tasks.

  15. Safe semi-supervised learning based on weighted likelihood.

    Science.gov (United States)

    Kawakita, Masanori; Takeuchi, Jun'ichi

    2014-05-01

    We are interested in developing a safe semi-supervised learning that works in any situation. Semi-supervised learning postulates that n(') unlabeled data are available in addition to n labeled data. However, almost all of the previous semi-supervised methods require additional assumptions (not only unlabeled data) to make improvements on supervised learning. If such assumptions are not met, then the methods possibly perform worse than supervised learning. Sokolovska, Cappé, and Yvon (2008) proposed a semi-supervised method based on a weighted likelihood approach. They proved that this method asymptotically never performs worse than supervised learning (i.e., it is safe) without any assumption. Their method is attractive because it is easy to implement and is potentially general. Moreover, it is deeply related to a certain statistical paradox. However, the method of Sokolovska et al. (2008) assumes a very limited situation, i.e., classification, discrete covariates, n(')→∞ and a maximum likelihood estimator. In this paper, we extend their method by modifying the weight. We prove that our proposal is safe in a significantly wide range of situations as long as n≤n('). Further, we give a geometrical interpretation of the proof of safety through the relationship with the above-mentioned statistical paradox. Finally, we show that the above proposal is asymptotically safe even when n(')

  16. Semi-supervised and unsupervised extreme learning machines.

    Science.gov (United States)

    Huang, Gao; Song, Shiji; Gupta, Jatinder N D; Wu, Cheng

    2014-12-01

    Extreme learning machines (ELMs) have proven to be efficient and effective learning mechanisms for pattern classification and regression. However, ELMs are primarily applied to supervised learning problems. Only a few existing research papers have used ELMs to explore unlabeled data. In this paper, we extend ELMs for both semi-supervised and unsupervised tasks based on the manifold regularization, thus greatly expanding the applicability of ELMs. The key advantages of the proposed algorithms are as follows: 1) both the semi-supervised ELM (SS-ELM) and the unsupervised ELM (US-ELM) exhibit learning capability and computational efficiency of ELMs; 2) both algorithms naturally handle multiclass classification or multicluster clustering; and 3) both algorithms are inductive and can handle unseen data at test time directly. Moreover, it is shown in this paper that all the supervised, semi-supervised, and unsupervised ELMs can actually be put into a unified framework. This provides new perspectives for understanding the mechanism of random feature mapping, which is the key concept in ELM theory. Empirical study on a wide range of data sets demonstrates that the proposed algorithms are competitive with the state-of-the-art semi-supervised or unsupervised learning algorithms in terms of accuracy and efficiency.

  17. Semi-supervised Eigenvectors for Locally-biased Learning

    DEFF Research Database (Denmark)

    Hansen, Toke Jansen; Mahoney, Michael W.

    2012-01-01

    In many applications, one has side information, e.g., labels that are provided in a semi-supervised manner, about a specific target region of a large data set, and one wants to perform machine learning and data analysis tasks "nearby" that pre-specified target region. Locally-biased problems of t...

  18. Semi-supervised learning for ordinal Kernel Discriminant Analysis.

    Science.gov (United States)

    Pérez-Ortiz, M; Gutiérrez, P A; Carbonero-Ruz, M; Hervás-Martínez, C

    2016-12-01

    Ordinal classification considers those classification problems where the labels of the variable to predict follow a given order. Naturally, labelled data is scarce or difficult to obtain in this type of problems because, in many cases, ordinal labels are given by a user or expert (e.g. in recommendation systems). Firstly, this paper develops a new strategy for ordinal classification where both labelled and unlabelled data are used in the model construction step (a scheme which is referred to as semi-supervised learning). More specifically, the ordinal version of kernel discriminant learning is extended for this setting considering the neighbourhood information of unlabelled data, which is proposed to be computed in the feature space induced by the kernel function. Secondly, a new method for semi-supervised kernel learning is devised in the context of ordinal classification, which is combined with our developed classification strategy to optimise the kernel parameters. The experiments conducted compare 6 different approaches for semi-supervised learning in the context of ordinal classification in a battery of 30 datasets, showing (1) the good synergy of the ordinal version of discriminant analysis and the use of unlabelled data and (2) the advantage of computing distances in the feature space induced by the kernel function. Copyright © 2016 Elsevier Ltd. All rights reserved.

  19. Regular graph construction for semi-supervised learning

    International Nuclear Information System (INIS)

    Vega-Oliveros, Didier A; Berton, Lilian; Eberle, Andre Mantini; Lopes, Alneu de Andrade; Zhao, Liang

    2014-01-01

    Semi-supervised learning (SSL) stands out for using a small amount of labeled points for data clustering and classification. In this scenario graph-based methods allow the analysis of local and global characteristics of the available data by identifying classes or groups regardless data distribution and representing submanifold in Euclidean space. Most of methods used in literature for SSL classification do not worry about graph construction. However, regular graphs can obtain better classification accuracy compared to traditional methods such as k-nearest neighbor (kNN), since kNN benefits the generation of hubs and it is not appropriate for high-dimensionality data. Nevertheless, methods commonly used for generating regular graphs have high computational cost. We tackle this problem introducing an alternative method for generation of regular graphs with better runtime performance compared to methods usually find in the area. Our technique is based on the preferential selection of vertices according some topological measures, like closeness, generating at the end of the process a regular graph. Experiments using the global and local consistency method for label propagation show that our method provides better or equal classification rate in comparison with kNN

  20. Maximum margin semi-supervised learning with irrelevant data.

    Science.gov (United States)

    Yang, Haiqin; Huang, Kaizhu; King, Irwin; Lyu, Michael R

    2015-10-01

    Semi-supervised learning (SSL) is a typical learning paradigms training a model from both labeled and unlabeled data. The traditional SSL models usually assume unlabeled data are relevant to the labeled data, i.e., following the same distributions of the targeted labeled data. In this paper, we address a different, yet formidable scenario in semi-supervised classification, where the unlabeled data may contain irrelevant data to the labeled data. To tackle this problem, we develop a maximum margin model, named tri-class support vector machine (3C-SVM), to utilize the available training data, while seeking a hyperplane for separating the targeted data well. Our 3C-SVM exhibits several characteristics and advantages. First, it does not need any prior knowledge and explicit assumption on the data relatedness. On the contrary, it can relieve the effect of irrelevant unlabeled data based on the logistic principle and maximum entropy principle. That is, 3C-SVM approaches an ideal classifier. This classifier relies heavily on labeled data and is confident on the relevant data lying far away from the decision hyperplane, while maximally ignoring the irrelevant data, which are hardly distinguished. Second, theoretical analysis is provided to prove that in what condition, the irrelevant data can help to seek the hyperplane. Third, 3C-SVM is a generalized model that unifies several popular maximum margin models, including standard SVMs, Semi-supervised SVMs (S(3)VMs), and SVMs learned from the universum (U-SVMs) as its special cases. More importantly, we deploy a concave-convex produce to solve the proposed 3C-SVM, transforming the original mixed integer programming, to a semi-definite programming relaxation, and finally to a sequence of quadratic programming subproblems, which yields the same worst case time complexity as that of S(3)VMs. Finally, we demonstrate the effectiveness and efficiency of our proposed 3C-SVM through systematical experimental comparisons. Copyright

  1. Semi-Supervised Multitask Learning for Scene Recognition.

    Science.gov (United States)

    Lu, Xiaoqiang; Li, Xuelong; Mou, Lichao

    2015-09-01

    Scene recognition has been widely studied to understand visual information from the level of objects and their relationships. Toward scene recognition, many methods have been proposed. They, however, encounter difficulty to improve the accuracy, mainly due to two limitations: 1) lack of analysis of intrinsic relationships across different scales, say, the initial input and its down-sampled versions and 2) existence of redundant features. This paper develops a semi-supervised learning mechanism to reduce the above two limitations. To address the first limitation, we propose a multitask model to integrate scene images of different resolutions. For the second limitation, we build a model of sparse feature selection-based manifold regularization (SFSMR) to select the optimal information and preserve the underlying manifold structure of data. SFSMR coordinates the advantages of sparse feature selection and manifold regulation. Finally, we link the multitask model and SFSMR, and propose the semi-supervised learning method to reduce the two limitations. Experimental results report the improvements of the accuracy in scene recognition.

  2. Prototype Vector Machine for Large Scale Semi-Supervised Learning

    Energy Technology Data Exchange (ETDEWEB)

    Zhang, Kai; Kwok, James T.; Parvin, Bahram

    2009-04-29

    Practicaldataminingrarelyfalls exactlyinto the supervisedlearning scenario. Rather, the growing amount of unlabeled data poses a big challenge to large-scale semi-supervised learning (SSL). We note that the computationalintensivenessofgraph-based SSLarises largely from the manifold or graph regularization, which in turn lead to large models that are dificult to handle. To alleviate this, we proposed the prototype vector machine (PVM), a highlyscalable,graph-based algorithm for large-scale SSL. Our key innovation is the use of"prototypes vectors" for effcient approximation on both the graph-based regularizer and model representation. The choice of prototypes are grounded upon two important criteria: they not only perform effective low-rank approximation of the kernel matrix, but also span a model suffering the minimum information loss compared with the complete model. We demonstrate encouraging performance and appealing scaling properties of the PVM on a number of machine learning benchmark data sets.

  3. Semi-Supervised Learning to Identify UMLS Semantic Relations.

    Science.gov (United States)

    Luo, Yuan; Uzuner, Ozlem

    2014-01-01

    The UMLS Semantic Network is constructed by experts and requires periodic expert review to update. We propose and implement a semi-supervised approach for automatically identifying UMLS semantic relations from narrative text in PubMed. Our method analyzes biomedical narrative text to collect semantic entity pairs, and extracts multiple semantic, syntactic and orthographic features for the collected pairs. We experiment with seeded k-means clustering with various distance metrics. We create and annotate a ground truth corpus according to the top two levels of the UMLS semantic relation hierarchy. We evaluate our system on this corpus and characterize the learning curves of different clustering configuration. Using KL divergence consistently performs the best on the held-out test data. With full seeding, we obtain macro-averaged F-measures above 70% for clustering the top level UMLS relations (2-way), and above 50% for clustering the second level relations (7-way).

  4. Building an Arabic Sentiment Lexicon Using Semi-supervised Learning

    Directory of Open Access Journals (Sweden)

    Fawaz H.H. Mahyoub

    2014-12-01

    Full Text Available Sentiment analysis is the process of determining a predefined sentiment from text written in a natural language with respect to the entity to which it is referring. A number of lexical resources are available to facilitate this task in English. One such resource is the SentiWordNet, which assigns sentiment scores to words found in the English WordNet. In this paper, we present an Arabic sentiment lexicon that assigns sentiment scores to the words found in the Arabic WordNet. Starting from a small seed list of positive and negative words, we used semi-supervised learning to propagate the scores in the Arabic WordNet by exploiting the synset relations. Our algorithm assigned a positive sentiment score to more than 800, a negative score to more than 600 and a neutral score to more than 6000 words in the Arabic WordNet. The lexicon was evaluated by incorporating it into a machine learning-based classifier. The experiments were conducted on several Arabic sentiment corpora, and we were able to achieve a 96% classification accuracy.

  5. Seizure Classification From EEG Signals Using Transfer Learning, Semi-Supervised Learning and TSK Fuzzy System.

    Science.gov (United States)

    Jiang, Yizhang; Wu, Dongrui; Deng, Zhaohong; Qian, Pengjiang; Wang, Jun; Wang, Guanjin; Chung, Fu-Lai; Choi, Kup-Sze; Wang, Shitong

    2017-12-01

    Recognition of epileptic seizures from offline EEG signals is very important in clinical diagnosis of epilepsy. Compared with manual labeling of EEG signals by doctors, machine learning approaches can be faster and more consistent. However, the classification accuracy is usually not satisfactory for two main reasons: the distributions of the data used for training and testing may be different, and the amount of training data may not be enough. In addition, most machine learning approaches generate black-box models that are difficult to interpret. In this paper, we integrate transductive transfer learning, semi-supervised learning and TSK fuzzy system to tackle these three problems. More specifically, we use transfer learning to reduce the discrepancy in data distribution between the training and testing data, employ semi-supervised learning to use the unlabeled testing data to remedy the shortage of training data, and adopt TSK fuzzy system to increase model interpretability. Two learning algorithms are proposed to train the system. Our experimental results show that the proposed approaches can achieve better performance than many state-of-the-art seizure classification algorithms.

  6. Semi-Supervised Learning for Classification of Protein Sequence Data

    Directory of Open Access Journals (Sweden)

    Brian R. King

    2008-01-01

    Full Text Available Protein sequence data continue to become available at an exponential rate. Annotation of functional and structural attributes of these data lags far behind, with only a small fraction of the data understood and labeled by experimental methods. Classification methods that are based on semi-supervised learning can increase the overall accuracy of classifying partly labeled data in many domains, but very few methods exist that have shown their effect on protein sequence classification. We show how proven methods from text classification can be applied to protein sequence data, as we consider both existing and novel extensions to the basic methods, and demonstrate restrictions and differences that must be considered. We demonstrate comparative results against the transductive support vector machine, and show superior results on the most difficult classification problems. Our results show that large repositories of unlabeled protein sequence data can indeed be used to improve predictive performance, particularly in situations where there are fewer labeled protein sequences available, and/or the data are highly unbalanced in nature.

  7. Accuracy of latent-variable estimation in Bayesian semi-supervised learning.

    Science.gov (United States)

    Yamazaki, Keisuke

    2015-09-01

    Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable ones. The estimation of latent variables in semi-supervised learning, where some labels are observed, will be more precise than that in unsupervised, and one of the concerns is to clarify the effect of the labeled data. However, there has not been sufficient theoretical analysis of the accuracy of the estimation of latent variables. In a previous study, a distribution-based error function was formulated, and its asymptotic form was calculated for unsupervised learning with generative models. It has been shown that, for the estimation of latent variables, the Bayes method is more accurate than the maximum-likelihood method. The present paper reveals the asymptotic forms of the error function in Bayesian semi-supervised learning for both discriminative and generative models. The results show that the generative model, which uses all of the given data, performs better when the model is well specified. Copyright © 2015 Elsevier Ltd. All rights reserved.

  8. Multi-Modal Curriculum Learning for Semi-Supervised Image Classification.

    Science.gov (United States)

    Gong, Chen; Tao, Dacheng; Maybank, Stephen J; Liu, Wei; Kang, Guoliang; Yang, Jie

    2016-07-01

    Semi-supervised image classification aims to classify a large quantity of unlabeled images by typically harnessing scarce labeled images. Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images, such as outliers, because they treat all unlabeled images equally and conduct classifications in an imperfectly ordered sequence. In this paper, we employ the curriculum learning methodology by investigating the difficulty of classifying every unlabeled image. The reliability and the discriminability of these unlabeled images are particularly investigated for evaluating their difficulty. As a result, an optimized image sequence is generated during the iterative propagations, and the unlabeled images are logically classified from simple to difficult. Furthermore, since images are usually characterized by multiple visual feature descriptors, we associate each kind of features with a teacher, and design a multi-modal curriculum learning (MMCL) strategy to integrate the information from different feature modalities. In each propagation, each teacher analyzes the difficulties of the currently unlabeled images from its own modality viewpoint. A consensus is subsequently reached among all the teachers, determining the currently simplest images (i.e., a curriculum), which are to be reliably classified by the multi-modal learner. This well-organized propagation process leveraging multiple teachers and one learner enables our MMCL to outperform five state-of-the-art methods on eight popular image data sets.

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

    Science.gov (United States)

    Yonemoto, Haruka; Asai, Kiyoshi; Hamada, Michiaki

    2015-08-01

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

  10. Active semi-supervised learning method with hybrid deep belief networks.

    Science.gov (United States)

    Zhou, Shusen; Chen, Qingcai; Wang, Xiaolong

    2014-01-01

    In this paper, we develop a novel semi-supervised learning algorithm called active hybrid deep belief networks (AHD), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltzmann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. Finally, active learning method is combined based on the proposed deep architecture. We did several experiments on five sentiment classification datasets, and show that AHD is competitive with previous semi-supervised learning algorithm. Experiments are also conducted to verify the effectiveness of our proposed method with different number of labeled reviews and unlabeled reviews respectively.

  11. Fully Decentralized Semi-supervised Learning via Privacy-preserving Matrix Completion.

    Science.gov (United States)

    Fierimonte, Roberto; Scardapane, Simone; Uncini, Aurelio; Panella, Massimo

    2016-08-26

    Distributed learning refers to the problem of inferring a function when the training data are distributed among different nodes. While significant work has been done in the contexts of supervised and unsupervised learning, the intermediate case of Semi-supervised learning in the distributed setting has received less attention. In this paper, we propose an algorithm for this class of problems, by extending the framework of manifold regularization. The main component of the proposed algorithm consists of a fully distributed computation of the adjacency matrix of the training patterns. To this end, we propose a novel algorithm for low-rank distributed matrix completion, based on the framework of diffusion adaptation. Overall, the distributed Semi-supervised algorithm is efficient and scalable, and it can preserve privacy by the inclusion of flexible privacy-preserving mechanisms for similarity computation. The experimental results and comparison on a wide range of standard Semi-supervised benchmarks validate our proposal.

  12. Contaminant source identification using semi-supervised machine learning

    International Nuclear Information System (INIS)

    Vesselinov, Velimir Valentinov; Alexandrov, Boian S.; O’Malley, Dan

    2017-01-01

    Identification of the original groundwater types present in geochemical mixtures observed in an aquifer is a challenging but very important task. Frequently, some of the groundwater types are related to different infiltration and/or contamination sources associated with various geochemical signatures and origins. The characterization of groundwater mixing processes typically requires solving complex inverse models representing groundwater flow and geochemical transport in the aquifer, where the inverse analysis accounts for available site data. Usually, the model is calibrated against the available data characterizing the spatial and temporal distribution of the observed geochemical types. Numerous different geochemical constituents and processes may need to be simulated in these models which further complicates the analyses. In this paper, we propose a new contaminant source identification approach that performs decomposition of the observation mixtures based on Non-negative Matrix Factorization (NMF) method for Blind Source Separation (BSS), coupled with a custom semi-supervised clustering algorithm. Our methodology, called NMFk, is capable of identifying (a) the unknown number of groundwater types and (b) the original geochemical concentration of the contaminant sources from measured geochemical mixtures with unknown mixing ratios without any additional site information. NMFk is tested on synthetic and real-world site data. Finally, the NMFk algorithm works with geochemical data represented in the form of concentrations, ratios (of two constituents; for example, isotope ratios), and delta notations (standard normalized stable isotope ratios).

  13. Evaluation of Semi-supervised Learning for Classification of Protein Crystallization Imagery.

    Science.gov (United States)

    Sigdel, Madhav; Dinç, İmren; Dinç, Semih; Sigdel, Madhu S; Pusey, Marc L; Aygün, Ramazan S

    2014-03-01

    In this paper, we investigate the performance of two wrapper methods for semi-supervised learning algorithms for classification of protein crystallization images with limited labeled images. Firstly, we evaluate the performance of semi-supervised approach using self-training with naïve Bayesian (NB) and sequential minimum optimization (SMO) as the base classifiers. The confidence values returned by these classifiers are used to select high confident predictions to be used for self-training. Secondly, we analyze the performance of Yet Another Two Stage Idea (YATSI) semi-supervised learning using NB, SMO, multilayer perceptron (MLP), J48 and random forest (RF) classifiers. These results are compared with the basic supervised learning using the same training sets. We perform our experiments on a dataset consisting of 2250 protein crystallization images for different proportions of training and test data. Our results indicate that NB and SMO using both self-training and YATSI semi-supervised approaches improve accuracies with respect to supervised learning. On the other hand, MLP, J48 and RF perform better using basic supervised learning. Overall, random forest classifier yields the best accuracy with supervised learning for our dataset.

  14. Multiclass semi-supervised learning for animal behavior recognition from accelerometer data

    NARCIS (Netherlands)

    Tanha, J.; van Someren, M.; de Bakker, M.; Bouten, W.; Shamoun-Baranes, J.; Afsarmanesh, H.

    2012-01-01

    In this paper we present a new Multiclass semi-supervised learning algorithm that uses a base classifier in combination with a similarity function applied to all data to find a classifier that maximizes the margin and consistency over all data. A novel multiclass loss function is presented and used

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

    Science.gov (United States)

    Patel, Nihir; Wang, Jason T L

    2015-10-01

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

  16. Ensemble learning with trees and rules: supervised, semi-supervised, unsupervised

    Science.gov (United States)

    In this article, we propose several new approaches for post processing a large ensemble of conjunctive rules for supervised and semi-supervised learning problems. We show with various examples that for high dimensional regression problems the models constructed by the post processing the rules with ...

  17. Integrative gene network construction to analyze cancer recurrence using semi-supervised learning.

    Science.gov (United States)

    Park, Chihyun; Ahn, Jaegyoon; Kim, Hyunjin; Park, Sanghyun

    2014-01-01

    The prognosis of cancer recurrence is an important research area in bioinformatics and is challenging due to the small sample sizes compared to the vast number of genes. There have been several attempts to predict cancer recurrence. Most studies employed a supervised approach, which uses only a few labeled samples. Semi-supervised learning can be a great alternative to solve this problem. There have been few attempts based on manifold assumptions to reveal the detailed roles of identified cancer genes in recurrence. In order to predict cancer recurrence, we proposed a novel semi-supervised learning algorithm based on a graph regularization approach. We transformed the gene expression data into a graph structure for semi-supervised learning and integrated protein interaction data with the gene expression data to select functionally-related gene pairs. Then, we predicted the recurrence of cancer by applying a regularization approach to the constructed graph containing both labeled and unlabeled nodes. The average improvement rate of accuracy for three different cancer datasets was 24.9% compared to existing supervised and semi-supervised methods. We performed functional enrichment on the gene networks used for learning. We identified that those gene networks are significantly associated with cancer-recurrence-related biological functions. Our algorithm was developed with standard C++ and is available in Linux and MS Windows formats in the STL library. The executable program is freely available at: http://embio.yonsei.ac.kr/~Park/ssl.php.

  18. Integrative gene network construction to analyze cancer recurrence using semi-supervised learning.

    Directory of Open Access Journals (Sweden)

    Chihyun Park

    Full Text Available BACKGROUND: The prognosis of cancer recurrence is an important research area in bioinformatics and is challenging due to the small sample sizes compared to the vast number of genes. There have been several attempts to predict cancer recurrence. Most studies employed a supervised approach, which uses only a few labeled samples. Semi-supervised learning can be a great alternative to solve this problem. There have been few attempts based on manifold assumptions to reveal the detailed roles of identified cancer genes in recurrence. RESULTS: In order to predict cancer recurrence, we proposed a novel semi-supervised learning algorithm based on a graph regularization approach. We transformed the gene expression data into a graph structure for semi-supervised learning and integrated protein interaction data with the gene expression data to select functionally-related gene pairs. Then, we predicted the recurrence of cancer by applying a regularization approach to the constructed graph containing both labeled and unlabeled nodes. CONCLUSIONS: The average improvement rate of accuracy for three different cancer datasets was 24.9% compared to existing supervised and semi-supervised methods. We performed functional enrichment on the gene networks used for learning. We identified that those gene networks are significantly associated with cancer-recurrence-related biological functions. Our algorithm was developed with standard C++ and is available in Linux and MS Windows formats in the STL library. The executable program is freely available at: http://embio.yonsei.ac.kr/~Park/ssl.php.

  19. Semi-Supervised Multi-View Ensemble Learning Based On Extracting Cross-View Correlation

    Directory of Open Access Journals (Sweden)

    ZALL, R.

    2016-05-01

    Full Text Available Correlated information between different views incorporate useful for learning in multi view data. Canonical correlation analysis (CCA plays important role to extract these information. However, CCA only extracts the correlated information between paired data and cannot preserve correlated information between within-class samples. In this paper, we propose a two-view semi-supervised learning method called semi-supervised random correlation ensemble base on spectral clustering (SS_RCE. SS_RCE uses a multi-view method based on spectral clustering which takes advantage of discriminative information in multiple views to estimate labeling information of unlabeled samples. In order to enhance discriminative power of CCA features, we incorporate the labeling information of both unlabeled and labeled samples into CCA. Then, we use random correlation between within-class samples from cross view to extract diverse correlated features for training component classifiers. Furthermore, we extend a general model namely SSMV_RCE to construct ensemble method to tackle semi-supervised learning in the presence of multiple views. Finally, we compare the proposed methods with existing multi-view feature extraction methods using multi-view semi-supervised ensembles. Experimental results on various multi-view data sets are presented to demonstrate the effectiveness of the proposed methods.

  20. A Cluster-then-label Semi-supervised Learning Approach for Pathology Image Classification.

    Science.gov (United States)

    Peikari, Mohammad; Salama, Sherine; Nofech-Mozes, Sharon; Martel, Anne L

    2018-05-08

    Completely labeled pathology datasets are often challenging and time-consuming to obtain. Semi-supervised learning (SSL) methods are able to learn from fewer labeled data points with the help of a large number of unlabeled data points. In this paper, we investigated the possibility of using clustering analysis to identify the underlying structure of the data space for SSL. A cluster-then-label method was proposed to identify high-density regions in the data space which were then used to help a supervised SVM in finding the decision boundary. We have compared our method with other supervised and semi-supervised state-of-the-art techniques using two different classification tasks applied to breast pathology datasets. We found that compared with other state-of-the-art supervised and semi-supervised methods, our SSL method is able to improve classification performance when a limited number of labeled data instances are made available. We also showed that it is important to examine the underlying distribution of the data space before applying SSL techniques to ensure semi-supervised learning assumptions are not violated by the data.

  1. Active learning for semi-supervised clustering based on locally linear propagation reconstruction.

    Science.gov (United States)

    Chang, Chin-Chun; Lin, Po-Yi

    2015-03-01

    The success of semi-supervised clustering relies on the effectiveness of side information. To get effective side information, a new active learner learning pairwise constraints known as must-link and cannot-link constraints is proposed in this paper. Three novel techniques are developed for learning effective pairwise constraints. The first technique is used to identify samples less important to cluster structures. This technique makes use of a kernel version of locally linear embedding for manifold learning. Samples neither important to locally linear propagation reconstructions of other samples nor on flat patches in the learned manifold are regarded as unimportant samples. The second is a novel criterion for query selection. This criterion considers not only the importance of a sample to expanding the space coverage of the learned samples but also the expected number of queries needed to learn the sample. To facilitate semi-supervised clustering, the third technique yields inferred must-links for passing information about flat patches in the learned manifold to semi-supervised clustering algorithms. Experimental results have shown that the learned pairwise constraints can capture the underlying cluster structures and proven the feasibility of the proposed approach. Copyright © 2014 Elsevier Ltd. All rights reserved.

  2. Can Semi-Supervised Learning Explain Incorrect Beliefs about Categories?

    Science.gov (United States)

    Kalish, Charles W.; Rogers, Timothy T.; Lang, Jonathan; Zhu, Xiaojin

    2011-01-01

    Three experiments with 88 college-aged participants explored how unlabeled experiences--learning episodes in which people encounter objects without information about their category membership--influence beliefs about category structure. Participants performed a simple one-dimensional categorization task in a brief supervised learning phase, then…

  3. Semi-supervised eigenvectors for large-scale locally-biased learning

    DEFF Research Database (Denmark)

    Hansen, Toke Jansen; Mahoney, Michael W.

    2014-01-01

    improved scaling properties. We provide several empirical examples demonstrating how these semi-supervised eigenvectors can be used to perform locally-biased learning; and we discuss the relationship between our results and recent machine learning algorithms that use global eigenvectors of the graph......In many applications, one has side information, e.g., labels that are provided in a semi-supervised manner, about a specific target region of a large data set, and one wants to perform machine learning and data analysis tasks nearby that prespecified target region. For example, one might......-based machine learning and data analysis tools. At root, the reason is that eigenvectors are inherently global quantities, thus limiting the applicability of eigenvector-based methods in situations where one is interested in very local properties of the data. In this paper, we address this issue by providing...

  4. Robust semi-supervised learning : projections, limits & constraints

    NARCIS (Netherlands)

    Krijthe, J.H.

    2018-01-01

    In many domains of science and society, the amount of data being gathered is increasing rapidly. To estimate input-output relationships that are often of interest, supervised learning techniques rely on a specific type of data: labeled examples for which we know both the input and an outcome. The

  5. Optimizing area under the ROC curve using semi-supervised learning.

    Science.gov (United States)

    Wang, Shijun; Li, Diana; Petrick, Nicholas; Sahiner, Berkman; Linguraru, Marius George; Summers, Ronald M

    2015-01-01

    Receiver operating characteristic (ROC) analysis is a standard methodology to evaluate the performance of a binary classification system. The area under the ROC curve (AUC) is a performance metric that summarizes how well a classifier separates two classes. Traditional AUC optimization techniques are supervised learning methods that utilize only labeled data (i.e., the true class is known for all data) to train the classifiers. In this work, inspired by semi-supervised and transductive learning, we propose two new AUC optimization algorithms hereby referred to as semi-supervised learning receiver operating characteristic (SSLROC) algorithms, which utilize unlabeled test samples in classifier training to maximize AUC. Unlabeled samples are incorporated into the AUC optimization process, and their ranking relationships to labeled positive and negative training samples are considered as optimization constraints. The introduced test samples will cause the learned decision boundary in a multidimensional feature space to adapt not only to the distribution of labeled training data, but also to the distribution of unlabeled test data. We formulate the semi-supervised AUC optimization problem as a semi-definite programming problem based on the margin maximization theory. The proposed methods SSLROC1 (1-norm) and SSLROC2 (2-norm) were evaluated using 34 (determined by power analysis) randomly selected datasets from the University of California, Irvine machine learning repository. Wilcoxon signed rank tests showed that the proposed methods achieved significant improvement compared with state-of-the-art methods. The proposed methods were also applied to a CT colonography dataset for colonic polyp classification and showed promising results.

  6. SSEL-ADE: A semi-supervised ensemble learning framework for extracting adverse drug events from social media.

    Science.gov (United States)

    Liu, Jing; Zhao, Songzheng; Wang, Gang

    2018-01-01

    With the development of Web 2.0 technology, social media websites have become lucrative but under-explored data sources for extracting adverse drug events (ADEs), which is a serious health problem. Besides ADE, other semantic relation types (e.g., drug indication and beneficial effect) could hold between the drug and adverse event mentions, making ADE relation extraction - distinguishing ADE relationship from other relation types - necessary. However, conducting ADE relation extraction in social media environment is not a trivial task because of the expertise-dependent, time-consuming and costly annotation process, and the feature space's high-dimensionality attributed to intrinsic characteristics of social media data. This study aims to develop a framework for ADE relation extraction using patient-generated content in social media with better performance than that delivered by previous efforts. To achieve the objective, a general semi-supervised ensemble learning framework, SSEL-ADE, was developed. The framework exploited various lexical, semantic, and syntactic features, and integrated ensemble learning and semi-supervised learning. A series of experiments were conducted to verify the effectiveness of the proposed framework. Empirical results demonstrate the effectiveness of each component of SSEL-ADE and reveal that our proposed framework outperforms most of existing ADE relation extraction methods The SSEL-ADE can facilitate enhanced ADE relation extraction performance, thereby providing more reliable support for pharmacovigilance. Moreover, the proposed semi-supervised ensemble methods have the potential of being applied to effectively deal with other social media-based problems. Copyright © 2017 Elsevier B.V. All rights reserved.

  7. Coupled dimensionality reduction and classification for supervised and semi-supervised multilabel learning.

    Science.gov (United States)

    Gönen, Mehmet

    2014-03-01

    Coupled training of dimensionality reduction and classification is proposed previously to improve the prediction performance for single-label problems. Following this line of research, in this paper, we first introduce a novel Bayesian method that combines linear dimensionality reduction with linear binary classification for supervised multilabel learning and present a deterministic variational approximation algorithm to learn the proposed probabilistic model. We then extend the proposed method to find intrinsic dimensionality of the projected subspace using automatic relevance determination and to handle semi-supervised learning using a low-density assumption. We perform supervised learning experiments on four benchmark multilabel learning data sets by comparing our method with baseline linear dimensionality reduction algorithms. These experiments show that the proposed approach achieves good performance values in terms of hamming loss, average AUC, macro F 1 , and micro F 1 on held-out test data. The low-dimensional embeddings obtained by our method are also very useful for exploratory data analysis. We also show the effectiveness of our approach in finding intrinsic subspace dimensionality and semi-supervised learning tasks.

  8. Information-theoretic semi-supervised metric learning via entropy regularization.

    Science.gov (United States)

    Niu, Gang; Dai, Bo; Yamada, Makoto; Sugiyama, Masashi

    2014-08-01

    We propose a general information-theoretic approach to semi-supervised metric learning called SERAPH (SEmi-supervised metRic leArning Paradigm with Hypersparsity) that does not rely on the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize its entropy on labeled data and minimize its entropy on unlabeled data following entropy regularization. For metric learning, entropy regularization improves manifold regularization by considering the dissimilarity information of unlabeled data in the unsupervised part, and hence it allows the supervised and unsupervised parts to be integrated in a natural and meaningful way. Moreover, we regularize SERAPH by trace-norm regularization to encourage low-dimensional projections associated with the distance metric. The nonconvex optimization problem of SERAPH could be solved efficiently and stably by either a gradient projection algorithm or an EM-like iterative algorithm whose M-step is convex. Experiments demonstrate that SERAPH compares favorably with many well-known metric learning methods, and the learned Mahalanobis distance possesses high discriminability even under noisy environments.

  9. Visual texture perception via graph-based semi-supervised learning

    Science.gov (United States)

    Zhang, Qin; Dong, Junyu; Zhong, Guoqiang

    2018-04-01

    Perceptual features, for example direction, contrast and repetitiveness, are important visual factors for human to perceive a texture. However, it needs to perform psychophysical experiment to quantify these perceptual features' scale, which requires a large amount of human labor and time. This paper focuses on the task of obtaining perceptual features' scale of textures by small number of textures with perceptual scales through a rating psychophysical experiment (what we call labeled textures) and a mass of unlabeled textures. This is the scenario that the semi-supervised learning is naturally suitable for. This is meaningful for texture perception research, and really helpful for the perceptual texture database expansion. A graph-based semi-supervised learning method called random multi-graphs, RMG for short, is proposed to deal with this task. We evaluate different kinds of features including LBP, Gabor, and a kind of unsupervised deep features extracted by a PCA-based deep network. The experimental results show that our method can achieve satisfactory effects no matter what kind of texture features are used.

  10. WLAN Fingerprint Indoor Positioning Strategy Based on Implicit Crowdsourcing and Semi-Supervised Learning

    Directory of Open Access Journals (Sweden)

    Chunjing Song

    2017-11-01

    Full Text Available Wireless local area network (WLAN fingerprint positioning is an indoor localization technique with high accuracy and low hardware requirements. However, collecting received signal strength (RSS samples for the fingerprint database is time-consuming and labor-intensive, hindering the use of this technique. The popular crowdsourcing sampling technique has been introduced to reduce the workload of sample collection, but has two challenges: one is the heterogeneity of devices, which can significantly affect the positioning accuracy; the other is the requirement of users’ intervention in traditional crowdsourcing, which reduces the practicality of the system. In response to these challenges, we have proposed a new WLAN indoor positioning strategy, which incorporates a new preprocessing method for RSS samples, the implicit crowdsourcing sampling technique, and a semi-supervised learning algorithm. First, implicit crowdsourcing does not require users’ intervention. The acquisition program silently collects unlabeled samples, the RSS samples, without information about the position. Secondly, to cope with the heterogeneity of devices, the preprocessing method maps all the RSS values of samples to a uniform range and discretizes them. Finally, by using a large number of unlabeled samples with some labeled samples, Co-Forest, the introduced semi-supervised learning algorithm, creates and repeatedly refines a random forest ensemble classifier that performs well for location estimation. The results of experiments conducted in a real indoor environment show that the proposed strategy reduces the demand for large quantities of labeled samples and achieves good positioning accuracy.

  11. Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking.

    Science.gov (United States)

    Hu, Weiming; Gao, Jin; Xing, Junliang; Zhang, Chao; Maybank, Stephen

    2017-01-01

    An appearance model adaptable to changes in object appearance is critical in visual object tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original image structure. We design two graphs for characterizing the intrinsic local geometrical structure of the tensor samples of the object and the background. Graph embedding is used to reduce the dimensions of the tensors while preserving the structure of the graphs. Then, a discriminant embedding space is constructed. We prove two propositions for finding the transformation matrices which are used to map the original tensor samples to the tensor-based graph embedding space. In order to encode more discriminant information in the embedding space, we propose a transfer-learning- based semi-supervised strategy to iteratively adjust the embedding space into which discriminative information obtained from earlier times is transferred. We apply the proposed semi-supervised tensor-based graph embedding learning algorithm to visual tracking. The new tracking algorithm captures an object's appearance characteristics during tracking and uses a particle filter to estimate the optimal object state. Experimental results on the CVPR 2013 benchmark dataset demonstrate the effectiveness of the proposed tracking algorithm.

  12. An empirical study of ensemble-based semi-supervised learning approaches for imbalanced splice site datasets.

    Science.gov (United States)

    Stanescu, Ana; Caragea, Doina

    2015-01-01

    Recent biochemical advances have led to inexpensive, time-efficient production of massive volumes of raw genomic data. Traditional machine learning approaches to genome annotation typically rely on large amounts of labeled data. The process of labeling data can be expensive, as it requires domain knowledge and expert involvement. Semi-supervised learning approaches that can make use of unlabeled data, in addition to small amounts of labeled data, can help reduce the costs associated with labeling. In this context, we focus on the problem of predicting splice sites in a genome using semi-supervised learning approaches. This is a challenging problem, due to the highly imbalanced distribution of the data, i.e., small number of splice sites as compared to the number of non-splice sites. To address this challenge, we propose to use ensembles of semi-supervised classifiers, specifically self-training and co-training classifiers. Our experiments on five highly imbalanced splice site datasets, with positive to negative ratios of 1-to-99, showed that the ensemble-based semi-supervised approaches represent a good choice, even when the amount of labeled data consists of less than 1% of all training data. In particular, we found that ensembles of co-training and self-training classifiers that dynamically balance the set of labeled instances during the semi-supervised iterations show improvements over the corresponding supervised ensemble baselines. In the presence of limited amounts of labeled data, ensemble-based semi-supervised approaches can successfully leverage the unlabeled data to enhance supervised ensembles learned from highly imbalanced data distributions. Given that such distributions are common for many biological sequence classification problems, our work can be seen as a stepping stone towards more sophisticated ensemble-based approaches to biological sequence annotation in a semi-supervised framework.

  13. A Novel Semi-Supervised Electronic Nose Learning Technique: M-Training

    Directory of Open Access Journals (Sweden)

    Pengfei Jia

    2016-03-01

    Full Text Available When an electronic nose (E-nose is used to distinguish different kinds of gases, the label information of the target gas could be lost due to some fault of the operators or some other reason, although this is not expected. Another fact is that the cost of getting the labeled samples is usually higher than for unlabeled ones. In most cases, the classification accuracy of an E-nose trained using labeled samples is higher than that of the E-nose trained by unlabeled ones, so gases without label information should not be used to train an E-nose, however, this wastes resources and can even delay the progress of research. In this work a novel multi-class semi-supervised learning technique called M-training is proposed to train E-noses with both labeled and unlabeled samples. We employ M-training to train the E-nose which is used to distinguish three indoor pollutant gases (benzene, toluene and formaldehyde. Data processing results prove that the classification accuracy of E-nose trained by semi-supervised techniques (tri-training and M-training is higher than that of an E-nose trained only with labeled samples, and the performance of M-training is better than that of tri-training because more base classifiers can be employed by M-training.

  14. Nonlinear Semi-Supervised Metric Learning Via Multiple Kernels and Local Topology.

    Science.gov (United States)

    Li, Xin; Bai, Yanqin; Peng, Yaxin; Du, Shaoyi; Ying, Shihui

    2018-03-01

    Changing the metric on the data may change the data distribution, hence a good distance metric can promote the performance of learning algorithm. In this paper, we address the semi-supervised distance metric learning (ML) problem to obtain the best nonlinear metric for the data. First, we describe the nonlinear metric by the multiple kernel representation. By this approach, we project the data into a high dimensional space, where the data can be well represented by linear ML. Then, we reformulate the linear ML by a minimization problem on the positive definite matrix group. Finally, we develop a two-step algorithm for solving this model and design an intrinsic steepest descent algorithm to learn the positive definite metric matrix. Experimental results validate that our proposed method is effective and outperforms several state-of-the-art ML methods.

  15. The helpfulness of category labels in semi-supervised learning depends on category structure.

    Science.gov (United States)

    Vong, Wai Keen; Navarro, Daniel J; Perfors, Amy

    2016-02-01

    The study of semi-supervised category learning has generally focused on how additional unlabeled information with given labeled information might benefit category learning. The literature is also somewhat contradictory, sometimes appearing to show a benefit to unlabeled information and sometimes not. In this paper, we frame the problem differently, focusing on when labels might be helpful to a learner who has access to lots of unlabeled information. Using an unconstrained free-sorting categorization experiment, we show that labels are useful to participants only when the category structure is ambiguous and that people's responses are driven by the specific set of labels they see. We present an extension of Anderson's Rational Model of Categorization that captures this effect.

  16. A semi-supervised learning framework for biomedical event extraction based on hidden topics.

    Science.gov (United States)

    Zhou, Deyu; Zhong, Dayou

    2015-05-01

    Scientists have devoted decades of efforts to understanding the interaction between proteins or RNA production. The information might empower the current knowledge on drug reactions or the development of certain diseases. Nevertheless, due to the lack of explicit structure, literature in life science, one of the most important sources of this information, prevents computer-based systems from accessing. Therefore, biomedical event extraction, automatically acquiring knowledge of molecular events in research articles, has attracted community-wide efforts recently. Most approaches are based on statistical models, requiring large-scale annotated corpora to precisely estimate models' parameters. However, it is usually difficult to obtain in practice. Therefore, employing un-annotated data based on semi-supervised learning for biomedical event extraction is a feasible solution and attracts more interests. In this paper, a semi-supervised learning framework based on hidden topics for biomedical event extraction is presented. In this framework, sentences in the un-annotated corpus are elaborately and automatically assigned with event annotations based on their distances to these sentences in the annotated corpus. More specifically, not only the structures of the sentences, but also the hidden topics embedded in the sentences are used for describing the distance. The sentences and newly assigned event annotations, together with the annotated corpus, are employed for training. Experiments were conducted on the multi-level event extraction corpus, a golden standard corpus. Experimental results show that more than 2.2% improvement on F-score on biomedical event extraction is achieved by the proposed framework when compared to the state-of-the-art approach. The results suggest that by incorporating un-annotated data, the proposed framework indeed improves the performance of the state-of-the-art event extraction system and the similarity between sentences might be precisely

  17. Arrangement and Applying of Movement Patterns in the Cerebellum Based on Semi-supervised Learning.

    Science.gov (United States)

    Solouki, Saeed; Pooyan, Mohammad

    2016-06-01

    Biological control systems have long been studied as a possible inspiration for the construction of robotic controllers. The cerebellum is known to be involved in the production and learning of smooth, coordinated movements. Therefore, highly regular structure of the cerebellum has been in the core of attention in theoretical and computational modeling. However, most of these models reflect some special features of the cerebellum without regarding the whole motor command computational process. In this paper, we try to make a logical relation between the most significant models of the cerebellum and introduce a new learning strategy to arrange the movement patterns: cerebellar modular arrangement and applying of movement patterns based on semi-supervised learning (CMAPS). We assume here the cerebellum like a big archive of patterns that has an efficient organization to classify and recall them. The main idea is to achieve an optimal use of memory locations by more than just a supervised learning and classification algorithm. Surely, more experimental and physiological researches are needed to confirm our hypothesis.

  18. Computerized breast cancer analysis system using three stage semi-supervised learning method.

    Science.gov (United States)

    Sun, Wenqing; Tseng, Tzu-Liang Bill; Zhang, Jianying; Qian, Wei

    2016-10-01

    A large number of labeled medical image data is usually a requirement to train a well-performed computer-aided detection (CAD) system. But the process of data labeling is time consuming, and potential ethical and logistical problems may also present complications. As a result, incorporating unlabeled data into CAD system can be a feasible way to combat these obstacles. In this study we developed a three stage semi-supervised learning (SSL) scheme that combines a small amount of labeled data and larger amount of unlabeled data. The scheme was modified on our existing CAD system using the following three stages: data weighing, feature selection, and newly proposed dividing co-training data labeling algorithm. Global density asymmetry features were incorporated to the feature pool to reduce the false positive rate. Area under the curve (AUC) and accuracy were computed using 10 fold cross validation method to evaluate the performance of our CAD system. The image dataset includes mammograms from 400 women who underwent routine screening examinations, and each pair contains either two cranio-caudal (CC) or two mediolateral-oblique (MLO) view mammograms from the right and the left breasts. From these mammograms 512 regions were extracted and used in this study, and among them 90 regions were treated as labeled while the rest were treated as unlabeled. Using our proposed scheme, the highest AUC observed in our research was 0.841, which included the 90 labeled data and all the unlabeled data. It was 7.4% higher than using labeled data only. With the increasing amount of labeled data, AUC difference between using mixed data and using labeled data only reached its peak when the amount of labeled data was around 60. This study demonstrated that our proposed three stage semi-supervised learning can improve the CAD performance by incorporating unlabeled data. Using unlabeled data is promising in computerized cancer research and may have a significant impact for future CAD system

  19. Automated Detection of Microaneurysms Using Scale-Adapted Blob Analysis and Semi-Supervised Learning

    Energy Technology Data Exchange (ETDEWEB)

    Adal, Kedir M. [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Sidebe, Desire [Univ. of Burgundy, Dijon (France); Ali, Sharib [Univ. of Burgundy, Dijon (France); Chaum, Edward [Univ. of Tennessee, Knoxville, TN (United States); Karnowski, Thomas Paul [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Meriaudeau, Fabrice [Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

    2014-01-07

    Despite several attempts, automated detection of microaneurysm (MA) from digital fundus images still remains to be an open issue. This is due to the subtle nature of MAs against the surrounding tissues. In this paper, the microaneurysm detection problem is modeled as finding interest regions or blobs from an image and an automatic local-scale selection technique is presented. Several scale-adapted region descriptors are then introduced to characterize these blob regions. A semi-supervised based learning approach, which requires few manually annotated learning examples, is also proposed to train a classifier to detect true MAs. The developed system is built using only few manually labeled and a large number of unlabeled retinal color fundus images. The performance of the overall system is evaluated on Retinopathy Online Challenge (ROC) competition database. A competition performance measure (CPM) of 0.364 shows the competitiveness of the proposed system against state-of-the art techniques as well as the applicability of the proposed features to analyze fundus images.

  20. Application of semi-supervised deep learning to lung sound analysis.

    Science.gov (United States)

    Chamberlain, Daniel; Kodgule, Rahul; Ganelin, Daniela; Miglani, Vivek; Fletcher, Richard Ribon

    2016-08-01

    The analysis of lung sounds, collected through auscultation, is a fundamental component of pulmonary disease diagnostics for primary care and general patient monitoring for telemedicine. Despite advances in computation and algorithms, the goal of automated lung sound identification and classification has remained elusive. Over the past 40 years, published work in this field has demonstrated only limited success in identifying lung sounds, with most published studies using only a small numbers of patients (typically Ndeep learning algorithm for automatically classify lung sounds from a relatively large number of patients (N=284). Focusing on the two most common lung sounds, wheeze and crackle, we present results from 11,627 sound files recorded from 11 different auscultation locations on these 284 patients with pulmonary disease. 890 of these sound files were labeled to evaluate the model, which is significantly larger than previously published studies. Data was collected with a custom mobile phone application and a low-cost (US$30) electronic stethoscope. On this data set, our algorithm achieves ROC curves with AUCs of 0.86 for wheeze and 0.74 for crackle. Most importantly, this study demonstrates how semi-supervised deep learning can be used with larger data sets without requiring extensive labeling of data.

  1. Semi-supervised Learning Predicts Approximately One Third of the Alternative Splicing Isoforms as Functional Proteins

    Directory of Open Access Journals (Sweden)

    Yanqi Hao

    2015-07-01

    Full Text Available Alternative splicing acts on transcripts from almost all human multi-exon genes. Notwithstanding its ubiquity, fundamental ramifications of splicing on protein expression remain unresolved. The number and identity of spliced transcripts that form stably folded proteins remain the sources of considerable debate, due largely to low coverage of experimental methods and the resulting absence of negative data. We circumvent this issue by developing a semi-supervised learning algorithm, positive unlabeled learning for splicing elucidation (PULSE; http://www.kimlab.org/software/pulse, which uses 48 features spanning various categories. We validated its accuracy on sets of bona fide protein isoforms and directly on mass spectrometry (MS spectra for an overall AU-ROC of 0.85. We predict that around 32% of “exon skipping” alternative splicing events produce stable proteins, suggesting that the process engenders a significant number of previously uncharacterized proteins. We also provide insights into the distribution of positive isoforms in various functional classes and into the structural effects of alternative splicing.

  2. Automated detection of microaneurysms using scale-adapted blob analysis and semi-supervised learning.

    Science.gov (United States)

    Adal, Kedir M; Sidibé, Désiré; Ali, Sharib; Chaum, Edward; Karnowski, Thomas P; Mériaudeau, Fabrice

    2014-04-01

    Despite several attempts, automated detection of microaneurysm (MA) from digital fundus images still remains to be an open issue. This is due to the subtle nature of MAs against the surrounding tissues. In this paper, the microaneurysm detection problem is modeled as finding interest regions or blobs from an image and an automatic local-scale selection technique is presented. Several scale-adapted region descriptors are introduced to characterize these blob regions. A semi-supervised based learning approach, which requires few manually annotated learning examples, is also proposed to train a classifier which can detect true MAs. The developed system is built using only few manually labeled and a large number of unlabeled retinal color fundus images. The performance of the overall system is evaluated on Retinopathy Online Challenge (ROC) competition database. A competition performance measure (CPM) of 0.364 shows the competitiveness of the proposed system against state-of-the art techniques as well as the applicability of the proposed features to analyze fundus images. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

  3. An Efficient Semi-supervised Learning Approach to Predict SH2 Domain Mediated Interactions.

    Science.gov (United States)

    Kundu, Kousik; Backofen, Rolf

    2017-01-01

    Src homology 2 (SH2) domain is an important subclass of modular protein domains that plays an indispensable role in several biological processes in eukaryotes. SH2 domains specifically bind to the phosphotyrosine residue of their binding peptides to facilitate various molecular functions. For determining the subtle binding specificities of SH2 domains, it is very important to understand the intriguing mechanisms by which these domains recognize their target peptides in a complex cellular environment. There are several attempts have been made to predict SH2-peptide interactions using high-throughput data. However, these high-throughput data are often affected by a low signal to noise ratio. Furthermore, the prediction methods have several additional shortcomings, such as linearity problem, high computational complexity, etc. Thus, computational identification of SH2-peptide interactions using high-throughput data remains challenging. Here, we propose a machine learning approach based on an efficient semi-supervised learning technique for the prediction of 51 SH2 domain mediated interactions in the human proteome. In our study, we have successfully employed several strategies to tackle the major problems in computational identification of SH2-peptide interactions.

  4. Porosity estimation by semi-supervised learning with sparsely available labeled samples

    Science.gov (United States)

    Lima, Luiz Alberto; Görnitz, Nico; Varella, Luiz Eduardo; Vellasco, Marley; Müller, Klaus-Robert; Nakajima, Shinichi

    2017-09-01

    This paper addresses the porosity estimation problem from seismic impedance volumes and porosity samples located in a small group of exploratory wells. Regression methods, trained on the impedance as inputs and the porosity as output labels, generally suffer from extremely expensive (and hence sparsely available) porosity samples. To optimally make use of the valuable porosity data, a semi-supervised machine learning method was proposed, Transductive Conditional Random Field Regression (TCRFR), showing good performance (Görnitz et al., 2017). TCRFR, however, still requires more labeled data than those usually available, which creates a gap when applying the method to the porosity estimation problem in realistic situations. In this paper, we aim to fill this gap by introducing two graph-based preprocessing techniques, which adapt the original TCRFR for extremely weakly supervised scenarios. Our new method outperforms the previous automatic estimation methods on synthetic data and provides a comparable result to the manual labored, time-consuming geostatistics approach on real data, proving its potential as a practical industrial tool.

  5. Semi-supervised learning based probabilistic latent semantic analysis for automatic image annotation

    Institute of Scientific and Technical Information of China (English)

    Tian Dongping

    2017-01-01

    In recent years, multimedia annotation problem has been attracting significant research attention in multimedia and computer vision areas, especially for automatic image annotation, whose purpose is to provide an efficient and effective searching environment for users to query their images more easily.In this paper, a semi-supervised learning based probabilistic latent semantic analysis ( PL-SA) model for automatic image annotation is presenred.Since it' s often hard to obtain or create la-beled images in large quantities while unlabeled ones are easier to collect, a transductive support vector machine ( TSVM) is exploited to enhance the quality of the training image data.Then, differ-ent image features with different magnitudes will result in different performance for automatic image annotation.To this end, a Gaussian normalization method is utilized to normalize different features extracted from effective image regions segmented by the normalized cuts algorithm so as to reserve the intrinsic content of images as complete as possible.Finally, a PLSA model with asymmetric mo-dalities is constructed based on the expectation maximization( EM) algorithm to predict a candidate set of annotations with confidence scores.Extensive experiments on the general-purpose Corel5k dataset demonstrate that the proposed model can significantly improve performance of traditional PL-SA for the task of automatic image annotation.

  6. Accurate in silico identification of protein succinylation sites using an iterative semi-supervised learning technique.

    Science.gov (United States)

    Zhao, Xiaowei; Ning, Qiao; Chai, Haiting; Ma, Zhiqiang

    2015-06-07

    As a widespread type of protein post-translational modifications (PTMs), succinylation plays an important role in regulating protein conformation, function and physicochemical properties. Compared with the labor-intensive and time-consuming experimental approaches, computational predictions of succinylation sites are much desirable due to their convenient and fast speed. Currently, numerous computational models have been developed to identify PTMs sites through various types of two-class machine learning algorithms. These methods require both positive and negative samples for training. However, designation of the negative samples of PTMs was difficult and if it is not properly done can affect the performance of computational models dramatically. So that in this work, we implemented the first application of positive samples only learning (PSoL) algorithm to succinylation sites prediction problem, which was a special class of semi-supervised machine learning that used positive samples and unlabeled samples to train the model. Meanwhile, we proposed a novel succinylation sites computational predictor called SucPred (succinylation site predictor) by using multiple feature encoding schemes. Promising results were obtained by the SucPred predictor with an accuracy of 88.65% using 5-fold cross validation on the training dataset and an accuracy of 84.40% on the independent testing dataset, which demonstrated that the positive samples only learning algorithm presented here was particularly useful for identification of protein succinylation sites. Besides, the positive samples only learning algorithm can be applied to build predictors for other types of PTMs sites with ease. A web server for predicting succinylation sites was developed and was freely accessible at http://59.73.198.144:8088/SucPred/. Copyright © 2015 Elsevier Ltd. All rights reserved.

  7. Restricted Boltzmann machines based oversampling and semi-supervised learning for false positive reduction in breast CAD.

