Classifying Radio Galaxies with the Convolutional Neural Network

Energy Technology Data Exchange (ETDEWEB)

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

2017-06-01

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

Classifying Radio Galaxies with the Convolutional Neural Network

Science.gov (United States)

Aniyan, A. K.; Thorat, K.

2017-06-01

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

Classifying Radio Galaxies with the Convolutional Neural Network

International Nuclear Information System (INIS)

Aniyan, A. K.; Thorat, K.

2017-01-01

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

Revealing effective classifiers through network comparison

Science.gov (United States)

Gallos, Lazaros K.; Fefferman, Nina H.

2014-11-01

The ability to compare complex systems can provide new insight into the fundamental nature of the processes captured, in ways that are otherwise inaccessible to observation. Here, we introduce the n-tangle method to directly compare two networks for structural similarity, based on the distribution of edge density in network subgraphs. We demonstrate that this method can efficiently introduce comparative analysis into network science and opens the road for many new applications. For example, we show how the construction of a “phylogenetic tree” across animal taxa according to their social structure can reveal commonalities in the behavioral ecology of the populations, or how students create similar networks according to the University size. Our method can be expanded to study many additional properties, such as network classification, changes during time evolution, convergence of growth models, and detection of structural changes during damage.

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

Directory of Open Access Journals (Sweden)

M. Njah

2017-06-01

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

Using the TensorFlow Deep Neural Network to Classify Mainland China Visitor Behaviours in Hong Kong from Check-in Data

Directory of Open Access Journals (Sweden)

Shanshan Han

2018-04-01

Full Text Available Over the past decade, big data, including Global Positioning System (GPS data, mobile phone tracking data and social media check-in data, have been widely used to analyse human movements and behaviours. Tourism management researchers have noted the potential of applying these data to study tourist behaviours, and many studies have shown that social media check-in data can provide new opportunities for extracting tourism activities and tourist behaviours. However, traditional methods may not be suitable for extracting comprehensive tourist behaviours due to the complexity and diversity of human behaviours. Studies have shown that deep neural networks have outpaced the abilities of human beings in many fields and that deep neural networks can be explained in a psychological manner. Thus, deep neural network methods can potentially be used to understand human behaviours. In this paper, a deep learning neural network constructed in TensorFlow is applied to classify Mainland China visitor behaviours in Hong Kong, and the characteristics of these visitors are analysed to verify the classification results. For the social science classification problem investigated in this study, the deep neural network classifier in TensorFlow provides better accuracy and more lucid visualisation than do traditional neural network methods, even for erratic classification rules. Furthermore, the results of this study reveal that TensorFlow has considerable potential for application in the human geography field.

Autoregressive Integrated Adaptive Neural Networks Classifier for EEG-P300 Classification

Directory of Open Access Journals (Sweden)

Demi Soetraprawata

2013-06-01

Full Text Available Brain Computer Interface has a potency to be applied in mechatronics apparatus and vehicles in the future. Compared to the other techniques, EEG is the most preferred for BCI designs. In this paper, a new adaptive neural network classifier of different mental activities from EEG-based P300 signals is proposed. To overcome the over-training that is caused by noisy and non-stationary data, the EEG signals are filtered and extracted using autoregressive models before passed to the adaptive neural networks classifier. To test the improvement in the EEG classification performance with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis. The experiment results show that the all subjects achieve a classification accuracy of 100%.

Constructing and Classifying Email Networks from Raw Forensic Images

Science.gov (United States)

2016-09-01

AUC value will be closer to 1. Figure 2.6 compares 3 different ROC curves. Figure 2.6. ROC curves compared. The dashed black curve at the top has the...main difference was the computation time. For example, on a 1275-node jazz musician network, the fast algorithm ran to completion in about one...königsberg bridges,” Scientific American , vol. 189, no. 1, pp. 66–70, 1953. [8] N. Biggs, E. K. Lloyd, and R. J. Wilson, Graph Theory, 1736-1936. Great

Transforming Musical Signals through a Genre Classifying Convolutional Neural Network

Science.gov (United States)

Geng, S.; Ren, G.; Ogihara, M.

2017-05-01

Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the abstracting process. One can hope to manipulate existing music based on this 'informed' network and create music with new features corresponding to the knowledge obtained by the network. In this paper, we propose a method to utilize the stored information from a CNN trained on musical genre classification task. The network was composed of three convolutional layers, and was trained to classify five-second song clips into five different genres. After training, randomly selected clips were modified by maximizing the sum of outputs from the network layers. In addition to the potential of such CNNs to produce interesting audio transformation, more information about the network and the original music could be obtained from the analysis of the generated features since these features indicate how the network 'understands' the music.

FERAL : Network-based classifier with application to breast cancer outcome prediction

NARCIS (Netherlands)

Allahyar, A.; De Ridder, J.

2015-01-01

Motivation: Breast cancer outcome prediction based on gene expression profiles is an important strategy for personalize patient care. To improve performance and consistency of discovered markers of the initial molecular classifiers, network-based outcome prediction methods (NOPs) have been proposed.

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

Science.gov (United States)

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

2017-03-01

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

How to construct the statistic network? An association network of herbaceous

Directory of Open Access Journals (Sweden)

WenJun Zhang

2012-06-01

Full Text Available In present study I defined a new type of network, the statistic network. The statistic network is a weighted and non-deterministic network. In the statistic network, a connection value, i.e., connection weight, represents connection strength and connection likelihood between two nodes and its absolute value falls in the interval (0,1]. The connection value is expressed as a statistical measure such as correlation coefficient, association coefficient, or Jaccard coefficient, etc. In addition, all connections of the statistic network can be statistically tested for their validity. A connection is true if the connection value is statistically significant. If all connection values of a node are not statistically significant, it is an isolated node. An isolated node has not any connection to other nodes in the statistic network. Positive and negative connection values denote distinct connectiontypes (positive or negative association or interaction. In the statistic network, two nodes with the greater connection value will show more similar trend in the change of their states. At any time we can obtain a sample network of the statistic network. A sample network is a non-weighted and deterministic network. Thestatistic network, in particular the plant association network that constructed from field sampling, is mostly an information network. Most of the interspecific relationships in plant community are competition and cooperation. Therefore in comparison to animal networks, the methodology of statistic network is moresuitable to construct plant association networks. Some conclusions were drawn from this study: (1 in the plant association network, most connections are weak and positive interactions. The association network constructed from Spearman rank correlation has most connections and isolated taxa are fewer. From net linear correlation,linear correlation, to Spearman rank correlation, the practical number of connections and connectance in the

Properties of healthcare teaming networks as a function of network construction algorithms.

Directory of Open Access Journals (Sweden)

Martin S Zand

Full Text Available Network models of healthcare systems can be used to examine how providers collaborate, communicate, refer patients to each other, and to map how patients traverse the network of providers. Most healthcare service network models have been constructed from patient claims data, using billing claims to link a patient with a specific provider in time. The data sets can be quite large (106-108 individual claims per year, making standard methods for network construction computationally challenging and thus requiring the use of alternate construction algorithms. While these alternate methods have seen increasing use in generating healthcare networks, there is little to no literature comparing the differences in the structural properties of the generated networks, which as we demonstrate, can be dramatically different. To address this issue, we compared the properties of healthcare networks constructed using different algorithms from 2013 Medicare Part B outpatient claims data. Three different algorithms were compared: binning, sliding frame, and trace-route. Unipartite networks linking either providers or healthcare organizations by shared patients were built using each method. We find that each algorithm produced networks with substantially different topological properties, as reflected by numbers of edges, network density, assortativity, clustering coefficients and other structural measures. Provider networks adhered to a power law, while organization networks were best fit by a power law with exponential cutoff. Censoring networks to exclude edges with less than 11 shared patients, a common de-identification practice for healthcare network data, markedly reduced edge numbers and network density, and greatly altered measures of vertex prominence such as the betweenness centrality. Data analysis identified patterns in the distance patients travel between network providers, and a striking set of teaming relationships between providers in the Northeast

Sequential Construction of Costly Networks

Energy Technology Data Exchange (ETDEWEB)

Gutfraind, Alexander [Los Alamos National Laboratory

2011-01-01

Natural disasters or attacks often disrupt infrastructure networks requiring a costly recovery. This motivates an optimization problem where the objecitve is to construct the nodes of a graph G(V;E), and the cost of each node is dependent on the number of its neighbors previously constructed, or more generally, any properties of the previously-completed subgraph. In this optimization problem the objective is to find a permutation of the nodes which results in the least construction cost. We prove that in the case where the cost of nodes is a convex function in the number of neighbors, the optimal construction sequence is to start at a single node and move outwards. We also introduce algorithms and heuristics for solving various instances of the problem. Those methods can be applied to help reduce the cost of recovering from disasters as well as to plan the deployment of new network infrastructure.

A systems biology-based classifier for hepatocellular carcinoma diagnosis.

Directory of Open Access Journals (Sweden)

Yanqiong Zhang

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

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

Science.gov (United States)

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data

Directory of Open Access Journals (Sweden)

Evangelos Stromatias

2017-06-01

Full Text Available This paper introduces a novel methodology for training an event-driven classifier within a Spiking Neural Network (SNN System capable of yielding good classification results when using both synthetic input data and real data captured from Dynamic Vision Sensor (DVS chips. The proposed supervised method uses the spiking activity provided by an arbitrary topology of prior SNN layers to build histograms and train the classifier in the frame domain using the stochastic gradient descent algorithm. In addition, this approach can cope with leaky integrate-and-fire neuron models within the SNN, a desirable feature for real-world SNN applications, where neural activation must fade away after some time in the absence of inputs. Consequently, this way of building histograms captures the dynamics of spikes immediately before the classifier. We tested our method on the MNIST data set using different synthetic encodings and real DVS sensory data sets such as N-MNIST, MNIST-DVS, and Poker-DVS using the same network topology and feature maps. We demonstrate the effectiveness of our approach by achieving the highest classification accuracy reported on the N-MNIST (97.77% and Poker-DVS (100% real DVS data sets to date with a spiking convolutional network. Moreover, by using the proposed method we were able to retrain the output layer of a previously reported spiking neural network and increase its performance by 2%, suggesting that the proposed classifier can be used as the output layer in works where features are extracted using unsupervised spike-based learning methods. In addition, we also analyze SNN performance figures such as total event activity and network latencies, which are relevant for eventual hardware implementations. In summary, the paper aggregates unsupervised-trained SNNs with a supervised-trained SNN classifier, combining and applying them to heterogeneous sets of benchmarks, both synthetic and from real DVS chips.

An Event-Driven Classifier for Spiking Neural Networks Fed with Synthetic or Dynamic Vision Sensor Data.

Science.gov (United States)

Stromatias, Evangelos; Soto, Miguel; Serrano-Gotarredona, Teresa; Linares-Barranco, Bernabé

2017-01-01

This paper introduces a novel methodology for training an event-driven classifier within a Spiking Neural Network (SNN) System capable of yielding good classification results when using both synthetic input data and real data captured from Dynamic Vision Sensor (DVS) chips. The proposed supervised method uses the spiking activity provided by an arbitrary topology of prior SNN layers to build histograms and train the classifier in the frame domain using the stochastic gradient descent algorithm. In addition, this approach can cope with leaky integrate-and-fire neuron models within the SNN, a desirable feature for real-world SNN applications, where neural activation must fade away after some time in the absence of inputs. Consequently, this way of building histograms captures the dynamics of spikes immediately before the classifier. We tested our method on the MNIST data set using different synthetic encodings and real DVS sensory data sets such as N-MNIST, MNIST-DVS, and Poker-DVS using the same network topology and feature maps. We demonstrate the effectiveness of our approach by achieving the highest classification accuracy reported on the N-MNIST (97.77%) and Poker-DVS (100%) real DVS data sets to date with a spiking convolutional network. Moreover, by using the proposed method we were able to retrain the output layer of a previously reported spiking neural network and increase its performance by 2%, suggesting that the proposed classifier can be used as the output layer in works where features are extracted using unsupervised spike-based learning methods. In addition, we also analyze SNN performance figures such as total event activity and network latencies, which are relevant for eventual hardware implementations. In summary, the paper aggregates unsupervised-trained SNNs with a supervised-trained SNN classifier, combining and applying them to heterogeneous sets of benchmarks, both synthetic and from real DVS chips.

[Regional ecological planning and ecological network construction: a case study of "Ji Triangle" Region].

Science.gov (United States)

Li, Bo; Han, Zeng-Lin; Tong, Lian-Jun

2009-05-01

By the methods of in situ investigation and regional ecological planning, the present ecological environment, ecosystem vulnerability, and ecological environment sensitivity in "Ji Triangle" Region were analyzed, and the ecological network of the study area was constructed. According to the ecological resources abundance degree, ecological recovery, farmland windbreak system, environmental carrying capacity, forestry foundation, and ecosystem integrity, the study area was classified into three regional ecological function ecosystems, i. e., east low hill ecosystem, middle plain ecosystem, and west plain wetland ecosystem. On the basis of marking regional ecological nodes, the regional ecological corridor (Haerbin-Dalian regional axis, Changchun-Jilin, Changchun-Songyuan, Jilin-Songyuan, Jilin-Siping, and Songyuan-Siping transportation corridor) and regional ecological network (one ring, three links, and three belts) were constructed. Taking the requests of regional ecological security into consideration, the ecological environment security system of "Ji Triangle" Region, including regional ecological conservation district, regional ecological restored district, and regional ecological management district, was built.

A new algorithm to construct phylogenetic networks from trees.

Science.gov (United States)

Wang, J

2014-03-06

Developing appropriate methods for constructing phylogenetic networks from tree sets is an important problem, and much research is currently being undertaken in this area. BIMLR is an algorithm that constructs phylogenetic networks from tree sets. The algorithm can construct a much simpler network than other available methods. Here, we introduce an improved version of the BIMLR algorithm, QuickCass. QuickCass changes the selection strategy of the labels of leaves below the reticulate nodes, i.e., the nodes with an indegree of at least 2 in BIMLR. We show that QuickCass can construct simpler phylogenetic networks than BIMLR. Furthermore, we show that QuickCass is a polynomial-time algorithm when the output network that is constructed by QuickCass is binary.

Drawing Inspiration from Human Brain Networks: Construction of Interconnected Virtual Networks.

Science.gov (United States)

Murakami, Masaya; Kominami, Daichi; Leibnitz, Kenji; Murata, Masayuki

2018-04-08

Virtualization of wireless sensor networks (WSN) is widely considered as a foundational block of edge/fog computing, which is a key technology that can help realize next-generation Internet of things (IoT) networks. In such scenarios, multiple IoT devices and service modules will be virtually deployed and interconnected over the Internet. Moreover, application services are expected to be more sophisticated and complex, thereby increasing the number of modifications required for the construction of network topologies. Therefore, it is imperative to establish a method for constructing a virtualized WSN (VWSN) topology that achieves low latency on information transmission and high resilience against network failures, while keeping the topological construction cost low. In this study, we draw inspiration from inter-modular connectivity in human brain networks, which achieves high performance when dealing with large-scale networks composed of a large number of modules (i.e., regions) and nodes (i.e., neurons). We propose a method for assigning inter-modular links based on a connectivity model observed in the cerebral cortex of the brain, known as the exponential distance rule (EDR) model. We then choose endpoint nodes of these links by controlling inter-modular assortativity, which characterizes the topological connectivity of brain networks. We test our proposed methods using simulation experiments. The results show that the proposed method based on the EDR model can construct a VWSN topology with an optimal combination of communication efficiency, robustness, and construction cost. Regarding the selection of endpoint nodes for the inter-modular links, the results also show that high assortativity enhances the robustness and communication efficiency because of the existence of inter-modular links of two high-degree nodes.

Drawing Inspiration from Human Brain Networks: Construction of Interconnected Virtual Networks

Directory of Open Access Journals (Sweden)

Masaya Murakami

2018-04-01

Full Text Available Virtualization of wireless sensor networks (WSN is widely considered as a foundational block of edge/fog computing, which is a key technology that can help realize next-generation Internet of things (IoT networks. In such scenarios, multiple IoT devices and service modules will be virtually deployed and interconnected over the Internet. Moreover, application services are expected to be more sophisticated and complex, thereby increasing the number of modifications required for the construction of network topologies. Therefore, it is imperative to establish a method for constructing a virtualized WSN (VWSN topology that achieves low latency on information transmission and high resilience against network failures, while keeping the topological construction cost low. In this study, we draw inspiration from inter-modular connectivity in human brain networks, which achieves high performance when dealing with large-scale networks composed of a large number of modules (i.e., regions and nodes (i.e., neurons. We propose a method for assigning inter-modular links based on a connectivity model observed in the cerebral cortex of the brain, known as the exponential distance rule (EDR model. We then choose endpoint nodes of these links by controlling inter-modular assortativity, which characterizes the topological connectivity of brain networks. We test our proposed methods using simulation experiments. The results show that the proposed method based on the EDR model can construct a VWSN topology with an optimal combination of communication efficiency, robustness, and construction cost. Regarding the selection of endpoint nodes for the inter-modular links, the results also show that high assortativity enhances the robustness and communication efficiency because of the existence of inter-modular links of two high-degree nodes.

Classifying dysmorphic syndromes by using artificial neural network based hierarchical decision tree.

Science.gov (United States)

Özdemir, Merve Erkınay; Telatar, Ziya; Eroğul, Osman; Tunca, Yusuf

2018-05-01

Dysmorphic syndromes have different facial malformations. These malformations are significant to an early diagnosis of dysmorphic syndromes and contain distinctive information for face recognition. In this study we define the certain features of each syndrome by considering facial malformations and classify Fragile X, Hurler, Prader Willi, Down, Wolf Hirschhorn syndromes and healthy groups automatically. The reference points are marked on the face images and ratios between the points' distances are taken into consideration as features. We suggest a neural network based hierarchical decision tree structure in order to classify the syndrome types. We also implement k-nearest neighbor (k-NN) and artificial neural network (ANN) classifiers to compare classification accuracy with our hierarchical decision tree. The classification accuracy is 50, 73 and 86.7% with k-NN, ANN and hierarchical decision tree methods, respectively. Then, the same images are shown to a clinical expert who achieve a recognition rate of 46.7%. We develop an efficient system to recognize different syndrome types automatically in a simple, non-invasive imaging data, which is independent from the patient's age, sex and race at high accuracy. The promising results indicate that our method can be used for pre-diagnosis of the dysmorphic syndromes by clinical experts.

High voltage power network construction

CERN Document Server

Harker, Keith

2018-01-01

This book examines the key requirements, considerations, complexities and constraints relevant to the task of high voltage power network construction, from design, finance, contracts and project management to installation and commissioning, with the aim of providing an overview of the holistic end to end construction task in a single volume.

CONSTRUCTION COST PREDICTION USING NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Smita K Magdum

2017-10-01

Full Text Available Construction cost prediction is important for construction firms to compete and grow in the industry. Accurate construction cost prediction in the early stage of project is important for project feasibility studies and successful completion. There are many factors that affect the cost prediction. This paper presents construction cost prediction as multiple regression model with cost of six materials as independent variables. The objective of this paper is to develop neural networks and multilayer perceptron based model for construction cost prediction. Different models of NN and MLP are developed with varying hidden layer size and hidden nodes. Four artificial neural network models and twelve multilayer perceptron models are compared. MLP and NN give better results than statistical regression method. As compared to NN, MLP works better on training dataset but fails on testing dataset. Five activation functions are tested to identify suitable function for the problem. ‘elu' transfer function gives better results than other transfer function.

A Neural Network-Based Interval Pattern Matcher

Directory of Open Access Journals (Sweden)

Jing Lu

2015-07-01

Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.

On library information resources construction under network environment

International Nuclear Information System (INIS)

Guo Huifang; Wang Jingjing

2014-01-01

Information resources construction is the primary task and critical measures for libraries. In the 2lst century, the knowledge economy era, with the continuous development of computer network technology, information resources have become an important part of libraries which have been a significant indicator of its capacity construction. The development of socialized Information, digitalization and internalization has put forward new requirements for library information resources construction. This paper describes the impact of network environment on construction of library information resources and proposes the measures of library information resources. (authors)

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

Directory of Open Access Journals (Sweden)

Yi Sun

2017-12-01

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

Classifying images using restricted Boltzmann machines and convolutional neural networks

Science.gov (United States)

Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

2017-07-01

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

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

Science.gov (United States)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

Classifying Sources Influencing Indoor Air Quality (IAQ Using Artificial Neural Network (ANN

Directory of Open Access Journals (Sweden)

Shaharil Mad Saad

2015-05-01

Full Text Available Monitoring indoor air quality (IAQ is deemed important nowadays. A sophisticated IAQ monitoring system which could classify the source influencing the IAQ is definitely going to be very helpful to the users. Therefore, in this paper, an IAQ monitoring system has been proposed with a newly added feature which enables the system to identify the sources influencing the level of IAQ. In order to achieve this, the data collected has been trained with artificial neural network or ANN—a proven method for pattern recognition. Basically, the proposed system consists of sensor module cloud (SMC, base station and service-oriented client. The SMC contain collections of sensor modules that measure the air quality data and transmit the captured data to base station through wireless network. The IAQ monitoring system is also equipped with IAQ Index and thermal comfort index which could tell the users about the room’s conditions. The results showed that the system is able to measure the level of air quality and successfully classify the sources influencing IAQ in various environments like ambient air, chemical presence, fragrance presence, foods and beverages and human activity.

A Neural Network Classifier Model for Forecasting Safety Behavior at Workplaces

Directory of Open Access Journals (Sweden)

Fakhradin Ghasemi

2017-07-01

Full Text Available The construction industry is notorious for having an unacceptable rate of fatal accidents. Unsafe behavior has been recognized as the main cause of most accidents occurring at workplaces, particularly construction sites. Having a predictive model of safety behavior can be helpful in preventing construction accidents. The aim of the present study was to build a predictive model of unsafe behavior using the Artificial Neural Network approach. A brief literature review was conducted on factors affecting safe behavior at workplaces and nine factors were selected to be included in the study. Data were gathered using a validated questionnaire from several construction sites. Multilayer perceptron approach was utilized for constructing the desired neural network. Several models with various architectures were tested to find the best one. Sensitivity analysis was conducted to find the most influential factors. The model with one hidden layer containing fourteen hidden neurons demonstrated the best performance (Sum of Squared Errors=6.73. The error rate of the model was approximately 21 percent. The results of sensitivity analysis showed that safety attitude, safety knowledge, supportive environment, and management commitment had the highest effects on safety behavior, while the effects from resource allocation and perceived work pressure were identified to be lower than those of others. The complex nature of human behavior at workplaces and the presence of many influential factors make it difficult to achieve a model with perfect performance.

A novel end-to-end classifier using domain transferred deep convolutional neural networks for biomedical images.

Science.gov (United States)

Pang, Shuchao; Yu, Zhezhou; Orgun, Mehmet A

2017-03-01

Highly accurate classification of biomedical images is an essential task in the clinical diagnosis of numerous medical diseases identified from those images. Traditional image classification methods combined with hand-crafted image feature descriptors and various classifiers are not able to effectively improve the accuracy rate and meet the high requirements of classification of biomedical images. The same also holds true for artificial neural network models directly trained with limited biomedical images used as training data or directly used as a black box to extract the deep features based on another distant dataset. In this study, we propose a highly reliable and accurate end-to-end classifier for all kinds of biomedical images via deep learning and transfer learning. We first apply domain transferred deep convolutional neural network for building a deep model; and then develop an overall deep learning architecture based on the raw pixels of original biomedical images using supervised training. In our model, we do not need the manual design of the feature space, seek an effective feature vector classifier or segment specific detection object and image patches, which are the main technological difficulties in the adoption of traditional image classification methods. Moreover, we do not need to be concerned with whether there are large training sets of annotated biomedical images, affordable parallel computing resources featuring GPUs or long times to wait for training a perfect deep model, which are the main problems to train deep neural networks for biomedical image classification as observed in recent works. With the utilization of a simple data augmentation method and fast convergence speed, our algorithm can achieve the best accuracy rate and outstanding classification ability for biomedical images. We have evaluated our classifier on several well-known public biomedical datasets and compared it with several state-of-the-art approaches. We propose a robust

ELHnet: a convolutional neural network for classifying cochlear endolymphatic hydrops imaged with optical coherence tomography.

Science.gov (United States)

Liu, George S; Zhu, Michael H; Kim, Jinkyung; Raphael, Patrick; Applegate, Brian E; Oghalai, John S

2017-10-01

Detection of endolymphatic hydrops is important for diagnosing Meniere's disease, and can be performed non-invasively using optical coherence tomography (OCT) in animal models as well as potentially in the clinic. Here, we developed ELHnet, a convolutional neural network to classify endolymphatic hydrops in a mouse model using learned features from OCT images of mice cochleae. We trained ELHnet on 2159 training and validation images from 17 mice, using only the image pixels and observer-determined labels of endolymphatic hydrops as the inputs. We tested ELHnet on 37 images from 37 mice that were previously not used, and found that the neural network correctly classified 34 of the 37 mice. This demonstrates an improvement in performance from previous work on computer-aided classification of endolymphatic hydrops. To the best of our knowledge, this is the first deep CNN designed for endolymphatic hydrops classification.

From gesture to sign language: conventionalization of classifier constructions by adult hearing learners of British Sign Language.

Science.gov (United States)

Marshall, Chloë R; Morgan, Gary

2015-01-01

There has long been interest in why languages are shaped the way they are, and in the relationship between sign language and gesture. In sign languages, entity classifiers are handshapes that encode how objects move, how they are located relative to one another, and how multiple objects of the same type are distributed in space. Previous studies have shown that hearing adults who are asked to use only manual gestures to describe how objects move in space will use gestures that bear some similarities to classifiers. We investigated how accurately hearing adults, who had been learning British Sign Language (BSL) for 1-3 years, produce and comprehend classifiers in (static) locative and distributive constructions. In a production task, learners of BSL knew that they could use their hands to represent objects, but they had difficulty choosing the same, conventionalized, handshapes as native signers. They were, however, highly accurate at encoding location and orientation information. Learners therefore show the same pattern found in sign-naïve gesturers. In contrast, handshape, orientation, and location were comprehended with equal (high) accuracy, and testing a group of sign-naïve adults showed that they too were able to understand classifiers with higher than chance accuracy. We conclude that adult learners of BSL bring their visuo-spatial knowledge and gestural abilities to the tasks of understanding and producing constructions that contain entity classifiers. We speculate that investigating the time course of adult sign language acquisition might shed light on how gesture became (and, indeed, becomes) conventionalized during the genesis of sign languages. Copyright © 2014 Cognitive Science Society, Inc.

Neural network construction via back-propagation

International Nuclear Information System (INIS)

Burwick, T.T.

1994-06-01

A method is presented that combines back-propagation with multi-layer neural network construction. Back-propagation is used not only to adjust the weights but also the signal functions. Going from one network to an equivalent one that has additional linear units, the non-linearity of these units and thus their effective presence is then introduced via back-propagation (weight-splitting). The back-propagated error causes the network to include new units in order to minimize the error function. We also show how this formalism allows to escape local minima

A Critical Evaluation of Network and Pathway-Based Classifiers for Outcome Prediction in Breast Cancer

NARCIS (Netherlands)

C. Staiger (Christine); S. Cadot; R Kooter; M. Dittrich (Marcus); T. Müller (Tobias); G.W. Klau (Gunnar); L.F.A. Wessels (Lodewyk)

2012-01-01

htmlabstractRecently, several classifiers that combine primary tumor data, like gene expression data, and secondary data sources, such as protein-protein interaction networks, have been proposed for predicting outcome in breast cancer. In these approaches, new composite features are typically

Moving image compression and generalization capability of constructive neural networks

Science.gov (United States)

Ma, Liying; Khorasani, Khashayar

2001-03-01

To date numerous techniques have been proposed to compress digital images to ease their storage and transmission over communication channels. Recently, a number of image compression algorithms using Neural Networks NNs have been developed. Particularly, several constructive feed-forward neural networks FNNs have been proposed by researchers for image compression, and promising results have been reported. At the previous SPIE AeroSense conference 2000, we proposed to use a constructive One-Hidden-Layer Feedforward Neural Network OHL-FNN for compressing digital images. In this paper, we first investigate the generalization capability of the proposed OHL-FNN in the presence of additive noise for network training and/ or generalization. Extensive experimental results for different scenarios are presented. It is revealed that the constructive OHL-FNN is not as robust to additive noise in input image as expected. Next, the constructive OHL-FNN is applied to moving images, video sequences. The first, or other specified frame in a moving image sequence is used to train the network. The remaining moving images that follow are then generalized/compressed by this trained network. Three types of correlation-like criteria measuring the similarity of any two images are introduced. The relationship between the generalization capability of the constructed net and the similarity of images is investigated in some detail. It is shown that the constructive OHL-FNN is promising even for changing images such as those extracted from a football game.

Exemplar-based optical neural net classifier for color pattern recognition

Science.gov (United States)

Yu, Francis T. S.; Uang, Chii-Maw; Yang, Xiangyang

1992-10-01

We present a color exemplar-based neural network that can be used as an optimum image classifier or an associative memory. Color decomposition and composition technique is used for constructing the polychromatic interconnection weight matrix (IWM). The Hamming net algorithm is modified to relax the dynamic range requirement of the spatial light modulator and to reduce the number of iteration cycles in the winner-take-all layer. Computer simulation results demonstrated the feasibility of this approach

Classifying magnetic resonance image modalities with convolutional neural networks

Science.gov (United States)

Remedios, Samuel; Pham, Dzung L.; Butman, John A.; Roy, Snehashis

2018-02-01

Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)- based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs postcontrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.

Influence of the time scale on the construction of financial networks.

Science.gov (United States)

Emmert-Streib, Frank; Dehmer, Matthias

2010-09-30

In this paper we investigate the definition and formation of financial networks. Specifically, we study the influence of the time scale on their construction. For our analysis we use correlation-based networks obtained from the daily closing prices of stock market data. More precisely, we use the stocks that currently comprise the Dow Jones Industrial Average (DJIA) and estimate financial networks where nodes correspond to stocks and edges correspond to none vanishing correlation coefficients. That means only if a correlation coefficient is statistically significant different from zero, we include an edge in the network. This construction procedure results in unweighted, undirected networks. By separating the time series of stock prices in non-overlapping intervals, we obtain one network per interval. The length of these intervals corresponds to the time scale of the data, whose influence on the construction of the networks will be studied in this paper. Numerical analysis of four different measures in dependence on the time scale for the construction of networks allows us to gain insights about the intrinsic time scale of the stock market with respect to a meaningful graph-theoretical analysis.

Constructing Battery-Aware Virtual Backbones in Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Yang Yuanyuan

2007-01-01

Full Text Available A critical issue in battery-powered sensor networks is to construct energy efficient virtual backbones for network routing. Recent study in battery technology reveals that batteries tend to discharge more power than needed and reimburse the over-discharged power if they are recovered. In this paper we first provide a mathematical battery model suitable for implementation in sensor networks. We then introduce the concept of battery-aware connected dominating set (BACDS and show that in general the minimum BACDS (MBACDS can achieve longer lifetime than the previous backbone structures. Then we show that finding a MBACDS is NP-hard and give a distributed approximation algorithm to construct the BACDS. The resulting BACDS constructed by our algorithm is at most opt size, where is the maximum node degree and opt is the size of an optimal BACDS. Simulation results show that the BACDS can save a significant amount of energy and achieve up to longer network lifetime than previous schemes.

Fingerprint prediction using classifier ensembles

CSIR Research Space (South Africa)

Molale, P

2011-11-01

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

Constructing level-2 phylogenetic networks from triplets

OpenAIRE

Iersel, Leo; Keijsper, J.C.M.; Kelk, Steven; Stougie, Leen; Hagen, F.; Boekhout, T.; Vingron, M.; Wong, L.

2009-01-01

htmlabstractJansson and Sung showed that, given a dense set of input triplets T (representing hypotheses about the local evolutionary relationships of triplets of taxa), it is possible to determine in polynomial time whether there exists a level-1 network consistent with T, and if so to construct such a network (Inferring a Level-1 Phylogenetic Network from a Dense Set of Rooted Triplets, Theoretical Computer Science, 363, pp. 60-68 (2006)). Here we extend this work by showing that this probl...

Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

International Nuclear Information System (INIS)

Li Qiang; Doi Kunio

2006-01-01

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an 'optimal' method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect

Digging into construction: social networks and their potential impact on knowledge transfer.

Science.gov (United States)

Carlan, N A; Kramer, D M; Bigelow, P; Wells, R; Garritano, E; Vi, P

2012-01-01

A six-year study is exploring the most effective ways to disseminate ideas to reduce musculoskeletal disorders (MSDs) in the construction sector. The sector was targeted because MSDs account for 35% of all lost time injuries. This paper reports on the organization of the construction sector, and maps potential pathways of communication, including social networks, to set the stage for future dissemination. The managers, health and safety specialists, union health and safety representatives, and 28 workers from small, medium and large construction companies participated. Over a three-year period, data were collected from 47 qualitative interviews. Questions were guided by the PARIHS (Promoting Action on Research Implementation in Health Services) knowledge-transfer conceptual framework and adapted for the construction sector. The construction sector is a complex and dynamic sector, with non-linear reporting relationships, and divided and diluted responsibilities. Four networks were identified that can potentially facilitate the dissemination of new knowledge: worksite-project networks; union networks; apprenticeship program networks; and networks established by the Construction Safety Association/Infrastructure Health and Safety Association. Flexible and multi-directional lines of communication must be used in this complex environment. This has implications for the future choice of knowledge transfer strategies.

Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis

Directory of Open Access Journals (Sweden)

Bach Phi Duong

2018-04-01

Full Text Available The simultaneous occurrence of various types of defects in bearings makes their diagnosis more challenging owing to the resultant complexity of the constituent parts of the acoustic emission (AE signals. To address this issue, a new approach is proposed in this paper for the detection of multiple combined faults in bearings. The proposed methodology uses a deep neural network (DNN architecture to effectively diagnose the combined defects. The DNN structure is based on the stacked denoising autoencoder non-mutually exclusive classifier (NMEC method for combined modes. The NMEC-DNN is trained using data for a single fault and it classifies both single faults and multiple combined faults. The results of experiments conducted on AE data collected through an experimental test-bed demonstrate that the DNN achieves good classification performance with a maximum accuracy of 95%. The proposed method is compared with a multi-class classifier based on support vector machines (SVMs. The NMEC-DNN yields better diagnostic performance in comparison to the multi-class classifier based on SVM. The NMEC-DNN reduces the number of necessary data collections and improves the bearing fault diagnosis performance.

Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis.

Science.gov (United States)

Duong, Bach Phi; Kim, Jong-Myon

2018-04-07

The simultaneous occurrence of various types of defects in bearings makes their diagnosis more challenging owing to the resultant complexity of the constituent parts of the acoustic emission (AE) signals. To address this issue, a new approach is proposed in this paper for the detection of multiple combined faults in bearings. The proposed methodology uses a deep neural network (DNN) architecture to effectively diagnose the combined defects. The DNN structure is based on the stacked denoising autoencoder non-mutually exclusive classifier (NMEC) method for combined modes. The NMEC-DNN is trained using data for a single fault and it classifies both single faults and multiple combined faults. The results of experiments conducted on AE data collected through an experimental test-bed demonstrate that the DNN achieves good classification performance with a maximum accuracy of 95%. The proposed method is compared with a multi-class classifier based on support vector machines (SVMs). The NMEC-DNN yields better diagnostic performance in comparison to the multi-class classifier based on SVM. The NMEC-DNN reduces the number of necessary data collections and improves the bearing fault diagnosis performance.

Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis

Science.gov (United States)

Kim, Jong-Myon

2018-01-01

The simultaneous occurrence of various types of defects in bearings makes their diagnosis more challenging owing to the resultant complexity of the constituent parts of the acoustic emission (AE) signals. To address this issue, a new approach is proposed in this paper for the detection of multiple combined faults in bearings. The proposed methodology uses a deep neural network (DNN) architecture to effectively diagnose the combined defects. The DNN structure is based on the stacked denoising autoencoder non-mutually exclusive classifier (NMEC) method for combined modes. The NMEC-DNN is trained using data for a single fault and it classifies both single faults and multiple combined faults. The results of experiments conducted on AE data collected through an experimental test-bed demonstrate that the DNN achieves good classification performance with a maximum accuracy of 95%. The proposed method is compared with a multi-class classifier based on support vector machines (SVMs). The NMEC-DNN yields better diagnostic performance in comparison to the multi-class classifier based on SVM. The NMEC-DNN reduces the number of necessary data collections and improves the bearing fault diagnosis performance. PMID:29642466

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

Science.gov (United States)

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

2018-01-01

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

Construction of the main building network environment in IHEP

International Nuclear Information System (INIS)

Wang Yanming

2004-01-01

Based on the new network structure at IHEP, we re-constructed the network in Main Building at IHEP in order to realize the goal of steadily supporting the network application. We chose high performance and administrable switches and configured them properly. This improved that the network security, management ability. So the network at Main Building became more safe, steady, reliable and high-efficient. (authors)

Project plan for PACS networking construction and cabling

International Nuclear Information System (INIS)

Luo Min; Wang Xiaolin; Luo Song; Lei Wenyong; Wang Xuejian; Wen Hongyue; Wu Hongxing

2002-01-01

Objective: To meet the networking requirement of the heave data flow, load balance, and potential networking storm during expanding the application of PACS. Methods: Intel Net Structure 480T Giga Switch was used as main switch and connected to each building by optical channel at 1 Giga speed to archive 100 MB/s to each port. At the same time, the in dependence of the original networking construction was physically kept. The layer 3 and 4 switchers was used as load balance to reduce the heavy load of the networking, and all the cabling for PACS used the super CAT5 along with the Intel Net Structure 1520 to prepare for the potential networking storm. Results: An advanced intranet was set up to fully meet the high standard requirement of PACS. The good foundation for upgrading the whole networking system to 1 Giga application was built for realized share and transmission of image, information, and patient data within the hospital. The base was established for the standardized management of the hospital. Conclusion: Good planning is the 1 st step in setting up PACS and the equipment are the platform to run PACS and all kinds of HIS. The networking construction is the foundation of e-hospitals

Classifying features in CT imagery: accuracy for some single- and multiple-species classifiers

Science.gov (United States)

Daniel L. Schmoldt; Jing He; A. Lynn Abbott

1998-01-01

Our current approach to automatically label features in CT images of hardwood logs classifies each pixel of an image individually. These feature classifiers use a back-propagation artificial neural network (ANN) and feature vectors that include a small, local neighborhood of pixels and the distance of the target pixel to the center of the log. Initially, this type of...

Composite Classifiers for Automatic Target Recognition

National Research Council Canada - National Science Library

Wang, Lin-Cheng

1998-01-01

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

Constructing Battery-Aware Virtual Backbones in Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Chi Ma

2007-05-01

Full Text Available A critical issue in battery-powered sensor networks is to construct energy efficient virtual backbones for network routing. Recent study in battery technology reveals that batteries tend to discharge more power than needed and reimburse the over-discharged power if they are recovered. In this paper we first provide a mathematical battery model suitable for implementation in sensor networks. We then introduce the concept of battery-aware connected dominating set (BACDS and show that in general the minimum BACDS (MBACDS can achieve longer lifetime than the previous backbone structures. Then we show that finding a MBACDS is NP-hard and give a distributed approximation algorithm to construct the BACDS. The resulting BACDS constructed by our algorithm is at most (8+Δopt size, where Δ is the maximum node degree and opt is the size of an optimal BACDS. Simulation results show that the BACDS can save a significant amount of energy and achieve up to 30% longer network lifetime than previous schemes.

Pap-smear Classification Using Efficient Second Order Neural Network Training Algorithms

DEFF Research Database (Denmark)

Ampazis, Nikolaos; Dounias, George; Jantzen, Jan

2004-01-01

In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier. The alg......In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier...

Hybrid classifiers methods of data, knowledge, and classifier combination

CERN Document Server

Wozniak, Michal

2014-01-01

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

Tailoring silver nanoparticle construction using dendrimer templated silica networks

International Nuclear Information System (INIS)

Liu Xiaojun; Kakkar, Ashok

2008-01-01

We have examined the role of the internal environment of dendrimer templated silica networks in tailoring the construction of silver nanoparticle assemblies. Silica networks from which 3,5-dihydroxybenzyl alcohol based dendrimer templates have been completely removed, slowly wet with an aqueous solution of silver acetate. The latter then reacts with internal silica silanol groups, leading to chemisorption of silver ions, followed by the growth of silver oxide nanoparticles. Silica network constructed using generation 4 dendrimer contains residual dendrimer template, and mixes with aqueous silver acetate solution easily. Upon chemisorption, silver ions get photolytically reduced to silver metal under a stabilizing dendrimer environment, leading to the formation of silver metal nanoparticles

Convolutional Neural Networks with Batch Normalization for Classifying Hi-hat, Snare, and Bass Percussion Sound Samples

DEFF Research Database (Denmark)

Gajhede, Nicolai; Beck, Oliver; Purwins, Hendrik

2016-01-01

After having revolutionized image and speech processing, convolu- tional neural networks (CNN) are now starting to become more and more successful in music information retrieval as well. We compare four CNN types for classifying a dataset of more than 3000 acoustic and synthesized samples...

Development of a skateboarding trick classifier using accelerometry and machine learning

Directory of Open Access Journals (Sweden)

Nicholas Kluge Corrêa

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

Use of artificial neural networks and geographic objects for classifying remote sensing imagery

Directory of Open Access Journals (Sweden)

Pedro Resende Silva

2014-06-01

Full Text Available The aim of this study was to develop a methodology for mapping land use and land cover in the northern region of Minas Gerais state, where, in addition to agricultural land, the landscape is dominated by native cerrado, deciduous forests, and extensive areas of vereda. Using forest inventory data, as well as RapidEye, Landsat TM and MODIS imagery, three specific objectives were defined: 1 to test use of image segmentation techniques for an object-based classification encompassing spectral, spatial and temporal information, 2 to test use of high spatial resolution RapidEye imagery combined with Landsat TM time series imagery for capturing the effects of seasonality, and 3 to classify data using Artificial Neural Networks. Using MODIS time series and forest inventory data, time signatures were extracted from the dominant vegetation formations, enabling selection of the best periods of the year to be represented in the classification process. Objects created with the segmentation of RapidEye images, along with the Landsat TM time series images, were classified by ten different Multilayer Perceptron network architectures. Results showed that the methodology in question meets both the purposes of this study and the characteristics of the local plant life. With excellent accuracy values for native classes, the study showed the importance of a well-structured database for classification and the importance of suitable image segmentation to meet specific purposes.

General and Local: Averaged k-Dependence Bayesian Classifiers

Directory of Open Access Journals (Sweden)

Limin Wang

2015-06-01

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

Noticing climate change in electricity network design and construction

International Nuclear Information System (INIS)

Syri, S.; Martikeinen, A.; Lehtonen, M.

2007-01-01

The climate change is widely known to cause remarkable effects to electricity network systems on the whole. Some of the changes are good but the most of the changes cause disadvantages to electricity network. Consequence of climate change, blackouts can be long-standing which affect remarkable society and economic life. Most of electricity networks are coming to a renovation phase and the solutions, that are being made nowadays, affect still after decades. Taking account of climate change, now when networks are being developed and planned, it is possible to avoid possible large repair operation and increase reliability of distribution in the future. The aim of this project is to clarify how climate change should be noticed in planning and construction processes. According to the results of this project electricity network companies can be prepared for climate change by developing planning processes and network cost effectively. Also construction processes are being developed but emphasis is on planning process. The results and developed knowledge of VTT research project 'Impacts of climate change on electricity network business' are exploited in this project. In addition, impacts of climate change on cables and transformers are analyzed in collaboration with TKK in the project. (orig.)

Comparison of artificial intelligence classifiers for SIP attack data

Science.gov (United States)

Safarik, Jakub; Slachta, Jiri

2016-05-01

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

BIMLR: a method for constructing rooted phylogenetic networks from rooted phylogenetic trees.

Science.gov (United States)

Wang, Juan; Guo, Maozu; Xing, Linlin; Che, Kai; Liu, Xiaoyan; Wang, Chunyu

2013-09-15

Rooted phylogenetic trees constructed from different datasets (e.g. from different genes) are often conflicting with one another, i.e. they cannot be integrated into a single phylogenetic tree. Phylogenetic networks have become an important tool in molecular evolution, and rooted phylogenetic networks are able to represent conflicting rooted phylogenetic trees. Hence, the development of appropriate methods to compute rooted phylogenetic networks from rooted phylogenetic trees has attracted considerable research interest of late. The CASS algorithm proposed by van Iersel et al. is able to construct much simpler networks than other available methods, but it is extremely slow, and the networks it constructs are dependent on the order of the input data. Here, we introduce an improved CASS algorithm, BIMLR. We show that BIMLR is faster than CASS and less dependent on the input data order. Moreover, BIMLR is able to construct much simpler networks than almost all other methods. BIMLR is available at http://nclab.hit.edu.cn/wangjuan/BIMLR/. © 2013 Elsevier B.V. All rights reserved.

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

Science.gov (United States)

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

2018-05-10

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

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

Directory of Open Access Journals (Sweden)

Hafza A. Mahmood

2018-04-01

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

An ensemble classifier to predict track geometry degradation

International Nuclear Information System (INIS)

Cárdenas-Gallo, Iván; Sarmiento, Carlos A.; Morales, Gilberto A.; Bolivar, Manuel A.; Akhavan-Tabatabaei, Raha

2017-01-01

Railway operations are inherently complex and source of several problems. In particular, track geometry defects are one of the leading causes of train accidents in the United States. This paper presents a solution approach which entails the construction of an ensemble classifier to forecast the degradation of track geometry. Our classifier is constructed by solving the problem from three different perspectives: deterioration, regression and classification. We considered a different model from each perspective and our results show that using an ensemble method improves the predictive performance. - Highlights: • We present an ensemble classifier to forecast the degradation of track geometry. • Our classifier considers three perspectives: deterioration, regression and classification. • We construct and test three models and our results show that using an ensemble method improves the predictive performance.

Signalling network construction for modelling plant defence response.

Directory of Open Access Journals (Sweden)

Dragana Miljkovic

Full Text Available Plant defence signalling response against various pathogens, including viruses, is a complex phenomenon. In resistant interaction a plant cell perceives the pathogen signal, transduces it within the cell and performs a reprogramming of the cell metabolism leading to the pathogen replication arrest. This work focuses on signalling pathways crucial for the plant defence response, i.e., the salicylic acid, jasmonic acid and ethylene signal transduction pathways, in the Arabidopsis thaliana model plant. The initial signalling network topology was constructed manually by defining the representation formalism, encoding the information from public databases and literature, and composing a pathway diagram. The manually constructed network structure consists of 175 components and 387 reactions. In order to complement the network topology with possibly missing relations, a new approach to automated information extraction from biological literature was developed. This approach, named Bio3graph, allows for automated extraction of biological relations from the literature, resulting in a set of (component1, reaction, component2 triplets and composing a graph structure which can be visualised, compared to the manually constructed topology and examined by the experts. Using a plant defence response vocabulary of components and reaction types, Bio3graph was applied to a set of 9,586 relevant full text articles, resulting in 137 newly detected reactions between the components. Finally, the manually constructed topology and the new reactions were merged to form a network structure consisting of 175 components and 524 reactions. The resulting pathway diagram of plant defence signalling represents a valuable source for further computational modelling and interpretation of omics data. The developed Bio3graph approach, implemented as an executable language processing and graph visualisation workflow, is publically available at http://ropot.ijs.si/bio3graph/and can be

Performance Analysis and Optimization for Cognitive Radio Networks with Classified Secondary Users and Impatient Packets

Directory of Open Access Journals (Sweden)

Yuan Zhao

2017-01-01

Full Text Available A cognitive radio network with classified Secondary Users (SUs is considered. There are two types of SU packets, namely, SU1 packets and SU2 packets, in the system. The SU1 packets have higher priority than the SU2 packets. Considering the diversity of the SU packets and the real-time need of the interrupted SU packets, a novel spectrum allocation strategy with classified SUs and impatient packets is proposed. Based on the number of PU packets, SU1 packets, and SU2 packets in the system, by modeling the queue dynamics of the networks users as a three-dimensional discrete-time Markov chain, the transition probability matrix of the Markov chain is given. Then with the steady-state analysis, some important performance measures of the SU2 packets are derived to show the system performance with numerical results. Specially, in order to optimize the system actions of the SU2 packets, the individually optimal strategy and the socially optimal strategy for the SU2 packets are demonstrated. Finally, a pricing mechanism is provided to oblige the SU2 packets to follow the socially optimal strategy.

Detecting Cyber-Attacks on Wireless Mobile Networks Using Multicriterion Fuzzy Classifier with Genetic Attribute Selection

Directory of Open Access Journals (Sweden)

El-Sayed M. El-Alfy

2015-01-01

Full Text Available With the proliferation of wireless and mobile network infrastructures and capabilities, a wide range of exploitable vulnerabilities emerges due to the use of multivendor and multidomain cross-network services for signaling and transport of Internet- and wireless-based data. Consequently, the rates and types of cyber-attacks have grown considerably and current security countermeasures for protecting information and communication may be no longer sufficient. In this paper, we investigate a novel methodology based on multicriterion decision making and fuzzy classification that can provide a viable second-line of defense for mitigating cyber-attacks. The proposed approach has the advantage of dealing with various types and sizes of attributes related to network traffic such as basic packet headers, content, and time. To increase the effectiveness and construct optimal models, we augmented the proposed approach with a genetic attribute selection strategy. This allows efficient and simpler models which can be replicated at various network components to cooperatively detect and report malicious behaviors. Using three datasets covering a variety of network attacks, the performance enhancements due to the proposed approach are manifested in terms of detection errors and model construction times.

Construction of ontology augmented networks for protein complex prediction.

Science.gov (United States)

Zhang, Yijia; Lin, Hongfei; Yang, Zhihao; Wang, Jian

2013-01-01

Protein complexes are of great importance in understanding the principles of cellular organization and function. The increase in available protein-protein interaction data, gene ontology and other resources make it possible to develop computational methods for protein complex prediction. Most existing methods focus mainly on the topological structure of protein-protein interaction networks, and largely ignore the gene ontology annotation information. In this article, we constructed ontology augmented networks with protein-protein interaction data and gene ontology, which effectively unified the topological structure of protein-protein interaction networks and the similarity of gene ontology annotations into unified distance measures. After constructing ontology augmented networks, a novel method (clustering based on ontology augmented networks) was proposed to predict protein complexes, which was capable of taking into account the topological structure of the protein-protein interaction network, as well as the similarity of gene ontology annotations. Our method was applied to two different yeast protein-protein interaction datasets and predicted many well-known complexes. The experimental results showed that (i) ontology augmented networks and the unified distance measure can effectively combine the structure closeness and gene ontology annotation similarity; (ii) our method is valuable in predicting protein complexes and has higher F1 and accuracy compared to other competing methods.

Constructing a Watts-Strogatz network from a small-world network with symmetric degree distribution.

Directory of Open Access Journals (Sweden)

Mozart B C Menezes

Full Text Available Though the small-world phenomenon is widespread in many real networks, it is still challenging to replicate a large network at the full scale for further study on its structure and dynamics when sufficient data are not readily available. We propose a method to construct a Watts-Strogatz network using a sample from a small-world network with symmetric degree distribution. Our method yields an estimated degree distribution which fits closely with that of a Watts-Strogatz network and leads into accurate estimates of network metrics such as clustering coefficient and degree of separation. We observe that the accuracy of our method increases as network size increases.

Constructing a Watts-Strogatz network from a small-world network with symmetric degree distribution.

Science.gov (United States)

Menezes, Mozart B C; Kim, Seokjin; Huang, Rongbing

2017-01-01

Though the small-world phenomenon is widespread in many real networks, it is still challenging to replicate a large network at the full scale for further study on its structure and dynamics when sufficient data are not readily available. We propose a method to construct a Watts-Strogatz network using a sample from a small-world network with symmetric degree distribution. Our method yields an estimated degree distribution which fits closely with that of a Watts-Strogatz network and leads into accurate estimates of network metrics such as clustering coefficient and degree of separation. We observe that the accuracy of our method increases as network size increases.

A computational geometry approach to pore network construction for granular packings

Science.gov (United States)

van der Linden, Joost H.; Sufian, Adnan; Narsilio, Guillermo A.; Russell, Adrian R.; Tordesillas, Antoinette

2018-03-01

Pore network construction provides the ability to characterize and study the pore space of inhomogeneous and geometrically complex granular media in a range of scientific and engineering applications. Various approaches to the construction have been proposed, however subtle implementational details are frequently omitted, open access to source code is limited, and few studies compare multiple algorithms in the context of a specific application. This study presents, in detail, a new pore network construction algorithm, and provides a comprehensive comparison with two other, well-established Delaunay triangulation-based pore network construction methods. Source code is provided to encourage further development. The proposed algorithm avoids the expensive non-linear optimization procedure in existing Delaunay approaches, and is robust in the presence of polydispersity. Algorithms are compared in terms of structural, geometrical and advanced connectivity parameters, focusing on the application of fluid flow characteristics. Sensitivity of the various networks to permeability is assessed through network (Stokes) simulations and finite-element (Navier-Stokes) simulations. Results highlight strong dependencies of pore volume, pore connectivity, throat geometry and fluid conductance on the degree of tetrahedra merging and the specific characteristics of the throats targeted by the merging algorithm. The paper concludes with practical recommendations on the applicability of the three investigated algorithms.

Integrative Analysis of DCE-MRI and Gene Expression Profiles in Construction of a Gene Classifier for Assessment of Hypoxia-Related Risk of Chemoradiotherapy Failure in Cervical Cancer

DEFF Research Database (Denmark)

Fjeldbo, Christina S; Julin, Cathinka H; Lando, Malin

2016-01-01

platforms. The prognostic value was independent of existing clinical markers, regardless of clinical endpoints. CONCLUSIONS: A robust DCE-MRI-associated gene classifier has been constructed that may be used to achieve an early indication of patients' risk of hypoxia-related chemoradiotherapy failure.......PURPOSE: A 31-gene expression signature reflected in dynamic contrast enhanced (DCE)-MR images and correlated with hypoxia-related aggressiveness in cervical cancer was identified in previous work. We here aimed to construct a dichotomous classifier with key signature genes and a predefined...... as an indicator of hypoxia. RESULTS: Classifier candidates were constructed by integrative analysis of ABrix and gene expression profiles in the training cohort and evaluated by a leave-one-out cross-validation approach. On the basis of their ability to separate patients correctly according to hypoxia status, a 6...

Automated Construction of Node Software Using Attributes in a Ubiquitous Sensor Network Environment

Science.gov (United States)

Lee, Woojin; Kim, Juil; Kang, JangMook

2010-01-01

In sensor networks, nodes must often operate in a demanding environment facing restrictions such as restricted computing resources, unreliable wireless communication and power shortages. Such factors make the development of ubiquitous sensor network (USN) applications challenging. To help developers construct a large amount of node software for sensor network applications easily and rapidly, this paper proposes an approach to the automated construction of node software for USN applications using attributes. In the proposed technique, application construction proceeds by first developing a model for the sensor network and then designing node software by setting the values of the predefined attributes. After that, the sensor network model and the design of node software are verified. The final source codes of the node software are automatically generated from the sensor network model. We illustrate the efficiency of the proposed technique by using a gas/light monitoring application through a case study of a Gas and Light Monitoring System based on the Nano-Qplus operating system. We evaluate the technique using a quantitative metric—the memory size of execution code for node software. Using the proposed approach, developers are able to easily construct sensor network applications and rapidly generate a large number of node softwares at a time in a ubiquitous sensor network environment. PMID:22163678

Automated Construction of Node Software Using Attributes in a Ubiquitous Sensor Network Environment

Directory of Open Access Journals (Sweden)

JangMook Kang

2010-09-01

Full Text Available In sensor networks, nodes must often operate in a demanding environment facing restrictions such as restricted computing resources, unreliable wireless communication and power shortages. Such factors make the development of ubiquitous sensor network (USN applications challenging. To help developers construct a large amount of node software for sensor network applications easily and rapidly, this paper proposes an approach to the automated construction of node software for USN applications using attributes. In the proposed technique, application construction proceeds by first developing a model for the sensor network and then designing node software by setting the values of the predefined attributes. After that, the sensor network model and the design of node software are verified. The final source codes of the node software are automatically generated from the sensor network model. We illustrate the efficiency of the proposed technique by using a gas/light monitoring application through a case study of a Gas and Light Monitoring System based on the Nano-Qplus operating system. We evaluate the technique using a quantitative metric—the memory size of execution code for node software. Using the proposed approach, developers are able to easily construct sensor network applications and rapidly generate a large number of node softwares at a time in a ubiquitous sensor network environment.

Automated construction of node software using attributes in a ubiquitous sensor network environment.

Science.gov (United States)

Lee, Woojin; Kim, Juil; Kang, JangMook

2010-01-01

In sensor networks, nodes must often operate in a demanding environment facing restrictions such as restricted computing resources, unreliable wireless communication and power shortages. Such factors make the development of ubiquitous sensor network (USN) applications challenging. To help developers construct a large amount of node software for sensor network applications easily and rapidly, this paper proposes an approach to the automated construction of node software for USN applications using attributes. In the proposed technique, application construction proceeds by first developing a model for the sensor network and then designing node software by setting the values of the predefined attributes. After that, the sensor network model and the design of node software are verified. The final source codes of the node software are automatically generated from the sensor network model. We illustrate the efficiency of the proposed technique by using a gas/light monitoring application through a case study of a Gas and Light Monitoring System based on the Nano-Qplus operating system. We evaluate the technique using a quantitative metric-the memory size of execution code for node software. Using the proposed approach, developers are able to easily construct sensor network applications and rapidly generate a large number of node softwares at a time in a ubiquitous sensor network environment.

Hybrid Neuro-Fuzzy Classifier Based On Nefclass Model

Directory of Open Access Journals (Sweden)

Bogdan Gliwa

2011-01-01

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

[Strategic thinking of the construction of national schistosomiasis laboratory network in China].

Science.gov (United States)

Qin, Zhi-Qiang; Xu, Jing; Feng, Ting; Zhu, Hong-Qing; Li, Shi-Zhu; Xiao, Ning; Zhou, Xiao-Nong

2013-08-01

A schistosomiasis laboratory network and its quality assurance system have been built and will be more and more perfect in China. This paper introduces the present situation of schistosomiasis diagnosis in China and expounds the basic ideas and the progress in the construction of schistosomiasis network platform. Furthermore, the face of schistosomiasis diagnosis network platform construction and operation of the challenge and the future work will be put forward in the latter part of this paper.

Infrared dim moving target tracking via sparsity-based discriminative classifier and convolutional network

Science.gov (United States)

Qian, Kun; Zhou, Huixin; Wang, Bingjian; Song, Shangzhen; Zhao, Dong

2017-11-01

Infrared dim and small target tracking is a great challenging task. The main challenge for target tracking is to account for appearance change of an object, which submerges in the cluttered background. An efficient appearance model that exploits both the global template and local representation over infrared image sequences is constructed for dim moving target tracking. A Sparsity-based Discriminative Classifier (SDC) and a Convolutional Network-based Generative Model (CNGM) are combined with a prior model. In the SDC model, a sparse representation-based algorithm is adopted to calculate the confidence value that assigns more weights to target templates than negative background templates. In the CNGM model, simple cell feature maps are obtained by calculating the convolution between target templates and fixed filters, which are extracted from the target region at the first frame. These maps measure similarities between each filter and local intensity patterns across the target template, therefore encoding its local structural information. Then, all the maps form a representation, preserving the inner geometric layout of a candidate template. Furthermore, the fixed target template set is processed via an efficient prior model. The same operation is applied to candidate templates in the CNGM model. The online update scheme not only accounts for appearance variations but also alleviates the migration problem. At last, collaborative confidence values of particles are utilized to generate particles' importance weights. Experiments on various infrared sequences have validated the tracking capability of the presented algorithm. Experimental results show that this algorithm runs in real-time and provides a higher accuracy than state of the art algorithms.

A computational framework for the automated construction of glycosylation reaction networks.

Science.gov (United States)

Liu, Gang; Neelamegham, Sriram

2014-01-01

Glycosylation is among the most common and complex post-translational modifications identified to date. It proceeds through the catalytic action of multiple enzyme families that include the glycosyltransferases that add monosaccharides to growing glycans, and glycosidases which remove sugar residues to trim glycans. The expression level and specificity of these enzymes, in part, regulate the glycan distribution or glycome of specific cell/tissue systems. Currently, there is no systematic method to describe the enzymes and cellular reaction networks that catalyze glycosylation. To address this limitation, we present a streamlined machine-readable definition for the glycosylating enzymes and additional methodologies to construct and analyze glycosylation reaction networks. In this computational framework, the enzyme class is systematically designed to store detailed specificity data such as enzymatic functional group, linkage and substrate specificity. The new classes and their associated functions enable both single-reaction inference and automated full network reconstruction, when given a list of reactants and/or products along with the enzymes present in the system. In addition, graph theory is used to support functions that map the connectivity between two or more species in a network, and that generate subset models to identify rate-limiting steps regulating glycan biosynthesis. Finally, this framework allows the synthesis of biochemical reaction networks using mass spectrometry (MS) data. The features described above are illustrated using three case studies that examine: i) O-linked glycan biosynthesis during the construction of functional selectin-ligands; ii) automated N-linked glycosylation pathway construction; and iii) the handling and analysis of glycomics based MS data. Overall, the new computational framework enables automated glycosylation network model construction and analysis by integrating knowledge of glycan structure and enzyme biochemistry. All

A computational framework for the automated construction of glycosylation reaction networks.

Directory of Open Access Journals (Sweden)

Gang Liu

Full Text Available Glycosylation is among the most common and complex post-translational modifications identified to date. It proceeds through the catalytic action of multiple enzyme families that include the glycosyltransferases that add monosaccharides to growing glycans, and glycosidases which remove sugar residues to trim glycans. The expression level and specificity of these enzymes, in part, regulate the glycan distribution or glycome of specific cell/tissue systems. Currently, there is no systematic method to describe the enzymes and cellular reaction networks that catalyze glycosylation. To address this limitation, we present a streamlined machine-readable definition for the glycosylating enzymes and additional methodologies to construct and analyze glycosylation reaction networks. In this computational framework, the enzyme class is systematically designed to store detailed specificity data such as enzymatic functional group, linkage and substrate specificity. The new classes and their associated functions enable both single-reaction inference and automated full network reconstruction, when given a list of reactants and/or products along with the enzymes present in the system. In addition, graph theory is used to support functions that map the connectivity between two or more species in a network, and that generate subset models to identify rate-limiting steps regulating glycan biosynthesis. Finally, this framework allows the synthesis of biochemical reaction networks using mass spectrometry (MS data. The features described above are illustrated using three case studies that examine: i O-linked glycan biosynthesis during the construction of functional selectin-ligands; ii automated N-linked glycosylation pathway construction; and iii the handling and analysis of glycomics based MS data. Overall, the new computational framework enables automated glycosylation network model construction and analysis by integrating knowledge of glycan structure and enzyme

Fast Construction of Near Parsimonious Hybridization Networks for Multiple Phylogenetic Trees.

Science.gov (United States)

Mirzaei, Sajad; Wu, Yufeng

2016-01-01

Hybridization networks represent plausible evolutionary histories of species that are affected by reticulate evolutionary processes. An established computational problem on hybridization networks is constructing the most parsimonious hybridization network such that each of the given phylogenetic trees (called gene trees) is "displayed" in the network. There have been several previous approaches, including an exact method and several heuristics, for this NP-hard problem. However, the exact method is only applicable to a limited range of data, and heuristic methods can be less accurate and also slow sometimes. In this paper, we develop a new algorithm for constructing near parsimonious networks for multiple binary gene trees. This method is more efficient for large numbers of gene trees than previous heuristics. This new method also produces more parsimonious results on many simulated datasets as well as a real biological dataset than a previous method. We also show that our method produces topologically more accurate networks for many datasets.

Sensitivity analysis of human brain structural network construction

Directory of Open Access Journals (Sweden)

Kuang Wei

2017-12-01

Full Text Available Network neuroscience leverages diffusion-weighted magnetic resonance imaging and tractography to quantify structural connectivity of the human brain. However, scientists and practitioners lack a clear understanding of the effects of varying tractography parameters on the constructed structural networks. With diffusion images from the Human Connectome Project (HCP, we characterize how structural networks are impacted by the spatial resolution of brain atlases, total number of tractography streamlines, and grey matter dilation with various graph metrics. We demonstrate how injudicious combinations of highly refined brain parcellations and low numbers of streamlines may inadvertently lead to disconnected network models with isolated nodes. Furthermore, we provide solutions to significantly reduce the likelihood of generating disconnected networks. In addition, for different tractography parameters, we investigate the distributions of values taken by various graph metrics across the population of HCP subjects. Analyzing the ranks of individual subjects within the graph metric distributions, we find that the ranks of individuals are affected differently by atlas scale changes. Our work serves as a guideline for researchers to optimize the selection of tractography parameters and illustrates how biological characteristics of the brain derived in network neuroscience studies can be affected by the choice of atlas parcellation schemes. Diffusion tractography has been proven to be a promising noninvasive technique to study the network properties of the human brain. However, how various tractography and network construction parameters affect network properties has not been studied using a large cohort of high-quality data. We utilize data provided by the Human Connectome Project to characterize the changes to network properties induced by varying the brain parcellation atlas scales, the number of reconstructed tractography tracks, and the degree of grey

Construction of functional linkage gene networks by data integration.

Science.gov (United States)

Linghu, Bolan; Franzosa, Eric A; Xia, Yu

2013-01-01

Networks of functional associations between genes have recently been successfully used for gene function and disease-related research. A typical approach for constructing such functional linkage gene networks (FLNs) is based on the integration of diverse high-throughput functional genomics datasets. Data integration is a nontrivial task due to the heterogeneous nature of the different data sources and their variable accuracy and completeness. The presence of correlations between data sources also adds another layer of complexity to the integration process. In this chapter we discuss an approach for constructing a human FLN from data integration and a subsequent application of the FLN to novel disease gene discovery. Similar approaches can be applied to nonhuman species and other discovery tasks.

Classifier fusion for VoIP attacks classification

Science.gov (United States)

Safarik, Jakub; Rezac, Filip

2017-05-01

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

Automating the construction of scene classifiers for content-based video retrieval

NARCIS (Netherlands)

Khan, L.; Israël, Menno; Petrushin, V.A.; van den Broek, Egon; van der Putten, Peter

2004-01-01

This paper introduces a real time automatic scene classifier within content-based video retrieval. In our envisioned approach end users like documentalists, not image processing experts, build classifiers interactively, by simply indicating positive examples of a scene. Classification consists of a

Construction of road network vulnerability evaluation index based on general travel cost

Science.gov (United States)

Leng, Jun-qiang; Zhai, Jing; Li, Qian-wen; Zhao, Lin

2018-03-01

With the development of China's economy and the continuous improvement of her urban road network, the vulnerability of the urban road network has attracted increasing attention. Based on general travel cost, this work constructs the vulnerability evaluation index for the urban road network, and evaluates the vulnerability of the urban road network from the perspective of user generalised travel cost. Firstly, the generalised travel cost model is constructed based on vehicle cost, travel time, and traveller comfort. Then, the network efficiency index is selected as an evaluation index of vulnerability: the network efficiency index is composed of the traffic volume and the generalised travel cost, which are obtained from the equilibrium state of the network. In addition, the research analyses the influence of traffic capacity decrease, road section attribute value, and location of road section, on vulnerability. Finally, the vulnerability index is used to analyse the local area network of Harbin and verify its applicability.

Construction and discussion of the science and technology information network of SWIP

International Nuclear Information System (INIS)

Wang Li; Zhang Yiming

2010-01-01

The digital library needs to be developed with the advancement of digitalisation and network, and the construction of digital information resource is more indispensable. This paper introduces the exploration and the work performed by the Research Office of Science and Technology Information of the Southwestern Institute of Physics with respect to preliminary construction of science and technology (S and T) information network resources and the magnitude alteration of S and T information service platform subsequently and the building of a dynamical network information service mode of its own characteristics. (authors)

Construction of programmable interconnected 3D microfluidic networks

International Nuclear Information System (INIS)

Hunziker, Patrick R; Wolf, Marc P; Wang, Xueya; Zhang, Bei; Marsch, Stephan; Salieb-Beugelaar, Georgette B

2015-01-01

Microfluidic systems represent a key-enabling platform for novel diagnostic tools for use at the point-of-care in clinical contexts as well as for evolving single cell diagnostics. The design of 3D microfluidic systems is an active field of development, but construction of true interconnected 3D microfluidic networks is still a challenge, in particular when the goal is rapid prototyping, accurate design and flexibility. We report a novel approach for the construction of programmable 3D microfluidic systems consisting of modular 3D template casting of interconnected threads to allow user-programmable flow paths and examine its structural characteristics and its modular function. To overcome problems with thread template casting reported in the literature, low-surface-energy polymer threads were used, that allow solvent-free production. Connected circular channels with excellent roundness and low diameter variability were created. Variable channel termination allowed programming a flow path on-the-fly, thus rendering the resulting 3D microfluidic systems highly customizable even after production. Thus, construction of programmable/reprogrammable fully 3D microfluidic systems by template casting of a network of interconnecting threads is feasible, leads to high-quality and highly reproducible, complex 3D geometries. (paper)

Classifiers based on optimal decision rules

KAUST Repository

Amin, Talha

2013-11-25

Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

Classifiers based on optimal decision rules

KAUST Repository

Amin, Talha M.; Chikalov, Igor; Moshkov, Mikhail; Zielosko, Beata

2013-01-01

Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

Optical Neural Network Classifier Architectures

National Research Council Canada - National Science Library

Getbehead, Mark

1998-01-01

We present an adaptive opto-electronic neural network hardware architecture capable of exploiting parallel optics to realize real-time processing and classification of high-dimensional data for Air...

Robust Template Decomposition without Weight Restriction for Cellular Neural Networks Implementing Arbitrary Boolean Functions Using Support Vector Classifiers

Directory of Open Access Journals (Sweden)

Yih-Lon Lin

2013-01-01

Full Text Available If the given Boolean function is linearly separable, a robust uncoupled cellular neural network can be designed as a maximal margin classifier. On the other hand, if the given Boolean function is linearly separable but has a small geometric margin or it is not linearly separable, a popular approach is to find a sequence of robust uncoupled cellular neural networks implementing the given Boolean function. In the past research works using this approach, the control template parameters and thresholds are restricted to assume only a given finite set of integers, and this is certainly unnecessary for the template design. In this study, we try to remove this restriction. Minterm- and maxterm-based decomposition algorithms utilizing the soft margin and maximal margin support vector classifiers are proposed to design a sequence of robust templates implementing an arbitrary Boolean function. Several illustrative examples are simulated to demonstrate the efficiency of the proposed method by comparing our results with those produced by other decomposition methods with restricted weights.

Implications of physical symmetries in adaptive image classifiers

DEFF Research Database (Denmark)

Sams, Thomas; Hansen, Jonas Lundbek

2000-01-01

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

An Efficient Distributed Algorithm for Constructing Spanning Trees in Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Rosana Lachowski

2015-01-01

Full Text Available Monitoring and data collection are the two main functions in wireless sensor networks (WSNs. Collected data are generally transmitted via multihop communication to a special node, called the sink. While in a typical WSN, nodes have a sink node as the final destination for the data traffic, in an ad hoc network, nodes need to communicate with each other. For this reason, routing protocols for ad hoc networks are inefficient for WSNs. Trees, on the other hand, are classic routing structures explicitly or implicitly used in WSNs. In this work, we implement and evaluate distributed algorithms for constructing routing trees in WSNs described in the literature. After identifying the drawbacks and advantages of these algorithms, we propose a new algorithm for constructing spanning trees in WSNs. The performance of the proposed algorithm and the quality of the constructed tree were evaluated in different network scenarios. The results showed that the proposed algorithm is a more efficient solution. Furthermore, the algorithm provides multiple routes to the sensor nodes to be used as mechanisms for fault tolerance and load balancing.

Dynamic Construction Scheme for Virtualization Security Service in Software-Defined Networks.

Science.gov (United States)

Lin, Zhaowen; Tao, Dan; Wang, Zhenji

2017-04-21

For a Software Defined Network (SDN), security is an important factor affecting its large-scale deployment. The existing security solutions for SDN mainly focus on the controller itself, which has to handle all the security protection tasks by using the programmability of the network. This will undoubtedly involve a heavy burden for the controller. More devastatingly, once the controller itself is attacked, the entire network will be paralyzed. Motivated by this, this paper proposes a novel security protection architecture for SDN. We design a security service orchestration center in the control plane of SDN, and this center physically decouples from the SDN controller and constructs SDN security services. We adopt virtualization technology to construct a security meta-function library, and propose a dynamic security service composition construction algorithm based on web service composition technology. The rule-combining method is used to combine security meta-functions to construct security services which meet the requirements of users. Moreover, the RETE algorithm is introduced to improve the efficiency of the rule-combining method. We evaluate our solutions in a realistic scenario based on OpenStack. Substantial experimental results demonstrate the effectiveness of our solutions that contribute to achieve the effective security protection with a small burden of the SDN controller.

Constructing ordinal partition transition networks from multivariate time series.