    Science.gov (United States)

    Cao, Peng; Liu, Xiaoli; Bao, Hang; Yang, Jinzhu; Zhao, Dazhe

    2015-01-01

    The false-positive reduction (FPR) is a crucial step in the computer aided detection system for the breast. The issues of imbalanced data distribution and the limitation of labeled samples complicate the classification procedure. To overcome these challenges, we propose oversampling and semi-supervised learning methods based on the restricted Boltzmann machines (RBMs) to solve the classification of imbalanced data with a few labeled samples. To evaluate the proposed method, we conducted a comprehensive performance study and compared its results with the commonly used techniques. Experiments on benchmark dataset of DDSM demonstrate the effectiveness of the RBMs based oversampling and semi-supervised learning method in terms of geometric mean (G-mean) for false positive reduction in Breast CAD.

  8. 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

  9. Graph-Based Semi-Supervised Learning for Indoor Localization Using Crowdsourced Data

    Directory of Open Access Journals (Sweden)

    Liye Zhang

    2017-04-01

    Full Text Available Indoor positioning based on the received signal strength (RSS of the WiFi signal has become the most popular solution for indoor localization. In order to realize the rapid deployment of indoor localization systems, solutions based on crowdsourcing have been proposed. However, compared to conventional methods, lots of different devices are used in crowdsourcing system and less RSS values are collected by each device. Therefore, the crowdsourced RSS values are more erroneous and can result in significant localization errors. In order to eliminate the signal strength variations across diverse devices, the Linear Regression (LR algorithm is proposed to solve the device diversity problem in crowdsourcing system. After obtaining the uniform RSS values, a graph-based semi-supervised learning (G-SSL method is used to exploit the correlation between the RSS values at nearby locations to estimate an optimal RSS value at each location. As a result, the negative effect of the erroneous measurements could be mitigated. Since the AP locations need to be known in G-SSL algorithm, the Compressed Sensing (CS method is applied to precisely estimate the location of the APs. Based on the location of the APs and a simple signal propagation model, the RSS difference between different locations is calculated and used as an additional constraint to improve the performance of G-SSL. Furthermore, to exploit the sparsity of the weights used in the G-SSL, we use the CS method to reconstruct these weights more accurately and make a further improvement on the performance of the G-SSL. Experimental results show improved results in terms of the smoothness of the radio map and the localization accuracy.

  10. Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods.

    Science.gov (United States)

    Honnorat, Nicolas; Dong, Aoyan; Meisenzahl-Lechner, Eva; Koutsouleris, Nikolaos; Davatzikos, Christos

    2017-12-20

    Schizophrenia is associated with heterogeneous clinical symptoms and neuroanatomical alterations. In this work, we aim to disentangle the patterns of neuroanatomical alterations underlying a heterogeneous population of patients using a semi-supervised clustering method. We apply this strategy to a cohort of patients with schizophrenia of varying extends of disease duration, and we describe the neuroanatomical, demographic and clinical characteristics of the subtypes discovered. We analyze the neuroanatomical heterogeneity of 157 patients diagnosed with Schizophrenia, relative to a control population of 169 subjects, using a machine learning method called CHIMERA. CHIMERA clusters the differences between patients and a demographically-matched population of healthy subjects, rather than clustering patients themselves, thereby specifically assessing disease-related neuroanatomical alterations. Voxel-Based Morphometry was conducted to visualize the neuroanatomical patterns associated with each group. The clinical presentation and the demographics of the groups were then investigated. Three subgroups were identified. The first two differed substantially, in that one involved predominantly temporal-thalamic-peri-Sylvian regions, whereas the other involved predominantly frontal regions and the thalamus. Both subtypes included primarily male patients. The third pattern was a mix of these two and presented milder neuroanatomic alterations and comprised a comparable number of men and women. VBM and statistical analyses suggest that these groups could correspond to different neuroanatomical dimensions of schizophrenia. Our analysis suggests that schizophrenia presents distinct neuroanatomical variants. This variability points to the need for a dimensional neuroanatomical approach using data-driven, mathematically principled multivariate pattern analysis methods, and should be taken into account in clinical studies. Copyright © 2017 Elsevier B.V. All rights reserved.

  11. Semi-supervised learning of hyperspectral image segmentation applied to vine tomatoes and table grapes

    Directory of Open Access Journals (Sweden)

    Jeroen van Roy

    2018-03-01

    Full Text Available Nowadays, quality inspection of fruit and vegetables is typically accomplished through visual inspection. Automation of this inspection is desirable to make it more objective. For this, hyperspectral imaging has been identified as a promising technique. When the field of view includes multiple objects, hypercubes should be segmented to assign individual pixels to different objects. Unsupervised and supervised methods have been proposed. While the latter are labour intensive as they require masking of the training images, the former are too computationally intensive for in-line use and may provide different results for different hypercubes. Therefore, a semi-supervised method is proposed to train a computationally efficient segmentation algorithm with minimal human interaction. As a first step, an unsupervised classification model is used to cluster spectra in similar groups. In the second step, a pixel selection algorithm applied to the output of the unsupervised classification is used to build a supervised model which is fast enough for in-line use. To evaluate this approach, it is applied to hypercubes of vine tomatoes and table grapes. After first derivative spectral preprocessing to remove intensity variation due to curvature and gloss effects, the unsupervised models segmented 86.11% of the vine tomato images correctly. Considering overall accuracy, sensitivity, specificity and time needed to segment one hypercube, partial least squares discriminant analysis (PLS-DA was found to be the best choice for in-line use, when using one training image. By adding a second image, the segmentation results improved considerably, yielding an overall accuracy of 96.95% for segmentation of vine tomatoes and 98.52% for segmentation of table grapes, demonstrating the added value of the learning phase in the algorithm.

  12. Alzheimer's Disease Early Diagnosis Using Manifold-Based Semi-Supervised Learning.

    Science.gov (United States)

    Khajehnejad, Moein; Saatlou, Forough Habibollahi; Mohammadzade, Hoda

    2017-08-20

    Alzheimer's disease (AD) is currently ranked as the sixth leading cause of death in the United States and recent estimates indicate that the disorder may rank third, just behind heart disease and cancer, as a cause of death for older people. Clearly, predicting this disease in the early stages and preventing it from progressing is of great importance. The diagnosis of Alzheimer's disease (AD) requires a variety of medical tests, which leads to huge amounts of multivariate heterogeneous data. It can be difficult and exhausting to manually compare, visualize, and analyze this data due to the heterogeneous nature of medical tests; therefore, an efficient approach for accurate prediction of the condition of the brain through the classification of magnetic resonance imaging (MRI) images is greatly beneficial and yet very challenging. In this paper, a novel approach is proposed for the diagnosis of very early stages of AD through an efficient classification of brain MRI images, which uses label propagation in a manifold-based semi-supervised learning framework. We first apply voxel morphometry analysis to extract some of the most critical AD-related features of brain images from the original MRI volumes and also gray matter (GM) segmentation volumes. The features must capture the most discriminative properties that vary between a healthy and Alzheimer-affected brain. Next, we perform a principal component analysis (PCA)-based dimension reduction on the extracted features for faster yet sufficiently accurate analysis. To make the best use of the captured features, we present a hybrid manifold learning framework which embeds the feature vectors in a subspace. Next, using a small set of labeled training data, we apply a label propagation method in the created manifold space to predict the labels of the remaining images and classify them in the two groups of mild Alzheimer's and normal condition (MCI/NC). The accuracy of the classification using the proposed method is 93

  13. Optimistic semi-supervised least squares classification

    DEFF Research Database (Denmark)

    Krijthe, Jesse H.; Loog, Marco

    2017-01-01

    The goal of semi-supervised learning is to improve supervised classifiers by using additional unlabeled training examples. In this work we study a simple self-learning approach to semi-supervised learning applied to the least squares classifier. We show that a soft-label and a hard-label variant ...

  14. Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments

    Science.gov (United States)

    Han, Wenjing; Coutinho, Eduardo; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

    2016-01-01

    Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances. PMID:27627768

  15. Semi-Supervised Active Learning for Sound Classification in Hybrid Learning Environments.

    Science.gov (United States)

    Han, Wenjing; Coutinho, Eduardo; Ruan, Huabin; Li, Haifeng; Schuller, Björn; Yu, Xiaojie; Zhu, Xuan

    2016-01-01

    Coping with scarcity of labeled data is a common problem in sound classification tasks. Approaches for classifying sounds are commonly based on supervised learning algorithms, which require labeled data which is often scarce and leads to models that do not generalize well. In this paper, we make an efficient combination of confidence-based Active Learning and Self-Training with the aim of minimizing the need for human annotation for sound classification model training. The proposed method pre-processes the instances that are ready for labeling by calculating their classifier confidence scores, and then delivers the candidates with lower scores to human annotators, and those with high scores are automatically labeled by the machine. We demonstrate the feasibility and efficacy of this method in two practical scenarios: pool-based and stream-based processing. Extensive experimental results indicate that our approach requires significantly less labeled instances to reach the same performance in both scenarios compared to Passive Learning, Active Learning and Self-Training. A reduction of 52.2% in human labeled instances is achieved in both of the pool-based and stream-based scenarios on a sound classification task considering 16,930 sound instances.

  16. Semi-supervised learning for genomic prediction of novel traits with small reference populations: an application to residual feed intake in dairy cattle.

    Science.gov (United States)

    Yao, Chen; Zhu, Xiaojin; Weigel, Kent A

    2016-11-07

    Genomic prediction for novel traits, which can be costly and labor-intensive to measure, is often hampered by low accuracy due to the limited size of the reference population. As an option to improve prediction accuracy, we introduced a semi-supervised learning strategy known as the self-training model, and applied this method to genomic prediction of residual feed intake (RFI) in dairy cattle. We describe a self-training model that is wrapped around a support vector machine (SVM) algorithm, which enables it to use data from animals with and without measured phenotypes. Initially, a SVM model was trained using data from 792 animals with measured RFI phenotypes. Then, the resulting SVM was used to generate self-trained phenotypes for 3000 animals for which RFI measurements were not available. Finally, the SVM model was re-trained using data from up to 3792 animals, including those with measured and self-trained RFI phenotypes. Incorporation of additional animals with self-trained phenotypes enhanced the accuracy of genomic predictions compared to that of predictions that were derived from the subset of animals with measured phenotypes. The optimal ratio of animals with self-trained phenotypes to animals with measured phenotypes (2.5, 2.0, and 1.8) and the maximum increase achieved in prediction accuracy measured as the correlation between predicted and actual RFI phenotypes (5.9, 4.1, and 2.4%) decreased as the size of the initial training set (300, 400, and 500 animals with measured phenotypes) increased. The optimal number of animals with self-trained phenotypes may be smaller when prediction accuracy is measured as the mean squared error rather than the correlation between predicted and actual RFI phenotypes. Our results demonstrate that semi-supervised learning models that incorporate self-trained phenotypes can achieve genomic prediction accuracies that are comparable to those obtained with models using larger training sets that include only animals with

  17. A new semi-supervised learning model combined with Cox and SP-AFT models in cancer survival analysis.

    Science.gov (United States)

    Chai, Hua; Li, Zi-Na; Meng, De-Yu; Xia, Liang-Yong; Liang, Yong

    2017-10-12

    Gene selection is an attractive and important task in cancer survival analysis. Most existing supervised learning methods can only use the labeled biological data, while the censored data (weakly labeled data) far more than the labeled data are ignored in model building. Trying to utilize such information in the censored data, a semi-supervised learning framework (Cox-AFT model) combined with Cox proportional hazard (Cox) and accelerated failure time (AFT) model was used in cancer research, which has better performance than the single Cox or AFT model. This method, however, is easily affected by noise. To alleviate this problem, in this paper we combine the Cox-AFT model with self-paced learning (SPL) method to more effectively employ the information in the censored data in a self-learning way. SPL is a kind of reliable and stable learning mechanism, which is recently proposed for simulating the human learning process to help the AFT model automatically identify and include samples of high confidence into training, minimizing interference from high noise. Utilizing the SPL method produces two direct advantages: (1) The utilization of censored data is further promoted; (2) the noise delivered to the model is greatly decreased. The experimental results demonstrate the effectiveness of the proposed model compared to the traditional Cox-AFT model.

  18. Semi-supervised manifold learning with affinity regularization for Alzheimer's disease identification using positron emission tomography imaging.

    Science.gov (United States)

    Lu, Shen; Xia, Yong; Cai, Tom Weidong; Feng, David Dagan

    2015-01-01

    Dementia, Alzheimer's disease (AD) in particular is a global problem and big threat to the aging population. An image based computer-aided dementia diagnosis method is needed to providing doctors help during medical image examination. Many machine learning based dementia classification methods using medical imaging have been proposed and most of them achieve accurate results. However, most of these methods make use of supervised learning requiring fully labeled image dataset, which usually is not practical in real clinical environment. Using large amount of unlabeled images can improve the dementia classification performance. In this study we propose a new semi-supervised dementia classification method based on random manifold learning with affinity regularization. Three groups of spatial features are extracted from positron emission tomography (PET) images to construct an unsupervised random forest which is then used to regularize the manifold learning objective function. The proposed method, stat-of-the-art Laplacian support vector machine (LapSVM) and supervised SVM are applied to classify AD and normal controls (NC). The experiment results show that learning with unlabeled images indeed improves the classification performance. And our method outperforms LapSVM on the same dataset.

  19. Deep Learning @15 Petaflops/second: Semi-supervised pattern detection for 15 Terabytes of climate data

    Science.gov (United States)

    Collins, W. D.; Wehner, M. F.; Prabhat, M.; Kurth, T.; Satish, N.; Mitliagkas, I.; Zhang, J.; Racah, E.; Patwary, M.; Sundaram, N.; Dubey, P.

    2017-12-01

    Anthropogenically-forced climate changes in the number and character of extreme storms have the potential to significantly impact human and natural systems. Current high-performance computing enables multidecadal simulations with global climate models at resolutions of 25km or finer. Such high-resolution simulations are demonstrably superior in simulating extreme storms such as tropical cyclones than the coarser simulations available in the Coupled Model Intercomparison Project (CMIP5) and provide the capability to more credibly project future changes in extreme storm statistics and properties. The identification and tracking of storms in the voluminous model output is very challenging as it is impractical to manually identify storms due to the enormous size of the datasets, and therefore automated procedures are used. Traditionally, these procedures are based on a multi-variate set of physical conditions based on known properties of the class of storms in question. In recent years, we have successfully demonstrated that Deep Learning produces state of the art results for pattern detection in climate data. We have developed supervised and semi-supervised convolutional architectures for detecting and localizing tropical cyclones, extra-tropical cyclones and atmospheric rivers in simulation data. One of the primary challenges in the applicability of Deep Learning to climate data is in the expensive training phase. Typical networks may take days to converge on 10GB-sized datasets, while the climate science community has ready access to O(10 TB)-O(PB) sized datasets. In this work, we present the most scalable implementation of Deep Learning to date. We successfully scale a unified, semi-supervised convolutional architecture on all of the Cori Phase II supercomputer at NERSC. We use IntelCaffe, MKL and MLSL libraries. We have optimized single node MKL libraries to obtain 1-4 TF on single KNL nodes. We have developed a novel hybrid parameter update strategy to improve

  20. Cancer survival analysis using semi-supervised learning method based on Cox and AFT models with L1/2 regularization.

    Science.gov (United States)

    Liang, Yong; Chai, Hua; Liu, Xiao-Ying; Xu, Zong-Ben; Zhang, Hai; Leung, Kwong-Sak

    2016-03-01

    One of the most important objectives of the clinical cancer research is to diagnose cancer more accurately based on the patients' gene expression profiles. Both Cox proportional hazards model (Cox) and accelerated failure time model (AFT) have been widely adopted to the high risk and low risk classification or survival time prediction for the patients' clinical treatment. Nevertheless, two main dilemmas limit the accuracy of these prediction methods. One is that the small sample size and censored data remain a bottleneck for training robust and accurate Cox classification model. In addition to that, similar phenotype tumours and prognoses are actually completely different diseases at the genotype and molecular level. Thus, the utility of the AFT model for the survival time prediction is limited when such biological differences of the diseases have not been previously identified. To try to overcome these two main dilemmas, we proposed a novel semi-supervised learning method based on the Cox and AFT models to accurately predict the treatment risk and the survival time of the patients. Moreover, we adopted the efficient L1/2 regularization approach in the semi-supervised learning method to select the relevant genes, which are significantly associated with the disease. The results of the simulation experiments show that the semi-supervised learning model can significant improve the predictive performance of Cox and AFT models in survival analysis. The proposed procedures have been successfully applied to four real microarray gene expression and artificial evaluation datasets. The advantages of our proposed semi-supervised learning method include: 1) significantly increase the available training samples from censored data; 2) high capability for identifying the survival risk classes of patient in Cox model; 3) high predictive accuracy for patients' survival time in AFT model; 4) strong capability of the relevant biomarker selection. Consequently, our proposed semi-supervised

  1. Semi-Supervised Learning of Lift Optimization of Multi-Element Three-Segment Variable Camber Airfoil

    Science.gov (United States)

    Kaul, Upender K.; Nguyen, Nhan T.

    2017-01-01

    This chapter describes a new intelligent platform for learning optimal designs of morphing wings based on Variable Camber Continuous Trailing Edge Flaps (VCCTEF) in conjunction with a leading edge flap called the Variable Camber Krueger (VCK). The new platform consists of a Computational Fluid Dynamics (CFD) methodology coupled with a semi-supervised learning methodology. The CFD component of the intelligent platform comprises of a full Navier-Stokes solution capability (NASA OVERFLOW solver with Spalart-Allmaras turbulence model) that computes flow over a tri-element inboard NASA Generic Transport Model (GTM) wing section. Various VCCTEF/VCK settings and configurations were considered to explore optimal design for high-lift flight during take-off and landing. To determine globally optimal design of such a system, an extremely large set of CFD simulations is needed. This is not feasible to achieve in practice. To alleviate this problem, a recourse was taken to a semi-supervised learning (SSL) methodology, which is based on manifold regularization techniques. A reasonable space of CFD solutions was populated and then the SSL methodology was used to fit this manifold in its entirety, including the gaps in the manifold where there were no CFD solutions available. The SSL methodology in conjunction with an elastodynamic solver (FiDDLE) was demonstrated in an earlier study involving structural health monitoring. These CFD-SSL methodologies define the new intelligent platform that forms the basis for our search for optimal design of wings. Although the present platform can be used in various other design and operational problems in engineering, this chapter focuses on the high-lift study of the VCK-VCCTEF system. Top few candidate design configurations were identified by solving the CFD problem in a small subset of the design space. The SSL component was trained on the design space, and was then used in a predictive mode to populate a selected set of test points outside

  2. Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

    Energy Technology Data Exchange (ETDEWEB)

    Park, Sang Hyun [Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States); Gao, Yaozong, E-mail: yzgao@cs.unc.edu [Department of Computer Science, Department of Radiology, and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 (United States); Shi, Yinghuan, E-mail: syh@nju.edu.cn [State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023 (China); Shen, Dinggang, E-mail: dgshen@med.unc.edu [Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599 and Department of Brain and Cognitive Engineering, Korea University, Seoul 136-713 (Korea, Republic of)

    2014-11-01

    Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very time-consuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, location-adaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm. Results: The proposed interactive segmentation method was applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to

  3. Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

    International Nuclear Information System (INIS)

    Park, Sang Hyun; Gao, Yaozong; Shi, Yinghuan; Shen, Dinggang

    2014-01-01

    Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very time-consuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, location-adaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm. Results: The proposed interactive segmentation method was applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to

  4. Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection.

    Science.gov (United States)

    Park, Sang Hyun; Gao, Yaozong; Shi, Yinghuan; Shen, Dinggang

    2014-11-01

    Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very time-consuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, location-adaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm. The proposed interactive segmentation method was applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency

  5. Determining effects of non-synonymous SNPs on protein-protein interactions using supervised and semi-supervised learning.

    Directory of Open Access Journals (Sweden)

    Nan Zhao

    2014-05-01

    Full Text Available Single nucleotide polymorphisms (SNPs are among the most common types of genetic variation in complex genetic disorders. A growing number of studies link the functional role of SNPs with the networks and pathways mediated by the disease-associated genes. For example, many non-synonymous missense SNPs (nsSNPs have been found near or inside the protein-protein interaction (PPI interfaces. Determining whether such nsSNP will disrupt or preserve a PPI is a challenging task to address, both experimentally and computationally. Here, we present this task as three related classification problems, and develop a new computational method, called the SNP-IN tool (non-synonymous SNP INteraction effect predictor. Our method predicts the effects of nsSNPs on PPIs, given the interaction's structure. It leverages supervised and semi-supervised feature-based classifiers, including our new Random Forest self-learning protocol. The classifiers are trained based on a dataset of comprehensive mutagenesis studies for 151 PPI complexes, with experimentally determined binding affinities of the mutant and wild-type interactions. Three classification problems were considered: (1 a 2-class problem (strengthening/weakening PPI mutations, (2 another 2-class problem (mutations that disrupt/preserve a PPI, and (3 a 3-class classification (detrimental/neutral/beneficial mutation effects. In total, 11 different supervised and semi-supervised classifiers were trained and assessed resulting in a promising performance, with the weighted f-measure ranging from 0.87 for Problem 1 to 0.70 for the most challenging Problem 3. By integrating prediction results of the 2-class classifiers into the 3-class classifier, we further improved its performance for Problem 3. To demonstrate the utility of SNP-IN tool, it was applied to study the nsSNP-induced rewiring of two disease-centered networks. The accurate and balanced performance of SNP-IN tool makes it readily available to study the

  6. Determining Effects of Non-synonymous SNPs on Protein-Protein Interactions using Supervised and Semi-supervised Learning

    Science.gov (United States)

    Zhao, Nan; Han, Jing Ginger; Shyu, Chi-Ren; Korkin, Dmitry

    2014-01-01

    Single nucleotide polymorphisms (SNPs) are among the most common types of genetic variation in complex genetic disorders. A growing number of studies link the functional role of SNPs with the networks and pathways mediated by the disease-associated genes. For example, many non-synonymous missense SNPs (nsSNPs) have been found near or inside the protein-protein interaction (PPI) interfaces. Determining whether such nsSNP will disrupt or preserve a PPI is a challenging task to address, both experimentally and computationally. Here, we present this task as three related classification problems, and develop a new computational method, called the SNP-IN tool (non-synonymous SNP INteraction effect predictor). Our method predicts the effects of nsSNPs on PPIs, given the interaction's structure. It leverages supervised and semi-supervised feature-based classifiers, including our new Random Forest self-learning protocol. The classifiers are trained based on a dataset of comprehensive mutagenesis studies for 151 PPI complexes, with experimentally determined binding affinities of the mutant and wild-type interactions. Three classification problems were considered: (1) a 2-class problem (strengthening/weakening PPI mutations), (2) another 2-class problem (mutations that disrupt/preserve a PPI), and (3) a 3-class classification (detrimental/neutral/beneficial mutation effects). In total, 11 different supervised and semi-supervised classifiers were trained and assessed resulting in a promising performance, with the weighted f-measure ranging from 0.87 for Problem 1 to 0.70 for the most challenging Problem 3. By integrating prediction results of the 2-class classifiers into the 3-class classifier, we further improved its performance for Problem 3. To demonstrate the utility of SNP-IN tool, it was applied to study the nsSNP-induced rewiring of two disease-centered networks. The accurate and balanced performance of SNP-IN tool makes it readily available to study the rewiring of

  7. Graph-based semi-supervised learning with genomic data integration using condition-responsive genes applied to phenotype classification.

    Science.gov (United States)

    Doostparast Torshizi, Abolfazl; Petzold, Linda R

    2018-01-01

    Data integration methods that combine data from different molecular levels such as genome, epigenome, transcriptome, etc., have received a great deal of interest in the past few years. It has been demonstrated that the synergistic effects of different biological data types can boost learning capabilities and lead to a better understanding of the underlying interactions among molecular levels. In this paper we present a graph-based semi-supervised classification algorithm that incorporates latent biological knowledge in the form of biological pathways with gene expression and DNA methylation data. The process of graph construction from biological pathways is based on detecting condition-responsive genes, where 3 sets of genes are finally extracted: all condition responsive genes, high-frequency condition-responsive genes, and P-value-filtered genes. The proposed approach is applied to ovarian cancer data downloaded from the Human Genome Atlas. Extensive numerical experiments demonstrate superior performance of the proposed approach compared to other state-of-the-art algorithms, including the latest graph-based classification techniques. Simulation results demonstrate that integrating various data types enhances classification performance and leads to a better understanding of interrelations between diverse omics data types. The proposed approach outperforms many of the state-of-the-art data integration algorithms. © 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

  8. Semi-supervised learning and domain adaptation in natural language processing

    CERN Document Server

    Søgaard, Anders

    2013-01-01

    This book introduces basic supervised learning algorithms applicable to natural language processing (NLP) and shows how the performance of these algorithms can often be improved by exploiting the marginal distribution of large amounts of unlabeled data. One reason for that is data sparsity, i.e., the limited amounts of data we have available in NLP. However, in most real-world NLP applications our labeled data is also heavily biased. This book introduces extensions of supervised learning algorithms to cope with data sparsity and different kinds of sampling bias.This book is intended to be both

  9. Manifold regularized multitask learning for semi-supervised multilabel image classification.

    Science.gov (United States)

    Luo, Yong; Tao, Dacheng; Geng, Bo; Xu, Chao; Maybank, Stephen J

    2013-02-01

    It is a significant challenge to classify images with multiple labels by using only a small number of labeled samples. One option is to learn a binary classifier for each label and use manifold regularization to improve the classification performance by exploring the underlying geometric structure of the data distribution. However, such an approach does not perform well in practice when images from multiple concepts are represented by high-dimensional visual features. Thus, manifold regularization is insufficient to control the model complexity. In this paper, we propose a manifold regularized multitask learning (MRMTL) algorithm. MRMTL learns a discriminative subspace shared by multiple classification tasks by exploiting the common structure of these tasks. It effectively controls the model complexity because different tasks limit one another's search volume, and the manifold regularization ensures that the functions in the shared hypothesis space are smooth along the data manifold. We conduct extensive experiments, on the PASCAL VOC'07 dataset with 20 classes and the MIR dataset with 38 classes, by comparing MRMTL with popular image classification algorithms. The results suggest that MRMTL is effective for image classification.

  10. Semi-supervised sparse coding

    KAUST Repository

    Wang, Jim Jing-Yan; Gao, Xin

    2014-01-01

    Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the manifold structure spanned by the data set of both labeled and unlabeled samples and the constraints provided by the labels of the labeled samples, we learn the variable class labels for all the samples. Furthermore, to improve the discriminative ability of the learned sparse codes, we assume that the class labels could be predicted from the sparse codes directly using a linear classifier. By solving the codebook, sparse codes, class labels and classifier parameters simultaneously in a unified objective function, we develop a semi-supervised sparse coding algorithm. Experiments on two real-world pattern recognition problems demonstrate the advantage of the proposed methods over supervised sparse coding methods on partially labeled data sets.

  11. Semi-supervised sparse coding

    KAUST Repository

    Wang, Jim Jing-Yan

    2014-07-06

    Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a semi-supervised manner, where only a few training samples are labeled. By using the manifold structure spanned by the data set of both labeled and unlabeled samples and the constraints provided by the labels of the labeled samples, we learn the variable class labels for all the samples. Furthermore, to improve the discriminative ability of the learned sparse codes, we assume that the class labels could be predicted from the sparse codes directly using a linear classifier. By solving the codebook, sparse codes, class labels and classifier parameters simultaneously in a unified objective function, we develop a semi-supervised sparse coding algorithm. Experiments on two real-world pattern recognition problems demonstrate the advantage of the proposed methods over supervised sparse coding methods on partially labeled data sets.

  12. Quality-Related Monitoring and Grading of Granulated Products by Weibull-Distribution Modeling of Visual Images with Semi-Supervised Learning.

    Science.gov (United States)

    Liu, Jinping; Tang, Zhaohui; Xu, Pengfei; Liu, Wenzhong; Zhang, Jin; Zhu, Jianyong

    2016-06-29

    The topic of online product quality inspection (OPQI) with smart visual sensors is attracting increasing interest in both the academic and industrial communities on account of the natural connection between the visual appearance of products with their underlying qualities. Visual images captured from granulated products (GPs), e.g., cereal products, fabric textiles, are comprised of a large number of independent particles or stochastically stacking locally homogeneous fragments, whose analysis and understanding remains challenging. A method of image statistical modeling-based OPQI for GP quality grading and monitoring by a Weibull distribution(WD) model with a semi-supervised learning classifier is presented. WD-model parameters (WD-MPs) of GP images' spatial structures, obtained with omnidirectional Gaussian derivative filtering (OGDF), which were demonstrated theoretically to obey a specific WD model of integral form, were extracted as the visual features. Then, a co-training-style semi-supervised classifier algorithm, named COSC-Boosting, was exploited for semi-supervised GP quality grading, by integrating two independent classifiers with complementary nature in the face of scarce labeled samples. Effectiveness of the proposed OPQI method was verified and compared in the field of automated rice quality grading with commonly-used methods and showed superior performance, which lays a foundation for the quality control of GP on assembly lines.

  13. Moment constrained semi-supervised LDA

    DEFF Research Database (Denmark)

    Loog, Marco

    2012-01-01

    This BNAIC compressed contribution provides a summary of the work originally presented at the First IAPR Workshop on Partially Supervised Learning and published in [5]. It outlines the idea behind supervised and semi-supervised learning and highlights the major shortcoming of many current methods...

  14. Projected estimators for robust semi-supervised classification

    NARCIS (Netherlands)

    Krijthe, J.H.; Loog, M.

    2017-01-01

    For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Unlike other approaches to semi-supervised learning, the

  15. Data integration modeling applied to drill hole planning through semi-supervised learning: A case study from the Dalli Cu-Au porphyry deposit in the central Iran

    Science.gov (United States)

    Fatehi, Moslem; Asadi, Hooshang H.

    2017-04-01

    In this study, the application of a transductive support vector machine (TSVM), an innovative semi-supervised learning algorithm, has been proposed for mapping the potential drill targets at a detailed exploration stage. The semi-supervised learning method is a hybrid of supervised and unsupervised learning approach that simultaneously uses both training and non-training data to design a classifier. By using the TSVM algorithm, exploration layers at the Dalli porphyry Cu-Au deposit in the central Iran were integrated to locate the boundary of the Cu-Au mineralization for further drilling. By applying this algorithm on the non-training (unlabeled) and limited training (labeled) Dalli exploration data, the study area was classified in two domains of Cu-Au ore and waste. Then, the results were validated by the earlier block models created, using the available borehole and trench data. In addition to TSVM, the support vector machine (SVM) algorithm was also implemented on the study area for comparison. Thirty percent of the labeled exploration data was used to evaluate the performance of these two algorithms. The results revealed 87 percent correct recognition accuracy for the TSVM algorithm and 82 percent for the SVM algorithm. The deepest inclined borehole, recently drilled in the western part of the Dalli deposit, indicated that the boundary of Cu-Au mineralization, as identified by the TSVM algorithm, was only 15 m off from the actual boundary intersected by this borehole. According to the results of the TSVM algorithm, six new boreholes were suggested for further drilling at the Dalli deposit. This study showed that the TSVM algorithm could be a useful tool for enhancing the mineralization zones and consequently, ensuring a more accurate drill hole planning.

  16. Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

    NARCIS (Netherlands)

    Cheplygina, Veronika; de Bruijne, Marleen; Pluim, Josien P. W.

    2018-01-01

    Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods which can learn

  17. Discriminative semi-supervised feature selection via manifold regularization.

    Science.gov (United States)

    Xu, Zenglin; King, Irwin; Lyu, Michael Rung-Tsong; Jin, Rong

    2010-07-01

    Feature selection has attracted a huge amount of interest in both research and application communities of data mining. We consider the problem of semi-supervised feature selection, where we are given a small amount of labeled examples and a large amount of unlabeled examples. Since a small number of labeled samples are usually insufficient for identifying the relevant features, the critical problem arising from semi-supervised feature selection is how to take advantage of the information underneath the unlabeled data. To address this problem, we propose a novel discriminative semi-supervised feature selection method based on the idea of manifold regularization. The proposed approach selects features through maximizing the classification margin between different classes and simultaneously exploiting the geometry of the probability distribution that generates both labeled and unlabeled data. In comparison with previous semi-supervised feature selection algorithms, our proposed semi-supervised feature selection method is an embedded feature selection method and is able to find more discriminative features. We formulate the proposed feature selection method into a convex-concave optimization problem, where the saddle point corresponds to the optimal solution. To find the optimal solution, the level method, a fairly recent optimization method, is employed. We also present a theoretic proof of the convergence rate for the application of the level method to our problem. Empirical evaluation on several benchmark data sets demonstrates the effectiveness of the proposed semi-supervised feature selection method.

  18. Semi-Supervised Tripled Dictionary Learning for Standard-dose PET Image Prediction using Low-dose PET and Multimodal MRI

    Science.gov (United States)

    Wang, Yan; Ma, Guangkai; An, Le; Shi, Feng; Zhang, Pei; Lalush, David S.; Wu, Xi; Pu, Yifei; Zhou, Jiliu; Shen, Dinggang

    2017-01-01

    Objective To obtain high-quality positron emission tomography (PET) image with low-dose tracer injection, this study attempts to predict the standard-dose PET (S-PET) image from both its low-dose PET (L-PET) counterpart and corresponding magnetic resonance imaging (MRI). Methods It was achieved by patch-based sparse representation (SR), using the training samples with a complete set of MRI, L-PET and S-PET modalities for dictionary construction. However, the number of training samples with complete modalities is often limited. In practice, many samples generally have incomplete modalities (i.e., with one or two missing modalities) that thus cannot be used in the prediction process. In light of this, we develop a semi-supervised tripled dictionary learning (SSTDL) method for S-PET image prediction, which can utilize not only the samples with complete modalities (called complete samples) but also the samples with incomplete modalities (called incomplete samples), to take advantage of the large number of available training samples and thus further improve the prediction performance. Results Validation was done on a real human brain dataset consisting of 18 subjects, and the results show that our method is superior to the SR and other baseline methods. Conclusion This work proposed a new S-PET prediction method, which can significantly improve the PET image quality with low-dose injection. Significance The proposed method is favorable in clinical application since it can decrease the potential radiation risk for patients. PMID:27187939

  19. Efficient Computation of Entropy Gradient for Semi-Supervised Conditional Random Fields

    National Research Council Canada - National Science Library

    Mann, Gideon S; McCallum, Andrew

    2007-01-01

    Entropy regularization is a straightforward and successful method of semi-supervised learning that augments the traditional conditional likelihood objective function with an additional term that aims...

  20. An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos

    Directory of Open Access Journals (Sweden)

    B. Ravi Kiran

    2018-02-01

    Full Text Available Videos represent the primary source of information for surveillance applications. Video material is often available in large quantities but in most cases it contains little or no annotation for supervised learning. This article reviews the state-of-the-art deep learning based methods for video anomaly detection and categorizes them based on the type of model and criteria of detection. We also perform simple studies to understand the different approaches and provide the criteria of evaluation for spatio-temporal anomaly detection.

  1. Semi-supervised clustering methods.

    Science.gov (United States)

    Bair, Eric

    2013-01-01

    Cluster analysis methods seek to partition a data set into homogeneous subgroups. It is useful in a wide variety of applications, including document processing and modern genetics. Conventional clustering methods are unsupervised, meaning that there is no outcome variable nor is anything known about the relationship between the observations in the data set. In many situations, however, information about the clusters is available in addition to the values of the features. For example, the cluster labels of some observations may be known, or certain observations may be known to belong to the same cluster. In other cases, one may wish to identify clusters that are associated with a particular outcome variable. This review describes several clustering algorithms (known as "semi-supervised clustering" methods) that can be applied in these situations. The majority of these methods are modifications of the popular k-means clustering method, and several of them will be described in detail. A brief description of some other semi-supervised clustering algorithms is also provided.

  2. Semi-supervised clustering methods

    Science.gov (United States)

    Bair, Eric

    2013-01-01

    Cluster analysis methods seek to partition a data set into homogeneous subgroups. It is useful in a wide variety of applications, including document processing and modern genetics. Conventional clustering methods are unsupervised, meaning that there is no outcome variable nor is anything known about the relationship between the observations in the data set. In many situations, however, information about the clusters is available in addition to the values of the features. For example, the cluster labels of some observations may be known, or certain observations may be known to belong to the same cluster. In other cases, one may wish to identify clusters that are associated with a particular outcome variable. This review describes several clustering algorithms (known as “semi-supervised clustering” methods) that can be applied in these situations. The majority of these methods are modifications of the popular k-means clustering method, and several of them will be described in detail. A brief description of some other semi-supervised clustering algorithms is also provided. PMID:24729830

  3. Enhanced manifold regularization for semi-supervised classification.

    Science.gov (United States)

    Gan, Haitao; Luo, Zhizeng; Fan, Yingle; Sang, Nong

    2016-06-01

    Manifold regularization (MR) has become one of the most widely used approaches in the semi-supervised learning field. It has shown superiority by exploiting the local manifold structure of both labeled and unlabeled data. The manifold structure is modeled by constructing a Laplacian graph and then incorporated in learning through a smoothness regularization term. Hence the labels of labeled and unlabeled data vary smoothly along the geodesics on the manifold. However, MR has ignored the discriminative ability of the labeled and unlabeled data. To address the problem, we propose an enhanced MR framework for semi-supervised classification in which the local discriminative information of the labeled and unlabeled data is explicitly exploited. To make full use of labeled data, we firstly employ a semi-supervised clustering method to discover the underlying data space structure of the whole dataset. Then we construct a local discrimination graph to model the discriminative information of labeled and unlabeled data according to the discovered intrinsic structure. Therefore, the data points that may be from different clusters, though similar on the manifold, are enforced far away from each other. Finally, the discrimination graph is incorporated into the MR framework. In particular, we utilize semi-supervised fuzzy c-means and Laplacian regularized Kernel minimum squared error for semi-supervised clustering and classification, respectively. Experimental results on several benchmark datasets and face recognition demonstrate the effectiveness of our proposed method.

  4. Projected estimators for robust semi-supervised classification

    DEFF Research Database (Denmark)

    Krijthe, Jesse H.; Loog, Marco

    2017-01-01

    For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Unlike other approaches to semi-supervised learning, the procedure...... specifically, we prove that, measured on the labeled and unlabeled training data, this semi-supervised procedure never gives a lower quadratic loss than the supervised alternative. To our knowledge this is the first approach that offers such strong, albeit conservative, guarantees for improvement over...... the supervised solution. The characteristics of our approach are explicated using benchmark datasets to further understand the similarities and differences between the quadratic loss criterion used in the theoretical results and the classification accuracy typically considered in practice....

  5. A semi-supervised learning approach to predict synthetic genetic interactions by combining functional and topological properties of functional gene network

    Directory of Open Access Journals (Sweden)

    Han Kyungsook

    2010-06-01

    Full Text Available Abstract Background Genetic interaction profiles are highly informative and helpful for understanding the functional linkages between genes, and therefore have been extensively exploited for annotating gene functions and dissecting specific pathway structures. However, our understanding is rather limited to the relationship between double concurrent perturbation and various higher level phenotypic changes, e.g. those in cells, tissues or organs. Modifier screens, such as synthetic genetic arrays (SGA can help us to understand the phenotype caused by combined gene mutations. Unfortunately, exhaustive tests on all possible combined mutations in any genome are vulnerable to combinatorial explosion and are infeasible either technically or financially. Therefore, an accurate computational approach to predict genetic interaction is highly desirable, and such methods have the potential of alleviating the bottleneck on experiment design. Results In this work, we introduce a computational systems biology approach for the accurate prediction of pairwise synthetic genetic interactions (SGI. First, a high-coverage and high-precision functional gene network (FGN is constructed by integrating protein-protein interaction (PPI, protein complex and gene expression data; then, a graph-based semi-supervised learning (SSL classifier is utilized to identify SGI, where the topological properties of protein pairs in weighted FGN is used as input features of the classifier. We compare the proposed SSL method with the state-of-the-art supervised classifier, the support vector machines (SVM, on a benchmark dataset in S. cerevisiae to validate our method's ability to distinguish synthetic genetic interactions from non-interaction gene pairs. Experimental results show that the proposed method can accurately predict genetic interactions in S. cerevisiae (with a sensitivity of 92% and specificity of 91%. Noticeably, the SSL method is more efficient than SVM, especially for

  6. Semi-Supervised Transductive Hot Spot Predictor Working on Multiple Assumptions

    KAUST Repository

    Wang, Jim Jing-Yan; Almasri, Islam; Shi, Yuexiang; Gao, Xin

    2014-01-01

    of the transductive semi-supervised algorithms takes all the three semisupervised assumptions, i.e., smoothness, cluster and manifold assumptions, together into account during learning. In this paper, we propose a novel semi-supervised method for hot spot residue

  7. A Semi-Supervised Learning Algorithm for Predicting Four Types MiRNA-Disease Associations by Mutual Information in a Heterogeneous Network.

    Science.gov (United States)

    Zhang, Xiaotian; Yin, Jian; Zhang, Xu

    2018-03-02

    Increasing evidence suggests that dysregulation of microRNAs (miRNAs) may lead to a variety of diseases. Therefore, identifying disease-related miRNAs is a crucial problem. Currently, many computational approaches have been proposed to predict binary miRNA-disease associations. In this study, in order to predict underlying miRNA-disease association types, a semi-supervised model called the network-based label propagation algorithm is proposed to infer multiple types of miRNA-disease associations (NLPMMDA) by mutual information derived from the heterogeneous network. The NLPMMDA method integrates disease semantic similarity, miRNA functional similarity, and Gaussian interaction profile kernel similarity information of miRNAs and diseases to construct a heterogeneous network. NLPMMDA is a semi-supervised model which does not require verified negative samples. Leave-one-out cross validation (LOOCV) was implemented for four known types of miRNA-disease associations and demonstrated the reliable performance of our method. Moreover, case studies of lung cancer and breast cancer confirmed effective performance of NLPMMDA to predict novel miRNA-disease associations and their association types.

  8. Semi-supervised detection of intracranial pressure alarms using waveform dynamics

    International Nuclear Information System (INIS)

    Scalzo, Fabien; Hu, Xiao

    2013-01-01

    Patient monitoring systems in intensive care units (ICU) are usually set to trigger alarms when abnormal values are detected. Alarms are generated by threshold-crossing rules that lead to high false alarm rates. This is a recognized issue that causes alarm fatigue, waste of human resources, and increased patient risks. Recently developed smart alarm models require alarms to be validated by experts during the training phase. The manual annotation process involved is time-consuming and virtually impossible to achieve for the thousands of alarms recorded in the ICU every week. To tackle this problem, we investigate in this study if the use of semi-supervised learning methods, that can naturally integrate unlabeled data samples in the model, can be used to improve the accuracy of the alarm detection. As a proof of concept, the detection system is evaluated on intracranial pressure (ICP) signal alarms. Specific morphological and trending features are extracted from the ICP signal waveform to capture the dynamic of the signal prior to alarms. This study is based on a comprehensive dataset of 4791 manually labeled alarms recorded from 108 neurosurgical patients. A comparative analysis is provided between kernel spectral regression (SR-KDA) and support vector machine (SVM) both modified for the semi-supervised setting. Results obtained during the experimental evaluations indicate that the two models can significantly reduce false alarms using unlabeled samples; especially in the presence of a restrained number of labeled examples. At a true alarm recognition rate of 99%, the false alarm reduction rates improved from 9% (supervised) to 27% (semi-supervised) for SR-KDA, and from 3% (supervised) to 16% (semi-supervised) for SVM. (paper)

  9. Semi-Supervised Multiple Feature Analysis for Action Recognition

    Science.gov (United States)

    2013-11-26

    in saving la- beling costs while simultaneously achieving good performance. Most semi-supervised learning methods assume that nearby points are likely...3, 5, 10 and 15) per category in the training set, thus resulting in , , , and randomly la- beled videos, with the remaining training videos unlabeled...with the increase of la- beled training samples, the performance of all algorithms rises. Meanwhile, the performance differences between our method and

  10. Predict subcellular locations of singleplex and multiplex proteins by semi-supervised learning and dimension-reducing general mode of Chou's PseAAC.

    Science.gov (United States)

    Pacharawongsakda, Eakasit; Theeramunkong, Thanaruk

    2013-12-01

    Predicting protein subcellular location is one of major challenges in Bioinformatics area since such knowledge helps us understand protein functions and enables us to select the targeted proteins during drug discovery process. While many computational techniques have been proposed to improve predictive performance for protein subcellular location, they have several shortcomings. In this work, we propose a method to solve three main issues in such techniques; i) manipulation of multiplex proteins which may exist or move between multiple cellular compartments, ii) handling of high dimensionality in input and output spaces and iii) requirement of sufficient labeled data for model training. Towards these issues, this work presents a new computational method for predicting proteins which have either single or multiple locations. The proposed technique, namely iFLAST-CORE, incorporates the dimensionality reduction in the feature and label spaces with co-training paradigm for semi-supervised multi-label classification. For this purpose, the Singular Value Decomposition (SVD) is applied to transform the high-dimensional feature space and label space into the lower-dimensional spaces. After that, due to limitation of labeled data, the co-training regression makes use of unlabeled data by predicting the target values in the lower-dimensional spaces of unlabeled data. In the last step, the component of SVD is used to project labels in the lower-dimensional space back to those in the original space and an adaptive threshold is used to map a numeric value to a binary value for label determination. A set of experiments on viral proteins and gram-negative bacterial proteins evidence that our proposed method improve the classification performance in terms of various evaluation metrics such as Aiming (or Precision), Coverage (or Recall) and macro F-measure, compared to the traditional method that uses only labeled data.

  11. Semi-supervised morphosyntactic classification of Old Icelandic.

    Science.gov (United States)

    Urban, Kryztof; Tangherlini, Timothy R; Vijūnas, Aurelijus; Broadwell, Peter M

    2014-01-01

    We present IceMorph, a semi-supervised morphosyntactic analyzer of Old Icelandic. In addition to machine-read corpora and dictionaries, it applies a small set of declension prototypes to map corpus words to dictionary entries. A web-based GUI allows expert users to modify and augment data through an online process. A machine learning module incorporates prototype data, edit-distance metrics, and expert feedback to continuously update part-of-speech and morphosyntactic classification. An advantage of the analyzer is its ability to achieve competitive classification accuracy with minimum training data.

  12. Semi-supervised drug-protein interaction prediction from heterogeneous biological spaces.

    Science.gov (United States)

    Xia, Zheng; Wu, Ling-Yun; Zhou, Xiaobo; Wong, Stephen T C

    2010-09-13

    Predicting drug-protein interactions from heterogeneous biological data sources is a key step for in silico drug discovery. The difficulty of this prediction task lies in the rarity of known drug-protein interactions and myriad unknown interactions to be predicted. To meet this challenge, a manifold regularization semi-supervised learning method is presented to tackle this issue by using labeled and unlabeled information which often generates better results than using the labeled data alone. Furthermore, our semi-supervised learning method integrates known drug-protein interaction network information as well as chemical structure and genomic sequence data. Using the proposed method, we predicted certain drug-protein interactions on the enzyme, ion channel, GPCRs, and nuclear receptor data sets. Some of them are confirmed by the latest publicly available drug targets databases such as KEGG. We report encouraging results of using our method for drug-protein interaction network reconstruction which may shed light on the molecular interaction inference and new uses of marketed drugs.

  13. Semi-supervised tracking of extreme weather events in global spatio-temporal climate datasets

    Science.gov (United States)

    Kim, S. K.; Prabhat, M.; Williams, D. N.

    2017-12-01

    Deep neural networks have been successfully applied to solve problem to detect extreme weather events in large scale climate datasets and attend superior performance that overshadows all previous hand-crafted methods. Recent work has shown that multichannel spatiotemporal encoder-decoder CNN architecture is able to localize events in semi-supervised bounding box. Motivated by this work, we propose new learning metric based on Variational Auto-Encoders (VAE) and Long-Short-Term-Memory (LSTM) to track extreme weather events in spatio-temporal dataset. We consider spatio-temporal object tracking problems as learning probabilistic distribution of continuous latent features of auto-encoder using stochastic variational inference. For this, we assume that our datasets are i.i.d and latent features is able to be modeled by Gaussian distribution. In proposed metric, we first train VAE to generate approximate posterior given multichannel climate input with an extreme climate event at fixed time. Then, we predict bounding box, location and class of extreme climate events using convolutional layers given input concatenating three features including embedding, sampled mean and standard deviation. Lastly, we train LSTM with concatenated input to learn timely information of dataset by recurrently feeding output back to next time-step's input of VAE. Our contribution is two-fold. First, we show the first semi-supervised end-to-end architecture based on VAE to track extreme weather events which can apply to massive scaled unlabeled climate datasets. Second, the information of timely movement of events is considered for bounding box prediction using LSTM which can improve accuracy of localization. To our knowledge, this technique has not been explored neither in climate community or in Machine Learning community.

  14. Flexible manifold embedding: a framework for semi-supervised and unsupervised dimension reduction.

    Science.gov (United States)

    Nie, Feiping; Xu, Dong; Tsang, Ivor Wai-Hung; Zhang, Changshui

    2010-07-01

    We propose a unified manifold learning framework for semi-supervised and unsupervised dimension reduction by employing a simple but effective linear regression function to map the new data points. For semi-supervised dimension reduction, we aim to find the optimal prediction labels F for all the training samples X, the linear regression function h(X) and the regression residue F(0) = F - h(X) simultaneously. Our new objective function integrates two terms related to label fitness and manifold smoothness as well as a flexible penalty term defined on the residue F(0). Our Semi-Supervised learning framework, referred to as flexible manifold embedding (FME), can effectively utilize label information from labeled data as well as a manifold structure from both labeled and unlabeled data. By modeling the mismatch between h(X) and F, we show that FME relaxes the hard linear constraint F = h(X) in manifold regularization (MR), making it better cope with the data sampled from a nonlinear manifold. In addition, we propose a simplified version (referred to as FME/U) for unsupervised dimension reduction. We also show that our proposed framework provides a unified view to explain and understand many semi-supervised, supervised and unsupervised dimension reduction techniques. Comprehensive experiments on several benchmark databases demonstrate the significant improvement over existing dimension reduction algorithms.

  15. Variational inference & deep learning : A new synthesis

    NARCIS (Netherlands)

    Kingma, D.P.

    2017-01-01

    In this thesis, Variational Inference and Deep Learning: A New Synthesis, we propose novel solutions to the problems of variational (Bayesian) inference, generative modeling, representation learning, semi-supervised learning, and stochastic optimization.

  16. Variational inference & deep learning: A new synthesis

    OpenAIRE

    Kingma, D.P.

    2017-01-01

    In this thesis, Variational Inference and Deep Learning: A New Synthesis, we propose novel solutions to the problems of variational (Bayesian) inference, generative modeling, representation learning, semi-supervised learning, and stochastic optimization.

  17. Classification of gene expression data: A hubness-aware semi-supervised approach.

    Science.gov (United States)

    Buza, Krisztian

    2016-04-01

    Classification of gene expression data is the common denominator of various biomedical recognition tasks. However, obtaining class labels for large training samples may be difficult or even impossible in many cases. Therefore, semi-supervised classification techniques are required as semi-supervised classifiers take advantage of unlabeled data. Gene expression data is high-dimensional which gives rise to the phenomena known under the umbrella of the curse of dimensionality, one of its recently explored aspects being the presence of hubs or hubness for short. Therefore, hubness-aware classifiers have been developed recently, such as Naive Hubness-Bayesian k-Nearest Neighbor (NHBNN). In this paper, we propose a semi-supervised extension of NHBNN which follows the self-training schema. As one of the core components of self-training is the certainty score, we propose a new hubness-aware certainty score. We performed experiments on publicly available gene expression data. These experiments show that the proposed classifier outperforms its competitors. We investigated the impact of each of the components (classification algorithm, semi-supervised technique, hubness-aware certainty score) separately and showed that each of these components are relevant to the performance of the proposed approach. Our results imply that our approach may increase classification accuracy and reduce computational costs (i.e., runtime). Based on the promising results presented in the paper, we envision that hubness-aware techniques will be used in various other biomedical machine learning tasks. In order to accelerate this process, we made an implementation of hubness-aware machine learning techniques publicly available in the PyHubs software package (http://www.biointelligence.hu/pyhubs) implemented in Python, one of the most popular programming languages of data science. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  18. Semi-Supervised Priors for Microblog Language Identification

    NARCIS (Netherlands)

    Carter, S.; Tsagkias, E.; Weerkamp, W.; Boscarino, C.; Hofmann, K.; Jijkoun, V.; Meij, E.; de Rijke, M.; Weerkamp, W.

    2011-01-01

    Offering access to information in microblog posts requires successful language identification. Language identification on sparse and noisy data can be challenging. In this paper we explore the performance of a state-of-the-art n-gram-based language identifier, and we introduce two semi-supervised

  19. Multi-Label Classification by Semi-Supervised Singular Value Decomposition.

    Science.gov (United States)

    Jing, Liping; Shen, Chenyang; Yang, Liu; Yu, Jian; Ng, Michael K

    2017-10-01

    Multi-label problems arise in various domains, including automatic multimedia data categorization, and have generated significant interest in computer vision and machine learning community. However, existing methods do not adequately address two key challenges: exploiting correlations between labels and making up for the lack of labelled data or even missing labelled data. In this paper, we proposed to use a semi-supervised singular value decomposition (SVD) to handle these two challenges. The proposed model takes advantage of the nuclear norm regularization on the SVD to effectively capture the label correlations. Meanwhile, it introduces manifold regularization on mapping to capture the intrinsic structure among data, which provides a good way to reduce the required labelled data with improving the classification performance. Furthermore, we designed an efficient algorithm to solve the proposed model based on the alternating direction method of multipliers, and thus, it can efficiently deal with large-scale data sets. Experimental results for synthetic and real-world multimedia data sets demonstrate that the proposed method can exploit the label correlations and obtain promising and better label prediction results than the state-of-the-art methods.

  20. Statistical mechanics of semi-supervised clustering in sparse graphs

    International Nuclear Information System (INIS)

    Ver Steeg, Greg; Galstyan, Aram; Allahverdyan, Armen E

    2011-01-01

    We theoretically study semi-supervised clustering in sparse graphs in the presence of pair-wise constraints on the cluster assignments of nodes. We focus on bi-cluster graphs and study the impact of semi-supervision for varying constraint density and overlap between the clusters. Recent results for unsupervised clustering in sparse graphs indicate that there is a critical ratio of within-cluster and between-cluster connectivities below which clusters cannot be recovered with better than random accuracy. The goal of this paper is to examine the impact of pair-wise constraints on the clustering accuracy. Our results suggest that the addition of constraints does not provide automatic improvement over the unsupervised case. When the density of the constraints is sufficiently small, their only impact is to shift the detection threshold while preserving the criticality. Conversely, if the density of (hard) constraints is above the percolation threshold, the criticality is suppressed and the detection threshold disappears

  1. Semi-supervised consensus clustering for gene expression data analysis

    OpenAIRE

    Wang, Yunli; Pan, Youlian

    2014-01-01

    Background Simple clustering methods such as hierarchical clustering and k-means are widely used for gene expression data analysis; but they are unable to deal with noise and high dimensionality associated with the microarray gene expression data. Consensus clustering appears to improve the robustness and quality of clustering results. Incorporating prior knowledge in clustering process (semi-supervised clustering) has been shown to improve the consistency between the data partitioning and do...