Science.gov (United States)

Zhang, Jiayang; Zhou, Jie; Tang, Ming; Guo, Heng; Small, Michael; Zou, Yong

2017-08-10

A growing number of algorithms have been proposed to map a scalar time series into ordinal partition transition networks. However, most observable phenomena in the empirical sciences are of a multivariate nature. We construct ordinal partition transition networks for multivariate time series. This approach yields weighted directed networks representing the pattern transition properties of time series in velocity space, which hence provides dynamic insights of the underling system. Furthermore, we propose a measure of entropy to characterize ordinal partition transition dynamics, which is sensitive to capturing the possible local geometric changes of phase space trajectories. We demonstrate the applicability of pattern transition networks to capture phase coherence to non-coherence transitions, and to characterize paths to phase synchronizations. Therefore, we conclude that the ordinal partition transition network approach provides complementary insight to the traditional symbolic analysis of nonlinear multivariate time series.

Bayesian-network-based safety risk analysis in construction projects

International Nuclear Information System (INIS)

Zhang, Limao; Wu, Xianguo; Skibniewski, Miroslaw J.; Zhong, Jingbing; Lu, Yujie

2014-01-01

This paper presents a systemic decision support approach for safety risk analysis under uncertainty in tunnel construction. Fuzzy Bayesian Networks (FBN) is used to investigate causal relationships between tunnel-induced damage and its influential variables based upon the risk/hazard mechanism analysis. Aiming to overcome limitations on the current probability estimation, an expert confidence indicator is proposed to ensure the reliability of the surveyed data for fuzzy probability assessment of basic risk factors. A detailed fuzzy-based inference procedure is developed, which has a capacity of implementing deductive reasoning, sensitivity analysis and abductive reasoning. The “3σ criterion” is adopted to calculate the characteristic values of a triangular fuzzy number in the probability fuzzification process, and the α-weighted valuation method is adopted for defuzzification. The construction safety analysis progress is extended to the entire life cycle of risk-prone events, including the pre-accident, during-construction continuous and post-accident control. A typical hazard concerning the tunnel leakage in the construction of Wuhan Yangtze Metro Tunnel in China is presented as a case study, in order to verify the applicability of the proposed approach. The results demonstrate the feasibility of the proposed approach and its application potential. A comparison of advantages and disadvantages between FBN and fuzzy fault tree analysis (FFTA) as risk analysis tools is also conducted. The proposed approach can be used to provide guidelines for safety analysis and management in construction projects, and thus increase the likelihood of a successful project in a complex environment. - Highlights: • A systemic Bayesian network based approach for safety risk analysis is developed. • An expert confidence indicator for probability fuzzification is proposed. • Safety risk analysis progress is extended to entire life cycle of risk-prone events. • A typical

Scalable Brain Network Construction on White Matter Fibers.

Science.gov (United States)

Chung, Moo K; Adluru, Nagesh; Dalton, Kim M; Alexander, Andrew L; Davidson, Richard J

2011-02-12

DTI offers a unique opportunity to characterize the structural connectivity of the human brain non-invasively by tracing white matter fiber tracts. Whole brain tractography studies routinely generate up to half million tracts per brain, which serves as edges in an extremely large 3D graph with up to half million edges. Currently there is no agreed-upon method for constructing the brain structural network graphs out of large number of white matter tracts. In this paper, we present a scalable iterative framework called the ε-neighbor method for building a network graph and apply it to testing abnormal connectivity in autism.

A Lindenmayer system-based approach for the design of nutrient delivery networks in tissue constructs

International Nuclear Information System (INIS)

Yasar, Ozlem; Starly, Binil; Lan, S-F

2009-01-01

Large thick tissue constructs have reported limited success primarily due to the inability of cells to survive deep within the scaffold. Without access to adequate nutrients, cells placed deep within the tissue construct will die out, leading to non-uniform tissue regeneration. Currently, there is a necessity to design nutrient conduit networks within the tissue construct to enable cells to survive in the matrix. However, the design of complex networks within a tissue construct is challenging. In this paper, we present the Lindenmayer system, an elegant fractal-based language algorithm framework, to generate conduit networks in two- and three-dimensional architecture with several degrees of complexity. The conduit network maintains a parent-child relationship between each branch of the network. Several L-system parameters have been studied-branching angle, branch length, ratio of parent to child branch diameter, etc-to simulate several architectures under a given L-system notation. We have also presented a layered manufacturing-based UV-photopolymerization process using the Texas Instruments DLP(TM) system to fabricate the branched structures. This preliminary work showcases the applicability of L-system-based construct designs to drive scaffold fabrication systems.

A Lindenmayer system-based approach for the design of nutrient delivery networks in tissue constructs

Energy Technology Data Exchange (ETDEWEB)

Yasar, Ozlem; Starly, Binil [School of Industrial Engineering, University of Oklahoma, Norman, OK 73019 (United States); Lan, S-F [University of Oklahoma Bioengineering Center, University of Oklahoma, Norman, OK 73019 (United States)

2009-12-15

Large thick tissue constructs have reported limited success primarily due to the inability of cells to survive deep within the scaffold. Without access to adequate nutrients, cells placed deep within the tissue construct will die out, leading to non-uniform tissue regeneration. Currently, there is a necessity to design nutrient conduit networks within the tissue construct to enable cells to survive in the matrix. However, the design of complex networks within a tissue construct is challenging. In this paper, we present the Lindenmayer system, an elegant fractal-based language algorithm framework, to generate conduit networks in two- and three-dimensional architecture with several degrees of complexity. The conduit network maintains a parent-child relationship between each branch of the network. Several L-system parameters have been studied-branching angle, branch length, ratio of parent to child branch diameter, etc-to simulate several architectures under a given L-system notation. We have also presented a layered manufacturing-based UV-photopolymerization process using the Texas Instruments DLP(TM) system to fabricate the branched structures. This preliminary work showcases the applicability of L-system-based construct designs to drive scaffold fabrication systems.

Classifying galaxy spectra at 0.5 < z < 1 with self-organizing maps

Science.gov (United States)

Rahmani, S.; Teimoorinia, H.; Barmby, P.

2018-05-01

The spectrum of a galaxy contains information about its physical properties. Classifying spectra using templates helps elucidate the nature of a galaxy's energy sources. In this paper, we investigate the use of self-organizing maps in classifying galaxy spectra against templates. We trained semi-supervised self-organizing map networks using a set of templates covering the wavelength range from far ultraviolet to near infrared. The trained networks were used to classify the spectra of a sample of 142 galaxies with 0.5 K-means clustering, a supervised neural network, and chi-squared minimization. Spectra corresponding to quiescent galaxies were more likely to be classified similarly by all methods while starburst spectra showed more variability. Compared to classification using chi-squared minimization or the supervised neural network, the galaxies classed together by the self-organizing map had more similar spectra. The class ordering provided by the one-dimensional self-organizing maps corresponds to an ordering in physical properties, a potentially important feature for the exploration of large datasets.

Discrimination of panti p → tanti t events by a neural network classifier

International Nuclear Information System (INIS)

Cherubini, A.; Odorico, R.

1992-01-01

Neural network and conventional statistical techniques are compared in the problem of discriminating panti p→tanti t events, with top quarks decaying into anything, from the associated hadronic background at the energy of the Fermilab collider. The NN we develop for this sake is an improved version of Kohonen's learning vector quantization scheme. Performance of the NN as a tanti t event classifier is found to be less satisfactory than that achievable by statistical methods. We conclude that the probable reasons for that are: i) The NN approach presents advantages only when dealing with event distributions in the feature space which substantially differ from Gaussians; ii) NN's require much larger training sets of events than statistical discrimination in order to give comparable results. (orig.)

Carbon classified?

DEFF Research Database (Denmark)

Lippert, Ingmar

2012-01-01

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

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

Science.gov (United States)

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

2017-10-01

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

Influence of the Time Scale on the Construction of Financial Networks

OpenAIRE

Emmert-Streib, Frank; Dehmer, Matthias

2010-01-01

BACKGROUND: In this paper we investigate the definition and formation of financial networks. Specifically, we study the influence of the time scale on their construction. METHODOLOGY/PRINCIPAL FINDINGS: For our analysis we use correlation-based networks obtained from the daily closing prices of stock market data. More precisely, we use the stocks that currently comprise the Dow Jones Industrial Average (DJIA) and estimate financial networks where nodes correspond to stocks and edges correspon...

Pap-smear Classification Using Efficient Second Order Neural Network Training Algorithms

DEFF Research Database (Denmark)

Ampazis, Nikolaos; Dounias, George; Jantzen, Jan

2004-01-01

In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier. The alg......In this paper we make use of two highly efficient second order neural network training algorithms, namely the LMAM (Levenberg-Marquardt with Adaptive Momentum) and OLMAM (Optimized Levenberg-Marquardt with Adaptive Momentum), for the construction of an efficient pap-smear test classifier....... The algorithms are methodologically similar, and are based on iterations of the form employed in the Levenberg-Marquardt (LM) method for non-linear least squares problems with the inclusion of an additional adaptive momentum term arising from the formulation of the training task as a constrained optimization...

A Constructive Neural-Network Approach to Modeling Psychological Development

Science.gov (United States)

Shultz, Thomas R.

2012-01-01

This article reviews a particular computational modeling approach to the study of psychological development--that of constructive neural networks. This approach is applied to a variety of developmental domains and issues, including Piagetian tasks, shift learning, language acquisition, number comparison, habituation of visual attention, concept…

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

Science.gov (United States)

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

2017-01-01

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

Construction of Pancreatic Cancer Classifier Based on SVM Optimized by Improved FOA

Science.gov (United States)

Ma, Xiaoqi

2015-01-01

A novel method is proposed to establish the pancreatic cancer classifier. Firstly, the concept of quantum and fruit fly optimal algorithm (FOA) are introduced, respectively. Then FOA is improved by quantum coding and quantum operation, and a new smell concentration determination function is defined. Finally, the improved FOA is used to optimize the parameters of support vector machine (SVM) and the classifier is established by optimized SVM. In order to verify the effectiveness of the proposed method, SVM and other classification methods have been chosen as the comparing methods. The experimental results show that the proposed method can improve the classifier performance and cost less time. PMID:26543867

Construction of Injectable Double-Network Hydrogels for Cell Delivery.

Science.gov (United States)

Yan, Yan; Li, Mengnan; Yang, Di; Wang, Qian; Liang, Fuxin; Qu, Xiaozhong; Qiu, Dong; Yang, Zhenzhong

2017-07-10

Herein we present a unique method of using dynamic cross-links, which are dynamic covalent bonding and ionic interaction, for the construction of injectable double-network (DN) hydrogels, with the objective of cell delivery for cartilage repair. Glycol chitosan and dibenzaldhyde capped poly(ethylene oxide) formed the first network, while calcium alginate formed the second one, and in the resultant DN hydrogel, either of the networks could be selectively removed. The moduli of the DN hydrogel were significantly improved compared to that of the parent single-network hydrogels and were tunable by changing the chemical components. In situ 3D cell encapsulation could be easily performed by mixing cell suspension to the polymer solutions and transferred through a syringe needle before sol-gel transition. Cell proliferation and mediated differentiation of mouse chondrogenic cells were achieved in the DN hydrogel extracellular matrix.

Evaluation of gene association methods for coexpression network construction and biological knowledge discovery.

Directory of Open Access Journals (Sweden)

Sapna Kumari

Full Text Available BACKGROUND: Constructing coexpression networks and performing network analysis using large-scale gene expression data sets is an effective way to uncover new biological knowledge; however, the methods used for gene association in constructing these coexpression networks have not been thoroughly evaluated. Since different methods lead to structurally different coexpression networks and provide different information, selecting the optimal gene association method is critical. METHODS AND RESULTS: In this study, we compared eight gene association methods - Spearman rank correlation, Weighted Rank Correlation, Kendall, Hoeffding's D measure, Theil-Sen, Rank Theil-Sen, Distance Covariance, and Pearson - and focused on their true knowledge discovery rates in associating pathway genes and construction coordination networks of regulatory genes. We also examined the behaviors of different methods to microarray data with different properties, and whether the biological processes affect the efficiency of different methods. CONCLUSIONS: We found that the Spearman, Hoeffding and Kendall methods are effective in identifying coexpressed pathway genes, whereas the Theil-sen, Rank Theil-Sen, Spearman, and Weighted Rank methods perform well in identifying coordinated transcription factors that control the same biological processes and traits. Surprisingly, the widely used Pearson method is generally less efficient, and so is the Distance Covariance method that can find gene pairs of multiple relationships. Some analyses we did clearly show Pearson and Distance Covariance methods have distinct behaviors as compared to all other six methods. The efficiencies of different methods vary with the data properties to some degree and are largely contingent upon the biological processes, which necessitates the pre-analysis to identify the best performing method for gene association and coexpression network construction.

Deconvolution When Classifying Noisy Data Involving Transformations

KAUST Repository

Carroll, Raymond

2012-09-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

Deconvolution When Classifying Noisy Data Involving Transformations.

Science.gov (United States)

Carroll, Raymond; Delaigle, Aurore; Hall, Peter

2012-09-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

Deconvolution When Classifying Noisy Data Involving Transformations

KAUST Repository

Carroll, Raymond; Delaigle, Aurore; Hall, Peter

2012-01-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

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

Directory of Open Access Journals (Sweden)

Shehzad Khalid

2014-01-01

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

The construction of an amino acid network for understanding protein structure and function.

Science.gov (United States)

Yan, Wenying; Zhou, Jianhong; Sun, Maomin; Chen, Jiajia; Hu, Guang; Shen, Bairong

2014-06-01

Amino acid networks (AANs) are undirected networks consisting of amino acid residues and their interactions in three-dimensional protein structures. The analysis of AANs provides novel insight into protein science, and several common amino acid network properties have revealed diverse classes of proteins. In this review, we first summarize methods for the construction and characterization of AANs. We then compare software tools for the construction and analysis of AANs. Finally, we review the application of AANs for understanding protein structure and function, including the identification of functional residues, the prediction of protein folding, analyzing protein stability and protein-protein interactions, and for understanding communication within and between proteins.

An Analysis of Construction Accident Factors Based on Bayesian Network

OpenAIRE

Yunsheng Zhao; Jinyong Pei

2013-01-01

In this study, we have an analysis of construction accident factors based on bayesian network. Firstly, accidents cases are analyzed to build Fault Tree method, which is available to find all the factors causing the accidents, then qualitatively and quantitatively analyzes the factors with Bayesian network method, finally determines the safety management program to guide the safety operations. The results of this study show that bad condition of geological environment has the largest posterio...

Classifying emotion in Twitter using Bayesian network

Science.gov (United States)

Surya Asriadie, Muhammad; Syahrul Mubarok, Mohamad; Adiwijaya

2018-03-01

Language is used to express not only facts, but also emotions. Emotions are noticeable from behavior up to the social media statuses written by a person. Analysis of emotions in a text is done in a variety of media such as Twitter. This paper studies classification of emotions on twitter using Bayesian network because of its ability to model uncertainty and relationships between features. The result is two models based on Bayesian network which are Full Bayesian Network (FBN) and Bayesian Network with Mood Indicator (BNM). FBN is a massive Bayesian network where each word is treated as a node. The study shows the method used to train FBN is not very effective to create the best model and performs worse compared to Naive Bayes. F1-score for FBN is 53.71%, while for Naive Bayes is 54.07%. BNM is proposed as an alternative method which is based on the improvement of Multinomial Naive Bayes and has much lower computational complexity compared to FBN. Even though it’s not better compared to FBN, the resulting model successfully improves the performance of Multinomial Naive Bayes. F1-Score for Multinomial Naive Bayes model is 51.49%, while for BNM is 52.14%.

Towards port sustainability through probabilistic models: Bayesian networks

Directory of Open Access Journals (Sweden)

B. Molina

2018-04-01

Full Text Available It is necessary that a manager of an infrastructure knows relations between variables. Using Bayesian networks, variables can be classified, predicted and diagnosed, being able to estimate posterior probability of the unknown ones based on known ones. The proposed methodology has generated a database with port variables, which have been classified as economic, social, environmental and institutional, as addressed in of smart ports studies made in all Spanish Port System. Network has been developed using an acyclic directed graph, which have let us know relationships in terms of parents and sons. In probabilistic terms, it can be concluded from the constructed network that the most decisive variables for port sustainability are those that are part of the institutional dimension. It has been concluded that Bayesian networks allow modeling uncertainty probabilistically even when the number of variables is high as it occurs in port planning and exploitation.

Efficient Geo-Computational Algorithms for Constructing Space-Time Prisms in Road Networks

Directory of Open Access Journals (Sweden)

Hui-Ping Chen

2016-11-01

Full Text Available The Space-time prism (STP is a key concept in time geography for analyzing human activity-travel behavior under various Space-time constraints. Most existing time-geographic studies use a straightforward algorithm to construct STPs in road networks by using two one-to-all shortest path searches. However, this straightforward algorithm can introduce considerable computational overhead, given the fact that accessible links in a STP are generally a small portion of the whole network. To address this issue, an efficient geo-computational algorithm, called NTP-A*, is proposed. The proposed NTP-A* algorithm employs the A* and branch-and-bound techniques to discard inaccessible links during two shortest path searches, and thereby improves the STP construction performance. Comprehensive computational experiments are carried out to demonstrate the computational advantage of the proposed algorithm. Several implementation techniques, including the label-correcting technique and the hybrid link-node labeling technique, are discussed and analyzed. Experimental results show that the proposed NTP-A* algorithm can significantly improve STP construction performance in large-scale road networks by a factor of 100, compared with existing algorithms.

Exploring the field of public construction clients by a graphical network analysis

OpenAIRE

Eisma, P.R.; Volker, L.

2014-01-01

Because public construction clients form the majority of construction clients and procure over 40% of the construction output in most countries, they are important actors in the construction industry. Yet, the field of research on clients is still underdeveloped. In order to identify the research gaps in this field, a graphical network analysis of existing literature is performed. The analysis is based on a query executed in the scientific database Scopus resulting in around 3,300 publication...

Feature genes in metastatic breast cancer identified by MetaDE and SVM classifier methods.

Science.gov (United States)

Tuo, Youlin; An, Ning; Zhang, Ming

2018-03-01

The aim of the present study was to investigate the feature genes in metastatic breast cancer samples. A total of 5 expression profiles of metastatic breast cancer samples were downloaded from the Gene Expression Omnibus database, which were then analyzed using the MetaQC and MetaDE packages in R language. The feature genes between metastasis and non‑metastasis samples were screened under the threshold of PSVM) classifier training and verification. The accuracy of the SVM classifier was then evaluated using another independent dataset from The Cancer Genome Atlas database. Finally, function and pathway enrichment analyses for genes in the SVM classifier were performed. A total of 541 feature genes were identified between metastatic and non‑metastatic samples. The top 10 genes with the highest betweenness centrality values in the PPI network of feature genes were Nuclear RNA Export Factor 1, cyclin‑dependent kinase 2 (CDK2), myelocytomatosis proto‑oncogene protein (MYC), Cullin 5, SHC Adaptor Protein 1, Clathrin heavy chain, Nucleolin, WD repeat domain 1, proteasome 26S subunit non‑ATPase 2 and telomeric repeat binding factor 2. The cyclin‑dependent kinase inhibitor 1A (CDKN1A), E2F transcription factor 1 (E2F1), and MYC interacted with CDK2. The SVM classifier constructed by the top 30 feature genes was able to distinguish metastatic samples from non‑metastatic samples [correct rate, specificity, positive predictive value and negative predictive value >0.89; sensitivity >0.84; area under the receiver operating characteristic curve (AUROC) >0.96]. The verification of the SVM classifier in an independent dataset (35 metastatic samples and 143 non‑metastatic samples) revealed an accuracy of 94.38% and AUROC of 0.958. Cell cycle associated functions and pathways were the most significant terms of the 30 feature genes. A SVM classifier was constructed to assess the possibility of breast cancer metastasis, which presented high accuracy in several

Identification of flooded area from satellite images using Hybrid Kohonen Fuzzy C-Means sigma classifier

Directory of Open Access Journals (Sweden)

Krishna Kant Singh

2017-06-01

Full Text Available A novel neuro fuzzy classifier Hybrid Kohonen Fuzzy C-Means-σ (HKFCM-σ is proposed in this paper. The proposed classifier is a hybridization of Kohonen Clustering Network (KCN with FCM-σ clustering algorithm. The network architecture of HKFCM-σ is similar to simple KCN network having only two layers, i.e., input and output layer. However, the selection of winner neuron is done based on FCM-σ algorithm. Thus, embedding the features of both, a neural network and a fuzzy clustering algorithm in the classifier. This hybridization results in a more efficient, less complex and faster classifier for classifying satellite images. HKFCM-σ is used to identify the flooding that occurred in Kashmir area in September 2014. The HKFCM-σ classifier is applied on pre and post flooding Landsat 8 OLI images of Kashmir to detect the areas that were flooded due to the heavy rainfalls of September, 2014. The classifier is trained using the mean values of the various spectral indices like NDVI, NDWI, NDBI and first component of Principal Component Analysis. The error matrix was computed to test the performance of the method. The method yields high producer’s accuracy, consumer’s accuracy and kappa coefficient value indicating that the proposed classifier is highly effective and efficient.

Multilevel regularized regression for simultaneous taxa selection and network construction with metagenomic count data.

Science.gov (United States)

Liu, Zhenqiu; Sun, Fengzhu; Braun, Jonathan; McGovern, Dermot P B; Piantadosi, Steven

2015-04-01

Identifying disease associated taxa and constructing networks for bacteria interactions are two important tasks usually studied separately. In reality, differentiation of disease associated taxa and correlation among taxa may affect each other. One genus can be differentiated because it is highly correlated with another highly differentiated one. In addition, network structures may vary under different clinical conditions. Permutation tests are commonly used to detect differences between networks in distinct phenotypes, and they are time-consuming. In this manuscript, we propose a multilevel regularized regression method to simultaneously identify taxa and construct networks. We also extend the framework to allow construction of a common network and differentiated network together. An efficient algorithm with dual formulation is developed to deal with the large-scale n ≪ m problem with a large number of taxa (m) and a small number of samples (n) efficiently. The proposed method is regularized with a general Lp (p ∈ [0, 2]) penalty and models the effects of taxa abundance differentiation and correlation jointly. We demonstrate that it can identify both true and biologically significant genera and network structures. Software MLRR in MATLAB is available at http://biostatistics.csmc.edu/mlrr/. Supplementary data are available at Bioinformatics online. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Time for a real shift to relations: appraisal of Social Network Analysis applications in the UK construction industry

Directory of Open Access Journals (Sweden)

Ximing Ruan

2013-03-01

Full Text Available The Social Network Analysis (SNA has been adopted in the UK construction management research and generated meaningful insights in analysing project management organisations from network perspectives. As an effective tool, social network analysis has been used to analyse information and knowledge flow between construction project teams which is considered as foundation for collaborative working and subsequently improving overall performance. Social network analysis is based on an assumption of the importance of relationships among interacting units. The social network perspective encompasses theories, models and applications that are expressed in terms of relational concepts or processes. Many believe, moreover, that the success or failure of organisations often depends on the patterning of their internal structure. This paper reviewed existing literatures on SNA applications in construction industry from three leading construction management journals.  From the review, the research proposed some advance in the application of SNA in the construction industry.

Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images.

Science.gov (United States)

Cheng, Phillip M; Malhi, Harshawn S

2017-04-01

The purpose of this study is to evaluate transfer learning with deep convolutional neural networks for the classification of abdominal ultrasound images. Grayscale images from 185 consecutive clinical abdominal ultrasound studies were categorized into 11 categories based on the text annotation specified by the technologist for the image. Cropped images were rescaled to 256 × 256 resolution and randomized, with 4094 images from 136 studies constituting the training set, and 1423 images from 49 studies constituting the test set. The fully connected layers of two convolutional neural networks based on CaffeNet and VGGNet, previously trained on the 2012 Large Scale Visual Recognition Challenge data set, were retrained on the training set. Weights in the convolutional layers of each network were frozen to serve as fixed feature extractors. Accuracy on the test set was evaluated for each network. A radiologist experienced in abdominal ultrasound also independently classified the images in the test set into the same 11 categories. The CaffeNet network classified 77.3% of the test set images accurately (1100/1423 images), with a top-2 accuracy of 90.4% (1287/1423 images). The larger VGGNet network classified 77.9% of the test set accurately (1109/1423 images), with a top-2 accuracy of VGGNet was 89.7% (1276/1423 images). The radiologist classified 71.7% of the test set images correctly (1020/1423 images). The differences in classification accuracies between both neural networks and the radiologist were statistically significant (p convolutional neural networks may be used to construct effective classifiers for abdominal ultrasound images.

Paving the Way Towards Reactive Planar Spanner Construction in Wireless Networks

Science.gov (United States)

Frey, Hannes; Rührup, Stefan

A spanner is a subgraph of a given graph that supports the original graph's shortest path lengths up to a constant factor. Planar spanners and their distributed construction are of particular interest for geographic routing, which is an efficient localized routing scheme for wireless ad hoc and sensor networks. Planarity of the network graph is a key criterion for guaranteed delivery, while the spanner property supports efficiency in terms of path length. We consider the problem of reactive local spanner construction, where a node's local topology is determined on demand. Known message-efficient reactive planarization algorithms do not preserve the spanner property, while reactive spanner constructions with a low message overhead have not been described so far. We introduce the concept of direct planarization which may be an enabler of efficient reactive spanner construction. Given an edge, nodes check for all incident intersecting edges a certain geometric criterion and withdraw the edge if this criterion is not satisfied. We use this concept to derive a generic reactive topology control mechanism and consider two geometric criteria. Simulation results show that direct planarization increases the performance of localized geographic routing by providing shorter paths than existing reactive approaches.

Constructing networks from a dynamical system perspective for multivariate nonlinear time series.

Science.gov (United States)

Nakamura, Tomomichi; Tanizawa, Toshihiro; Small, Michael

2016-03-01

We describe a method for constructing networks for multivariate nonlinear time series. We approach the interaction between the various scalar time series from a deterministic dynamical system perspective and provide a generic and algorithmic test for whether the interaction between two measured time series is statistically significant. The method can be applied even when the data exhibit no obvious qualitative similarity: a situation in which the naive method utilizing the cross correlation function directly cannot correctly identify connectivity. To establish the connectivity between nodes we apply the previously proposed small-shuffle surrogate (SSS) method, which can investigate whether there are correlation structures in short-term variabilities (irregular fluctuations) between two data sets from the viewpoint of deterministic dynamical systems. The procedure to construct networks based on this idea is composed of three steps: (i) each time series is considered as a basic node of a network, (ii) the SSS method is applied to verify the connectivity between each pair of time series taken from the whole multivariate time series, and (iii) the pair of nodes is connected with an undirected edge when the null hypothesis cannot be rejected. The network constructed by the proposed method indicates the intrinsic (essential) connectivity of the elements included in the system or the underlying (assumed) system. The method is demonstrated for numerical data sets generated by known systems and applied to several experimental time series.

Convergence and divergence across construction methods for human brain white matter networks: an assessment based on individual differences.

Science.gov (United States)

Zhong, Suyu; He, Yong; Gong, Gaolang

2015-05-01

Using diffusion MRI, a number of studies have investigated the properties of whole-brain white matter (WM) networks with differing network construction methods (node/edge definition). However, how the construction methods affect individual differences of WM networks and, particularly, if distinct methods can provide convergent or divergent patterns of individual differences remain largely unknown. Here, we applied 10 frequently used methods to construct whole-brain WM networks in a healthy young adult population (57 subjects), which involves two node definitions (low-resolution and high-resolution) and five edge definitions (binary, FA weighted, fiber-density weighted, length-corrected fiber-density weighted, and connectivity-probability weighted). For these WM networks, individual differences were systematically analyzed in three network aspects: (1) a spatial pattern of WM connections, (2) a spatial pattern of nodal efficiency, and (3) network global and local efficiencies. Intriguingly, we found that some of the network construction methods converged in terms of individual difference patterns, but diverged with other methods. Furthermore, the convergence/divergence between methods differed among network properties that were adopted to assess individual differences. Particularly, high-resolution WM networks with differing edge definitions showed convergent individual differences in the spatial pattern of both WM connections and nodal efficiency. For the network global and local efficiencies, low-resolution and high-resolution WM networks for most edge definitions consistently exhibited a highly convergent pattern in individual differences. Finally, the test-retest analysis revealed a decent temporal reproducibility for the patterns of between-method convergence/divergence. Together, the results of the present study demonstrated a measure-dependent effect of network construction methods on the individual difference of WM network properties. © 2015 Wiley

Distributed Classification of Localization Attacks in Sensor Networks Using Exchange-Based Feature Extraction and Classifier

Directory of Open Access Journals (Sweden)

Su-Zhe Wang

2016-01-01

Full Text Available Secure localization under different forms of attack has become an essential task in wireless sensor networks. Despite the significant research efforts in detecting the malicious nodes, the problem of localization attack type recognition has not yet been well addressed. Motivated by this concern, we propose a novel exchange-based attack classification algorithm. This is achieved by a distributed expectation maximization extractor integrated with the PECPR-MKSVM classifier. First, the mixed distribution features based on the probabilistic modeling are extracted using a distributed expectation maximization algorithm. After feature extraction, by introducing the theory from support vector machine, an extensive contractive Peaceman-Rachford splitting method is derived to build the distributed classifier that diffuses the iteration calculation among neighbor sensors. To verify the efficiency of the distributed recognition scheme, four groups of experiments were carried out under various conditions. The average success rate of the proposed classification algorithm obtained in the presented experiments for external attacks is excellent and has achieved about 93.9% in some cases. These testing results demonstrate that the proposed algorithm can produce much greater recognition rate, and it can be also more robust and efficient even in the presence of excessive malicious scenario.

[Construction and optimization of ecological network for nature reserves in Fujian Province, China].

Science.gov (United States)

Gu, Fan; Huang, Yi Xiong; Chen, Chuan Ming; Cheng, Dong Liang; Guo, Jia Lei

2017-03-18

The nature reserve is very important to biodiversity maintenance. However, due to the urbanization, the nature reserve has been fragmented with reduction in area, leading to the loss of species diversity. Establishing ecological network can effectively connect the fragmented habitats and plays an important role in species conversation. In this paper, based on deciding habitat patches and the landscape cost surface in ArcGIS, a minimum cumulative resistance model was used to simulate the potential ecological network of Fujian provincial nature reserves. The connectivity and importance of network were analyzed and evaluated based on comparison of connectivity indices (including the integral index of connectivity and probability of connectivity) and gravity model both before and after the potential ecological network construction. The optimum ecological network optimization measures were proposed. The result demonstrated that woodlands, grasslands and wetlands together made up the important part of the nature reserve ecological network. The habitats with large area had a higher degree of importance in the network. After constructing the network, the connectivity level was significantly improved. Although interaction strength between different patches va-ried greatly, the corridors between patches with large interaction were very important. The research could provide scientific reference and basis for nature protection and planning in Fujian Province.

Time for a real shift to relations: appraisal of Social Network Analysis applications in the UK construction industry

Directory of Open Access Journals (Sweden)

Ximing Ruan

2013-03-01

Full Text Available The Social Network Analysis (SNA has been adopted in the UK construction management research and generated meaningful insights in analysing project management organisations from network perspectives. As an effective tool, social network analysis has been used to analyse information and knowledge flow between construction project teams which is considered as foundation for collaborative working and subsequently improving overall performance. Social network analysis is based on an assumption of the importance of relationships among interacting units. The social network perspective encompasses theories, models and applications that are expressed in terms of relational concepts or processes. Many believe, moreover, that the success or failure of organisations often depends on the patterning of their internal structure. This paper reviewed existing literatures on SNA applications in construction industry from three leading construction management journals.  From the review, the research proposed some advance in the application of SNA in the construction industry. 

Constructing a research network: accounting knowledge in production

OpenAIRE

Joannides , Vassili; Berland , Nicolas

2013-01-01

Avec Nicolas Berland; International audience; Purpose - This paper contributes to the sociology-of-science type of accounting literature, addressing how accounting knowledge is established, advanced and extended. Design/methodology/approach - The research question is answered through the example of research into linkages between accounting and religion. Adopting an Actor-Network Theory (ANT) approach, we follow the actors involved in the construction of accounting as an academic discipline th...

Refining a Heuristic for Constructing Bayesian Networks from Structured Arguments

NARCIS (Netherlands)

Wieten, G.M.; Bex, F.J.; van der Gaag, L.C.; Prakken, H.; Renooij, S.

2018-01-01

Recently, a heuristic was proposed for constructing Bayesian networks (BNs) from structured arguments. This heuristic helps domain experts who are accustomed to argumentation to transform their reasoning into a BN and subsequently weigh their case evidence in a probabilistic manner. While the

Organizational Data Classification Based on the Importance Concept of Complex Networks.

Science.gov (United States)

Carneiro, Murillo Guimaraes; Zhao, Liang

2017-08-01

Data classification is a common task, which can be performed by both computers and human beings. However, a fundamental difference between them can be observed: computer-based classification considers only physical features (e.g., similarity, distance, or distribution) of input data; by contrast, brain-based classification takes into account not only physical features, but also the organizational structure of data. In this paper, we figure out the data organizational structure for classification using complex networks constructed from training data. Specifically, an unlabeled instance is classified by the importance concept characterized by Google's PageRank measure of the underlying data networks. Before a test data instance is classified, a network is constructed from vector-based data set and the test instance is inserted into the network in a proper manner. To this end, we also propose a measure, called spatio-structural differential efficiency, to combine the physical and topological features of the input data. Such a method allows for the classification technique to capture a variety of data patterns using the unique importance measure. Extensive experiments demonstrate that the proposed technique has promising predictive performance on the detection of heart abnormalities.

Cost effectiveness of DH-network construction. Final report; Kaukolaempoeverkon rakentamisen kehittaeminen; Loppuraportti

Energy Technology Data Exchange (ETDEWEB)

Kivistoe, V.M. [Ekono Energy Ltd, Espoo (Finland)

1993-12-31

Construction cost of DH networks were analyzed in the study. Basing on the analysis, those areas of construction activities were selected, where cost effectiveness could be improved. According to the study, the civil works` cost form about half of the total construction cost on small diameter networks and 30..40 % of the cost of larger sizes. The impact of the design on the construction cost should be emphasized. According to the study it is possible to find significant reduction in the construction cost by increased use of twin pipe where the both carrier pipes are included in the same insulation casing. In small network sizes the reduction of cost achievable by the above is about 30..35 % and in larger sizes about 10 % (DN 125..DN 200) when comparing with a design by individual pipes. The use of twin pipe also causes savings in thermal loss. In sizes DN 65 and up, the saving in heat loss is about 90..95 FIM/m which represents about half of the total savings when compared with design by individual pipes. The possibility of prestressing the twin pipe element at factory in order to shorten the installation time at site was also studied and test pipes was also done. By factory prestressing it would be possible to avoid preheating of pipes at construction site. The trench could be backfilled immediately after pipe laying, welding and inspections. Theoretically and based on test pipes done the prestressing of twin pipe element looks very promising. When factory prestressing would be used, the open time of the trench is reduced significantly and for instance the disturbance to traffic is smaller. As well the use of labour and machinery at site could be more effective

A support vector machine and a random forest classifier indicates a 15-miRNA set related to osteosarcoma recurrence

Directory of Open Access Journals (Sweden)

He Y

2018-01-01

Full Text Available Yunfei He,1,2,* Jun Ma,1,* An Wang,1,3,* Weiheng Wang,1 Shengchang Luo,1 Yaoming Liu,2 Xiaojian Ye1 1Department of Orthopaedics, Changzheng Hospital Affiliated with Second Military Medical University, Shanghai, 2Department of Orthopaedics, Lanzhou General Hospital of Lanzhou Military Command Region, Lanzhou, 3Department of Orthopaedics, Shanghai Armed Police Force Hospital, Shanghai, People’s Republic of China *These authors contributed equally to this work Background: Osteosarcoma, which originates in the mesenchymal tissue, is the prevalent primary solid malignancy of the bone. It is of great importance to explore the mechanisms of metastasis and recurrence, which are two primary reasons accounting for the high death rate in osteosarcoma. Data and methods: Three miRNA expression profiles related to osteosarcoma were downloaded from GEO DataSets. Differentially expressed miRNAs (DEmiRs were screened using MetaDE.ES of the MetaDE package. A support vector machine (SVM classifier was constructed using optimal miRNAs, and its prediction efficiency for recurrence was detected in independent datasets. Finally, a co-expression network was constructed based on the DEmiRs and their target genes. Results: In total, 78 significantly DEmiRs were screened. The SVM classifier constructed by 15 miRNAs could accurately classify 58 samples in 65 samples (89.2% in the GSE39040 database, which was validated in another two databases, GSE39052 (84.62%, 22/26 and GSE79181 (91.3%, 21/23. Cox regression showed that four miRNAs, including hsa-miR-10b, hsa-miR-1227, hsa-miR-146b-3p, and hsa-miR-873, significantly correlated with tumor recurrence time. There were 137, 147, 145, and 77 target genes of the above four miRNAs, respectively, which were assigned to 17 gene ontology functionally annotated terms and 14 Kyoto Encyclopedia of Genes and Genomes pathways. Among them, the “Osteoclast differentiation” pathway contained a total of seven target genes and was

Constructing financial network based on PMFG and threshold method

Science.gov (United States)

Nie, Chun-Xiao; Song, Fu-Tie

2018-04-01

Based on planar maximally filtered graph (PMFG) and threshold method, we introduced a correlation-based network named PMFG-based threshold network (PTN). We studied the community structure of PTN and applied ISOMAP algorithm to represent PTN in low-dimensional Euclidean space. The results show that the community corresponds well to the cluster in the Euclidean space. Further, we studied the dynamics of the community structure and constructed the normalized mutual information (NMI) matrix. Based on the real data in the market, we found that the volatility of the market can lead to dramatic changes in the community structure, and the structure is more stable during the financial crisis.