  2. A Novel Classification Algorithm Based on Incremental Semi-Supervised Support Vector Machine.

    Directory of Open Access Journals (Sweden)

    Fei Gao

    Full Text Available For current computational intelligence techniques, a major challenge is how to learn new concepts in changing environment. Traditional learning schemes could not adequately address this problem due to a lack of dynamic data selection mechanism. In this paper, inspired by human learning process, a novel classification algorithm based on incremental semi-supervised support vector machine (SVM is proposed. Through the analysis of prediction confidence of samples and data distribution in a changing environment, a "soft-start" approach, a data selection mechanism and a data cleaning mechanism are designed, which complete the construction of our incremental semi-supervised learning system. Noticeably, with the ingenious design procedure of our proposed algorithm, the computation complexity is reduced effectively. In addition, for the possible appearance of some new labeled samples in the learning process, a detailed analysis is also carried out. The results show that our algorithm does not rely on the model of sample distribution, has an extremely low rate of introducing wrong semi-labeled samples and can effectively make use of the unlabeled samples to enrich the knowledge system of classifier and improve the accuracy rate. Moreover, our method also has outstanding generalization performance and the ability to overcome the concept drift in a changing environment.

  3. Semi-Supervised Transductive Hot Spot Predictor Working on Multiple Assumptions

    KAUST Repository

    Wang, Jim Jing-Yan

    2014-05-23

    Protein-protein interactions are critically dependent on just a few residues (“hot spots”) at the interfaces. Hot spots make a dominant contribution to the binding free energy and if mutated they can disrupt the interaction. As mutagenesis studies require significant experimental efforts, there exists a need for accurate and reliable computational hot spot prediction methods. Compared to the supervised hot spot prediction algorithms, the semi-supervised prediction methods can take into consideration both the labeled and unlabeled residues in the dataset during the prediction procedure. The transductive support vector machine has been utilized for this task and demonstrated a better prediction performance. To the best of our knowledge, however, none of the transductive semi-supervised algorithms takes all the three semisupervised assumptions, i.e., smoothness, cluster and manifold assumptions, together into account during learning. In this paper, we propose a novel semi-supervised method for hot spot residue prediction, by considering all the three semisupervised assumptions using nonlinear models. Our algorithm, IterPropMCS, works in an iterative manner. In each iteration, the algorithm first propagates the labels of the labeled residues to the unlabeled ones, along the shortest path between them on a graph, assuming that they lie on a nonlinear manifold. Then it selects the most confident residues as the labeled ones for the next iteration, according to the cluster and smoothness criteria, which is implemented by a nonlinear density estimator. Experiments on a benchmark dataset, using protein structure-based features, demonstrate that our approach is effective in predicting hot spots and compares favorably to other available methods. The results also show that our method outperforms the state-of-the-art transductive learning methods.

  4. A semi-supervised approach using label propagation to support citation screening.

    Science.gov (United States)

    Kontonatsios, Georgios; Brockmeier, Austin J; Przybyła, Piotr; McNaught, John; Mu, Tingting; Goulermas, John Y; Ananiadou, Sophia

    2017-08-01

    Citation screening, an integral process within systematic reviews that identifies citations relevant to the underlying research question, is a time-consuming and resource-intensive task. During the screening task, analysts manually assign a label to each citation, to designate whether a citation is eligible for inclusion in the review. Recently, several studies have explored the use of active learning in text classification to reduce the human workload involved in the screening task. However, existing approaches require a significant amount of manually labelled citations for the text classification to achieve a robust performance. In this paper, we propose a semi-supervised method that identifies relevant citations as early as possible in the screening process by exploiting the pairwise similarities between labelled and unlabelled citations to improve the classification performance without additional manual labelling effort. Our approach is based on the hypothesis that similar citations share the same label (e.g., if one citation should be included, then other similar citations should be included also). To calculate the similarity between labelled and unlabelled citations we investigate two different feature spaces, namely a bag-of-words and a spectral embedding based on the bag-of-words. The semi-supervised method propagates the classification codes of manually labelled citations to neighbouring unlabelled citations in the feature space. The automatically labelled citations are combined with the manually labelled citations to form an augmented training set. For evaluation purposes, we apply our method to reviews from clinical and public health. The results show that our semi-supervised method with label propagation achieves statistically significant improvements over two state-of-the-art active learning approaches across both clinical and public health reviews. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.

  5. Active link selection for efficient semi-supervised community detection

    Science.gov (United States)

    Yang, Liang; Jin, Di; Wang, Xiao; Cao, Xiaochun

    2015-01-01

    Several semi-supervised community detection algorithms have been proposed recently to improve the performance of traditional topology-based methods. However, most of them focus on how to integrate supervised information with topology information; few of them pay attention to which information is critical for performance improvement. This leads to large amounts of demand for supervised information, which is expensive or difficult to obtain in most fields. For this problem we propose an active link selection framework, that is we actively select the most uncertain and informative links for human labeling for the efficient utilization of the supervised information. We also disconnect the most likely inter-community edges to further improve the efficiency. Our main idea is that, by connecting uncertain nodes to their community hubs and disconnecting the inter-community edges, one can sharpen the block structure of adjacency matrix more efficiently than randomly labeling links as the existing methods did. Experiments on both synthetic and real networks demonstrate that our new approach significantly outperforms the existing methods in terms of the efficiency of using supervised information. It needs ~13% of the supervised information to achieve a performance similar to that of the original semi-supervised approaches. PMID:25761385

  6. Improving head and body pose estimation through semi-supervised manifold alignment

    KAUST Repository

    Heili, Alexandre

    2014-10-27

    In this paper, we explore the use of a semi-supervised manifold alignment method for domain adaptation in the context of human body and head pose estimation in videos. We build upon an existing state-of-the-art system that leverages on external labelled datasets for the body and head features, and on the unlabelled test data with weak velocity labels to do a coupled estimation of the body and head pose. While this previous approach showed promising results, the learning of the underlying manifold structure of the features in the train and target data and the need to align them were not explored despite the fact that the pose features between two datasets may vary according to the scene, e.g. due to different camera point of view or perspective. In this paper, we propose to use a semi-supervised manifold alignment method to bring the train and target samples closer within the resulting embedded space. To this end, we consider an adaptation set from the target data and rely on (weak) labels, given for example by the velocity direction whenever they are reliable. These labels, along with the training labels are used to bias the manifold distance within each manifold and to establish correspondences for alignment.

  7. Graph-Based Semi-Supervised Hyperspectral Image Classification Using Spatial Information

    Science.gov (United States)

    Jamshidpour, N.; Homayouni, S.; Safari, A.

    2017-09-01

    Hyperspectral image classification has been one of the most popular research areas in the remote sensing community in the past decades. However, there are still some problems that need specific attentions. For example, the lack of enough labeled samples and the high dimensionality problem are two most important issues which degrade the performance of supervised classification dramatically. The main idea of semi-supervised learning is to overcome these issues by the contribution of unlabeled samples, which are available in an enormous amount. In this paper, we propose a graph-based semi-supervised classification method, which uses both spectral and spatial information for hyperspectral image classification. More specifically, two graphs were designed and constructed in order to exploit the relationship among pixels in spectral and spatial spaces respectively. Then, the Laplacians of both graphs were merged to form a weighted joint graph. The experiments were carried out on two different benchmark hyperspectral data sets. The proposed method performed significantly better than the well-known supervised classification methods, such as SVM. The assessments consisted of both accuracy and homogeneity analyses of the produced classification maps. The proposed spectral-spatial SSL method considerably increased the classification accuracy when the labeled training data set is too scarce.When there were only five labeled samples for each class, the performance improved 5.92% and 10.76% compared to spatial graph-based SSL, for AVIRIS Indian Pine and Pavia University data sets respectively.

  8. A multimedia retrieval framework based on semi-supervised ranking and relevance feedback.

    Science.gov (United States)

    Yang, Yi; Nie, Feiping; Xu, Dong; Luo, Jiebo; Zhuang, Yueting; Pan, Yunhe

    2012-04-01

    We present a new framework for multimedia content analysis and retrieval which consists of two independent algorithms. First, we propose a new semi-supervised algorithm called ranking with Local Regression and Global Alignment (LRGA) to learn a robust Laplacian matrix for data ranking. In LRGA, for each data point, a local linear regression model is used to predict the ranking scores of its neighboring points. A unified objective function is then proposed to globally align the local models from all the data points so that an optimal ranking score can be assigned to each data point. Second, we propose a semi-supervised long-term Relevance Feedback (RF) algorithm to refine the multimedia data representation. The proposed long-term RF algorithm utilizes both the multimedia data distribution in multimedia feature space and the history RF information provided by users. A trace ratio optimization problem is then formulated and solved by an efficient algorithm. The algorithms have been applied to several content-based multimedia retrieval applications, including cross-media retrieval, image retrieval, and 3D motion/pose data retrieval. Comprehensive experiments on four data sets have demonstrated its advantages in precision, robustness, scalability, and computational efficiency.

  9. A semi-supervised classification algorithm using the TAD-derived background as training data

    Science.gov (United States)

    Fan, Lei; Ambeau, Brittany; Messinger, David W.

    2013-05-01

    In general, spectral image classification algorithms fall into one of two categories: supervised and unsupervised. In unsupervised approaches, the algorithm automatically identifies clusters in the data without a priori information about those clusters (except perhaps the expected number of them). Supervised approaches require an analyst to identify training data to learn the characteristics of the clusters such that they can then classify all other pixels into one of the pre-defined groups. The classification algorithm presented here is a semi-supervised approach based on the Topological Anomaly Detection (TAD) algorithm. The TAD algorithm defines background components based on a mutual k-Nearest Neighbor graph model of the data, along with a spectral connected components analysis. Here, the largest components produced by TAD are used as regions of interest (ROI's),or training data for a supervised classification scheme. By combining those ROI's with a Gaussian Maximum Likelihood (GML) or a Minimum Distance to the Mean (MDM) algorithm, we are able to achieve a semi supervised classification method. We test this classification algorithm against data collected by the HyMAP sensor over the Cooke City, MT area and University of Pavia scene.

  10. GRAPH-BASED SEMI-SUPERVISED HYPERSPECTRAL IMAGE CLASSIFICATION USING SPATIAL INFORMATION

    Directory of Open Access Journals (Sweden)

    N. Jamshidpour

    2017-09-01

    Full Text Available Hyperspectral image classification has been one of the most popular research areas in the remote sensing community in the past decades. However, there are still some problems that need specific attentions. For example, the lack of enough labeled samples and the high dimensionality problem are two most important issues which degrade the performance of supervised classification dramatically. The main idea of semi-supervised learning is to overcome these issues by the contribution of unlabeled samples, which are available in an enormous amount. In this paper, we propose a graph-based semi-supervised classification method, which uses both spectral and spatial information for hyperspectral image classification. More specifically, two graphs were designed and constructed in order to exploit the relationship among pixels in spectral and spatial spaces respectively. Then, the Laplacians of both graphs were merged to form a weighted joint graph. The experiments were carried out on two different benchmark hyperspectral data sets. The proposed method performed significantly better than the well-known supervised classification methods, such as SVM. The assessments consisted of both accuracy and homogeneity analyses of the produced classification maps. The proposed spectral-spatial SSL method considerably increased the classification accuracy when the labeled training data set is too scarce.When there were only five labeled samples for each class, the performance improved 5.92% and 10.76% compared to spatial graph-based SSL, for AVIRIS Indian Pine and Pavia University data sets respectively.

  11. Semi-supervised Probabilistic Distance Clustering and the Uncertainty of Classification

    Science.gov (United States)

    Iyigun, Cem; Ben-Israel, Adi

    Semi-supervised clustering is an attempt to reconcile clustering (unsupervised learning) and classification (supervised learning, using prior information on the data). These two modes of data analysis are combined in a parameterized model, the parameter θ ∈ [0, 1] is the weight attributed to the prior information, θ = 0 corresponding to clustering, and θ = 1 to classification. The results (cluster centers, classification rule) depend on the parameter θ, an insensitivity to θ indicates that the prior information is in agreement with the intrinsic cluster structure, and is otherwise redundant. This explains why some data sets (such as the Wisconsin breast cancer data, Merz and Murphy, UCI repository of machine learning databases, University of California, Irvine, CA) give good results for all reasonable classification methods. The uncertainty of classification is represented here by the geometric mean of the membership probabilities, shown to be an entropic distance related to the Kullback-Leibler divergence.

  12. An iterated Laplacian based semi-supervised dimensionality reduction for classification of breast cancer on ultrasound images.

    Science.gov (United States)

    Liu, Xiao; Shi, Jun; Zhou, Shichong; Lu, Minhua

    2014-01-01

    The dimensionality reduction is an important step in ultrasound image based computer-aided diagnosis (CAD) for breast cancer. A newly proposed l2,1 regularized correntropy algorithm for robust feature selection (CRFS) has achieved good performance for noise corrupted data. Therefore, it has the potential to reduce the dimensions of ultrasound image features. However, in clinical practice, the collection of labeled instances is usually expensive and time costing, while it is relatively easy to acquire the unlabeled or undetermined instances. Therefore, the semi-supervised learning is very suitable for clinical CAD. The iterated Laplacian regularization (Iter-LR) is a new regularization method, which has been proved to outperform the traditional graph Laplacian regularization in semi-supervised classification and ranking. In this study, to augment the classification accuracy of the breast ultrasound CAD based on texture feature, we propose an Iter-LR-based semi-supervised CRFS (Iter-LR-CRFS) algorithm, and then apply it to reduce the feature dimensions of ultrasound images for breast CAD. We compared the Iter-LR-CRFS with LR-CRFS, original supervised CRFS, and principal component analysis. The experimental results indicate that the proposed Iter-LR-CRFS significantly outperforms all other algorithms.

  13. Deep Web Search Interface Identification: A Semi-Supervised Ensemble Approach

    Directory of Open Access Journals (Sweden)

    Hong Wang

    2014-12-01

    Full Text Available To surface the Deep Web, one crucial task is to predict whether a given web page has a search interface (searchable HyperText Markup Language (HTML form or not. Previous studies have focused on supervised classification with labeled examples. However, labeled data are scarce, hard to get and requires tediousmanual work, while unlabeled HTML forms are abundant and easy to obtain. In this research, we consider the plausibility of using both labeled and unlabeled data to train better models to identify search interfaces more effectively. We present a semi-supervised co-training ensemble learning approach using both neural networks and decision trees to deal with the search interface identification problem. We show that the proposed model outperforms previous methods using only labeled data. We also show that adding unlabeled data improves the effectiveness of the proposed model.

  14. Semi-Supervised Half-Quadratic Nonnegative Matrix Factorization for Face Recognition

    KAUST Repository

    Alghamdi, Masheal M.

    2014-05-01

    Face recognition is a challenging problem in computer vision. Difficulties such as slight differences between similar faces of different people, changes in facial expressions, light and illumination condition, and pose variations add extra complications to the face recognition research. Many algorithms are devoted to solving the face recognition problem, among which the family of nonnegative matrix factorization (NMF) algorithms has been widely used as a compact data representation method. Different versions of NMF have been proposed. Wang et al. proposed the graph-based semi-supervised nonnegative learning (S2N2L) algorithm that uses labeled data in constructing intrinsic and penalty graph to enforce separability of labeled data, which leads to a greater discriminating power. Moreover the geometrical structure of labeled and unlabeled data is preserved through using the smoothness assumption by creating a similarity graph that conserves the neighboring information for all labeled and unlabeled data. However, S2N2L is sensitive to light changes, illumination, and partial occlusion. In this thesis, we propose a Semi-Supervised Half-Quadratic NMF (SSHQNMF) algorithm that combines the benefits of S2N2L and the robust NMF by the half- quadratic minimization (HQNMF) algorithm.Our algorithm improves upon the S2N2L algorithm by replacing the Frobenius norm with a robust M-Estimator loss function. A multiplicative update solution for our SSHQNMF algorithmis driven using the half- 4 quadratic (HQ) theory. Extensive experiments on ORL, Yale-A and a subset of the PIE data sets for nine M-estimator loss functions for both SSHQNMF and HQNMF algorithms are investigated, and compared with several state-of-the-art supervised and unsupervised algorithms, along with the original S2N2L algorithm in the context of classification, clustering, and robustness against partial occlusion. The proposed algorithm outperformed the other algorithms. Furthermore, SSHQNMF with Maximum Correntropy

  15. Semi-supervised weighted kernel clustering based on gravitational search for fault diagnosis.

    Science.gov (United States)

    Li, Chaoshun; Zhou, Jianzhong

    2014-09-01

    Supervised learning method, like support vector machine (SVM), has been widely applied in diagnosing known faults, however this kind of method fails to work correctly when new or unknown fault occurs. Traditional unsupervised kernel clustering can be used for unknown fault diagnosis, but it could not make use of the historical classification information to improve diagnosis accuracy. In this paper, a semi-supervised kernel clustering model is designed to diagnose known and unknown faults. At first, a novel semi-supervised weighted kernel clustering algorithm based on gravitational search (SWKC-GS) is proposed for clustering of dataset composed of labeled and unlabeled fault samples. The clustering model of SWKC-GS is defined based on wrong classification rate of labeled samples and fuzzy clustering index on the whole dataset. Gravitational search algorithm (GSA) is used to solve the clustering model, while centers of clusters, feature weights and parameter of kernel function are selected as optimization variables. And then, new fault samples are identified and diagnosed by calculating the weighted kernel distance between them and the fault cluster centers. If the fault samples are unknown, they will be added in historical dataset and the SWKC-GS is used to partition the mixed dataset and update the clustering results for diagnosing new fault. In experiments, the proposed method has been applied in fault diagnosis for rotatory bearing, while SWKC-GS has been compared not only with traditional clustering methods, but also with SVM and neural network, for known fault diagnosis. In addition, the proposed method has also been applied in unknown fault diagnosis. The results have shown effectiveness of the proposed method in achieving expected diagnosis accuracy for both known and unknown faults of rotatory bearing. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

  16. Efficient dynamic graph construction for inductive semi-supervised learning.

    Science.gov (United States)

    Dornaika, F; Dahbi, R; Bosaghzadeh, A; Ruichek, Y

    2017-10-01

    Most of graph construction techniques assume a transductive setting in which the whole data collection is available at construction time. Addressing graph construction for inductive setting, in which data are coming sequentially, has received much less attention. For inductive settings, constructing the graph from scratch can be very time consuming. This paper introduces a generic framework that is able to make any graph construction method incremental. This framework yields an efficient and dynamic graph construction method that adds new samples (labeled or unlabeled) to a previously constructed graph. As a case study, we use the recently proposed Two Phase Weighted Regularized Least Square (TPWRLS) graph construction method. The paper has two main contributions. First, we use the TPWRLS coding scheme to represent new sample(s) with respect to an existing database. The representative coefficients are then used to update the graph affinity matrix. The proposed method not only appends the new samples to the graph but also updates the whole graph structure by discovering which nodes are affected by the introduction of new samples and by updating their edge weights. The second contribution of the article is the application of the proposed framework to the problem of graph-based label propagation using multiple observations for vision-based recognition tasks. Experiments on several image databases show that, without any significant loss in the accuracy of the final classification, the proposed dynamic graph construction is more efficient than the batch graph construction. Copyright © 2017 Elsevier Ltd. All rights reserved.

  17. An immune-inspired semi-supervised algorithm for breast cancer diagnosis.

    Science.gov (United States)

    Peng, Lingxi; Chen, Wenbin; Zhou, Wubai; Li, Fufang; Yang, Jin; Zhang, Jiandong

    2016-10-01

    Breast cancer is the most frequently and world widely diagnosed life-threatening cancer, which is the leading cause of cancer death among women. Early accurate diagnosis can be a big plus in treating breast cancer. Researchers have approached this problem using various data mining and machine learning techniques such as support vector machine, artificial neural network, etc. The computer immunology is also an intelligent method inspired by biological immune system, which has been successfully applied in pattern recognition, combination optimization, machine learning, etc. However, most of these diagnosis methods belong to a supervised diagnosis method. It is very expensive to obtain labeled data in biology and medicine. In this paper, we seamlessly integrate the state-of-the-art research on life science with artificial intelligence, and propose a semi-supervised learning algorithm to reduce the need for labeled data. We use two well-known benchmark breast cancer datasets in our study, which are acquired from the UCI machine learning repository. Extensive experiments are conducted and evaluated on those two datasets. Our experimental results demonstrate the effectiveness and efficiency of our proposed algorithm, which proves that our algorithm is a promising automatic diagnosis method for breast cancer. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  18. MULTI-LABEL ASRS DATASET CLASSIFICATION USING SEMI-SUPERVISED SUBSPACE CLUSTERING

    Data.gov (United States)

    National Aeronautics and Space Administration — MULTI-LABEL ASRS DATASET CLASSIFICATION USING SEMI-SUPERVISED SUBSPACE CLUSTERING MOHAMMAD SALIM AHMED, LATIFUR KHAN, NIKUNJ OZA, AND MANDAVA RAJESWARI Abstract....

  19. Tracking mobile users in wireless networks via semi-supervised colocalization.

    Science.gov (United States)

    Pan, Jeffrey Junfeng; Pan, Sinno Jialin; Yin, Jie; Ni, Lionel M; Yang, Qiang

    2012-03-01

    Recent years have witnessed the growing popularity of sensor and sensor-network technologies, supporting important practical applications. One of the fundamental issues is how to accurately locate a user with few labeled data in a wireless sensor network, where a major difficulty arises from the need to label large quantities of user location data, which in turn requires knowledge about the locations of signal transmitters or access points. To solve this problem, we have developed a novel machine learning-based approach that combines collaborative filtering with graph-based semi-supervised learning to learn both mobile users' locations and the locations of access points. Our framework exploits both labeled and unlabeled data from mobile devices and access points. In our two-phase solution, we first build a manifold-based model from a batch of labeled and unlabeled data in an offline training phase and then use a weighted k-nearest-neighbor method to localize a mobile client in an online localization phase. We extend the two-phase colocalization to an online and incremental model that can deal with labeled and unlabeled data that come sequentially and adapt to environmental changes. Finally, we embed an action model to the framework such that additional kinds of sensor signals can be utilized to further boost the performance of mobile tracking. Compared to other state-of-the-art systems, our framework has been shown to be more accurate while requiring less calibration effort in our experiments performed on three different testbeds.

  20. Postprocessing of Accidental Scenarios by Semi-Supervised Self-Organizing Maps

    Directory of Open Access Journals (Sweden)

    Francesco Di Maio

    2017-01-01

    Full Text Available Integrated Deterministic and Probabilistic Safety Analysis (IDPSA of dynamic systems calls for the development of efficient methods for accidental scenarios generation. The necessary consideration of failure events timing and sequencing along the scenarios requires the number of scenarios to be generated to increase with respect to conventional PSA. Consequently, their postprocessing for retrieving safety relevant information regarding the system behavior is challenged because of the large amount of generated scenarios that makes the computational cost for scenario postprocessing enormous and the retrieved information difficult to interpret. In the context of IDPSA, the interpretation consists in the classification of the generated scenarios as safe, failed, Near Misses (NMs, and Prime Implicants (PIs. To address this issue, in this paper we propose the use of an ensemble of Semi-Supervised Self-Organizing Maps (SSSOMs whose outcomes are combined by a locally weighted aggregation according to two strategies: a locally weighted aggregation and a decision tree based aggregation. In the former, we resort to the Local Fusion (LF principle for accounting the classification reliability of the different SSSOM classifiers, whereas in the latter we build a classification scheme to select the appropriate classifier (or ensemble of classifiers, for the type of scenario to be classified. The two strategies are applied for the postprocessing of the accidental scenarios of a dynamic U-Tube Steam Generator (UTSG.

  1. Machinery running state identification based on discriminant semi-supervised local tangent space alignment for feature fusion and extraction

    International Nuclear Information System (INIS)

    Su, Zuqiang; Xiao, Hong; Zhang, Yi; Tang, Baoping; Jiang, Yonghua

    2017-01-01

    Extraction of sensitive features is a challenging but key task in data-driven machinery running state identification. Aimed at solving this problem, a method for machinery running state identification that applies discriminant semi-supervised local tangent space alignment (DSS-LTSA) for feature fusion and extraction is proposed. Firstly, in order to extract more distinct features, the vibration signals are decomposed by wavelet packet decomposition WPD, and a mixed-domain feature set consisted of statistical features, autoregressive (AR) model coefficients, instantaneous amplitude Shannon entropy and WPD energy spectrum is extracted to comprehensively characterize the properties of machinery running state(s). Then, the mixed-dimension feature set is inputted into DSS-LTSA for feature fusion and extraction to eliminate redundant information and interference noise. The proposed DSS-LTSA can extract intrinsic structure information of both labeled and unlabeled state samples, and as a result the over-fitting problem of supervised manifold learning and blindness problem of unsupervised manifold learning are overcome. Simultaneously, class discrimination information is integrated within the dimension reduction process in a semi-supervised manner to improve sensitivity of the extracted fusion features. Lastly, the extracted fusion features are inputted into a pattern recognition algorithm to achieve the running state identification. The effectiveness of the proposed method is verified by a running state identification case in a gearbox, and the results confirm the improved accuracy of the running state identification. (paper)

  2. Semi-supervised prediction of SH2-peptide interactions from imbalanced high-throughput data.

    Science.gov (United States)

    Kundu, Kousik; Costa, Fabrizio; Huber, Michael; Reth, Michael; Backofen, Rolf

    2013-01-01

    Src homology 2 (SH2) domains are the largest family of the peptide-recognition modules (PRMs) that bind to phosphotyrosine containing peptides. Knowledge about binding partners of SH2-domains is key for a deeper understanding of different cellular processes. Given the high binding specificity of SH2, in-silico ligand peptide prediction is of great interest. Currently however, only a few approaches have been published for the prediction of SH2-peptide interactions. Their main shortcomings range from limited coverage, to restrictive modeling assumptions (they are mainly based on position specific scoring matrices and do not take into consideration complex amino acids inter-dependencies) and high computational complexity. We propose a simple yet effective machine learning approach for a large set of known human SH2 domains. We used comprehensive data from micro-array and peptide-array experiments on 51 human SH2 domains. In order to deal with the high data imbalance problem and the high signal-to-noise ration, we casted the problem in a semi-supervised setting. We report competitive predictive performance w.r.t. state-of-the-art. Specifically we obtain 0.83 AUC ROC and 0.93 AUC PR in comparison to 0.71 AUC ROC and 0.87 AUC PR previously achieved by the position specific scoring matrices (PSSMs) based SMALI approach. Our work provides three main contributions. First, we showed that better models can be obtained when the information on the non-interacting peptides (negative examples) is also used. Second, we improve performance when considering high order correlations between the ligand positions employing regularization techniques to effectively avoid overfitting issues. Third, we developed an approach to tackle the data imbalance problem using a semi-supervised strategy. Finally, we performed a genome-wide prediction of human SH2-peptide binding, uncovering several findings of biological relevance. We make our models and genome-wide predictions, for all the 51 SH2

  3. Semi-supervised vibration-based classification and condition monitoring of compressors

    Science.gov (United States)

    Potočnik, Primož; Govekar, Edvard

    2017-09-01

    Semi-supervised vibration-based classification and condition monitoring of the reciprocating compressors installed in refrigeration appliances is proposed in this paper. The method addresses the problem of industrial condition monitoring where prior class definitions are often not available or difficult to obtain from local experts. The proposed method combines feature extraction, principal component analysis, and statistical analysis for the extraction of initial class representatives, and compares the capability of various classification methods, including discriminant analysis (DA), neural networks (NN), support vector machines (SVM), and extreme learning machines (ELM). The use of the method is demonstrated on a case study which was based on industrially acquired vibration measurements of reciprocating compressors during the production of refrigeration appliances. The paper presents a comparative qualitative analysis of the applied classifiers, confirming the good performance of several nonlinear classifiers. If the model parameters are properly selected, then very good classification performance can be obtained from NN trained by Bayesian regularization, SVM and ELM classifiers. The method can be effectively applied for the industrial condition monitoring of compressors.

  4. A Hybrid Semi-Supervised Anomaly Detection Model for High-Dimensional Data

    Directory of Open Access Journals (Sweden)

    Hongchao Song

    2017-01-01

    Full Text Available Anomaly detection, which aims to identify observations that deviate from a nominal sample, is a challenging task for high-dimensional data. Traditional distance-based anomaly detection methods compute the neighborhood distance between each observation and suffer from the curse of dimensionality in high-dimensional space; for example, the distances between any pair of samples are similar and each sample may perform like an outlier. In this paper, we propose a hybrid semi-supervised anomaly detection model for high-dimensional data that consists of two parts: a deep autoencoder (DAE and an ensemble k-nearest neighbor graphs- (K-NNG- based anomaly detector. Benefiting from the ability of nonlinear mapping, the DAE is first trained to learn the intrinsic features of a high-dimensional dataset to represent the high-dimensional data in a more compact subspace. Several nonparametric KNN-based anomaly detectors are then built from different subsets that are randomly sampled from the whole dataset. The final prediction is made by all the anomaly detectors. The performance of the proposed method is evaluated on several real-life datasets, and the results confirm that the proposed hybrid model improves the detection accuracy and reduces the computational complexity.

  5. A Saliency Guided Semi-Supervised Building Change Detection Method for High Resolution Remote Sensing Images

    Directory of Open Access Journals (Sweden)

    Bin Hou

    2016-08-01

    Full Text Available Characterizations of up to date information of the Earth’s surface are an important application providing insights to urban planning, resources monitoring and environmental studies. A large number of change detection (CD methods have been developed to solve them by utilizing remote sensing (RS images. The advent of high resolution (HR remote sensing images further provides challenges to traditional CD methods and opportunities to object-based CD methods. While several kinds of geospatial objects are recognized, this manuscript mainly focuses on buildings. Specifically, we propose a novel automatic approach combining pixel-based strategies with object-based ones for detecting building changes with HR remote sensing images. A multiresolution contextual morphological transformation called extended morphological attribute profiles (EMAPs allows the extraction of geometrical features related to the structures within the scene at different scales. Pixel-based post-classification is executed on EMAPs using hierarchical fuzzy clustering. Subsequently, the hierarchical fuzzy frequency vector histograms are formed based on the image-objects acquired by simple linear iterative clustering (SLIC segmentation. Then, saliency and morphological building index (MBI extracted on difference images are used to generate a pseudo training set. Ultimately, object-based semi-supervised classification is implemented on this training set by applying random forest (RF. Most of the important changes are detected by the proposed method in our experiments. This study was checked for effectiveness using visual evaluation and numerical evaluation.

  6. Semi-Supervised Classification for Fault Diagnosis in Nuclear Power Plants

    International Nuclear Information System (INIS)

    Ma, Jian Ping; Jiang, Jin

    2014-01-01

    Pattern classification methods have become important tools for fault diagnosis in industrial systems. However, it is normally difficult to obtain reliable labeled data to train a supervised pattern classification model for applications in a nuclear power plant (NPP). However, unlabeled data easily become available through increased deployment of supervisory, control, and data acquisition (SCADA) systems. In this paper, a fault diagnosis scheme based on semi-supervised classification (SSC) method is developed with specific applications for NPP. In this scheme, newly measured plant data are treated as unlabeled data. They are integrated with selected labeled data to train a SSC model which is then used to estimate labels of the new data. Compared to exclusive supervised approaches, the proposed scheme requires significantly less number of labeled data to train a classifier. Furthermore, it is shown that higher degree of uncertainties in the labeled data can be tolerated. The developed scheme has been validated using the data generated from a desktop NPP simulator and also from a physical NPP simulator using a graph-based SSC algorithm. Two case studies have been used in the validation process. In the first case study, three faults have been simulated on the desktop simulator. These faults have all been classified successfully with only four labeled data points per fault case. In the second case, six types of fault are simulated on the physical NPP simulator. All faults have been successfully diagnosed. The results have demonstrated that SSC is a promising tool for fault diagnosis

  7. Semi-supervised adaptation in ssvep-based brain-computer interface using tri-training

    DEFF Research Database (Denmark)

    Bender, Thomas; Kjaer, Troels W.; Thomsen, Carsten E.

    2013-01-01

    This paper presents a novel and computationally simple tri-training based semi-supervised steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI). It is implemented with autocorrelation-based features and a Naïve-Bayes classifier (NBC). The system uses nine characters...

  8. Semi-supervised rail defect detection from imbalanced image data

    NARCIS (Netherlands)

    Hajizadeh, S.; Nunez Vicencio, Alfredo; Tax, D.M.J.; Acarman, Tankut

    2016-01-01

    Rail defect detection by video cameras has recently gained much attention in both
    academia and industry. Rail image data has two properties. It is highly imbalanced towards the non-defective class and it has a large number of unlabeled data samples available for semisupervised learning

  9. Vinayaka : A Semi-Supervised Projected Clustering Method Using Differential Evolution

    OpenAIRE

    Satish Gajawada; Durga Toshniwal

    2012-01-01

    Differential Evolution (DE) is an algorithm for evolutionary optimization. Clustering problems have beensolved by using DE based clustering methods but these methods may fail to find clusters hidden insubspaces of high dimensional datasets. Subspace and projected clustering methods have been proposed inliterature to find subspace clusters that are present in subspaces of dataset. In this paper we proposeVINAYAKA, a semi-supervised projected clustering method based on DE. In this method DE opt...

  10. GMDH-Based Semi-Supervised Feature Selection for Electricity Load Classification Forecasting

    Directory of Open Access Journals (Sweden)

    Lintao Yang

    2018-01-01

    Full Text Available With the development of smart power grids, communication network technology and sensor technology, there has been an exponential growth in complex electricity load data. Irregular electricity load fluctuations caused by the weather and holiday factors disrupt the daily operation of the power companies. To deal with these challenges, this paper investigates a day-ahead electricity peak load interval forecasting problem. It transforms the conventional continuous forecasting problem into a novel interval forecasting problem, and then further converts the interval forecasting problem into the classification forecasting problem. In addition, an indicator system influencing the electricity load is established from three dimensions, namely the load series, calendar data, and weather data. A semi-supervised feature selection algorithm is proposed to address an electricity load classification forecasting issue based on the group method of data handling (GMDH technology. The proposed algorithm consists of three main stages: (1 training the basic classifier; (2 selectively marking the most suitable samples from the unclassified label data, and adding them to an initial training set; and (3 training the classification models on the final training set and classifying the test samples. An empirical analysis of electricity load dataset from four Chinese cities is conducted. Results show that the proposed model can address the electricity load classification forecasting problem more efficiently and effectively than the FW-Semi FS (forward semi-supervised feature selection and GMDH-U (GMDH-based semi-supervised feature selection for customer classification models.

  11. Auxiliary Deep Generative Models

    DEFF Research Database (Denmark)

    Maaløe, Lars; Sønderby, Casper Kaae; Sønderby, Søren Kaae

    2016-01-01

    Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave...... the generative model unchanged but make the variational distribution more expressive. Inspired by the structure of the auxiliary variable we also propose a model with two stochastic layers and skip connections. Our findings suggest that more expressive and properly specified deep generative models converge...... faster with better results. We show state-of-the-art performance within semi-supervised learning on MNIST (0.96%), SVHN (16.61%) and NORB (9.40%) datasets....

  12. SSC-EKE: Semi-Supervised Classification with Extensive Knowledge Exploitation.

    Science.gov (United States)

    Qian, Pengjiang; Xi, Chen; Xu, Min; Jiang, Yizhang; Su, Kuan-Hao; Wang, Shitong; Muzic, Raymond F

    2018-01-01

    We introduce a new, semi-supervised classification method that extensively exploits knowledge. The method has three steps. First, the manifold regularization mechanism, adapted from the Laplacian support vector machine (LapSVM), is adopted to mine the manifold structure embedded in all training data, especially in numerous label-unknown data. Meanwhile, by converting the labels into pairwise constraints, the pairwise constraint regularization formula (PCRF) is designed to compensate for the few but valuable labelled data. Second, by further combining the PCRF with the manifold regularization, the precise manifold and pairwise constraint jointly regularized formula (MPCJRF) is achieved. Third, by incorporating the MPCJRF into the framework of the conventional SVM, our approach, referred to as semi-supervised classification with extensive knowledge exploitation (SSC-EKE), is developed. The significance of our research is fourfold: 1) The MPCJRF is an underlying adjustment, with respect to the pairwise constraints, to the graph Laplacian enlisted for approximating the potential data manifold. This type of adjustment plays the correction role, as an unbiased estimation of the data manifold is difficult to obtain, whereas the pairwise constraints, converted from the given labels, have an overall high confidence level. 2) By transforming the values of the two terms in the MPCJRF such that they have the same range, with a trade-off factor varying within the invariant interval [0, 1), the appropriate impact of the pairwise constraints to the graph Laplacian can be self-adaptively determined. 3) The implication regarding extensive knowledge exploitation is embodied in SSC-EKE. That is, the labelled examples are used not only to control the empirical risk but also to constitute the MPCJRF. Moreover, all data, both labelled and unlabelled, are recruited for the model smoothness and manifold regularization. 4) The complete framework of SSC-EKE organically incorporates multiple

  13. spa: Semi-Supervised Semi-Parametric Graph-Based Estimation in R

    Directory of Open Access Journals (Sweden)

    Mark Culp

    2011-04-01

    Full Text Available In this paper, we present an R package that combines feature-based (X data and graph-based (G data for prediction of the response Y . In this particular case, Y is observed for a subset of the observations (labeled and missing for the remainder (unlabeled. We examine an approach for fitting Y = Xβ + f(G where β is a coefficient vector and f is a function over the vertices of the graph. The procedure is semi-supervised in nature (trained on the labeled and unlabeled sets, requiring iterative algorithms for fitting this estimate. The package provides several key functions for fitting and evaluating an estimator of this type. The package is illustrated on a text analysis data set, where the observations are text documents (papers, the response is the category of paper (either applied or theoretical statistics, the X information is the name of the journal in which the paper resides, and the graph is a co-citation network, with each vertex an observation and each edge the number of times that the two papers cite a common paper. An application involving classification of protein location using a protein interaction graph and an application involving classification on a manifold with part of the feature data converted to a graph are also presented.

  14. A semi-supervised method to detect seismic random noise with fuzzy GK clustering

    International Nuclear Information System (INIS)

    Hashemi, Hosein; Javaherian, Abdolrahim; Babuska, Robert

    2008-01-01

    We present a new method to detect random noise in seismic data using fuzzy Gustafson–Kessel (GK) clustering. First, using an adaptive distance norm, a matrix is constructed from the observed seismic amplitudes. The next step is to find centres of ellipsoidal clusters and construct a partition matrix which determines the soft decision boundaries between seismic events and random noise. The GK algorithm updates the cluster centres in order to iteratively minimize the cluster variance. Multiplication of the fuzzy membership function with values of each sample yields new sections; we name them 'clustered sections'. The seismic amplitude values of the clustered sections are given in a way to decrease the level of noise in the original noisy seismic input. In pre-stack data, it is essential to study the clustered sections in a f–k domain; finding the quantitative index for weighting the post-stack data needs a similar approach. Using the knowledge of a human specialist together with the fuzzy unsupervised clustering, the method is a semi-supervised random noise detection. The efficiency of this method is investigated on synthetic and real seismic data for both pre- and post-stack data. The results show a significant improvement of the input noisy sections without harming the important amplitude and phase information of the original data. The procedure for finding the final weights of each clustered section should be carefully done in order to keep almost all the evident seismic amplitudes in the output section. The method interactively uses the knowledge of the seismic specialist in detecting the noise

  15. Manifold Based Low-rank Regularization for Image Restoration and Semi-supervised Learning

    OpenAIRE

    Lai, Rongjie; Li, Jia

    2017-01-01

    Low-rank structures play important role in recent advances of many problems in image science and data science. As a natural extension of low-rank structures for data with nonlinear structures, the concept of the low-dimensional manifold structure has been considered in many data processing problems. Inspired by this concept, we consider a manifold based low-rank regularization as a linear approximation of manifold dimension. This regularization is less restricted than the global low-rank regu...

  16. Semi-supervised spectral algorithms for community detection in complex networks based on equivalence of clustering methods

    Science.gov (United States)

    Ma, Xiaoke; Wang, Bingbo; Yu, Liang

    2018-01-01

    Community detection is fundamental for revealing the structure-functionality relationship in complex networks, which involves two issues-the quantitative function for community as well as algorithms to discover communities. Despite significant research on either of them, few attempt has been made to establish the connection between the two issues. To attack this problem, a generalized quantification function is proposed for community in weighted networks, which provides a framework that unifies several well-known measures. Then, we prove that the trace optimization of the proposed measure is equivalent with the objective functions of algorithms such as nonnegative matrix factorization, kernel K-means as well as spectral clustering. It serves as the theoretical foundation for designing algorithms for community detection. On the second issue, a semi-supervised spectral clustering algorithm is developed by exploring the equivalence relation via combining the nonnegative matrix factorization and spectral clustering. Different from the traditional semi-supervised algorithms, the partial supervision is integrated into the objective of the spectral algorithm. Finally, through extensive experiments on both artificial and real world networks, we demonstrate that the proposed method improves the accuracy of the traditional spectral algorithms in community detection.

  17. Learning with partially labeled and interdependent data

    CERN Document Server

    Amini, Massih-Reza

    2015-01-01

    This book develops two key machine learning principles: the semi-supervised paradigm and learning with interdependent data. It reveals new applications, primarily web related, that transgress the classical machine learning framework through learning with interdependent data. The book traces how the semi-supervised paradigm and the learning to rank paradigm emerged from new web applications, leading to a massive production of heterogeneous textual data. It explains how semi-supervised learning techniques are widely used, but only allow a limited analysis of the information content and thus d

  18. Semi-Supervised Clustering for High-Dimensional and Sparse Features

    Science.gov (United States)

    Yan, Su

    2010-01-01

    Clustering is one of the most common data mining tasks, used frequently for data organization and analysis in various application domains. Traditional machine learning approaches to clustering are fully automated and unsupervised where class labels are unknown a priori. In real application domains, however, some "weak" form of side…

  19. Generation Z, Meet Cooperative Learning

    Science.gov (United States)

    Igel, Charles; Urquhart, Vicki

    2012-01-01

    Today's Generation Z teens need to develop teamwork and social learning skills to be successful in the 21st century workplace. Teachers can help students develop these skills and enhance academic achievement by implementing cooperative learning strategies. Three key principles for successful cooperative learning are discussed. (Contains 1 figure.)

  20. A Semi-Supervised Approach for Refining Transcriptional Signatures of Drug Response and Repositioning Predictions.

    Directory of Open Access Journals (Sweden)

    Francesco Iorio

    Full Text Available We present a novel strategy to identify drug-repositioning opportunities. The starting point of our method is the generation of a signature summarising the consensual transcriptional response of multiple human cell lines to a compound of interest (namely the seed compound. This signature can be derived from data in existing databases, such as the connectivity-map, and it is used at first instance to query a network interlinking all the connectivity-map compounds, based on the similarity of their transcriptional responses. This provides a drug neighbourhood, composed of compounds predicted to share some effects with the seed one. The original signature is then refined by systematically reducing its overlap with the transcriptional responses induced by drugs in this neighbourhood that are known to share a secondary effect with the seed compound. Finally, the drug network is queried again with the resulting refined signatures and the whole process is carried on for a number of iterations. Drugs in the final refined neighbourhood are then predicted to exert the principal mode of action of the seed compound. We illustrate our approach using paclitaxel (a microtubule stabilising agent as seed compound. Our method predicts that glipizide and splitomicin perturb microtubule function in human cells: a result that could not be obtained through standard signature matching methods. In agreement, we find that glipizide and splitomicin reduce interphase microtubule growth rates and transiently increase the percentage of mitotic cells-consistent with our prediction. Finally, we validated the refined signatures of paclitaxel response by mining a large drug screening dataset, showing that human cancer cell lines whose basal transcriptional profile is anti-correlated to them are significantly more sensitive to paclitaxel and docetaxel.

  1. Generative Learning: Adults Learning within Ambiguity

    Science.gov (United States)

    Nicolaides, Aliki

    2015-01-01

    This study explored the extent to which ambiguity can serve as a catalyst for adult learning. The purpose of this study is to understand learning that is generated when encountering ambiguity agitated by the complexity of liquid modernity. "Ambiguity," in this study, describes an encounter with an appearance of reality that is at first…

  2. Transductive Pattern Learning for Information Extraction

    National Research Council Canada - National Science Library

    McLernon, Brian; Kushmerick, Nicholas

    2006-01-01

    .... We present TPLEX, a semi-supervised learning algorithm for information extraction that can acquire extraction patterns from a small amount of labelled text in conjunction with a large amount of unlabelled text...

  3. Machine learning applications in genetics and genomics.

    Science.gov (United States)

    Libbrecht, Maxwell W; Noble, William Stafford

    2015-06-01

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

  4. The benefit of generating errors during learning.

    Science.gov (United States)

    Potts, Rosalind; Shanks, David R

    2014-04-01

    Testing has been found to be a powerful learning tool, but educators might be reluctant to make full use of its benefits for fear that any errors made would be harmful to learning. We asked whether testing could be beneficial to memory even during novel learning, when nearly all responses were errors, and where errors were unlikely to be related to either cues or targets. In 4 experiments, participants learned definitions for unfamiliar English words, or translations for foreign vocabulary, by generating a response and being given corrective feedback, by reading the word and its definition or translation, or by selecting from a choice of definitions or translations followed by feedback. In a final test of all words, generating errors followed by feedback led to significantly better memory for the correct definition or translation than either reading or making incorrect choices, suggesting that the benefits of generation are not restricted to correctly generated items. Even when information to be learned is novel, errorful generation may play a powerful role in potentiating encoding of corrective feedback. Experiments 2A, 2B, and 3 revealed, via metacognitive judgments of learning, that participants are strikingly unaware of this benefit, judging errorful generation to be a less effective encoding method than reading or incorrect choosing, when in fact it was better. Predictions reflected participants' subjective experience during learning. If subjective difficulty leads to more effort at encoding, this could at least partly explain the errorful generation advantage.

  5. Semi-Supervised Kernel PCA

    DEFF Research Database (Denmark)

    Walder, Christian; Henao, Ricardo; Mørup, Morten

    We present three generalisations of Kernel Principal Components Analysis (KPCA) which incorporate knowledge of the class labels of a subset of the data points. The first, MV-KPCA, penalises within class variances similar to Fisher discriminant analysis. The second, LSKPCA is a hybrid of least...... squares regression and kernel PCA. The final LR-KPCA is an iteratively reweighted version of the previous which achieves a sigmoid loss function on the labeled points. We provide a theoretical risk bound as well as illustrative experiments on real and toy data sets....

  6. Generating Multimedia Components for M-Learning

    Directory of Open Access Journals (Sweden)

    Adriana REVEIU

    2009-01-01

    Full Text Available The paper proposes a solution to generate template based multimedia components for instruction and learning available both for computer based applications and for mobile devices. The field of research is situated at the intersection of computer science, mobile tools and e-learning and is generically named mobile learning or M-learning. The research goal is to provide access to computer based training resources from any location and to adapt the training content to the specific features of mobile devices, communication environment, users' preferences and users' knowledge. To become important tools in education field, the technical solutions proposed will follow to use the potential of mobile devices.

  7. Net Generation's Learning Styles in Nursing Education.

    Science.gov (United States)

    Christodoulou, Eleni; Kalokairinou, Athina

    2015-01-01

    Numerous surveys have confirmed that emerging technologies and Web 2.0 tools have been a defining feature in the lives of current students, estimating that there is a fundamental shift in the way young people communicate, socialize and learn. Nursing students in higher education are characterized as digital literate with distinct traits which influence their learning styles. Millennials exhibit distinct learning preferences such as teamwork, experiential activities, structure, instant feedback and technology integration. Higher education institutions should be aware of the implications of the Net Generation coming to university and be prepared to meet their expectations and learning needs.

  8. Generative Inferences Based on Learned Relations

    Science.gov (United States)

    Chen, Dawn; Lu, Hongjing; Holyoak, Keith J.

    2017-01-01

    A key property of relational representations is their "generativity": From partial descriptions of relations between entities, additional inferences can be drawn about other entities. A major theoretical challenge is to demonstrate how the capacity to make generative inferences could arise as a result of learning relations from…

  9. Unifying generative and discriminative learning principles

    Directory of Open Access Journals (Sweden)

    Strickert Marc

    2010-02-01

    Full Text Available Abstract Background The recognition of functional binding sites in genomic DNA remains one of the fundamental challenges of genome research. During the last decades, a plethora of different and well-adapted models has been developed, but only little attention has been payed to the development of different and similarly well-adapted learning principles. Only recently it was noticed that discriminative learning principles can be superior over generative ones in diverse bioinformatics applications, too. Results Here, we propose a generalization of generative and discriminative learning principles containing the maximum likelihood, maximum a posteriori, maximum conditional likelihood, maximum supervised posterior, generative-discriminative trade-off, and penalized generative-discriminative trade-off learning principles as special cases, and we illustrate its efficacy for the recognition of vertebrate transcription factor binding sites. Conclusions We find that the proposed learning principle helps to improve the recognition of transcription factor binding sites, enabling better computational approaches for extracting as much information as possible from valuable wet-lab data. We make all implementations available in the open-source library Jstacs so that this learning principle can be easily applied to other classification problems in the field of genome and epigenome analysis.

  10. Semantic e-Learning: Next Generation of e-Learning?

    Science.gov (United States)

    Konstantinos, Markellos; Penelope, Markellou; Giannis, Koutsonikos; Aglaia, Liopa-Tsakalidi

    Semantic e-learning aspires to be the next generation of e-learning, since the understanding of learning materials and knowledge semantics allows their advanced representation, manipulation, sharing, exchange and reuse and ultimately promote efficient online experiences for users. In this context, the paper firstly explores some fundamental Semantic Web technologies and then discusses current and potential applications of these technologies in e-learning domain, namely, Semantic portals, Semantic search, personalization, recommendation systems, social software and Web 2.0 tools. Finally, it highlights future research directions and open issues of the field.

  11. Intergenerational Learning Program: A Bridge between Generations

    Directory of Open Access Journals (Sweden)

    Seyedeh Zahra Aemmi

    2017-12-01

    Full Text Available One of the goals of education can be considered the transfer of knowledge, skills, competencies, wisdom, norms and values between generations. Intergenerational learning program provide this goal and opportunities for lifelong learning and sharing knowledge and experience between generations. This review aimed to investigate the benefits of this program for the children and older adult and its application in health care systems. An extensive literature search was conducted in some online databases such as Magiran, SID, Scopus, EMBASE, and Medline via PubMed until July 2016 and Persian and English language publications studied that met inclusion criteria. The review concluded that this program can be provided wonderful resources for the social and emotional growth of the children and older adults and can be used for caring, education and follow-up in health care systems especially by nurses. Also, this review highlighted the need for research about this form of learning in Iran.

  12. MEAT: An Authoring Tool for Generating Adaptable Learning Resources

    Science.gov (United States)

    Kuo, Yen-Hung; Huang, Yueh-Min

    2009-01-01

    Mobile learning (m-learning) is a new trend in the e-learning field. The learning services in m-learning environments are supported by fundamental functions, especially the content and assessment services, which need an authoring tool to rapidly generate adaptable learning resources. To fulfill the imperious demand, this study proposes an…

  13. Generative adversarial networks for brain lesion detection

    Science.gov (United States)

    Alex, Varghese; Safwan, K. P. Mohammed; Chennamsetty, Sai Saketh; Krishnamurthi, Ganapathy

    2017-02-01

    Manual segmentation of brain lesions from Magnetic Resonance Images (MRI) is cumbersome and introduces errors due to inter-rater variability. This paper introduces a semi-supervised technique for detection of brain lesion from MRI using Generative Adversarial Networks (GANs). GANs comprises of a Generator network and a Discriminator network which are trained simultaneously with the objective of one bettering the other. The networks were trained using non lesion patches (n=13,000) from 4 different MR sequences. The network was trained on BraTS dataset and patches were extracted from regions excluding tumor region. The Generator network generates data by modeling the underlying probability distribution of the training data, (PData). The Discriminator learns the posterior probability P (Label Data) by classifying training data and generated data as "Real" or "Fake" respectively. The Generator upon learning the joint distribution, produces images/patches such that the performance of the Discriminator on them are random, i.e. P (Label Data = GeneratedData) = 0.5. During testing, the Discriminator assigns posterior probability values close to 0.5 for patches from non lesion regions, while patches centered on lesion arise from a different distribution (PLesion) and hence are assigned lower posterior probability value by the Discriminator. On the test set (n=14), the proposed technique achieves whole tumor dice score of 0.69, sensitivity of 91% and specificity of 59%. Additionally the generator network was capable of generating non lesion patches from various MR sequences.

  14. Scaling up machine learning: parallel and distributed approaches

    National Research Council Canada - National Science Library

    Bekkerman, Ron; Bilenko, Mikhail; Langford, John

    2012-01-01

    ... presented in the book cover a range of parallelization platforms from FPGAs and GPUs to multi-core systems and commodity clusters; concurrent programming frameworks that include CUDA, MPI, MapReduce, and DryadLINQ; and various learning settings: supervised, unsupervised, semi-supervised, and online learning. Extensive coverage of parallelizat...

  15. DIDACTIC ENGINEERING: DESIGNING NEW GENERATION LEARNING SYSTEMS

    Directory of Open Access Journals (Sweden)

    Nail K. Nuriyev

    2016-09-01

    Full Text Available Introduction: the article deals with the organisation of training activities in the man-made environment. Didactic engineering is seen as a methodology within which problems of didactics are solved with application of pedagogical, psychological, engineering methods. It is obvious that in order to implement the training of future engineers in a competence-based format (according to educational standard a new type of teaching system is needed, with new capacities (properties. These systems should set each student towards the development of professionally significant (key abilities, taking into account his/her psychological characteristics; ensure training on the verge of permissible difficulties (developing training, and thereby achieve rapid development of key skills, through his/her zone of “immediate development”; to diagnose the quality of possession of a competence in the academic sense. For the objectivity and reliability of assessment of the level and depth of learned knowledge it is necessary to generate this evaluation in a metric format. As a result, we created a didactic system, which combines all the listed properties and the properties of classical systems. This allowed us to construct a new generation of didactic systems. Materials and Methods: the research is based on a systematic analysis of the activity of an engineer; on models of “zones of immediate development” by L. S. Vygotsky; on “developmental education” by L. N. Zankova; on the use of pedagogical and psychological patterns as well as taxonomic methods, didactic engineering, theory of probability and mathematical statistics. Results: constructed is a model for training engineers in the metric format of competence, which envisages a rapid development of students project and constructive abilit ies based on their knowledge learned. Discussion and Conclusions: the parameters defining the probability of engineer’s success have been described; the taxonomic scale

  16. Online transfer learning with extreme learning machine

    Science.gov (United States)

    Yin, Haibo; Yang, Yun-an

    2017-05-01

    In this paper, we propose a new transfer learning algorithm for online training. The proposed algorithm, which is called Online Transfer Extreme Learning Machine (OTELM), is based on Online Sequential Extreme Learning Machine (OSELM) while it introduces Semi-Supervised Extreme Learning Machine (SSELM) to transfer knowledge from the source to the target domain. With the manifold regularization, SSELM picks out instances from the source domain that are less relevant to those in the target domain to initialize the online training, so as to improve the classification performance. Experimental results demonstrate that the proposed OTELM can effectively use instances in the source domain to enhance the learning performance.

  17. Understanding of Foreign Language Learning of Generation Y

    Science.gov (United States)

    Bozavli, Ebubekir

    2016-01-01

    Different generations are constituted depending on social changes and they are designed sociologically as traditional, baby boomer, X, Y and Z. Many studies have been reported on understanding of foreign language learning generation Y. This study aims to realise the gap in and contribute to the research on language learning understanding of…

  18. Mobile e-Learning for Next Generation Communication Environment

    Science.gov (United States)

    Wu, Tin-Yu; Chao, Han-Chieh

    2008-01-01

    This article develops an environment for mobile e-learning that includes an interactive course, virtual online labs, an interactive online test, and lab-exercise training platform on the fourth generation mobile communication system. The Next Generation Learning Environment (NeGL) promotes the term "knowledge economy." Inter-networking…

  19. Generation of Tutorial Dialogues: Discourse Strategies for Active Learning

    Science.gov (United States)

    1998-05-29

    AND SUBTITLE Generation of Tutorial Dialogues: Discourse Strategies for active Learning AUTHORS Dr. Martha Evens 7. PERFORMING ORGANI2ATION NAME...time the student starts in on a new topic. Michael and Rovick constantly attempt to promote active learning . They regularly use hints and only resort...Controlling active learning : How tutors decide when to generate hints. Proceedings of FLAIRS 󈨣. Melbourne Beach, FL. 157-161. Hume, G., Michael

  20. Learning sparse generative models of audiovisual signals

    OpenAIRE

    Monaci, Gianluca; Sommer, Friedrich T.; Vandergheynst, Pierre

    2008-01-01

    This paper presents a novel framework to learn sparse represen- tations for audiovisual signals. An audiovisual signal is modeled as a sparse sum of audiovisual kernels. The kernels are bimodal functions made of synchronous audio and video components that can be positioned independently and arbitrarily in space and time. We design an algorithm capable of learning sets of such audiovi- sual, synchronous, shift-invariant functions by alternatingly solving a coding and a learning pr...

  1. Intergenerational Learning (Between Generation X & Y) in Learning Families: A Narrative Inquiry

    Science.gov (United States)

    Ho, C. Y. Cherri

    2010-01-01

    The purpose of this study is to examine intergenerational learning behaviour within ten Hong Kong families between Generation X parents and their Generation Y children. It tries to investigate intergenerational knowledge exchange, identify the characteristics of learning behaviour and culture in their "learning families". A narrative…

  2. Renewable electricity generation in India—A learning rate analysis

    International Nuclear Information System (INIS)

    Partridge, Ian

    2013-01-01

    The cost of electricity generation using renewable technologies is widely assumed to be higher than the cost for conventional generation technologies, but likely to fall with growing experience of the technologies concerned. This paper tests the second part of that statement using learning rate analysis, based on large samples of wind and small hydro projects in India, and projects likely changes in these costs through 2020. It is the first study of learning rates for renewable generation technologies in India, and only the second in any developing country—it provides valuable input to the development of Indian energy policy and will be relevant to policy makers in other developing countries. The paper considers some potential problems with learning rate analysis raised by Nordhaus (2009. The Perils of the Learning Model for Modeling Endogenous Technological Change. National Bureau of Economic Research Working Paper Series No. 14638). By taking account of these issues, it is possible both to improve the models used for making cost projections and to examine the potential impact of remaining forecasting problems. - Highlights: • The first learning rate analysis of wind generation costs in India. • Only the second learning rate analysis for wind in any developing country. • Reviews missing variable and related issues in learning rate analysis. • Finds a 17.7% learning rate for wind generation costs in India. • Finds no significant learning effect for small hydro

  3. Make Learning Matter for the Multitasking Generation

    Science.gov (United States)

    Adams, Jill

    2012-01-01

    Technological advances have created amazing opportunities for people throughout the world to access and share information. These opportunities have helped to create a generation of young adolescents who want to make the most of each minute of the day, seizing opportunities to seek information and communicate at the same time. This generation is…

  4. How Effective Is Example Generation for Learning Declarative Concepts?

    Science.gov (United States)

    Rawson, Katherine A.; Dunlosky, John

    2016-01-01

    Declarative concepts (i.e., key terms and corresponding definitions for abstract concepts) represent foundational knowledge that students learn in many content domains. Thus, investigating techniques to enhance concept learning is of critical importance. Various theoretical accounts support the expectation that example generation will serve this…

  5. Learning Orthographic Structure with Sequential Generative Neural Networks

    Science.gov (United States)

    Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

    2016-01-01

    Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in…

  6. Generative Learning Objects Instantiated with Random Numbers Based Expressions

    Directory of Open Access Journals (Sweden)

    Ciprian Bogdan Chirila

    2015-12-01

    Full Text Available The development of interactive e-learning content requires special skills like programming techniques, web integration, graphic design etc. Generally, online educators do not possess such skills and their e-learning products tend to be static like presentation slides and textbooks. In this paper we propose a new interactive model of generative learning objects as a compromise betweenstatic, dull materials and dynamic, complex software e-learning materials developed by specialized teams. We find that random numbers based automatic initialization learning objects increases content diversity, interactivity thus enabling learners’ engagement. The resulted learning object model is at a limited level of complexity related to special e-learning software, intuitive and capable of increasing learners’ interactivity, engagement and motivation through dynamic content. The approach was applied successfully on several computer programing disciplines.

  7. Generating pseudo test collections for learning to rank scientific articles

    NARCIS (Netherlands)

    Berendsen, R.; Tsagkias, M.; de Rijke, M.; Meij, E.

    2012-01-01

    Pseudo test collections are automatically generated to provide training material for learning to rank methods. We propose a method for generating pseudo test collections in the domain of digital libraries, where data is relatively sparse, but comes with rich annotations. Our intuition is that

  8. Generation Y students: Appropriate learning styles and teaching ...

    African Journals Online (AJOL)

    Generation Y students (born after 1982) have developed a different set of attitudes and aptitudes as a result of growing up in an IT and media-rich environment. This article has two objectives: firstly to discuss the learning styles preferred by generation Y students in order to identify the effect of these preferences on tertiary ...

  9. Responsibility and Generativity in Online Learning Communities

    Science.gov (United States)

    Beth, Alicia D.; Jordan, Michelle E.; Schallert, Diane L.; Reed, JoyLynn H.; Kim, Minseong

    2015-01-01

    The purpose of this study was to investigate whether and how students enact "responsibility" and "generativity" through their comments in asynchronous online discussions. "Responsibility" referred to discourse markers indicating participants' sense that their contributions are required in order to uphold their…

  10. Student-generated e-learning for clinical education.

    Science.gov (United States)

    Isaacs, Alex N; Nisly, Sarah; Walton, Alison

    2017-04-01

    Within clinical education, e-learning facilitates a standardised learning experience to augment the clinical experience while enabling learner and teacher flexibility. With the shift of students from consumers to creators, student-generated content is expanding within higher education; however, there is sparse literature evaluating the impact of student-developed e-learning within clinical education. The aim of this study was to implement and evaluate a student-developed e-learning clinical module series within ambulatory care clinical pharmacy experiences. Three clinical e-learning modules were developed by students for use prior to clinical experiences. E-learning modules were created by fourth-year professional pharmacy students and reviewed by pharmacy faculty members. A pre-/post-assessment was performed to evaluate knowledge comprehension before and after participating in the e-learning modules. Additionally, a survey on student perceptions of this educational tool was performed at the end of the clinical experience. There is sparse literature evaluating the impact of student-developed e-learning within clinical education RESULTS: Of the 31 students eligible for study inclusion, 94 per cent participated in both the pre- and post-assessments. The combined post-assessment score was significantly improved after participating in the student-developed e-learning modules (p = 0.008). The student perception survey demonstrated positive perceptions of e-learning within clinical education. Student-generated e-learning was able to enhance knowledge and was positively perceived by learners. As e-learning continues to expand within health sciences education, students can be incorporated into the development and execution of this educational tool. © 2016 John Wiley & Sons Ltd.

  11. Learning Orthographic Structure With Sequential Generative Neural Networks.

    Science.gov (United States)

    Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

    2016-04-01

    Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. Copyright © 2015 Cognitive Science Society, Inc.

  12. Asymmetric Variate Generation via a Parameterless Dual Neural Learning Algorithm

    Directory of Open Access Journals (Sweden)

    Simone Fiori

    2008-01-01

    Full Text Available In a previous work (S. Fiori, 2006, we proposed a random number generator based on a tunable non-linear neural system, whose learning rule is designed on the basis of a cardinal equation from statistics and whose implementation is based on look-up tables (LUTs. The aim of the present manuscript is to improve the above-mentioned random number generation method by changing the learning principle, while retaining the efficient LUT-based implementation. The new method proposed here proves easier to implement and relaxes some previous limitations.

  13. Empirical Studies On Machine Learning Based Text Classification Algorithms

    OpenAIRE

    Shweta C. Dharmadhikari; Maya Ingle; Parag Kulkarni

    2011-01-01

    Automatic classification of text documents has become an important research issue now days. Properclassification of text documents requires information retrieval, machine learning and Natural languageprocessing (NLP) techniques. Our aim is to focus on important approaches to automatic textclassification based on machine learning techniques viz. supervised, unsupervised and semi supervised.In this paper we present a review of various text classification approaches under machine learningparadig...

  14. Using Generative Routines to Support Learning of Ambitious Mathematics Teaching

    Science.gov (United States)

    Ghousseini, Hala; Beasley, Heather; Lord, Sarah

    2017-01-01

    In this paper, we integrate a set of theoretical considerations that together serve as a model for investigating how high-leverage practices could be generative of teacher learning. We use the context of rehearsals to investigate how the use of a specified question sequence aimed at eliciting student mathematical thinking can afford opportunities…

  15. Axis: Generating Explanations at Scale with Learnersourcing and Machine Learning

    Science.gov (United States)

    Williams, Joseph Jay; Kim, Juho; Rafferty, Anna; Heffernan, Neil; Maldonado, Samuel; Gajos, Krzysztof Z.; Lasecki, Walter S.; Heffernan, Neil

    2016-01-01

    While explanations may help people learn by providing information about why an answer is correct, many problems on online platforms lack high-quality explanations. This paper presents AXIS (Adaptive eXplanation Improvement System), a system for obtaining explanations. AXIS asks learners to generate, revise, and evaluate explanations as they solve…

  16. 2020 Vision: Envisioning a New Generation of STEM Learning Research

    Science.gov (United States)

    Dierking, Lynn D.; Falk, John H.

    2016-01-01

    In this issue, we have compiled six original papers, outcomes from the U.S. National Science Foundation (US-NSF)-funded REESE (Research and Evaluation on Education in Science and Engineering) 2020 Vision: The Next Generation of STEM Learning Research project. The purpose of 2020 Vision was to re-envision the questions and frameworks guiding STEM…

  17. Individual Learning Strategies and Choice in Student-Generated Multimedia

    Science.gov (United States)

    McGahan, William T.; Ernst, Hardy; Dyson, Laurel Evelyn

    2016-01-01

    There has been an increasing focus on student-generated multimedia assessment as a way of introducing the benefits of both visual literacy and peer-mediated learning into university courses. One such assessment was offered to first-year health science students but, contrary to expectations, led to poorer performance in their end-of-semester…

  18. Joint sparse learning for 3-D facial expression generation.

    Science.gov (United States)

    Song, Mingli; Tao, Dacheng; Sun, Shengpeng; Chen, Chun; Bu, Jiajun

    2013-08-01

    3-D facial expression generation, including synthesis and retargeting, has received intensive attentions in recent years, because it is important to produce realistic 3-D faces with specific expressions in modern film production and computer games. In this paper, we present joint sparse learning (JSL) to learn mapping functions and their respective inverses to model the relationship between the high-dimensional 3-D faces (of different expressions and identities) and their corresponding low-dimensional representations. Based on JSL, we can effectively and efficiently generate various expressions of a 3-D face by either synthesizing or retargeting. Furthermore, JSL is able to restore 3-D faces with holes by learning a mapping function between incomplete and intact data. Experimental results on a wide range of 3-D faces demonstrate the effectiveness of the proposed approach by comparing with representative ones in terms of quality, time cost, and robustness.

  19. Active Learning Innovations in Knowledge Management Education Generate Higher Quality Learning Outcomes

    Directory of Open Access Journals (Sweden)

    Arthur Shelley

    2014-01-01

    Full Text Available Innovations in how a postgraduate course in knowledge management is delivered have generated better learning outcomes and made the course more engaging for learners. Course participant feedback has shown that collaborative active learning is preferred and provides them with richer insights into how knowledge is created and applied to generate innovation and value. The course applies an andragogy approach in which students collaborate in weekly dialogue of their experiences of the content, rather than learn the content itself. The approach combines systems thinking, learning praxis, and active learning to explore the interdependencies between topics and how they impact outcomes in real world situations. This has stimulated students to apply these ideas in their own workplaces.

  20. A Machine Learning Approach to Test Data Generation

    DEFF Research Database (Denmark)

    Christiansen, Henning; Dahmcke, Christina Mackeprang

    2007-01-01

    been tested, and a more thorough statistical foundation is required. We propose to use logic-statistical modelling methods for machine-learning for analyzing existing and manually marked up data, integrated with the generation of new, artificial data. More specifically, we suggest to use the PRISM...... system developed by Sato and Kameya. Based on logic programming extended with random variables and parameter learning, PRISM appears as a powerful modelling environment, which subsumes HMMs and a wide range of other methods, all embedded in a declarative language. We illustrate these principles here...

  1. Theory-generating practice. Proposing a principle for learning design

    DEFF Research Database (Denmark)

    Buhl, Mie

    2016-01-01

    This contribution proposes a principle for learning design – Theory-Generating Practice (TGP) – as an alternative to the way university courses are traditionally taught and structured, with a series of theoretical lectures isolated from practical experience and concluding with an exam or a project...... building, and takes tacit knowledge into account. The article introduces TGP, contextualizes it to a Danish tradition of didactics, and discusses it in relation to contemporary conceptual currents of didactic design and learning design. This is followed by a theoretical framing of TGP. Finally, three...

  2. Perceptual learning of acoustic noise generates memory-evoked potentials.

    Science.gov (United States)

    Andrillon, Thomas; Kouider, Sid; Agus, Trevor; Pressnitzer, Daniel

    2015-11-02

    Experience continuously imprints on the brain at all stages of life. The traces it leaves behind can produce perceptual learning [1], which drives adaptive behavior to previously encountered stimuli. Recently, it has been shown that even random noise, a type of sound devoid of acoustic structure, can trigger fast and robust perceptual learning after repeated exposure [2]. Here, by combining psychophysics, electroencephalography (EEG), and modeling, we show that the perceptual learning of noise is associated with evoked potentials, without any salient physical discontinuity or obvious acoustic landmark in the sound. Rather, the potentials appeared whenever a memory trace was observed behaviorally. Such memory-evoked potentials were characterized by early latencies and auditory topographies, consistent with a sensory origin. Furthermore, they were generated even on conditions of diverted attention. The EEG waveforms could be modeled as standard evoked responses to auditory events (N1-P2) [3], triggered by idiosyncratic perceptual features acquired through learning. Thus, we argue that the learning of noise is accompanied by the rapid formation of sharp neural selectivity to arbitrary and complex acoustic patterns, within sensory regions. Such a mechanism bridges the gap between the short-term and longer-term plasticity observed in the learning of noise [2, 4-6]. It could also be key to the processing of natural sounds within auditory cortices [7], suggesting that the neural code for sound source identification will be shaped by experience as well as by acoustics. Copyright © 2015 Elsevier Ltd. All rights reserved.

  3. Theory-Generating Practice: Proposing a principle for learning design

    Directory of Open Access Journals (Sweden)

    Mie Buhl

    2016-06-01

    Full Text Available This contribution proposes a principle for learning design: Theory-Generating Practice (TGP as an alternative to the way university courses often are taught and structured with a series of theoretical lectures separate from practical experience and concluding with an exam or a project. The aim is to contribute to a development of theoretical frameworks for learning designs by suggesting TGP which may lead to new practices and turn the traditional dramaturgy for teaching upside down. TGP focuses on embodied experience prior to text reading and lectures to enhance theoretical knowledge building and takes tacit knowledge into account. The article introduces TGP and contextualizes it to a Danish tradition of didactics as well as discusses it in relation to contemporary conceptual currents of didactic design and learning design. This is followed by a theoretical framing of TGP, and is discussed through three empirical examples from bachelor and master programs involving technology, and showing three ways of practicing it.

  4. Theory-Generating Practice: Proposing a principle for learning design

    Directory of Open Access Journals (Sweden)

    Mie Buhl

    2016-05-01

    Full Text Available This contribution proposes a principle for learning design: Theory-Generating Practice (TGP as an alternative to the way university courses often are taught and structured with a series of theoretical lectures separate from practical experience and concluding with an exam or a project. The aim is to contribute to a development of theoretical frameworks for learning designs by suggesting TGP which may lead to new practices and turn the traditional dramaturgy for teaching upside down. TGP focuses on embodied experience prior to text reading and lectures to enhance theoretical knowledge building and takes tacit knowledge into account. The article introduces TGP and contextualizes it to a Danish tradition of didactics as well as discusses it in relation to contemporary conceptual currents of didactic design and learning design. This is followed by a theoretical framing of TGP, and is discussed through three empirical examples from bachelor and master programs involving technology, and showing three ways of practicing it.

  5. Zero-Shot Learning by Generating Pseudo Feature Representations

    OpenAIRE

    Lu, Jiang; Li, Jin; Yan, Ziang; Zhang, Changshui

    2017-01-01

    Zero-shot learning (ZSL) is a challenging task aiming at recognizing novel classes without any training instances. In this paper we present a simple but high-performance ZSL approach by generating pseudo feature representations (GPFR). Given the dataset of seen classes and side information of unseen classes (e.g. attributes), we synthesize feature-level pseudo representations for novel concepts, which allows us access to the formulation of unseen class predictor. Firstly we design a Joint Att...

  6. Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots

    Directory of Open Access Journals (Sweden)

    Akira Taniguchi

    2017-12-01

    Full Text Available In this paper, we propose a Bayesian generative model that can form multiple categories based on each sensory-channel and can associate words with any of the four sensory-channels (action, position, object, and color. This paper focuses on cross-situational learning using the co-occurrence between words and information of sensory-channels in complex situations rather than conventional situations of cross-situational learning. We conducted a learning scenario using a simulator and a real humanoid iCub robot. In the scenario, a human tutor provided a sentence that describes an object of visual attention and an accompanying action to the robot. The scenario was set as follows: the number of words per sensory-channel was three or four, and the number of trials for learning was 20 and 40 for the simulator and 25 and 40 for the real robot. The experimental results showed that the proposed method was able to estimate the multiple categorizations and to learn the relationships between multiple sensory-channels and words accurately. In addition, we conducted an action generation task and an action description task based on word meanings learned in the cross-situational learning scenario. The experimental results showed that the robot could successfully use the word meanings learned by using the proposed method.

  7. An Incremental Type-2 Meta-Cognitive Extreme Learning Machine.

    Science.gov (United States)

    Pratama, Mahardhika; Zhang, Guangquan; Er, Meng Joo; Anavatti, Sreenatha

    2017-02-01

    Existing extreme learning algorithm have not taken into account four issues: 1) complexity; 2) uncertainty; 3) concept drift; and 4) high dimensionality. A novel incremental type-2 meta-cognitive extreme learning machine (ELM) called evolving type-2 ELM (eT2ELM) is proposed to cope with the four issues in this paper. The eT2ELM presents three main pillars of human meta-cognition: 1) what-to-learn; 2) how-to-learn; and 3) when-to-learn. The what-to-learn component selects important training samples for model updates by virtue of the online certainty-based active learning method, which renders eT2ELM as a semi-supervised classifier. The how-to-learn element develops a synergy between extreme learning theory and the evolving concept, whereby the hidden nodes can be generated and pruned automatically from data streams with no tuning of hidden nodes. The when-to-learn constituent makes use of the standard sample reserved strategy. A generalized interval type-2 fuzzy neural network is also put forward as a cognitive component, in which a hidden node is built upon the interval type-2 multivariate Gaussian function while exploiting a subset of Chebyshev series in the output node. The efficacy of the proposed eT2ELM is numerically validated in 12 data streams containing various concept drifts. The numerical results are confirmed by thorough statistical tests, where the eT2ELM demonstrates the most encouraging numerical results in delivering reliable prediction, while sustaining low complexity.

  8. Analysis of students’ generated questions in laboratory learning environments

    Directory of Open Access Journals (Sweden)

    Juan Antonio Llorens-Molina

    2012-03-01

    Full Text Available In order to attain a reliable laboratory work assessment, we argue taking the Learning Environment as a core concept and a research paradigm that considers the factors affecting the laboratory as a particularly complex educational context. With regard to Laboratory Learning Environments (LLEs, a well known approach is the SLEI (Science Laboratory Environment Inventory. The aim of this research is to design and apply an alternative and qualitative assessment tool to characterize Laboratory Learning Environments in an introductory course of organic chemistry. An alternative and qualitative assessment tool would be useful for providing feed-back for experimental learning improvement; serving as a complementary triangulation tool in educational research on LLEs; and generating meaningful categories in order to design quantitative research instruments. Toward this end, spontaneous questions by students have been chosen as a reliable source of information. To process these questions, a methodology based on the Grounded Theory has been developed to provide a framework for characterizing LLEs. This methodology has been applied in two case studies. The conclusions lead us to argue for using more holistic assessment tools in both everyday practice and research. Likewise, a greater attention should be paid to metacognition to achieve suitable self-perception concerning students’ previous knowledge and manipulative skills.

  9. Leveraging Random Number Generation for Mastery of Learning in Teaching Quantitative Research Courses via an E-Learning Method

    Science.gov (United States)

    Boonsathorn, Wasita; Charoen, Danuvasin; Dryver, Arthur L.

    2014-01-01

    E-Learning brings access to a powerful but often overlooked teaching tool: random number generation. Using random number generation, a practically infinite number of quantitative problem-solution sets can be created. In addition, within the e-learning context, in the spirit of the mastery of learning, it is possible to assign online quantitative…

  10. Automated problem generation in Learning Management Systems: a tutorial

    Directory of Open Access Journals (Sweden)

    Jaime Romero

    2016-07-01

    Full Text Available The benefits of solving problems have been widely acknowledged by literature. Its implementation in e–learning platforms can make easier its management and the learning process itself. However, its implementation can also become a very time–consuming task, particularly when the number of problems to generate is high. In this tutorial we describe a methodology that we have developed aiming to alleviate the workload of producing a great deal of problems in Moodle for an undergraduate business course. This methodology follows a six-step process and allows evaluating student’s skills in problem solving, minimizes plagiarism behaviors and provides immediate feedback. We expect this tutorial encourage other educators to apply our six steps process, thus benefiting themselves and their students of its advantages.

  11. Generation and Application of Virtual Dynamic Learning Environments

    Directory of Open Access Journals (Sweden)

    Esther Zaretsky

    2009-04-01

    Full Text Available The generation of virtual dynamic learning environments by mental imagery improved physical education of student teachers. Up-to-date studies showed that training computerized simulations improved spatial abilities, especially visualization of the body's movements in space, and enhanced academic achievements. The main program of the research concentrated on creating teaching units focusing on a variety of physical skills through computerized dynamic presentations. The findings showed that as the student teachers practiced the creation of simulations through the PowerPoint Software, it became clear to them how the computer is related to physical activities. Consequently their presentations became highly animated, and applied to the natural environment. The student teachers applied their presentations in their practical classroom and reported about their pupils' progress in physical skills. Moreover the motivation of the student teachers and pupils to both modes of learning, manipulating virtually and physically, was enhanced.

  12. A Deep Learning Approach to LIBS Spectroscopy for Planetary Applications

    Science.gov (United States)

    Mullen, T. H.; Parente, M.; Gemp, I.; Dyar, M. D.

    2017-12-01

    The ChemCam instrument on the Curiousity rover has collected >440,000 laser-induced breakdown spectra (LIBS) from 1500 different geological targets since 2012. The team is using a pipeline of preprocessing and partial least squares techniques to predict compositions of surface materials [1]. Unfortunately, such multivariate techniques are plagued by hard-to-meet assumptions involving constant hyperparameter tuning to specific elements and the amount of training data available; if the whole distribution of data is not seen, the method will overfit to the training data and generalizability will suffer. The rover only has 10 calibration targets on-board that represent a small subset of the geochemical samples the rover is expected to investigate. Deep neural networks have been used to bypass these issues in other fields. Semi-supervised techniques allow researchers to utilized small labeled datasets and vast amounts of unlabeled data. One example is the variational autoencoder model, a semi-supervised generative model in the form of a deep neural network. The autoencoder assumes that LIBS spectra are generated from a distribution conditioned on the elemental compositions in the sample and some nuisance. The system is broken into two models: one that predicts elemental composition from the spectra and one that generates spectra from compositions that may or may not be seen in the training set. The synthesized spectra show strong agreement with geochemical conventions to express specific compositions. The predictions of composition show improved generalizability to PLS. Deep neural networks have also been used to transfer knowledge from one dataset to another to solve unlabeled data problems. Given that vast amounts of laboratry LIBS spectra have been obtained in the past few years, it is now feasible train a deep net to predict elemental composition from lab spectra. Transfer learning (manifold alignment or calibration transfer) [2] is then used to fine-tune the model

  13. Learning for the Next Generation: Predicting the Usage of Synthetic Learning Environments

    Science.gov (United States)

    Evans, Arthur William, III

    2010-01-01

    The push to further the use of technology in learning has broadened the attempts of many to find innovated ways to aid the new, technologically savvy generation of learners, in acquiring the knowledge needed for their education and training. A critical component to the success of these initiatives is the proper application of the "science of…

  14. Evolutionarily stable learning schedules and cumulative culture in discrete generation models.

    Science.gov (United States)

    Aoki, Kenichi; Wakano, Joe Yuichiro; Lehmann, Laurent

    2012-06-01

    Individual learning (e.g., trial-and-error) and social learning (e.g., imitation) are alternative ways of acquiring and expressing the appropriate phenotype in an environment. The optimal choice between using individual learning and/or social learning may be dictated by the life-stage or age of an organism. Of special interest is a learning schedule in which social learning precedes individual learning, because such a schedule is apparently a necessary condition for cumulative culture. Assuming two obligatory learning stages per discrete generation, we obtain the evolutionarily stable learning schedules for the three situations where the environment is constant, fluctuates between generations, or fluctuates within generations. During each learning stage, we assume that an organism may target the optimal phenotype in the current environment by individual learning, and/or the mature phenotype of the previous generation by oblique social learning. In the absence of exogenous costs to learning, the evolutionarily stable learning schedules are predicted to be either pure social learning followed by pure individual learning ("bang-bang" control) or pure individual learning at both stages ("flat" control). Moreover, we find for each situation that the evolutionarily stable learning schedule is also the one that optimizes the learned phenotype at equilibrium. Copyright © 2012 Elsevier Inc. All rights reserved.

  15. Machine learning and next-generation asteroid surveys

    Science.gov (United States)

    Nugent, Carrie R.; Dailey, John; Cutri, Roc M.; Masci, Frank J.; Mainzer, Amy K.

    2017-10-01

    Next-generation surveys such as NEOCam (Mainzer et al., 2016) will sift through tens of millions of point source detections daily to detect and discover asteroids. This requires new, more efficient techniques to distinguish between solar system objects, background stars and galaxies, and artifacts such as cosmic rays, scattered light and diffraction spikes.Supervised machine learning is a set of algorithms that allows computers to classify data on a training set, and then apply that classification to make predictions on new datasets. It has been employed by a broad range of fields, including computer vision, medical diagnoses, economics, and natural language processing. It has also been applied to astronomical datasets, including transient identification in the Palomar Transient Factory pipeline (Masci et al., 2016), and in the Pan-STARRS1 difference imaging (D. E. Wright et al., 2015).As part of the NEOCam extended phase A work we apply machine learning techniques to the problem of asteroid detection. Asteroid detection is an ideal application of supervised learning, as there is a wealth of metrics associated with each extracted source, and suitable training sets are easily created. Using the vetted NEOWISE dataset (E. L. Wright et al., 2010, Mainzer et al., 2011) as a proof-of-concept of this technique, we applied the python package sklearn. We report on reliability, feature set selection, and the suitability of various algorithms.

  16. Ichthyoplankton Classification Tool using Generative Adversarial Networks and Transfer Learning

    KAUST Repository

    Aljaafari, Nura

    2018-04-15

    The study and the analysis of marine ecosystems is a significant part of the marine science research. These systems are valuable resources for fisheries, improving water quality and can even be used in drugs production. The investigation of ichthyoplankton inhabiting these ecosystems is also an important research field. Ichthyoplankton are fish in their early stages of life. In this stage, the fish have relatively similar shape and are small in size. The currently used way of identifying them is not optimal. Marine scientists typically study such organisms by sending a team that collects samples from the sea which is then taken to the lab for further investigation. These samples need to be studied by an expert and usually end needing a DNA sequencing. This method is time-consuming and requires a high level of experience. The recent advances in AI have helped to solve and automate several difficult tasks which motivated us to develop a classification tool for ichthyoplankton. We show that using machine learning techniques, such as generative adversarial networks combined with transfer learning solves such a problem with high accuracy. We show that using traditional machine learning algorithms fails to solve it. We also give a general framework for creating a classification tool when the dataset used for training is a limited dataset. We aim to build a user-friendly tool that can be used by any user for the classification task and we aim to give a guide to the researchers so that they can follow in creating a classification tool.

  17. Efficient generation of image chips for training deep learning algorithms

    Science.gov (United States)

    Han, Sanghui; Fafard, Alex; Kerekes, John; Gartley, Michael; Ientilucci, Emmett; Savakis, Andreas; Law, Charles; Parhan, Jason; Turek, Matt; Fieldhouse, Keith; Rovito, Todd

    2017-05-01

    Training deep convolutional networks for satellite or aerial image analysis often requires a large amount of training data. For a more robust algorithm, training data need to have variations not only in the background and target, but also radiometric variations in the image such as shadowing, illumination changes, atmospheric conditions, and imaging platforms with different collection geometry. Data augmentation is a commonly used approach to generating additional training data. However, this approach is often insufficient in accounting for real world changes in lighting, location or viewpoint outside of the collection geometry. Alternatively, image simulation can be an efficient way to augment training data that incorporates all these variations, such as changing backgrounds, that may be encountered in real data. The Digital Imaging and Remote Sensing Image Image Generation (DIRSIG) model is a tool that produces synthetic imagery using a suite of physics-based radiation propagation modules. DIRSIG can simulate images taken from different sensors with variation in collection geometry, spectral response, solar elevation and angle, atmospheric models, target, and background. Simulation of Urban Mobility (SUMO) is a multi-modal traffic simulation tool that explicitly models vehicles that move through a given road network. The output of the SUMO model was incorporated into DIRSIG to generate scenes with moving vehicles. The same approach was used when using helicopters as targets, but with slight modifications. Using the combination of DIRSIG and SUMO, we quickly generated many small images, with the target at the center with different backgrounds. The simulations generated images with vehicles and helicopters as targets, and corresponding images without targets. Using parallel computing, 120,000 training images were generated in about an hour. Some preliminary results show an improvement in the deep learning algorithm when real image training data are augmented with

  18. Learning Over Time: Using Rapid Prototyping Generative Analysis Experts and Reduction of Scope to Operationalize Design

    Science.gov (United States)

    2010-05-04

    during the Vietnam Conflict. 67 David A. Kolb , Experiential Learning : Experience as the Source of Learning and Development. (Upper Saddle River, NJ...Essentials for Military Applications. Newport Paper #10. Newport: Newport War College Press. 1996. Kolb , David A. Experiential Learning : Experience... learning over analysis. A broad review of design theory suggests that four techniques - rapid prototyping, generative analysis, use of experts, and

  19. Probabilistic forecasting of wind power generation using extreme learning machine

    DEFF Research Database (Denmark)

    Wan, Can; Xu, Zhao; Pinson, Pierre

    2014-01-01

    an extreme learning machine (ELM)-based probabilistic forecasting method for wind power generation. To account for the uncertainties in the forecasting results, several bootstrapmethods have been compared for modeling the regression uncertainty, based on which the pairs bootstrap method is identified......Accurate and reliable forecast of wind power is essential to power system operation and control. However, due to the nonstationarity of wind power series, traditional point forecasting can hardly be accurate, leading to increased uncertainties and risks for system operation. This paper proposes...... with the best performance. Consequently, a new method for prediction intervals formulation based on theELMand the pairs bootstrap is developed.Wind power forecasting has been conducted in different seasons using the proposed approach with the historical wind power time series as the inputs alone. The results...

  20. Deep generative learning of location-invariant visual word recognition.

    Science.gov (United States)

    Di Bono, Maria Grazia; Zorzi, Marco

    2013-01-01

    It is widely believed that orthographic processing implies an approximate, flexible coding of letter position, as shown by relative-position and transposition priming effects in visual word recognition. These findings have inspired alternative proposals about the representation of letter position, ranging from noisy coding across the ordinal positions to relative position coding based on open bigrams. This debate can be cast within the broader problem of learning location-invariant representations of written words, that is, a coding scheme abstracting the identity and position of letters (and combinations of letters) from their eye-centered (i.e., retinal) locations. We asked whether location-invariance would emerge from deep unsupervised learning on letter strings and what type of intermediate coding would emerge in the resulting hierarchical generative model. We trained a deep network with three hidden layers on an artificial dataset of letter strings presented at five possible retinal locations. Though word-level information (i.e., word identity) was never provided to the network during training, linear decoding from the activity of the deepest hidden layer yielded near-perfect accuracy in location-invariant word recognition. Conversely, decoding from lower layers yielded a large number of transposition errors. Analyses of emergent internal representations showed that word selectivity and location invariance increased as a function of layer depth. Word-tuning and location-invariance were found at the level of single neurons, but there was no evidence for bigram coding. Finally, the distributed internal representation of words at the deepest layer showed higher similarity to the representation elicited by the two exterior letters than by other combinations of two contiguous letters, in agreement with the hypothesis that word edges have special status. These results reveal that the efficient coding of written words-which was the model's learning objective

  1. Deep generative learning of location-invariant visual word recognition

    Directory of Open Access Journals (Sweden)

    Maria Grazia eDi Bono

    2013-09-01

    Full Text Available It is widely believed that orthographic processing implies an approximate, flexible coding of letter position, as shown by relative-position and transposition priming effects in visual word recognition. These findings have inspired alternative proposals about the representation of letter position, ranging from noisy coding across the ordinal positions to relative position coding based on open bigrams. This debate can be cast within the broader problem of learning location-invariant representations of written words, that is, a coding scheme abstracting the identity and position of letters (and combinations of letters from their eye-centred (i.e., retinal locations. We asked whether location-invariance would emerge from deep unsupervised learning on letter strings and what type of intermediate coding would emerge in the resulting hierarchical generative model. We trained a deep network with three hidden layers on an artificial dataset of letter strings presented at five possible retinal locations. Though word-level information (i.e., word identity was never provided to the network during training, linear decoding from the activity of the deepest hidden layer yielded near-perfect accuracy in location-invariant word recognition. Conversely, decoding from lower layers yielded a large number of transposition errors. Analyses of emergent internal representations showed that word selectivity and location invariance increased as a function of layer depth. Conversely, there was no evidence for bigram coding. Finally, the distributed internal representation of words at the deepest layer showed higher similarity to the representation elicited by the two exterior letters than by other combinations of two contiguous letters, in agreement with the hypothesis that word edges have special status. These results reveal that the efficient coding of written words – which was the model’s learning objective – is largely based on letter-level information.

  2. Deep generative learning of location-invariant visual word recognition

    Science.gov (United States)

    Di Bono, Maria Grazia; Zorzi, Marco

    2013-01-01

    It is widely believed that orthographic processing implies an approximate, flexible coding of letter position, as shown by relative-position and transposition priming effects in visual word recognition. These findings have inspired alternative proposals about the representation of letter position, ranging from noisy coding across the ordinal positions to relative position coding based on open bigrams. This debate can be cast within the broader problem of learning location-invariant representations of written words, that is, a coding scheme abstracting the identity and position of letters (and combinations of letters) from their eye-centered (i.e., retinal) locations. We asked whether location-invariance would emerge from deep unsupervised learning on letter strings and what type of intermediate coding would emerge in the resulting hierarchical generative model. We trained a deep network with three hidden layers on an artificial dataset of letter strings presented at five possible retinal locations. Though word-level information (i.e., word identity) was never provided to the network during training, linear decoding from the activity of the deepest hidden layer yielded near-perfect accuracy in location-invariant word recognition. Conversely, decoding from lower layers yielded a large number of transposition errors. Analyses of emergent internal representations showed that word selectivity and location invariance increased as a function of layer depth. Word-tuning and location-invariance were found at the level of single neurons, but there was no evidence for bigram coding. Finally, the distributed internal representation of words at the deepest layer showed higher similarity to the representation elicited by the two exterior letters than by other combinations of two contiguous letters, in agreement with the hypothesis that word edges have special status. These results reveal that the efficient coding of written words—which was the model's learning objective

  3. Supervised learning with restricted training sets: a generating functional analysis

    Energy Technology Data Exchange (ETDEWEB)

    Heimel, J.A.F.; Coolen, A.C.C. [Department of Mathematics, King' s College London, Strand, London (United Kingdom)

    2001-10-26

    We study the dynamics of supervised on-line learning of realizable tasks in feed-forward neural networks. We focus on the regime where the number of examples used for training is proportional to the number of input channels N. Using generating functional techniques from spin glass theory, we are able to average over the composition of the training set and transform the problem for N{yields}{infinity} to an effective single pattern system described completely by the student autocovariance, the student-teacher overlap and the student response function with exact closed equations. Our method applies to arbitrary learning rules, i.e., not necessarily of a gradient-descent type. The resulting exact macroscopic dynamical equations can be integrated without finite-size effects up to any degree of accuracy, but their main value is in providing an exact and simple starting point for analytical approximation schemes. Finally, we show how, in the region of absent anomalous response and using the hypothesis that (as in detailed balance systems) the short-time part of the various operators can be transformed away, one can describe the stationary state of the network successfully by a set of coupled equations involving only four scalar order parameters. (author)

  4. Classification of ECG beats using deep belief network and active learning.

    Science.gov (United States)

    G, Sayantan; T, Kien P; V, Kadambari K

    2018-04-12

    A new semi-supervised approach based on deep learning and active learning for classification of electrocardiogram signals (ECG) is proposed. The objective of the proposed work is to model a scientific method for classification of cardiac irregularities using electrocardiogram beats. The model follows the Association for the Advancement of medical instrumentation (AAMI) standards and consists of three phases. In phase I, feature representation of ECG is learnt using Gaussian-Bernoulli deep belief network followed by a linear support vector machine (SVM) training in the consecutive phase. It yields three deep models which are based on AAMI-defined classes, namely N, V, S, and F. In the last phase, a query generator is introduced to interact with the expert to label few beats to improve accuracy and sensitivity. The proposed approach depicts significant improvement in accuracy with minimal queries posed to the expert and fast online training as tested on the MIT-BIH Arrhythmia Database and the MIT-BIH Supra-ventricular Arrhythmia Database (SVDB). With 100 queries labeled by the expert in phase III, the method achieves an accuracy of 99.5% in "S" versus all classifications (SVEB) and 99.4% accuracy in "V " versus all classifications (VEB) on MIT-BIH Arrhythmia Database. In a similar manner, it is attributed that an accuracy of 97.5% for SVEB and 98.6% for VEB on SVDB database is achieved respectively. Graphical Abstract Reply- Deep belief network augmented by active learning for efficient prediction of arrhythmia.

  5. Accuracy Feedback Improves Word Learning from Context: Evidence from a Meaning-Generation Task

    Science.gov (United States)

    Frishkoff, Gwen A.; Collins-Thompson, Kevyn; Hodges, Leslie; Crossley, Scott

    2016-01-01

    The present study asked whether accuracy feedback on a meaning generation task would lead to improved contextual word learning (CWL). Active generation can facilitate learning by increasing task engagement and memory retrieval, which strengthens new word representations. However, forced generation results in increased errors, which can be…

  6. Development of Web-Based Learning Application for Generation Z

    Science.gov (United States)

    Hariadi, Bambang; Dewiyani Sunarto, M. J.; Sudarmaningtyas, Pantjawati

    2016-01-01

    This study aimed to develop a web-based learning application as a form of learning revolution. The form of learning revolution includes the provision of unlimited teaching materials, real time class organization, and is not limited by time or place. The implementation of this application is in the form of hybrid learning by using Google Apps for…

  7. Multi-task Vector Field Learning.

    Science.gov (United States)

    Lin, Binbin; Yang, Sen; Zhang, Chiyuan; Ye, Jieping; He, Xiaofei

    2012-01-01

    Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously and identifying the shared information among tasks. Most of existing MTL methods focus on learning linear models under the supervised setting. We propose a novel semi-supervised and nonlinear approach for MTL using vector fields. A vector field is a smooth mapping from the manifold to the tangent spaces which can be viewed as a directional derivative of functions on the manifold. We argue that vector fields provide a natural way to exploit the geometric structure of data as well as the shared differential structure of tasks, both of which are crucial for semi-supervised multi-task learning. In this paper, we develop multi-task vector field learning (MTVFL) which learns the predictor functions and the vector fields simultaneously. MTVFL has the following key properties. (1) The vector fields MTVFL learns are close to the gradient fields of the predictor functions. (2) Within each task, the vector field is required to be as parallel as possible which is expected to span a low dimensional subspace. (3) The vector fields from all tasks share a low dimensional subspace. We formalize our idea in a regularization framework and also provide a convex relaxation method to solve the original non-convex problem. The experimental results on synthetic and real data demonstrate the effectiveness of our proposed approach.

  8. 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

  9. Generating region proposals for histopathological whole slide image retrieval.

    Science.gov (United States)

    Ma, Yibing; Jiang, Zhiguo; Zhang, Haopeng; Xie, Fengying; Zheng, Yushan; Shi, Huaqiang; Zhao, Yu; Shi, Jun

    2018-06-01

    Content-based image retrieval is an effective method for histopathological image analysis. However, given a database of huge whole slide images (WSIs), acquiring appropriate region-of-interests (ROIs) for training is significant and difficult. Moreover, histopathological images can only be annotated by pathologists, resulting in the lack of labeling information. Therefore, it is an important and challenging task to generate ROIs from WSI and retrieve image with few labels. This paper presents a novel unsupervised region proposing method for histopathological WSI based on Selective Search. Specifically, the WSI is over-segmented into regions which are hierarchically merged until the WSI becomes a single region. Nucleus-oriented similarity measures for region mergence and Nucleus-Cytoplasm color space for histopathological image are specially defined to generate accurate region proposals. Additionally, we propose a new semi-supervised hashing method for image retrieval. The semantic features of images are extracted with Latent Dirichlet Allocation and transformed into binary hashing codes with Supervised Hashing. The methods are tested on a large-scale multi-class database of breast histopathological WSIs. The results demonstrate that for one WSI, our region proposing method can generate 7.3 thousand contoured regions which fit well with 95.8% of the ROIs annotated by pathologists. The proposed hashing method can retrieve a query image among 136 thousand images in 0.29 s and reach precision of 91% with only 10% of images labeled. The unsupervised region proposing method can generate regions as predictions of lesions in histopathological WSI. The region proposals can also serve as the training samples to train machine-learning models for image retrieval. The proposed hashing method can achieve fast and precise image retrieval with small amount of labels. Furthermore, the proposed methods can be potentially applied in online computer-aided-diagnosis systems. Copyright

  10. Student-generated instructional videos facilitate learning through positive emotions

    OpenAIRE

    Pirhonen, Juhani; Rasi, Päivi

    2017-01-01

    The central focus of this study is a learning method in which university students produce instructional videos about the content matter as part of their learning process, combined with other learning assignments. The rationale for this is to promote a more multimodal pedagogy, and to provide students opportunities for a more learner-centred, motivating, active, engaging and productive role in their learning process. As such we designed a ‘video course’ where the students needed to produce an ...

  11. Student-Generated Instructional Videos Facilitate Learning through Positive Emotions

    Science.gov (United States)

    Pirhonen, Juhani; Rasi, Päivi

    2017-01-01

    The central focus of this study is a learning method in which university students produce instructional videos about the content matter as part of their learning process, combined with other learning assignments. The rationale for this is to promote a more multimodal pedagogy, and to provide students opportunities for a more learner-centred,…

  12. Developing Students' Listening Metacognitive Strategies Using Online Videotext Self-Dictation-Generation Learning Activity

    Science.gov (United States)

    Chang, Ching; Chang, Chih-Kai

    2014-01-01

    The study is based on the use of a flexible learning framework to help students improve information processes underlying strategy instruction in EFL listening. By exploiting the online videotext self-dictation-generation (video-SDG) learning activity implemented on the YouTube caption manager platform, the learning cycle was emphasized to promote…

  13. Rewired: Understanding the iGeneration and the Way They Learn

    Science.gov (United States)

    Rosen, Larry D.

    2010-01-01

    The iGeneration is radically different from any previous generation of students and a variety of existing technologies can be used to engage and excite them in the learning process. The iGeneration is a creative, multimedia generation. They think of the world as a canvas to paint with words, sights, sounds, video, music, web pages, and anything…

  14. Web Log Pre-processing and Analysis for Generation of Learning Profiles in Adaptive E-learning

    Directory of Open Access Journals (Sweden)

    Radhika M. Pai

    2016-03-01

    Full Text Available Adaptive E-learning Systems (AESs enhance the efficiency of online courses in education by providing personalized contents and user interfaces that changes according to learner’s requirements and usage patterns. This paper presents the approach to generate learning profile of each learner which helps to identify the learning styles and provide Adaptive User Interface which includes adaptive learning components and learning material. The proposed method analyzes the captured web usage data to identify the learning profile of the learners. The learning profiles are identified by an algorithmic approach that is based on the frequency of accessing the materials and the time spent on the various learning components on the portal. The captured log data is pre-processed and converted into standard XML format to generate learners sequence data corresponding to the different sessions and time spent. The learning style model adopted in this approach is Felder-Silverman Learning Style Model (FSLSM. This paper also presents the analysis of learner’s activities, preprocessed XML files and generated sequences.

  15. Web Log Pre-processing and Analysis for Generation of Learning Profiles in Adaptive E-learning

    Directory of Open Access Journals (Sweden)

    Radhika M. Pai

    2016-04-01

    Full Text Available Adaptive E-learning Systems (AESs enhance the efficiency of online courses in education by providing personalized contents and user interfaces that changes according to learner’s requirements and usage patterns. This paper presents the approach to generate learning profile of each learner which helps to identify the learning styles and provide Adaptive User Interface which includes adaptive learning components and learning material. The proposed method analyzes the captured web usage data to identify the learning profile of the learners. The learning profiles are identified by an algorithmic approach that is based on the frequency of accessing the materials and the time spent on the various learning components on the portal. The captured log data is pre-processed and converted into standard XML format to generate learners sequence data corresponding to the different sessions and time spent. The learning style model adopted in this approach is Felder-Silverman Learning Style Model (FSLSM. This paper also presents the analysis of learner’s activities, preprocessed XML files and generated sequences.

  16. Advanced Machine Learning for Classification, Regression, and Generation in Jet Physics

    CERN Multimedia

    CERN. Geneva

    2017-01-01

    There is a deep connection between machine learning and jet physics - after all, jets are defined by unsupervised learning algorithms. Jet physics has been a driving force for studying modern machine learning in high energy physics. Domain specific challenges require new techniques to make full use of the algorithms. A key focus is on understanding how and what the algorithms learn. Modern machine learning techniques for jet physics are demonstrated for classification, regression, and generation. In addition to providing powerful baseline performance, we show how to train complex models directly on data and to generate sparse stacked images with non-uniform granularity.

  17. Building a New Generation of Learning: Conversations to Catalyze Our Construction

    Science.gov (United States)

    Milliron, Mark David; Plinske, Kathleen; Noonan-Terry, Coral

    2008-01-01

    Rather than focus primarily on the next generation of learners, the authors argue we are best served to focus on building out our on-ground and online infrastructures for a new generation of learning--blending multiple learning modes, technologies, and techniques over the course of the next 15-20 years to serve the diverse array of students from…

  18. The "Tse Tsa Watle" Speaker Series: An Example of Ensemble Leadership and Generative Adult Learning

    Science.gov (United States)

    McKendry, Virginia

    2017-01-01

    This chapter examines an Indigenous speaker series formed to foster intercultural partnerships at a Canadian university. Using ensemble leadership and generative learning theories to make sense of the project, the author argues that ensemble leadership is key to designing the generative learning adult learners need in an era of ambiguity.

  19. The Effects of Student Question-Generation with Online Prompts on Learning

    Science.gov (United States)

    Yu, Fu-Yun; Pan, Kuan-Jung

    2014-01-01

    The focus of this study was to investigate the effects of student-question generation with online prompts on student academic achievement, question-generation performance, learning satisfaction and learning anxiety. This study adopted a quasi-experimental research design. Two classes of eighth grade students (N = 64) from one middle school…

  20. Entrepreneurial learning requires action on the meaning generated

    DEFF Research Database (Denmark)

    Brink, Tove; Madsen, Svend Ole

    2015-01-01

    Purpose: This paper reveals how managers of small- and medium-sized enterprises (SMEs) can utilise their participation in research-based training to enable innovation and growth. Design/methodology/approach: Action research and action learning from a longitudinal study of 10 SME managers...... in the wind turbine industry are conducted to reveal SME managers learning and the impact of the application of learning in the wind turbine industry. Findings: The findings of this study show that SME managers employ a practice-shaped holistic cross-disciplinary approach to learning. This learning approach...... is supported by theory dissemination and collaboration on the business challenges perceived. Open mindedness to new learning by SME managers and to cross-disciplinary collaboration with SME managers by university facilitators/ researchers is required. Research limitations/implications: The research...

  1. Smart e-Learning: A greater perspective; from the fourth to the fifth generation e-learning

    Directory of Open Access Journals (Sweden)

    Shehab A. Gamalel-Din

    2010-06-01

    This research has focused on improving the effectiveness and quality of web-based e-learning through adapting the course authoring and delivery to match each individual student skills and preferences. In this article, we shed lights on the vision and status of the eight-year Smart e-Learning environment project: The main objective of this project is to employ AI techniques to advance e-learning forward towards the fifth generation e-learning as we envision it. The idea is to embed instructional design theories as well as learning and cognition theories into e-learning environments to provide a more intelligent and, hence, more effective one-to-one e-learning environments. This article only gives a high level overview; however, the more interested reader will be referred to articles describing the work in more technical details.

  2. Combining generative and discriminative representation learning for lung CT analysis with convolutional restricted Boltzmann machines

    DEFF Research Database (Denmark)

    van Tulder, Gijs; de Bruijne, Marleen

    2016-01-01

    The choice of features greatly influences the performance of a tissue classification system. Despite this, many systems are built with standard, predefined filter banks that are not optimized for that particular application. Representation learning methods such as restricted Boltzmann machines may...... outperform these standard filter banks because they learn a feature description directly from the training data. Like many other representation learning methods, restricted Boltzmann machines are unsupervised and are trained with a generative learning objective; this allows them to learn representations from...... unlabeled data, but does not necessarily produce features that are optimal for classification. In this paper we propose the convolutional classification restricted Boltzmann machine, which combines a generative and a discriminative learning objective. This allows it to learn filters that are good both...

  3. Is there a digital generation gap for e-learning in plastic surgery?

    Science.gov (United States)

    Stevens, Roger J G; Hamilton, Neil M

    2012-01-01

    Some authors have claimed that those plastic surgeons born between 1965 and 1979 (generation X, or Gen-X) are more technologically able than those born between 1946 and 1964 (Baby Boomers, or BB). Those born after 1980, which comprise generation Y (Gen-Y), might be the most technologically able and most demanding for electronic learning (e-learning) to support their education and training in plastic surgery. These differences might represent a "digital generation gap" and would have practical and financial implications for the development of e-learning. The aim of this study was to survey plastic surgeons on their experience and preferences in e-learning in plastic surgery and to establish whether there was a difference between different generations. Online survey (e-survey) of plastic surgeons within the UK and Ireland was used for this study. In all, 624 plastic surgeons were invited by e-mail to complete an e-survey anonymously for their experience of e-learning in plastic surgery, whether they would like access to e-learning and, if so, whether this should this be provided nationally, locally, or not at all. By stratifying plastic surgeons into three generations (BB, Gen-X, and Gen-Y), the responses between generations were compared using the χ(2)-test for linear trend. A p value learning. These findings refute the claim that there are differences in the experience of e-learning of plastic surgeons by generation. Furthermore, there is no evidence that there are differences in whether there should be access to e-learning and how e-learning should be provided for different generations of plastic surgeons. Copyright © 2012 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

  4. Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping

    CSIR Research Space (South Africa)

    Davel, MH

    2004-10-01

    Full Text Available The authors focus on factors related to the underlying rule-extraction algorithms, and demonstrate variants of the Dynamically Expanding Context algorithm, which are beneficial for this application. They show that continuous updating of the learned...

  5. The comparative effect of individually-generated vs. collaboratively-generated computer-based concept mapping on science concept learning

    Science.gov (United States)

    Kwon, So Young

    Using a quasi-experimental design, the researcher investigated the comparative effects of individually-generated and collaboratively-generated computer-based concept mapping on middle school science concept learning. Qualitative data were analyzed to explain quantitative findings. One hundred sixty-one students (74 boys and 87 girls) in eight, seventh grade science classes at a middle school in Southeast Texas completed the entire study. Using prior science performance scores to assure equivalence of student achievement across groups, the researcher assigned the teacher's classes to one of the three experimental groups. The independent variable, group, consisted of three levels: 40 students in a control group, 59 students trained to individually generate concept maps on computers, and 62 students trained to collaboratively generate concept maps on computers. The dependent variables were science concept learning as demonstrated by comprehension test scores, and quality of concept maps created by students in experimental groups as demonstrated by rubric scores. Students in the experimental groups received concept mapping training and used their newly acquired concept mapping skills to individually or collaboratively construct computer-based concept maps during study time. The control group, the individually-generated concept mapping group, and the collaboratively-generated concept mapping group had equivalent learning experiences for 50 minutes during five days, excepting that students in a control group worked independently without concept mapping activities, students in the individual group worked individually to construct concept maps, and students in the collaborative group worked collaboratively to construct concept maps during their study time. Both collaboratively and individually generated computer-based concept mapping had a positive effect on seventh grade middle school science concept learning but neither strategy was more effective than the other. However

  6. Organisational Learning as an Emerging Process: The Generative Role of Digital Tools in Informal Learning Practices

    Science.gov (United States)

    Za, Stefano; Spagnoletti, Paolo; North-Samardzic, Andrea

    2014-01-01

    Increasing attention is paid to organisational learning, with the success of contemporary organisations strongly contingent on their ability to learn and grow. Importantly, informal learning is argued to be even more significant than formal learning initiatives. Given the widespread use of digital technologies in the workplace, what requires…

  7. On the Use of Extended TAM to Assess Students' Acceptance and Intent to Use Third-Generation Learning Management Systems

    Science.gov (United States)

    Ros, Salvador; Hernández, Roberto; Caminero, Agustín; Robles, Antonio; Barbero, Isabel; Maciá, Araceli; Holgado, Francisco Pablo

    2015-01-01

    Service-oriented e-learning platforms can be considered as a third generation of learning management systems (LMSs). As opposed to the previous generations, consisting of ad hoc solutions and traditional LMS, this new technology contemplates e-learning systems as services that can be integrated into different learning scenarios. This paper shows…

  8. Generations at School: Building an Age-Friendly Learning Community

    Science.gov (United States)

    Lovely, Suzette; Buffum, Austin G.; Barth, Roland S.