New neural network classifier of fall-risk based on the Mahalanobis distance and kinematic parameters assessed by a wearable device

International Nuclear Information System (INIS)

Giansanti, Daniele; Macellari, Velio; Maccioni, Giovanni

2008-01-01

Fall prevention lacks easy, quantitative and wearable methods for the classification of fall-risk (FR). Efforts must be thus devoted to the choice of an ad hoc classifier both to reduce the size of the sample used to train the classifier and to improve performances. A new methodology that uses a neural network (NN) and a wearable device are hereby proposed for this purpose. The NN uses kinematic parameters assessed by a wearable device with accelerometers and rate gyroscopes during a posturography protocol. The training of the NN was based on the Mahalanobis distance and was carried out on two groups of 30 elderly subjects with varying fall-risk Tinetti scores. The validation was done on two groups of 100 subjects with different fall-risk Tinetti scores and showed that, both in terms of specificity and sensitivity, the NN performed better than other classifiers (naive Bayes, Bayes net, multilayer perceptron, support vector machines, statistical classifiers). In particular, (i) the proposed NN methodology improved the specificity and sensitivity by a mean of 3% when compared to the statistical classifier based on the Mahalanobis distance (SCMD) described in Giansanti (2006 Physiol. Meas. 27 1081–90); (ii) the assessed specificity was 97%, the assessed sensitivity was 98% and the area under receiver operator characteristics was 0.965. (note)

A network analysis of the Chinese stock market

Science.gov (United States)

Huang, Wei-Qiang; Zhuang, Xin-Tian; Yao, Shuang

2009-07-01

In many practical important cases, a massive dataset can be represented as a very large network with certain attributes associated with its vertices and edges. Stock markets generate huge amounts of data, which can be use for constructing the network reflecting the market’s behavior. In this paper, we use a threshold method to construct China’s stock correlation network and then study the network’s structural properties and topological stability. We conduct a statistical analysis of this network and show that it follows a power-law model. We also detect components, cliques and independent sets in this network. These analyses allows one to apply a new data mining technique of classifying financial instruments based on stock price data, which provides a deeper insight into the internal structure of the stock market. Moreover, we test the topological stability of this network and find that it displays a topological robustness against random vertex failures, but it is also fragile to intentional attacks. Such a network stability property would be also useful for portfolio investment and risk management.

Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data.

Science.gov (United States)

Ye, Fei

2017-01-01

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks.

Constructing an integrated gene similarity network for the identification of disease genes.

Science.gov (United States)

Tian, Zhen; Guo, Maozu; Wang, Chunyu; Xing, LinLin; Wang, Lei; Zhang, Yin

2017-09-20

Discovering novel genes that are involved human diseases is a challenging task in biomedical research. In recent years, several computational approaches have been proposed to prioritize candidate disease genes. Most of these methods are mainly based on protein-protein interaction (PPI) networks. However, since these PPI networks contain false positives and only cover less half of known human genes, their reliability and coverage are very low. Therefore, it is highly necessary to fuse multiple genomic data to construct a credible gene similarity network and then infer disease genes on the whole genomic scale. We proposed a novel method, named RWRB, to infer causal genes of interested diseases. First, we construct five individual gene (protein) similarity networks based on multiple genomic data of human genes. Then, an integrated gene similarity network (IGSN) is reconstructed based on similarity network fusion (SNF) method. Finally, we employee the random walk with restart algorithm on the phenotype-gene bilayer network, which combines phenotype similarity network, IGSN as well as phenotype-gene association network, to prioritize candidate disease genes. We investigate the effectiveness of RWRB through leave-one-out cross-validation methods in inferring phenotype-gene relationships. Results show that RWRB is more accurate than state-of-the-art methods on most evaluation metrics. Further analysis shows that the success of RWRB is benefited from IGSN which has a wider coverage and higher reliability comparing with current PPI networks. Moreover, we conduct a comprehensive case study for Alzheimer's disease and predict some novel disease genes that supported by literature. RWRB is an effective and reliable algorithm in prioritizing candidate disease genes on the genomic scale. Software and supplementary information are available at http://nclab.hit.edu.cn/~tianzhen/RWRB/ .

Design and Implementation of Behavior Recognition System Based on Convolutional Neural Network

Directory of Open Access Journals (Sweden)

Yu Bo

2017-01-01

Full Text Available We build a set of human behavior recognition system based on the convolution neural network constructed for the specific human behavior in public places. Firstly, video of human behavior data set will be segmented into images, then we process the images by the method of background subtraction to extract moving foreground characters of body. Secondly, the training data sets are trained into the designed convolution neural network, and the depth learning network is constructed by stochastic gradient descent. Finally, the various behaviors of samples are classified and identified with the obtained network model, and the recognition results are compared with the current mainstream methods. The result show that the convolution neural network can study human behavior model automatically and identify human’s behaviors without any manually annotated trainings.

Impact of small-world network topology on the conventional artificial neural network for the diagnosis of diabetes

International Nuclear Information System (INIS)

Erkaymaz, Okan; Ozer, Mahmut

2016-01-01

Artificial intelligent systems have been widely used for diagnosis of diseases. Due to their importance, new approaches are attempted consistently to increase the performance of these systems. In this study, we introduce a new approach for diagnosis of diabetes based on the Small-World Feed Forward Artificial Neural Network (SW- FFANN). We construct the small-world network by following the Watts–Strogatz approach, and use this architecture for classifying the diabetes, and compare its performance with that of the regular or the conventional FFANN. We show that the classification performance of the SW-FFANN is better than that of the conventional FFANN. The SW-FFANN approach also results in both the highest output correlation and the best output error parameters. We also perform the accuracy analysis and show that SW-FFANN approach exhibits the highest classifier performance.

Construction and Analysis of Functional Networks in the Gut Microbiome of Type 2 Diabetes Patients.

Science.gov (United States)

Li, Lianshuo; Wang, Zicheng; He, Peng; Ma, Shining; Du, Jie; Jiang, Rui

2016-10-01

Although networks of microbial species have been widely used in the analysis of 16S rRNA sequencing data of a microbiome, the construction and analysis of a complete microbial gene network are in general problematic because of the large number of microbial genes in metagenomics studies. To overcome this limitation, we propose to map microbial genes to functional units, including KEGG orthologous groups and the evolutionary genealogy of genes: Non-supervised Orthologous Groups (eggNOG) orthologous groups, to enable the construction and analysis of a microbial functional network. We devised two statistical methods to infer pairwise relationships between microbial functional units based on a deep sequencing dataset of gut microbiome from type 2 diabetes (T2D) patients as well as healthy controls. Networks containing such functional units and their significant interactions were constructed subsequently. We conducted a variety of analyses of global properties, local properties, and functional modules in the resulting functional networks. Our data indicate that besides the observations consistent with the current knowledge, this study provides novel biological insights into the gut microbiome associated with T2D. Copyright © 2016. Production and hosting by Elsevier Ltd.

Construction of Pipelined Strategic Connected Dominating Set for Mobile Ad Hoc Networks

Directory of Open Access Journals (Sweden)

Ceronmani Sharmila

2016-06-01

Full Text Available Efficient routing between nodes is the most important challenge in a Mobile Ad Hoc Network (MANET. A Connected Dominating Set (CDS acts as a virtual backbone for routing in a MANET. Hence, the construction of CDS based on the need and its application plays a vital role in the applications of MANET. The PipeLined Strategic CDS (PLS-CDS is constructed based on strategy, dynamic diameter and transmission range. The strategy used for selecting the starting node is, any source node in the network, which has its entire destination within a virtual pipelined coverage, instead of the node with maximum connectivity. The other nodes are then selected based on density and velocity. The proposed CDS also utilizes the energy of the nodes in the network in an optimized manner. Simulation results showed that the proposed algorithm is better in terms of size of the CDS and average hop per path length.

Genonets server-a web server for the construction, analysis and visualization of genotype networks.

Science.gov (United States)

Khalid, Fahad; Aguilar-Rodríguez, José; Wagner, Andreas; Payne, Joshua L

2016-07-08

A genotype network is a graph in which vertices represent genotypes that have the same phenotype. Edges connect vertices if their corresponding genotypes differ in a single small mutation. Genotype networks are used to study the organization of genotype spaces. They have shed light on the relationship between robustness and evolvability in biological systems as different as RNA macromolecules and transcriptional regulatory circuits. Despite the importance of genotype networks, no tool exists for their automatic construction, analysis and visualization. Here we fill this gap by presenting the Genonets Server, a tool that provides the following features: (i) the construction of genotype networks for categorical and univariate phenotypes from DNA, RNA, amino acid or binary sequences; (ii) analyses of genotype network topology and how it relates to robustness and evolvability, as well as analyses of genotype network topography and how it relates to the navigability of a genotype network via mutation and natural selection; (iii) multiple interactive visualizations that facilitate exploratory research and education. The Genonets Server is freely available at http://ieu-genonets.uzh.ch. © The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.

Characterizing system dynamics with a weighted and directed network constructed from time series data

International Nuclear Information System (INIS)

Sun, Xiaoran; Small, Michael; Zhao, Yi; Xue, Xiaoping

2014-01-01

In this work, we propose a novel method to transform a time series into a weighted and directed network. For a given time series, we first generate a set of segments via a sliding window, and then use a doubly symbolic scheme to characterize every windowed segment by combining absolute amplitude information with an ordinal pattern characterization. Based on this construction, a network can be directly constructed from the given time series: segments corresponding to different symbol-pairs are mapped to network nodes and the temporal succession between nodes is represented by directed links. With this conversion, dynamics underlying the time series has been encoded into the network structure. We illustrate the potential of our networks with a well-studied dynamical model as a benchmark example. Results show that network measures for characterizing global properties can detect the dynamical transitions in the underlying system. Moreover, we employ a random walk algorithm to sample loops in our networks, and find that time series with different dynamics exhibits distinct cycle structure. That is, the relative prevalence of loops with different lengths can be used to identify the underlying dynamics

Characterizing system dynamics with a weighted and directed network constructed from time series data

Energy Technology Data Exchange (ETDEWEB)

Sun, Xiaoran, E-mail: sxr0806@gmail.com [Shenzhen Graduate School, Harbin Institute of Technology, Shenzhen 518055 (China); School of Mathematics and Statistics, The University of Western Australia, Crawley WA 6009 (Australia); Small, Michael, E-mail: michael.small@uwa.edu.au [School of Mathematics and Statistics, The University of Western Australia, Crawley WA 6009 (Australia); Zhao, Yi [Shenzhen Graduate School, Harbin Institute of Technology, Shenzhen 518055 (China); Xue, Xiaoping [Department of Mathematics, Harbin Institute of Technology, Harbin 150025 (China)

2014-06-15

In this work, we propose a novel method to transform a time series into a weighted and directed network. For a given time series, we first generate a set of segments via a sliding window, and then use a doubly symbolic scheme to characterize every windowed segment by combining absolute amplitude information with an ordinal pattern characterization. Based on this construction, a network can be directly constructed from the given time series: segments corresponding to different symbol-pairs are mapped to network nodes and the temporal succession between nodes is represented by directed links. With this conversion, dynamics underlying the time series has been encoded into the network structure. We illustrate the potential of our networks with a well-studied dynamical model as a benchmark example. Results show that network measures for characterizing global properties can detect the dynamical transitions in the underlying system. Moreover, we employ a random walk algorithm to sample loops in our networks, and find that time series with different dynamics exhibits distinct cycle structure. That is, the relative prevalence of loops with different lengths can be used to identify the underlying dynamics.

Adaptation in P300 braincomputer interfaces: A two-classifier cotraining approach

DEFF Research Database (Denmark)

Panicker, Rajesh C.; Sun, Ying; Puthusserypady, Sadasivan

2010-01-01

A cotraining-based approach is introduced for constructing high-performance classifiers for P300-based braincomputer interfaces (BCIs), which were trained from very little data. It uses two classifiers: Fishers linear discriminant analysis and Bayesian linear discriminant analysis progressively...

Connection with seismic networks and construction of real time earthquake monitoring system

Energy Technology Data Exchange (ETDEWEB)

Chi, Heon Cheol; Lee, H. I.; Shin, I. C.; Lim, I. S.; Park, J. H.; Lee, B. K.; Whee, K. H.; Cho, C. S. [Korea Atomic Energy Research Institute, Taejon (Korea, Republic of)

2000-12-15

It is natural to use the nuclear power plant seismic network which have been operated by KEPRI(Korea Electric Power Research Institute) and local seismic network by KIGAM(Korea Institute of Geology, Mining and Material). The real time earthquake monitoring system is composed with monitoring module and data base module. Data base module plays role of seismic data storage and classification and the other, monitoring module represents the status of acceleration in the nuclear power plant area. This research placed the target on the first, networking the KIN's seismic monitoring system with KIGAM and KEPRI seismic network and the second, construction the KIN's Independent earthquake monitoring system.

Connection with seismic networks and construction of real time earthquake monitoring system

International Nuclear Information System (INIS)

Chi, Heon Cheol; Lee, H. I.; Shin, I. C.; Lim, I. S.; Park, J. H.; Lee, B. K.; Whee, K. H.; Cho, C. S.

2000-12-01

It is natural to use the nuclear power plant seismic network which have been operated by KEPRI(Korea Electric Power Research Institute) and local seismic network by KIGAM(Korea Institute of Geology, Mining and Material). The real time earthquake monitoring system is composed with monitoring module and data base module. Data base module plays role of seismic data storage and classification and the other, monitoring module represents the status of acceleration in the nuclear power plant area. This research placed the target on the first, networking the KIN's seismic monitoring system with KIGAM and KEPRI seismic network and the second, construction the KIN's Independent earthquake monitoring system

Construction of Individual Morphological Brain Networks with Multiple Morphometric Features

Directory of Open Access Journals (Sweden)

Chunlan Yang

2017-04-01

Full Text Available In recent years, researchers have increased attentions to the morphological brain network, which is generally constructed by measuring the mathematical correlation across regions using a certain morphometric feature, such as regional cortical thickness and voxel intensity. However, cerebral structure can be characterized by various factors, such as regional volume, surface area, and curvature. Moreover, most of the morphological brain networks are population-based, which has limitations in the investigations of individual difference and clinical applications. Hence, we have extended previous studies by proposing a novel method for realizing the construction of an individual-based morphological brain network through a combination of multiple morphometric features. In particular, interregional connections are estimated using our newly introduced feature vectors, namely, the Pearson correlation coefficient of the concatenation of seven morphometric features. Experiments were performed on a healthy cohort of 55 subjects (24 males aged from 20 to 29 and 31 females aged from 20 to 28 each scanned twice, and reproducibility was evaluated through test–retest reliability. The robustness of morphometric features was measured firstly to select the more reproducible features to form the connectomes. Then the topological properties were analyzed and compared with previous reports of different modalities. Small-worldness was observed in all the subjects at the range of the entire network sparsity (20–40%, and configurations were comparable with previous findings at the sparsity of 23%. The spatial distributions of the hub were found to be significantly influenced by the individual variances, and the hubs obtained by averaging across subjects and sparsities showed correspondence with previous reports. The intraclass coefficient of graphic properties (clustering coefficient = 0.83, characteristic path length = 0.81, betweenness centrality = 0.78 indicates

Classifying and Analyzing 3d Cell Motion in Jammed Microgels

Science.gov (United States)

Bhattacharjee, Tapomoy; Sawyer, W. Gregory; Angelini, Thomas

Soft granular polyelectrolyte microgels swell in liquid cell growth media to form a continuous elastic solid that can easily transition between solid to fluid state under a low shear stress. Such Liquid-like solids (LLS) have recently been used to create 3D cellular constructs as well as to support, culture and harvest cells in 3D. Current understanding of cell migration mechanics in 3D was established from experiments performed in natural and synthetic polymer networks. Spatial variation in network structure and the transience of degradable gels limit their usefulness in quantitative cell mechanics studies. By contrast, LLS growth media approximates a homogeneous continuum, enabling tractable cell mechanics measurements to be performed in 3D. Here, we introduce a process to understand and classify cytotoxic T cell motion in 3D by studying cellular motility in LLS media. General classification of T cell motion can be achieved with a very traditional statistical approach: the cell's mean squared displacement (MSD) as a function of delay time. We will also use Langevin approaches combined with the constitutive equations of the LLS medium to predict the statistics of T cell motion. National Science Foundation under Grant No. DMR-1352043.

Comparison of two neural network classifiers in the differential diagnosis of essential tremor and Parkinson's disease by 123I-FP-CIT brain SPECT

International Nuclear Information System (INIS)

Palumbo, Barbara; Fravolini, Mario Luca; Nuvoli, Susanna; Spanu, Angela; Madeddu, Giuseppe; Paulus, Kai Stephan; Schillaci, Orazio

2010-01-01

To contribute to the differentiation of Parkinson's disease (PD) and essential tremor (ET), we compared two different artificial neural network classifiers using 123 I-FP-CIT SPECT data, a probabilistic neural network (PNN) and a classification tree (ClT). 123 I-FP-CIT brain SPECT with semiquantitative analysis was performed in 216 patients: 89 with ET, 64 with PD with a Hoehn and Yahr (H and Y) score of ≤2 (early PD), and 63 with PD with a H and Y score of ≥2.5 (advanced PD). For each of the 1,000 experiments carried out, 108 patients were randomly selected as the PNN training set, while the remaining 108 validated the trained PNN, and the percentage of the validation data correctly classified in the three groups of patients was computed. The expected performance of an ''average performance PNN'' was evaluated. In analogy, for ClT 1,000 classification trees with similar structures were generated. For PNN, the probability of correct classification in patients with early PD was 81.9±8.1% (mean±SD), in patients with advanced PD 78.9±8.1%, and in ET patients 96.6±2.6%. For ClT, the first decision rule gave a mean value for the putamen of 5.99, which resulted in a probability of correct classification of 93.5±3.4%. This means that patients with putamen values >5.99 were classified as having ET, while patients with putamen values <5.99 were classified as having PD. Furthermore, if the caudate nucleus value was higher than 6.97 patients were classified as having early PD (probability 69.8±5.3%), and if the value was <6.97 patients were classified as having advanced PD (probability 88.1%±8.8%). These results confirm that PNN achieved valid classification results. Furthermore, ClT provided reliable cut-off values able to differentiate ET and PD of different severities. (orig.)

Systematic construction and control of stereo nerve vision network in intelligent manufacturing

Science.gov (United States)

Liu, Hua; Wang, Helong; Guo, Chunjie; Ding, Quanxin; Zhou, Liwei

2017-10-01

A system method of constructing stereo vision by using neural network is proposed, and the operation and control mechanism in actual operation are proposed. This method makes effective use of the neural network in learning and memory function, by after training with samples. Moreover, the neural network can learn the nonlinear relationship in the stereoscopic vision system and the internal and external orientation elements. These considerations are Worthy of attention, which includes limited constraints, the scientific of critical group, the operating speed and the operability in technical aspects. The results support our theoretical forecast.

Analysis of Informationization Construction of Business Financial Management under the Network Economy

Science.gov (United States)

Dong, Yahui; Zhang, Pengwei; Li, Wei

To strengthen the informationization construction of the financial management has great significance to the achievement of business management informationization, and under the network economic environment, it is an important task of the financial management that how to conduct informationization construction of traditional financial management to provide true, reliable and complete financial information system for the business managers. This paper thoroughly researches the problem of financial information orientation management (FIOM) by taking the method of combining theory with practice. This paper puts forward the thinking method of financial information management, makes the new contents of E-finance. At last, this paper rebuilds the system of finance internal control from four aspects such as control of organization and management, system development control and safety control of network system.

29 CFR 1926.407 - Hazardous (classified) locations.

Science.gov (United States)

2010-07-01

...) locations, unless modified by provisions of this section. (b) Electrical installations. Equipment, wiring..., DEPARTMENT OF LABOR (CONTINUED) SAFETY AND HEALTH REGULATIONS FOR CONSTRUCTION Electrical Installation Safety... electric equipment and wiring in locations which are classified depending on the properties of the...

Oblique decision trees using embedded support vector machines in classifier ensembles

NARCIS (Netherlands)

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

2008-01-01

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

Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data

Science.gov (United States)

2017-01-01

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks. PMID:29236718

Constructing Ecological Networks Based on Habitat Quality Assessment: A Case Study of Changzhou, China

Science.gov (United States)

Gao, Yu; Ma, Lei; Liu, Jiaxun; Zhuang, Zhuzhou; Huang, Qiuhao; Li, Manchun

2017-01-01

Fragmentation and reduced continuity of habitat patches threaten the environment and biodiversity. Recently, ecological networks are increasingly attracting the attention of researchers as they provide fundamental frameworks for environmental protection. This study suggests a set of procedures to construct an ecological network. First, we proposed a method to construct a landscape resistance surface based on the assessment of habitat quality. Second, to analyze the effect of the resistance surface on corridor simulations, we used three methods to construct resistance surfaces: (1) the method proposed in this paper, (2) the entropy coefficient method, and (3) the expert scoring method. Then, we integrated habitat patches and resistance surfaces to identify potential corridors using graph theory. These procedures were tested in Changzhou, China. Comparing the outputs of using different resistance surfaces demonstrated that: (1) different landscape resistance surfaces contribute to how corridors are identified, but only slightly affect the assessment of the importance of habitat patches and potential corridors; (2) the resistance surface, which is constructed based on habitat quality, is more applicable to corridor simulations; and (3) the assessment of the importance of habitat patches is fundamental for ecological network optimization in the conservation of critical habitat patches and corridors. PMID:28393879

Evaluation of Classifier Performance for Multiclass Phenotype Discrimination in Untargeted Metabolomics.

Science.gov (United States)

Trainor, Patrick J; DeFilippis, Andrew P; Rai, Shesh N

2017-06-21

Statistical classification is a critical component of utilizing metabolomics data for examining the molecular determinants of phenotypes. Despite this, a comprehensive and rigorous evaluation of the accuracy of classification techniques for phenotype discrimination given metabolomics data has not been conducted. We conducted such an evaluation using both simulated and real metabolomics datasets, comparing Partial Least Squares-Discriminant Analysis (PLS-DA), Sparse PLS-DA, Random Forests, Support Vector Machines (SVM), Artificial Neural Network, k -Nearest Neighbors ( k -NN), and Naïve Bayes classification techniques for discrimination. We evaluated the techniques on simulated data generated to mimic global untargeted metabolomics data by incorporating realistic block-wise correlation and partial correlation structures for mimicking the correlations and metabolite clustering generated by biological processes. Over the simulation studies, covariance structures, means, and effect sizes were stochastically varied to provide consistent estimates of classifier performance over a wide range of possible scenarios. The effects of the presence of non-normal error distributions, the introduction of biological and technical outliers, unbalanced phenotype allocation, missing values due to abundances below a limit of detection, and the effect of prior-significance filtering (dimension reduction) were evaluated via simulation. In each simulation, classifier parameters, such as the number of hidden nodes in a Neural Network, were optimized by cross-validation to minimize the probability of detecting spurious results due to poorly tuned classifiers. Classifier performance was then evaluated using real metabolomics datasets of varying sample medium, sample size, and experimental design. We report that in the most realistic simulation studies that incorporated non-normal error distributions, unbalanced phenotype allocation, outliers, missing values, and dimension reduction

Mal-Netminer: Malware Classification Approach Based on Social Network Analysis of System Call Graph

Directory of Open Access Journals (Sweden)

Jae-wook Jang

2015-01-01

Full Text Available As the security landscape evolves over time, where thousands of species of malicious codes are seen every day, antivirus vendors strive to detect and classify malware families for efficient and effective responses against malware campaigns. To enrich this effort and by capitalizing on ideas from the social network analysis domain, we build a tool that can help classify malware families using features driven from the graph structure of their system calls. To achieve that, we first construct a system call graph that consists of system calls found in the execution of the individual malware families. To explore distinguishing features of various malware species, we study social network properties as applied to the call graph, including the degree distribution, degree centrality, average distance, clustering coefficient, network density, and component ratio. We utilize features driven from those properties to build a classifier for malware families. Our experimental results show that “influence-based” graph metrics such as the degree centrality are effective for classifying malware, whereas the general structural metrics of malware are less effective for classifying malware. Our experiments demonstrate that the proposed system performs well in detecting and classifying malware families within each malware class with accuracy greater than 96%.

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

Science.gov (United States)

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

2017-01-01

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

A convolutional neural network neutrino event classifier

International Nuclear Information System (INIS)

Aurisano, A.; Sousa, A.; Radovic, A.; Vahle, P.; Rocco, D.; Pawloski, G.; Himmel, A.; Niner, E.; Messier, M.D.; Psihas, F.

2016-01-01

Convolutional neural networks (CNNs) have been widely applied in the computer vision community to solve complex problems in image recognition and analysis. We describe an application of the CNN technology to the problem of identifying particle interactions in sampling calorimeters used commonly in high energy physics and high energy neutrino physics in particular. Following a discussion of the core concepts of CNNs and recent innovations in CNN architectures related to the field of deep learning, we outline a specific application to the NOvA neutrino detector. This algorithm, CVN (Convolutional Visual Network) identifies neutrino interactions based on their topology without the need for detailed reconstruction and outperforms algorithms currently in use by the NOvA collaboration.

The Discursive Construction of Teachers’ Desirable Identity on a Social Networking Site

Directory of Open Access Journals (Sweden)

Radzuwan Ab Rashid

2016-09-01

Full Text Available This study is situated in the broader identity-construction literature. Bringing discourse community theory to examine teachers’ postings on Facebook Timelines, we explored how teachers discursively construct socially desirable identities to fit into the Timeline community. Data were gathered from the Status updates and Comments on 29 Timelines belonged to Malaysian English language teachers who were purposively chosen as they often posted and commented on teaching-related issues on their Timelines. The analysis shows that the commonest form of identity construction on the teachers’ Timelines was as an engager which had been carefully constructed to portray positive self-image. This paper concludes that when participating on a public networking site, the teachers were being strategic as not to construct identities which could tarnish their professional image.

Ecological risk assessment of hydropower dam construction based on ecological network analysis

OpenAIRE

Chen, Shaoqing; Fath, Brian D.; Chen, Bin

2010-01-01

Dam construction is regarded as one of the major factors contributing to significant modifications of the river ecosystems, and the ecological risk (ER) assessment of dam construction has received growing attention in recent years. In the present study, we explored the potential ecological risk caused by dam project based on the general principles of the ecological risk assessment. Ecological network analysis was proposed as the usable analytic method for the implement of ecological risk asse...

A KST framework for correlation network construction from time series signals

Science.gov (United States)

Qi, Jin-Peng; Gu, Quan; Zhu, Ying; Zhang, Ping

2018-04-01

A KST (Kolmogorov-Smirnov test and T statistic) method is used for construction of a correlation network based on the fluctuation of each time series within the multivariate time signals. In this method, each time series is divided equally into multiple segments, and the maximal data fluctuation in each segment is calculated by a KST change detection procedure. Connections between each time series are derived from the data fluctuation matrix, and are used for construction of the fluctuation correlation network (FCN). The method was tested with synthetic simulations and the result was compared with those from using KS or T only for detection of data fluctuation. The novelty of this study is that the correlation analyses was based on the data fluctuation in each segment of each time series rather than on the original time signals, which would be more meaningful for many real world applications and for analysis of large-scale time signals where prior knowledge is uncertain.

The construction of corporate social responsibility in network societies: A communication view

NARCIS (Netherlands)

Schultz, F.; Castello, I.; Morsing, M.

2013-01-01

The paper introduces the communication view on Corporate Social Responsibility (CSR), which regards CSR as communicatively constructed in dynamic interaction processes in today's networked societies. Building on the idea that communication constitutes organizations we discuss the potentially

Evidence reasoning method for constructing conditional probability tables in a Bayesian network of multimorbidity.

Science.gov (United States)

Du, Yuanwei; Guo, Yubin

2015-01-01

The intrinsic mechanism of multimorbidity is difficult to recognize and prediction and diagnosis are difficult to carry out accordingly. Bayesian networks can help to diagnose multimorbidity in health care, but it is difficult to obtain the conditional probability table (CPT) because of the lack of clinically statistical data. Today, expert knowledge and experience are increasingly used in training Bayesian networks in order to help predict or diagnose diseases, but the CPT in Bayesian networks is usually irrational or ineffective for ignoring realistic constraints especially in multimorbidity. In order to solve these problems, an evidence reasoning (ER) approach is employed to extract and fuse inference data from experts using a belief distribution and recursive ER algorithm, based on which evidence reasoning method for constructing conditional probability tables in Bayesian network of multimorbidity is presented step by step. A multimorbidity numerical example is used to demonstrate the method and prove its feasibility and application. Bayesian network can be determined as long as the inference assessment is inferred by each expert according to his/her knowledge or experience. Our method is more effective than existing methods for extracting expert inference data accurately and is fused effectively for constructing CPTs in a Bayesian network of multimorbidity.

Construction of phylogenetic trees by kernel-based comparative analysis of metabolic networks.

Science.gov (United States)

Oh, S June; Joung, Je-Gun; Chang, Jeong-Ho; Zhang, Byoung-Tak

2006-06-06

To infer the tree of life requires knowledge of the common characteristics of each species descended from a common ancestor as the measuring criteria and a method to calculate the distance between the resulting values of each measure. Conventional phylogenetic analysis based on genomic sequences provides information about the genetic relationships between different organisms. In contrast, comparative analysis of metabolic pathways in different organisms can yield insights into their functional relationships under different physiological conditions. However, evaluating the similarities or differences between metabolic networks is a computationally challenging problem, and systematic methods of doing this are desirable. Here we introduce a graph-kernel method for computing the similarity between metabolic networks in polynomial time, and use it to profile metabolic pathways and to construct phylogenetic trees. To compare the structures of metabolic networks in organisms, we adopted the exponential graph kernel, which is a kernel-based approach with a labeled graph that includes a label matrix and an adjacency matrix. To construct the phylogenetic trees, we used an unweighted pair-group method with arithmetic mean, i.e., a hierarchical clustering algorithm. We applied the kernel-based network profiling method in a comparative analysis of nine carbohydrate metabolic networks from 81 biological species encompassing Archaea, Eukaryota, and Eubacteria. The resulting phylogenetic hierarchies generally support the tripartite scheme of three domains rather than the two domains of prokaryotes and eukaryotes. By combining the kernel machines with metabolic information, the method infers the context of biosphere development that covers physiological events required for adaptation by genetic reconstruction. The results show that one may obtain a global view of the tree of life by comparing the metabolic pathway structures using meta-level information rather than sequence

Construction of phylogenetic trees by kernel-based comparative analysis of metabolic networks

Directory of Open Access Journals (Sweden)

Chang Jeong-Ho

2006-06-01

Full Text Available Abstract Background To infer the tree of life requires knowledge of the common characteristics of each species descended from a common ancestor as the measuring criteria and a method to calculate the distance between the resulting values of each measure. Conventional phylogenetic analysis based on genomic sequences provides information about the genetic relationships between different organisms. In contrast, comparative analysis of metabolic pathways in different organisms can yield insights into their functional relationships under different physiological conditions. However, evaluating the similarities or differences between metabolic networks is a computationally challenging problem, and systematic methods of doing this are desirable. Here we introduce a graph-kernel method for computing the similarity between metabolic networks in polynomial time, and use it to profile metabolic pathways and to construct phylogenetic trees. Results To compare the structures of metabolic networks in organisms, we adopted the exponential graph kernel, which is a kernel-based approach with a labeled graph that includes a label matrix and an adjacency matrix. To construct the phylogenetic trees, we used an unweighted pair-group method with arithmetic mean, i.e., a hierarchical clustering algorithm. We applied the kernel-based network profiling method in a comparative analysis of nine carbohydrate metabolic networks from 81 biological species encompassing Archaea, Eukaryota, and Eubacteria. The resulting phylogenetic hierarchies generally support the tripartite scheme of three domains rather than the two domains of prokaryotes and eukaryotes. Conclusion By combining the kernel machines with metabolic information, the method infers the context of biosphere development that covers physiological events required for adaptation by genetic reconstruction. The results show that one may obtain a global view of the tree of life by comparing the metabolic pathway

Gearbox Condition Monitoring Using Advanced Classifiers

Directory of Open Access Journals (Sweden)

P. Večeř

2010-01-01

Full Text Available New efficient and reliable methods for gearbox diagnostics are needed in automotive industry because of growing demand for production quality. This paper presents the application of two different classifiers for gearbox diagnostics – Kohonen Neural Networks and the Adaptive-Network-based Fuzzy Interface System (ANFIS. Two different practical applications are presented. In the first application, the tested gearboxes are separated into two classes according to their condition indicators. In the second example, ANFIS is applied to label the tested gearboxes with a Quality Index according to the condition indicators. In both applications, the condition indicators were computed from the vibration of the gearbox housing. 

Ensembles of novelty detection classifiers for structural health monitoring using guided waves

Science.gov (United States)

Dib, Gerges; Karpenko, Oleksii; Koricho, Ermias; Khomenko, Anton; Haq, Mahmoodul; Udpa, Lalita

2018-01-01

Guided wave structural health monitoring uses sparse sensor networks embedded in sophisticated structures for defect detection and characterization. The biggest challenge of those sensor networks is developing robust techniques for reliable damage detection under changing environmental and operating conditions (EOC). To address this challenge, we develop a novelty classifier for damage detection based on one class support vector machines. We identify appropriate features for damage detection and introduce a feature aggregation method which quadratically increases the number of available training observations. We adopt a two-level voting scheme by using an ensemble of classifiers and predictions. Each classifier is trained on a different segment of the guided wave signal, and each classifier makes an ensemble of predictions based on a single observation. Using this approach, the classifier can be trained using a small number of baseline signals. We study the performance using Monte-Carlo simulations of an analytical model and data from impact damage experiments on a glass fiber composite plate. We also demonstrate the classifier performance using two types of baseline signals: fixed and rolling baseline training set. The former requires prior knowledge of baseline signals from all EOC, while the latter does not and leverages the fact that EOC vary slowly over time and can be modeled as a Gaussian process.

Diagnosis of Broiler Livers by Classifying Image Patches

DEFF Research Database (Denmark)

Jørgensen, Anders; Fagertun, Jens; Moeslund, Thomas B.

2017-01-01

The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps...

Communication Behaviour-Based Big Data Application to Classify and Detect HTTP Automated Software

Directory of Open Access Journals (Sweden)

Manh Cong Tran

2016-01-01

Full Text Available HTTP is recognized as the most widely used protocol on the Internet when applications are being transferred more and more by developers onto the web. Due to increasingly complex computer systems, diversity HTTP automated software (autoware thrives. Unfortunately, besides normal autoware, HTTP malware and greyware are also spreading rapidly in web environment. Consequently, network communication is not just rigorously controlled by users intention. This raises the demand for analyzing HTTP autoware communication behaviour to detect and classify malicious and normal activities via HTTP traffic. Hence, in this paper, based on many studies and analysis of the autoware communication behaviour through access graph, a new method to detect and classify HTTP autoware communication at network level is presented. The proposal system includes combination of MapReduce of Hadoop and MarkLogic NoSQL database along with xQuery to deal with huge HTTP traffic generated each day in a large network. The method is examined with real outbound HTTP traffic data collected through a proxy server of a private network. Experimental results obtained for proposed method showed that promised outcomes are achieved since 95.1% of suspicious autoware are classified and detected. This finding may assist network and system administrator in inspecting early the internal threats caused by HTTP autoware.

Constructing general partial differential equations using polynomial and neural networks.

Science.gov (United States)

Zjavka, Ladislav; Pedrycz, Witold

2016-01-01

Sum fraction terms can approximate multi-variable functions on the basis of discrete observations, replacing a partial differential equation definition with polynomial elementary data relation descriptions. Artificial neural networks commonly transform the weighted sum of inputs to describe overall similarity relationships of trained and new testing input patterns. Differential polynomial neural networks form a new class of neural networks, which construct and solve an unknown general partial differential equation of a function of interest with selected substitution relative terms using non-linear multi-variable composite polynomials. The layers of the network generate simple and composite relative substitution terms whose convergent series combinations can describe partial dependent derivative changes of the input variables. This regression is based on trained generalized partial derivative data relations, decomposed into a multi-layer polynomial network structure. The sigmoidal function, commonly used as a nonlinear activation of artificial neurons, may transform some polynomial items together with the parameters with the aim to improve the polynomial derivative term series ability to approximate complicated periodic functions, as simple low order polynomials are not able to fully make up for the complete cycles. The similarity analysis facilitates substitutions for differential equations or can form dimensional units from data samples to describe real-world problems. Copyright © 2015 Elsevier Ltd. All rights reserved.