    2007-01-01

    Today's workforce comprises distinct generational cohorts-Veterans, Baby Boomers, Gen-Xers, and Millennials. "Generations at School" provides educators with the knowledge and tools to create and sustain true collaboration, teamwork, and consensus. Suzette Lovely and Austin G. Buffum introduce the traits and tipping points of these diverse age…

  9. Web-Based Collaborative Learning: An Assessment of a Question-Generation Approach

    National Research Council Canada - National Science Library

    Belanich, James

    2003-01-01

    .... In research reported here, students used a learning aid for collaborative question generation called Army TEAMThink, a commercial program modified for Army use under a TRADOC Delivery Order contract...

  10. Scenario analysis for estimating the learning rate of photovoltaic power generation based on learning curve theory in South Korea

    International Nuclear Information System (INIS)

    Hong, Sungjun; Chung, Yanghon; Woo, Chungwon

    2015-01-01

    South Korea, as the 9th largest energy consuming in 2013 and the 7th largest greenhouse gas emitting country in 2011, established ‘Low Carbon Green Growth’ as the national vision in 2008, and is announcing various active energy policies that are set to gain the attention of the world. In this paper, we estimated the decrease of photovoltaic power generation cost in Korea based on the learning curve theory. Photovoltaic energy is one of the leading renewable energy sources, and countries all over the world are currently expanding R and D, demonstration and deployment of photovoltaic technology. In order to estimate the learning rate of photovoltaic energy in Korea, both conventional 1FLC (one-factor learning curve), which considers only the cumulative power generation, and 2FLC, which also considers R and D investment were applied. The 1FLC analysis showed that the cost of power generation decreased by 3.1% as the cumulative power generation doubled. The 2FCL analysis presented that the cost decreases by 2.33% every time the cumulative photovoltaic power generation is doubled and by 5.13% every time R and D investment is doubled. Moreover, the effect of R and D investment on photovoltaic technology took after around 3 years, and the depreciation rate of R and D investment was around 20%. - Highlights: • We analyze the learning effects of photovoltaic energy technology in Korea. • In order to calculate the learning rate, we use 1FLC (one-factor learning curve) and 2FLC methods, respectively. • 1FLC method considers only the cumulative power generation. • 2FLC method considers both cumulative power generation and knowledge stock. • We analyze a variety of scenarios by time lag and depreciation rate of R and D investment

  11. High Temperature Gas-Cooled Reactors Lessons Learned Applicable to the Next Generation Nuclear Plant

    International Nuclear Information System (INIS)

    Beck, J.M.; Collins, J.W.; Garcia, C.B.; Pincock, L.F.

    2010-01-01

    High Temperature Gas Reactors (HTGR) have been designed and operated throughout the world over the past five decades. These seven HTGRs are varied in size, outlet temperature, primary fluid, and purpose. However, there is much the Next Generation Nuclear Plant (NGNP) has learned and can learn from these experiences. This report captures these various experiences and documents the lessons learned according to the physical NGNP hardware (i.e., systems, subsystems, and components) affected thereby.

  12. Model of e-learning with electronic educational resources of new generation

    OpenAIRE

    A. V. Loban; D. A. Lovtsov

    2017-01-01

    Purpose of the article: improving of scientific and methodical base of the theory of the е-learning of variability. Methods used: conceptual and logical modeling of the е-learning of variability process with electronic educational resource of new generation and system analysis of the interconnection of the studied subject area, methods, didactics approaches and information and communication technologies means. Results: the formalization complex model of the е-learning of variability with elec...

  13. Learning to Generate Dialogue: Theory, Practice, and Evaluation

    DEFF Research Database (Denmark)

    McCallie, Ellen; Simonsson, Elin; Gammon, Ben

    2007-01-01

    Over the past decade in the UK, communities of scientists, governmental bodies, and informal learning organizations have increasingly promoted public engagement with science. One of the most visible features of these efforts within museums is the staging of adult-focused, face-to-face forums...

  14. Toward a Generative Model of the Teaching-Learning Process.

    Science.gov (United States)

    McMullen, David W.

    Until the rise of cognitive psychology, models of the teaching-learning process (TLP) stressed external rather than internal variables. Models remained general descriptions until control theory introduced explicit system analyses. Cybernetic models emphasize feedback and adaptivity but give little attention to creativity. Research on artificial…

  15. Generating a Spanish Affective Dictionary with Supervised Learning Techniques

    Science.gov (United States)

    Bermudez-Gonzalez, Daniel; Miranda-Jiménez, Sabino; García-Moreno, Raúl-Ulises; Calderón-Nepamuceno, Dora

    2016-01-01

    Nowadays, machine learning techniques are being used in several Natural Language Processing (NLP) tasks such as Opinion Mining (OM). OM is used to analyse and determine the affective orientation of texts. Usually, OM approaches use affective dictionaries in order to conduct sentiment analysis. These lexicons are labeled manually with affective…

  16. Creating Next Generation Blended Learning Environments Using Mixed Reality, Video Games and Simulations

    Science.gov (United States)

    Kirkley, Sonny E.; Kirkley, Jamie R.

    2005-01-01

    In this article, the challenges and issues of designing next generation learning environments using current and emerging technologies are addressed. An overview of the issues is provided as well as design principles that support the design of instruction and the overall learning environment. Specific methods for creating cognitively complex,…

  17. Learning and inference using complex generative models in a spatial localization task.

    Science.gov (United States)

    Bejjanki, Vikranth R; Knill, David C; Aslin, Richard N

    2016-01-01

    A large body of research has established that, under relatively simple task conditions, human observers integrate uncertain sensory information with learned prior knowledge in an approximately Bayes-optimal manner. However, in many natural tasks, observers must perform this sensory-plus-prior integration when the underlying generative model of the environment consists of multiple causes. Here we ask if the Bayes-optimal integration seen with simple tasks also applies to such natural tasks when the generative model is more complex, or whether observers rely instead on a less efficient set of heuristics that approximate ideal performance. Participants localized a "hidden" target whose position on a touch screen was sampled from a location-contingent bimodal generative model with different variances around each mode. Over repeated exposure to this task, participants learned the a priori locations of the target (i.e., the bimodal generative model), and integrated this learned knowledge with uncertain sensory information on a trial-by-trial basis in a manner consistent with the predictions of Bayes-optimal behavior. In particular, participants rapidly learned the locations of the two modes of the generative model, but the relative variances of the modes were learned much more slowly. Taken together, our results suggest that human performance in a more complex localization task, which requires the integration of sensory information with learned knowledge of a bimodal generative model, is consistent with the predictions of Bayes-optimal behavior, but involves a much longer time-course than in simpler tasks.

  18. Generation of Tutorial Dialogues: Discourse Strategies for Active Learning

    National Research Council Canada - National Science Library

    Evans, Martha

    1998-01-01

    With the support of the Cognitive Science Program of ONR, we are developing the capability to generate complex natural language tutorial dialogues for an intelligent tutoring system designed to help...

  19. Handwriting generates variable visual output to facilitate symbol learning.

    Science.gov (United States)

    Li, Julia X; James, Karin H

    2016-03-01

    Recent research has demonstrated that handwriting practice facilitates letter categorization in young children. The present experiments investigated why handwriting practice facilitates visual categorization by comparing 2 hypotheses: that handwriting exerts its facilitative effect because of the visual-motor production of forms, resulting in a direct link between motor and perceptual systems, or because handwriting produces variable visual instances of a named category in the environment that then changes neural systems. We addressed these issues by measuring performance of 5-year-old children on a categorization task involving novel, Greek symbols across 6 different types of learning conditions: 3 involving visual-motor practice (copying typed symbols independently, tracing typed symbols, tracing handwritten symbols) and 3 involving visual-auditory practice (seeing and saying typed symbols of a single typed font, of variable typed fonts, and of handwritten examples). We could therefore compare visual-motor production with visual perception both of variable and similar forms. Comparisons across the 6 conditions (N = 72) demonstrated that all conditions that involved studying highly variable instances of a symbol facilitated symbol categorization relative to conditions where similar instances of a symbol were learned, regardless of visual-motor production. Therefore, learning perceptually variable instances of a category enhanced performance, suggesting that handwriting facilitates symbol understanding by virtue of its environmental output: supporting the notion of developmental change though brain-body-environment interactions. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

  20. Handwriting generates variable visual input to facilitate symbol learning

    Science.gov (United States)

    Li, Julia X.; James, Karin H.

    2015-01-01

    Recent research has demonstrated that handwriting practice facilitates letter categorization in young children. The present experiments investigated why handwriting practice facilitates visual categorization by comparing two hypotheses: That handwriting exerts its facilitative effect because of the visual-motor production of forms, resulting in a direct link between motor and perceptual systems, or because handwriting produces variable visual instances of a named category in the environment that then changes neural systems. We addressed these issues by measuring performance of 5 year-old children on a categorization task involving novel, Greek symbols across 6 different types of learning conditions: three involving visual-motor practice (copying typed symbols independently, tracing typed symbols, tracing handwritten symbols) and three involving visual-auditory practice (seeing and saying typed symbols of a single typed font, of variable typed fonts, and of handwritten examples). We could therefore compare visual-motor production with visual perception both of variable and similar forms. Comparisons across the six conditions (N=72) demonstrated that all conditions that involved studying highly variable instances of a symbol facilitated symbol categorization relative to conditions where similar instances of a symbol were learned, regardless of visual-motor production. Therefore, learning perceptually variable instances of a category enhanced performance, suggesting that handwriting facilitates symbol understanding by virtue of its environmental output: supporting the notion of developmental change though brain-body-environment interactions. PMID:26726913

  1. Leading and Managing Disparate Generations in Cross-Cultural Learning Organizations

    Science.gov (United States)

    Mujtaba, Bahaudin; Thomas, Gimol

    2005-01-01

    The enclosed literature focuses on learning about the various generations of the workforce and techniques that employers can utilize to organize collaborative teams in today's multigenerational and multicultural workplaces. Trainers and teachers can use this material to provide effective skills for managers that deal with a multi-generation of…

  2. Generation Y Students: Appropriate Learning Styles and Teaching Approaches in the Economic and Management Sciences Faculty

    Science.gov (United States)

    Wessels, P. L.; Steenkamp, L. P.

    2009-01-01

    Generation Y students (born after 1982) have developed a different set of attitudes and aptitudes as a result of growing up in an IT and media-rich environment. This article has two objectives: firstly to discuss the learning styles preferred by generation Y students in order to identify the effect of these preferences on tertiary education in…

  3. Learning Technology through Three Generations of Technology Enhanced Distance Education Pedagogy

    Science.gov (United States)

    Anderson, Terry; Dron, Jon

    2012-01-01

    This paper updates earlier work in which we defined three generations of distance education pedagogy. We then describe emerging technologies that are most conducive to instructional designs that evolve with each generation. Finally we discuss matching the pedagogies with learning outcomes. (Contains 3 figures.)

  4. Metacognitive Unawareness of the Errorful Generation Benefit and Its Effects on Self-Regulated Learning

    Science.gov (United States)

    Yang, Chunliang; Potts, Rosalind; Shanks, David R.

    2017-01-01

    Generating errors followed by corrective feedback enhances retention more effectively than does reading--the benefit of errorful generation--but people tend to be unaware of this benefit. The current research explored this metacognitive unawareness, its effect on self-regulated learning, and how to alleviate or reverse it. People's beliefs about…

  5. Generational Learning Style Preferences Based on Computer-Based Healthcare Training

    Science.gov (United States)

    Knight, Michaelle H.

    2016-01-01

    Purpose. The purpose of this mixed-method study was to determine the degree of perceived differences for auditory, visual and kinesthetic learning styles of Traditionalist, Baby Boomers, Generation X and Millennial generational healthcare workers participating in technology-assisted healthcare training. Methodology. This mixed-method research…

  6. Learning to Generate Dialogue: Theory, Practice, and Evaluation

    DEFF Research Database (Denmark)

    McCallie, Ellen; Simonsson, Elin; Gammon, Ben

    2007-01-01

    -commonly called dialogue events-that bring scientific and technical experts, social scientists, and policymakers into discussion with members of the public about contemporary science-based issues. This article clarifies the difference between non-policy-informing dialogue events and other interactions in museums......Over the past decade in the UK, communities of scientists, governmental bodies, and informal learning organizations have increasingly promoted public engagement with science. One of the most visible features of these efforts within museums is the staging of adult-focused, face-to-face forums...... of engagement through dialogue related to science and society...

  7. Generative Models in Deep Learning: Constraints for Galaxy Evolution

    Science.gov (United States)

    Turp, Maximilian Dennis; Schawinski, Kevin; Zhang, Ce; Weigel, Anna K.

    2018-01-01

    New techniques are essential to make advances in the field of galaxy evolution. Recent developments in the field of artificial intelligence and machine learning have proven that these tools can be applied to problems far more complex than simple image recognition. We use these purely data driven approaches to investigate the process of star formation quenching. We show that Variational Autoencoders provide a powerful method to forward model the process of galaxy quenching. Our results imply that simple changes in specific star formation rate and bulge to disk ratio cannot fully describe the properties of the quenched population.

  8. Helping the Me Generation Decenter: Service Learning with Refugees

    Science.gov (United States)

    Hawkins, LouAnne B.; Kaplan, Leslie G.

    2016-01-01

    Recent research has empirically demonstrated that young adults today are different from prior generations in their decreased empathy, increased narcissism, and decreased civic engagement. The formative years of young adulthood are a critical period for the development of civic values and civil ideologies, a time when college-age adults need to…

  9. Denoising by semi-supervised kernel PCA preimaging

    DEFF Research Database (Denmark)

    Hansen, Toke Jansen; Abrahamsen, Trine Julie; Hansen, Lars Kai

    2014-01-01

    Kernel Principal Component Analysis (PCA) has proven a powerful tool for nonlinear feature extraction, and is often applied as a pre-processing step for classification algorithms. In denoising applications Kernel PCA provides the basis for dimensionality reduction, prior to the so-called pre-imag...

  10. Semi-supervised prediction of gene regulatory networks using ...

    Indian Academy of Sciences (India)

    2015-09-28

    Sep 28, 2015 ... Use of computational methods to predict gene regulatory networks (GRNs) from gene expression data is a challenging ... two types of methods differ primarily based on whether ..... negligible, allowing us to draw the qualitative conclusions .... research will be conducted to develop additional biologically.

  11. Effective Modification of a Nonprescription Medicines Course to Optimize Learning of Millennial Generation Students

    Directory of Open Access Journals (Sweden)

    Bella H Mehta

    2013-01-01

    Full Text Available Objective: To describe examples of effective teaching strategies utilized within a required nonprescription therapeutics course, in order to accommodate learning characteristics of Millennials. Case Study: Instructors identified unique characteristics of Millennial generation students through literature review and focused educational workshops. These characteristics include the desire for active learning where didactic lectures make a connection to life, the incorporation of technology, and assignments that focus on team work. Course modifications were then made based on these characteristics including redesign of large group course lectures with incorporation of patient cases, inclusion of a variety of online components including the opportunity to provide course feedback, and active learning small group projects within workshop sections. Evaluation:Student evaluation of the course and instructors significantly improved after introducing changes to the course compared to previous years. Each component of the student evaluation resulted in a statistically significant change in mean score. Verbal and written evaluations indicated a very positive learning experience for students. Grade mean (3.3 vs. 3.8, p Conclusions: By identifying characteristics of Millennial generation student learners, traditional teaching methods can be modified in order to enhance retention of material and optimize their learning process. Course changes improved the learning experience for students and instructors. Instructors' willingness to evaluate generational differences and adapt teaching enhances the learning experiences in the classroom for both students and instructors.   Type: Case Study

  12. Preferences for Learning and Skill Development at Work: Comparison of Two Generations

    Directory of Open Access Journals (Sweden)

    Mariya Karaivanova

    2014-09-01

    Full Text Available The changing economic conditions of the current dynamic and insecure labour market make learning a constant preoccupation of the workforce with view of meeting the growing qualification demands. These demands are likely to influence the work preferences of both young people now entering the labour market and older people with established career paths. Research findings suggest that the younger generation exhibits a stronger orientation towards learning and skill development as compared to the older generations. Moreover, studies show that the younger people are more ready to leave the organization when they have better learning opportunities elsewhere. The present study aims at establishing how preferences for learning and skill development in the workplace relate to a number of job and organizational characteristics. Particular focus is placed on the predictive capacity of perceived learning opportunities towards the tendency to leave the organization for either of the two generations. The study addresses work preferences of two generations in the Bulgarian labour market. To this aim, 121 respondents answered a 55-item questionnaire consisting of newly developed scales as well as scales based on or adopted from standardized instruments such as the Extended Delft Measurement Kit (Roe et al., 2000. Contrary to findings from previous research done in countries with different cultural and socio-economic background, the older people in our sample were more eager to learn and more ready to leave their organization in pursuit of better opportunities, as compared to the younger generation. Another noteworthy conclusion is that the preferences for learning and development form different patterns in each of the two age groups and are expressed in a different way for each of the two generations.

  13. Lessons learned from first generation nuclear plant probabalistic risk assessments

    International Nuclear Information System (INIS)

    Garrick, B.J.

    1984-01-01

    The paper by Garrick summarizes the state-of-the-art in what are perhaps the most archetypical probabilistic risk assessments (PRAs). Because of its unique regulatory environment and because of the high levels of perceived (not necessarily actual) risk, the nuclear industry more than any other has been concerned with quantitative risk analysis. Garrick's paper summarizes the lessons learned from ten PRA's conducted in the nuclear industry, including six that can be characterized as full-scope risk studies. Most of the quantitative data, though, came from two especially thorough studies done for the Zion and Indian Point power plants, operated by Commonwealth Edison and Consolidated Edison respectively. The principal conclusions of the Garrick survey are that the public risk (from radiation release) is now known to be very small for commercial nuclear power plants, but that the risk to utilities (from core damage) is somewhat larger. Significant radiation releases require both core meltdown -- an event occurring only about once every 10,000 reactor-years -- and containment failure, occurring only about once in every hundred meltdowns

  14. Innovating Training through Immersive Environments: Generation Y, Exploratory Learning, and Serious Games

    Science.gov (United States)

    Gendron, Gerald

    2012-01-01

    Over the next decade, those entering Service and Joint Staff positions within the military will come from a different generation than the current leadership. They will come from Generation Y and have differing preferences for learning. Immersive learning environments like serious games and virtual world initiatives can complement traditional training methods to provide a better overall training program for staffs. Generation Y members desire learning methods which are relevant and interactive, regardless of whether they are delivered over the internet or in person. This paper focuses on a project undertaken to assess alternative training methods to teach special operations staffs. It provides a summary of the needs analysis used to consider alternatives and to better posture the Department of Defense for future training development.

  15. Why formal learning theory matters for cognitive science.

    Science.gov (United States)

    Fulop, Sean; Chater, Nick

    2013-01-01

    This article reviews a number of different areas in the foundations of formal learning theory. After outlining the general framework for formal models of learning, the Bayesian approach to learning is summarized. This leads to a discussion of Solomonoff's Universal Prior Distribution for Bayesian learning. Gold's model of identification in the limit is also outlined. We next discuss a number of aspects of learning theory raised in contributed papers, related to both computational and representational complexity. The article concludes with a description of how semi-supervised learning can be applied to the study of cognitive learning models. Throughout this overview, the specific points raised by our contributing authors are connected to the models and methods under review. Copyright © 2013 Cognitive Science Society, Inc.

  16. Learning a generative probabilistic grammar of experience: a process-level model of language acquisition.

    Science.gov (United States)

    Kolodny, Oren; Lotem, Arnon; Edelman, Shimon

    2015-03-01

    We introduce a set of biologically and computationally motivated design choices for modeling the learning of language, or of other types of sequential, hierarchically structured experience and behavior, and describe an implemented system that conforms to these choices and is capable of unsupervised learning from raw natural-language corpora. Given a stream of linguistic input, our model incrementally learns a grammar that captures its statistical patterns, which can then be used to parse or generate new data. The grammar constructed in this manner takes the form of a directed weighted graph, whose nodes are recursively (hierarchically) defined patterns over the elements of the input stream. We evaluated the model in seventeen experiments, grouped into five studies, which examined, respectively, (a) the generative ability of grammar learned from a corpus of natural language, (b) the characteristics of the learned representation, (c) sequence segmentation and chunking, (d) artificial grammar learning, and (e) certain types of structure dependence. The model's performance largely vindicates our design choices, suggesting that progress in modeling language acquisition can be made on a broad front-ranging from issues of generativity to the replication of human experimental findings-by bringing biological and computational considerations, as well as lessons from prior efforts, to bear on the modeling approach. Copyright © 2014 Cognitive Science Society, Inc.

  17. Developing students' listening metacognitive strategies using online videotext self-dictation-generation learning activity

    Directory of Open Access Journals (Sweden)

    Ching Chang

    2014-03-01

    Full Text Available The study is based on the use of a flexible learning framework to help students improve information processes underlying strategy instruction in EFL listening. By exploiting the online videotext self-dictation-generation (video-SDG learning activity implemented on the YouTube caption manager platform, the learning cycle was emphasized to promote metacognitive listening development. Two theories were used to guide the online video-SDG learning activity: a student question-generation method and a metacognitive listening training model in a second language (L2. The study investigated how college students in the online video-SDG activity enhanced the use of listening strategies by developing metacognitive listening skills. With emphasis on the metacognitive instructional process, students could promote their listening comprehension of advertisement videos (AVs. Forty-eight students were recruited to participate in the study. Through data collected from the online learning platform, questionnaires, a focus-group interview, and pre- and post- achievement tests, the results revealed that the online video-SDG learning activity could effectively engage students in reflecting upon their perceptions of specific problems countered, listening strategy usages, and strategic knowledge exploited in the metacognitive instructional process. The importance of employing cost-effective online video-SGD learning activities is worthy of consideration in developing students’ metacognitive listening knowledge for enhancing EFL listening strategy instruction.

  18. Didactic Networks: A Proposal for e-learning Content Generation

    Directory of Open Access Journals (Sweden)

    F. Javier Del Alamo

    2010-12-01

    Full Text Available The Didactic Networks proposed in this paper are based on previous publications in the field of the RSR (Rhetorical-Semantic Relations. The RSR is a set of primitive relations used for building a specific kind of semantic networks for artificial intelligence applications on the web: the RSN (Rhetorical-Semantic Networks. We bring into focus the RSR application in the field of elearning, by defining Didactic Networks as a new set of semantic patterns oriented to the development of elearning applications. The different lines we offer in our research fall mainly into three levels: (1 The most basic one is in the field of computational linguistics and related to Logical Operations on RSR (RSR Inverses and plurals, RSR combinations, etc, once they have been created. The application of Walter Bosma's results regarding rhetorical distance application and treatment as semantic weighted networks is one of the important issues here. (2 In parallel, we have been working on the creation of a knowledge representation and storage model and data architecture capable of supporting the definition of knowledge networks based on RSR. (3 The third strategic line is in the meso-level, the formulation of a molecular structure of knowledge based on the most frequently used patterns. The main contribution at this level is the set of Fundamental Cognitive Networks (FCN as an application of Novak's mental maps proposal. This paper is part of this third intermediate level, and the Fundamental Didactic Networks (FDN are the result of the application of rhetorical theory procedures to the instructional theory. We have formulated a general set of RSR capable of building discourse, making it possible to express any concept, procedure or principle in terms of knowledge nodes and RSRs. The Instructional knowledge can then be elaborated in the same way. This network structure expressing the instructional knowledge in terms of RSR makes the objective of developing web-learning

  19. Generational influences in academic emergency medicine: teaching and learning, mentoring, and technology (part I).

    Science.gov (United States)

    Mohr, Nicholas M; Moreno-Walton, Lisa; Mills, Angela M; Brunett, Patrick H; Promes, Susan B

    2011-02-01

    For the first time in history, four generations are working together-traditionalists, baby boomers, generation Xers (Gen Xers), and millennials. Members of each generation carry with them a unique perspective of the world and interact differently with those around them. Through a review of the literature and consensus by modified Delphi methodology of the Society for Academic Emergency Medicine Aging and Generational Issues Task Force, the authors have developed this two-part series to address generational issues present in academic emergency medicine (EM). Understanding generational characteristics and mitigating strategies can help address some common issues encountered in academic EM. Through recognition of the unique characteristics of each of the generations with respect to teaching and learning, mentoring, and technology, academicians have the opportunity to strategically optimize interactions with one another. © 2011 by the Society for Academic Emergency Medicine.

  20. Generational Influences in Academic Emergency Medicine: Teaching and Learning, Mentoring, and Technology (Part I)

    Science.gov (United States)

    Mohr, Nicholas M.; Moreno-Walton, Lisa; Mills, Angela M.; Brunett, Patrick H.; Promes, Susan B.

    2010-01-01

    For the first time in history, four generations are working together – Traditionalists, Baby Boomers, Generation Xers, and Millennials. Members of each generation carry with them a unique perspective of the world and interact differently with those around them. Through a review of the literature and consensus by modified Delphi methodology of the Society for Academic Emergency Medicine (SAEM) Aging and Generational Issues Task Force, the authors have developed this two-part series to address generational issues present in academic emergency medicine (EM). Understanding generational characteristics and mitigating strategies can help address some common issues encountered in academic EM. Through recognition of the unique characteristics of each of the generations with respect to teaching and learning, mentoring, and technology, academicians have the opportunity to strategically optimize interactions with one another. PMID:21314779

  1. Lessons learned from tubes pulled from French steam generators

    International Nuclear Information System (INIS)

    Berge, Ph.; Boursier, J.M.; Dallery, D.; De Keroulas, F.; Rouillon, Y.

    1998-01-01

    Since 1981, the Chinon Hot Laboratory has completed more than 380 metallurgical examinations of pulled French steam generator tubes. Electricite de France decided to perform such investigations from the very outset of the French nuclear program, in order to contribute to nuclear power plant safety. The main reasons for withdrawing tubes are to evaluate the degradation, to validate non destructive examination (NDE) techniques, to gain a better understanding of cracking phenomena, and to ensure that the criteria on which plugging operations are based remain conservative. Considerable experience has been accumulated in the field of primary water stress corrosion cracking (PWSCC), OD (secondary) side corrosion, leak and burst tests, and various tube plugging techniques. This paper focuses on the PWSCC phenomenon and on the secondary side corrosion process, and in particular, attempts to correlate French data from pulled tubes with the results of fundamental R and D studies. Finally, within the framework of the Nuclear Power Plant Safety and Maintenance Policy, all these results are discussed in terms of optimization of the field inspection of tube bundles and plugging criteria. (author)

  2. Generation Y Health Professional Students ’ Preferred Teaching and Learning Approaches: A Systematic Review

    Directory of Open Access Journals (Sweden)

    Caroline Mary Hills

    2017-01-01

    Full Text Available Generation Y or Millennials are descriptors for those born between 1982 and 2000. This cohort has grown up in the digital age and is purported to have different learning preferences from previous generations. Students are important stakeholders in identifying their preferred teaching and learning approaches in health professional programs. This study aimed to identify, appraise, and synthesize the best available evidence regarding the teaching and learning preferences of Generation Y health professional students. The review considered any objectively measured or self-reported outcomes of teaching and learning reported from Generation Y health professional student perspectives. In accordance with a previously published Joanna Briggs Institute Protocol, a three-step search strategy was completed. Two research articles (nursing and dental hygiene students and three dissertations (nursing were critically appraised. All studies were cross-sectional descriptive studies. A range of pedagogical approaches was reported, including lecture, group work, and teaching clinical skills. Based on the Joanna Briggs Institute levels of evidence, reviewers deemed the evidence as Level 3. Some generational differences were reported, but these were inconsistent across the studies reviewed. There is, therefore, insufficient evidence to provide specific recommendations for the preferred educational approaches of health professional students and further research is warranted.

  3. Development of fuzzy algorithm with learning function for nuclear steam generator level control

    International Nuclear Information System (INIS)

    Park, Gee Yong; Seong, Poong Hyun

    1993-01-01

    A fuzzy algorithm with learning function is applied to the steam generator level control of nuclear power plant. This algorithm can make its rule base and membership functions suited for steam generator level control by use of the data obtained from the control actions of a skilled operator or of other controllers (i.e., PID controller). The rule base of fuzzy controller with learning function is divided into two parts. One part of the rule base is provided to level control of steam generator at low power level (0 % - 30 % of full power) and the other to level control at high power level (30 % - 100 % of full power). Response time of steam generator level control at low power range with this rule base is shown to be shorter than that of fuzzy controller with direct inference. (Author)

  4. Applications of Generative Learning for the Survey of International Economics Course

    Science.gov (United States)

    Sharp, David C.; Knowlton, Dave S.; Weiss, Renee E.

    2005-01-01

    Generative learning provides students with opportunities to organize course content, integrate new content with students' current knowledge, and elaborate on course content by making connections to real-world events. These opportunities promote less reliance on professors' lectures and simultaneously create more self-reliance among students. The…

  5. A new generative complexity science of learning for a complex pedagogy

    NARCIS (Netherlands)

    Jörg, T.

    2007-01-01

    Proposal for the SIG Chaos and Complexity Theories at AERA 2007 Title: A New Generative Complexity Science of Learning for a Complex Pedagogy Ton Jörg IVLOS Institute of Education University of Utrecht The Netherlands A.G.D.Jorg@ivlos.uu.nl Introduction My paper focuses on the link between thinking

  6. Student-Generated Content: Enhancing Learning through Sharing Multiple-Choice Questions

    Science.gov (United States)

    Hardy, Judy; Bates, Simon P.; Casey, Morag M.; Galloway, Kyle W.; Galloway, Ross K.; Kay, Alison E.; Kirsop, Peter; McQueen, Heather A.

    2014-01-01

    The relationship between students' use of PeerWise, an online tool that facilitates peer learning through student-generated content in the form of multiple-choice questions (MCQs), and achievement, as measured by their performance in the end-of-module examinations, was investigated in 5 large early-years science modules (in physics, chemistry and…

  7. Process Improvement for Next Generation Space Flight Vehicles: MSFC Lessons Learned

    Science.gov (United States)

    Housch, Helen

    2008-01-01

    This viewgraph presentation reviews the lessons learned from process improvement for Next Generation Space Flight Vehicles. The contents include: 1) Organizational profile; 2) Process Improvement History; 3) Appraisal Preparation; 4) The Appraisal Experience; 5) Useful Tools; and 6) Is CMMI working?

  8. The Passion of Teaching: Learning from an Older Generation of Teachers

    Science.gov (United States)

    Santoro, Ninetta; Pietsch, Marilyn; Borg, Tracey

    2012-01-01

    This article reports on a qualitative small-scale case study that investigated what pre-service teachers learned from a former generation of teachers about the context and nature of teaching and teacher education during the 1950s and 1960s. Data comprised semi-structured interviews and a grounded theoretical approach was used to analyse the data.…

  9. An Emerging Learning Design for Student-Generated "iVideos"

    Science.gov (United States)

    Kearney, Matthew; Jones, Glynis; Roberts, Lynn

    2012-01-01

    This paper describes an emerging learning design for a popular genre of learner-generated video projects: "Ideas Videos" or "iVideos." These advocacy-style videos are short, two-minute, digital videos designed "to evoke powerful experiences about educative ideas" (Wong, Mishra, Koehler & Siebenthal, 2007, p1). We…

  10. Learning Ecosystem Complexity: A Study on Small-Scale Fishers' Ecological Knowledge Generation

    Science.gov (United States)

    Garavito-Bermúdez, Diana

    2018-01-01

    Small-scale fisheries are learning contexts of importance for generating, transferring and updating ecological knowledge of natural environments through everyday work practices. The rich knowledge fishers have of local ecosystems is the result of the intimate relationship fishing communities have had with their natural environments across…

  11. A Typology of Agency in New Generation Learning Environments: Emerging Relational, Ecological and New Material Considerations

    Science.gov (United States)

    Charteris, Jennifer; Smardon, Dianne

    2018-01-01

    The impetus to move to a new generation learning environments places a spotlight on the relational dynamics of classroom spaces. A key feature is the notion of learner agency. A complex notion, learner agency involves both compliance with and resistance to classroom norms and therefore is far more sophisticated than acting in acquiescence to…

  12. Challenges to the Learning Organization in the Context of Generational Diversity and Social Networks

    Science.gov (United States)

    Kaminska, Renata; Borzillo, Stefano

    2018-01-01

    Purpose: The purpose of this paper is to gain a better understanding of the challenges to the emergence of a learning organization (LO) posed by a context of generational diversity and an enterprise social networking system (ESNS). Design/methodology/approach: This study uses a qualitative methodology based on an analysis of 20 semi-structured…

  13. Learning the Brain in Introductory Psychology: Examining the Generation Effect for Mnemonics and Examples

    Science.gov (United States)

    McCabe, Jennifer A.

    2015-01-01

    The goal of this research was to determine whether there is a generation effect for learner-created keyword mnemonics and real-life examples, compared to instructor-provided materials, when learning neurophysiological terms and definitions in introductory psychology. Students participated in an individual (Study 1) or small-group (Study 2)…

  14. Development and Evaluation of HawkLearn: A Next Generation Learning Management System

    Science.gov (United States)

    Round, Kimberlee L.

    2013-01-01

    Cloud-based computing in higher education has the potential to impact institutions on a myriad of fronts, including technology governance, flexibility, financial, and intellectual property. As the demand for blended and online education increases, institutions are considering expedient approaches to implementing learning management systems (LMSs).…

  15. Leveraging Machine Learning to Estimate Soil Salinity through Satellite-Based Remote Sensing

    Science.gov (United States)

    Welle, P.; Ravanbakhsh, S.; Póczos, B.; Mauter, M.

    2016-12-01

    Human-induced salinization of agricultural soils is a growing problem which now affects an estimated 76 million hectares and causes billions of dollars of lost agricultural revenues annually. While there are indications that soil salinization is increasing in extent, current assessments of global salinity levels are outdated and rely heavily on expert opinion due to the prohibitive cost of a worldwide sampling campaign. A more practical alternative to field sampling may be earth observation through remote sensing, which takes advantage of the distinct spectral signature of salts in order to estimate soil conductivity. Recent efforts to map salinity using remote sensing have been met with limited success due to tractability issues of managing the computational load associated with large amounts of satellite data. In this study, we use Google Earth Engine to create composite satellite soil datasets, which combine data from multiple sources and sensors. These composite datasets contain pixel-level surface reflectance values for dates in which the algorithm is most confident that the surface contains bare soil. We leverage the detailed soil maps created and updated by the United States Geological Survey as label data and apply machine learning regression techniques such as Gaussian processes to learn a smooth mapping from surface reflection to noisy estimates of salinity. We also explore a semi-supervised approach using deep generative convolutional networks to leverage the abundance of unlabeled satellite images in producing better estimates for salinity values where we have relatively fewer measurements across the globe. The general method results in two significant contributions: (1) an algorithm that can be used to predict levels of soil salinity in regions without detailed soil maps and (2) a general framework that serves as an example for how remote sensing can be paired with extensive label data to generate methods for prediction of physical phenomenon.

  16. Multiple Chaotic Central Pattern Generators with Learning for Legged Locomotion and Malfunction Compensation

    DEFF Research Database (Denmark)

    Ren, Guanjiao; Chen, Weihai; Dasgupta, Sakyasingha

    2015-01-01

    on a simulated annealing algorithm. In a normal situation, the CPGs synchronize and their dynamics are identical. With leg malfunction or disability, the CPGs lose synchronization leading to independent dynamics. In this case, the learning mechanism is applied to automatically adjust the remaining legs...... in a physical simulation of a quadruped as well as a hexapod robot and finally in a real six-legged walking machine called AMOSII. The experimental results presented here reveal that using multiple CPGs with learning is an effective approach for adaptive locomotion generation where, for instance, different body...... chaotic CPG controller has difficulties dealing with leg malfunction. Specifically, in the scenarios presented here, its movement permanently deviates from the desired trajectory. To address this problem, we extend the single chaotic CPG to multiple CPGs with learning. The learning mechanism is based...

  17. Model of e-learning with electronic educational resources of new generation

    Directory of Open Access Journals (Sweden)

    A. V. Loban

    2017-01-01

    Full Text Available Purpose of the article: improving of scientific and methodical base of the theory of the е-learning of variability. Methods used: conceptual and logical modeling of the е-learning of variability process with electronic educational resource of new generation and system analysis of the interconnection of the studied subject area, methods, didactics approaches and information and communication technologies means. Results: the formalization complex model of the е-learning of variability with electronic educational resource of new generation is developed, conditionally decomposed into three basic components: the formalization model of the course in the form of the thesaurusclassifier (“Author of e-resource”, the model of learning as management (“Coordination. Consultation. Control”, the learning model with the thesaurus-classifier (“Student”. Model “Author of e-resource” allows the student to achieve completeness, high degree of didactic elaboration and structuring of the studied material in triples of variants: modules of education information, practical task and control tasks; the result of the student’s (author’s of e-resource activity is the thesaurus-classifier. Model of learning as management is based on the principle of personal orientation of learning in computer environment and determines the logic of interaction between the lecturer and the student when determining the triple of variants individually for each student; organization of a dialogue between the lecturer and the student for consulting purposes; personal control of the student’s success (report generation and iterative search for the concept of the class assignment in the thesaurus-classifier before acquiring the required level of training. Model “Student” makes it possible to concretize the learning tasks in relation to the personality of the student and to the training level achieved; the assumption of the lecturer about the level of training of a

  18. Evolution of co-management: role of knowledge generation, bridging organizations and social learning.

    Science.gov (United States)

    Berkes, Fikret

    2009-04-01

    Over a period of some 20 years, different aspects of co-management (the sharing of power and responsibility between the government and local resource users) have come to the forefront. The paper focuses on a selection of these: knowledge generation, bridging organizations, social learning, and the emergence of adaptive co-management. Co-management can be considered a knowledge partnership. Different levels of organization, from local to international, have comparative advantages in the generation and mobilization of knowledge acquired at different scales. Bridging organizations provide a forum for the interaction of these different kinds of knowledge, and the coordination of other tasks that enable co-operation: accessing resources, bringing together different actors, building trust, resolving conflict, and networking. Social learning is one of these tasks, essential both for the co-operation of partners and an outcome of the co-operation of partners. It occurs most efficiently through joint problem solving and reflection within learning networks. Through successive rounds of learning and problem solving, learning networks can incorporate new knowledge to deal with problems at increasingly larger scales, with the result that maturing co-management arrangements become adaptive co-management in time.

  19. Learning-Related Changes in Adolescents' Neural Networks during Hypothesis-Generating and Hypothesis-Understanding Training

    Science.gov (United States)

    Lee, Jun-Ki; Kwon, Yongju

    2012-01-01

    Fourteen science high school students participated in this study, which investigated neural-network plasticity associated with hypothesis-generating and hypothesis-understanding in learning. The students were divided into two groups and participated in either hypothesis-generating or hypothesis-understanding type learning programs, which were…

  20. Chamilo 2.0: A Second Generation Open Source E-learning and Collaboration Platform

    OpenAIRE

    Jean-Marie Maes

    2010-01-01

    Dokeos used to be one of the leading open source learning platforms. It is well known for the wide range of functions it offers and especially for its ease of use. In many ways it is however a typical first generation learning management system (LMS) consisting of a set of loosely integrated tools. The original design of this LMS has a number of serious drawbacks and limitations. Because of this it was decided to opt for a completely new system that would use state of the art development tech...

  1. Design of fuzzy learning control systems for steam generator water level control

    International Nuclear Information System (INIS)

    Park, Gee Yong

    1996-02-01

    A fuzzy learning algorithm is developed in order to construct the useful control rules and tune the membership functions in the fuzzy logic controller used for water level control of nuclear steam generator. The fuzzy logic controllers have shown to perform better than conventional controllers for ill-defined or complex processes such as nuclear steam generator. Whereas the fuzzy logic controller does not need a detailed mathematical model of a plant to be controlled, its structure is to be made on the basis of the operator's linguistic information experienced from the plant operations. It is not an easy work and also there is no systematic way to translate the operator's linguistic information into quantitative information. When the linguistic information of operators is incomplete, tuning the parameters of fuzzy controller is to be performed for better control performance. It is the time and effort consuming procedure that controller designer has to tune the structure of fuzzy logic controller for optimal performance. And if the number of control inputs is many and the rule base is constructed in multidimensional space, it is very difficult for a controller designer to tune the fuzzy controller structure. Hence, the difficulty in putting the experimental knowledge into quantitative (or numerical) data and the difficulty in tuning the rules are the major problems in designing fuzzy logic controller. In order to overcome the problems described above, a learning algorithm by gradient descent method is included in the fuzzy control system such that the membership functions are tuned and the necessary rules are created automatically for good control performance. For stable learning in gradient descent method, the optimal range of learning coefficient not to be trapped and not to provide too slow learning speed is investigated. With the optimal range of learning coefficient, the optimal value of learning coefficient is suggested and with this value, the gradient

  2. Steam generator replacement at Bruce A: approach, results, and lessons learned

    International Nuclear Information System (INIS)

    Tomkiewicz, W.; Savage, B.; Smith, J.

    2008-01-01

    Steam Generator Replacement is now complete in Bruce A Units 1 and 2. In each reactor, eight steam generators were replaced; these were the first CANDU steam generator replacements performed anywhere in the world. The plans for replacement were developed in 2004 and 2005, and were summarized in an earlier paper for the CNS Conference held in November, 2006. The present paper briefly summarizes the methodologies and special processes used such as metrology, cutting and welding and heavy lifting. The paper provides an update since the earlier report and focuses on the project achievements to date, such as: - A combination of engineered methodology, laser metrology and precise remote machining led to accurate first time fit-ups of each new replacement steam generator and steam drums - Lessons learned in the first unit led to schedule improvements in the second unit - Dose received was lowest recorded for any steam generator replacement project. The experience gained and lessons learned from Units 1 and 2 will be valuable in planning and executing future replacement steam generator projects. A video was presented

  3. LEARNING STRATEGY IMPLEMENTATION OF GENERATIVE LEARNING ASSISTED SCIENTIST’S CARD TO IMPROVE SELF EFFICACY OF JUNIOR HIGH SCHOOL STUDENT IN CLASS VIII

    Directory of Open Access Journals (Sweden)

    R. Yuliarti

    2016-01-01

    Full Text Available In general, self-efficacy of the students is still low. This study aims to determine the learning strategies implementation of generative learning assisted scientist's card in improving self-efficacy and cognitive learning outcomes of the students. The study designed form One Group Pretest-Posttest Design. The improvement of self-efficacy can be determined from the change in the questionnaire score before and after the learning and observations during the learning process. Cognitive learning outcomes are known from pretest and posttest scores. To determine the improvement, the data were analyzed by using the gain test. The results showed that N-gain of self-efficacy is 0.13 (low and N-gain of cognitive learning is 0.60 (medium. Based on the observation, students’ self-efficacy has increased each meeting. Cognitive learning results also achieved mastery learning as big as 72.88%. It could be concluded that the learning strategy of generative learning assisted scientist's card can improve self efficacy and cognitive learning outcomes of the students.Pada umumnya, self efficacy yang dimiliki siswa masih rendah. Penelitian ini bertujuan untuk mengetahui penerapan strategi pembelajaran generative learning berbantuan scientist’s card dalam meningkatkan self efficacy dan  hasil belajar  kognitif siswa.  Desain penelitian berbentuk One Group Pretest-Posttest Design. Peningkatan self efficacy dapat diketahui dari perubahan  skor angket sebelum dan sesudah pembelajaran dan hasil observasi selama pembelajaran. Hasil  belajar kognitif diketahui dari skor pretest dan posttest. Untuk mengetahui peningkatannya, data yang diperoleh dianalisis menggunakan uji gain. Hasil penelitian menunjukkan bahwa peningkatan self efficacy berkatagori rendah dan peningkatan hasil belajar kognitif berkatagori sedang. Berdasarkan hasil observasi, self efficacy siswa setiap pertemuan meningkat. Hasil belajar ranah kognitif juga mencapai ketuntasan belajar .Jadi dapat

  4. Flexible Generation of E-Learning Exams in R: Moodle Quizzes, OLAT Assessments, and Beyond

    Directory of Open Access Journals (Sweden)

    Achim Zeileis

    2014-06-01

    Full Text Available The capabilities of the package exams for automatic generation of (statistical exams in R are extended by adding support for learning management systems: As in earlier versions of the package exam generation is still based on separate Sweave ?les for each exercise but rather than just producing di?erent types of PDF output ?les, the package can now render the same exercises into a wide variety of output formats. These include HTML (with various options for displaying mathematical content and XML speci?cations for online exams in learning management systems such as Moodle or OLAT. This ?exibility is accomplished by a new modular and extensible design of the package that allows for reading all weaved exercises into R and managing associated supplementary ?les (such as graphics or data ?les. The manuscript discusses the readily available user interfaces, the design of the underlying infrastructure, and how new functionality can be built on top of the existing tools.

  5. Incremental Learning of Context Free Grammars by Parsing-Based Rule Generation and Rule Set Search

    Science.gov (United States)

    Nakamura, Katsuhiko; Hoshina, Akemi

    This paper discusses recent improvements and extensions in Synapse system for inductive inference of context free grammars (CFGs) from sample strings. Synapse uses incremental learning, rule generation based on bottom-up parsing, and the search for rule sets. The form of production rules in the previous system is extended from Revised Chomsky Normal Form A→βγ to Extended Chomsky Normal Form, which also includes A→B, where each of β and γ is either a terminal or nonterminal symbol. From the result of bottom-up parsing, a rule generation mechanism synthesizes minimum production rules required for parsing positive samples. Instead of inductive CYK algorithm in the previous version of Synapse, the improved version uses a novel rule generation method, called ``bridging,'' which bridges the lacked part of the derivation tree for the positive string. The improved version also employs a novel search strategy, called serial search in addition to minimum rule set search. The synthesis of grammars by the serial search is faster than the minimum set search in most cases. On the other hand, the size of the generated CFGs is generally larger than that by the minimum set search, and the system can find no appropriate grammar for some CFL by the serial search. The paper shows experimental results of incremental learning of several fundamental CFGs and compares the methods of rule generation and search strategies.

  6. Hydrogen Fuel Cell Analysis: Lessons Learned from Stationary Power Generation Final Report

    Energy Technology Data Exchange (ETDEWEB)

    Scott E. Grasman; John W. Sheffield; Fatih Dogan; Sunggyu Lee; Umit O. Koylu; Angie Rolufs

    2010-04-30

    This study considered opportunities for hydrogen in stationary applications in order to make recommendations related to RD&D strategies that incorporate lessons learned and best practices from relevant national and international stationary power efforts, as well as cost and environmental modeling of pathways. The study analyzed the different strategies utilized in power generation systems and identified the different challenges and opportunities for producing and using hydrogen as an energy carrier. Specific objectives included both a synopsis/critical analysis of lessons learned from previous stationary power programs and recommendations for a strategy for hydrogen infrastructure deployment. This strategy incorporates all hydrogen pathways and a combination of distributed power generating stations, and provides an overview of stationary power markets, benefits of hydrogen-based stationary power systems, and competitive and technological challenges. The motivation for this project was to identify the lessons learned from prior stationary power programs, including the most significant obstacles, how these obstacles have been approached, outcomes of the programs, and how this information can be used by the Hydrogen, Fuel Cells & Infrastructure Technologies Program to meet program objectives primarily related to hydrogen pathway technologies (production, storage, and delivery) and implementation of fuel cell technologies for distributed stationary power. In addition, the lessons learned address environmental and safety concerns, including codes and standards, and education of key stakeholders.

  7. Advances in Bayesian Model Based Clustering Using Particle Learning

    Energy Technology Data Exchange (ETDEWEB)

    Merl, D M

    2009-11-19

    implementation of Carvalho et al that allow us to retain the computational advantages of particle learning while improving the suitability of the methodology to the analysis of streaming data and simultaneously facilitating the real time discovery of latent cluster structures. Section 4 demonstrates our methodological enhancements in the context of several simulated and classical data sets, showcasing the use of particle learning methods for online anomaly detection, label generation, drift detection, and semi-supervised classification, none of which would be achievable through a standard MCMC approach. Section 5 concludes with a discussion of future directions for research.

  8. Children's Everyday Learning by Assuming Responsibility for Others: Indigenous Practices as a Cultural Heritage Across Generations.

    Science.gov (United States)

    Fernández, David Lorente

    2015-01-01

    This chapter uses a comparative approach to examine the maintenance of Indigenous practices related with Learning by Observing and Pitching In in two generations--parent generation and current child generation--in a Central Mexican Nahua community. In spite of cultural changes and the increase of Western schooling experience, these practices persist, to different degrees, as a Nahua cultural heritage with close historical relations to the key value of cuidado (stewardship). The chapter explores how children learn the value of cuidado in a variety of everyday activities, which include assuming responsibility in many social situations, primarily in cultivating corn, raising and protecting domestic animals, health practices, and participating in family ceremonial life. The chapter focuses on three main points: (1) Cuidado (assuming responsibility for), in the Nahua socio-cultural context, refers to the concepts of protection and "raising" as well as fostering other beings, whether humans, plants, or animals, to reach their potential and fulfill their development. (2) Children learn cuidado by contributing to family endeavors: They develop attention and self-motivation; they are capable of responsible actions; and they are able to transform participation to achieve the status of a competent member of local society. (3) This collaborative participation allows children to continue the cultural tradition and to preserve a Nahua heritage at a deeper level in a community in which Nahuatl language and dress have disappeared, and people do not identify themselves as Indigenous. © 2015 Elsevier Inc. All rights reserved.

  9. Application of a fuzzy control algorithm with improved learning speed to nuclear steam generator level control

    International Nuclear Information System (INIS)

    Park, Gee Yong; Seong, Poong Hyun

    1994-01-01

    In order to reduce the load of tuning works by trial-and-error for obtaining the best control performance of conventional fuzzy control algorithm, a fuzzy control algorithm with learning function is investigated in this work. This fuzzy control algorithm can make its rule base and tune the membership functions automatically by use of learning function which needs the data from the control actions of the plant operator or other controllers. Learning process in fuzzy control algorithm is to find the optimal values of parameters, which consist of the membership functions and the rule base, by gradient descent method. Learning speed of gradient descent is significantly improved in this work with the addition of modified momentum. This control algorithm is applied to the steam generator level control by computer simulations. The simulation results confirm the good performance of this control algorithm for level control and show that the fuzzy learning algorithm has the generalization capability for the relation of inputs and outputs and it also has the excellent capability of disturbance rejection

  10. Deep generative learning for automated EHR diagnosis of traditional Chinese medicine.

    Science.gov (United States)

    Liang, Zhaohui; Liu, Jun; Ou, Aihua; Zhang, Honglai; Li, Ziping; Huang, Jimmy Xiangji

    2018-05-04

    Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM. A two-step model is applied in our study. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. There are two data sets used in the experiments. One is a plain text data set indexed by medical experts. The other is a structured dataset on primary hypertension. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. Two conventional shallow models (support vector machine / SVM and decision tree / DT) are applied as the comparisons to show the superiority of our proposed approach. The deep learning (DBN + SVM) model outperforms simple SVM and DT on two data sets in terms of all the evaluation measures, which confirms our motivation that the deep model is good at capturing the key features with less dependence when the index is built up by manpower. Our study shows the two-step deep learning model achieves high performance for medical

  11. Evaluating mobile learning practice. Towards a framework for analysis of user-generated contexts with reference to the socio-cultural ecology of mobile learning

    Directory of Open Access Journals (Sweden)

    Judith Seipold

    2011-04-01

    Full Text Available Against the conceptual and theoretical background of a socio-culturally orientated approach to mobile learning (Pachler, Bachmair and Cook, 2010, this paper examines the evaluation of user-generated contexts by referring to an example from the use of mobile phones in schools. We discuss how mobile device-related, user- generated contexts around structures, agency and cultural practices might be brought into a fruitful relationship with institution-based learning. And, we provide categories for evaluating the use of mobile devices to generate meaning from and with fragmented and discontinuous media and modes at the interface of learning in formal, institutionalised and informal, self-directed settings. The evaluation criteria build on the framework of a socio-cultural ecology of mobile learning developed by the London Mobile Learning Group.

  12. Learning Physics-based Models in Hydrology under the Framework of Generative Adversarial Networks

    Science.gov (United States)

    Karpatne, A.; Kumar, V.

    2017-12-01

    Generative adversarial networks (GANs), that have been highly successful in a number of applications involving large volumes of labeled and unlabeled data such as computer vision, offer huge potential for modeling the dynamics of physical processes that have been traditionally studied using simulations of physics-based models. While conventional physics-based models use labeled samples of input/output variables for model calibration (estimating the right parametric forms of relationships between variables) or data assimilation (identifying the most likely sequence of system states in dynamical systems), there is a greater opportunity to explore the full power of machine learning (ML) methods (e.g, GANs) for studying physical processes currently suffering from large knowledge gaps, e.g. ground-water flow. However, success in this endeavor requires a principled way of combining the strengths of ML methods with physics-based numerical models that are founded on a wealth of scientific knowledge. This is especially important in scientific domains like hydrology where the number of data samples is small (relative to Internet-scale applications such as image recognition where machine learning methods has found great success), and the physical relationships are complex (high-dimensional) and non-stationary. We will present a series of methods for guiding the learning of GANs using physics-based models, e.g., by using the outputs of physics-based models as input data to the generator-learner framework, and by using physics-based models as generators trained using validation data in the adversarial learning framework. These methods are being developed under the broad paradigm of theory-guided data science that we are developing to integrate scientific knowledge with data science methods for accelerating scientific discovery.

  13. Effect of problem solving support and cognitive style on idea generation: Implications for Technology-Enhanced-Learning

    NARCIS (Netherlands)

    Stoyanov, Slavi; Kirschner, Paul A.

    2008-01-01

    Stoyanov, S., & Kirschner, P. (2007). Effect of problem solving support and cognitive style on idea generation: Implications for Technology-Enhanced-Learning. Journal of Research on Technology in Education, 40(1), 49-63.

  14. A Course Wiki: Challenges in Facilitating and Assessing Student-Generated Learning Content for the Humanities Classroom

    Science.gov (United States)

    Lazda-Cazers, Rasma

    2010-01-01

    New Web technology allows for the design of traditionally lecture-centered humanities courses by fostering active learning and engaging students as producers of learning content. The article presents the experiences with a student-generated wiki for a Germanic Mythology course. Evaluations indicated an overwhelmingly positive student experience…

  15. Teaching the Next Generation of Information Literacy Educators: Pedagogy and Learning

    Directory of Open Access Journals (Sweden)

    Sheila Webber

    2016-12-01

    Full Text Available The aim of this presentation is to compare key aspects of learning in two core information literacy (IL modules, one delivered to a face-to-face cohort (MA Librarianship and one to distance learners (MA Library and Information Service Management. Graduates of these programmes (delivered by the University of Sheffield iSchool, UK often pursue careers that require excellent personal Information Literacy (IL and the ability to teach IL to others. Inskip’s research (2015 identified that these are subjects that library and information (LIS students want to learn, and Saunders et al.’s (2015 international study found that LIS students’ IL requires development. Our modules aim to develop the students’ understanding of themselves as information literate citizens and teachers, and introduce them to theories and models in the fields of IL and information behavior, teaching and learning. The modules include a practical strand (searching, evaluating, using (etc. information and assessment is through coursework. Using Entwistle et al.’s (2004 model of the Teaching and Learning Environment (TLE, we will map key elements (e.g. learner characteristics, approaches of teachers, course design relevant to the quality of learning. We will also look at three “layers” of teaching: (1 overall pedagogic beliefs and institutional policies, (2 design for learning (overall planning for achieving learning outcomes, and (3 techniques, tools and methods used. We will draw on documentation, reflection and (with cooperation from learners material created by learners during, and subsequent to, the modules. Through the use of the TLE model we will surface differences in the experience of face-to-face and distance learners and also differences in development of their personal IL and pedagogic knowledge for IL.  References at https://docs.google.com/document/d/1JwNCYU-Uh9e-AIyRwTnMyU6Qooab0Tn8vYC-kzd1_Mw/edit?usp=sharing The PowerPoint slides that accompany this

  16. DNA Cryptography and Deep Learning using Genetic Algorithm with NW algorithm for Key Generation.

    Science.gov (United States)

    Kalsi, Shruti; Kaur, Harleen; Chang, Victor

    2017-12-05

    Cryptography is not only a science of applying complex mathematics and logic to design strong methods to hide data called as encryption, but also to retrieve the original data back, called decryption. The purpose of cryptography is to transmit a message between a sender and receiver such that an eavesdropper is unable to comprehend it. To accomplish this, not only we need a strong algorithm, but a strong key and a strong concept for encryption and decryption process. We have introduced a concept of DNA Deep Learning Cryptography which is defined as a technique of concealing data in terms of DNA sequence and deep learning. In the cryptographic technique, each alphabet of a letter is converted into a different combination of the four bases, namely; Adenine (A), Cytosine (C), Guanine (G) and Thymine (T), which make up the human deoxyribonucleic acid (DNA). Actual implementations with the DNA don't exceed laboratory level and are expensive. To bring DNA computing on a digital level, easy and effective algorithms are proposed in this paper. In proposed work we have introduced firstly, a method and its implementation for key generation based on the theory of natural selection using Genetic Algorithm with Needleman-Wunsch (NW) algorithm and Secondly, a method for implementation of encryption and decryption based on DNA computing using biological operations Transcription, Translation, DNA Sequencing and Deep Learning.

  17. Generation and Validation of Spatial Distribution of Hourly Wind Speed Time-Series using Machine Learning

    International Nuclear Information System (INIS)

    Veronesi, F; Grassi, S

    2016-01-01

    Wind resource assessment is a key aspect of wind farm planning since it allows to estimate the long term electricity production. Moreover, wind speed time-series at high resolution are helpful to estimate the temporal changes of the electricity generation and indispensable to design stand-alone systems, which are affected by the mismatch of supply and demand. In this work, we present a new generalized statistical methodology to generate the spatial distribution of wind speed time-series, using Switzerland as a case study. This research is based upon a machine learning model and demonstrates that statistical wind resource assessment can successfully be used for estimating wind speed time-series. In fact, this method is able to obtain reliable wind speed estimates and propagate all the sources of uncertainty (from the measurements to the mapping process) in an efficient way, i.e. minimizing computational time and load. This allows not only an accurate estimation, but the creation of precise confidence intervals to map the stochasticity of the wind resource for a particular site. The validation shows that machine learning can minimize the bias of the wind speed hourly estimates. Moreover, for each mapped location this method delivers not only the mean wind speed, but also its confidence interval, which are crucial data for planners. (paper)

  18. Generation and Validation of Spatial Distribution of Hourly Wind Speed Time-Series using Machine Learning

    Science.gov (United States)

    Veronesi, F.; Grassi, S.

    2016-09-01

    Wind resource assessment is a key aspect of wind farm planning since it allows to estimate the long term electricity production. Moreover, wind speed time-series at high resolution are helpful to estimate the temporal changes of the electricity generation and indispensable to design stand-alone systems, which are affected by the mismatch of supply and demand. In this work, we present a new generalized statistical methodology to generate the spatial distribution of wind speed time-series, using Switzerland as a case study. This research is based upon a machine learning model and demonstrates that statistical wind resource assessment can successfully be used for estimating wind speed time-series. In fact, this method is able to obtain reliable wind speed estimates and propagate all the sources of uncertainty (from the measurements to the mapping process) in an efficient way, i.e. minimizing computational time and load. This allows not only an accurate estimation, but the creation of precise confidence intervals to map the stochasticity of the wind resource for a particular site. The validation shows that machine learning can minimize the bias of the wind speed hourly estimates. Moreover, for each mapped location this method delivers not only the mean wind speed, but also its confidence interval, which are crucial data for planners.

  19. Detecting representative data and generating synthetic samples to improve learning accuracy with imbalanced data sets.

    Directory of Open Access Journals (Sweden)

    Der-Chiang Li

    Full Text Available It is difficult for learning models to achieve high classification performances with imbalanced data sets, because with imbalanced data sets, when one of the classes is much larger than the others, most machine learning and data mining classifiers are overly influenced by the larger classes and ignore the smaller ones. As a result, the classification algorithms often have poor learning performances due to slow convergence in the smaller classes. To balance such data sets, this paper presents a strategy that involves reducing the sizes of the majority data and generating synthetic samples for the minority data. In the reducing operation, we use the box-and-whisker plot approach to exclude outliers and the Mega-Trend-Diffusion method to find representative data from the majority data. To generate the synthetic samples, we propose a counterintuitive hypothesis to find the distributed shape of the minority data, and then produce samples according to this distribution. Four real datasets were used to examine the performance of the proposed approach. We used paired t-tests to compare the Accuracy, G-mean, and F-measure scores of the proposed data pre-processing (PPDP method merging in the D3C method (PPDP+D3C with those of the one-sided selection (OSS, the well-known SMOTEBoost (SB study, and the normal distribution-based oversampling (NDO approach, and the proposed data pre-processing (PPDP method. The results indicate that the classification performance of the proposed approach is better than that of above-mentioned methods.

  20. Discourse Analysis and the teaching of Biochemistry: contextualized learning based on "alcoholic beverages" as generative theme

    Directory of Open Access Journals (Sweden)

    R. M.; A. S. Lima; Conceição

    2017-07-01

    Full Text Available The World Health Organization classifies alcohol as a psychoactive substance capable of producing addiction, associated to various diseases and social problems. However, it is largely consumed in the various social strata by youngster which ultimately leads to its common practice. These individuals know little about the harms posed by excessive consumption of alcoholic beverages. In this scenario, education is a major promoter of change in this longstanding social behavior. This study aimed at promoting the consolidation of the teaching of Biology by using alcohol as generative themes for the development of contents in Biochemistry, as well as elaborating a methodology that will stimulate learning about ethanol metabolism. A research was carried out with 316 individuals in the age group 13-19, enrolled in four public High Schools in the Municipality of Campos dos Goytacazes/RJ. Prevalence of alcoholic beverages was identified among 72%, and beginning of such habit was found in the 13-15 age group motivated by curiosity or peer influence. Considering these data, an educational methodology was developed based on the concept of generative themes by Paulo Freire and structured by Delizoicov (2007. To verify the value of such methodology in Biochemistry classroom, data was collected by applying a questionnaire and images with texts produced by students. Several didactic resources designed by the authors were used, such as slide presentation and a roulette game named “Bioquimicados”. Critical analysis of texts written by students were carried out before and after the class using DTA. Students developed more grounded scientific concepts, making use of terms common in scientific language. This suggests that the use of the Generating Issue in a lesson based on problematization, and supported by a ludic activity, provided a meaningful contribution to improve the students' understanding of the scientific content. A non-traditional class promotes

  1. Exploring the roles of cannot-link constraint in community detection via Multi-variance Mixed Gaussian Generative Model

    Science.gov (United States)

    Ge, Meng; Jin, Di; He, Dongxiao; Fu, Huazhu; Wang, Jing; Cao, Xiaochun

    2017-01-01

    Due to the demand for performance improvement and the existence of prior information, semi-supervised community detection with pairwise constraints becomes a hot topic. Most existing methods have been successfully encoding the must-link constraints, but neglect the opposite ones, i.e., the cannot-link constraints, which can force the exclusion between nodes. In this paper, we are interested in understanding the role of cannot-link constraints and effectively encoding pairwise constraints. Towards these goals, we define an integral generative process jointly considering the network topology, must-link and cannot-link constraints. We propose to characterize this process as a Multi-variance Mixed Gaussian Generative (MMGG) Model to address diverse degrees of confidences that exist in network topology and pairwise constraints and formulate it as a weighted nonnegative matrix factorization problem. The experiments on artificial and real-world networks not only illustrate the superiority of our proposed MMGG, but also, most importantly, reveal the roles of pairwise constraints. That is, though the must-link is more important than cannot-link when either of them is available, both must-link and cannot-link are equally important when both of them are available. To the best of our knowledge, this is the first work on discovering and exploring the importance of cannot-link constraints in semi-supervised community detection. PMID:28678864

  2. Lessons learned from hydrogen generation and burning during the TMI-2 event

    International Nuclear Information System (INIS)

    Henrie, J.O.; Postma, A.K.

    1987-05-01

    This document summarizes what has been learned from generation of hydrogen in the reactor core and the hydrogen burn that occurred in the containment building of the Three Mile Island Unit No. 2 (TMI-2) nuclear power plant on March 28, 1979. During the TMI-2 loss-of-coolant accident (LOCA), a large quantity of hydrogen was generated by a zirconium-water reaction. The hydrogen burn that occurred 9 h and 50 min after the initiation of the TMI-2 accident went essentially unnoticed for the first few days. Even through the burn increased the containment gas temperature and pressure to 1200 0 F (650 0 C) and 29 lb/in 2 (200 kPa) gage, there was no serious threat to the containment building. The processes, rates, and quantities of hydrogen gas generated and removed during and following the LOCA are described in this report. In addition, the methods which were used to define the conditions that existed in the containment building before, during, and after the hydrogen burn are described. The results of data evaluations and engineering calculations are presented to show the pressure and temperature histories of the atmosphere in various containment segments during and after the burn. Material and equipment in reactor containment buildings can be protected from burn damage by the use of relatively simple enclosures or insulation

  3. DISTRIBUTED LEADERSHIP COLLABORATION FACTORS TO SUPPORT IDEA GENERATION IN COMPUTER-SUPPORTED COLLABORATIVE e-LEARNING

    Directory of Open Access Journals (Sweden)

    Niki Lambropoulos

    2011-01-01

    Full Text Available This paper aims to identify, discuss and analyze students’ collaboration factors related to distributed leadership (DL, which correlates with interaction quality evident in idea generation. Scripting computer-supported collaborative e-learning (CSCeL activities based on DL can scaffold students’ interactions that support collaboration and promote idea generation. Furthermore, the associated tools can facilitate collaboration via scripting and shed light on students’ interactions and dialogical sequences. Such detailed planning can result in effective short e-courses. In this case study, 21 MSc students’ teams worked on a DL project within a 2-day e-course at the IT Institute (ITIN, France. The research methods involved a self-reported questionnaire; the Non-Negative Matrix Factorization (NNMF algorithm with qualitative analysis; and outcomes from the Social Network Analysis (SNA tools implemented within the forums. The results indicated that scripting DL based on the identified distributed leadership attributes can support values such as collaboration and can be useful in supporting idea generation in short e-courses.

  4. Distinguishing Computer-Generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning

    Directory of Open Access Journals (Sweden)

    Ye Yao

    2018-04-01

    Full Text Available Computer-generated graphics (CGs are images generated by computer software. The rapid development of computer graphics technologies has made it easier to generate photorealistic computer graphics, and these graphics are quite difficult to distinguish from natural images (NIs with the naked eye. In this paper, we propose a method based on sensor pattern noise (SPN and deep learning to distinguish CGs from NIs. Before being fed into our convolutional neural network (CNN-based model, these images—CGs and NIs—are clipped into image patches. Furthermore, three high-pass filters (HPFs are used to remove low-frequency signals, which represent the image content. These filters are also used to reveal the residual signal as well as SPN introduced by the digital camera device. Different from the traditional methods of distinguishing CGs from NIs, the proposed method utilizes a five-layer CNN to classify the input image patches. Based on the classification results of the image patches, we deploy a majority vote scheme to obtain the classification results for the full-size images. The experiments have demonstrated that (1 the proposed method with three HPFs can achieve better results than that with only one HPF or no HPF and that (2 the proposed method with three HPFs achieves 100% accuracy, although the NIs undergo a JPEG compression with a quality factor of 75.

  5. Deep Learning-Based Data Forgery Detection in Automatic Generation Control

    Energy Technology Data Exchange (ETDEWEB)

    Zhang, Fengli [Univ. of Arkansas, Fayetteville, AR (United States); Li, Qinghua [Univ. of Arkansas, Fayetteville, AR (United States)

    2017-10-09

    Automatic Generation Control (AGC) is a key control system in the power grid. It is used to calculate the Area Control Error (ACE) based on frequency and tie-line power flow between balancing areas, and then adjust power generation to maintain the power system frequency in an acceptable range. However, attackers might inject malicious frequency or tie-line power flow measurements to mislead AGC to do false generation correction which will harm the power grid operation. Such attacks are hard to be detected since they do not violate physical power system models. In this work, we propose algorithms based on Neural Network and Fourier Transform to detect data forgery attacks in AGC. Different from the few previous work that rely on accurate load prediction to detect data forgery, our solution only uses the ACE data already available in existing AGC systems. In particular, our solution learns the normal patterns of ACE time series and detects abnormal patterns caused by artificial attacks. Evaluations on the real ACE dataset show that our methods have high detection accuracy.

  6. Test Framing Generates a Stability Bias for Predictions of Learning by Causing People to Discount their Learning Beliefs

    Science.gov (United States)

    Ariel, Robert; Hines, Jarrod C.; Hertzog, Christopher

    2014-01-01

    People estimate minimal changes in learning when making predictions of learning (POLs) for future study opportunities despite later showing increased performance and an awareness of that increase (Kornell & Bjork, 2009). This phenomenon is conceptualized as a stability bias in judgments about learning. We investigated the malleability of this effect, and whether it reflected people’s underlying beliefs about learning. We manipulated prediction framing to emphasize the role of testing vs. studying on memory and directly measured beliefs about multi-trial study effects on learning by having participants construct predicted learning curves before and after the experiment. Mean POLs were more sensitive to the number of study-test opportunities when performance was framed in terms of study benefits rather than testing benefits and POLs reflected pre-existing beliefs about learning. The stability bias is partially due to framing and reflects discounted beliefs about learning benefits rather than inherent belief in the stability of performance. PMID:25067885

  7. Learning by Doing versus Learning by Viewing: Three Experimental Comparisons of Learner-Generated versus Author-Provided Graphic Organizers

    Science.gov (United States)

    Stull, Andrew T.; Mayer, Richard E.

    2007-01-01

    Do students learn more deeply from a passage when they attempt to construct their own graphic organizers (i.e., learning by doing) than when graphic organizers are provided (i.e., learning by viewing)? In 3 experiments, learners were tested on retention and transfer after reading a passage with author-provided graphic organizers or when asked to…

  8. Embodied learning of a generative neural model for biological motion perception and inference.

    Science.gov (United States)

    Schrodt, Fabian; Layher, Georg; Neumann, Heiko; Butz, Martin V

    2015-01-01

    Although an action observation network and mirror neurons for understanding the actions and intentions of others have been under deep, interdisciplinary consideration over recent years, it remains largely unknown how the brain manages to map visually perceived biological motion of others onto its own motor system. This paper shows how such a mapping may be established, even if the biologically motion is visually perceived from a new vantage point. We introduce a learning artificial neural network model and evaluate it on full body motion tracking recordings. The model implements an embodied, predictive inference approach. It first learns to correlate and segment multimodal sensory streams of own bodily motion. In doing so, it becomes able to anticipate motion progression, to complete missing modal information, and to self-generate learned motion sequences. When biological motion of another person is observed, this self-knowledge is utilized to recognize similar motion patterns and predict their progress. Due to the relative encodings, the model shows strong robustness in recognition despite observing rather large varieties of body morphology and posture dynamics. By additionally equipping the model with the capability to rotate its visual frame of reference, it is able to deduce the visual perspective onto the observed person, establishing full consistency to the embodied self-motion encodings by means of active inference. In further support of its neuro-cognitive plausibility, we also model typical bistable perceptions when crucial depth information is missing. In sum, the introduced neural model proposes a solution to the problem of how the human brain may establish correspondence between observed bodily motion and its own motor system, thus offering a mechanism that supports the development of mirror neurons.

  9. Embodied Learning of a Generative Neural Model for Biological Motion Perception and Inference

    Directory of Open Access Journals (Sweden)

    Fabian eSchrodt

    2015-07-01

    Full Text Available Although an action observation network and mirror neurons for understanding the actions and intentions of others have been under deep, interdisciplinary consideration over recent years, it remains largely unknown how the brain manages to map visually perceived biological motion of others onto its own motor system. This paper shows how such a mapping may be established, even if the biologically motion is visually perceived from a new vantage point. We introduce a learning artificial neural network model and evaluate it on full body motion tracking recordings. The model implements an embodied, predictive inference approach. It first learns to correlate and segment multimodal sensory streams of own bodily motion. In doing so, it becomes able to anticipate motion progression, to complete missing modal information, and to self-generate learned motion sequences. When biological motion of another person is observed, this self-knowledge is utilized to recognize similar motion patterns and predict their progress. Due to the relative encodings, the model shows strong robustness in recognition despite observing rather large varieties of body morphology and posture dynamics. By additionally equipping the model with the capability to rotate its visual frame of reference, it is able to deduce the visual perspective onto the observed person, establishing full consistency to the embodied self-motion encodings by means of active inference. In further support of its neuro-cognitive plausibility, we also model typical bistable perceptions when crucial depth information is missing. In sum, the introduced neural model proposes a solution to the problem of how the human brain may establish correspondence between observed bodily motion and its own motor system, thus offering a mechanism that supports the development of mirror neurons.

  10. Whose context is it anyway? Workplace e-learning as a synthesis of designer- and learner-generated contexts

    OpenAIRE

    Whitworth, Andrew

    2009-01-01

    This paper describes the consequences for workplace e-learning of viewing organisations as political systems. Organisations tend to stratify, and potential conflicts develop between ???top-down???, or designer-generation of workplace systems, and ???bottom-up???, or learner- and practice-based approaches. The differences between these groups in terms of their objectives, procedures, tacit knowledge and conceptions of the value of workplace e-learning have led to conflicts which have damaged r...

  11. Impact of problem-based, active learning on graduation rates for 10 generations of Dutch medical students.

    Science.gov (United States)

    Schmidt, Henk G; Cohen-Schotanus, Janke; Arends, Lidia R

    2009-03-01

    We aimed to study the effects of active-learning curricula on graduation rates of students and on the length of time needed to graduate. Graduation rates for 10 generations of students enrolling in the eight Dutch medical schools between 1989 and 1998 were analysed. In addition, time needed to graduate was recorded. Three of the eight schools had curricula emphasising active learning, small-group instruction and limited numbers of lectures; the other five had conventional curricula to varying degrees. Overall, the active-learning curricula graduated on average 8% more students per year, and these students graduated on average 5 months earlier than their colleagues from conventional curricula. Four hypotheses potentially explaining the effect of active learning on graduation rate and study duration were considered: (i) active-learning curricula promote the social and academic integration of students; (ii) active-learning curricula attract brighter students; (iii) active-learning curricula retain more poor students, and (iv) the active engagement of students with their study required by active-learning curricula induces better academic performance and, hence, lower dropout rates. The first three hypotheses had to be rejected. It was concluded that the better-learning hypothesis provides the most parsimonious account for the data.

  12. Elevated dopamine alters consummatory pattern generation and increases behavioral variability during learning

    Directory of Open Access Journals (Sweden)

    Mark A. Rossi

    2015-05-01

    Full Text Available The role of dopamine in controlling behavior remains poorly understood. In this study we examined licking behavior in an established hyperdopaminergic mouse model—dopamine transporter knockout (DAT KO mice. DAT KO mice showed higher rates of licking, which is due to increased perseveration of licking in a bout. By contrast, they showed increased individual lick durations, and reduced inter-lick-intervals. During extinction, both KO and control mice transiently increased variability in lick pattern generation while reducing licking rate, yet they showed very different behavioral patterns. Control mice gradually increased lick duration as well as variability. By contrast, DAT KO mice exhibited more immediate (within 10 licks adjustments—an immediate increase in lick duration variability, as well as more rapid extinction. These results suggest that the level of dopamine can modulate the persistence and pattern generation of a highly stereotyped consummatory behavior like licking, as well as new learning in response to changes in environmental feedback. Increased dopamine in DAT KO mice not only increased perseveration of bouts and individual lick duration, but also increased the behavioral variability in response to the extinction contingency and the rate of extinction.

  13. Using Deep Learning to Predict Complex Systems: A Case Study in Wind Farm Generation

    Directory of Open Access Journals (Sweden)

    J. M. Torres

    2018-01-01

    Full Text Available Making every component of an electrical system work in unison is being made more challenging by the increasing number of renewable energies used, the electrical output of which is difficult to determine beforehand. In Spain, the daily electricity market opens with a 12-hour lead time, where the supply and demand expected for the following 24 hours are presented. When estimating the generation, energy sources like nuclear are highly stable, while peaking power plants can be run as necessary. Renewable energies, however, which should eventually replace peakers insofar as possible, are reliant on meteorological conditions. In this paper we propose using different deep-learning techniques and architectures to solve the problem of predicting wind generation in order to participate in the daily market, by making predictions 12 and 36 hours in advance. We develop and compare various estimators based on feedforward, convolutional, and recurrent neural networks. These estimators were trained and validated with data from a wind farm located on the island of Tenerife. We show that the best candidates for each type are more precise than the reference estimator and the polynomial regression currently used at the wind farm. We also conduct a sensitivity analysis to determine which estimator type is most robust to perturbations. An analysis of our findings shows that the most accurate and robust estimators are those based on feedforward neural networks with a SELU activation function and convolutional neural networks.

  14. At the Core of the Apple Store: Images of Next Generation Learning

    Science.gov (United States)

    Washor, Elliot; Mojkowski, Charles; Newsom, Loran

    2009-01-01

    The physical, psychological, cultural, social, and organizational elements of a learning environment are as important as the learning opportunities themselves. The Apple Store blends retail and school into a new type of learning environment that lets the customer learn anything, at any time, at any level, from experts, expert practitioners, and…

  15. Adaptive template generation for amyloid PET using a deep learning approach.

    Science.gov (United States)

    Kang, Seung Kwan; Seo, Seongho; Shin, Seong A; Byun, Min Soo; Lee, Dong Young; Kim, Yu Kyeong; Lee, Dong Soo; Lee, Jae Sung

    2018-05-11

    Accurate spatial normalization (SN) of amyloid positron emission tomography (PET) images for Alzheimer's disease assessment without coregistered anatomical magnetic resonance imaging (MRI) of the same individual is technically challenging. In this study, we applied deep neural networks to generate individually adaptive PET templates for robust and accurate SN of amyloid PET without using matched 3D MR images. Using 681 pairs of simultaneously acquired 11 C-PIB PET and T1-weighted 3D MRI scans of AD, MCI, and cognitively normal subjects, we trained and tested two deep neural networks [convolutional auto-encoder (CAE) and generative adversarial network (GAN)] that produce adaptive best PET templates. More specifically, the networks were trained using 685,100 pieces of augmented data generated by rotating 527 randomly selected datasets and validated using 154 datasets. The input to the supervised neural networks was the 3D PET volume in native space and the label was the spatially normalized 3D PET image using the transformation parameters obtained from MRI-based SN. The proposed deep learning approach significantly enhanced the quantitative accuracy of MRI-less amyloid PET assessment by reducing the SN error observed when an average amyloid PET template is used. Given an input image, the trained deep neural networks rapidly provide individually adaptive 3D PET templates without any discontinuity between the slices (in 0.02 s). As the proposed method does not require 3D MRI for the SN of PET images, it has great potential for use in routine analysis of amyloid PET images in clinical practice and research. © 2018 Wiley Periodicals, Inc.

  16. Impact of problem-based, active learning on graduation rates for 10 generations of Dutch medical students

    NARCIS (Netherlands)

    Schmidt, Henk G.; Cohen-Schotanus, Janke; Arends, Lidia R.

    We aimed to study the effects of active-learning curricula on graduation rates of students and on the length of time needed to graduate. Graduation rates for 10 generations of students enrolling in the eight Dutch medical schools between 1989 and 1998 were analysed. In addition, time needed to

  17. The Multigenerational Workforce within Two-Year Public Community Colleges: A Study of Generational Factors Affecting Employee Learning and Interaction

    Science.gov (United States)

    Starks, Florida Elizabeth

    2014-01-01

    The purpose of this quantitative study is to broaden multigenerational workforce research involving factors affecting employee learning and interaction by using a population of Baby Boomer, Generation X, and Millennial faculty and staff age cohorts employed at two-year public community college organizations. Researchers have studied…

  18. Generational, Cultural, and Linguistic Integration for Literacy Learning and Teaching in Uganda: Pedagogical Possibilities, Challenges, and Lessons from One NGO

    Science.gov (United States)

    Ngaka, Willy; Graham, Ross; Masaazi, Fred Masagazi; Anyandru, Elly Moses

    2016-01-01

    This qualitative case study focuses on a volunteer-led local NGO in Uganda to examine how integrating generations, cultures, and languages is enhancing literacy learning to help ethnically and linguistically diverse rural communities survive in the prevailing globally competitive neoliberal environment. Immersing the study in the social practices…

  19. Learning to Generate Sequences with Combination of Hebbian and Non-hebbian Plasticity in Recurrent Spiking Neural Networks.

    Science.gov (United States)

    Panda, Priyadarshini; Roy, Kaushik

    2017-01-01

    Synaptic Plasticity, the foundation for learning and memory formation in the human brain, manifests in various forms. Here, we combine the standard spike timing correlation based Hebbian plasticity with a non-Hebbian synaptic decay mechanism for training a recurrent spiking neural model to generate sequences. We show that inclusion of the adaptive decay of synaptic weights with standard STDP helps learn stable contextual dependencies between temporal sequences, while reducing the strong attractor states that emerge in recurrent models due to feedback loops. Furthermore, we show that the combined learning scheme suppresses the chaotic activity in the recurrent model substantially, thereby enhancing its' ability to generate sequences consistently even in the presence of perturbations.

  20. Employing UMLS for generating hints in a tutoring system for medical problem-based learning.

    Science.gov (United States)

    Kazi, Hameedullah; Haddawy, Peter; Suebnukarn, Siriwan

    2012-06-01

    While problem-based learning has become widely popular for imparting clinical reasoning skills, the dynamics of medical PBL require close attention to a small group of students, placing a burden on medical faculty, whose time is over taxed. Intelligent tutoring systems (ITSs) offer an attractive means to increase the amount of facilitated PBL training the students receive. But typical intelligent tutoring system architectures make use of a domain model that provides a limited set of approved solutions to problems presented to students. Student solutions that do not match the approved ones, but are otherwise partially correct, receive little acknowledgement as feedback, stifling broader reasoning. Allowing students to creatively explore the space of possible solutions is exactly one of the attractive features of PBL. This paper provides an alternative to the traditional ITS architecture by using a hint generation strategy that leverages a domain ontology to provide effective feedback. The concept hierarchy and co-occurrence between concepts in the domain ontology are drawn upon to ascertain partial correctness of a solution and guide student reasoning towards a correct solution. We describe the strategy incorporated in METEOR, a tutoring system for medical PBL, wherein the widely available UMLS is deployed and represented as the domain ontology. Evaluation of expert agreement with system generated hints on a 5-point likert scale resulted in an average score of 4.44 (Spearman's ρ=0.80, p<0.01). Hints containing partial correctness feedback scored significantly higher than those without it (Mann Whitney, p<0.001). Hints produced by a human expert received an average score of 4.2 (Spearman's ρ=0.80, p<0.01). Copyright © 2012 Elsevier Inc. All rights reserved.

  1. Biological oscillations for learning walking coordination: dynamic recurrent neural network functionally models physiological central pattern generator.

    Science.gov (United States)

    Hoellinger, Thomas; Petieau, Mathieu; Duvinage, Matthieu; Castermans, Thierry; Seetharaman, Karthik; Cebolla, Ana-Maria; Bengoetxea, Ana; Ivanenko, Yuri; Dan, Bernard; Cheron, Guy

    2013-01-01

    The existence of dedicated neuronal modules such as those organized in the cerebral cortex, thalamus, basal ganglia, cerebellum, or spinal cord raises the question of how these functional modules are coordinated for appropriate motor behavior. Study of human locomotion offers an interesting field for addressing this central question. The coordination of the elevation of the 3 leg segments under a planar covariation rule (Borghese et al., 1996) was recently modeled (Barliya et al., 2009) by phase-adjusted simple oscillators shedding new light on the understanding of the central pattern generator (CPG) processing relevant oscillation signals. We describe the use of a dynamic recurrent neural network (DRNN) mimicking the natural oscillatory behavior of human locomotion for reproducing the planar covariation rule in both legs at different walking speeds. Neural network learning was based on sinusoid signals integrating frequency and amplitude features of the first three harmonics of the sagittal elevation angles of the thigh, shank, and foot of each lower limb. We verified the biological plausibility of the neural networks. Best results were obtained with oscillations extracted from the first three harmonics in comparison to oscillations outside the harmonic frequency peaks. Physiological replication steadily increased with the number of neuronal units from 1 to 80, where similarity index reached 0.99. Analysis of synaptic weighting showed that the proportion of inhibitory connections consistently increased with the number of neuronal units in the DRNN. This emerging property in the artificial neural networks resonates with recent advances in neurophysiology of inhibitory neurons that are involved in central nervous system oscillatory activities. The main message of this study is that this type of DRNN may offer a useful model of physiological central pattern generator for gaining insights in basic research and developing clinical applications.

  2. Mirror Worlds: Examining the Affordances of a Next Generation Immersive Learning Environment

    Science.gov (United States)

    Gautam, Aakash; Williams, Daron; Terry, Krista; Robinson, Kelly; Newbill, Phyllis

    2018-01-01

    As technologies continue to develop and evolve, it is imperative that instructional technologists, learning scientists, and educators involved with examining learning affordances of emerging technologies investigate the potential of innovative environments to promote and facilitate learning. This paper, as such, will describe a newly developed…

  3. Three Generational Issues in Organizational Learning: Knowledge Management, Perspectives on Training and "Low-Stakes" Development

    Science.gov (United States)

    Sprinkle, Therese A.; Urick, Michael J.

    2018-01-01

    Purpose: Methods for facilitating learning and knowledge transfer in multigenerational workplaces are of importance to organizations. Yet, intergenerational learning is vastly understudied in academic organizational literature. This conceptual paper aims to recommend future directions for studying intergenerational learning by examining three…

  4. Appreciative Inquiry: Guided Reflection to Generate Change in Service-Learning Courses

    Science.gov (United States)

    Lahman, Mary

    2012-01-01

    Service-learning scholars contend that engaging students in systematic reflection during community service promotes one, if not all, of the following student outcomes: (1) academic learning; (2) personal growth; and (3) civic engagement. For communication instructors in particular, Applegate and Morreale (1999) proposed that service-learning both…

  5. Learning from peer feedback on student-generated multiple choice questions: Views of introductory physics students

    Science.gov (United States)

    Kay, Alison E.; Hardy, Judy; Galloway, Ross K.

    2018-06-01

    PeerWise is an online application where students are encouraged to generate a bank of multiple choice questions for their classmates to answer. After answering a question, students can provide feedback to the question author about the quality of the question and the question author can respond to this. Student use of, and attitudes to, this online community within PeerWise was investigated in two large first year undergraduate physics courses, across three academic years, to explore how students interact with the system and the extent to which they believe PeerWise to be useful to their learning. Most students recognized that there is value in engaging with PeerWise, and many students engaged deeply with the system, thinking critically about the quality of their submissions and reflecting on feedback provided to them. Students also valued the breadth of topics and level of difficulty offered by the questions, recognized the revision benefits afforded by the resource, and were often willing to contribute to the community by providing additional explanations and engaging in discussion.

  6. Informative sensor selection and learning for prediction of lower limb kinematics using generative stochastic neural networks.

    Science.gov (United States)

    Eunsuk Chong; Taejin Choi; Hyungmin Kim; Seung-Jong Kim; Yoha Hwang; Jong Min Lee

    2017-07-01

    We propose a novel approach of selecting useful input sensors as well as learning a mathematical model for predicting lower limb joint kinematics. We applied a feature selection method based on the mutual information called the variational information maximization, which has been reported as the state-of-the-art work among information based feature selection methods. The main difficulty in applying the method is estimating reliable probability density of input and output data, especially when the data are high dimensional and real-valued. We addressed this problem by applying a generative stochastic neural network called the restricted Boltzmann machine, through which we could perform sampling based probability estimation. The mutual informations between inputs and outputs are evaluated in each backward sensor elimination step, and the least informative sensor is removed with its network connections. The entire network is fine-tuned by maximizing conditional likelihood in each step. Experimental results are shown for 4 healthy subjects walking with various speeds, recording 64 sensor measurements including electromyogram, acceleration, and foot-pressure sensors attached on both lower limbs for predicting hip and knee joint angles. For test set of walking with arbitrary speed, our results show that our suggested method can select informative sensors while maintaining a good prediction accuracy.

  7. The effects of question-generation training on metacognitive knowledge, self regulation and learning approaches in science.

    Science.gov (United States)

    Cano García, Francisco; García, Ángela; Berbén, A B G; Pichardo, M C; Justicia, Fernando

    2014-01-01

    Although much research has examined the impact of question generation on students' reading comprehension and learning from lectures, far less research has analysed its influence on how students learn and study science. The present study aims to bridge this knowledge gap. Using a quasi-experimental design, three complete ninth-grade science classes, with a total of 72 students, were randomly assigned to three conditions (groups): (G1) questioning-training by providing prompts; (G2) question-generation without any explicit instruction; and (G3) no question control. Participants' pre-test and post-test self-reported measures of metacognitive knowledge, self-regulation and learning approaches were collected and data analysed with multivariate and univariate analyses of covariance. (a) MANCOVA revealed a significant effect for group; (b) ANCOVAs showed the highest average gains for G1 and statistically significant between-group differences in the two components of metacognition: metacognitive knowledge and self-regulation; and (c) the direction of these differences seemed to vary in each of these components. Question-generation training influenced how students learned and studied, specifically their metacognition, and it had a medium to large effect size, which was somewhat related to the prompts used.

  8. Social learning and human mate preferences: a potential mechanism for generating and maintaining between-population diversity in attraction

    Science.gov (United States)

    Little, Anthony C.; Jones, Benedict C.; DeBruine, Lisa M.; Caldwell, Christine A.

    2011-01-01

    Inspired by studies demonstrating mate-choice copying effects in non-human species, recent studies of attractiveness judgements suggest that social learning also influences human preferences. In the first part of our article, we review evidence for social learning effects on preferences in humans and other animals. In the second part, we present new empirical evidence that social learning not only influences the attractiveness of specific individuals, but can also generalize to judgements of previously unseen individuals possessing similar physical traits. The different conditions represent different populations and, once a preference arises in a population, social learning can lead to the spread of preferences within that population. In the final part of our article, we discuss the theoretical basis for, and possible impact of, biases in social learning whereby individuals may preferentially copy the choices of those with high status or better access to critical information about potential mates. Such biases could mean that the choices of a select few individuals carry the greatest weight, rapidly generating agreement in preferences within a population. Collectively, these issues suggest that social learning mechanisms encourage the spread of preferences for certain traits once they arise within a population and so may explain certain cross-cultural differences. PMID:21199841

  9. A novel approach to locomotion learning: Actor-Critic architecture using central pattern generators and dynamic motor primitives.

    Science.gov (United States)

    Li, Cai; Lowe, Robert; Ziemke, Tom

    2014-01-01

    In this article, we propose an architecture of a bio-inspired controller that addresses the problem of learning different locomotion gaits for different robot morphologies. The modeling objective is split into two: baseline motion modeling and dynamics adaptation. Baseline motion modeling aims to achieve fundamental functions of a certain type of locomotion and dynamics adaptation provides a "reshaping" function for adapting the baseline motion to desired motion. Based on this assumption, a three-layer architecture is developed using central pattern generators (CPGs, a bio-inspired locomotor center for the baseline motion) and dynamic motor primitives (DMPs, a model with universal "reshaping" functions). In this article, we use this architecture with the actor-critic algorithms for finding a good "reshaping" function. In order to demonstrate the learning power of the actor-critic based architecture, we tested it on two experiments: (1) learning to crawl on a humanoid and, (2) learning to gallop on a puppy robot. Two types of actor-critic algorithms (policy search and policy gradient) are compared in order to evaluate the advantages and disadvantages of different actor-critic based learning algorithms for different morphologies. Finally, based on the analysis of the experimental results, a generic view/architecture for locomotion learning is discussed in the conclusion.

  10. A Novel Approach to Locomotion Learning: Actor-Critic Architecture using Central Pattern Generators and Dynamic Motor Primitives

    Directory of Open Access Journals (Sweden)

    Cai eLi

    2014-10-01

    Full Text Available In this article, we propose an architecture of a bio-inspired controller that addresses the problem of learning different locomotion gaits for different robot morphologies. The modelling objective is split into two: baseline motion modelling and dynamics adaptation. Baseline motion modelling aims to achieve fundamental functions of a certain type of locomotion and dynamics adaptation provides a ``reshaping function for adapting the baseline motion to desired motion. Based on this assumption, a three-layer architecture is developed using central pattern generators (CPGs, a bio-inspired locomotor center for the the baseline motion and dynamic motor primitives (DMPs, a model with universal ``reshaping functions. In this article, we use this architecture with the actor-critic algorithms for finding a good ``reshaping function. In order to demonstrate the learning power of the actor-critic based architecture, we tested it on two experiments: 1 learning to crawl on a humanoid and, 2 learning to gallop on a puppy robot. Two types of actor-critic algorithms (policy search and policy gradient are compared in order to evaluate the advantages and disadvantages of different actor-critic based learning algorithms for different morphologies. Finally, based on the analysis of the experimental results, a generic view/architecture for locomotion learning is discussed in the conclusion.

  11. Teaching Sport Psychology to the XBox Generation: Further evidence for game-based learning

    OpenAIRE

    Manley, A; Whitaker, L; Patterson, L

    2012-01-01

    Objective: To extend recent research examining the impact of game-based activities on the learning experience of undergraduate psychology students. Design: A counterbalanced repeated measures design was employed to evaluate students’ learning experiences following their involvement in active game-based learning activities. Method: Students on a Level 5 sport psychology module (N=134) were asked to participate in four practical classes demonstrating the impact of psychological factors (e.g. an...

  12. Evaluation of machine learning tools for inspection of steam generator tube structures using pulsed eddy current

    Science.gov (United States)

    Buck, J. A.; Underhill, P. R.; Morelli, J.; Krause, T. W.

    2017-02-01

    Degradation of nuclear steam generator (SG) tubes and support structures can result in a loss of reactor efficiency. Regular in-service inspection, by conventional eddy current testing (ECT), permits detection of cracks, measurement of wall loss, and identification of other SG tube degradation modes. However, ECT is challenged by overlapping degradation modes such as might occur for SG tube fretting accompanied by tube off-set within a corroding ferromagnetic support structure. Pulsed eddy current (PEC) is an emerging technology examined here for inspection of Alloy-800 SG tubes and associated carbon steel drilled support structures. Support structure hole size was varied to simulate uniform corrosion, while SG tube was off-set relative to hole axis. PEC measurements were performed using a single driver with an 8 pick-up coil configuration in the presence of flat-bottom rectangular frets as an overlapping degradation mode. A modified principal component analysis (MPCA) was performed on the time-voltage data in order to reduce data dimensionality. The MPCA scores were then used to train a support vector machine (SVM) that simultaneously targeted four independent parameters associated with; support structure hole size, tube off-centering in two dimensions and fret depth. The support vector machine was trained, tested, and validated on experimental data. Results were compared with a previously developed artificial neural network (ANN) trained on the same data. Estimates of tube position showed comparable results between the two machine learning tools. However, the ANN produced better estimates of hole inner diameter and fret depth. The better results from ANN analysis was attributed to challenges associated with the SVM when non-constant variance is present in the data.

  13. Entropy method combined with extreme learning machine method for the short-term photovoltaic power generation forecasting

    International Nuclear Information System (INIS)

    Tang, Pingzhou; Chen, Di; Hou, Yushuo

    2016-01-01

    As the world’s energy problem becomes more severe day by day, photovoltaic power generation has opened a new door for us with no doubt. It will provide an effective solution for this severe energy problem and meet human’s needs for energy if we can apply photovoltaic power generation in real life, Similar to wind power generation, photovoltaic power generation is uncertain. Therefore, the forecast of photovoltaic power generation is very crucial. In this paper, entropy method and extreme learning machine (ELM) method were combined to forecast a short-term photovoltaic power generation. First, entropy method is used to process initial data, train the network through the data after unification, and then forecast electricity generation. Finally, the data results obtained through the entropy method with ELM were compared with that generated through generalized regression neural network (GRNN) and radial basis function neural network (RBF) method. We found that entropy method combining with ELM method possesses higher accuracy and the calculation is faster.

  14. Social Web Content Enhancement in a Distance Learning Environment: Intelligent Metadata Generation for Resources

    Science.gov (United States)

    García-Floriano, Andrés; Ferreira-Santiago, Angel; Yáñez-Márquez, Cornelio; Camacho-Nieto, Oscar; Aldape-Pérez, Mario; Villuendas-Rey, Yenny

    2017-01-01

    Social networking potentially offers improved distance learning environments by enabling the exchange of resources between learners. The existence of properly classified content results in an enhanced distance learning experience in which appropriate materials can be retrieved efficiently; however, for this to happen, metadata needs to be present.…

  15. A Generational Opportunity: A 21st Century Learning Content Delivery System

    Science.gov (United States)

    McElroy, Patrick

    2007-01-01

    This paper describes a collaboratively developed, open marketplace for network-based learning and research content for the higher education community. It explores how available technologies and standards can facilitate a new knowledge creation industry for higher education learning content that engages all stakeholders in new ways. The Advisory…

  16. The Role of a Reference Synthetic Data Generator within the Field of Learning Analytics

    Science.gov (United States)

    Berg, Alan\tM.; Mol, Stefan T.; Kismihók, Gábor; Sclater, Niall

    2016-01-01

    This paper details the anticipated impact of synthetic "big" data on learning analytics (LA) infrastructures, with a particular focus on data governance, the acceleration of service development, and the benchmarking of predictive models. By reviewing two cases, one at the sector-wide level (the Jisc learning analytics architecture) and…

  17. Concrescent Conversations: Generating a Cooperative Learning Experience in Principles of Management--A Postmodern Analysis

    Science.gov (United States)

    Akan, Obasi Haki

    2005-01-01

    By taking a postmodern ontology that elevates becoming over the modern ontology of being, the author of this article proposes a theory and describes a method that teachers can use to enhance students' cooperative learning of management principles. The author asserts that the social construction of learning groups is an effect of organizing…

  18. A hybrid fuzzy logic and extreme learning machine for improving efficiency of circulating water systems in power generation plant

    Science.gov (United States)

    Aziz, Nur Liyana Afiqah Abdul; Siah Yap, Keem; Afif Bunyamin, Muhammad

    2013-06-01

    This paper presents a new approach of the fault detection for improving efficiency of circulating water system (CWS) in a power generation plant using a hybrid Fuzzy Logic System (FLS) and Extreme Learning Machine (ELM) neural network. The FLS is a mathematical tool for calculating the uncertainties where precision and significance are applied in the real world. It is based on natural language which has the ability of "computing the word". The ELM is an extremely fast learning algorithm for neural network that can completed the training cycle in a very short time. By combining the FLS and ELM, new hybrid model, i.e., FLS-ELM is developed. The applicability of this proposed hybrid model is validated in fault detection in CWS which may help to improve overall efficiency of power generation plant, hence, consuming less natural recourses and producing less pollutions.

  19. A hybrid fuzzy logic and extreme learning machine for improving efficiency of circulating water systems in power generation plant

    International Nuclear Information System (INIS)

    Aziz, Nur Liyana Afiqah Abdul; Yap, Keem Siah; Bunyamin, Muhammad Afif

    2013-01-01

    This paper presents a new approach of the fault detection for improving efficiency of circulating water system (CWS) in a power generation plant using a hybrid Fuzzy Logic System (FLS) and Extreme Learning Machine (ELM) neural network. The FLS is a mathematical tool for calculating the uncertainties where precision and significance are applied in the real world. It is based on natural language which has the ability of c omputing the word . The ELM is an extremely fast learning algorithm for neural network that can completed the training cycle in a very short time. By combining the FLS and ELM, new hybrid model, i.e., FLS-ELM is developed. The applicability of this proposed hybrid model is validated in fault detection in CWS which may help to improve overall efficiency of power generation plant, hence, consuming less natural recourses and producing less pollutions.

  20. Ontario Power Generation Fukushima emergency response drill strengthens and lessons learned - Ontario Power Generation Fukushima Emergency Response Drill Highlights

    International Nuclear Information System (INIS)

    Miller, David W.

    2014-01-01

    Japan's Fukushima Daiichi severe nuclear accident in March 2011 has resulted in a reassessment of nuclear emergency response and preparedness in Canada. On May 26, 27 and 28, 2014 Ontario Power Generation (OPG) conducted the first North American full scale nuclear emergency response exercise designed to include regional, provincial and federal bodies as well as the utility. This paper describes the radiological aspects of the OPG Exercise Unified Response (ExUR) with emphasis on deployment of new Fukushima equipment on the Darlington site, management of emergency workers deplored in the vicinity of Darlington to collect environmental samples and radiation measurements, performance of dose calculations, communication of dose projections and protective actions to local, provincial and federal agencies and conduct of vehicle, truck and personnel monitoring and decontamination facilities. The ExUR involved more than 1000 personnel from local, provincial and federal bodies. Also, 200 OPG employees participated in the off-site emergency response duties. The objective of the ExUR was to test and enhance the preparedness of the utility (OPG), government and non-government agencies and communities to respond to a nuclear emergency. The types of radiological instrumentation and mobile facilities employed are highlighted in the presentation. The establishment of temporary emergency rooms with 8 beds and treatment facilities to manage potentially contaminated injuries from the nuclear emergency is also described. (author)

  1. Egg incubation effects generate positive correlations between size, speed and learning ability in young lizards.

    Science.gov (United States)

    Amiel, Joshua Johnstone; Lindström, Tom; Shine, Richard

    2014-03-01

    Previous studies have suggested that body size and locomotor performance are targets of Darwinian selection in reptiles. However, much of the variation in these traits may derive from phenotypically plastic responses to incubation temperature, rather than from underlying genetic variation. Intriguingly, incubation temperature may also influence cognitive traits such as learning ability. Therefore, we might expect correlations between a reptile's size, locomotor speed and learning ability either due to selection on all of these traits or due to environmental effects during egg incubation. In the present study, we incubated lizard eggs (Scincidae: Bassiana duperreyi) under 'hot' and 'cold' thermal regimes and then assessed differences in hatchling body size, running speed and learning ability. We measured learning ability using a Y-maze and a food reward. We found high correlations between size, speed and learning ability, using two different metrics to quantify learning (time to solution, and directness of route), and showed that environmental effects (incubation temperature) cause these correlations. If widespread, such correlations challenge any simple interpretation of fitness advantages due to body size or speed within a population; for example, survivors may be larger and faster than nonsurvivors because of differences in learning ability, not because of their size or speed.

  2. Learning Nursing in the Workplace Community: The Generation of Professional Capital

    Science.gov (United States)

    Gobbi, Mary

    This chapter explores the connections between learning, working and professional communities in nursing. It draws on experiences and research in nursing practice and education, where not only do isolated professionals learn as a result of their actions for patients and others, but those professionals are part of a community whose associated networks enable learning to occur. Several characteristics of this professional community are shared with those found in Communities of Practice (CoPs) (Lave and Wenger, 1991; Wenger, 1998), but the balance and importance of many elements can differ. For instance, whilst Lave and Wenger (1991) describe many aspects of situated learning in CoPs that apply to nurses, their model is of little help in understanding the ways in which other professions as well as patients/clients and carers influence the development of nursing practice. Therefore, I shall argue that it is not just the Community of Practice that we need to consider

  3. For the Love of the Game: Game- Versus Lecture-Based Learning With Generation Z Patients.

    Science.gov (United States)

    Adamson, Mary A; Chen, Hengyi; Kackley, Russell; Micheal, Alicia

    2018-02-01

    The current study evaluated adolescent patients' enjoyment of and knowledge gained from game-based learning compared with an interactive lecture format on the topic of mood disorders. It was hypothesized that game-based learning would be statistically more effective than a lecture in knowledge acquisition and satisfaction scores. A pre-post design was implemented in which a convenience sample of 160 adolescent patients were randomized to either a lecture (n = 80) or game-based (n = 80) group. Both groups completed a pretest/posttest and satisfaction survey. Results showed that both groups had significant improvement in knowledge from pretest compared to posttest. Game-based learning was statistically more effective than the interactive lecture in knowledge achievement and satisfaction scores. This finding supports the contention that game-based learning is an active technique that may be used with patient education. [Journal of Psychosocial Nursing and Mental Health Services, 56(2), 29-36.]. Copyright 2018, SLACK Incorporated.

  4. Learning and development across the generations: a cultural-historical study of everyday family practices.

    OpenAIRE

    Monk, Hilary

    2017-01-01

    Intergenerational research in familial and non-familial contexts appears to be strongly influenced by the positivist traditions of sociology where top-down transmission models of intergenerational learning and development dominate thinking and research. This thesis uses an interpretivist approach framed in Vygotsky’s (1987) cultural-historical theory and contributes alternative perspectives and interpretations of intergenerational learning and development. The study explored the relations a...

  5. Creative Generation of 3D Objects with Deep Learning and Innovation Engines

    DEFF Research Database (Denmark)

    Lehman, Joel Anthony; Risi, Sebastian; Clune, Jeff

    2016-01-01

    Advances in supervised learning with deep neural networks have enabled robust classification in many real world domains. An interesting question is if such advances can also be leveraged effectively for computational creativity. One insight is that because evolutionary algorithms are free from st...... creativity. The results of this automated process are interesting and recognizable 3D-printable objects, demonstrating the creative potential for combining evolutionary computation and deep learning in this way....

  6. Hebbian learning in a model with dynamic rate-coded neurons: an alternative to the generative model approach for learning receptive fields from natural scenes.

    Science.gov (United States)

    Hamker, Fred H; Wiltschut, Jan

    2007-09-01

    Most computational models of coding are based on a generative model according to which the feedback signal aims to reconstruct the visual scene as close as possible. We here explore an alternative model of feedback. It is derived from studies of attention and thus, probably more flexible with respect to attentive processing in higher brain areas. According to this model, feedback implements a gain increase of the feedforward signal. We use a dynamic model with presynaptic inhibition and Hebbian learning to simultaneously learn feedforward and feedback weights. The weights converge to localized, oriented, and bandpass filters similar as the ones found in V1. Due to presynaptic inhibition the model predicts the organization of receptive fields within the feedforward pathway, whereas feedback primarily serves to tune early visual processing according to the needs of the task.

  7. High Temperature Gas-Cooled Reactors Lessons Learned Applicable to the Next Generation Nuclear Plant

    Energy Technology Data Exchange (ETDEWEB)

    J. M. Beck; L. F. Pincock

    2011-04-01

    The purpose of this report is to identify possible issues highlighted by these lessons learned that could apply to the NGNP in reducing technical risks commensurate with the current phase of design. Some of the lessons learned have been applied to the NGNP and documented in the Preconceptual Design Report. These are addressed in the background section of this document and include, for example, the decision to use TRISO fuel rather than BISO fuel used in the Peach Bottom reactor; the use of a reactor pressure vessel rather than prestressed concrete found in Fort St. Vrain; and the use of helium as a primary coolant rather than CO2. Other lessons learned, 68 in total, are documented in Sections 2 through 6 and will be applied, as appropriate, in advancing phases of design. The lessons learned are derived from both negative and positive outcomes from prior HTGR experiences. Lessons learned are grouped according to the plant, areas, systems, subsystems, and components defined in the NGNP Preconceptual Design Report, and subsequent NGNP project documents.

  8. Designing Production Based Learning as a Basic Strategy for Creating Income Generating Units at Universitas Pendidikan Indonesia

    Science.gov (United States)

    Suryadi, D.; Supriatna, N.

    2018-02-01

    The establishment of Universitas Pendidikan Indonesia (later to be referred as UPI) Statute as a State-Owned State University (PTN-BH) has implications for UPI requirements. One of them is the need for UPI to generate an Income Generating Unit (IGU) of at least IDR 100 Billion (one hundred billion rupiah). This requirement is considered difficult since UPI is one of the universities whose focus is on the world of education and not the business and industry. Surely this becomes the thinking of the entire academic community to make a breakthrough by optimizing their potential. This study aims to find the pattern of learning practice that produces economic value products as one indicator of IGU value achievement as an effort to support UPI as PTN-BH. Learning strategy is done by designing and implementing the production base learning (PBL) approach as the basis strategy for the development of production units capable of becoming IGU in UPI. The research method used refers to research and development methods with adjustments taking into account the effectiveness in validating and conducting field model trials. The result of this research is the basic design of PBL model as the development strategy of production unit in the achievement of IGU UPI PTN-BH.

  9. Exploring Student-Generated Animations, Combined with a Representational Pedagogy, as a Tool for Learning in Chemistry

    Science.gov (United States)

    Yaseen, Zeynep; Aubusson, Peter

    2018-02-01

    This article describes an investigation into teaching and learning with student-generated animations combined with a representational pedagogy. In particular, it reports on interactive discussions that were stimulated by the students' own animations as well as their critiques of experts' animations. Animations representing views of states of matter provided a vehicle by which to investigate learning in a series of lessons. The study was implemented with Year 11 high school students. After students constructed, presented and discussed their animations, they watched and critiqued experts' animations. They were then interviewed about the teaching-learning process. Most students (91%) spoke positively about follow-up discussion classes, saying that their previous conceptions and understanding of states of matter had improved. They explained that they had identified some alternative conceptions, which they had held regarding states of matter and explained how their conceptions had changed. They reported that the teaching/learning process had helped them to develop a deeper understanding of the changing states of matter.

  10. Millennial generation student nurses' perceptions of the impact of multiple technologies on learning.

    Science.gov (United States)

    Montenery, Susan M; Walker, Marjorie; Sorensen, Elizabeth; Thompson, Rhonda; Kirklin, Dena; White, Robin; Ross, Carl

    2013-01-01

    To determine how millennial nursing students perceive the effects of instructional technology on their attentiveness, knowledge, critical thinking, and satisfaction. BACKGROUND Millennial learners develop critical thinking through experimentation, active participation, and multitasking with rapid shifts between technological devices. They desire immediate feedback. METHOD; A descriptive, longitudinal, anonymous survey design was used with a convenience sample of 108 sophomore, junior, and senior baccalaureate nursing students (participation rates 95 percent, winter, 85 percent, spring). Audience response, virtual learning, simulation, and computerized testing technologies were used. An investigator-designed instrument measured attentiveness, knowledge, critical thinking, and satisfaction (Cronbach's alphas 0.73, winter; 0.84, spring). Participants positively rated the audience response, virtual learning, and simulation instructional technologies on their class participation, learning, attention, and satisfaction. They strongly preferred computerized testing. Consistent with other studies, these students engaged positively with new teaching strategies using contemporary instructional technology. Faculty should consider using instructional technologies.

  11. Analysis of dynamic Cournot learning models for generation companies based on conjectural variations and forward expectation

    International Nuclear Information System (INIS)

    Gutierrez-Alcaraz, G.; Tovar-Hernandez, Jose H.; Moreno-Goytia, Edgar L.