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

Science.gov (United States)

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

2018-04-01

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

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

Directory of Open Access Journals (Sweden)

Dawei Li

2017-01-01

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

Cost-Sensitive Radial Basis Function Neural Network Classifier for Software Defect Prediction.

Science.gov (United States)

Kumudha, P; Venkatesan, R

Effective prediction of software modules, those that are prone to defects, will enable software developers to achieve efficient allocation of resources and to concentrate on quality assurance activities. The process of software development life cycle basically includes design, analysis, implementation, testing, and release phases. Generally, software testing is a critical task in the software development process wherein it is to save time and budget by detecting defects at the earliest and deliver a product without defects to the customers. This testing phase should be carefully operated in an effective manner to release a defect-free (bug-free) software product to the customers. In order to improve the software testing process, fault prediction methods identify the software parts that are more noted to be defect-prone. This paper proposes a prediction approach based on conventional radial basis function neural network (RBFNN) and the novel adaptive dimensional biogeography based optimization (ADBBO) model. The developed ADBBO based RBFNN model is tested with five publicly available datasets from the NASA data program repository. The computed results prove the effectiveness of the proposed ADBBO-RBFNN classifier approach with respect to the considered metrics in comparison with that of the early predictors available in the literature for the same datasets.

Research information network survey of innovative technology for the earth. 2; Chikyu kankyo taisaku gijutsu no kenkyu joho network chosa. 2

Energy Technology Data Exchange (ETDEWEB)

NONE

1997-03-01

In order to construct the information network system for a research of innovative technology for the earth, a prototype has been made. To draw necessary functions for the information network system, an information flow in a general research work is analyzed to classify it based on the functions. The information collecting function, information accumulating and sharing function, special information system for research, information providing function, and communication function of the net work correspond to the collecting information, accumulating information, being engaged in research, providing information, and communication of researcher`s actions, respectively. The services on network system supposed from these functions are the homepage search mailing list, intranet service, special information system for research, WWW Internet broadcasting, and BBS/news/conference tool, respectively. It was found that latest Internet technology enabled to construct easily controlled system environment for users and WWW would develop as a standard communication tool. 2 refs., 26 figs., 27 tabs.

A greedy construction heuristic for the liner service network design problem

DEFF Research Database (Denmark)

Brouer, Berit Dangaard

is challenging due to the size of a global liner shipping operation and due to the hub-and-spoke network design, where a high percentage of the total cargo is transshipped. We present the first construction heuristic for large scale instances of the LSN-DP. The heuristic is able to find a solution for a real...

Bayes classifiers for imbalanced traffic accidents datasets.

Science.gov (United States)

Mujalli, Randa Oqab; López, Griselda; Garach, Laura

2016-03-01

Traffic accidents data sets are usually imbalanced, where the number of instances classified under the killed or severe injuries class (minority) is much lower than those classified under the slight injuries class (majority). This, however, supposes a challenging problem for classification algorithms and may cause obtaining a model that well cover the slight injuries instances whereas the killed or severe injuries instances are misclassified frequently. Based on traffic accidents data collected on urban and suburban roads in Jordan for three years (2009-2011); three different data balancing techniques were used: under-sampling which removes some instances of the majority class, oversampling which creates new instances of the minority class and a mix technique that combines both. In addition, different Bayes classifiers were compared for the different imbalanced and balanced data sets: Averaged One-Dependence Estimators, Weightily Average One-Dependence Estimators, and Bayesian networks in order to identify factors that affect the severity of an accident. The results indicated that using the balanced data sets, especially those created using oversampling techniques, with Bayesian networks improved classifying a traffic accident according to its severity and reduced the misclassification of killed and severe injuries instances. On the other hand, the following variables were found to contribute to the occurrence of a killed causality or a severe injury in a traffic accident: number of vehicles involved, accident pattern, number of directions, accident type, lighting, surface condition, and speed limit. This work, to the knowledge of the authors, is the first that aims at analyzing historical data records for traffic accidents occurring in Jordan and the first to apply balancing techniques to analyze injury severity of traffic accidents. Copyright © 2015 Elsevier Ltd. All rights reserved.

Context-Aware Community Construction in Proximity-Based Mobile Networks

Directory of Open Access Journals (Sweden)

Na Yu

2015-01-01

Full Text Available Sensor-equipped mobile devices have allowed users to participate in various social networking services. We focus on proximity-based mobile social networking environments where users can share information obtained from different places via their mobile devices when they are in proximity. Since people are more likely to share information if they can benefit from the sharing or if they think the information is of interest to others, there might exist community structures where users who share information more often are grouped together. Communities in proximity-based mobile networks represent social groups where connections are built when people are in proximity. We consider information influence (i.e., specify who shares information with whom as the connection and the space and time related to the shared information as the contexts. To model the potential information influences, we construct an influence graph by integrating the space and time contexts into the proximity-based contacts of mobile users. Further, we propose a two-phase strategy to detect and track context-aware communities based on the influence graph and show how the context-aware community structure improves the performance of two types of mobile social applications.

Diagnostic Classifiers: Revealing how Neural Networks Process Hierarchical Structure

NARCIS (Netherlands)

Veldhoen, S.; Hupkes, D.; Zuidema, W.

2016-01-01

We investigate how neural networks can be used for hierarchical, compositional semantics. To this end, we define the simple but nontrivial artificial task of processing nested arithmetic expressions and study whether different types of neural networks can learn to add and subtract. We find that

Use of classifier to determine coffee harvest time by detachment force

Directory of Open Access Journals (Sweden)

Murilo M. de Barros

Full Text Available ABSTRACT Coffee quality is an essential aspect to increase its commercial value and for the Brazilian coffee business to remain prominent in the world market. Fruit maturity stage at harvest is an important factor that affects the quality and commercial value of the product. Therefore, the objective of this study was to develop a classifier using neural networks to distinguish green coffee fruits from mature coffee fruits, based on the detachment force. Fruit detachment force and the percentage value of the maturity stage were measured during a 75-day harvest window. Collections were carried out biweekly, resulting in five different moments within the harvest period. A classifier was developed using neural networks to distinguish green fruits from mature fruits in the harvest period analyzed. The results show that, in the first half of June, the supervised classified had the highest success percentage in differentiating green fruits from mature fruits, and this period was considered as ideal for a selective harvest under these experimental conditions.

Construction and analysis of circular RNA molecular regulatory networks in liver cancer.

Science.gov (United States)

Ren, Shuangchun; Xin, Zhuoyuan; Xu, Yinyan; Xu, Jianting; Wang, Guoqing

2017-01-01

Liver cancer is the sixth most prevalent cancer, and the third most frequent cause of cancer-related deaths. Circular RNAs (circRNAs), a kind of special endogenous ncRNAs, have been coming back to the forefront of cancer genomics research. In this study, we used a systems biology approach to construct and analyze the circRNA molecular regulatory networks in the context of liver cancer. We detected a total of 127 differentially expressed circRNAs and 3,235 differentially expressed mRNAs. We selected the top-5 upregulated circRNAs to construct a circRNA-miRNA-mRNA network. We enriched the pathways and gene ontology items and determined their participation in cancer-related pathways such as p53 signaling pathway and pathways involved in angiogenesis and cell cycle. Quantitative real-time PCR was performed to verify the top-five circRNAs. ROC analysis showed circZFR, circFUT8, circIPO11 could significantly distinguish the cancer samples, with an AUC of 0.7069, 0.7575, and 0.7103, respectively. Our results suggest the circRNA-miRNA-mRNA network may help us further understand the molecular mechanisms of tumor progression in liver cancer, and reveal novel biomarkers and therapeutic targets.

Ship localization in Santa Barbara Channel using machine learning classifiers.

Science.gov (United States)

Niu, Haiqiang; Ozanich, Emma; Gerstoft, Peter

2017-11-01

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

A Bayesian classifier for symbol recognition

OpenAIRE

Barrat , Sabine; Tabbone , Salvatore; Nourrissier , Patrick

2007-01-01

URL : http://www.buyans.com/POL/UploadedFile/134_9977.pdf; International audience; We present in this paper an original adaptation of Bayesian networks to symbol recognition problem. More precisely, a descriptor combination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor, is presented. In this perspective, we use a simple Bayesian classifier, called naive Bayes. In fact, probabilistic graphical models, more spec...

Construction of coffee transcriptome networks based on gene annotation semantics

Directory of Open Access Journals (Sweden)

Castillo Luis F.

2012-12-01

Full Text Available Gene annotation is a process that encompasses multiple approaches on the analysis of nucleic acids or protein sequences in order to assign structural and functional characteristics to gene models. When thousands of gene models are being described in an organism genome, construction and visualization of gene networks impose novel challenges in the understanding of complex expression patterns and the generation of new knowledge in genomics research. In order to take advantage of accumulated text data after conventional gene sequence analysis, this work applied semantics in combination with visualization tools to build transcriptome networks from a set of coffee gene annotations. A set of selected coffee transcriptome sequences, chosen by the quality of the sequence comparison reported by Basic Local Alignment Search Tool (BLAST and Interproscan, were filtered out by coverage, identity, length of the query, and e-values. Meanwhile, term descriptors for molecular biology and biochemistry were obtained along the Wordnet dictionary in order to construct a Resource Description Framework (RDF using Ruby scripts and Methontology to find associations between concepts. Relationships between sequence annotations and semantic concepts were graphically represented through a total of 6845 oriented vectors, which were reduced to 745 non-redundant associations. A large gene network connecting transcripts by way of relational concepts was created where detailed connections remain to be validated for biological significance based on current biochemical and genetics frameworks. Besides reusing text information in the generation of gene connections and for data mining purposes, this tool development opens the possibility to visualize complex and abundant transcriptome data, and triggers the formulation of new hypotheses in metabolic pathways analysis.

Comparison of two neural network classifiers in the differential diagnosis of essential tremor and Parkinson's disease by {sup 123}I-FP-CIT brain SPECT

Energy Technology Data Exchange (ETDEWEB)

Palumbo, Barbara [University of Perugia, Nuclear Medicine Section, Department of Surgical, Radiological and Odontostomatological Sciences, Ospedale S. Maria della Misericordia, Perugia (Italy); Fravolini, Mario Luca [University of Perugia, Department of Electronic and Information Engineering, Perugia (Italy); Nuvoli, Susanna; Spanu, Angela; Madeddu, Giuseppe [University of Sassari, Department of Nuclear Medicine, Sassari (Italy); Paulus, Kai Stephan [University of Sassari, Department of Neurology, Sassari (Italy); Schillaci, Orazio [University Tor Vergata, Department of Biopathology and Diagnostic Imaging, Rome (Italy); IRCSS Neuromed, Pozzilli (Italy)

2010-11-15

To contribute to the differentiation of Parkinson's disease (PD) and essential tremor (ET), we compared two different artificial neural network classifiers using {sup 123}I-FP-CIT SPECT data, a probabilistic neural network (PNN) and a classification tree (ClT). {sup 123}I-FP-CIT brain SPECT with semiquantitative analysis was performed in 216 patients: 89 with ET, 64 with PD with a Hoehn and Yahr (H and Y) score of {<=}2 (early PD), and 63 with PD with a H and Y score of {>=}2.5 (advanced PD). For each of the 1,000 experiments carried out, 108 patients were randomly selected as the PNN training set, while the remaining 108 validated the trained PNN, and the percentage of the validation data correctly classified in the three groups of patients was computed. The expected performance of an ''average performance PNN'' was evaluated. In analogy, for ClT 1,000 classification trees with similar structures were generated. For PNN, the probability of correct classification in patients with early PD was 81.9{+-}8.1% (mean{+-}SD), in patients with advanced PD 78.9{+-}8.1%, and in ET patients 96.6{+-}2.6%. For ClT, the first decision rule gave a mean value for the putamen of 5.99, which resulted in a probability of correct classification of 93.5{+-}3.4%. This means that patients with putamen values >5.99 were classified as having ET, while patients with putamen values <5.99 were classified as having PD. Furthermore, if the caudate nucleus value was higher than 6.97 patients were classified as having early PD (probability 69.8{+-}5.3%), and if the value was <6.97 patients were classified as having advanced PD (probability 88.1%{+-}8.8%). These results confirm that PNN achieved valid classification results. Furthermore, ClT provided reliable cut-off values able to differentiate ET and PD of different severities. (orig.)

A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification

Science.gov (United States)

Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun

2016-01-01

Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

Constructing Better Classifier Ensemble Based on Weighted Accuracy and Diversity Measure

Directory of Open Access Journals (Sweden)

Xiaodong Zeng

2014-01-01

Full Text Available A weighted accuracy and diversity (WAD method is presented, a novel measure used to evaluate the quality of the classifier ensemble, assisting in the ensemble selection task. The proposed measure is motivated by a commonly accepted hypothesis; that is, a robust classifier ensemble should not only be accurate but also different from every other member. In fact, accuracy and diversity are mutual restraint factors; that is, an ensemble with high accuracy may have low diversity, and an overly diverse ensemble may negatively affect accuracy. This study proposes a method to find the balance between accuracy and diversity that enhances the predictive ability of an ensemble for unknown data. The quality assessment for an ensemble is performed such that the final score is achieved by computing the harmonic mean of accuracy and diversity, where two weight parameters are used to balance them. The measure is compared to two representative measures, Kappa-Error and GenDiv, and two threshold measures that consider only accuracy or diversity, with two heuristic search algorithms, genetic algorithm, and forward hill-climbing algorithm, in ensemble selection tasks performed on 15 UCI benchmark datasets. The empirical results demonstrate that the WAD measure is superior to others in most cases.

RRHGE: A Novel Approach to Classify the Estrogen Receptor Based Breast Cancer Subtypes

Directory of Open Access Journals (Sweden)

Ashish Saini

2014-01-01

Full Text Available Background. Breast cancer is the most common type of cancer among females with a high mortality rate. It is essential to classify the estrogen receptor based breast cancer subtypes into correct subclasses, so that the right treatments can be applied to lower the mortality rate. Using gene signatures derived from gene interaction networks to classify breast cancers has proven to be more reproducible and can achieve higher classification performance. However, the interactions in the gene interaction network usually contain many false-positive interactions that do not have any biological meanings. Therefore, it is a challenge to incorporate the reliability assessment of interactions when deriving gene signatures from gene interaction networks. How to effectively extract gene signatures from available resources is critical to the success of cancer classification. Methods. We propose a novel method to measure and extract the reliable (biologically true or valid interactions from gene interaction networks and incorporate the extracted reliable gene interactions into our proposed RRHGE algorithm to identify significant gene signatures from microarray gene expression data for classifying ER+ and ER− breast cancer samples. Results. The evaluation on real breast cancer samples showed that our RRHGE algorithm achieved higher classification accuracy than the existing approaches.

Proposed hybrid-classifier ensemble algorithm to map snow cover area

Science.gov (United States)

Nijhawan, Rahul; Raman, Balasubramanian; Das, Josodhir

2018-01-01

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

Word2Vec inversion and traditional text classifiers for phenotyping lupus.

Science.gov (United States)

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

2017-08-22

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

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

Energy Technology Data Exchange (ETDEWEB)

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

2011-04-15

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

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

International Nuclear Information System (INIS)

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

2011-01-01

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

Classifying objects in LWIR imagery via CNNs

Science.gov (United States)

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

2016-10-01

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

EVALUATING A COMPUTER BASED SKILLS ACQUISITION TRAINER TO CLASSIFY BADMINTON PLAYERS

Directory of Open Access Journals (Sweden)

Minh Vu Huynh

2011-09-01

Full Text Available The aim of the present study was to compare the statistical ability of both neural networks and discriminant function analysis on the newly developed SATB program. Using these statistical tools, we identified the accuracy of the SATB in classifying badminton players into different skill level groups. Forty-one participants, classified as advanced, intermediate, or beginner skilled level, participated in this study. Results indicated neural networks are more effective in predicting group membership, and displayed higher predictive validity when compared to discriminant analysis. Using these outcomes, in conjunction with the physiological and biomechanical variables of the participants, we assessed the authenticity and accuracy of the SATB and commented on the overall effectiveness of the visual based training approach to training badminton athletes

Comparison of classifiers for decoding sensory and cognitive information from prefrontal neuronal populations.

Directory of Open Access Journals (Sweden)

Elaine Astrand

Full Text Available Decoding neuronal information is important in neuroscience, both as a basic means to understand how neuronal activity is related to cerebral function and as a processing stage in driving neuroprosthetic effectors. Here, we compare the readout performance of six commonly used classifiers at decoding two different variables encoded by the spiking activity of the non-human primate frontal eye fields (FEF: the spatial position of a visual cue, and the instructed orientation of the animal's attention. While the first variable is exogenously driven by the environment, the second variable corresponds to the interpretation of the instruction conveyed by the cue; it is endogenously driven and corresponds to the output of internal cognitive operations performed on the visual attributes of the cue. These two variables were decoded using either a regularized optimal linear estimator in its explicit formulation, an optimal linear artificial neural network estimator, a non-linear artificial neural network estimator, a non-linear naïve Bayesian estimator, a non-linear Reservoir recurrent network classifier or a non-linear Support Vector Machine classifier. Our results suggest that endogenous information such as the orientation of attention can be decoded from the FEF with the same accuracy as exogenous visual information. All classifiers did not behave equally in the face of population size and heterogeneity, the available training and testing trials, the subject's behavior and the temporal structure of the variable of interest. In most situations, the regularized optimal linear estimator and the non-linear Support Vector Machine classifiers outperformed the other tested decoders.

Causality in Psychiatry: A Hybrid Symptom Network Construct Model

Directory of Open Access Journals (Sweden)

Gerald eYoung

2015-11-01

Full Text Available Causality or etiology in psychiatry is marked by standard biomedical, reductionistic models (symptoms reflect the construct involved that inform approaches to nosology, or classification, such as in the DSM-5 (Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition; American Psychiatric Association, 2013. However, network approaches to symptom interaction (i.e., symptoms are formative of the construct; e.g., McNally, Robinaugh, Wu, Wang, Deserno, & Borsboom, 2014, for PTSD (posttraumatic stress disorder are being developed that speak to bottom-up processes in mental disorder, in contrast to the typical top-down psychological construct approach. The present article presents a hybrid top-down, bottom-up model of the relationship between symptoms and mental disorder, viewing symptom expression and their causal complex as a reciprocally dynamic system with multiple levels, from lower-order symptoms in interaction to higher-order constructs affecting them. The hybrid model hinges on good understanding of systems theory in which it is embedded, so that the article reviews in depth nonlinear dynamical systems theory (NLDST. The article applies the concept of emergent circular causality (Young, 2011 to symptom development, as well. Conclusions consider that symptoms vary over several dimensions, including: subjectivity; objectivity; conscious motivation effort; and unconscious influences, and the degree to which individual (e.g., meaning and universal (e.g., causal processes are involved. The opposition between science and skepticism is a complex one that the article addresses in final comments.

Use of limited data to construct Bayesian networks for probabilistic risk assessment.

Energy Technology Data Exchange (ETDEWEB)

Groth, Katrina M.; Swiler, Laura Painton

2013-03-01

Probabilistic Risk Assessment (PRA) is a fundamental part of safety/quality assurance for nuclear power and nuclear weapons. Traditional PRA very effectively models complex hardware system risks using binary probabilistic models. However, traditional PRA models are not flexible enough to accommodate non-binary soft-causal factors, such as digital instrumentation&control, passive components, aging, common cause failure, and human errors. Bayesian Networks offer the opportunity to incorporate these risks into the PRA framework. This report describes the results of an early career LDRD project titled %E2%80%9CUse of Limited Data to Construct Bayesian Networks for Probabilistic Risk Assessment%E2%80%9D. The goal of the work was to establish the capability to develop Bayesian Networks from sparse data, and to demonstrate this capability by producing a data-informed Bayesian Network for use in Human Reliability Analysis (HRA) as part of nuclear power plant Probabilistic Risk Assessment (PRA). This report summarizes the research goal and major products of the research.

Linear programming model to construct phylogenetic network for 16S rRNA sequences of photosynthetic organisms and influenza viruses.

Science.gov (United States)

Mathur, Rinku; Adlakha, Neeru

2014-06-01

Phylogenetic trees give the information about the vertical relationships of ancestors and descendants but phylogenetic networks are used to visualize the horizontal relationships among the different organisms. In order to predict reticulate events there is a need to construct phylogenetic networks. Here, a Linear Programming (LP) model has been developed for the construction of phylogenetic network. The model is validated by using data sets of chloroplast of 16S rRNA sequences of photosynthetic organisms and Influenza A/H5N1 viruses. Results obtained are in agreement with those obtained by earlier researchers.

CLASSIFYING BENIGN AND MALIGNANT MASSES USING STATISTICAL MEASURES

Directory of Open Access Journals (Sweden)

B. Surendiran

2011-11-01

Full Text Available Breast cancer is the primary and most common disease found in women which causes second highest rate of death after lung cancer. The digital mammogram is the X-ray of breast captured for the analysis, interpretation and diagnosis. According to Breast Imaging Reporting and Data System (BIRADS benign and malignant can be differentiated using its shape, size and density, which is how radiologist visualize the mammograms. According to BIRADS mass shape characteristics, benign masses tend to have round, oval, lobular in shape and malignant masses are lobular or irregular in shape. Measuring regular and irregular shapes mathematically is found to be a difficult task, since there is no single measure to differentiate various shapes. In this paper, the malignant and benign masses present in mammogram are classified using Hue, Saturation and Value (HSV weight function based statistical measures. The weight function is robust against noise and captures the degree of gray content of the pixel. The statistical measures use gray weight value instead of gray pixel value to effectively discriminate masses. The 233 mammograms from the Digital Database for Screening Mammography (DDSM benchmark dataset have been used. The PASW data mining modeler has been used for constructing Neural Network for identifying importance of statistical measures. Based on the obtained important statistical measure, the C5.0 tree has been constructed with 60-40 data split. The experimental results are found to be encouraging. Also, the results will agree to the standard specified by the American College of Radiology-BIRADS Systems.

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

Directory of Open Access Journals (Sweden)

Mark D McDonnell

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

A neural-fuzzy approach to classify the ecological status in surface waters

International Nuclear Information System (INIS)

Ocampo-Duque, William; Schuhmacher, Marta; Domingo, Jose L.

2007-01-01

A methodology based on a hybrid approach that combines fuzzy inference systems and artificial neural networks has been used to classify ecological status in surface waters. This methodology has been proposed to deal efficiently with the non-linearity and highly subjective nature of variables involved in this serious problem. Ecological status has been assessed with biological, hydro-morphological, and physicochemical indicators. A data set collected from 378 sampling sites in the Ebro river basin has been used to train and validate the hybrid model. Up to 97.6% of sampling sites have been correctly classified with neural-fuzzy models. Such performance resulted very competitive when compared with other classification algorithms. With non-parametric classification-regression trees and probabilistic neural networks, the predictive capacities were 90.7% and 97.0%, respectively. The proposed methodology can support decision-makers in evaluation and classification of ecological status, as required by the EU Water Framework Directive. - Fuzzy inference systems can be used as environmental classifiers

Arabic text classification using Polynomial Networks

Directory of Open Access Journals (Sweden)

Mayy M. Al-Tahrawi

2015-10-01

Full Text Available In this paper, an Arabic statistical learning-based text classification system has been developed using Polynomial Neural Networks. Polynomial Networks have been recently applied to English text classification, but they were never used for Arabic text classification. In this research, we investigate the performance of Polynomial Networks in classifying Arabic texts. Experiments are conducted on a widely used Arabic dataset in text classification: Al-Jazeera News dataset. We chose this dataset to enable direct comparisons of the performance of Polynomial Networks classifier versus other well-known classifiers on this dataset in the literature of Arabic text classification. Results of experiments show that Polynomial Networks classifier is a competitive algorithm to the state-of-the-art ones in the field of Arabic text classification.

Lung Nodule Image Classification Based on Local Difference Pattern and Combined Classifier.

Science.gov (United States)

Mao, Keming; Deng, Zhuofu

2016-01-01

This paper proposes a novel lung nodule classification method for low-dose CT images. The method includes two stages. First, Local Difference Pattern (LDP) is proposed to encode the feature representation, which is extracted by comparing intensity difference along circular regions centered at the lung nodule. Then, the single-center classifier is trained based on LDP. Due to the diversity of feature distribution for different class, the training images are further clustered into multiple cores and the multicenter classifier is constructed. The two classifiers are combined to make the final decision. Experimental results on public dataset show the superior performance of LDP and the combined classifier.

Lung Nodule Image Classification Based on Local Difference Pattern and Combined Classifier

Directory of Open Access Journals (Sweden)

Keming Mao

2016-01-01

Full Text Available This paper proposes a novel lung nodule classification method for low-dose CT images. The method includes two stages. First, Local Difference Pattern (LDP is proposed to encode the feature representation, which is extracted by comparing intensity difference along circular regions centered at the lung nodule. Then, the single-center classifier is trained based on LDP. Due to the diversity of feature distribution for different class, the training images are further clustered into multiple cores and the multicenter classifier is constructed. The two classifiers are combined to make the final decision. Experimental results on public dataset show the superior performance of LDP and the combined classifier.

Pixel Classification of SAR ice images using ANFIS-PSO Classifier

Directory of Open Access Journals (Sweden)

G. Vasumathi

2016-12-01

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

Naïve Bayesian Classifier for Selecting Good/Bad Projects during the Early Stage of International Construction Bidding Decisions

Directory of Open Access Journals (Sweden)

Woosik Jang

2015-01-01

Full Text Available Since the 1970s, revenues generated by Korean contractors in international construction have increased rapidly, exceeding USD 70 billion per year in recent years. However, Korean contractors face significant risks from market uncertainty and sensitivity to economic volatility and technical difficulties. As the volatility of these risks threatens project profitability, approximately 15% of bad projects were found to account for 74% of losses from the same international construction sector. Anticipating bad projects via preemptive risk management can better prevent losses so that contractors can enhance the efficiency of bidding decisions during the early stages of a project cycle. In line with these objectives, this paper examines the effect of such factors on the degree of project profitability. The Naïve Bayesian classifier is applied to identify a good project screening tool, which increases practical applicability using binomial variables with limited information that is obtainable in the early stages. The proposed model produced superior classification results that adequately reflect contractor views of risk. It is anticipated that when users apply the proposed model based on their own knowledge and expertise, overall firm profit rates will increase as a result of early abandonment of bad projects as well as the prioritization of good projects before final bidding decisions are made.

Forecasting Construction Cost Index based on visibility graph: A network approach

Science.gov (United States)

Zhang, Rong; Ashuri, Baabak; Shyr, Yu; Deng, Yong

2018-03-01

Engineering News-Record (ENR), a professional magazine in the field of global construction engineering, publishes Construction Cost Index (CCI) every month. Cost estimators and contractors assess projects, arrange budgets and prepare bids by forecasting CCI. However, fluctuations and uncertainties of CCI cause irrational estimations now and then. This paper aims at achieving more accurate predictions of CCI based on a network approach in which time series is firstly converted into a visibility graph and future values are forecasted relied on link prediction. According to the experimental results, the proposed method shows satisfactory performance since the error measures are acceptable. Compared with other methods, the proposed method is easier to implement and is able to forecast CCI with less errors. It is convinced that the proposed method is efficient to provide considerably accurate CCI predictions, which will make contributions to the construction engineering by assisting individuals and organizations in reducing costs and making project schedules.

Ecological network analysis: network construction

NARCIS (Netherlands)

Fath, B.D.; Scharler, U.M.; Ulanowicz, R.E.; Hannon, B.

2007-01-01

Ecological network analysis (ENA) is a systems-oriented methodology to analyze within system interactions used to identify holistic properties that are otherwise not evident from the direct observations. Like any analysis technique, the accuracy of the results is as good as the data available, but

Construction and evaluation of yeast expression networks by database-guided predictions

Directory of Open Access Journals (Sweden)

Katharina Papsdorf

2016-05-01

Full Text Available DNA-Microarrays are powerful tools to obtain expression data on the genome-wide scale. We performed microarray experiments to elucidate the transcriptional networks, which are up- or down-regulated in response to the expression of toxic polyglutamine proteins in yeast. Such experiments initially generate hit lists containing differentially expressed genes. To look into transcriptional responses, we constructed networks from these genes. We therefore developed an algorithm, which is capable of dealing with very small numbers of microarrays by clustering the hits based on co-regulatory relationships obtained from the SPELL database. Here, we evaluate this algorithm according to several criteria and further develop its statistical capabilities. Initially, we define how the number of SPELL-derived co-regulated genes and the number of input hits influences the quality of the networks. We then show the ability of our networks to accurately predict further differentially expressed genes. Including these predicted genes into the networks improves the network quality and allows quantifying the predictive strength of the networks based on a newly implemented scoring method. We find that this approach is useful for our own experimental data sets and also for many other data sets which we tested from the SPELL microarray database. Furthermore, the clusters obtained by the described algorithm greatly improve the assignment to biological processes and transcription factors for the individual clusters. Thus, the described clustering approach, which will be available through the ClusterEx web interface, and the evaluation parameters derived from it represent valuable tools for the fast and informative analysis of yeast microarray data.

EEG-based motor network biomarkers for identifying target patients with stroke for upper limb rehabilitation and its construct validity.

Directory of Open Access Journals (Sweden)

Chun-Chuan Chen

Full Text Available Rehabilitation is the main therapeutic approach for reducing poststroke functional deficits in the affected upper limb; however, significant between-patient variability in rehabilitation efficacy indicates the need to target patients who are likely to have clinically significant improvement after treatment. Many studies have determined robust predictors of recovery and treatment gains and yielded many great results using linear approachs. Evidence has emerged that the nonlinearity is a crucial aspect to study the inter-areal communication in human brains and abnormality of oscillatory activities in the motor system is linked to the pathological states. In this study, we hypothesized that combinations of linear and nonlinear (cross-frequency network connectivity parameters are favourable biomarkers for stratifying patients for upper limb rehabilitation with increased accuracy. We identified the biomarkers by using 37 prerehabilitation electroencephalogram (EEG datasets during a movement task through effective connectivity and logistic regression analyses. The predictive power of these biomarkers was then tested by using 16 independent datasets (i.e. construct validation. In addition, 14 right handed healthy subjects were also enrolled for comparisons. The result shows that the beta plus gamma or theta network features provided the best classification accuracy of 92%. The predictive value and the sensitivity of these biomarkers were 81.3% and 90.9%, respectively. Subcortical lesion, the time poststroke and initial Wolf Motor Function Test (WMFT score were identified as the most significant clinical variables affecting the classification accuracy of this predictive model. Moreover, 12 of 14 normal controls were classified as having favourable recovery. In conclusion, EEG-based linear and nonlinear motor network biomarkers are robust and can help clinical decision making.

Construction and repair of highly ordered 2D covalent networks by chemical equilibrium regulation.

Science.gov (United States)

Guan, Cui-Zhong; Wang, Dong; Wan, Li-Jun

2012-03-21

The construction of well-ordered 2D covalent networks via the dehydration of di-borate aromatic molecules was successfully realized through introducing a small amount of water into a closed reaction system to regulate the chemical equilibrium.

Construction and analysis of protein-protein interaction networks based on proteomics data of prostate cancer

Science.gov (United States)

CHEN, CHEN; SHEN, HONG; ZHANG, LI-GUO; LIU, JIAN; CAO, XIAO-GE; YAO, AN-LIANG; KANG, SHAO-SAN; GAO, WEI-XING; HAN, HUI; CAO, FENG-HONG; LI, ZHI-GUO

2016-01-01

Currently, using human prostate cancer (PCa) tissue samples to conduct proteomics research has generated a large amount of data; however, only a very small amount has been thoroughly investigated. In this study, we manually carried out the mining of the full text of proteomics literature that involved comparisons between PCa and normal or benign tissue and identified 41 differentially expressed proteins verified or reported more than 2 times from different research studies. We regarded these proteins as seed proteins to construct a protein-protein interaction (PPI) network. The extended network included one giant network, which consisted of 1,264 nodes connected via 1,744 edges, and 3 small separate components. The backbone network was then constructed, which was derived from key nodes and the subnetwork consisting of the shortest path between seed proteins. Topological analyses of these networks were conducted to identify proteins essential for the genesis of PCa. Solute carrier family 2 (facilitated glucose transporter), member 4 (SLC2A4) had the highest closeness centrality located in the center of each network, and the highest betweenness centrality and largest degree in the backbone network. Tubulin, beta 2C (TUBB2C) had the largest degree in the giant network and subnetwork. In addition, using module analysis of the whole PPI network, we obtained a densely connected region. Functional annotation indicated that the Ras protein signal transduction biological process, mitogen-activated protein kinase (MAPK), neurotrophin and the gonadotropin-releasing hormone (GnRH) signaling pathway may play an important role in the genesis and development of PCa. Further investigation of the SLC2A4, TUBB2C proteins, and these biological processes and pathways may therefore provide a potential target for the diagnosis and treatment of PCa. PMID:27121963

The development of natural-draught cooling towers of prestressed wire-rope network construction of aerodynamic design

International Nuclear Information System (INIS)

Braun, R.; Jasch, E.

1975-01-01

Natural-draught cooling towers carried to a height of up to 200 m will be required for the dissipation of the residual heat from the thermal processes of large-capacity power stations to be erected in future. The structural problems involved in such large-size towers can be overcome by using prestressed wire-rope network construction. A structural concept is discussed which proposes to use a cooling tower shell constructed of a prestressed, planked wire-rope network of circular hyperbolic form carried by a spacer ring attached to the central mast. Comments are given on the ensuing problems of aerodynamics, stress-strength assessment, and erection. (orig.) [de

A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping

Directory of Open Access Journals (Sweden)

Marko Scholze

2010-03-01

Full Text Available Satellite remote sensing, with its unique synoptic coverage capabilities, can provide accurate and immediately valuable information on fire analysis and post-fire assessment, including estimation of burnt areas. In this study the potential for burnt area mapping of the combined use of Artificial Neural Network (ANN and Spectral Angle Mapper (SAM classifiers with Landsat TM satellite imagery was evaluated in a Mediterranean setting. As a case study one of the most catastrophic forest fires, which occurred near the capital of Greece during the summer of 2007, was used. The accuracy of the two algorithms in delineating the burnt area from the Landsat TM imagery, acquired shortly after the fire suppression, was determined by the classification accuracy results of the produced thematic maps. In addition, the derived burnt area estimates from the two classifiers were compared with independent estimates available for the study region, obtained from the analysis of higher spatial resolution satellite data. In terms of the overall classification accuracy, ANN outperformed (overall accuracy 90.29%, Kappa coefficient 0.878 the SAM classifier (overall accuracy 83.82%, Kappa coefficient 0.795. Total burnt area estimates from the two classifiers were found also to be in close agreement with the other available estimates for the study region, with a mean absolute percentage difference of ~1% for ANN and ~6.5% for SAM. The study demonstrates the potential of the examined here algorithms in detecting burnt areas in a typical Mediterranean setting.

The Closing of the Classified Catalog at Boston University

Science.gov (United States)

Hazen, Margaret Hindle

1974-01-01

Although the classified catalog at Boston University libraries has been a useful research tool, it has proven too expensive to keep current. The library has converted to a traditional alphabetic subject catalog and will recieve catalog cards from the Ohio College Library Center through the New England Library Network. (Author/LS)

Current Directional Protection of Series Compensated Line Using Intelligent Classifier

Directory of Open Access Journals (Sweden)

M. Mollanezhad Heydarabadi

2016-12-01

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

Constructing a Bayesian network model for improving safety behavior of employees at workplaces.

Science.gov (United States)

Mohammadfam, Iraj; Ghasemi, Fakhradin; Kalatpour, Omid; Moghimbeigi, Abbas

2017-01-01

Unsafe behavior increases the risk of accident at workplaces and needs to be managed properly. The aim of the present study was to provide a model for managing and improving safety behavior of employees using the Bayesian networks approach. The study was conducted in several power plant construction projects in Iran. The data were collected using a questionnaire composed of nine factors, including management commitment, supporting environment, safety management system, employees' participation, safety knowledge, safety attitude, motivation, resource allocation, and work pressure. In order for measuring the score of each factor assigned by a responder, a measurement model was constructed for each of them. The Bayesian network was constructed using experts' opinions and Dempster-Shafer theory. Using belief updating, the best intervention strategies for improving safety behavior also were selected. The result of the present study demonstrated that the majority of employees do not tend to consider safety rules, regulation, procedures and norms in their behavior at the workplace. Safety attitude, safety knowledge, and supporting environment were the best predictor of safety behavior. Moreover, it was determined that instantaneous improvement of supporting environment and employee participation is the best strategy to reach a high proportion of safety behavior at the workplace. The lack of a comprehensive model that can be used for explaining safety behavior was one of the most problematic issues of the study. Furthermore, it can be concluded that belief updating is a unique feature of Bayesian networks that is very useful in comparing various intervention strategies and selecting the best one form them. Copyright © 2016 Elsevier Ltd. All rights reserved.