    2009-01-01

    Electricity spot markets generally operate on an hourly basis; under this condition GENCOs can closely observe their competitors' market behavior. For this purposes, a detailed dynamic model is one of the tools used by GENCOs to understand the behavioral variations of competitors over time. The required abilities to rapidly adjust one's own decision-making create a need for new learning procedures and models. Conjectural variations (CV) have been proposed as a learning approach. In this paper a model based on forward expectations (FE) is proposed as a learning approach, and through illustrative examples it is shown that the market equilibria found by the CV model are also obtained by the FE model. (author)

  12. The research-based learning development model as a foundation in generating research ideas

    Science.gov (United States)

    Puspitasari, Poppy; Dika, Johan Wayan; Permanasari, Avita Ayu

    2017-09-01

    Research Based Learning is learning that requires students to have exploration skills related to their field. By doing so, students are encouraged to create skills in managing the higherorder of abstraction in order to resolve any problems encountered. The study was done to make the schemes and sequences of learning needed by the students in order to help them to explore first ideas for their upcoming thesis. The scheme development resulted in five stages consisting of 1) identifying research journals; 2) track the development of research topics; 3) reviewing research journals; 4) discussing the results of the reviews; and 5) formulating the research topic. Furthermore, the application of 5 the stage receives percentage agreement of students was 85.9%. Therefore, it can be noted that the application of the scheme is definitely a help for students to find research ideas.

  13. First-Generation College Student Dissertation Abstracts: Research Strategies, Topical Analysis, and Lessons Learned

    Science.gov (United States)

    Banning, James H.

    2014-01-01

    First-generation college students are students whose parents or guardians did not obtain a four year college degree (Davis, 2012). As a group these students make up a large part of the college student population and are often reported to encounter difficulties in their campus experience. While the topic of first-generation student has received…

  14. Finishing and Special Motifs: Lessons Learned from CRISPR Analysis Using Next-Generation Draft Sequences (7th Annual SFAF Meeting, 2012)

    Energy Technology Data Exchange (ETDEWEB)

    Campbell, Catherine

    2012-06-01

    Catherine Campbell on "Finishing and Special Motifs: Lessons learned from CRISPR analysis using next-generation draft sequences" at the 2012 Sequencing, Finishing, Analysis in the Future Meeting held June 5-7, 2012 in Santa Fe, New Mexico.

  15. When Success Is the Only Option: Designing Competency-Based Pathways for Next Generation Learning

    Science.gov (United States)

    Sturgis, Chris; Patrick, Susan

    2010-01-01

    This exploration into competency-based innovation at the school, district, and state levels suggests that competency-based pathways are a re-engineering of this nation's education system around learning--a re-engineering designed for success in which failure is no longer viable. This discussion draws on interviews and site visits with innovators…

  16. When Failure Is Not An Option: Designing Competency-Based Pathways for Next Generation Learning

    Science.gov (United States)

    Sturgis, Chris; Patrick, Susan

    2010-01-01

    This exploration into competency-based innovation at the school, district, and state levels suggests that competency-based pathways are a re-engineering of this nation's education system around learning--a re-engineering designed for success in which failure is no longer an option. Competency-based approaches build upon standards reforms, offering…

  17. The role of a reference synthetic data generator within the field of learning analytics

    NARCIS (Netherlands)

    Berg, A.M.; Mol, S.T.; Kismihók, G.; Sclater, N.

    2016-01-01

    This paper details the anticipated impact of synthetic ‘big’ data on learning analytics (LA) infrastructures, with a particular focus on data governance, the acceleration of service development, and the benchmarking of predictive models. By reviewing two cases, one at sector wide level and the other

  18. Which Technique Is Most Effective for Learning Declarative Concepts--Provided Examples, Generated Examples, or Both?

    Science.gov (United States)

    Zamary, Amanda; Rawson, Katherine A.

    2018-01-01

    Students in many courses are commonly expected to learn declarative concepts, which are abstract concepts denoted by key terms with short definitions that can be applied to a variety of scenarios as reported by Rawson et al. ("Educational Psychology Review" 27:483-504, 2015). Given that declarative concepts are common and foundational in…

  19. Plasticity in learning causes immediate and trans-generational changes in allocation of resources.

    Science.gov (United States)

    Snell-Rood, Emilie C; Davidowitz, Goggy; Papaj, Daniel R

    2013-08-01

    Plasticity in the development and expression of behavior may allow organisms to cope with novel and rapidly changing environments. However, plasticity itself may depend on the developmental experiences of an individual. For instance, individuals reared in complex, enriched environments develop enhanced cognitive abilities as a result of increased synaptic connections and neurogenesis. This suggests that costs associated with behavioral plasticity-in particular, increased investment in "self" at the expense of reproduction-may also be flexible. Using butterflies as a system, this work tests whether allocation of resources changes as a result of experiences in "difficult" environments that require more investment in learning. We contrast allocation of resources among butterflies with experience in environments that vary in the need for learning. Butterflies with experience searching for novel (i.e., red) hosts, or searching in complex non-host environments, allocate more resources (protein and carbohydrate reserves) to their own flight muscle. In addition, butterflies with experience in these more difficult environments allocate more resources per individual offspring (i.e., egg size and/or lipid reserves). This results in a mother's experience having significant effects on the growth of her offspring (i.e., dry mass and wing length). A separate study showed this re-allocation of resources comes at the expense of lifetime fecundity. These results suggest that investment in learning, and associated changes in life history, can be adjusted depending on an individual's current need, and their offspring's future needs, for learning.

  20. Narrative Generates a Learning Spiral in Education: Recognition, Reflection, and Reconstruction

    Science.gov (United States)

    Liu, Xueyang

    2015-01-01

    The narrative form is everywhere. It can be as common as our daily stories and as significant as a great novel. Narrating can be a process of self-assessment and introspection around a certain theme. In this sense it is important in education. In this paper I argue that people learn not only by listening to narrative but also by teaching others…

  1. THIRD GENERATION TELEPHONY: NEW TECHNOLOGICAL SUPPORT FOR COMPUTER ASSISTED LANGUAGE LEARNING

    Directory of Open Access Journals (Sweden)

    Jose Carlos Garcia Cabrero

    2002-06-01

    Full Text Available The expansion of the lnternet has Ied to the development of distance teaching models based on the net (e learning. One of the crucial factors in this phenomenon is the continuous training required by workers to maintain or improve their professional skills. Foreign languages are, without doubt, one of the most in demand subjects. This is because they are needed for comunication in an increasingly globalized world. The development of new wireless communication technologies, UMTS or 3G nets, and their corresponding access terminals (Palm-size PCs, PPCs, with wireless telephone connection. also called smart-phones. will enable solutions to be found for some of the problems Iaeed hy current e-learning users. These problems include access speed and the physical constraints of tlhe ( The new wireless comunication technologies will bring other benefits like portability. always on-line, etc. This article presents one on' the world's first prototypes of language learning software or smart-phones, produced by the Laboratorio de lngenieria Didactica e lngenieria Linguistica of UNED (Didactic Engineering and Linguistic Engineering Laboratory (LIDIL, http://www.vip.~ined.es. i¿le Enllearning Spanish for business.

  2. Leaders Behaving Badly: Using Power to Generate Undiscussables in Action Learning Sets

    Science.gov (United States)

    Donovan, Paul Jeffrey

    2014-01-01

    "Undiscussables" are topics associated with threat or embarrassment that are avoided by groups, where that avoidance is also not discussed. Their deleterious effect on executive groups has been a point of discussion for several decades. More recently critical action learning (AL) has brought a welcome focus to power relations within AL…

  3. Bridging the Generation Gap: "Growing Golf" through an Action Learning Activity

    Science.gov (United States)

    Elbert, Norb; Cumiskey, Kevin J.

    2014-01-01

    This paper describes an action learning simulation designed for a Professional Golf Management (PGM) program housed in a College of Business of a public university. The PGA Golf Management University Program, a 4.5- to 5-year college curriculum for aspiring PGA Professionals is offered at 19 PGA accredited universities nationwide. The program…

  4. Combining Generative and Discriminative Representation Learning for Lung CT Analysis With Convolutional Restricted Boltzmann Machines

    NARCIS (Netherlands)

    G. van Tulder (Gijs); M. de Bruijne (Marleen)

    2016-01-01

    textabstractThe choice of features greatly influences the performance of a tissue classification system. Despite this, many systems are built with standard, predefined filter banks that are not optimized for that particular application. Representation learning methods such as restricted Boltzmann

  5. The e-Generation: The Use of Technology for Foreign Language Learning

    Science.gov (United States)

    Gonzalez-Vera, Pilar

    2016-01-01

    After the Bologna Process, European Higher Education was reformulated as a response to a change of roles in higher education in a globalised society. The implementation of a new system of credits, the European Credit Transfer System (ECTS), implied an enormous increase of autonomous learning hours. The high percentage of student workload reflected…

  6. Generative Learning Strategy Use and Self-Regulatory Prompting in Digital Text

    Science.gov (United States)

    Reid, Alan J.; Morrison, Gary M.

    2014-01-01

    The digital revolution is shifting print-based textbooks to digital text, and it has afforded the opportunity to incorporate meaningful learning strategies and otherwise separate metacognitive activities directly into these texts as embedded support. A sample of 89 undergraduates read a digital, expository text on the basics of photography. The…

  7. Automatic Earthquake Detection by Active Learning

    Science.gov (United States)

    Bergen, K.; Beroza, G. C.

    2017-12-01

    In recent years, advances in machine learning have transformed fields such as image recognition, natural language processing and recommender systems. Many of these performance gains have relied on the availability of large, labeled data sets to train high-accuracy models; labeled data sets are those for which each sample includes a target class label, such as waveforms tagged as either earthquakes or noise. Earthquake seismologists are increasingly leveraging machine learning and data mining techniques to detect and analyze weak earthquake signals in large seismic data sets. One of the challenges in applying machine learning to seismic data sets is the limited labeled data problem; learning algorithms need to be given examples of earthquake waveforms, but the number of known events, taken from earthquake catalogs, may be insufficient to build an accurate detector. Furthermore, earthquake catalogs are known to be incomplete, resulting in training data that may be biased towards larger events and contain inaccurate labels. This challenge is compounded by the class imbalance problem; the events of interest, earthquakes, are infrequent relative to noise in continuous data sets, and many learning algorithms perform poorly on rare classes. In this work, we investigate the use of active learning for automatic earthquake detection. Active learning is a type of semi-supervised machine learning that uses a human-in-the-loop approach to strategically supplement a small initial training set. The learning algorithm incorporates domain expertise through interaction between a human expert and the algorithm, with the algorithm actively posing queries to the user to improve detection performance. We demonstrate the potential of active machine learning to improve earthquake detection performance with limited available training data.

  8. Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model

    OpenAIRE

    Lu, Jiasen; Kannan, Anitha; Yang, Jianwei; Parikh, Devi; Batra, Dhruv

    2017-01-01

    We present a novel training framework for neural sequence models, particularly for grounded dialog generation. The standard training paradigm for these models is maximum likelihood estimation (MLE), or minimizing the cross-entropy of the human responses. Across a variety of domains, a recurring problem with MLE trained generative neural dialog models (G) is that they tend to produce 'safe' and generic responses ("I don't know", "I can't tell"). In contrast, discriminative dialog models (D) th...

  9. Milestones and Millennials: A Perfect Pairing-Competency-Based Medical Education and the Learning Preferences of Generation Y.

    Science.gov (United States)

    Desy, Janeve R; Reed, Darcy A; Wolanskyj, Alexandra P

    2017-02-01

    Millennials are quickly becoming the most prevalent generation of medical learners. These individuals have a unique outlook on education and have different preferences and expectations than their predecessors. As evidenced by its implementation by the Accreditation Council for Graduate Medical Education in the United States and the Royal College of Physicians and Surgeons in Canada, competency based medical education is rapidly gaining international acceptance. Characteristics of competency based medical education can be perfectly paired with Millennial educational needs in several dimensions including educational expectations, the educational process, attention to emotional quotient and professionalism, assessment, feedback, and intended outcomes. We propose that with its attention to transparency, personalized learning, and frequent formative assessment, competency based medical education is an ideal fit for the Millennial generation as it realigns education and assessment with the needs of these 21st century learners. Copyright © 2016 Mayo Foundation for Medical Education and Research. Published by Elsevier Inc. All rights reserved.

  10. 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.

  11. On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks.

    Directory of Open Access Journals (Sweden)

    Paul Tonelli

    Full Text Available A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1 the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2 synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT. Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1 in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2 whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities.

  12. Novel Machine Learning-Based Techniques for Efficient Resource Allocation in Next Generation Wireless Networks

    KAUST Repository

    AlQuerm, Ismail A.

    2018-02-21

    There is a large demand for applications of high data rates in wireless networks. These networks are becoming more complex and challenging to manage due to the heterogeneity of users and applications specifically in sophisticated networks such as the upcoming 5G. Energy efficiency in the future 5G network is one of the essential problems that needs consideration due to the interference and heterogeneity of the network topology. Smart resource allocation, environmental adaptivity, user-awareness and energy efficiency are essential features in the future networks. It is important to support these features at different networks topologies with various applications. Cognitive radio has been found to be the paradigm that is able to satisfy the above requirements. It is a very interdisciplinary topic that incorporates flexible system architectures, machine learning, context awareness and cooperative networking. Mitola’s vision about cognitive radio intended to build context-sensitive smart radios that are able to adapt to the wireless environment conditions while maintaining quality of service support for different applications. Artificial intelligence techniques including heuristics algorithms and machine learning are the shining tools that are employed to serve the new vision of cognitive radio. In addition, these techniques show a potential to be utilized in an efficient resource allocation for the upcoming 5G networks’ structures such as heterogeneous multi-tier 5G networks and heterogeneous cloud radio access networks due to their capability to allocate resources according to real-time data analytics. In this thesis, we study cognitive radio from a system point of view focusing closely on architectures, artificial intelligence techniques that can enable intelligent radio resource allocation and efficient radio parameters reconfiguration. We propose a modular cognitive resource management architecture, which facilitates a development of flexible control for

  13. Learning from examples - Generation and evaluation of decision trees for software resource analysis

    Science.gov (United States)

    Selby, Richard W.; Porter, Adam A.

    1988-01-01

    A general solution method for the automatic generation of decision (or classification) trees is investigated. The approach is to provide insights through in-depth empirical characterization and evaluation of decision trees for software resource data analysis. The trees identify classes of objects (software modules) that had high development effort. Sixteen software systems ranging from 3,000 to 112,000 source lines were selected for analysis from a NASA production environment. The collection and analysis of 74 attributes (or metrics), for over 4,700 objects, captured information about the development effort, faults, changes, design style, and implementation style. A total of 9,600 decision trees were automatically generated and evaluated. The trees correctly identified 79.3 percent of the software modules that had high development effort or faults, and the trees generated from the best parameter combinations correctly identified 88.4 percent of the modules on the average.

  14. Learning a generative model of images by factoring appearance and shape.

    Science.gov (United States)

    Le Roux, Nicolas; Heess, Nicolas; Shotton, Jamie; Winn, John

    2011-03-01

    Computer vision has grown tremendously in the past two decades. Despite all efforts, existing attempts at matching parts of the human visual system's extraordinary ability to understand visual scenes lack either scope or power. By combining the advantages of general low-level generative models and powerful layer-based and hierarchical models, this work aims at being a first step toward richer, more flexible models of images. After comparing various types of restricted Boltzmann machines (RBMs) able to model continuous-valued data, we introduce our basic model, the masked RBM, which explicitly models occlusion boundaries in image patches by factoring the appearance of any patch region from its shape. We then propose a generative model of larger images using a field of such RBMs. Finally, we discuss how masked RBMs could be stacked to form a deep model able to generate more complicated structures and suitable for various tasks such as segmentation or object recognition.

  15. Laying the Groundwork: Lessons Learned from the Telecommunications Industry for Distributed Generation; Preprint

    Energy Technology Data Exchange (ETDEWEB)

    Wise, A. L.

    2008-05-01

    The telecommunications industry went through growing pains in the past that hold some interesting lessons for the growing distributed generation (DG) industry. The technology shifts and stakeholders involved with the historic market transformation of the telecommunications sector mirror similar factors involved in distributed generation today. An examination of these factors may inform best practices when approaching the conduits necessary to accelerate the shifting of our nation's energy system to cleaner forms of generation and use. From a technical perspective, the telecom industry in the 1990s saw a shift from highly centralized systems that had no capacity for adaptation to highly adaptive, distributed network systems. From a management perspective, the industry shifted from small, private-company structures to big, capital-intensive corporations. This presentation will explore potential correlation and outline the lessons that we can take away from this comparison.

  16. Underspecification-Based Grammatical Feedback Generation Tailored to the Learner's Current Acquisition Level in an e-Learning System for German as Second Language

    Science.gov (United States)

    Harbusch, Karin; Cameran, Christel-Joy; Härtel, Johannes

    2014-01-01

    We present a new feedback strategy implemented in a natural language generation-based e-learning system for German as a second language (L2). Although the system recognizes a large proportion of the grammar errors in learner-produced written sentences, its automatically generated feedback only addresses errors against rules that are relevant at…

  17. Iterative learning control with applications in energy generation, lasers and health care.

    Science.gov (United States)

    Rogers, E; Tutty, O R

    2016-09-01

    Many physical systems make repeated executions of the same finite time duration task. One example is a robot in a factory or warehouse whose task is to collect an object in sequence from a location, transfer it over a finite duration, place it at a specified location or on a moving conveyor and then return for the next one and so on. Iterative learning control was especially developed for systems with this mode of operation and this paper gives an overview of this control design method using relatively recent relevant applications in wind turbines, free-electron lasers and health care, as exemplars to demonstrate its applicability.

  18. The obser-view: a method of generating data and learning

    DEFF Research Database (Denmark)

    Kragelund, Linda

    2013-01-01

    nurses' learning processes because the students wanted to talk with me, the researcher, after I had observed them. Conducting a non-scripted interview immediately post-observation became the obser-view. Data sources: Eleven student nurses doing clinical placement in psychiatric hospital wards...... research transparent, as the obser-view both would give me an inside, an outside and an inter-subjective perspective on data and increase the internal validity of the research. Conclusion: During the obser-view dialogue the researcher, as a catalyst for reflection, has the opportunity to get the research...

  19. Harnessing user generated multimedia content in the creation of collaborative classification structures and retrieval learning games

    Science.gov (United States)

    Borchert, Otto Jerome

    This paper describes a software tool to assist groups of people in the classification and identification of real world objects called the Classification, Identification, and Retrieval-based Collaborative Learning Environment (CIRCLE). A thorough literature review identified current pedagogical theories that were synthesized into a series of five tasks: gathering, elaboration, classification, identification, and reinforcement through game play. This approach is detailed as part of an included peer reviewed paper. Motivation is increased through the use of formative and summative gamification; getting points completing important portions of the tasks and playing retrieval learning based games, respectively, which is also included as a peer-reviewed conference proceedings paper. Collaboration is integrated into the experience through specific tasks and communication mediums. Implementation focused on a REST-based client-server architecture. The client is a series of web-based interfaces to complete each of the tasks, support formal classroom interaction through faculty accounts and student tracking, and a module for peers to help each other. The server, developed using an in-house JavaMOO platform, stores relevant project data and serves data through a series of messages implemented as a JavaScript Object Notation Application Programming Interface (JSON API). Through a series of two beta tests and two experiments, it was discovered the second, elaboration, task requires considerable support. While students were able to properly suggest experiments and make observations, the subtask involving cleaning the data for use in CIRCLE required extra support. When supplied with more structured data, students were enthusiastic about the classification and identification tasks, showing marked improvement in usability scores and in open ended survey responses. CIRCLE tracks a variety of educationally relevant variables, facilitating support for instructors and researchers. Future

  20. AUTOMOTIVE DIESEL MAINTENANCE 2. UNIT XVI, LEARNING ABOUT AC GENERATOR (ALTERNATOR) PRINCIPLES (PART I).

    Science.gov (United States)

    Human Engineering Inst., Cleveland, OH.

    THIS MODULE OF A 25-MODULE COURSE IS DESIGNED TO DEVELOP AN UNDERSTANDING OF THE OPERATING PRINCIPLES OF ALTERNATING CURRENT GENERATORS USED ON DIESEL POWERED EQUIPMENT. TOPICS ARE REVIEWING ELECTRICAL FUNDAMENTALS, AND OPERATING PRINCIPLES OF ALTERNATORS. THE MODULE CONSISTS OF A SELF-INSTRUCTIONAL PROGRAMED TRAINING FILM "AC GENERATORS…

  1. Rotor Position Estimation for Switched Reluctance Wind Generator Using Extreme Learning Machine

    DEFF Research Database (Denmark)

    Wang, Chao; Liu, Xiao; Chen, Zhe

    2014-01-01

    Switched reluctance generator (SRG) is becoming more and more attractive in wind energy applications mainly because of its high fault tolerant ability and high reliability. The position sensor is one of the vulnerable points of the SRG when exposed to harsh environments such as offshore where man...

  2. Adapting Training to Meet the Preferred Learning Styles of Different Generations

    Science.gov (United States)

    Urick, Michael

    2017-01-01

    This article considers how training professionals can respond to differences in training preferences between generational groups. It adopts two methods. First, it surveys the existing research and finds generally that preferences for training approaches can differ between groups and specifically that younger employees are perceived to leverage…

  3. How First-Generation Students Learn to Navigate Education Systems: A Case Study of First Graduate

    Science.gov (United States)

    Kirshner, Ben; Saldivar, Manuel Gerardo; Tracy, Rita

    2011-01-01

    Students from underrepresented groups who seek to become the first in their family to attend college confront economically and racially stratified education systems. This article reports findings from an evaluation of First Graduate, an organization that offers college advising, mentoring, tutoring, and case management to first-generation students…

  4. Workplaces that Support High-Performing Teaching and Learning: Insights from Generation Y Teachers

    Science.gov (United States)

    Coggshall, Jane G.; Behrstock-Sherratt, Ellen; Drill, Karen

    2011-01-01

    Generation Y public school teachers--those born between 1977 and 1995-- who have been serving students for nearly a decade now, represent an increasingly large proportion of the teaching workforce, and, with concerted support, promise to help bring needed transformation to schools that too often remain stuck in an earlier age. Members of this…

  5. Evaluation of Computer Tools for Idea Generation and Team Formation in Project-Based Learning

    Science.gov (United States)

    Ardaiz-Villanueva, Oscar; Nicuesa-Chacon, Xabier; Brene-Artazcoz, Oscar; Sanz de Acedo Lizarraga, Maria Luisa; Sanz de Acedo Baquedano, Maria Teresa

    2011-01-01

    The main objective of this research was to validate the effectiveness of Wikideas and Creativity Connector tools to stimulate the generation of ideas and originality by university students organized into groups according to their indexes of creativity and affinity. Another goal of the study was to evaluate the classroom climate created by these…

  6. Study Navigator: An Algorithmically Generated Aid for Learning from Electronic Textbooks

    Science.gov (United States)

    Agrawal, Rakesh; Gollapudi, Sreenivas; Kannan, Anitha; Kenthapadi, Krishnaram

    2014-01-01

    We present "study navigator," an algorithmically-generated aid for enhancing the experience of studying from electronic textbooks. The study navigator for a section of the book consists of helpful "concept references" for understanding this section. Each concept reference is a pair consisting of a concept phrase explained…

  7. Cross-View Action Recognition via Transferable Dictionary Learning.

    Science.gov (United States)

    Zheng, Jingjing; Jiang, Zhuolin; Chellappa, Rama

    2016-05-01

    Discriminative appearance features are effective for recognizing actions in a fixed view, but may not generalize well to a new view. In this paper, we present two effective approaches to learn dictionaries for robust action recognition across views. In the first approach, we learn a set of view-specific dictionaries where each dictionary corresponds to one camera view. These dictionaries are learned simultaneously from the sets of correspondence videos taken at different views with the aim of encouraging each video in the set to have the same sparse representation. In the second approach, we additionally learn a common dictionary shared by different views to model view-shared features. This approach represents the videos in each view using a view-specific dictionary and the common dictionary. More importantly, it encourages the set of videos taken from the different views of the same action to have the similar sparse representations. The learned common dictionary not only has the capability to represent actions from unseen views, but also makes our approach effective in a semi-supervised setting where no correspondence videos exist and only a few labeled videos exist in the target view. The extensive experiments using three public datasets demonstrate that the proposed approach outperforms recently developed approaches for cross-view action recognition.

  8. The BRAIN Initiative Cell Census Consortium: Lessons Learned toward Generating a Comprehensive Brain Cell Atlas.

    Science.gov (United States)

    Ecker, Joseph R; Geschwind, Daniel H; Kriegstein, Arnold R; Ngai, John; Osten, Pavel; Polioudakis, Damon; Regev, Aviv; Sestan, Nenad; Wickersham, Ian R; Zeng, Hongkui

    2017-11-01

    A comprehensive characterization of neuronal cell types, their distributions, and patterns of connectivity is critical for understanding the properties of neural circuits and how they generate behaviors. Here we review the experiences of the BRAIN Initiative Cell Census Consortium, ten pilot projects funded by the U.S. BRAIN Initiative, in developing, validating, and scaling up emerging genomic and anatomical mapping technologies for creating a complete inventory of neuronal cell types and their connections in multiple species and during development. These projects lay the foundation for a larger and longer-term effort to generate whole-brain cell atlases in species including mice and humans. Copyright © 2017 Elsevier Inc. All rights reserved.

  9. Thirty years of advocacy in San Francisco: lessons learned and the next generation of leadership.

    Science.gov (United States)

    Lee, Ntanya

    2008-01-01

    Professional advocacy organizations are often challenged by the question of their authentic community representation and their ability to balance short-term pragmatism with strategic plans for long-term, systemic change. Coleman Advocates, one of the nation's most effective child advocacy organizations, has taken up this challenge under the leadership of a next-generation leader of color who followed a dynamic director of the baby boom generation. In this piece, Coleman's thirty years of social change strategies are analyzed from the perspective of this new executive director, who has facilitated the latest organizational shift that deepens its commitment to building bottom-up grassroots leadership and community power while keeping the best of the professional, staff-led advocacy model. Issues of race, accountability, power, and movement building are addressed through the lens of one organization's evolution, with the goal of building a long-term movement that will achieve racial and economic equity for all children and families.

  10. Eddy Current Signature Classification of Steam Generator Tube Defects Using A Learning Vector Quantization Neural Network

    International Nuclear Information System (INIS)

    Garcia, Gabe V.

    2005-01-01

    A major cause of failure in nuclear steam generators is degradation of their tubes. Although seven primary defect categories exist, one of the principal causes of tube failure is intergranular attack/stress corrosion cracking (IGA/SCC). This type of defect usually begins on the secondary side surface of the tubes and propagates both inwards and laterally. In many cases this defect is found at or near the tube support plates

  11. Improving the quality of competition in the US power generation market: Lessons learned in the UK

    International Nuclear Information System (INIS)

    McNair, K.; Tivey, B.

    1993-01-01

    This presentation examines the effects of deregulation and liberalization of the power generation market in the United Kingdom and the potential for translation of that experience to other markets. The topics of the presentation include the changes in the UK, the pool and electricity contracts, competition, continued state ownership of nuclear power plants, transitioning the coal industry to free market conditions, the benefits, and the impact of privatization on the National Power government agency

  12. Application of Next Generation Sequencing in Mammalian Embryogenomics: Lessons Learned from Endogenous Betaretroviruses of Sheep

    Science.gov (United States)

    Spencer, Thomas E.; Palmarini, Massimo

    2012-01-01

    Endogenous retroviruses (ERVs) are present in the genome of all vertebrates and are remnants of ancient exogenous retroviral infections of the host germline transmitted vertically from generation to generation. The sheep genome contains 27 JSRV-related endogenous betaretroviruses (enJSRVs) related to the pathogenic Jaagsiekte sheep retrovirus (JSRV) that have been integrating in the host genome for the last 5 to 7 million years. The exogenous JSRV is a causative agent of a transmissible lung cancer in sheep, and enJSRVs are able to protect the host against JSRV infection. In sheep, the enJSRVs are most abundantly expressed in the uterine epithelia as well as in the conceptus (embryo and associated extraembryonic membranes) trophectoderm. Sixteen of the 27 enJSRV loci contain an envelope (env) gene with an intact open reading frame, and in utero loss-of-function experiments found the enJSRVs Env to be essential for trophoblast outgrowth and conceptus elongation. Collectively, available evidence supports the ideas that genes captured from ancestral retroviruses were pivotal in the acquisition of new, important functions in mammalian evolution and were positively selected for biological roles in genome plasticity, protection of the host against infection of related pathogenic and exogenous retroviruses, and a convergent physiological role in placental morphogenesis and thus mammalian reproduction. The discovery of ERVs in mammals was initially based on molecular cloning discovery techniques and will be boosted forward by next generation sequencing technologies and in silico discovery techniques. PMID:22951118

  13. GUDM: Automatic Generation of Unified Datasets for Learning and Reasoning in Healthcare.

    Science.gov (United States)

    Ali, Rahman; Siddiqi, Muhammad Hameed; Idris, Muhammad; Ali, Taqdir; Hussain, Shujaat; Huh, Eui-Nam; Kang, Byeong Ho; Lee, Sungyoung

    2015-07-02

    A wide array of biomedical data are generated and made available to healthcare experts. However, due to the diverse nature of data, it is difficult to predict outcomes from it. It is therefore necessary to combine these diverse data sources into a single unified dataset. This paper proposes a global unified data model (GUDM) to provide a global unified data structure for all data sources and generate a unified dataset by a "data modeler" tool. The proposed tool implements user-centric priority based approach which can easily resolve the problems of unified data modeling and overlapping attributes across multiple datasets. The tool is illustrated using sample diabetes mellitus data. The diverse data sources to generate the unified dataset for diabetes mellitus include clinical trial information, a social media interaction dataset and physical activity data collected using different sensors. To realize the significance of the unified dataset, we adopted a well-known rough set theory based rules creation process to create rules from the unified dataset. The evaluation of the tool on six different sets of locally created diverse datasets shows that the tool, on average, reduces 94.1% time efforts of the experts and knowledge engineer while creating unified datasets.

  14. Automated generation and ensemble-learned matching of X-ray absorption spectra

    Science.gov (United States)

    Zheng, Chen; Mathew, Kiran; Chen, Chi; Chen, Yiming; Tang, Hanmei; Dozier, Alan; Kas, Joshua J.; Vila, Fernando D.; Rehr, John J.; Piper, Louis F. J.; Persson, Kristin A.; Ong, Shyue Ping

    2018-03-01

    X-ray absorption spectroscopy (XAS) is a widely used materials characterization technique to determine oxidation states, coordination environment, and other local atomic structure information. Analysis of XAS relies on comparison of measured spectra to reliable reference spectra. However, existing databases of XAS spectra are highly limited both in terms of the number of reference spectra available as well as the breadth of chemistry coverage. In this work, we report the development of XASdb, a large database of computed reference XAS, and an Ensemble-Learned Spectra IdEntification (ELSIE) algorithm for the matching of spectra. XASdb currently hosts more than 800,000 K-edge X-ray absorption near-edge spectra (XANES) for over 40,000 materials from the open-science Materials Project database. We discuss a high-throughput automation framework for FEFF calculations, built on robust, rigorously benchmarked parameters. FEFF is a computer program uses a real-space Green's function approach to calculate X-ray absorption spectra. We will demonstrate that the ELSIE algorithm, which combines 33 weak "learners" comprising a set of preprocessing steps and a similarity metric, can achieve up to 84.2% accuracy in identifying the correct oxidation state and coordination environment of a test set of 19 K-edge XANES spectra encompassing a diverse range of chemistries and crystal structures. The XASdb with the ELSIE algorithm has been integrated into a web application in the Materials Project, providing an important new public resource for the analysis of XAS to all materials researchers. Finally, the ELSIE algorithm itself has been made available as part of veidt, an open source machine-learning library for materials science.

  15. Adaptive high learning rate probabilistic disruption predictors from scratch for the next generation of tokamaks

    International Nuclear Information System (INIS)

    Vega, J.; Moreno, R.; Pereira, A.; Acero, A.; Murari, A.; Dormido-Canto, S.

    2014-01-01

    The development of accurate real-time disruption predictors is a pre-requisite to any mitigation action. Present theoretical models of disruptions do not reliably cope with the disruption issues. This article deals with data-driven predictors and a review of existing machine learning techniques, from both physics and engineering points of view, is provided. All these methods need large training datasets to develop successful predictors. However, ITER or DEMO cannot wait for hundreds of disruptions to have a reliable predictor. So far, the attempts to extrapolate predictors between different tokamaks have not shown satisfactory results. In addition, it is not clear how valid this approach can be between present devices and ITER/DEMO, due to the differences in their respective scales and possibly underlying physics. Therefore, this article analyses the requirements to create adaptive predictors from scratch to learn from the data of an individual machine from the beginning of operation. A particular algorithm based on probabilistic classifiers has been developed and it has been applied to the database of the three first ITER-like wall campaigns of JET (1036 non-disruptive and 201 disruptive discharges). The predictions start from the first disruption and only 12 re-trainings have been necessary as a consequence of missing 12 disruptions only. Almost 10 000 different predictors have been developed (they differ in their features) and after the chronological analysis of the 1237 discharges, the predictors recognize 94% of all disruptions with an average warning time (AWT) of 654 ms. This percentage corresponds to the sum of tardy detections (11%), valid alarms (76%) and premature alarms (7%). The false alarm rate is 4%. If only valid alarms are considered, the AWT is 244 ms and the standard deviation is 205 ms. The average probability interval about the reliability and accuracy of all the individual predictions is 0.811 ± 0.189. (paper)

  16. Adaptive high learning rate probabilistic disruption predictors from scratch for the next generation of tokamaks

    Science.gov (United States)

    Vega, J.; Murari, A.; Dormido-Canto, S.; Moreno, R.; Pereira, A.; Acero, A.; Contributors, JET-EFDA

    2014-12-01

    The development of accurate real-time disruption predictors is a pre-requisite to any mitigation action. Present theoretical models of disruptions do not reliably cope with the disruption issues. This article deals with data-driven predictors and a review of existing machine learning techniques, from both physics and engineering points of view, is provided. All these methods need large training datasets to develop successful predictors. However, ITER or DEMO cannot wait for hundreds of disruptions to have a reliable predictor. So far, the attempts to extrapolate predictors between different tokamaks have not shown satisfactory results. In addition, it is not clear how valid this approach can be between present devices and ITER/DEMO, due to the differences in their respective scales and possibly underlying physics. Therefore, this article analyses the requirements to create adaptive predictors from scratch to learn from the data of an individual machine from the beginning of operation. A particular algorithm based on probabilistic classifiers has been developed and it has been applied to the database of the three first ITER-like wall campaigns of JET (1036 non-disruptive and 201 disruptive discharges). The predictions start from the first disruption and only 12 re-trainings have been necessary as a consequence of missing 12 disruptions only. Almost 10 000 different predictors have been developed (they differ in their features) and after the chronological analysis of the 1237 discharges, the predictors recognize 94% of all disruptions with an average warning time (AWT) of 654 ms. This percentage corresponds to the sum of tardy detections (11%), valid alarms (76%) and premature alarms (7%). The false alarm rate is 4%. If only valid alarms are considered, the AWT is 244 ms and the standard deviation is 205 ms. The average probability interval about the reliability and accuracy of all the individual predictions is 0.811 ± 0.189.

  17. Wind Turbine Driving a PM Synchronous Generator Using Novel Recurrent Chebyshev Neural Network Control with the Ideal Learning Rate

    Directory of Open Access Journals (Sweden)

    Chih-Hong Lin

    2016-06-01

    Full Text Available A permanent magnet (PM synchronous generator system driven by wind turbine (WT, connected with smart grid via AC-DC converter and DC-AC converter, are controlled by the novel recurrent Chebyshev neural network (NN and amended particle swarm optimization (PSO to regulate output power and output voltage in two power converters in this study. Because a PM synchronous generator system driven by WT is an unknown non-linear and time-varying dynamic system, the on-line training novel recurrent Chebyshev NN control system is developed to regulate DC voltage of the AC-DC converter and AC voltage of the DC-AC converter connected with smart grid. Furthermore, the variable learning rate of the novel recurrent Chebyshev NN is regulated according to discrete-type Lyapunov function for improving the control performance and enhancing convergent speed. Finally, some experimental results are shown to verify the effectiveness of the proposed control method for a WT driving a PM synchronous generator system in smart grid.

  18. Empowering Teachers and New Generations through Design Thinking and Digital Fabrication Learning Activities

    DEFF Research Database (Denmark)

    Pitkänen, Kati; Andersen, Hanne Voldborg

    2018-01-01

    are seen ever more important in society and working life. Digital fabrication may be seen as next generations ‘information technology’. The paper examines Danish FabLab@SCHOOLdk partnership and its several different models to arrange further education of FabLab Pioneer Teachers in the three unique...... municipalities involved. The study identifies five important stakeholders inside the FabLab@SCHOOLdk initiative and illuminates their different roles and tasks for supporting processes to empower teachers. A Framework is suggested for the evaluation of the initiative of FabLab@SCHOOLdk or as inspiration...

  19. Emergency diesel generators manufactured by Transamerica Delaval, Inc. problems, their resolution and lessons learned

    Energy Technology Data Exchange (ETDEWEB)

    Berlinger, C. H.; Murphy, E. L. [United States Nuclear Regulatory Commission, Washington, D.C. 20555 (United States)

    1986-02-15

    Emergency standby diesel generators manufactured by Transamerica Delaval, Inc. experienced a number of major problems during preoperational qualification testing at several U.S. nuclear sites. Most notably these have included a complete fracture of a crankshaft, an engine block failure, piston failures, and cracked and leaking cylinder heads. These problems appear to stem from deficiencies in design and manufacturing quality by the engine manufacturer. This paper discusses some of the more significant problems experienced and actions taken by the nuclear utility owners and the NRC to reestablish confidence in the reliability of these engines and to qualify these engines for nuclear service. (authors)

  20. Emergency diesel generators manufactured by Transamerica Delaval, Inc. problems, their resolution and lessons learned

    International Nuclear Information System (INIS)

    Berlinger, C.H.; Murphy, E.L.

    1986-01-01

    Emergency standby diesel generators manufactured by Transamerica Delaval, Inc. experienced a number of major problems during preoperational qualification testing at several U.S. nuclear sites. Most notably these have included a complete fracture of a crankshaft, an engine block failure, piston failures, and cracked and leaking cylinder heads. These problems appear to stem from deficiencies in design and manufacturing quality by the engine manufacturer. This paper discusses some of the more significant problems experienced and actions taken by the nuclear utility owners and the NRC to reestablish confidence in the reliability of these engines and to qualify these engines for nuclear service. (authors)

  1. Deep Web Search Interface Identification: A Semi-Supervised Ensemble Approach

    OpenAIRE

    Hong Wang; Qingsong Xu; Lifeng Zhou

    2014-01-01

    To surface the Deep Web, one crucial task is to predict whether a given web page has a search interface (searchable HyperText Markup Language (HTML) form) or not. Previous studies have focused on supervised classification with labeled examples. However, labeled data are scarce, hard to get and requires tediousmanual work, while unlabeled HTML forms are abundant and easy to obtain. In this research, we consider the plausibility of using both labeled and unlabeled data to train better models to...

  2. Semi-supervised probabilistics approach for normalising informal short text messages

    CSIR Research Space (South Africa)

    Modupe, A

    2017-03-01

    Full Text Available The growing use of informal social text messages on Twitter is one of the known sources of big data. These type of messages are noisy and frequently rife with acronyms, slangs, grammatical errors and non-standard words causing grief for natural...

  3. Improving head and body pose estimation through semi-supervised manifold alignment

    KAUST Repository

    Heili, Alexandre; Varadarajan, Jagannadan; Ghanem, Bernard; Ahuja, Narendra; Odobez, Jean-Marc

    2014-01-01

    structure of the features in the train and target data and the need to align them were not explored despite the fact that the pose features between two datasets may vary according to the scene, e.g. due to different camera point of view or perspective

  4. Semi-Supervised Half-Quadratic Nonnegative Matrix Factorization for Face Recognition

    KAUST Repository

    Alghamdi, Masheal M.

    2014-01-01

    complications to the face recognition research. Many algorithms are devoted to solving the face recognition problem, among which the family of nonnegative matrix factorization (NMF) algorithms has been widely used as a compact data representation method

  5. Semi-Supervised Bayesian Classification of Materials with Impact-Echo Signals

    Directory of Open Access Journals (Sweden)

    Jorge Igual

    2015-05-01

    Full Text Available The detection and identification of internal defects in a material require the use of some technology that translates the hidden interior damages into observable signals with different signature-defect correspondences. We apply impact-echo techniques for this purpose. The materials are classified according to their defective status (homogeneous, one defect or multiple defects and kind of defect (hole or crack, passing through or not. Every specimen is impacted by a hammer, and the spectrum of the propagated wave is recorded. This spectrum is the input data to a Bayesian classifier that is based on the modeling of the conditional probabilities with a mixture of Gaussians. The parameters of the Gaussian mixtures and the class probabilities are estimated using an extended expectation-maximization algorithm. The advantage of our proposal is that it is flexible, since it obtains good results for a wide range of models even under little supervision; e.g., it obtains a harmonic average of precision and recall value of 92.38% given only a 10% supervision ratio. We test the method with real specimens made of aluminum alloy. The results show that the algorithm works very well. This technique could be applied in many industrial problems, such as the optimization of the marble cutting process.

  6. A Semi-supervised Heat Kernel Pagerank MBO Algorithm for Data Classification

    Science.gov (United States)

    2016-07-01

    φ∈E. The gradient operator is defined as (∇u)w(x,y) =w(x,y)1−q(u(y)−u(x)), and the divergence operator can be formulated as the adjoint of the... divergence operators, one can define a family of graph Laplacians 4r = divw ∇̇ : V→V: (4wu)(x) = ∑ y w(x,y) d(x)r (u(y)−u(x)). We also formulate the...A.L. Bertozzi, F. Chung 7 According to Theorem III.2 in [62], the solution to (2.3) is given by u(t) =D−1ρtrt,f , f =u(0) trD, (2.4) where M tr denotes

  7. A semi-supervised segmentation algorithm as applied to k-means ...

    African Journals Online (AJOL)

    Density based clustering makes use of probability density estimates to define ...... [2] Anderson R, 2007, The credit scoring toolkit: theory and practice for retail credit .... [46] Shifa N & Rashid M, 2003, Monte Carlo Evaluation of Consistency and ...

  8. A semi-supervised segmentation algorithm as applied to k-means ...

    African Journals Online (AJOL)

    Segmentation (or partitioning) of data for the purpose of enhancing predictive modelling is a well-established practice in the banking industry. Unsupervised and supervised approaches are the two main streams of segmentation and examples exist where the application of these techniques improved the performance of ...

  9. Combination of supervised and semi-supervised regression models for improved unbiased estimation

    DEFF Research Database (Denmark)

    Arenas-Garía, Jeronimo; Moriana-Varo, Carlos; Larsen, Jan

    2010-01-01

    In this paper we investigate the steady-state performance of semisupervised regression models adjusted using a modified RLS-like algorithm, identifying the situations where the new algorithm is expected to outperform standard RLS. By using an adaptive combination of the supervised and semisupervi......In this paper we investigate the steady-state performance of semisupervised regression models adjusted using a modified RLS-like algorithm, identifying the situations where the new algorithm is expected to outperform standard RLS. By using an adaptive combination of the supervised...

  10. Data Generation in the Discovery Sciences—Learning from the Practices in an Advanced Research Laboratory

    Science.gov (United States)

    Roth, Wolff-Michael

    2013-08-01

    General scientific literacy includes understanding the grounds on which scientific claims are based. The measurements scientists make and the data that they produce from them generally constitute these grounds. However, the nature of data generation has received relatively little attention from those interested in teaching science through inquiry. To inform curriculum designers about the process of data generation and its relation to the understanding of patterns as these may arise from graphs, this 5-year ethnographic study in one advanced research laboratory was designed to investigate how natural scientists make decisions about the inclusion/exclusion of certain measurements in/from their data sources. The study shows that scientists exclude measurements from their data sources even before attempting to mathematize and interpret the data. The excluded measurements therefore never even enter the ground from and against which the scientific phenomenon emerges and therefore remain invisible to it. I conclude by encouraging science educators to squarely address this aspect of the discovery sciences in their teaching, which has both methodological and ethical implications.

  11. Generating Expectations: What Pediatric Rehabilitation Can Learn From Mental Health Literature.

    Science.gov (United States)

    Smart, Eric; Nalder, Emily; Rigby, Patty; King, Gillian

    2018-04-03

    Family-Centered Care (FCC) represents the ideal service delivery approach in pediatric rehabilitation. Nonetheless, implementing FCC as intended in clinical settings continues to be hindered by knowledge gaps. One overlooked gap is our understanding of clients' therapy expectations. This perspective article synthesizes knowledge from the mental health services literature on strategies recommended to service providers for generating transparent and congruent therapy expectations with clients, and applies this knowledge to the pediatric rehabilitation literature, where this topic has been researched significantly less, for the purpose of improving FCC implementation. Dimensions of the Measure of Processes of Care, an assessment tool that measures clients' perceptions of the extent a service is family-centered, inform the organization of therapy expectation-generating strategies: (1) Providing Respectful and Supportive Care (assessing and validating clients' expectations); (2) General and Specific Information (foreshadowing therapy journeys, explaining treatment rationale, and conveying service provider qualifications); (3) Coordinated and Comprehensive Care (socializing clients to roles and reflecting on past socialization); and (4) Enabling and Partnership (applying a negotiation framework and fostering spaces safe to critique). Strategies can help pediatric rehabilitation service providers work with families to reframe unrealistic expectations, establish congruent beliefs supporting effective partnerships, and prevent possible disillusionment with therapy over time.

  12. Improving nuclear utility generation capacity, understanding the sources of forced outage and learning how to prevent them

    International Nuclear Information System (INIS)

    Brodeur, D.L.; Todreas, N.E.; Angus, V.T.

    1998-01-01

    MIT and PECO Energy have completed a detailed examination of the sources of forced outages at the Limerick Generating Station (LGS) Boiling Water Reactor Class IV (BWR IV) site over a five year period and contrasted that information to similar BWR IV utilities in the United States over the same period. Each forced outage was attributed to one system and assigned causal codes of equipment versus human factors and failure attributes such as weak design, poor craftsmanship, and worn parts. It was found that fifty four percent of the lost power at LGS was the result of Balance of Plant failures. Industry wide data identifies fifty nine percent of the lost power as attributed to Balance of Plant failures. Balance of Plant systems are those systems not included in the primary and safety related system category. Considering failure causal factors, forty six percent of the lost power at the utility under study was the result of equipment factors such as weak design or worn parts. Significantly, the study showed a high variance between those systems which caused significant forced outage at the two sister LGS units. This demonstrated the infrequent nature of plant forced outages within a given system. This was supported by the observation that dominant systems attributing to forced outage at LGS were not equally represented in industry data. It is suggested that for individual utilities to dramatically improve unit capability factors with regard to Balance of Plant systems, they must learn from industry wide experiences and develop cooperative means of exchanging lessons learned among similarly designed plants and systems. With the broad knowledge base of system failures, current designs must be frequently assessed and altered until each system poses an acceptable level of risk to generation capacity. (author)

  13. Towards Self-Learning Based Hypotheses Generation in Biomedical Text Domain.

    Science.gov (United States)

    Gopalakrishnan, Vishrawas; Jha, Kishlay; Xun, Guangxu; Ngo, Hung Q; Zhang, Aidong

    2017-12-26

    The overwhelming amount of research articles in the domain of bio-medicine might cause important connections to remain unnoticed. Literature Based Discovery is a sub-field within biomedical text mining that peruses these articles to formulate high confident hypotheses on possible connections between medical concepts. Although many alternate methodologies have been proposed over the last decade, they still suffer from scalability issues. The primary reason, apart from the dense inter-connections between biological concepts, is the absence of information on the factors that lead to the edge-formation. In this work, we formulate this problem as a collaborative filtering task and leverage a relatively new concept of word-vectors to learn and mimic the implicit edge-formation process. Along with single-class classifier, we prune the search-space of redundant and irrelevant hypotheses to increase the efficiency of the system and at the same time maintaining and in some cases even boosting the overall accuracy. We show that our proposed framework is able to prune up to 90% of the hypotheses while still retaining high recall in top-K results. This level of efficiency enables the discovery algorithm to look for higher-order hypotheses, something that was infeasible until now. Furthermore, the generic formulation allows our approach to be agile to performboth open and closed discovery.We also experimentally validate that the core data-structures upon which the system bases its decision has a high concordance with the opinion of the experts.This coupled with the ability to understand the edge formation process provides us with interpretable results without any manual intervention. The relevant JAVA codes are available at: https://github.com/vishrawas/Medline-Code_v2. vishrawa@buffalo.edukishlayj@buffalo.edu. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email

  14. Learning progressions from a sociocultural perspective: response to "co-constructing cultural landscapes for disciplinary learning in and out of school: the next generation science standards and learning progressions in action"

    Science.gov (United States)

    Tytler, Russell

    2016-10-01

    This article discusses a case for a different, socio-cultural way of looking at learning progressions as treated in the next generation science standards (NGSS) as described by Ralph Cordova and Phyllis Balcerzak's paper "Co-constructing cultural landscapes for disciplinary learning in and out of school: the next generation science standards and learning progressions in action". The paper is interesting for a number of reasons, and in this response I will identify different aspects of the paper and link the points made to my own research, and that of colleagues, as complementary perspectives. First, the way that the science curriculum is conceived as an expanding experience that moves from the classroom into the community, across subjects, and across time, links to theoretical positions on disciplinary literacies and notions of learning as apprenticeship into the discursive tools, or `habits of mind' as the authors put it, that underpin disciplinary practice. Second, the formulation of progression through widening communities of practice is a strong feature of the paper, and shows how children take on the role of scientists through this expanding exposure. I will link this approach to some of our own work with school—community science partnerships, drawing on the construct of boundary crossing to tease out relations between school science and professional practice. Third, the demonstration of the expansion of the children's view of what scientists do is well documented in the paper, illustrated by Figure 13 for instance. However I will, in this response, try to draw out and respond to what the paper is saying about the nature of progression; what the progression consists of, over what temporal or spatial dimensions it progresses, and how it can productively frame curriculum processes.

  15. Extraction of Pluvial Flood Relevant Volunteered Geographic Information (VGI by Deep Learning from User Generated Texts and Photos

    Directory of Open Access Journals (Sweden)

    Yu Feng

    2018-01-01

    Full Text Available In recent years, pluvial floods caused by extreme rainfall events have occurred frequently. Especially in urban areas, they lead to serious damages and endanger the citizens’ safety. Therefore, real-time information about such events is desirable. With the increasing popularity of social media platforms, such as Twitter or Instagram, information provided by voluntary users becomes a valuable source for emergency response. Many applications have been built for disaster detection and flood mapping using crowdsourcing. Most of the applications so far have merely used keyword filtering or classical language processing methods to identify disaster relevant documents based on user generated texts. As the reliability of social media information is often under criticism, the precision of information retrieval plays a significant role for further analyses. Thus, in this paper, high quality eyewitnesses of rainfall and flooding events are retrieved from social media by applying deep learning approaches on user generated texts and photos. Subsequently, events are detected through spatiotemporal clustering and visualized together with these high quality eyewitnesses in a web map application. Analyses and case studies are conducted during flooding events in Paris, London and Berlin.

  16. Lessons learned from the seismic reevaluation of San Onofre Nuclear Generating Station, Unit 1

    International Nuclear Information System (INIS)

    Russell, M.J.; Shieh, L.C.; Tsai, N.C.; Cheng, T.M.

    1987-01-01

    A seismic reevaluation program was conducted for the San Onofre Nuclear Generating Station, Unit No. 1 (SONGS 1). SEP was created by the NRC to provide (1) an assessment of the significance of differences between current technical positions on safety issues and those that existed when a particular plant was licensed, (2) a basis for deciding on how these differences should be resolved in an integrated plant review, and (3) a documented evaluation of plant safety. The Systematic Evaluation Program (SEP) seismic review for SONGS 1 was exacerbated by the results of an evaluation of an existing capable fault near the site during the design review for Units 2 and 3, which resulted in a design ground acceleration of 0.67g. Southern California Edison Company (SCE), the licensee for SONGS 1, realized that a uniform application of existing seismic criteria and methods would not be feasible for the upgrading of SONGS 1 to such a high seismic requirement. Instead, SCE elected to supplement existing seismic criteria and analysis methods by developing criteria and methods closer to the state of the art in seismic evaluation techniques

  17. Automatic generation control of multi-area power systems with diverse energy sources using Teaching Learning Based Optimization algorithm

    Directory of Open Access Journals (Sweden)

    Rabindra Kumar Sahu

    2016-03-01

    Full Text Available This paper presents the design and analysis of Proportional-Integral-Double Derivative (PIDD controller for Automatic Generation Control (AGC of multi-area power systems with diverse energy sources using Teaching Learning Based Optimization (TLBO algorithm. At first, a two-area reheat thermal power system with appropriate Generation Rate Constraint (GRC is considered. The design problem is formulated as an optimization problem and TLBO is employed to optimize the parameters of the PIDD controller. The superiority of the proposed TLBO based PIDD controller has been demonstrated by comparing the results with recently published optimization technique such as hybrid Firefly Algorithm and Pattern Search (hFA-PS, Firefly Algorithm (FA, Bacteria Foraging Optimization Algorithm (BFOA, Genetic Algorithm (GA and conventional Ziegler Nichols (ZN for the same interconnected power system. Also, the proposed approach has been extended to two-area power system with diverse sources of generation like thermal, hydro, wind and diesel units. The system model includes boiler dynamics, GRC and Governor Dead Band (GDB non-linearity. It is observed from simulation results that the performance of the proposed approach provides better dynamic responses by comparing the results with recently published in the literature. Further, the study is extended to a three unequal-area thermal power system with different controllers in each area and the results are compared with published FA optimized PID controller for the same system under study. Finally, sensitivity analysis is performed by varying the system parameters and operating load conditions in the range of ±25% from their nominal values to test the robustness.

  18. Engineering mechanical gradients in next generation biomaterials - Lessons learned from medical textile design.

    Science.gov (United States)

    Ng, Joanna L; Collins, Ciara E; Knothe Tate, Melissa L

    2017-07-01

    Nonwoven and textile membranes have been applied both externally and internally to prescribe boundary conditions for medical conditions as diverse as oedema and tissue defects. Incorporation of mechanical gradients in next generation medical membrane design offers great potential to enhance function in a dynamic, physiological context. Yet the gradient properties and resulting mechanical performance of current membranes are not well described. To bridge this knowledge gap, we tested and compared the mechanical properties of bounding membranes used in both external (compression sleeves for oedema, exercise bands) and internal (surgical membranes) physiological contexts. We showed that anisotropic compression garment textiles, isotropic exercise bands and surgical membranes exhibit similar ranges of resistance to tension under physiologic strains. However, their mechanical gradients and resulting stress-strain relationships show differences in work capacity and energy expenditure. Exercise bands' moduli of elasticity and respective thicknesses allow for controlled, incremental increases in loading to facilitate healing as injured tissues return to normal structure and function. In contrast, the gradients intrinsic to compression sleeve design exhibit gaps in the middle range (1-5N) of physiological strains and also inconsistencies along the length of the sleeve, resulting in less than optimal performance of these devices. These current shortcomings in compression textile and garment design may be addressed in the future through implementation of novel approaches. For example, patterns, fibre compositions, and fibre anisotropy can be incorporated into biomaterial design to achieve seamless mechanical gradients in structure and resulting dynamic function, which would be particularly useful in physiological contexts. These concepts can be applied further to biomaterial design to deliver pressure gradients during movement of oedematous limbs (compression garments) and

  19. Pairwise Constraint-Guided Sparse Learning for Feature Selection.

    Science.gov (United States)

    Liu, Mingxia; Zhang, Daoqiang

    2016-01-01

    Feature selection aims to identify the most informative features for a compact and accurate data representation. As typical supervised feature selection methods, Lasso and its variants using L1-norm-based regularization terms have received much attention in recent studies, most of which use class labels as supervised information. Besides class labels, there are other types of supervised information, e.g., pairwise constraints that specify whether a pair of data samples belong to the same class (must-link constraint) or different classes (cannot-link constraint). However, most of existing L1-norm-based sparse learning methods do not take advantage of the pairwise constraints that provide us weak and more general supervised information. For addressing that problem, we propose a pairwise constraint-guided sparse (CGS) learning method for feature selection, where the must-link and the cannot-link constraints are used as discriminative regularization terms that directly concentrate on the local discriminative structure of data. Furthermore, we develop two variants of CGS, including: 1) semi-supervised CGS that utilizes labeled data, pairwise constraints, and unlabeled data and 2) ensemble CGS that uses the ensemble of pairwise constraint sets. We conduct a series of experiments on a number of data sets from University of California-Irvine machine learning repository, a gene expression data set, two real-world neuroimaging-based classification tasks, and two large-scale attribute classification tasks. Experimental results demonstrate the efficacy of our proposed methods, compared with several established feature selection methods.

  20. Technology Learning Activities. Design Brief--Measuring Inaccessible Distances. Alternative Energy Sources: Designing a Wind Powered Generator. Alternative Energy Sources: Designing a Hot Dog Heater Using Solar Energy.

    Science.gov (United States)

    Technology Teacher, 1991

    1991-01-01

    These three learning activities are on measuring accessible distances, designing a wind powered generator, and designing a hot dog heater using solar energy. Each activity includes description of context, objectives, list of materials and equipment, challenge to students, and evaluation questions. (SK)

  1. User-Generated Content, YouTube and Participatory Culture on the Web: Music Learning and Teaching in Two Contrasting Online Communities

    Science.gov (United States)

    Waldron, Janice

    2013-01-01

    In this paper, I draw on seminal literature from new media researchers to frame the broader implications that user-generated content (UGC), YouTube, and participatory culture have for music learning and teaching in online communities; to illustrate, I use examples from two contrasting online music communities, the Online Academy of Irish…

  2. Disturbance of endogenous hydrogen sulfide generation and endoplasmic reticulum stress in hippocampus are involved in homocysteine-induced defect in learning and memory of rats.

    Science.gov (United States)

    Li, Man-Hong; Tang, Ji-Ping; Zhang, Ping; Li, Xiang; Wang, Chun-Yan; Wei, Hai-Jun; Yang, Xue-Feng; Zou, Wei; Tang, Xiao-Qing

    2014-04-01

    Homocysteine (Hcy) is a risk factor for Alzheimer's disease (AD). Hydrogen sulfide (H2S) acts as an endogenous neuromodulator and neuroprotectant. It has been shown that endoplasmic reticulum (ER) stress is involved in the pathological mechanisms of the learning and memory dysfunctions and that H2S exerts its neuroprotective role via suppressing ER stress. In the present work, we explored the effects of intracerebroventricular injection of Hcy on the formation of learning and memory, the generation of endogenous H2S, and the expression of ER stress in the hippocampus of rats. We found that intracerebroventricular injection of Hcy in rats leads to learning and memory dysfunctions in the Morris water maze and novel of object recognition test and decreases in the expression of cystathionine-β-synthase, the major enzyme responsible for endogenous H2S generation, and the generation of endogenous H2S in the hippocampus of rats. We also showed that exposure of Hcy could up-regulate the expressions of glucose-regulated protein 78 (GRP78), CHOP, and cleaved caspase-12, which are the major mark proteins of ER stress, in the hippocampus of rats. Taken together, these results suggest that the disturbance of hippocampal endogenous H2S generation and the increase in ER stress in the hippocampus are related to Hcy-induced defect in learning and memory. Copyright © 2014 Elsevier B.V. All rights reserved.

  3. A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids

    International Nuclear Information System (INIS)

    Xi, Lei; Yu, Tao; Yang, Bo; Zhang, Xiaoshun

    2015-01-01

    Highlights: • Proposing a decentralized smart generation control scheme for the automatic generation control coordination. • A novel multi-agent learning algorithm is developed to resolve stochastic control problems in power systems. • A variable learning rate are introduced base on the framework of stochastic games. • A simulation platform is developed to test the performance of different algorithms. - Abstract: This paper proposes a multi-agent smart generation control scheme for the automatic generation control coordination in interconnected complex power systems. A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm is developed, which can effectively identify the optimal average policies via a variable learning rate under various operation conditions. Based on control performance standards, the proposed approach is implemented in a flexible multi-agent stochastic dynamic game-based smart generation control simulation platform. Based on the mixed strategy and average policy, it is highly adaptive in stochastic non-Markov environments and large time-delay systems, which can fulfill automatic generation control coordination in interconnected complex power systems in the presence of increasing penetration of decentralized renewable energy. Two case studies on both a two-area load–frequency control power system and the China Southern Power Grid model have been done. Simulation results verify that multi-agent smart generation control scheme based on the proposed approach can obtain optimal average policies thus improve the closed-loop system performances, and can achieve a fast convergence rate with significant robustness compared with other methods

  4. "Digitize Me": Generating E-Learning Profiles for Media and Communication Students in a Jamaican Tertiary-Level Institution

    Science.gov (United States)

    Stewart-McKoy, Michelle A.

    2014-01-01

    The purpose of this project was to develop an e-learning profile for a group of media and communication students enrolled in a Jamaican tertiary-level institution in order to make informed decisions most the appropriate [online] learning complement for these students. The objectives sought to determine the e-learning profile of media and…

  5. How the Young Generation Uses Digital Textbooks via Mobile Learning Terminals: Measurement of Elementary School Students in China

    Science.gov (United States)

    Sun, Zhong; Jiang, Yuzhen

    2015-01-01

    Digital textbooks that offer multimedia features, interactive controls, e-annotation and learning process tracking are gaining increasing attention in today's mobile learning era, particularly with the rapid development of mobile learning terminals such as Apple's iPad series and Android-based models. Accordingly, this study explores how…

  6. The New Generation of Auditors Meeting Praxis: Dual Learning's Role in Audit Students' Professional Development

    Science.gov (United States)

    Agevall, Lena; Broberg, Pernilla; Umans, Timurs

    2018-01-01

    This paper explores whether and in what way "dual learning" can develop understanding of the relationship between structure/judgement and explores audit student's perceptions of the audit profession. The Work Integrated Learning (WIL) module, serving as a tool of enabling dual learning, represents the context for this exploration. The…

  7. 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.

  8. Distributed Generation Planning using Peer Enhanced Multi-objective Teaching-Learning based Optimization in Distribution Networks

    Science.gov (United States)

    Selvam, Kayalvizhi; Vinod Kumar, D. M.; Siripuram, Ramakanth

    2017-04-01

    In this paper, an optimization technique called peer enhanced teaching learning based optimization (PeTLBO) algorithm is used in multi-objective problem domain. The PeTLBO algorithm is parameter less so it reduced the computational burden. The proposed peer enhanced multi-objective based TLBO (PeMOTLBO) algorithm has been utilized to find a set of non-dominated optimal solutions [distributed generation (DG) location and sizing in distribution network]. The objectives considered are: real power loss and the voltage deviation subjected to voltage limits and maximum penetration level of DG in distribution network. Since the DG considered is capable of injecting real and reactive power to the distribution network the power factor is considered as 0.85 lead. The proposed peer enhanced multi-objective optimization technique provides different trade-off solutions in order to find the best compromise solution a fuzzy set theory approach has been used. The effectiveness of this proposed PeMOTLBO is tested on IEEE 33-bus and Indian 85-bus distribution system. The performance is validated with Pareto fronts and two performance metrics (C-metric and S-metric) by comparing with robust multi-objective technique called non-dominated sorting genetic algorithm-II and also with the basic TLBO.

  9. A machine learning model to determine the accuracy of variant calls in capture-based next generation sequencing.

    Science.gov (United States)

    van den Akker, Jeroen; Mishne, Gilad; Zimmer, Anjali D; Zhou, Alicia Y

    2018-04-17

    Next generation sequencing (NGS) has become a common technology for clinical genetic tests. The quality of NGS calls varies widely and is influenced by features like reference sequence characteristics, read depth, and mapping accuracy. With recent advances in NGS technology and software tools, the majority of variants called using NGS alone are in fact accurate and reliable. However, a small subset of difficult-to-call variants that still do require orthogonal confirmation exist. For this reason, many clinical laboratories confirm NGS results using orthogonal technologies such as Sanger sequencing. Here, we report the development of a deterministic machine-learning-based model to differentiate between these two types of variant calls: those that do not require confirmation using an orthogonal technology (high confidence), and those that require additional quality testing (low confidence). This approach allows reliable NGS-based calling in a clinical setting by identifying the few important variant calls that require orthogonal confirmation. We developed and tested the model using a set of 7179 variants identified by a targeted NGS panel and re-tested by Sanger sequencing. The model incorporated several signals of sequence characteristics and call quality to determine if a variant was identified at high or low confidence. The model was tuned to eliminate false positives, defined as variants that were called by NGS but not confirmed by Sanger sequencing. The model achieved very high accuracy: 99.4% (95% confidence interval: +/- 0.03%). It categorized 92.2% (6622/7179) of the variants as high confidence, and 100% of these were confirmed to be present by Sanger sequencing. Among the variants that were categorized as low confidence, defined as NGS calls of low quality that are likely to be artifacts, 92.1% (513/557) were found to be not present by Sanger sequencing. This work shows that NGS data contains sufficient characteristics for a machine-learning-based model to

  10. Safety design criteria for the next generation Sodium-cooled fast reactors based on lessons learned from the Fukushima NPS accident

    International Nuclear Information System (INIS)

    Sakai, Takaaki

    2012-01-01

    In this presentation, architecture of the safety design criteria as requirements for SFR system and the activities on safety research works to establish safety evaluation methods for the next generation SFRs are summarized with the basis on lessons learned from the Fukushima NPS accident. Nuclear safety is a grovel issue which should be achieved by the international cooperation. In respect of the development for the next generation reactor, it is necessary to build the harmonized safety criteria and evaluation methods to establish the next level of safety

  11. Learning

    Directory of Open Access Journals (Sweden)

    Mohsen Laabidi

    2014-01-01

    Full Text Available Nowadays learning technologies transformed educational systems with impressive progress of Information and Communication Technologies (ICT. Furthermore, when these technologies are available, affordable and accessible, they represent more than a transformation for people with disabilities. They represent real opportunities with access to an inclusive education and help to overcome the obstacles they met in classical educational systems. In this paper, we will cover basic concepts of e-accessibility, universal design and assistive technologies, with a special focus on accessible e-learning systems. Then, we will present recent research works conducted in our research Laboratory LaTICE toward the development of an accessible online learning environment for persons with disabilities from the design and specification step to the implementation. We will present, in particular, the accessible version “MoodleAcc+” of the well known e-learning platform Moodle as well as new elaborated generic models and a range of tools for authoring and evaluating accessible educational content.

  12. "Digitize Me": Generating E-Learning Profiles for Media and Communication Students in a Jamaican Tertiary-Level Institution

    Directory of Open Access Journals (Sweden)

    Michelle A. Stewart-McKoy

    2014-01-01

    Full Text Available The purpose of this project was to develop an e-learning profile for a group of media and communication students enrolled in a Jamaican tertiary-level institution in order to make informed decisions most the appropriate [online] learning complement for these students. The objectives sought to determine the e-learning profile of media and communication students but more specifically, the profile examined students’ demographic data, their technology access, usage, proficiency and comfort levels as well as their learning styles, preferences, behaviours, strategies and their preferences for specific teaching styles. The research utilised a survey research design and the participants involved in the research were ninety-eight students from all year groups in the programme. Findings reveal that the “typical” media and communication student is a young Jamaican adult with limited technology access, usage and proficiency, who stays connected with others largely by phone texts, phone calls, emails, instant messages and posts via the Facebook social network, who has a visual-learning orientation, is a sequential learner who is extrinsically motivated and who readily employs surface learning strategies.

  13. An Active Learning Framework for Hyperspectral Image Classification Using Hierarchical Segmentation

    Science.gov (United States)

    Zhang, Zhou; Pasolli, Edoardo; Crawford, Melba M.; Tilton, James C.

    2015-01-01

    Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral-spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral-spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

  14. Predicting protein complexes using a supervised learning method combined with local structural information.

    Science.gov (United States)

    Dong, Yadong; Sun, Yongqi; Qin, Chao

    2018-01-01

    The existing protein complex detection methods can be broadly divided into two categories: unsupervised and supervised learning methods. Most of the unsupervised learning methods assume that protein complexes are in dense regions of protein-protein interaction (PPI) networks even though many true complexes are not dense subgraphs. Supervised learning methods utilize the informative properties of known complexes; they often extract features from existing complexes and then use the features to train a classification model. The trained model is used to guide the search process for new complexes. However, insufficient extracted features, noise in the PPI data and the incompleteness of complex data make the classification model imprecise. Consequently, the classification model is not sufficient for guiding the detection of complexes. Therefore, we propose a new robust score function that combines the classification model with local structural information. Based on the score function, we provide a search method that works both forwards and backwards. The results from experiments on six benchmark PPI datasets and three protein complex datasets show that our approach can achieve better performance compared with the state-of-the-art supervised, semi-supervised and unsupervised methods for protein complex detection, occasionally significantly outperforming such methods.

  15. Out-of-Sample Generalizations for Supervised Manifold Learning for Classification.

    Science.gov (United States)

    Vural, Elif; Guillemot, Christine

    2016-03-01

    Supervised manifold learning methods for data classification map high-dimensional data samples to a lower dimensional domain in a structure-preserving way while increasing the separation between different classes. Most manifold learning methods compute the embedding only of the initially available data; however, the generalization of the embedding to novel points, i.e., the out-of-sample extension problem, becomes especially important in classification applications. In this paper, we propose a semi-supervised method for building an interpolation function that provides an out-of-sample extension for general supervised manifold learning algorithms studied in the context of classification. The proposed algorithm computes a radial basis function interpolator that minimizes an objective function consisting of the total embedding error of unlabeled test samples, defined as their distance to the embeddings of the manifolds of their own class, as well as a regularization term that controls the smoothness of the interpolation function in a direction-dependent way. The class labels of test data and the interpolation function parameters are estimated jointly with an iterative process. Experimental results on face and object images demonstrate the potential of the proposed out-of-sample extension algorithm for the classification of manifold-modeled data sets.

  16. Application of the self-generation effect to the learning of Blissymbols by persons presenting with a severe aphasia.

    Science.gov (United States)

    Rajaram, Priya; Alant, Erna; Dada, Shakila

    2012-06-01

    This study investigated the application of the self-generation effect to enhance the recognition and retention of Blissymbols in persons with severe aphasia. A 2×2×3 factorial design of two treatment types (self-generation and non-generation) was used to teach two sets of Blissymbols. These were administered during 3 training days, between which were withdrawal periods of 1 day and 7 days. Recognition and retention probes were administered at intervals during the training. ANOVA analysis showed that the self-generation treatment produced no immediate recognition advantage; however, better retention of symbol recognition may have occurred over time. Hence, the potential application of the self-generation effect in enhancing the retention of Blissymbols in persons with severe aphasia may warrant further investigation.

  17. Evaluating Student-Generated Film as a Learning Tool for Qualitative Methods: Geographical "Drifts" and the City

    Science.gov (United States)

    Anderson, Jon

    2013-01-01

    Film as a tool for learning offers considerable opportunity for enhancing student understanding. This paper reflects on the experiences of a project that required students to make a short film demonstrating their practical understanding of qualitative methods. In the psychogeographical tradition, students were asked to "drift" across the…

  18. Marketing Learning Communities to Generation Z: The Importance of Face-to-Face Interaction in a Digitally Driven World

    Science.gov (United States)

    Spears, Julia; Zobac, Stephanie R.; Spillane, Allison; Thomas, Shannon

    2015-01-01

    This article aims to identify the marketing strategies utilized by Learning Community (LC) administrators at two large, public, four-year research universities in the Midwest. The use of digital media coupled with face-to-face interaction is identified as an effective method of marketing LCs to the newest population of incoming college students,…

  19. Engaging the YouTube Google-Eyed Generation: Strategies for Using Web 2.0 in Teaching and Learning

    Science.gov (United States)

    Duffy, Peter

    2008-01-01

    YouTube, Podcasting, Blogs, Wikis and RSS are buzz words currently associated with the term Web 2.0 and represent a shifting pedagogical paradigm for the use of a new set of tools within education. The implication here is a possible shift from the basic archetypical vehicles used for (e)learning today (lecture notes, printed material, PowerPoint,…

  20. Teaching, Learning, and Leading with Schools and Communities: One Urban University Re-Envisions Teacher Preparation for the Next Generation

    Science.gov (United States)

    Ryan, Ann Marie; Ensminger, David C.; Heineke, Amy J.; Kennedy, Adam S.; Prasse, David P; Smetana, Lara K.

    2014-01-01

    Ultimately, the national goals of improving learning outcomes for all students and reducing, if not eliminating, the achievement gap require a teaching corps that brings knowledge and professional competencies to have positive impacts on diverse learners in diverse settings (Gándara & Maxwell-Jolly, 2006). As central actors in schools,…

  1. Competitive Debate as Competency-Based Learning: Civic Engagement and Next-Generation Assessment in the Era of the Common Core Learning Standards

    Science.gov (United States)

    McIntosh, Jonathan; Milam, Myra

    2016-01-01

    As the adoption and execution of the Common Core State Standards (CCSS) have steadily increased, the debate community is presented with an opportunity to be more forward thinking and sustainable through the translation to curriculum planning and next-generation assessment as a movement towards Performance-Based Assessments. This paper focuses on…

  2. The Fundamentals of Economic Dynamics and Policy Analyses : Learning through Numerical Examples. Part Ⅳ. Overlapping Generations Model

    OpenAIRE

    Futamura, Hiroshi

    2015-01-01

    An overlapping generations model is an applied dynamic general equilibrium model for which the lifecycle models are employed as main analytical tools. At any point in time, there are overlapping generations consisting of individuals born this year, individuals born last year, individuals born two years ago, and so on. As we saw in the analysis of lifecycle models, each individual makes an optimal consumption-saving plan to maximize lifetime utility over her/his lifecycle. For example, an indi...

  3. [Potential of cooperative learning in project development : Relevance of cooperative participation procedure for the further development of generation-appropriate accomodation in structurally weak rural areas].

    Science.gov (United States)

    Kaufmann, Gerd; Frankenberg, Olga; Sommer, Ralf-Rüdiger; Jost, Annemarie

    2017-04-01

    A joint initiative of existing senior care organizations, the municipality of Meyenburg and the state of Brandenburg was further developed by affiliation of an institute of the Brandenburg University of Technology Cottbus-Senftenberg (ABV) in cooperation with members of the architecture and social work departments in 2014. A cooperative process between different players was central to create an appropriate structure of services for this region. Cooperative projects are necessary to establish new forms of generation-appropriate living and care concepts in rural areas. Cooperative learning methods are needed to develop new forms of generation-appropriate living and care concepts in rural areas, which take the diversity of elderly people, the rural context, intergenerational residential arrangements and affordable accommodation that meets the requirements of the social security system into account. Furthermore, the project had to reflect the recent developments of the German care insurance. The article describes the participatory methods, the coordination process and the resulting concept.

  4. An Interactive System of Computer Generated Graphic Displays for Motivating Meaningful Learning of Matrix Operations and Concepts of Matrix Algebra

    Science.gov (United States)

    1990-09-01

    community’s search for a workable set of standards for school mathematics . In 1989 the National Council of Teachers of Mathematics ( NCTM ) established the...made by the Commission on Standards for School Mathematics to the National Council of Teachers of Mathematics ( NCTM ). Of the 40 students who...Abstract This -s-y evaluated students’ responses to a teaching method designed to involve students and teachers of mathematics in a meaningful learning

  5. The Atualidades Project – a generator of improvement in the teaching-learning process: report of a teaching method carried out in a higher education institution

    Directory of Open Access Journals (Sweden)

    Orlandy Orlandi

    2015-11-01

    Full Text Available Objective – Being up-to-date requires reading newspapers and articles concerning issues that are relevant to professional training; the objective of this paper is to present the teaching method Atualidades project – a generator of improvement in the teaching-learning process, carried out in a higher education institution. Design/methodology/approach – This is qualitative, exploratory research, containing testimonies by 50 students, six invited entrepreneurs and professionals, and four teachers, between years 2006 and 2010, using direct observation of students’ and guests’ presentations, document analysis of project data, and testimonies by those involved. Analytical categories: recognizing the importance of updating, relationship between selected material and subject content, awakening to the interface between theory and practice, discovery of and access to a greater amount of research sources, sharing of ideas and improvement in capacity of working in the classroom. Theoretical framework – This study considered research on teaching and learning based on systematic, disciplined, reflective and meaningful reading and interpretation of knowledge produced worldwide, which requires professionals who are connected with the world through knowledge, constant appreciation of citizens and their local, regional and international actions, in which reading is considered a promoter of prosperity and social inclusion (Lowman, 2004; Dewey, 1978; Pestalozzi, 1946. Findings – The results revealed that students, when seeking to update themselves through reading, discovered local reference business practices. Contributions – The studied teaching method contributes to education concerning teaching and learning and corroborates studies that discuss the formation of critical minds in higher education.

  6. Creating a Learning Continuum: A Critical Look at the Intersection of Prior Knowledge, Outdoor Education, and Next Generation Science Standards Disciplinary Core Ideas and Practices

    Science.gov (United States)

    Schlobohm, Trisha Leigh

    Outdoor School is a cherished educational tradition in the Portland, OR region. This program's success is attributed to its presumed ability to positively impact affective and cognitive student outcomes. Residential programs such as Outdoor School are considered to be an important supplement to the classroom model of learning because they offer an authentic, contextually rich learning environment. References to relevant literature support the idea that student gains in affective and cognitive domains occur as a result of the multi-sensory, enjoyable, hands-on nature of outdoor learning. The sample population for this study was 115 sixth graders from a demographically diverse Portland, OR school district. This study used an instrument developed by the Common Measures System that was administered to students as part of Outdoor School's professional and program development project. The affective student outcome data measured by the Common Measures instrument was complemented by a formative assessment probe ascertaining prior knowledge of the definition of plants and field notes detailing Field Study instructor lesson content. This first part of this study examined the changes that take place in students' attitudes toward science as a result of attending Outdoor School. The second part took a look at how Outdoor School instruction in the Plants field study aligned with NGSS MS-LS Disciplinary Core Ideas and Practices. The third section of the study compared how Outdoor School instruction in the Plants Field Study and students' prior knowledge of what defines a plant aligned with NGSS MS-LS DCIs. The intent of the research was to arrive at a more nuanced understanding of how students' attitudes toward science are influenced by participating in an outdoor education program and contribute to the development of a continuum between classroom and outdoor school learning using Next Generation Science Standards Disciplinary Core Ideas and Practices as a framework. Results of

  7. Learning About Parenting Together: A Programme to Support Parents with Inter-generational Concerns in Pune, India

    NARCIS (Netherlands)

    de Wit, E.E.; Chakranarayan, C; Bunders-Aelen, J.G.F.; Regeer, B.J.

    2017-01-01

    Rapid developments in the last few decades have brought about dramatic changes in Indian social life, particularly affecting new middle-class families. Inter-generational conflicts, high academic pressures, and modern anxieties lead to stress both in parents and in children. There is a need for

  8. The 2nd Generation Street Children (SGSC) in Accra: Developing Teaching Strategies to Enhance Positive Learning Outcomes in Schools

    Science.gov (United States)

    Kuyini, Alhassan Abdul-Razak; Abosi, Okechuwu

    2011-01-01

    Ghana is witnessing an increasing number of 2nd generation street children (SGSC) living in the street of Accra, the capital city as a result of many factors including teenage pregnancy among street girls, ethnic conflicts and rural-urban migration. Street presents enormous risks to street children; they are excluded from safe-family environment,…

  9. Reinforcement Learning Approach to Generate Goal-directed Locomotion of a Snake-Like Robot with Screw-Drive Units

    DEFF Research Database (Denmark)

    Chatterjee, Sromona; Nachstedt, Timo; Tamosiunaite, Minija

    2014-01-01

    Abstract—In this paper we apply a policy improvement algorithm called Policy Improvement using Path Integrals (PI2) to generate goal-directed locomotion of a complex snake-like robot with screw-drive units. PI2 is numerically simple and has an ability to deal with high dimensional systems. Here...

  10. What can the 50 Hz market learn from the 60 Hz market to avoid generator and exciter failures and damage?

    Energy Technology Data Exchange (ETDEWEB)

    Weigelt, Klaus [Brush Aftermarket, Ridderkerk (Netherlands). Global Engineering

    2012-07-01

    The economic significance of older turbo-sets lies primarily in their steadily increasing share of the total power generated worldwide. This is reflected by a trend in which plants originally built for base-load operation are increasingly being used for variable load or even continuous start-stop operation. This change occurred in the 60 Hz US market more than 25 years ago. The paper gives an overview about numerous solutions for refurbishment, life extension, retrofits and upgrades developed for generator rotors, stators and exciters. These are no prototype solutions, but solutions which already work reliably for the 60 Hz market for many years and which can be applied and adapted of the same problems of the 50 Hz market. (orig.)

  11. Developing a yearlong Next Generation Science Standard (NGSS) learning sequence focused on climate solutions: opportunities, challenges and reflections

    Science.gov (United States)

    Cordero, E.; Centeno, D.

    2015-12-01

    Over the last four years, the Green Ninja Project (GNP) has been developing educational media (e.g., videos, games and online lessons) to help motivate student interest and engagement around climate science and solutions. Inspired by the new emphasis in NGSS on climate change, human impact and engineering design, the GNP is developing a technology focused, integrative, and yearlong science curriculum focused around solutions to climate change. Recognizing the importance of teacher training on the successful implementation of NGSS, we have also integrated teacher professional development into our curriculum. During the presentation, we will describe the design philosophy around our middle school curriculum and share data from a series of classes that are piloting the curriculum during Fall 2015. We will also share our perspectives on how data, media creation and engineering can be used to create educational experiences that model the type of 'three-dimensional learning' encouraged by NGSS.

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

    Science.gov (United States)

    Torija, Antonio J; Ruiz, Diego P

    2015-02-01

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

  13. Towards the next generation of climate change assessment: learning from past experiences to inform a sustainable future

    Science.gov (United States)

    Mach, K. J.; Field, C. B.

    2017-12-01

    Over decades, assessment by the Intergovernmental Panel on Climate Change and many others has bolstered understanding of the climate problem: unequivocal warming, pervasive impacts, and serious risks from continued high emissions of heat-trapping gases. Societies are increasingly responding with early actions to decarbonize energy systems and prepare for impacts. This emerging era of climate solutions creates a need for new approaches to assessment that emphasize learning from ongoing real-world experiences and that help close the gap between aspirations and the pace of progress. Against this backdrop, the presentation will take stock of recent advances and challenges in assessment, especially drawing from analysis of climate change assessment. Four assessment priorities will be considered: (1) integrating diverse evidence including quantitative and qualitative results, (2) applying rigorous expert judgment in evaluating knowledge and uncertainties, (3) exploring widely ranging futures and their connections to ongoing choices and actions, and (4) incorporating interactions among experts and decision-makers in assessment processes. Across these assessment priorities, the presentation will critique both opportunities and pitfalls, outlining possibilities for future experimentation, innovation, and learning. It will evaluate, in particular, lessons from risk-based approaches; strategies for transparently acknowledging persistent uncertainties and contested priorities; ways to minimize biases and foster creativity in expert judgments; scenario-based assessment of surprises, deep uncertainties, and decision-making implications; and opportunities for broadening the conception of expertise and engaging different decision-makers and stakeholders. Overall, these approaches can advance assessment products and processes as a basis for sustained dialogue supporting decision-making.

  14. Three children with autism spectrum disorder learn to perform a three-step communication sequence using an iPad®-based speech-generating device.

    Science.gov (United States)

    Waddington, Hannah; Sigafoos, Jeff; Lancioni, Giulio E; O'Reilly, Mark F; van der Meer, Larah; Carnett, Amarie; Stevens, Michelle; Roche, Laura; Hodis, Flaviu; Green, Vanessa A; Sutherland, Dean; Lang, Russell; Marschik, Peter B

    2014-12-01

    Many children with autism spectrum disorder (ASD) have limited or absent speech and might therefore benefit from learning to use a speech-generating device (SGD). The purpose of this study was to evaluate a procedure aimed at teaching three children with ASD to use an iPad(®)-based SGD to make a general request for access to toys, then make a specific request for one of two toys, and then communicate a thank-you response after receiving the requested toy. A multiple-baseline across participants design was used to determine whether systematic instruction involving least-to-most-prompting, time delay, error correction, and reinforcement was effective in teaching the three children to engage in this requesting and social communication sequence. Generalization and follow-up probes were conducted for two of the three participants. With intervention, all three children showed improvement in performing the communication sequence. This improvement was maintained with an unfamiliar communication partner and during the follow-up sessions. With systematic instruction, children with ASD and severe communication impairment can learn to use an iPad-based SGD to complete multi-step communication sequences that involve requesting and social communication functions. Copyright © 2014 ISDN. Published by Elsevier Ltd. All rights reserved.

  15. Secondary side corrosion in steam generator tubes: lessons learned in France from the in-service inspection results

    International Nuclear Information System (INIS)

    Comby, R.

    1997-01-01

    Non-destructive testing (NDT) has proved to be very important in the maintenance of steam generator tubing. This is particularly true in the case of secondary side corrosion, because this type of degradation leads to various morphologies which are often complex (intergranular attack) (IGA), intergranular stress corrosion cracking (IGSCC), or a mixture of both. Their detection and characterization by the usual NDT techniques have been achieved through numerous laboratory studies, which were conducted in order to determine the performance and limitations of NDT. Pulled tube examination in a hot laboratory was very valuable, for both NDT and fracture mechanics aspects. The eddy current bobbin coil probe, used for multipurpose inspection of tubes, allows the detection of IGA-SCC at the tube support plate elevation. In France, the use of rotating probes is not required for that type of degradation, since the repair criterion is based on bobbin coil results only. The bobbin coil is also used for detection of IGSCC occurring in free spans, within sludge deposits. The eddy current rotating probe allows, in that case, characterization of main cracks. Concerning the outer diameter initiated circumferential cracks which occur at the top of the tube sheet, only the rotating probe is used. An ultrasonic (UT) inspection was performed several times, in order to obtain information on UT capabilities. The goal of tube inspection is obviously knowledge of the status of steam generators, but also to follow up degradations and to estimate their revolution, and to verify the beneficial effect of some corrective measures, e.g. boric acid injection. (orig.)

  16. Automata learning algorithms and processes for providing more complete systems requirements specification by scenario generation, CSP-based syntax-oriented model construction, and R2D2C system requirements transformation

    Science.gov (United States)

    Hinchey, Michael G. (Inventor); Margaria, Tiziana (Inventor); Rash, James L. (Inventor); Rouff, Christopher A. (Inventor); Steffen, Bernard (Inventor)

    2010-01-01

    Systems, methods and apparatus are provided through which in some embodiments, automata learning algorithms and techniques are implemented to generate a more complete set of scenarios for requirements based programming. More specifically, a CSP-based, syntax-oriented model construction, which requires the support of a theorem prover, is complemented by model extrapolation, via automata learning. This may support the systematic completion of the requirements, the nature of the requirement being partial, which provides focus on the most prominent scenarios. This may generalize requirement skeletons by extrapolation and may indicate by way of automatically generated traces where the requirement specification is too loose and additional information is required.

  17. Automated Learning of Subcellular Variation among Punctate Protein Patterns and a Generative Model of Their Relation to Microtubules.

    Directory of Open Access Journals (Sweden)

    Gregory R Johnson

    2015-12-01

    Full Text Available Characterizing the spatial distribution of proteins directly from microscopy images is a difficult problem with numerous applications in cell biology (e.g. identifying motor-related proteins and clinical research (e.g. identification of cancer biomarkers. Here we describe the design of a system that provides automated analysis of punctate protein patterns in microscope images, including quantification of their relationships to microtubules. We constructed the system using confocal immunofluorescence microscopy images from the Human Protein Atlas project for 11 punctate proteins in three cultured cell lines. These proteins have previously been characterized as being primarily located in punctate structures, but their images had all been annotated by visual examination as being simply "vesicular". We were able to show that these patterns could be distinguished from each other with high accuracy, and we were able to assign to one of these subclasses hundreds of proteins whose subcellular localization had not previously been well defined. In addition to providing these novel annotations, we built a generative approach to modeling of punctate distributions that captures the essential characteristics of the distinct patterns. Such models are expected to be valuable for representing and summarizing each pattern and for constructing systems biology simulations of cell behaviors.

  18. Designing next-generation platforms for evaluating scientific output: What scientists can learn from the social web

    Directory of Open Access Journals (Sweden)

    Tal eYarkoni

    2012-10-01

    Full Text Available Traditional pre-publication peer review of scientific output is a slow, inefficient, and unreliable process. Efforts to replace or supplement traditional evaluation models with open evaluation platforms that leverage advances in information technology are slowly gaining traction, but remain in the early stages of design and implementation. Here I discuss a number of considerations relevant to the development of such platforms. I focus particular attention on three core elements that next-generation evaluation platforms should strive to emphasize, including (a open and transparent access to accumulated evaluation data, (b personalized and highly customizable performance metrics, and (c appropriate short-term incentivization of the userbase. Because all of these elements have already been successfully implemented on a large scale in hundreds of existing social web applications, I argue that development of new scientific evaluation platforms should proceed largely by adapting existing techniques rather than engineering entirely new evaluation mechanisms. Successful implementation of open evaluation platforms has the potential to substantially advance both the pace and the quality of scientific publication and evaluation, and the scientific community has a vested interest in shifting towards such models as soon as possible.

  19. Educational Software for the Teaching and Learning of Quadrilaterals Generated from a Programming Language and the Dabeja Method (Invited Paper

    Directory of Open Access Journals (Sweden)

    Daniel Bejarano Segura

    2016-06-01

    Full Text Available The teaching of math is a process that starts from an early age especially the teaching of geometry through which different representations, constructions, axioms, and theorems among others helps develop the formal thoughts of individuals. This requires not only graphical but demonstrative processes that mentally schemes chords to generate levels of rational thought. Quadrilaterals are part of the components of geometry in the two-dimensional and three-dimensional fields. They possess properties, definitions, classifications, and studies through postulations of parallelism and perpendicularity. Using dynamic strategies and formal processes of knowledge as the Dabeja method to strengthen the teaching of geometry of quadrilaterals through the construction of dynamic courseware, is one of the questions that reveals problems in thought formation. This is an investigation of a parametric quantitative approach with an experimental design of research aimed at the techno de facto and their relationship with the individual development of a formal thinking. An educational software was developed using the Java programming language to construct quadrilaterals, demonstrate their properties and relationships through the Dabeja method.

  20. L1-norm locally linear representation regularization multi-source adaptation learning.

    Science.gov (United States)

    Tao, Jianwen; Wen, Shiting; Hu, Wenjun

    2015-09-01

    In most supervised domain adaptation learning (DAL) tasks, one has access only to a small number of labeled examples from target domain. Therefore the success of supervised DAL in this "small sample" regime needs the effective utilization of the large amounts of unlabeled data to extract information that is useful for generalization. Toward this end, we here use the geometric intuition of manifold assumption to extend the established frameworks in existing model-based DAL methods for function learning by incorporating additional information about the target geometric structure of the marginal distribution. We would like to ensure that the solution is smooth with respect to both the ambient space and the target marginal distribution. In doing this, we propose a novel L1-norm locally linear representation regularization multi-source adaptation learning framework which exploits the geometry of the probability distribution, which has two techniques. Firstly, an L1-norm locally linear representation method is presented for robust graph construction by replacing the L2-norm reconstruction measure in LLE with L1-norm one, which is termed as L1-LLR for short. Secondly, considering the robust graph regularization, we replace traditional graph Laplacian regularization with our new L1-LLR graph Laplacian regularization and therefore construct new graph-based semi-supervised learning framework with multi-source adaptation constraint, which is coined as L1-MSAL method. Moreover, to deal with the nonlinear learning problem, we also generalize the L1-MSAL method by mapping the input data points from the input space to a high-dimensional reproducing kernel Hilbert space (RKHS) via a nonlinear mapping. Promising experimental results have been obtained on several real-world datasets such as face, visual video and object. Copyright © 2015 Elsevier Ltd. All rights reserved.

  1. PAHs and the Diffuse Interstellar Bands. What have we Learned from the New Generation of Laboratory and Observational Studies?

    Science.gov (United States)

    Salama, Farid

    2005-01-01

    Polycyclic Aromatic Hydrocarbons (PAHs) are an important and ubiquitous component of carbon-bearing materials in space. PAHs are the best-known candidates to account for the IR emission bands (UIR bands) and PAH spectral features are now being used as new probes of the ISM. PAHs are also thought to be among the carriers of the diffuse interstellar absorption bands (DIBs). In the model dealing with the interstellar spectral features, PAHs are present as a mixture of radicals, ions and neutral species. PAH ionization states reflect the ionization balance of the medium while PAH size, composition, and structure reflect the energetic and chemical history of the medium. A major challenge for laboratory astrophysics is to reproduce (in a realistic way) the physical conditions that exist in the emission and/or absorption interstellar zones, An extensive laboratory program has been developed at NASA Ames to characterize the physical and chemical properties of PAHs in astrophysical environments and to describe how they influence the radiation and energy balance in space and the interstellar chemistry. In particular, laboratory experiments provide measurements of the spectral characteristics of interstellar PAH analogs from the ultraviolet and visible range to the infrared range for comparison with astronomical data. This paper will focus on the recent progress made in the laboratory to measure the direct absorption spectra of neutral and ionized PAHs in the gas phase in the near-W and visible range in astrophysically relevant environments. These measurements provide data on PAHs and nanometer-sized particles that can now be directly compared to astronomical observations. The harsh physical conditions of the IS medium - characterized by a low temperature, an absence of collisions and strong V W radiation fields - are simulated in the laboratory by associating a molecular beam with an ionizing discharge to generate a cold plasma expansion. PAH ions are formed from the neutral

  2. Lessons learned from the Febex in situ test: geochemical processes associated to the microbial degradation and gas generation

    International Nuclear Information System (INIS)

    Fernandez, A. M.; Sanchez, D.M.; Melon, A.; Mingarro, M.; Wieczorek, K.

    2012-01-01

    existence of gaps between the bentonite blocks, which favour the development and growth of inactive and dormant cells or spores belonging to the original bentonite. In this work, the observed geochemical and corrosion processes influenced both by organic matter degradation and micro-organisms in the 1:1 scale FEBEX in situ test (Grimsel, Switzerland) are described. This test consists of two heaters, simulating radioactive waste containers, emplaced in a horizontal gallery and surrounded by a highly compacted bentonite barrier. Samples from pore water, gases and bentonite (SHSDI-01: clay in contact with AISI 316L metal; S29 and BSBI-26: clay in contact with carbon steel) have been analysed. The samples were obtained during the test and the dismantling of the heater 1 after six years of experiment. The solid samples were analysed by XRD, SEM, XPS, FTIR, ATD-TG and chemical analysis; the water samples by IC and ICP-OES, and the gases by gas chromatography. Different geochemical processes have been detected as a function of the temperature and water content of the samples. When the water content is high, there are aerobic respiration and fermentation processes, anaerobic respiration with SO 4 2- as electron acceptor, and anaerobic production of methane with CO 2 as electron acceptor. In a first phase, both oxygen consumption and an increase of CH 4 and CO 2 is observed. Afterwards, there is a reduction of sulfates by SRB bacteria, which provokes corrosion processes. As a consequence, a precipitation of sulphurs, iron oxy-hydroxides and carbonates occurs, as well as H 2 generation. There is an increase of the iron content in the smectite and the neo-formation of zeolites. However this alteration is punctual and localized. The redox potential of the bentonite pore water was of -284 mV. When the temperature is high and water content is low, other processes take place

  3. Do planetary seasons play a fundamental role in attaining habitable climates?

    DEFF Research Database (Denmark)

    Olsen, Kasper Wibeck; Bohr, Jakob

    2016-01-01

    Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave...... the generative model unchanged but make the variational distribution more expressive. Inspired by the structure of the auxiliary variable we also propose a model with two stochastic layers and skip connections. Our findings suggest that more expressive and properly specified deep generative models converge...

  4. Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

    Energy Technology Data Exchange (ETDEWEB)

    Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin, E-mail: xmli@cqu.edu.cn [Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education, Chongqing University, Chongqing 400044 (China); College of Automation, Chongqing University, Chongqing 400044 (China)

    2015-11-15

    In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

  5. Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

    International Nuclear Information System (INIS)

    Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

    2015-01-01

    In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing

  6. A Novel Method of Building Functional Brain Network Using Deep Learning Algorithm with Application in Proficiency Detection.

    Science.gov (United States)

    Hua, Chengcheng; Wang, Hong; Wang, Hong; Lu, Shaowen; Liu, Chong; Khalid, Syed Madiha

    2018-04-11

    Functional brain network (FBN) has become very popular to analyze the interaction between cortical regions in the last decade. But researchers always spend a long time to search the best way to compute FBN for their specific studies. The purpose of this study is to detect the proficiency of operators during their mineral grinding process controlling based on FBN. To save the search time, a novel semi-data-driven method of computing functional brain connection based on stacked autoencoder (BCSAE) is proposed in this paper. This method uses stacked autoencoder (SAE) to encode the multi-channel EEG data into codes and then computes the dissimilarity between the codes from every pair of electrodes to build FBN. The highlight of this method is that the SAE has a multi-layered structure and is semi-supervised, which means it can dig deeper information and generate better features. Then an experiment was performed, the EEG of the operators were collected while they were operating and analyzed to detect their proficiency. The results show that the BCSAE method generated more number of separable features with less redundancy, and the average accuracy of classification (96.18%) is higher than that of the control methods: PLV (92.19%) and PLI (78.39%).

  7. Multimodal manifold-regularized transfer learning for MCI conversion prediction.

    Science.gov (United States)

    Cheng, Bo; Liu, Mingxia; Suk, Heung-Il; Shen, Dinggang; Zhang, Daoqiang

    2015-12-01

    As the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has high chance to convert to AD. Effective prediction of such conversion from MCI to AD is of great importance for early diagnosis of AD and also for evaluating AD risk pre-symptomatically. Unlike most previous methods that used only the samples from a target domain to train a classifier, in this paper, we propose a novel multimodal manifold-regularized transfer learning (M2TL) method that jointly utilizes samples from another domain (e.g., AD vs. normal controls (NC)) as well as unlabeled samples to boost the performance of the MCI conversion prediction. Specifically, the proposed M2TL method includes two key components. The first one is a kernel-based maximum mean discrepancy criterion, which helps eliminate the potential negative effect induced by the distributional difference between the auxiliary domain (i.e., AD and NC) and the target domain (i.e., MCI converters (MCI-C) and MCI non-converters (MCI-NC)). The second one is a semi-supervised multimodal manifold-regularized least squares classification method, where the target-domain samples, the auxiliary-domain samples, and the unlabeled samples can be jointly used for training our classifier. Furthermore, with the integration of a group sparsity constraint into our objective function, the proposed M2TL has a capability of selecting the informative samples to build a robust classifier. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database validate the effectiveness of the proposed method by significantly improving the classification accuracy of 80.1 % for MCI conversion prediction, and also outperforming the state-of-the-art methods.

  8. Improved Neural Signal Classification in a Rapid Serial Visual Presentation Task Using Active Learning.

    Science.gov (United States)

    Marathe, Amar R; Lawhern, Vernon J; Wu, Dongrui; Slayback, David; Lance, Brent J

    2016-03-01

    The application space for brain-computer interface (BCI) technologies is rapidly expanding with improvements in technology. However, most real-time BCIs require extensive individualized calibration prior to use, and systems often have to be recalibrated to account for changes in the neural signals due to a variety of factors including changes in human state, the surrounding environment, and task conditions. Novel approaches to reduce calibration time or effort will dramatically improve the usability of BCI systems. Active Learning (AL) is an iterative semi-supervised learning technique for learning in situations in which data may be abundant, but labels for the data are difficult or expensive to obtain. In this paper, we apply AL to a simulated BCI system for target identification using data from a rapid serial visual presentation (RSVP) paradigm to minimize the amount of training samples needed to initially calibrate a neural classifier. Our results show AL can produce similar overall classification accuracy with significantly less labeled data (in some cases less than 20%) when compared to alternative calibration approaches. In fact, AL classification performance matches performance of 10-fold cross-validation (CV) in over 70% of subjects when training with less than 50% of the data. To our knowledge, this is the first work to demonstrate the use of AL for offline electroencephalography (EEG) calibration in a simulated BCI paradigm. While AL itself is not often amenable for use in real-time systems, this work opens the door to alternative AL-like systems that are more amenable for BCI applications and thus enables future efforts for developing highly adaptive BCI systems.

  9. Deterministic and probabilistic interval prediction for short-term wind power generation based on variational mode decomposition and machine learning methods

    International Nuclear Information System (INIS)

    Zhang, Yachao; Liu, Kaipei; Qin, Liang; An, Xueli

    2016-01-01

    Highlights: • Variational mode decomposition is adopted to process original wind power series. • A novel combined model based on machine learning methods is established. • An improved differential evolution algorithm is proposed for weight adjustment. • Probabilistic interval prediction is performed by quantile regression averaging. - Abstract: Due to the increasingly significant energy crisis nowadays, the exploitation and utilization of new clean energy gains more and more attention. As an important category of renewable energy, wind power generation has become the most rapidly growing renewable energy in China. However, the intermittency and volatility of wind power has restricted the large-scale integration of wind turbines into power systems. High-precision wind power forecasting is an effective measure to alleviate the negative influence of wind power generation on the power systems. In this paper, a novel combined model is proposed to improve the prediction performance for the short-term wind power forecasting. Variational mode decomposition is firstly adopted to handle the instability of the raw wind power series, and the subseries can be reconstructed by measuring sample entropy of the decomposed modes. Then the base models can be established for each subseries respectively. On this basis, the combined model is developed based on the optimal virtual prediction scheme, the weight matrix of which is dynamically adjusted by a self-adaptive multi-strategy differential evolution algorithm. Besides, a probabilistic interval prediction model based on quantile regression averaging and variational mode decomposition-based hybrid models is presented to quantify the potential risks of the wind power series. The simulation results indicate that: (1) the normalized mean absolute errors of the proposed combined model from one-step to three-step forecasting are 4.34%, 6.49% and 7.76%, respectively, which are much lower than those of the base models and the hybrid

  10. In-situ trainable intrusion detection system

    Energy Technology Data Exchange (ETDEWEB)

    Symons, Christopher T.; Beaver, Justin M.; Gillen, Rob; Potok, Thomas E.

    2016-11-15

    A computer implemented method detects intrusions using a computer by analyzing network traffic. The method includes a semi-supervised learning module connected to a network node. The learning module uses labeled and unlabeled data to train a semi-supervised machine learning sensor. The method records events that include a feature set made up of unauthorized intrusions and benign computer requests. The method identifies at least some of the benign computer requests that occur during the recording of the events while treating the remainder of the data as unlabeled. The method trains the semi-supervised learning module at the network node in-situ, such that the semi-supervised learning modules may identify malicious traffic without relying on specific rules, signatures, or anomaly detection.

  11. Active Learning Methods

    Science.gov (United States)

    Zayapragassarazan, Z.; Kumar, Santosh

    2012-01-01

    Present generation students are primarily active learners with varied learning experiences and lecture courses may not suit all their learning needs. Effective learning involves providing students with a sense of progress and control over their own learning. This requires creating a situation where learners have a chance to try out or test their…

  12. Followers of Confucianism or a New Generation? Learning Culture of Mainland Chinese: In Pursuit of Western-Based Business Education Away from Mainland China

    Science.gov (United States)

    Rajaram, Kumaran

    2013-01-01

    The mainland Chinese learning culture has evolved due to the rapid changes in the economic, political, cultural and demographic demands. The changing characteristics of the Chinese students' learning behavioral styles and preferences, as well as the challenges faced in pursuit of Western-based education, are discussed with suggested…

  13. Teaching Millennials and Generation Z: Bridging the Generational Divide.

    Science.gov (United States)

    Shatto, Bobbi; Erwin, Kelly

    2017-02-01

    Most undergraduate students today are part of the millennial generation. However, the next wave of students-Generation Z-are just beginning to enter universities. Although these groups share many similarities, they each have unique characteristics that create challenges in the classroom. Incorporating technology, engaging students with adaptive learning activities, and understanding basic generational differences are ways to limit the effects of generational conflict while keeping both millennials and Generation Z students engaged in learning. It is important to understand basic differences and distinctions across generations for developing pedagogy that reaches these unique student populations.

  14. Context-sensitive intra-class clustering

    KAUST Repository

    Yu, Yingwei; Gutierrez-Osuna, Ricardo; Choe, Yoonsuck

    2014-01-01

    This paper describes a new semi-supervised learning algorithm for intra-class clustering (ICC). ICC partitions each class into sub-classes in order to minimize overlap across clusters from different classes. This is achieved by allowing partitioning

  15. E-assessment for learning? Exploring the potential of computer-marked assessment and computer-generated feedback, from short-answer questions to assessment analytics.

    OpenAIRE

    Jordan, Sally

    2014-01-01

    This submission draws on research from twelve publications, all addressing some aspect of the broad research question: “Can interactive computer-marked assessment improve the effectiveness of assessment for learning?” \\ud \\ud The work starts from a consideration of the conditions under which assessment of any sort is predicted to best support learning, and reviews the broader literature of assessment and feedback before considering the potential of computer-based assessment, focusing on relat...

  16. Is mobile learning a substitute for electronic learning?

    OpenAIRE

    Sitthiworachart, Jirarat; Joy, Mike

    2008-01-01

    Mobile learning is widely regarded as the next generation of learning technologies, and refers to the use of mobile devices in education to enhance learning activities. The increasing use of mobile devices has encouraged research into the capabilities of mobile learning systems. Many questions arise about mobile learning, such as whether mobile learning can be a substitute for electronic learning, what the potential benefits and problems of utilizing mobile devices in education are, and what ...

  17. A Reinforcement Learning Model Equipped with Sensors for Generating Perception Patterns: Implementation of a Simulated Air Navigation System Using ADS-B (Automatic Dependent Surveillance-Broadcast) Technology.

    Science.gov (United States)

    Álvarez de Toledo, Santiago; Anguera, Aurea; Barreiro, José M; Lara, Juan A; Lizcano, David

    2017-01-19

    Over the last few decades, a number of reinforcement learning techniques have emerged, and different reinforcement learning-based applications have proliferated. However, such techniques tend to specialize in a particular field. This is an obstacle to their generalization and extrapolation to other areas. Besides, neither the reward-punishment (r-p) learning process nor the convergence of results is fast and efficient enough. To address these obstacles, this research proposes a general reinforcement learning model. This model is independent of input and output types and based on general bioinspired principles that help to speed up the learning process. The model is composed of a perception module based on sensors whose specific perceptions are mapped as perception patterns. In this manner, similar perceptions (even if perceived at different positions in the environment) are accounted for by the same perception pattern. Additionally, the model includes a procedure that statistically associates perception-action pattern pairs depending on the positive or negative results output by executing the respective action in response to a particular perception during the learning process. To do this, the model is fitted with a mechanism that reacts positively or negatively to particular sensory stimuli in order to rate results. The model is supplemented by an action module that can be configured depending on the maneuverability of each specific agent. The model has been applied in the air navigation domain, a field with strong safety restrictions, which led us to implement a simulated system equipped with the proposed model. Accordingly, the perception sensors were based on Automatic Dependent Surveillance-Broadcast (ADS-B) technology, which is described in this paper. The results were quite satisfactory, and it outperformed traditional methods existing in the literature with respect to learning reliability and efficiency.

  18. Motion Learning Based on Bayesian Program Learning

    Directory of Open Access Journals (Sweden)

    Cheng Meng-Zhen

    2017-01-01

    Full Text Available The concept of virtual human has been highly anticipated since the 1980s. By using computer technology, Human motion simulation could generate authentic visual effect, which could cheat human eyes visually. Bayesian Program Learning train one or few motion data, generate new motion data by decomposing and combining. And the generated motion will be more realistic and natural than the traditional one.In this paper, Motion learning based on Bayesian program learning allows us to quickly generate new motion data, reduce workload, improve work efficiency, reduce the cost of motion capture, and improve the reusability of data.

  19. 學生出題的學習歷程及其與工作價值感之相關 Student Question-Generation: The Learning Processes Involved and Their Relationships with Students’ Perceived Value

    Directory of Open Access Journals (Sweden)

    于富雲 Fu-Yun Yu

    2012-12-01

    Full Text Available 目前學生出題相關研究主要採用實驗設計法或行動研究法,以驗證此教學策略的學習成效。雖然學生出題已有理論以及實證基礎雄厚,有關學生出題的學習歷程以及其與工作價值感之相關性為何,目前尚少研究深入探究與瞭解。考量上述議題具學生出題教學意涵,且有其實證、研究方法與理論之重要性,本研究鎖定以下議題探究:一、以訊息處理與學生學習方法理論解析學生出題的內在運思歷程;二、建立單一學習情境下多重學習方法的實證基礎,並瞭解不同學習方法下,學習策略運用與學生出題價值感的差異情形;三、探究學生出題價值感、學習策略運用與學習方法間的關係。採調查研究法,針對50 位教育學程修課學生,以信度與效度俱全的研究工具蒐集相關資料。主要研究發現:一、學生出題情境下,學生傾向採用學習策略與深層學習方法;二、特定情境下多重學習方法現象確實存在;三、不同學習方法採用者在學生出題價值感與學習策略上有顯著不同;四、學生出題價值感愈高者愈傾向採用深層的學習方法。文末,提出本研究在理論、研究方法與實證上的貢獻,以及教學實施與未來研究建議。 Studies on student question-generation have mainly emphasized its value as an instructional intervention and examined its effects using experimental or action research methods. Although the theoretical foundations of student question-generation are sound and its empirical bases are solid, issues with regard to the nature of the enacted learning processes and their relationships with perceived value remain largely unexamined empirically. These issues should have important instructional implications, as well as empirical, methodological, and theoretical significance. Therefore, this study aims to reveal the nature of student

  20. Third generation coaching

    DEFF Research Database (Denmark)

    Stelter, Reinhard

    2014-01-01

    Third generation coaching unfolds a new universe for coaching and coaching psychology in the framework of current social research, new learning theories and discourses about personal leadership. Third generation coaching views coaching in a societal perspective. Coaching has become important...... transformation. Coaching thus facilitates new reflections and perspectives, as well as empowerment and support for self-Bildung processes. Third generation coaching focuses on the coach and the coachee in their narrative collaborative partnership. Unlike first generation coaching, where the goal is to help...