Comparison of Classifier Architectures for Online Neural Spike Sorting.

Science.gov (United States)

Saeed, Maryam; Khan, Amir Ali; Kamboh, Awais Mehmood

2017-04-01

High-density, intracranial recordings from micro-electrode arrays need to undergo Spike Sorting in order to associate the recorded neuronal spikes to particular neurons. This involves spike detection, feature extraction, and classification. To reduce the data transmission and power requirements, on-chip real-time processing is becoming very popular. However, high computational resources are required for classifiers in on-chip spike-sorters, making scalability a great challenge. In this review paper, we analyze several popular classifiers to propose five new hardware architectures using the off-chip training with on-chip classification approach. These include support vector classification, fuzzy C-means classification, self-organizing maps classification, moving-centroid K-means classification, and Cosine distance classification. The performance of these architectures is analyzed in terms of accuracy and resource requirement. We establish that the neural networks based Self-Organizing Maps classifier offers the most viable solution. A spike sorter based on the Self-Organizing Maps classifier, requires only 7.83% of computational resources of the best-reported spike sorter, hierarchical adaptive means, while offering a 3% better accuracy at 7 dB SNR.

A Time-constrained Network Voronoi Construction and Accessibility Analysis in Location-based Service Technology

Science.gov (United States)

Yu, W.; Ai, T.

2014-11-01

Accessibility analysis usually requires special models of spatial location analysis based on some geometric constructions, such as Voronoi diagram (abbreviated to VD). There are many achievements in classic Voronoi model research, however suffering from the following limitations for location-based services (LBS) applications. (1) It is difficult to objectively reflect the actual service areas of facilities by using traditional planar VDs, because human activities in LBS are usually constrained only to the network portion of the planar space. (2) Although some researchers have adopted network distance to construct VDs, their approaches are used in a static environment, where unrealistic measures of shortest path distance based on assumptions about constant travel speeds through the network were often used. (3) Due to the computational complexity of the shortest-path distance calculating, previous researches tend to be very time consuming, especially for large datasets and if multiple runs are required. To solve the above problems, a novel algorithm is developed in this paper. We apply network-based quadrat system and 1-D sequential expansion to find the corresponding subnetwork for each focus. The idea is inspired by the natural phenomenon that water flow extends along certain linear channels until meets others or arrives at the end of route. In order to accommodate the changes in traffic conditions, the length of network-quadrat is set upon the traffic condition of the corresponding street. The method has the advantage over Dijkstra's algorithm in that the time cost is avoided, and replaced with a linear time operation.

WAVELET ANALYSIS AND NEURAL NETWORK CLASSIFIERS TO DETECT MID-SAGITTAL SECTIONS FOR NUCHAL TRANSLUCENCY MEASUREMENT

Directory of Open Access Journals (Sweden)

Giuseppa Sciortino

2016-04-01

Full Text Available We propose a methodology to support the physician in the automatic identification of mid-sagittal sections of the fetus in ultrasound videos acquired during the first trimester of pregnancy. A good mid-sagittal section is a key requirement to make the correct measurement of nuchal translucency which is one of the main marker for screening of chromosomal defects such as trisomy 13, 18 and 21. NT measurement is beyond the scope of this article. The proposed methodology is mainly based on wavelet analysis and neural network classifiers to detect the jawbone and on radial symmetry analysis to detect the choroid plexus. Those steps allow to identify the frames which represent correct mid-sagittal sections to be processed. The performance of the proposed methodology was analyzed on 3000 random frames uniformly extracted from 10 real clinical ultrasound videos. With respect to a ground-truth provided by an expert physician, we obtained a true positive, a true negative and a balanced accuracy equal to 87.26%, 94.98% and 91.12% respectively.

Deciphering deterioration mechanisms of complex diseases based on the construction of dynamic networks and systems analysis

Science.gov (United States)

Li, Yuanyuan; Jin, Suoqin; Lei, Lei; Pan, Zishu; Zou, Xiufen

2015-03-01

The early diagnosis and investigation of the pathogenic mechanisms of complex diseases are the most challenging problems in the fields of biology and medicine. Network-based systems biology is an important technique for the study of complex diseases. The present study constructed dynamic protein-protein interaction (PPI) networks to identify dynamical network biomarkers (DNBs) and analyze the underlying mechanisms of complex diseases from a systems level. We developed a model-based framework for the construction of a series of time-sequenced networks by integrating high-throughput gene expression data into PPI data. By combining the dynamic networks and molecular modules, we identified significant DNBs for four complex diseases, including influenza caused by either H3N2 or H1N1, acute lung injury and type 2 diabetes mellitus, which can serve as warning signals for disease deterioration. Function and pathway analyses revealed that the identified DNBs were significantly enriched during key events in early disease development. Correlation and information flow analyses revealed that DNBs effectively discriminated between different disease processes and that dysfunctional regulation and disproportional information flow may contribute to the increased disease severity. This study provides a general paradigm for revealing the deterioration mechanisms of complex diseases and offers new insights into their early diagnoses.

A method for classification of network traffic based on C5.0 Machine Learning Algorithm

DEFF Research Database (Denmark)

Bujlow, Tomasz; Riaz, M. Tahir; Pedersen, Jens Myrup

2012-01-01

current network traffic. To overcome the drawbacks of existing methods for traffic classification, usage of C5.0 Machine Learning Algorithm (MLA) was proposed. On the basis of statistical traffic information received from volunteers and C5.0 algorithm we constructed a boosted classifier, which was shown...... and classification, an algorithm for recognizing flow direction and the C5.0 itself. Classified applications include Skype, FTP, torrent, web browser traffic, web radio, interactive gaming and SSH. We performed subsequent tries using different sets of parameters and both training and classification options...

A History of Classified Activities at Oak Ridge National Laboratory

Energy Technology Data Exchange (ETDEWEB)

Quist, A.S.

2001-01-30

The facilities that became Oak Ridge National Laboratory (ORNL) were created in 1943 during the United States' super-secret World War II project to construct an atomic bomb (the Manhattan Project). During World War II and for several years thereafter, essentially all ORNL activities were classified. Now, in 2000, essentially all ORNL activities are unclassified. The major purpose of this report is to provide a brief history of ORNL's major classified activities from 1943 until the present (September 2000). This report is expected to be useful to the ORNL Classification Officer and to ORNL's Authorized Derivative Classifiers and Authorized Derivative Declassifiers in their classification review of ORNL documents, especially those documents that date from the 1940s and 1950s.

Feature weighting using particle swarm optimization for learning vector quantization classifier

Science.gov (United States)

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

2018-03-01

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

Construction of Network Management Information System of Agricultural Products Supply Chain Based on 3PLs

Institute of Scientific and Technical Information of China (English)

2010-01-01

The necessity to construct the network management information system of 3PLs agricultural supply chain is analyzed,showing that 3PLs can improve the overall competitive advantage of agricultural supply chain.3PLs changes the homogeneity management into specialized management of logistics service and achieves the alliance of the subjects at different nodes of agricultural products supply chain.Network management information system structure of agricultural products supply chain based on 3PLs is constructed,including the four layers (the network communication layer,the hardware and software environment layer,the database layer,and the application layer) and 7 function modules (centralized control,transportation process management,material and vehicle scheduling,customer relationship,storage management,customer inquiry,and financial management).Framework for the network management information system of agricultural products supply chain based on 3PLs is put forward.The management of 3PLs mainly includes purchasing management,supplier relationship management,planning management,customer relationship management,storage management and distribution management.Thus,a management system of internal and external integrated agricultural enterprises is obtained.The network management information system of agricultural products supply chain based on 3PLs has realized the effective sharing of enterprise information of agricultural products supply chain at different nodes,establishing a long-term partnership revolving around the 3PLs core enterprise,as well as a supply chain with stable relationship based on the supply chain network system,so as to improve the circulation efficiency of agricultural products,and to explore the sales market for agricultural products.

Classification of Two Comic Books based on Convolutional Neural Networks

Directory of Open Access Journals (Sweden)

Miki UENO

2017-03-01

Full Text Available Unphotographic images are the powerful representations described various situations. Thus, understanding intellectual products such as comics and picture books is one of the important topics in the field of artificial intelligence. Hence, stepwise analysis of a comic story, i.e., features of a part of the image, information features, features relating to continuous scene etc., was pursued. Especially, the length and each scene of four-scene comics are limited so as to ensure a clear interpretation of the contents.In this study, as the first step in this direction, the problem to classify two four-scene comics by the same artists were focused as the example. Several classifiers were constructed by utilizing a Convolutional Neural Network(CNN, and the results of classification by a human annotator and by a computational method were compared.From these experiments, we have clearly shown that CNN is efficient way to classify unphotographic gray scaled images and found that characteristic features of images to classify incorrectly.

Early-life exposure to caffeine affects the construction and activity of cortical networks in mice.

Science.gov (United States)

Fazeli, Walid; Zappettini, Stefania; Marguet, Stephan Lawrence; Grendel, Jasper; Esclapez, Monique; Bernard, Christophe; Isbrandt, Dirk

2017-09-01

The consumption of psychoactive drugs during pregnancy can have deleterious effects on newborns. It remains unclear whether early-life exposure to caffeine, the most widely consumed psychoactive substance, alters brain development. We hypothesized that maternal caffeine ingestion during pregnancy and the early postnatal period in mice affects the construction and activity of cortical networks in offspring. To test this hypothesis, we focused on primary visual cortex (V1) as a model neocortical region. In a study design mimicking the daily consumption of approximately three cups of coffee during pregnancy in humans, caffeine was added to the drinking water of female mice and their offspring were compared to control offspring. Caffeine altered the construction of GABAergic neuronal networks in V1, as reflected by a reduced number of somatostatin-containing GABA neurons at postnatal days 6-7, with the remaining ones showing poorly developed dendritic arbors. These findings were accompanied by increased synaptic activity in vitro and elevated network activity in vivo in V1. Similarly, in vivo hippocampal network activity was altered from the neonatal period until adulthood. Finally, caffeine-exposed offspring showed increased seizure susceptibility in a hyperthermia-induced seizure model. In summary, our results indicate detrimental effects of developmental caffeine exposure on mouse brain development. Copyright © 2017 Elsevier Inc. All rights reserved.

Time-of-flight discrimination between gamma-rays and neutrons by using artificial neural networks

International Nuclear Information System (INIS)

Akkoyun, S.

2013-01-01

Highlights: ► Time-of-flight (tof) is an obvious method for separation between gamma and neutron particles. ► tof distributions are obtained by neural networks. ► Neural network method is consistent with the experimental results. ► Neural networks can classify different events for discrimination. - Abstract: In gamma-ray spectroscopy, a number of neutrons are emitted from the nuclei together with the gamma-rays. These neutrons influence gamma-ray spectra. An obvious method for discrimination between neutrons and gamma-rays is based on the time-of-flight (tof) technique. In this work, the tof distributions of gamma-rays and neutrons were obtained both experimentally and by using artificial neural networks (ANNs). It was shown that, ANN can correctly classify gamma-ray and neutron events. Also, for highly nonlinear detector response for tof, we have constructed consistent empirical physical formulas (EPFs) by appropriate ANNs. These ANN–EPFs can be used to derive further physical functions which could be relevant to discrimination between gamma-rays and neutrons

Seeded Bayesian Networks: Constructing genetic networks from microarray data

Directory of Open Access Journals (Sweden)

Quackenbush John

2008-07-01

Full Text Available Abstract Background DNA microarrays and other genomics-inspired technologies provide large datasets that often include hidden patterns of correlation between genes reflecting the complex processes that underlie cellular metabolism and physiology. The challenge in analyzing large-scale expression data has been to extract biologically meaningful inferences regarding these processes – often represented as networks – in an environment where the datasets are often imperfect and biological noise can obscure the actual signal. Although many techniques have been developed in an attempt to address these issues, to date their ability to extract meaningful and predictive network relationships has been limited. Here we describe a method that draws on prior information about gene-gene interactions to infer biologically relevant pathways from microarray data. Our approach consists of using preliminary networks derived from the literature and/or protein-protein interaction data as seeds for a Bayesian network analysis of microarray results. Results Through a bootstrap analysis of gene expression data derived from a number of leukemia studies, we demonstrate that seeded Bayesian Networks have the ability to identify high-confidence gene-gene interactions which can then be validated by comparison to other sources of pathway data. Conclusion The use of network seeds greatly improves the ability of Bayesian Network analysis to learn gene interaction networks from gene expression data. We demonstrate that the use of seeds derived from the biomedical literature or high-throughput protein-protein interaction data, or the combination, provides improvement over a standard Bayesian Network analysis, allowing networks involving dynamic processes to be deduced from the static snapshots of biological systems that represent the most common source of microarray data. Software implementing these methods has been included in the widely used TM4 microarray analysis package.

Tight bounds on the size of neural networks for classification problems

Energy Technology Data Exchange (ETDEWEB)

Beiu, V. [Los Alamos National Lab., NM (United States); Pauw, T. de [Universite Catholique de Louvain, Louvain-la-Neuve (Belgium). Dept. de Mathematique

1997-06-01

This paper relies on the entropy of a data-set (i.e., number-of-bits) to prove tight bounds on the size of neural networks solving a classification problem. First, based on a sequence of geometrical steps, the authors constructively compute an upper bound of O(mn) on the number-of-bits for a given data-set - here m is the number of examples and n is the number of dimensions (i.e., R{sup n}). This result is used further in a nonconstructive way to bound the size of neural networks which correctly classify that data-set.

Research on Risk Manage of Power Construction Project Based on Bayesian Network

Science.gov (United States)

Jia, Zhengyuan; Fan, Zhou; Li, Yong

With China's changing economic structure and increasingly fierce competition in the market, the uncertainty and risk factors in the projects of electric power construction are increasingly complex, the projects will face huge risks or even fail if we don't consider or ignore these risk factors. Therefore, risk management in the projects of electric power construction plays an important role. The paper emphatically elaborated the influence of cost risk in electric power projects through study overall risk management and the behavior of individual in risk management, and introduced the Bayesian network to the project risk management. The paper obtained the order of key factors according to both scene analysis and causal analysis for effective risk management.

Discussion on the nuclear information resources co-constructing and sharing under network information

International Nuclear Information System (INIS)

Wu Yang

2010-01-01

During the tenth five-year plan, along with the digitization of information, and the development of information transmission network, the co-construction and sharing of China's nuclear industry information is facing a new development opportunities and challenges. This paper is based on the analysis of the nuclear library status and characteristics, combined of the development process of nuclear information resources over the past 20 years. For the characteristic of information sharing and services in the net environment, the problem in the current co-construction and sharing of nuclear information, and the needs of the future nuclear research and development of nuclear production, this paper forecast the work trends of nuclear information, and gives some countermeasure to strength the development of the co-construction and sharing of nuclear information. (author)

cooccurNet: an R package for co-occurrence network construction and analysis.

Science.gov (United States)

Zou, Yuanqiang; Wu, Zhiqiang; Deng, Lizong; Wu, Aiping; Wu, Fan; Li, Kenli; Jiang, Taijiao; Peng, Yousong

2017-06-15

Previously, we developed a computational model to identify genomic co-occurrence networks that was applied to capture the coevolution patterns within genomes of influenza viruses. To facilitate easy public use of this model, an R package 'cooccurNet' is presented here. 'cooccurNet' includes functionalities of construction and analysis of residues (e.g. nucleotides, amino acids and SNPs) co-occurrence network. In addition, a new method for measuring residues coevolution, defined as residue co-occurrence score (RCOS), is proposed and implemented in 'cooccurNet' based on the co-occurrence network. 'cooccurNet' is publicly available on CRAN repositories under the GPL-3 Open Source License ( http://cran.r-project.org/package=cooccurNet ). taijiao@ibms.pumc.edu.cn or pys2013@hnu.edu.cn. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Perspectives of construction robots

Science.gov (United States)

Stepanov, M. A.; Gridchin, A. M.

2018-03-01

This article is an overview of construction robots features, based on formulating the list of requirements for different types of construction robots in relation to different types of construction works.. It describes a variety of construction works and ways to construct new or to adapt existing robot designs for a construction process. Also, it shows the prospects of AI-controlled machines, implementation of automated control systems and networks on construction sites. In the end, different ways to develop and improve, including ecological aspect, the construction process through the wide robotization, creating of data communication networks and, in perspective, establishing of fully AI-controlled construction complex are formulated.

Visual Representations of Microcosm in Textbooks of Chemistry: Constructing a Systemic Network for Their Main Conceptual Framework

Science.gov (United States)

Papageorgiou, George; Amariotakis, Vasilios; Spiliotopoulou, Vasiliki

2017-01-01

The main objective of this work is to analyse the visual representations (VRs) of the microcosm depicted in nine Greek secondary chemistry school textbooks of the last three decades in order to construct a systemic network for their main conceptual framework and to evaluate the contribution of each one of the resulting categories to the network.…

A construct-network approach to bridging diagnostic and physiological domains: application to assessment of externalizing psychopathology.

Science.gov (United States)

Patrick, Christopher J; Venables, Noah C; Yancey, James R; Hicks, Brian M; Nelson, Lindsay D; Kramer, Mark D

2013-08-01

A crucial challenge in efforts to link psychological disorders to neural systems, with the aim of developing biologically informed conceptions of such disorders, is the problem of method variance (Campbell & Fiske, 1959). Since even measures of the same construct in differing domains correlate only moderately, it is unsurprising that large sample studies of diagnostic biomarkers yield only modest associations. To address this challenge, a construct-network approach is proposed in which psychometric operationalizations of key neurobehavioral constructs serve as anchors for identifying neural indicators of psychopathology-relevant dispositions, and as vehicles for bridging between domains of clinical problems and neurophysiology. An empirical illustration is provided for the construct of inhibition-disinhibition, which is of central relevance to problems entailing deficient impulse control. Findings demonstrate that: (1) a well-designed psychometric index of trait disinhibition effectively predicts externalizing problems of multiple types, (2) this psychometric measure of disinhibition shows reliable brain response correlates, and (3) psychometric and brain-response indicators can be combined to form a joint psychoneurometric factor that predicts effectively across clinical and physiological domains. As a methodology for bridging between clinical problems and neural systems, the construct-network approach provides a concrete means by which existing conceptions of psychological disorders can accommodate and be reshaped by neurobiological insights. PsycINFO Database Record (c) 2013 APA, all rights reserved.

Hash function construction using weighted complex dynamical networks

International Nuclear Information System (INIS)

Song Yu-Rong; Jiang Guo-Ping

2013-01-01

A novel scheme to construct a hash function based on a weighted complex dynamical network (WCDN) generated from an original message is proposed in this paper. First, the original message is divided into blocks. Then, each block is divided into components, and the nodes and weighted edges are well defined from these components and their relations. Namely, the WCDN closely related to the original message is established. Furthermore, the node dynamics of the WCDN are chosen as a chaotic map. After chaotic iterations, quantization and exclusive-or operations, the fixed-length hash value is obtained. This scheme has the property that any tiny change in message can be diffused rapidly through the WCDN, leading to very different hash values. Analysis and simulation show that the scheme possesses good statistical properties, excellent confusion and diffusion, strong collision resistance and high efficiency. (general)

Wavelet classifier used for diagnosing shock absorbers in cars

Directory of Open Access Journals (Sweden)

Janusz GARDULSKI

2007-01-01

Full Text Available The paper discusses some commonly used methods of hydraulic absorbertesting. Disadvantages of the methods are described. A vibro-acoustic method is presented and recommended for practical use on existing test rigs. The method is based on continuous wavelet analysis combined with neural classifier and 25-neuron, one-way, three-layer back propagation network. The analysis satisfies the intended aim.

Validating User Flows to Protect Software Defined Network Environments

Directory of Open Access Journals (Sweden)

Ihsan H. Abdulqadder

2018-01-01

Full Text Available Software Defined Network is a promising network paradigm which has led to several security threats in SDN applications that involve user flows, switches, and controllers in the network. Threats as spoofing, tampering, information disclosure, Denial of Service, flow table overloading, and so on have been addressed by many researchers. In this paper, we present novel SDN design to solve three security threats: flow table overloading is solved by constructing a star topology-based architecture, unsupervised hashing method mitigates link spoofing attack, and fuzzy classifier combined with L1-ELM running on a neural network for isolating anomaly packets from normal packets. For effective flow migration Discrete-Time Finite-State Markov Chain model is applied. Extensive simulations using OMNeT++ demonstrate the performance of our proposed approach, which is better at preserving holding time than are other state-of-the-art works from the literature.

The construction of a public key infrastructure for healthcare information networks in Japan.

Science.gov (United States)

Sakamoto, N

2001-01-01

The digital signature is a key technology in the forthcoming Internet society for electronic healthcare as well as for electronic commerce. Efficient exchanges of authorized information with a digital signature in healthcare information networks require a construction of a public key infrastructure (PKI). In order to introduce a PKI to healthcare information networks in Japan, we proposed a development of a user authentication system based on a PKI for user management, user authentication and privilege management of healthcare information systems. In this paper, we describe the design of the user authentication system and its implementation. The user authentication system provides a certification authority service and a privilege management service while it is comprised of a user authentication client and user authentication serves. It is designed on a basis of an X.509 PKI and is implemented with using OpenSSL and OpenLDAP. It was incorporated into the financial information management system for the national university hospitals and has been successfully working for about one year. The hospitals plan to use it as a user authentication method for their whole healthcare information systems. One implementation of the system is free to the national university hospitals with permission of the Japanese Ministry of Education, Culture, Sports, Science and Technology. Another implementation is open to the other healthcare institutes by support of the Medical Information System Development Center (MEDIS-DC). We are moving forward to a nation-wide construction of a PKI for healthcare information networks based on it.

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

Science.gov (United States)

He, Jian; Bai, Shuang; Wang, Xiaoyi

2017-06-16

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

Classifying Microorganisms

DEFF Research Database (Denmark)

Sommerlund, Julie

2006-01-01

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

SNRFCB: sub-network based random forest classifier for predicting chemotherapy benefit on survival for cancer treatment.

Science.gov (United States)

Shi, Mingguang; He, Jianmin

2016-04-01

Adjuvant chemotherapy (CTX) should be individualized to provide potential survival benefit and avoid potential harm to cancer patients. Our goal was to establish a computational approach for making personalized estimates of the survival benefit from adjuvant CTX. We developed Sub-Network based Random Forest classifier for predicting Chemotherapy Benefit (SNRFCB) based gene expression datasets of lung cancer. The SNRFCB approach was then validated in independent test cohorts for identifying chemotherapy responder cohorts and chemotherapy non-responder cohorts. SNRFCB involved the pre-selection of gene sub-network signatures based on the mutations and on protein-protein interaction data as well as the application of the random forest algorithm to gene expression datasets. Adjuvant CTX was significantly associated with the prolonged overall survival of lung cancer patients in the chemotherapy responder group (P = 0.008), but it was not beneficial to patients in the chemotherapy non-responder group (P = 0.657). Adjuvant CTX was significantly associated with the prolonged overall survival of lung cancer squamous cell carcinoma (SQCC) subtype patients in the chemotherapy responder cohorts (P = 0.024), but it was not beneficial to patients in the chemotherapy non-responder cohorts (P = 0.383). SNRFCB improved prediction performance as compared to the machine learning method, support vector machine (SVM). To test the general applicability of the predictive model, we further applied the SNRFCB approach to human breast cancer datasets and also observed superior performance. SNRFCB could provide recurrent probability for individual patients and identify which patients may benefit from adjuvant CTX in clinical trials.

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

Science.gov (United States)

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

2017-01-01

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

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

Directory of Open Access Journals (Sweden)

C. V. Subbulakshmi

2015-01-01

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

Using SAR images to delineate ocean oil slicks with a texture-classifying neural network algorithm (TCNNA)

Energy Technology Data Exchange (ETDEWEB)

Garcia-Pineda, O.; MacDonald, I.R. [Florida State Univ., Tallahassee, FL (United States). Dept. of Oceanography; Zimmer, B. [Texas A and M Univ., Corpus Christi, TX (United States). Dept. of Mathematics and Statistics; Howard, M. [Texas A and M Univ., College Station, TX (United States). Dept. of Oceanography; Pichel, W. [National Oceanic and Atmospheric Administration, Camp Springs, MD (United States). Center for Satellite Applications and Research, National Environmental Satellite, Data and Information Service; Li, X. [National Oceanic and Atmospheric Administration, Camp Springs, MD (United States). Systems Group, National Environmental Satellite, Data and Information

2009-10-15

Synthetic aperture radar (SAR) is used to detect surfactant layers produced by floating oil on the ocean surface. This study presented details of a texture-classifying neural network algorithm (TCNNA) designed to process SAR data from a wide selection of beam modes. Patterns from SAR imagery were extracted in a semi-supervised procedure using a combination of edge-detection filters; texture descriptors; collection information; and environmental data. Various natural oil seeps in the Gulf of Mexico were used as case studies. An analysis of the case studies demonstrated that the TCNNA was able to extract targets and rapidly interpret images collected under a range of environmental conditions. Results presented by the TCNNA were used to evaluate the effects of different environmental conditions on the expressions of oil slicks detected by the data. Optimal incidence angle ranges and wind speed ranges for surfactant film detection were also presented. Results obtained by the TCNNA can be stored and manipulated in geographic information system (GIS) data layers. 26 refs., 1 tab., 7 figs.

A ternary logic model for recurrent neuromime networks with delay.

Science.gov (United States)

Hangartner, R D; Cull, P

1995-07-01

In contrast to popular recurrent artificial neural network (RANN) models, biological neural networks have unsymmetric structures and incorporate significant delays as a result of axonal propagation. Consequently, biologically inspired neural network models are more accurately described by nonlinear differential-delay equations rather than nonlinear ordinary differential equations (ODEs), and the standard techniques for studying the dynamics of RANNs are wholly inadequate for these models. This paper develops a ternary-logic based method for analyzing these networks. Key to the technique is the realization that a nonzero delay produces a bounded stability region. This result significantly simplifies the construction of sufficient conditions for characterizing the network equilibria. If the network gain is large enough, each equilibrium can be classified as either asymptotically stable or unstable. To illustrate the analysis technique, the swim central pattern generator (CPG) of the sea slug Tritonia diomedea is examined. For wide range of reasonable parameter values, the ternary analysis shows that none of the network equilibria are stable, and thus the network must oscillate. The results show that complex synaptic dynamics are not necessary for pattern generation.

Design and Construction of a High-speed Network Connecting All the Protein Crystallography Beamlines at the Photon Factory

International Nuclear Information System (INIS)

Matsugaki, Naohiro; Yamada, Yusuke; Igarashi, Noriyuki; Wakatsuki, Soichi

2007-01-01

A private network, physically separated from the facility network, was designed and constructed which covered all the four protein crystallography beamlines at the Photon Factory (PF) and Structural Biology Research Center (SBRC). Connecting all the beamlines in the same network allows for simple authentication and a common working environment for a user who uses multiple beamlines. Giga-bit Ethernet wire-speed was achieved for the communication among the beamlines and SBRC buildings

Maximum margin classifier working in a set of strings.

Science.gov (United States)

Koyano, Hitoshi; Hayashida, Morihiro; Akutsu, Tatsuya

2016-03-01

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

Neural network segmentation of magnetic resonance images

International Nuclear Information System (INIS)

Frederick, B.

1990-01-01

Neural networks are well adapted to the task of grouping input patterns into subsets which share some similarity. Moreover, once trained, they can generalize their classification rules to classify new data sets. Sets of pixel intensities from magnetic resonance (MR) images provide a natural input to a neural network; by varying imaging parameters, MR images can reflect various independent physical parameters of tissues in their pixel intensities. A neural net can then be trained to classify physically similar tissue types based on sets of pixel intensities resulting from different imaging studies on the same subject. This paper reports that a neural network classifier for image segmentation was implanted on a Sun 4/60, and was tested on the task of classifying tissues of canine head MR images. Four images of a transaxial slice with different imaging sequences were taken as input to the network (three spin-echo images and an inversion recovery image). The training set consisted of 691 representative samples of gray matter, white matter, cerebrospinal fluid, bone, and muscle preclassified by a neuroscientist. The network was trained using a fast backpropagation algorithm to derive the decision criteria to classify any location in the image by its pixel intensities, and the image was subsequently segmented by the classifier

Comparison of Two Classifiers; K-Nearest Neighbor and Artificial Neural Network, for Fault Diagnosis on a Main Engine Journal-Bearing

Directory of Open Access Journals (Sweden)

A. Moosavian

2013-01-01

Full Text Available Vibration analysis is an accepted method in condition monitoring of machines, since it can provide useful and reliable information about machine working condition. This paper surveys a new scheme for fault diagnosis of main journal-bearings of internal combustion (IC engine based on power spectral density (PSD technique and two classifiers, namely, K-nearest neighbor (KNN and artificial neural network (ANN. Vibration signals for three different conditions of journal-bearing; normal, with oil starvation condition and extreme wear fault were acquired from an IC engine. PSD was applied to process the vibration signals. Thirty features were extracted from the PSD values of signals as a feature source for fault diagnosis. KNN and ANN were trained by training data set and then used as diagnostic classifiers. Variable K value and hidden neuron count (N were used in the range of 1 to 20, with a step size of 1 for KNN and ANN to gain the best classification results. The roles of PSD, KNN and ANN techniques were studied. From the results, it is shown that the performance of ANN is better than KNN. The experimental results dèmonstrate that the proposed diagnostic method can reliably separate different fault conditions in main journal-bearings of IC engine.

Spatial Models and Networks of Living Systems

DEFF Research Database (Denmark)

Juul, Jeppe Søgaard

When studying the dynamics of living systems, insight can often be gained by developing a mathematical model that can predict future behaviour of the system or help classify system characteristics. However, in living cells, organisms, and especially groups of interacting individuals, a large number...... variables of the system. However, this approach disregards any spatial structure of the system, which may potentially change the behaviour drastically. An alternative approach is to construct a cellular automaton with nearest neighbour interactions, or even to model the system as a complex network...... with interactions defined by network topology. In this thesis I first describe three different biological models of ageing and cancer, in which spatial structure is important for the system dynamics. I then turn to describe characteristics of ecosystems consisting of three cyclically interacting species...

A Poisson Log-Normal Model for Constructing Gene Covariation Network Using RNA-seq Data.

Science.gov (United States)

Choi, Yoonha; Coram, Marc; Peng, Jie; Tang, Hua

2017-07-01

Constructing expression networks using transcriptomic data is an effective approach for studying gene regulation. A popular approach for constructing such a network is based on the Gaussian graphical model (GGM), in which an edge between a pair of genes indicates that the expression levels of these two genes are conditionally dependent, given the expression levels of all other genes. However, GGMs are not appropriate for non-Gaussian data, such as those generated in RNA-seq experiments. We propose a novel statistical framework that maximizes a penalized likelihood, in which the observed count data follow a Poisson log-normal distribution. To overcome the computational challenges, we use Laplace's method to approximate the likelihood and its gradients, and apply the alternating directions method of multipliers to find the penalized maximum likelihood estimates. The proposed method is evaluated and compared with GGMs using both simulated and real RNA-seq data. The proposed method shows improved performance in detecting edges that represent covarying pairs of genes, particularly for edges connecting low-abundant genes and edges around regulatory hubs.

The complex network of global cargo ship movements.

Science.gov (United States)

Kaluza, Pablo; Kölzsch, Andrea; Gastner, Michael T; Blasius, Bernd

2010-07-06

Transportation networks play a crucial role in human mobility, the exchange of goods and the spread of invasive species. With 90 per cent of world trade carried by sea, the global network of merchant ships provides one of the most important modes of transportation. Here, we use information about the itineraries of 16 363 cargo ships during the year 2007 to construct a network of links between ports. We show that the network has several features that set it apart from other transportation networks. In particular, most ships can be classified into three categories: bulk dry carriers, container ships and oil tankers. These three categories do not only differ in the ships' physical characteristics, but also in their mobility patterns and networks. Container ships follow regularly repeating paths whereas bulk dry carriers and oil tankers move less predictably between ports. The network of all ship movements possesses a heavy-tailed distribution for the connectivity of ports and for the loads transported on the links with systematic differences between ship types. The data analysed in this paper improve current assumptions based on gravity models of ship movements, an important step towards understanding patterns of global trade and bioinvasion.

Cubical sets as a classifying topos

DEFF Research Database (Denmark)

Spitters, Bas

Coquand’s cubical set model for homotopy type theory provides the basis for a computational interpretation of the univalence axiom and some higher inductive types, as implemented in the cubical proof assistant. We show that the underlying cube category is the opposite of the Lawvere theory of De...... Morgan algebras. The topos of cubical sets itself classifies the theory of ‘free De Morgan algebras’. This provides us with a topos with an internal ‘interval’. Using this interval we construct a model of type theory following van den Berg and Garner. We are currently investigating the precise relation...

Entropy based classifier for cross-domain opinion mining

Directory of Open Access Journals (Sweden)

Jyoti S. Deshmukh

2018-01-01

Full Text Available In recent years, the growth of social network has increased the interest of people in analyzing reviews and opinions for products before they buy them. Consequently, this has given rise to the domain adaptation as a prominent area of research in sentiment analysis. A classifier trained from one domain often gives poor results on data from another domain. Expression of sentiment is different in every domain. The labeling cost of each domain separately is very high as well as time consuming. Therefore, this study has proposed an approach that extracts and classifies opinion words from one domain called source domain and predicts opinion words of another domain called target domain using a semi-supervised approach, which combines modified maximum entropy and bipartite graph clustering. A comparison of opinion classification on reviews on four different product domains is presented. The results demonstrate that the proposed method performs relatively well in comparison to the other methods. Comparison of SentiWordNet of domain-specific and domain-independent words reveals that on an average 72.6% and 88.4% words, respectively, are correctly classified.

Autonomous construction agents: An investigative framework for large sensor network self-management

Energy Technology Data Exchange (ETDEWEB)

Koch, Joshua Bruce [Iowa State Univ., Ames, IA (United States)

2008-01-01

Recent technological advances have made it cost effective to utilize massive, heterogeneous sensor networks. To gain appreciable value from these informational systems, there must be a control scheme that coordinates information flow to produce meaningful results. This paper will focus on tools developed to manage the coordination of autonomous construction agents using stigmergy, in which a set of basic low-level rules are implemented through various environmental cues. Using VE-Suite, an open-source virtual engineering software package, an interactive environment is created to explore various informational configurations for the construction problem. A simple test case is developed within the framework, and construction times are analyzed for possible functional relationships pertaining to performance of a particular set of parameters and a given control process. Initial experiments for the test case show sensor saturation occurs relatively quickly with 5-7 sensors, and construction time is generally independent of sensor range except for small numbers of sensors. Further experiments using this framework are needed to define other aspects of sensor performance. These trends can then be used to help decide what kinds of sensing capabilities are required to simultaneously achieve the most cost-effective solution and provide the required value of information when applied to the development of real world sensor applications.

Construction of an integrated gene regulatory network link to stress-related immune system in cattle.

Science.gov (United States)

Behdani, Elham; Bakhtiarizadeh, Mohammad Reza

2017-10-01

The immune system is an important biological system that is negatively impacted by stress. This study constructed an integrated regulatory network to enhance our understanding of the regulatory gene network used in the stress-related immune system. Module inference was used to construct modules of co-expressed genes with bovine leukocyte RNA-Seq data. Transcription factors (TFs) were then assigned to these modules using Lemon-Tree algorithms. In addition, the TFs assigned to each module were confirmed using the promoter analysis and protein-protein interactions data. Therefore, our integrated method identified three TFs which include one TF that is previously known to be involved in immune response (MYBL2) and two TFs (E2F8 and FOXS1) that had not been recognized previously and were identified for the first time in this study as novel regulatory candidates in immune response. This study provides valuable insights on the regulatory programs of genes involved in the stress-related immune system.

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

Science.gov (United States)

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

2018-06-01

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

Matching Matched Filtering with Deep Networks for Gravitational-Wave Astronomy

Science.gov (United States)

Gabbard, Hunter; Williams, Michael; Hayes, Fergus; Messenger, Chris

2018-04-01

We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals. The standard method for the detection of well-modeled transient gravitational-wave signals is matched filtering. We use only whitened time series of measured gravitational-wave strain as an input, and we train and test on simulated binary black hole signals in synthetic Gaussian noise representative of Advanced LIGO sensitivity. We show that our network can classify signal from noise with a performance that emulates that of match filtering applied to the same data sets when considering the sensitivity defined by receiver-operator characteristics.

Matching Matched Filtering with Deep Networks for Gravitational-Wave Astronomy.

Science.gov (United States)

Gabbard, Hunter; Williams, Michael; Hayes, Fergus; Messenger, Chris

2018-04-06

We report on the construction of a deep convolutional neural network that can reproduce the sensitivity of a matched-filtering search for binary black hole gravitational-wave signals. The standard method for the detection of well-modeled transient gravitational-wave signals is matched filtering. We use only whitened time series of measured gravitational-wave strain as an input, and we train and test on simulated binary black hole signals in synthetic Gaussian noise representative of Advanced LIGO sensitivity. We show that our network can classify signal from noise with a performance that emulates that of match filtering applied to the same data sets when considering the sensitivity defined by receiver-operator characteristics.

Multi-objective evolutionary optimization for constructing neural networks for virtual reality visual data mining: application to geophysical prospecting.

Science.gov (United States)

Valdés, Julio J; Barton, Alan J

2007-05-01

A method for the construction of virtual reality spaces for visual data mining using multi-objective optimization with genetic algorithms on nonlinear discriminant (NDA) neural networks is presented. Two neural network layers (the output and the last hidden) are used for the construction of simultaneous solutions for: (i) a supervised classification of data patterns and (ii) an unsupervised similarity structure preservation between the original data matrix and its image in the new space. A set of spaces are constructed from selected solutions along the Pareto front. This strategy represents a conceptual improvement over spaces computed by single-objective optimization. In addition, genetic programming (in particular gene expression programming) is used for finding analytic representations of the complex mappings generating the spaces (a composition of NDA and orthogonal principal components). The presented approach is domain independent and is illustrated via application to the geophysical prospecting of caves.

A dynamic Bayesian network based approach to safety decision support in tunnel construction

International Nuclear Information System (INIS)

Wu, Xianguo; Liu, Huitao; Zhang, Limao; Skibniewski, Miroslaw J.; Deng, Qianli; Teng, Jiaying

2015-01-01

This paper presents a systemic decision approach with step-by-step procedures based on dynamic Bayesian network (DBN), aiming to provide guidelines for dynamic safety analysis of the tunnel-induced road surface damage over time. The proposed DBN-based approach can accurately illustrate the dynamic and updated feature of geological, design and mechanical variables as the construction progress evolves, in order to overcome deficiencies of traditional fault analysis methods. Adopting the predictive, sensitivity and diagnostic analysis techniques in the DBN inference, this approach is able to perform feed-forward, concurrent and back-forward control respectively on a quantitative basis, and provide real-time support before and after an accident. A case study in relating to dynamic safety analysis in the construction of Wuhan Yangtze Metro Tunnel in China is used to verify the feasibility of the proposed approach, as well as its application potential. The relationships between the DBN-based and BN-based approaches are further discussed according to analysis results. The proposed approach can be used as a decision tool to provide support for safety analysis in tunnel construction, and thus increase the likelihood of a successful project in a dynamic project environment. - Highlights: • A dynamic Bayesian network (DBN) based approach for safety decision support is developed. • This approach is able to perform feed-forward, concurrent and back-forward analysis and control. • A case concerning dynamic safety analysis in Wuhan Yangtze Metro Tunnel in China is presented. • DBN-based approach can perform a higher accuracy than traditional static BN-based approach

Dual Cross-Linked Biofunctional and Self-Healing Networks to Generate User-Defined Modular Gradient Hydrogel Constructs.

Science.gov (United States)

Wei, Zhao; Lewis, Daniel M; Xu, Yu; Gerecht, Sharon

2017-08-01

Gradient hydrogels have been developed to mimic the spatiotemporal differences of multiple gradient cues in tissues. Current approaches used to generate such hydrogels are restricted to a single gradient shape and distribution. Here, a hydrogel is designed that includes two chemical cross-linking networks, biofunctional, and self-healing networks, enabling the customizable formation of modular gradient hydrogel construct with various gradient distributions and flexible shapes. The biofunctional networks are formed via Michael addition between the acrylates of oxidized acrylated hyaluronic acid (OAHA) and the dithiol of matrix metalloproteinase (MMP)-sensitive cross-linker and RGD peptides. The self-healing networks are formed via dynamic Schiff base reaction between N-carboxyethyl chitosan (CEC) and OAHA, which drives the modular gradient units to self-heal into an integral modular gradient hydrogel. The CEC-OAHA-MMP hydrogel exhibits excellent flowability at 37 °C under shear stress, enabling its injection to generate gradient distributions and shapes. Furthermore, encapsulated sarcoma cells respond to the gradient cues of RGD peptides and MMP-sensitive cross-linkers in the hydrogel. With these superior properties, the dual cross-linked CEC-OAHA-MMP hydrogel holds significant potential for generating customizable gradient hydrogel constructs, to study and guide cellular responses to their microenvironment such as in tumor mimicking, tissue engineering, and stem cell differentiation and morphogenesis. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

A Naive-Bayes classifier for damage detection in engineering materials

Energy Technology Data Exchange (ETDEWEB)

Addin, O. [Laboratory of Intelligent Systems, Institute of Advanced Technology, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia); Sapuan, S.M. [Department of Mechanical and Manufacturing Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia)]. E-mail: sapuan@eng.upm.edu.my; Mahdi, E. [Department of Aerospace Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia); Othman, M. [Department of Communication Technology and Networks, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia)

2007-07-01

This paper is intended to introduce the Bayesian network in general and the Naive-Bayes classifier in particular as one of the most successful classification systems to simulate damage detection in engineering materials. A method for feature subset selection has also been introduced too. The method is based on mean and maximum values of the amplitudes of waves after dividing them into folds then grouping them by a clustering algorithm (e.g. k-means algorithm). The Naive-Bayes classifier and the feature sub-set selection method were analyzed and tested on two sets of data. The data sets were conducted based on artificial damages created in quasi isotopic laminated composites of the AS4/3501-6 graphite/epoxy system and ball bearing of the type 6204 with a steel cage. The Naive-Bayes classifier and the proposed feature subset selection algorithm have been shown as efficient techniques for damage detection in engineering materials.

Classification of epileptic seizures using wavelet packet log energy and norm entropies with recurrent Elman neural network classifier.

Science.gov (United States)

Raghu, S; Sriraam, N; Kumar, G Pradeep

2017-02-01

Electroencephalogram shortly termed as EEG is considered as the fundamental segment for the assessment of the neural activities in the brain. In cognitive neuroscience domain, EEG-based assessment method is found to be superior due to its non-invasive ability to detect deep brain structure while exhibiting superior spatial resolutions. Especially for studying the neurodynamic behavior of epileptic seizures, EEG recordings reflect the neuronal activity of the brain and thus provide required clinical diagnostic information for the neurologist. This specific proposed study makes use of wavelet packet based log and norm entropies with a recurrent Elman neural network (REN) for the automated detection of epileptic seizures. Three conditions, normal, pre-ictal and epileptic EEG recordings were considered for the proposed study. An adaptive Weiner filter was initially applied to remove the power line noise of 50 Hz from raw EEG recordings. Raw EEGs were segmented into 1 s patterns to ensure stationarity of the signal. Then wavelet packet using Haar wavelet with a five level decomposition was introduced and two entropies, log and norm were estimated and were applied to REN classifier to perform binary classification. The non-linear Wilcoxon statistical test was applied to observe the variation in the features under these conditions. The effect of log energy entropy (without wavelets) was also studied. It was found from the simulation results that the wavelet packet log entropy with REN classifier yielded a classification accuracy of 99.70 % for normal-pre-ictal, 99.70 % for normal-epileptic and 99.85 % for pre-ictal-epileptic.

Classifying spaces of degenerating polarized Hodge structures

CERN Document Server

Kato, Kazuya

2009-01-01

In 1970, Phillip Griffiths envisioned that points at infinity could be added to the classifying space D of polarized Hodge structures. In this book, Kazuya Kato and Sampei Usui realize this dream by creating a logarithmic Hodge theory. They use the logarithmic structures begun by Fontaine-Illusie to revive nilpotent orbits as a logarithmic Hodge structure. The book focuses on two principal topics. First, Kato and Usui construct the fine moduli space of polarized logarithmic Hodge structures with additional structures. Even for a Hermitian symmetric domain D, the present theory is a refinem

Bringing abundance into environmental politics: Constructing a Zionist network of water abundance, immigration, and colonization.

Science.gov (United States)

Alatout, Samer

2009-06-01

For more than five decades, resource scarcity has been the lead story in debates over environmental politics. More importantly, and whenever environmental politics implies conflict, resource scarcity is constructed as the culprit. Abundance of resources, if at all visited in the literature, holds less importance. Resource abundance is seen, at best, as the other side of scarcity--maybe the successful conclusion of multiple interventions that may turn scarcity into abundance. This paper reinstates abundance as a politico-environmental category in its own right. Rather than relegating abundance to a second-order environmental actor that matters only on occasion, this paper foregrounds it as a crucial element in modern environmental politics. On the substantive level, and using insights from science and technology studies, especially a slightly modified actor-network framework, I describe the emergence and consolidation of a Zionist network of abundance, immigration, and colonization in Palestine between 1918 and 1948. The essential argument here is that water abundance was constructed as fact, and became a political rallying point around which a techno-political network emerged that included a great number of elements. To name just a few, the following were enrolled in the service of such a network: geologists, geophysicists, Zionist settlement experts, Zionist organizations, political and technical categories of all sorts, Palestinians as the negated others, Palestinian revolts in search of political rights, the British Mandate authorities, the hydrological system of Palestine, and the absorptive capacity of Palestine, among others. The point was to successfully articulate these disparate elements into a network that seeks opening Palestine for Jewish immigration, redefining Palestinian geography and history through Judeo-Christian Biblical narratives, and, in the process, de-legitimizing political Palestinian presence in historic Palestine.

Guidance for RNA-seq co-expression network construction and analysis: safety in numbers.

Science.gov (United States)

Ballouz, S; Verleyen, W; Gillis, J

2015-07-01

RNA-seq co-expression analysis is in its infancy and reasonable practices remain poorly defined. We assessed a variety of RNA-seq expression data to determine factors affecting functional connectivity and topology in co-expression networks. We examine RNA-seq co-expression data generated from 1970 RNA-seq samples using a Guilt-By-Association framework, in which genes are assessed for the tendency of co-expression to reflect shared function. Minimal experimental criteria to obtain performance on par with microarrays were >20 samples with read depth >10 M per sample. While the aggregate network constructed shows good performance (area under the receiver operator characteristic curve ∼0.71), the dependency on number of experiments used is nearly identical to that present in microarrays, suggesting thousands of samples are required to obtain 'gold-standard' co-expression. We find a major topological difference between RNA-seq and microarray co-expression in the form of low overlaps between hub-like genes from each network due to changes in the correlation of expression noise within each technology. jgillis@cshl.edu or sballouz@cshl.edu Networks are available at: http://gillislab.labsites.cshl.edu/supplements/rna-seq-networks/ and supplementary data are available at Bioinformatics online. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

GIS-based planning system for managing the flow of construction and demolition waste in Brazil.

Science.gov (United States)

Paz, Diogo Henrique Fernandes da; Lafayette, Kalinny Patrícia Vaz; Sobral, Maria do Carmo

2018-05-01

The objective of this article was to plan a network for municipal management of construction and demolition waste in Brazil with the assistance of a geographic information system, using the city of Recife as a case study. The methodology was carried out in three stages. The first was to map the illegal construction and demolition of waste disposal points across Recife and classify the waste according to its recyclability. In sequence, a method for indicating suitable areas for installation of voluntary delivery points, for small waste generators, are presented. Finally, a method for indicating suitable areas for the installation of trans-shipment and waste sorting areas, developed for large generators, is presented. The results show that a geographic information system is an essential tool in the planning of municipal construction and demolition waste management, in order to facilitate the spatial analysis and control the generation, sorting, collection, transportation, and final destination of construction and demolition waste, increasing the rate of recovery and recycling of materials.

Neural Network Aided Glitch-Burst Discrimination and Glitch Classification

Science.gov (United States)

Rampone, Salvatore; Pierro, Vincenzo; Troiano, Luigi; Pinto, Innocenzo M.

2013-11-01

We investigate the potential of neural-network based classifiers for discriminating gravitational wave bursts (GWBs) of a given canonical family (e.g. core-collapse supernova waveforms) from typical transient instrumental artifacts (glitches), in the data of a single detector. The further classification of glitches into typical sets is explored. In order to provide a proof of concept, we use the core-collapse supernova waveform catalog produced by H. Dimmelmeier and co-Workers, and the data base of glitches observed in laser interferometer gravitational wave observatory (LIGO) data maintained by P. Saulson and co-Workers to construct datasets of (windowed) transient waveforms (glitches and bursts) in additive (Gaussian and compound-Gaussian) noise with different signal-to-noise ratios (SNR). Principal component analysis (PCA) is next implemented for reducing data dimensionality, yielding results consistent with, and extending those in the literature. Then, a multilayer perceptron is trained by a backpropagation algorithm (MLP-BP) on a data subset, and used to classify the transients as glitch or burst. A Self-Organizing Map (SOM) architecture is finally used to classify the glitches. The glitch/burst discrimination and glitch classification abilities are gauged in terms of the related truth tables. Preliminary results suggest that the approach is effective and robust throughout the SNR range of practical interest. Perspective applications pertain both to distributed (network, multisensor) detection of GWBs, where some intelligence at the single node level can be introduced, and instrument diagnostics/optimization, where spurious transients can be identified, classified and hopefully traced back to their entry points.

Complexity analysis on public transport networks of 97 large- and medium-sized cities in China

Science.gov (United States)

Tian, Zhanwei; Zhang, Zhuo; Wang, Hongfei; Ma, Li

2018-04-01

The traffic situation in Chinese urban areas is continuing to deteriorate. To make a better planning and designing of the public transport system, it is necessary to make profound research on the structure of urban public transport networks (PTNs). We investigate 97 large- and medium-sized cities’ PTNs in China, construct three types of network models — bus stop network, bus transit network and bus line network, then analyze the structural characteristics of them. It is revealed that bus stop network is small-world and scale-free, bus transit network and bus line network are both small-world. Betweenness centrality of each city’s PTN shows similar distribution pattern, although these networks’ size is various. When classifying cities according to the characteristics of PTNs or economic development level, the results are similar. It means that the development of cities’ economy and transport network has a strong correlation, PTN expands in a certain model with the development of economy.

Information theoretic description of networks

Science.gov (United States)

Wilhelm, Thomas; Hollunder, Jens

2007-11-01

We present a new information theoretic approach for network characterizations. It is developed to describe the general type of networks with n nodes and L directed and weighted links, i.e., it also works for the simpler undirected and unweighted networks. The new information theoretic measures for network characterizations are based on a transmitter-receiver analogy of effluxes and influxes. Based on these measures, we classify networks as either complex or non-complex and as either democracy or dictatorship networks. Directed networks, in particular, are furthermore classified as either information spreading and information collecting networks. The complexity classification is based on the information theoretic network complexity measure medium articulation (MA). It is proven that special networks with a medium number of links ( L∼n1.5) show the theoretical maximum complexity MA=(log n)2/2. A network is complex if its MA is larger than the average MA of appropriately randomized networks: MA>MAr. A network is of the democracy type if its redundancy Rdictatorship network. In democracy networks all nodes are, on average, of similar importance, whereas in dictatorship networks some nodes play distinguished roles in network functioning. In other words, democracy networks are characterized by cycling of information (or mass, or energy), while in dictatorship networks there is a straight through-flow from sources to sinks. The classification of directed networks into information spreading and information collecting networks is based on the conditional entropies of the considered networks ( H(A/B)=uncertainty of sender node if receiver node is known, H(B/A)=uncertainty of receiver node if sender node is known): if H(A/B)>H(B/A), it is an information collecting network, otherwise an information spreading network. Finally, different real networks (directed and undirected, weighted and unweighted) are classified according to our general scheme.

A systems biology approach to construct the gene regulatory network of systemic inflammation via microarray and databases mining

Directory of Open Access Journals (Sweden)

Lan Chung-Yu

2008-09-01

Full Text Available Abstract Background Inflammation is a hallmark of many human diseases. Elucidating the mechanisms underlying systemic inflammation has long been an important topic in basic and clinical research. When primary pathogenetic events remains unclear due to its immense complexity, construction and analysis of the gene regulatory network of inflammation at times becomes the best way to understand the detrimental effects of disease. However, it is difficult to recognize and evaluate relevant biological processes from the huge quantities of experimental data. It is hence appealing to find an algorithm which can generate a gene regulatory network of systemic inflammation from high-throughput genomic studies of human diseases. Such network will be essential for us to extract valuable information from the complex and chaotic network under diseased conditions. Results In this study, we construct a gene regulatory network of inflammation using data extracted from the Ensembl and JASPAR databases. We also integrate and apply a number of systematic algorithms like cross correlation threshold, maximum likelihood estimation method and Akaike Information Criterion (AIC on time-lapsed microarray data to refine the genome-wide transcriptional regulatory network in response to bacterial endotoxins in the context of dynamic activated genes, which are regulated by transcription factors (TFs such as NF-κB. This systematic approach is used to investigate the stochastic interaction represented by the dynamic leukocyte gene expression profiles of human subject exposed to an inflammatory stimulus (bacterial endotoxin. Based on the kinetic parameters of the dynamic gene regulatory network, we identify important properties (such as susceptibility to infection of the immune system, which may be useful for translational research. Finally, robustness of the inflammatory gene network is also inferred by analyzing the hubs and "weak ties" structures of the gene network

Statistical text classifier to detect specific type of medical incidents.

Science.gov (United States)

Wong, Zoie Shui-Yee; Akiyama, Masanori

2013-01-01

WHO Patient Safety has put focus to increase the coherence and expressiveness of patient safety classification with the foundation of International Classification for Patient Safety (ICPS). Text classification and statistical approaches has showed to be successful to identifysafety problems in the Aviation industryusing incident text information. It has been challenging to comprehend the taxonomy of medical incidents in a structured manner. Independent reporting mechanisms for patient safety incidents have been established in the UK, Canada, Australia, Japan, Hong Kong etc. This research demonstrates the potential to construct statistical text classifiers to detect specific type of medical incidents using incident text data. An illustrative example for classifying look-alike sound-alike (LASA) medication incidents using structured text from 227 advisories related to medication errors from Global Patient Safety Alerts (GPSA) is shown in this poster presentation. The classifier was built using logistic regression model. ROC curve and the AUC value indicated that this is a satisfactory good model.

Construction and application of a protein and genetic interaction network (yeast interactome).

Science.gov (United States)

Stuart, Gregory R; Copeland, William C; Strand, Micheline K

2009-04-01

Cytoscape is a bioinformatic data analysis and visualization platform that is well-suited to the analysis of gene expression data. To facilitate the analysis of yeast microarray data using Cytoscape, we constructed an interaction network (interactome) using the curated interaction data available from the Saccharomyces Genome Database (www.yeastgenome.org) and the database of yeast transcription factors at YEASTRACT (www.yeastract.com). These data were formatted and imported into Cytoscape using semi-automated methods, including Linux-based scripts, that simplified the process while minimizing the introduction of processing errors. The methods described for the construction of this yeast interactome are generally applicable to the construction of any interactome. Using Cytoscape, we illustrate the use of this interactome through the analysis of expression data from a recent yeast diauxic shift experiment. We also report and briefly describe the complex associations among transcription factors that result in the regulation of thousands of genes through coordinated changes in expression of dozens of transcription factors. These cells are thus able to sensitively regulate cellular metabolism in response to changes in genetic or environmental conditions through relatively small changes in the expression of large numbers of genes, affecting the entire yeast metabolome.

Security Enrichment in Intrusion Detection System Using Classifier Ensemble

Directory of Open Access Journals (Sweden)

Uma R. Salunkhe

2017-01-01

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

A Hierarchical Approach to Persistent Scatterer Network Construction and Deformation Time Series Estimation

Directory of Open Access Journals (Sweden)

Rui Zhang

2014-12-01

Full Text Available This paper presents a hierarchical approach to network construction and time series estimation in persistent scatterer interferometry (PSI for deformation analysis using the time series of high-resolution satellite SAR images. To balance between computational efficiency and solution accuracy, a dividing and conquering algorithm (i.e., two levels of PS networking and solution is proposed for extracting deformation rates of a study area. The algorithm has been tested using 40 high-resolution TerraSAR-X images collected between 2009 and 2010 over Tianjin in China for subsidence analysis, and validated by using the ground-based leveling measurements. The experimental results indicate that the hierarchical approach can remarkably reduce computing time and memory requirements, and the subsidence measurements derived from the hierarchical solution are in good agreement with the leveling data.

Classifier-Guided Sampling for Complex Energy System Optimization

Energy Technology Data Exchange (ETDEWEB)

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

2015-09-01

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

Online identity: constructing interpersonal trust and openness through participating in hospitality social networks

Directory of Open Access Journals (Sweden)

Alexander Ronzhyn

2013-06-01

Full Text Available The present article describes the results of research on online identity construction during the participation in the hospitality social networks. Specifically the user references are analysed to understand patterns that form the image of a member. CouchSurfing service (couchsurfing.org allows users to leave short texts where the experience of hosting/being hosted by a CS member is described, is an evaluation of the CS members of each other’s personal traits, skills and common experience. Therefore references can become a good instrument for portraying a CouchSurfing member and understanding his or her particular traits. References form an important part of a user’s virtual identity in the network. Using a sample of references of Spanish CouchSurfing users, the research established main characteristics of the references, which are the openness, readiness to share ideas and experiences and trustworthiness. These concepts illustrate the typical traits associated with a user of the network and also shed light on the activities common during offl ine CS meetings

Exploiting The Brain’s Network Structure in Identifying ADHD

Directory of Open Access Journals (Sweden)

Soumyabrata eDey

2012-11-01

Full Text Available Attention Deficit Hyperactive Disorder (ADHD is a common behavioral problem affecting children. In this work, we investigate the automatic classification of ADHD subjects using the resting state Functional Magnetic Resonance Imaging (fMRI sequences of the brain. We show that brain can be modeled as a functional network, and certain properties of the networks differ in ADHD subjects from control subjects. We compute the pairwise correlation of brain voxels' activity over the time frame of the experimental protocol which helps to model the function of a brain as a network. Different network features are computed for each of the voxels constructing the network. The concatenation of the network features of all the voxels in a brain serves as the feature vector. Feature vectors from a set of subjects are then used to train a PCA-LDA (principal component analysis-linear discriminant analysis based classifier. We hypothesized that ADHD related differences lie in some specific regions of brain and using features only from those regions are sufficient to discriminate ADHD and control subjects. We propose a method to create a brain mask which includes the useful regions only and demonstrate that using the feature from the masked regions improves classification accuracy on the test data set. We train our classifier with 776 subjects, and test on 171 subjects provided by The Neuro Bureau for the ADHD-200 challenge. We demonstrate the utility of graph-motif features, specifically the maps that represent the frequency of participation of voxels in network cycles of length 3. The best classification performance (69.59% is achieved using 3-cycle map features with masking. Our proposed approach holds promise in being able to diagnose and understand the disorder.

Two channel EEG thought pattern classifier.

Science.gov (United States)

Craig, D A; Nguyen, H T; Burchey, H A

2006-01-01

This paper presents a real-time electro-encephalogram (EEG) identification system with the goal of achieving hands free control. With two EEG electrodes placed on the scalp of the user, EEG signals are amplified and digitised directly using a ProComp+ encoder and transferred to the host computer through the RS232 interface. Using a real-time multilayer neural network, the actual classification for the control of a powered wheelchair has a very fast response. It can detect changes in the user's thought pattern in 1 second. Using only two EEG electrodes at positions O(1) and C(4) the system can classify three mental commands (forward, left and right) with an accuracy of more than 79 %

Graphic Symbol Recognition using Graph Based Signature and Bayesian Network Classifier

OpenAIRE

Luqman, Muhammad Muzzamil; Brouard, Thierry; Ramel, Jean-Yves

2010-01-01

We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image analysis and is at heart of most graphic recognition systems. Our method uses structural approach for symbol representation and statistical classifier for symbol recognition. In our system we represent symbols by their graph based signatures: a graphic symbol is vectorized and is converted to an attributed relational g...

Dynamic cluster generation for a fuzzy classifier with ellipsoidal regions.

Science.gov (United States)

Abe, S

1998-01-01

In this paper, we discuss a fuzzy classifier with ellipsoidal regions that dynamically generates clusters. First, for the data belonging to a class we define a fuzzy rule with an ellipsoidal region. Namely, using the training data for each class, we calculate the center and the covariance matrix of the ellipsoidal region for the class. Then we tune the fuzzy rules, i.e., the slopes of the membership functions, successively until there is no improvement in the recognition rate of the training data. Then if the number of the data belonging to a class that are misclassified into another class exceeds a prescribed number, we define a new cluster to which those data belong and the associated fuzzy rule. Then we tune the newly defined fuzzy rules in the similar way as stated above, fixing the already obtained fuzzy rules. We iterate generation of clusters and tuning of the newly generated fuzzy rules until the number of the data belonging to a class that are misclassified into another class does not exceed the prescribed number. We evaluate our method using thyroid data, Japanese Hiragana data of vehicle license plates, and blood cell data. By dynamic cluster generation, the generalization ability of the classifier is improved and the recognition rate of the fuzzy classifier for the test data is the best among the neural network classifiers and other fuzzy classifiers if there are no discrete input variables.

Towards the prediction of essential genes by integration of network topology, cellular localization and biological process information

Directory of Open Access Journals (Sweden)

Lemke Ney

2009-09-01

Full Text Available Abstract Background The identification of essential genes is important for the understanding of the minimal requirements for cellular life and for practical purposes, such as drug design. However, the experimental techniques for essential genes discovery are labor-intensive and time-consuming. Considering these experimental constraints, a computational approach capable of accurately predicting essential genes would be of great value. We therefore present here a machine learning-based computational approach relying on network topological features, cellular localization and biological process information for prediction of essential genes. Results We constructed a decision tree-based meta-classifier and trained it on datasets with individual and grouped attributes-network topological features, cellular compartments and biological processes-to generate various predictors of essential genes. We showed that the predictors with better performances are those generated by datasets with integrated attributes. Using the predictor with all attributes, i.e., network topological features, cellular compartments and biological processes, we obtained the best predictor of essential genes that was then used to classify yeast genes with unknown essentiality status. Finally, we generated decision trees by training the J48 algorithm on datasets with all network topological features, cellular localization and biological process information to discover cellular rules for essentiality. We found that the number of protein physical interactions, the nuclear localization of proteins and the number of regulating transcription factors are the most important factors determining gene essentiality. Conclusion We were able to demonstrate that network topological features, cellular localization and biological process information are reliable predictors of essential genes. Moreover, by constructing decision trees based on these data, we could discover cellular rules governing

Evaluation of Network Failure induced IPTV degradation in Metro Networks

DEFF Research Database (Denmark)

Wessing, Henrik; Berger, Michael Stübert; Yu, Hao

2009-01-01

In this paper, we evaluate future network services and classify them according to their network requirements. IPTV is used as candidate service to evaluate the performance of Carrier Ethernet OAM update mechanisms and requirements. The latter is done through quality measurements using MDI...

A unified classifier for robust face recognition based on combining multiple subspace algorithms

Science.gov (United States)

Ijaz Bajwa, Usama; Ahmad Taj, Imtiaz; Waqas Anwar, Muhammad

2012-10-01

Face recognition being the fastest growing biometric technology has expanded manifold in the last few years. Various new algorithms and commercial systems have been proposed and developed. However, none of the proposed or developed algorithm is a complete solution because it may work very well on one set of images with say illumination changes but may not work properly on another set of image variations like expression variations. This study is motivated by the fact that any single classifier cannot claim to show generally better performance against all facial image variations. To overcome this shortcoming and achieve generality, combining several classifiers using various strategies has been studied extensively also incorporating the question of suitability of any classifier for this task. The study is based on the outcome of a comprehensive comparative analysis conducted on a combination of six subspace extraction algorithms and four distance metrics on three facial databases. The analysis leads to the selection of the most suitable classifiers which performs better on one task or the other. These classifiers are then combined together onto an ensemble classifier by two different strategies of weighted sum and re-ranking. The results of the ensemble classifier show that these strategies can be effectively used to construct a single classifier that can successfully handle varying facial image conditions of illumination, aging and facial expressions.

Automatic Assessing of Tremor Severity Using Nonlinear Dynamics, Artificial Neural Networks and Neuro-Fuzzy Classifier

Directory of Open Access Journals (Sweden)

GEMAN, O.

2014-02-01

Full Text Available Neurological diseases like Alzheimer, epilepsy, Parkinson's disease, multiple sclerosis and other dementias influence the lives of patients, their families and society. Parkinson's disease (PD is a neurodegenerative disease that occurs due to loss of dopamine, a neurotransmitter and slow destruction of neurons. Brain area affected by progressive destruction of neurons is responsible for controlling movements, and patients with PD reveal rigid and uncontrollable gestures, postural instability, small handwriting and tremor. Commercial activity-promoting gaming systems such as the Nintendo Wii and Xbox Kinect can be used as tools for tremor, gait or other biomedical signals acquisitions. They also can aid for rehabilitation in clinical settings. This paper emphasizes the use of intelligent optical sensors or accelerometers in biomedical signal acquisition, and of the specific nonlinear dynamics parameters or fuzzy logic in Parkinson's disease tremor analysis. Nowadays, there is no screening test for early detection of PD. So, we investigated a method to predict PD, based on the image processing of the handwriting belonging to a candidate of PD. For classification and discrimination between healthy people and PD people we used Artificial Neural Networks (Radial Basis Function - RBF and Multilayer Perceptron - MLP and an Adaptive Neuro-Fuzzy Classifier (ANFC. In general, the results may be expressed as a prognostic (risk degree to contact PD.

Brain without anatomy: construction and comparison of fully network-driven structural MRI connectomes.

Directory of Open Access Journals (Sweden)

Olga Tymofiyeva

Full Text Available MRI connectomics methods treat the brain as a network and provide new information about its organization, efficiency, and mechanisms of disruption. The most commonly used method of defining network nodes is to register the brain to a standardized anatomical atlas based on the Brodmann areas. This approach is limited by inter-subject variability and can be especially problematic in the context of brain maturation or neuroplasticity (cerebral reorganization after brain damage. In this study, we combined different image processing and network theory methods and created a novel approach that enables atlas-free construction and connection-wise comparison of diffusion MRI-based brain networks. We illustrated the proposed approach in three age groups: neonates, 6-month-old infants, and adults. First, we explored a data-driven method of determining the optimal number of equal-area nodes based on the assumption that all cortical areas of the brain are connected and, thus, no part of the brain is structurally isolated. Second, to enable a connection-wise comparison, alignment to a "reference brain" was performed in the network domain within each group using a matrix alignment algorithm with simulated annealing. The correlation coefficients after pair-wise network alignment ranged from 0.6102 to 0.6673. To test the method's reproducibility, one subject from the 6-month-old group and one from the adult group were scanned twice, resulting in correlation coefficients of 0.7443 and 0.7037, respectively. While being less than 1 due to parcellation and noise, statistically, these values were significantly higher than inter-subject values. Rotation of the parcellation largely explained the variability. Through the abstraction from anatomy, the developed framework allows for a fully network-driven analysis of structural MRI connectomes and can be applied to subjects at any stage of development and with substantial differences in cortical anatomy.

Recurrent Neural Network Model for Constructive Peptide Design.

Science.gov (United States)

Müller, Alex T; Hiss, Jan A; Schneider, Gisbert

2018-02-26

We present a generative long short-term memory (LSTM) recurrent neural network (RNN) for combinatorial de novo peptide design. RNN models capture patterns in sequential data and generate new data instances from the learned context. Amino acid sequences represent a suitable input for these machine-learning models. Generative models trained on peptide sequences could therefore facilitate the design of bespoke peptide libraries. We trained RNNs with LSTM units on pattern recognition of helical antimicrobial peptides and used the resulting model for de novo sequence generation. Of these sequences, 82% were predicted to be active antimicrobial peptides compared to 65% of randomly sampled sequences with the same amino acid distribution as the training set. The generated sequences also lie closer to the training data than manually designed amphipathic helices. The results of this study showcase the ability of LSTM RNNs to construct new amino acid sequences within the applicability domain of the model and motivate their prospective application to peptide and protein design without the need for the exhaustive enumeration of sequence libraries.

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

Science.gov (United States)

Alippi, Cesare; Roveri, Manuel

2008-12-01

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

The networked student: A design-based research case study of student constructed personal learning environments in a middle school science course

Science.gov (United States)

Drexler, Wendy

This design-based research case study applied a networked learning approach to a seventh grade science class at a public school in the southeastern United States. Students adapted emerging Web applications to construct personal learning environments for in-depth scientific inquiry of poisonous and venomous life forms. The personal learning environments constructed used Application Programming Interface (API) widgets to access, organize, and synthesize content from a number of educational Internet resources and social network connections. This study examined the nature of personal learning environments; the processes students go through during construction, and patterns that emerged. The project was documented from both an instructional and student-design perspective. Findings revealed that students applied the processes of: practicing digital responsibility; practicing digital literacy; organizing content; collaborating and socializing; and synthesizing and creating. These processes informed a model of the networked student that will serve as a framework for future instructional designs. A networked learning approach that incorporates these processes into future designs has implications for student learning, teacher roles, professional development, administrative policies, and delivery. This work is significant in that it shifts the focus from technology innovations based on tools to student empowerment based on the processes required to support learning. It affirms the need for greater attention to digital literacy and responsibility in K12 schools as well as consideration for those skills students will need to achieve success in the 21st century. The design-based research case study provides a set of design principles for teachers to follow when facilitating student construction of personal learning environments.

Neural network consistent empirical physical formula construction for neutron–gamma discrimination in gamma ray tracking

International Nuclear Information System (INIS)

Yildiz, Nihat; Akkoyun, Serkan

2013-01-01

Highlights: ► Detector responses in neutron–gamma discrimination were estimated by neural networks. ► Novel consistent neural network empirical physical formulas (EPFs) were constructed for detector responses. ► The EPFs are of explicit mathematical functional form. ► The EPFs can be used to derive various physical functions relevant to neutron–gamma discrimination in gamma ray tracking. -- Abstract: Gamma ray tracking is an efficient detection technique in studying exotic nuclei which lies far from beta stability line. To achieve very powerful and extraordinary resolution ability, new detectors based on gamma ray tracking are currently being developed. To reach this achievement, the neutron–gamma discrimination in these detectors is also an important task. In this paper, by suitable layered feedforward neural networks (LFNNs), we have constructed novel and consistent empirical physical formulas (EPFs) for some highly nonlinear detector counts measured in neutron–gamma discrimination. The detector counts data used in the discrimination was actually borrowed from our previous paper. The counts used here had been originally measured versus the following parameters: energy deposited in the first interaction points, difference in the incoming direction of initial gamma rays, and finally figure of merit values of the clusters determined by tracking. The LFNN–EPFs are of explicit mathematical functional form. Therefore, by various suitable operations of mathematical analysis, these LFNN–EPFs can be used to derivate further physical functions which might be potentially relevant to neutron–gamma discrimination performance of gamma ray tracking.

Case Library Construction Technology of Energy Loss in Distribution Networks Considering Regional Differentiation Theory

Directory of Open Access Journals (Sweden)

Ze Yuan

2017-11-01

Full Text Available The grid structures, load levels, and running states of distribution networks in different supply regions are known as the influencing factors of energy loss. In this paper, the case library of energy loss is constructed to differentiate the crucial factors of energy loss in the different supply regions. First of all, the characteristic state values are selected as the representation of the cases based on the analysis of energy loss under various voltage classes and in different types of regions. Then, the methods of Grey Relational Analysis and the K-Nearest Neighbor are utilized to implement the critical technologies of case library construction, including case representation, processing, analysis, and retrieval. Moreover, the analysis software of the case library is designed based on the case library construction technology. Some case studies show that there are many differences and similarities concerning the factors that influence the energy loss in different types of regions. In addition, the most relevant sample case can be retrieved from the case library. Compared with the traditional techniques, constructing a case library provides a new way to find out the characteristics of energy loss in different supply regions and constitutes differentiated loss-reducing programs.

Online Adaboost-Based Parameterized Methods for Dynamic Distributed Network Intrusion Detection.

Science.gov (United States)

Hu, Weiming; Gao, Jun; Wang, Yanguo; Wu, Ou; Maybank, Stephen

2014-01-01

Current network intrusion detection systems lack adaptability to the frequently changing network environments. Furthermore, intrusion detection in the new distributed architectures is now a major requirement. In this paper, we propose two online Adaboost-based intrusion detection algorithms. In the first algorithm, a traditional online Adaboost process is used where decision stumps are used as weak classifiers. In the second algorithm, an improved online Adaboost process is proposed, and online Gaussian mixture models (GMMs) are used as weak classifiers. We further propose a distributed intrusion detection framework, in which a local parameterized detection model is constructed in each node using the online Adaboost algorithm. A global detection model is constructed in each node by combining the local parametric models using a small number of samples in the node. This combination is achieved using an algorithm based on particle swarm optimization (PSO) and support vector machines. The global model in each node is used to detect intrusions. Experimental results show that the improved online Adaboost process with GMMs obtains a higher detection rate and a lower false alarm rate than the traditional online Adaboost process that uses decision stumps. Both the algorithms outperform existing intrusion detection algorithms. It is also shown that our PSO, and SVM-based algorithm effectively combines the local detection models into the global model in each node; the global model in a node can handle the intrusion types that are found in other nodes, without sharing the samples of these intrusion types.

Protein-protein networks construction and their relevance measurement based on multi-epitope-ligand-kartographie and gene ontology data of T-cell surface proteins for polymyositis.

Science.gov (United States)

Li, Fang-Zhen; Gao, Feng

2012-08-01

Polymyositis is an inflammatory myopathy characterized by muscle invasion of T-cells penetrating the basal lamina and displacing the plasma membrane of normal muscle fibers. In order to understand the different adhesive mechanisms at the T-cell surface, Schubert randomly selected 19 proteins expressed at the T-cell surface and studied them using MELK technique [4], among which 15 proteins are picked up for further study by us. Two types of functional similarity networks are constructed for these proteins. The first type is MELK similarity network, which is constructed based on their MELK data by using the McNemar's test [24]. The second type is GO similarity network, which is constructed based on their GO annotation data by using the RSS method to measuring functional similarity. Then the subset surprisology theory is employed to measure the degree of similarity between two networks. Our computing results show that these two types of networks are high related. This conclusion added new values on MELK technique and expanded its applications greatly.

A Novel HMM Distributed Classifier for the Detection of Gait Phases by Means of a Wearable Inertial Sensor Network

Directory of Open Access Journals (Sweden)

Juri Taborri

2014-09-01

Full Text Available In this work, we decided to apply a hierarchical weighted decision, proposed and used in other research fields, for the recognition of gait phases. The developed and validated novel distributed classifier is based on hierarchical weighted decision from outputs of scalar Hidden Markov Models (HMM applied to angular velocities of foot, shank, and thigh. The angular velocities of ten healthy subjects were acquired via three uni-axial gyroscopes embedded in inertial measurement units (IMUs during one walking task, repeated three times, on a treadmill. After validating the novel distributed classifier and scalar and vectorial classifiers-already proposed in the literature, with a cross-validation, classifiers were compared for sensitivity, specificity, and computational load for all combinations of the three targeted anatomical segments. Moreover, the performance of the novel distributed classifier in the estimation of gait variability in terms of mean time and coefficient of variation was evaluated. The highest values of specificity and sensitivity (>0.98 for the three classifiers examined here were obtained when the angular velocity of the foot was processed. Distributed and vectorial classifiers reached acceptable values (>0.95 when the angular velocity of shank and thigh were analyzed. Distributed and scalar classifiers showed values of computational load about 100 times lower than the one obtained with the vectorial classifier. In addition, distributed classifiers showed an excellent reliability for the evaluation of mean time and a good/excellent reliability for the coefficient of variation. In conclusion, due to the better performance and the small value of computational load, the here proposed novel distributed classifier can be implemented in the real-time application of gait phases recognition, such as to evaluate gait variability in patients or to control active orthoses for the recovery of mobility of lower limb joints.

Fault Diagnosis for Distribution Networks Using Enhanced Support Vector Machine Classifier with Classical Multidimensional Scaling

Directory of Open Access Journals (Sweden)

Ming-Yuan Cho

2017-09-01

Full Text Available In this paper, a new fault diagnosis techniques based on time domain reflectometry (TDR method with pseudo-random binary sequence (PRBS stimulus and support vector machine (SVM classifier has been investigated to recognize the different types of fault in the radial distribution feeders. This novel technique has considered the amplitude of reflected signals and the peaks of cross-correlation (CCR between the reflected and incident wave for generating fault current dataset for SVM. Furthermore, this multi-layer enhanced SVM classifier is combined with classical multidimensional scaling (CMDS feature extraction algorithm and kernel parameter optimization to increase training speed and improve overall classification accuracy. The proposed technique has been tested on a radial distribution feeder to identify ten different types of fault considering 12 input features generated by using Simulink software and MATLAB Toolbox. The success rate of SVM classifier is over 95% which demonstrates the effectiveness and the high accuracy of proposed method.

An Improvement of E-Systems over Networks via the use of Artificial Intelligence

Directory of Open Access Journals (Sweden)

Yaser A. Jasim

2018-03-01

Full Text Available Nowadays, many research has been dedicated to the distribution of expert systems; unfortunately, few have deliberated the study of Dynamic Host Configuration Protocol (DHCP. In this paper, the researcher will demonstrate the construction of vacuum tubes, which embodies the principles of software engineering. In order to classify this challenge, the researcher argues not only that local-area networks (LAN can be made event-driven, stable, and random but the same is true for the Universal Automatic Computer (UNIVAC. 

Learning a Markov Logic network for supervised gene regulatory network inference.

Science.gov (United States)

Brouard, Céline; Vrain, Christel; Dubois, Julie; Castel, David; Debily, Marie-Anne; d'Alché-Buc, Florence

2013-09-12

Gene regulatory network inference remains a challenging problem in systems biology despite the numerous approaches that have been proposed. When substantial knowledge on a gene regulatory network is already available, supervised network inference is appropriate. Such a method builds a binary classifier able to assign a class (Regulation/No regulation) to an ordered pair of genes. Once learnt, the pairwise classifier can be used to predict new regulations. In this work, we explore the framework of Markov Logic Networks (MLN) that combine features of probabilistic graphical models with the expressivity of first-order logic rules. We propose to learn a Markov Logic network, e.g. a set of weighted rules that conclude on the predicate "regulates", starting from a known gene regulatory network involved in the switch proliferation/differentiation of keratinocyte cells, a set of experimental transcriptomic data and various descriptions of genes all encoded into first-order logic. As training data are unbalanced, we use asymmetric bagging to learn a set of MLNs. The prediction of a new regulation can then be obtained by averaging predictions of individual MLNs. As a side contribution, we propose three in silico tests to assess the performance of any pairwise classifier in various network inference tasks on real datasets. A first test consists of measuring the average performance on balanced edge prediction problem; a second one deals with the ability of the classifier, once enhanced by asymmetric bagging, to update a given network. Finally our main result concerns a third test that measures the ability of the method to predict regulations with a new set of genes. As expected, MLN, when provided with only numerical discretized gene expression data, does not perform as well as a pairwise SVM in terms of AUPR. However, when a more complete description of gene properties is provided by heterogeneous sources, MLN achieves the same performance as a black-box model such as a

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

Directory of Open Access Journals (Sweden)

Mei Cai

2017-01-01

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

Mastering the political Process of Building Innovation Networks - A Case from the Danish Construction Industry

DEFF Research Database (Denmark)

Stissing Jensen, Jens; Koch, Christian; Thomassen, Mikkel

2008-01-01

Drawing on network of innovation and organizational politics perspectives this paper analyzes the role of an innovation broker organization in developing and supporting an inter-organizational innovation process in the Danish construction industry. The aim is to implement an ICT-based product...... configuration tool to support the production, sale, and installation of balconies. It is suggested that the innovation broker was successful in stabilizing the innovation process by supplying minimal structures which provided a template which facilitated a combination of individual flexibility and overall...... the network. The innovation thus grew strong enough to replace existing practices and identities and to embed new ones into new organizational structures and a new business-concept...

Constructing Precisely Computing Networks with Biophysical Spiking Neurons.

Science.gov (United States)

Schwemmer, Michael A; Fairhall, Adrienne L; Denéve, Sophie; Shea-Brown, Eric T

2015-07-15

While spike timing has been shown to carry detailed stimulus information at the sensory periphery, its possible role in network computation is less clear. Most models of computation by neural networks are based on population firing rates. In equivalent spiking implementations, firing is assumed to be random such that averaging across populations of neurons recovers the rate-based approach. Recently, however, Denéve and colleagues have suggested that the spiking behavior of neurons may be fundamental to how neuronal networks compute, with precise spike timing determined by each neuron's contribution to producing the desired output (Boerlin and Denéve, 2011; Boerlin et al., 2013). By postulating that each neuron fires to reduce the error in the network's output, it was demonstrated that linear computations can be performed by networks of integrate-and-fire neurons that communicate through instantaneous synapses. This left open, however, the possibility that realistic networks, with conductance-based neurons with subthreshold nonlinearity and the slower timescales of biophysical synapses, may not fit into this framework. Here, we show how the spike-based approach can be extended to biophysically plausible networks. We then show that our network reproduces a number of key features of cortical networks including irregular and Poisson-like spike times and a tight balance between excitation and inhibition. Lastly, we discuss how the behavior of our model scales with network size or with the number of neurons "recorded" from a larger computing network. These results significantly increase the biological plausibility of the spike-based approach to network computation. We derive a network of neurons with standard spike-generating currents and synapses with realistic timescales that computes based upon the principle that the precise timing of each spike is important for the computation. We then show that our network reproduces a number of key features of cortical networks

The Construction of Support Vector Machine Classifier Using the Firefly Algorithm

Directory of Open Access Journals (Sweden)

Chih-Feng Chao

2015-01-01

Full Text Available The setting of parameters in the support vector machines (SVMs is very important with regard to its accuracy and efficiency. In this paper, we employ the firefly algorithm to train all parameters of the SVM simultaneously, including the penalty parameter, smoothness parameter, and Lagrangian multiplier. The proposed method is called the firefly-based SVM (firefly-SVM. This tool is not considered the feature selection, because the SVM, together with feature selection, is not suitable for the application in a multiclass classification, especially for the one-against-all multiclass SVM. In experiments, binary and multiclass classifications are explored. In the experiments on binary classification, ten of the benchmark data sets of the University of California, Irvine (UCI, machine learning repository are used; additionally the firefly-SVM is applied to the multiclass diagnosis of ultrasonic supraspinatus images. The classification performance of firefly-SVM is also compared to the original LIBSVM method associated with the grid search method and the particle swarm optimization based SVM (PSO-SVM. The experimental results advocate the use of firefly-SVM to classify pattern classifications for maximum accuracy.

Mapping and discrimination of networks in the complexity-entropy plane

Science.gov (United States)

Wiedermann, Marc; Donges, Jonathan F.; Kurths, Jürgen; Donner, Reik V.

2017-10-01

Complex networks are usually characterized in terms of their topological, spatial, or information-theoretic properties and combinations of the associated metrics are used to discriminate networks into different classes or categories. However, even with the present variety of characteristics at hand it still remains a subject of current research to appropriately quantify a network's complexity and correspondingly discriminate between different types of complex networks, like infrastructure or social networks, on such a basis. Here we explore the possibility to classify complex networks by means of a statistical complexity measure that has formerly been successfully applied to distinguish different types of chaotic and stochastic time series. It is composed of a network's averaged per-node entropic measure characterizing the network's information content and the associated Jenson-Shannon divergence as a measure of disequilibrium. We study 29 real-world networks and show that networks of the same category tend to cluster in distinct areas of the resulting complexity-entropy plane. We demonstrate that within our framework, connectome networks exhibit among the highest complexity while, e.g., transportation and infrastructure networks display significantly lower values. Furthermore, we demonstrate the utility of our framework by applying it to families of random scale-free and Watts-Strogatz model networks. We then show in a second application that the proposed framework is useful to objectively construct threshold-based networks, such as functional climate networks or recurrence networks, by choosing the threshold such that the statistical network complexity is maximized.

Evaluating the Impacts of Health, Social Network and Capital on Craft Efficiency and Productivity: A Case Study of Construction Workers in China.

Science.gov (United States)

Yuan, Jingfeng; Yi, Wen; Miao, Mengyi; Zhang, Lei

2018-02-15

The construction industry has been recognized, for many years, as among those having a high likelihood of accidents, injuries and occupational illnesses. Such risks of construction workers can lead to low productivity and social problems. As a result, construction workers' well-being should be highly addressed to improve construction workers' efficiency and productivity. Meanwhile, the social support from a social network and capital (SNC) of construction workers has been considered as an effective approach to promote construction workers' physical and mental health (P&M health), as well as their work efficiency and productivity. Based on a comprehensive literature review, a conceptual model, which aims to improve construction workers' efficiency and productivity from the perspective of health and SNC, was proposed. A questionnaire survey was conducted to investigate the construction workers' health, SNC and work efficiency and productivity in Nanjing, China. A structural equation model (SEM) was employed to test the three hypothetical relationships among construction workers' P&M health, SNC and work efficiency and productivity. The results indicated that the direct impacts from construction workers' P&M health on work efficiency and productivity were more significant than that from the SNC. In addition, the construction workers' social capital and the network can indirectly influence the work efficiency and productivity by affecting the construction workers' P&M health. Therefore, strategies for enhancing construction workers' efficiency and productivity were proposed. Furthermore, many useable suggestions can be drawn from the research findings from the perspective of a government. The identified indicators and relationships would contribute to the construction work efficiency and productivity assessment and health management from the perspective of the construction workers.

Evaluating the Impacts of Health, Social Network and Capital on Craft Efficiency and Productivity: A Case Study of Construction Workers in China

Directory of Open Access Journals (Sweden)

Jingfeng Yuan

2018-02-01

Full Text Available The construction industry has been recognized, for many years, as among those having a high likelihood of accidents, injuries and occupational illnesses. Such risks of construction workers can lead to low productivity and social problems. As a result, construction workers’ well-being should be highly addressed to improve construction workers’ efficiency and productivity. Meanwhile, the social support from a social network and capital (SNC of construction workers has been considered as an effective approach to promote construction workers’ physical and mental health (P&M health, as well as their work efficiency and productivity. Based on a comprehensive literature review, a conceptual model, which aims to improve construction workers’ efficiency and productivity from the perspective of health and SNC, was proposed. A questionnaire survey was conducted to investigate the construction workers’ health, SNC and work efficiency and productivity in Nanjing, China. A structural equation model (SEM was employed to test the three hypothetical relationships among construction workers’ P&M health, SNC and work efficiency and productivity. The results indicated that the direct impacts from construction workers’ P&M health on work efficiency and productivity were more significant than that from the SNC. In addition, the construction workers’ social capital and the network can indirectly influence the work efficiency and productivity by affecting the construction workers’ P&M health. Therefore, strategies for enhancing construction workers’ efficiency and productivity were proposed. Furthermore, many useable suggestions can be drawn from the research findings from the perspective of a government. The identified indicators and relationships would contribute to the construction work efficiency and productivity assessment and health management from the perspective of the construction workers.

Evaluating the Impacts of Health, Social Network and Capital on Craft Efficiency and Productivity: A Case Study of Construction Workers in China

Science.gov (United States)

Yi, Wen; Miao, Mengyi; Zhang, Lei

2018-01-01

The construction industry has been recognized, for many years, as among those having a high likelihood of accidents, injuries and occupational illnesses. Such risks of construction workers can lead to low productivity and social problems. As a result, construction workers’ well-being should be highly addressed to improve construction workers’ efficiency and productivity. Meanwhile, the social support from a social network and capital (SNC) of construction workers has been considered as an effective approach to promote construction workers’ physical and mental health (P&M health), as well as their work efficiency and productivity. Based on a comprehensive literature review, a conceptual model, which aims to improve construction workers’ efficiency and productivity from the perspective of health and SNC, was proposed. A questionnaire survey was conducted to investigate the construction workers’ health, SNC and work efficiency and productivity in Nanjing, China. A structural equation model (SEM) was employed to test the three hypothetical relationships among construction workers’ P&M health, SNC and work efficiency and productivity. The results indicated that the direct impacts from construction workers’ P&M health on work efficiency and productivity were more significant than that from the SNC. In addition, the construction workers’ social capital and the network can indirectly influence the work efficiency and productivity by affecting the construction workers’ P&M health. Therefore, strategies for enhancing construction workers’ efficiency and productivity were proposed. Furthermore, many useable suggestions can be drawn from the research findings from the perspective of a government. The identified indicators and relationships would contribute to the construction work efficiency and productivity assessment and health management from the perspective of the construction workers. PMID:29462861

A Comparison of Geographic Information Systems, Complex Networks, and Other Models for Analyzing Transportation Network Topologies

Science.gov (United States)

Alexandrov, Natalia (Technical Monitor); Kuby, Michael; Tierney, Sean; Roberts, Tyler; Upchurch, Christopher

2005-01-01

This report reviews six classes of models that are used for studying transportation network topologies. The report is motivated by two main questions. First, what can the "new science" of complex networks (scale-free, small-world networks) contribute to our understanding of transport network structure, compared to more traditional methods? Second, how can geographic information systems (GIS) contribute to studying transport networks? The report defines terms that can be used to classify different kinds of models by their function, composition, mechanism, spatial and temporal dimensions, certainty, linearity, and resolution. Six broad classes of models for analyzing transport network topologies are then explored: GIS; static graph theory; complex networks; mathematical programming; simulation; and agent-based modeling. Each class of models is defined and classified according to the attributes introduced earlier. The paper identifies some typical types of research questions about network structure that have been addressed by each class of model in the literature.

Deep Feature Learning and Cascaded Classifier for Large Scale Data

DEFF Research Database (Denmark)

Prasoon, Adhish

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

Constructing an Intelligent Patent Network Analysis Method

Directory of Open Access Journals (Sweden)

Chao-Chan Wu

2012-11-01

Full Text Available Patent network analysis, an advanced method of patent analysis, is a useful tool for technology management. This method visually displays all the relationships among the patents and enables the analysts to intuitively comprehend the overview of a set of patents in the field of the technology being studied. Although patent network analysis possesses relative advantages different from traditional methods of patent analysis, it is subject to several crucial limitations. To overcome the drawbacks of the current method, this study proposes a novel patent analysis method, called the intelligent patent network analysis method, to make a visual network with great precision. Based on artificial intelligence techniques, the proposed method provides an automated procedure for searching patent documents, extracting patent keywords, and determining the weight of each patent keyword in order to generate a sophisticated visualization of the patent network. This study proposes a detailed procedure for generating an intelligent patent network that is helpful for improving the efficiency and quality of patent analysis. Furthermore, patents in the field of Carbon Nanotube Backlight Unit (CNT-BLU were analyzed to verify the utility of the proposed method.

Strategies for Transporting Data Between Classified and Unclassified Networks

Science.gov (United States)

2016-03-01

datagram protocol (UDP) must be used. The UDP is typically used when speed is a higher priority than data integrity, such as in music or video streaming ...and the exit point of data are separate and can be tightly controlled. This does effectively prevent the comingling of data and is used in industry to...perform functions such as streaming video and audio from secure to insecure networks (ref. 1). A second disadvantage lies in the fact that the

Feasibility of Construction of the Continuously Operating Geodetic GPS Network of Sinaloa, Mexico

Science.gov (United States)

Vazquez, G. E.; Jacobo, C.

2011-12-01

This research is based on the study and analysis of feasibility for the construction of the geodetic network for GPS continuous operation for Sinaloa, hereafter called (RGOCSIN). A GPS network of continuous operation is defined as that materialized structure physically through permanent monuments where measurements to the systems of Global Positioning (GPS) is performed continuously throughout a region. The GPS measurements in this network are measurements of accuracy according to international standards to define its coordinates, thus constituting the basic structure of geodetic referencing for a country. In this context is that in the near future the RGOCSIN constitutes a system state only accurate and reliable georeferencing in real-time (continuous and permanent operation) and will be used for different purposes; i.e., in addition to being fundamental basis for any lifting topographic or geodetic survey, and other areas such as: (1) Different construction processes (control and monitoring of engineering works); (2) Studies of deformation of the Earth's crust (before and after a seismic event); (3) GPS meteorology (weather forecasting); (4) Demarcation projects (natural and political); (5) Establishment of bases to generate mapping (necessary for the economic and social development of the state); (6) Precision agriculture (optimization of economic resources to the various crops); (7) Geographic information systems (Organization and planning activities associated with the design and construction of public services); (8) Urban growth (possible settlements in the appropriate form and taking care of the environmental aspect), among others. However there are criteria and regulations according to the INEGI (Instituto Nacional de Estadística y Geografía, http://www.inegi.org.mx/) that must be met; even for this stage of feasibility of construction that sees this project as a first phase. The fundamental criterion to be taken into account according to INEGI is a

Collective Classification in Network Data

OpenAIRE

Sen, Prithviraj; Namata, Galileo; Bilgic, Mustafa; Getoor, Lise; University of Maryland; Galligher, Brian; Eliassi-Rad, Tina

2008-01-01

Many real-world applications produce networked data such as the world-wide web (hypertext documents connected via hyperlinks), social networks (for example, people connected by friendship links), communication networks (computers connected via communication links) and biological networks (for example, protein interaction networks). A recent focus in machine learning research has been to extend traditional machine learning classification techniques to classify nodes in such networks. In this a...

The construction of gender through discourse on the social network Badoo: exploring virtual interaction

OpenAIRE

Martínez Lirola, María

2013-01-01

Nowadays many meetings and conversations take place through social networks. Badoo.com is one of the best known, with more than 102 million users in 2010. This article concentrates on communication through the chat in Badoo between 150 men and the author. The study analyses the main linguistic characteristics in the conversations (orthography, use of capital letters, emoticons and strategies of courtesy and discourtesy) in order to observe how gender is constructed in interaction. The analysi...

An evaluation of the composition of soil cement bricks with construction and demolition waste - doi: 10.4025/actascitechnol.v33i2.9377

Directory of Open Access Journals (Sweden)

Antonio Anderson da Silva Segantini

2011-04-01

Full Text Available Sustainable development requires the existence of a production network that includes the reuse of construction waste for new materials. Current analysis investigates an optimal soil-cement composition made up of construction and demolition waste for the manufacture of pressed bricks. Soil-cement bricks were manufactured from construction and demolition wastes (CDW, A-4 classified fine sandy soil and cement CP II Z 32. Laboratory tests, comprising test compaction, optimum water content and maximum dry specific weight, consistency limits, grain size distribution and linear shrinkage, were made to characterize the materials researched. Compressive strength and absorption tests were also undertaken in different combinations of composition. Results showed that the application of CDW improved soil-cement qualities and reduced shrinkage of the material used.

Integrating external biological knowledge in the construction of regulatory networks from time-series expression data

Directory of Open Access Journals (Sweden)

Lo Kenneth

2012-08-01

Full Text Available Abstract Background Inference about regulatory networks from high-throughput genomics data is of great interest in systems biology. We present a Bayesian approach to infer gene regulatory networks from time series expression data by integrating various types of biological knowledge. Results We formulate network construction as a series of variable selection problems and use linear regression to model the data. Our method summarizes additional data sources with an informative prior probability distribution over candidate regression models. We extend the Bayesian model averaging (BMA variable selection method to select regulators in the regression framework. We summarize the external biological knowledge by an informative prior probability distribution over the candidate regression models. Conclusions We demonstrate our method on simulated data and a set of time-series microarray experiments measuring the effect of a drug perturbation on gene expression levels, and show that it outperforms leading regression-based methods in the literature.

Construct Validation of Wenger's Support Network Typology.

Science.gov (United States)

Szabo, Agnes; Stephens, Christine; Allen, Joanne; Alpass, Fiona

2016-10-07

The study aimed to validate Wenger's empirically derived support network typology of responses to the Practitioner Assessment of Network Type (PANT) in an older New Zealander population. The configuration of network types was tested across ethnic groups and in the total sample. Data (N = 872, Mage = 67 years, SDage = 1.56 years) from the 2006 wave of the New Zealand Health, Work and Retirement study were analyzed using latent profile analysis. In addition, demographic differences among the emerging profiles were tested. Competing models were evaluated based on a range of fit criteria, which supported a five-profile solution. The "locally integrated," "community-focused," "local self-contained," "private-restricted," and "friend- and family-dependent" network types were identified as latent profiles underlying the data. There were no differences between Māori and non-Māori in final profile configurations. However, Māori were more likely to report integrated network types. Findings confirm the validity of Wenger's network types. However, the level to which participants endorse accessibility of family, frequency of interactions, and community engagement can be influenced by sample and contextual characteristics. Future research using the PANT items should empirically verify and derive the social support network types, rather than use a predefined scoring system. © The Author 2016. Published by Oxford University Press on behalf of The Gerontological Society of America. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Quantifying immediate price impact of trades based on the k-shell decomposition of stock trading networks

Science.gov (United States)

Xie, Wen-Jie; Li, Ming-Xia; Xu, Hai-Chuan; Chen, Wei; Zhou, Wei-Xing; Stanley, H. Eugene

2016-10-01

Traders in a stock market exchange stock shares and form a stock trading network. Trades at different positions of the stock trading network may contain different information. We construct stock trading networks based on the limit order book data and classify traders into k classes using the k-shell decomposition method. We investigate the influences of trading behaviors on the price impact by comparing a closed national market (A-shares) with an international market (B-shares), individuals and institutions, partially filled and filled trades, buyer-initiated and seller-initiated trades, and trades at different positions of a trading network. Institutional traders professionally use some trading strategies to reduce the price impact and individuals at the same positions in the trading network have a higher price impact than institutions. We also find that trades in the core have higher price impacts than those in the peripheral shell.

A deep learning method for classifying mammographic breast density categories.

Science.gov (United States)

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

2018-01-01

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

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

Directory of Open Access Journals (Sweden)

Jaemu LEE,

2012-08-01

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

Fault diagnosis for temperature, flow rate and pressure sensors in VAV systems using wavelet neural network

Energy Technology Data Exchange (ETDEWEB)

Du, Zhimin; Jin, Xinqiao; Yang, Yunyu [School of Mechanical Engineering, Shanghai Jiao Tong University, 800, Dongchuan Road, Shanghai (China)

2009-09-15

Wavelet neural network, the integration of wavelet analysis and neural network, is presented to diagnose the faults of sensors including temperature, flow rate and pressure in variable air volume (VAV) systems to ensure well capacity of energy conservation. Wavelet analysis is used to process the original data collected from the building automation first. With three-level wavelet decomposition, the series of characteristic information representing various operation conditions of the system are obtained. In addition, neural network is developed to diagnose the source of the fault. To improve the diagnosis efficiency, three data groups based on several physical models or balances are classified and constructed. Using the data decomposed by three-level wavelet, the neural network can be well trained and series of convergent networks are obtained. Finally, the new measurements to diagnose are similarly processed by wavelet. And the well-trained convergent neural networks are used to identify the operation condition and isolate the source of the fault. (author)

DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier

KAUST Repository

Kulmanov, Maxat

2017-09-27

Motivation A large number of protein sequences are becoming available through the application of novel high-throughput sequencing technologies. Experimental functional characterization of these proteins is time-consuming and expensive, and is often only done rigorously for few selected model organisms. Computational function prediction approaches have been suggested to fill this gap. The functions of proteins are classified using the Gene Ontology (GO), which contains over 40 000 classes. Additionally, proteins have multiple functions, making function prediction a large-scale, multi-class, multi-label problem. Results We have developed a novel method to predict protein function from sequence. We use deep learning to learn features from protein sequences as well as a cross-species protein–protein interaction network. Our approach specifically outputs information in the structure of the GO and utilizes the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and demonstrate a significant improvement over baseline methods such as BLAST, in particular for predicting cellular locations.

Construction of diabatic energy surfaces for LiFH with artificial neural networks

Science.gov (United States)

Guan, Yafu; Fu, Bina; Zhang, Dong H.

2017-12-01

A new set of diabatic potential energy surfaces (PESs) for LiFH is constructed with artificial neural networks (NNs). The adiabatic PESs of the ground state and the first excited state are directly fitted with NNs. Meanwhile, the adiabatic-to-diabatic transformation (ADT) angles (mixing angles) are obtained by simultaneously fitting energy difference and interstate coupling gradients. No prior assumptions of the functional form of ADT angles are used before fitting, and the ab initio data including energy difference and interstate coupling gradients are well reproduced. Converged dynamical results show remarkable differences between adiabatic and diabatic PESs, which suggests the significance of non-adiabatic processes.

Tabular data base construction and analysis from thematic classified Landsat imagery of Portland, Oregon

Science.gov (United States)

Bryant, N. A.; George, A. J., Jr.; Hegdahl, R.

1977-01-01

A systematic verification of Landsat data classifications of the Portland, Oregon metropolitan area has been undertaken on the basis of census tract data. The degree of systematic misclassification due to the Bayesian classifier used to process the Landsat data was noted for the various suburban, industrialized and central business districts of the metropolitan area. The Landsat determinations of residential land use were employed to estimate the number of automobile trips generated in the region and to model air pollution hazards.

Feature Import Vector Machine: A General Classifier with Flexible Feature Selection.

Science.gov (United States)

Ghosh, Samiran; Wang, Yazhen

2015-02-01

The support vector machine (SVM) and other reproducing kernel Hilbert space (RKHS) based classifier systems are drawing much attention recently due to its robustness and generalization capability. General theme here is to construct classifiers based on the training data in a high dimensional space by using all available dimensions. The SVM achieves huge data compression by selecting only few observations which lie close to the boundary of the classifier function. However when the number of observations are not very large (small n ) but the number of dimensions/features are large (large p ), then it is not necessary that all available features are of equal importance in the classification context. Possible selection of an useful fraction of the available features may result in huge data compression. In this paper we propose an algorithmic approach by means of which such an optimal set of features could be selected. In short, we reverse the traditional sequential observation selection strategy of SVM to that of sequential feature selection. To achieve this we have modified the solution proposed by Zhu and Hastie (2005) in the context of import vector machine (IVM), to select an optimal sub-dimensional model to build the final classifier with sufficient accuracy.

A sub-nJ CMOS ECG classifier for wireless smart sensor.

Science.gov (United States)

Chollet, Paul; Pallas, Remi; Lahuec, Cyril; Arzel, Matthieu; Seguin, Fabrice

2017-07-01

Body area sensor networks hold the promise of more efficient and cheaper medical care services through the constant monitoring of physiological markers such as heart beats. Continuously transmitting the electrocardiogram (ECG) signal requires most of the wireless ECG sensor energy budget. This paper presents the analog implantation of a classifier for ECG signals that can be embedded onto a sensor. The classifier is a sparse neural associative memory. It is implemented using the ST 65 nm CMOS technology and requires only 234 pJ per classification while achieving a 93.6% classification accuracy. The energy requirement is 6 orders of magnitude lower than a digital accelerator that performs a similar task. The lifespan of the resulting sensor is 191 times as large as that of a sensor sending all the data.

Reliability analysis with linguistic data: An evidential network approach

International Nuclear Information System (INIS)

Zhang, Xiaoge; Mahadevan, Sankaran; Deng, Xinyang

2017-01-01

In practical applications of reliability assessment of a system in-service, information about the condition of a system and its components is often available in text form, e.g., inspection reports. Estimation of the system reliability from such text-based records becomes a challenging problem. In this paper, we propose a four-step framework to deal with this problem. In the first step, we construct an evidential network with the consideration of available knowledge and data. Secondly, we train a Naive Bayes text classification algorithm based on the past records. By using the trained Naive Bayes algorithm to classify the new records, we build interval basic probability assignments (BPA) for each new record available in text form. Thirdly, we combine the interval BPAs of multiple new records using an evidence combination approach based on evidence theory. Finally, we propagate the interval BPA through the evidential network constructed earlier to obtain the system reliability. Two numerical examples are used to demonstrate the efficiency of the proposed method. We illustrate the effectiveness of the proposed method by comparing with Monte Carlo Simulation (MCS) results. - Highlights: • We model reliability analysis with linguistic data using evidential network. • Two examples are used to demonstrate the efficiency of the proposed method. • We compare the results with Monte Carlo Simulation (MCS).

Self-organizing map classifier for stressed speech recognition

Science.gov (United States)

Partila, Pavol; Tovarek, Jaromir; Voznak, Miroslav

2016-05-01

This paper presents a method for detecting speech under stress using Self-Organizing Maps. Most people who are exposed to stressful situations can not adequately respond to stimuli. Army, police, and fire department occupy the largest part of the environment that are typical of an increased number of stressful situations. The role of men in action is controlled by the control center. Control commands should be adapted to the psychological state of a man in action. It is known that the psychological changes of the human body are also reflected physiologically, which consequently means the stress effected speech. Therefore, it is clear that the speech stress recognizing system is required in the security forces. One of the possible classifiers, which are popular for its flexibility, is a self-organizing map. It is one type of the artificial neural networks. Flexibility means independence classifier on the character of the input data. This feature is suitable for speech processing. Human Stress can be seen as a kind of emotional state. Mel-frequency cepstral coefficients, LPC coefficients, and prosody features were selected for input data. These coefficients were selected for their sensitivity to emotional changes. The calculation of the parameters was performed on speech recordings, which can be divided into two classes, namely the stress state recordings and normal state recordings. The benefit of the experiment is a method using SOM classifier for stress speech detection. Results showed the advantage of this method, which is input data flexibility.

Statistical identification of gene association by CID in application of constructing ER regulatory network

Directory of Open Access Journals (Sweden)

Lien Huang-Chun

2009-03-01

Full Text Available Abstract Background A variety of high-throughput techniques are now available for constructing comprehensive gene regulatory networks in systems biology. In this study, we report a new statistical approach for facilitating in silico inference of regulatory network structure. The new measure of association, coefficient of intrinsic dependence (CID, is model-free and can be applied to both continuous and categorical distributions. When given two variables X and Y, CID answers whether Y is dependent on X by examining the conditional distribution of Y given X. In this paper, we apply CID to analyze the regulatory relationships between transcription factors (TFs (X and their downstream genes (Y based on clinical data. More specifically, we use estrogen receptor α (ERα as the variable X, and the analyses are based on 48 clinical breast cancer gene expression arrays (48A. Results The analytical utility of CID was evaluated in comparison with four commonly used statistical methods, Galton-Pearson's correlation coefficient (GPCC, Student's t-test (STT, coefficient of determination (CoD, and mutual information (MI. When being compared to GPCC, CoD, and MI, CID reveals its preferential ability to discover the regulatory association where distribution of the mRNA expression levels on X and Y does not fit linear models. On the other hand, when CID is used to measure the association of a continuous variable (Y against a discrete variable (X, it shows similar performance as compared to STT, and appears to outperform CoD and MI. In addition, this study established a two-layer transcriptional regulatory network to exemplify the usage of CID, in combination with GPCC, in deciphering gene networks based on gene expression profiles from patient arrays. Conclusion CID is shown to provide useful information for identifying associations between genes and transcription factors of interest in patient arrays. When coupled with the relationships detected by GPCC, the

Constructing a generalized network design model to study air distribution in ventilation networks in subway with a single-track tunnel

Science.gov (United States)

Lugin, IV

2018-03-01

In focus are the features of construction of the generalized design model for the network method to study air distribution in ventilation system in subway with the single-track tunnel. The generalizations, assumptions and simplifications included in the model are specified. The air distribution is calculated with regard to the influence of topology and air resistances of the ventilation network sections. The author studies two variants of the subway line: half-open and closed with dead end on the both sides. It is found that the total air exchange at a subway station depends on the station location within the line. The operating mode of fans remains unaltered in this case. The article shows that elimination of air leakage in the station ventilation room allows an increase in the air flow rate by 7–8% at the same energy consumption by fans. The influence of the stop of a train in the tunnel on the air distribution is illustrated.

Young module multiplicities and classifying the indecomposable Young permutation modules

OpenAIRE

Gill, Christopher C.

2012-01-01

We study the multiplicities of Young modules as direct summands of permutation modules on cosets of Young subgroups. Such multiplicities have become known as the p-Kostka numbers. We classify the indecomposable Young permutation modules, and, applying the Brauer construction for p-permutation modules, we give some new reductions for p-Kostka numbers. In particular we prove that p-Kostka numbers are preserved under multiplying partitions by p, and strengthen a known reduction given by Henke, c...

Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program

Science.gov (United States)

Benaouda, D.; Wadge, G.; Whitmarsh, R. B.; Rothwell, R. G.; MacLeod, C.

1999-02-01

In boreholes with partial or no core recovery, interpretations of lithology in the remainder of the hole are routinely attempted using data from downhole geophysical sensors. We present a practical neural net-based technique that greatly enhances lithological interpretation in holes with partial core recovery by using downhole data to train classifiers to give a global classification scheme for those parts of the borehole for which no core was retrieved. We describe the system and its underlying methods of data exploration, selection and classification, and present a typical example of the system in use. Although the technique is equally applicable to oil industry boreholes, we apply it here to an Ocean Drilling Program (ODP) borehole (Hole 792E, Izu-Bonin forearc, a mixture of volcaniclastic sandstones, conglomerates and claystones). The quantitative benefits of quality-control measures and different subsampling strategies are shown. Direct comparisons between a number of discriminant analysis methods and the use of neural networks with back-propagation of error are presented. The neural networks perform better than the discriminant analysis techniques both in terms of performance rates with test data sets (2-3 per cent better) and in qualitative correlation with non-depth-matched core. We illustrate with the Hole 792E data how vital it is to have a system that permits the number and membership of training classes to be changed as analysis proceeds. The initial classification for Hole 792E evolved from a five-class to a three-class and then to a four-class scheme with resultant classification performance rates for the back-propagation neural network method of 83, 84 and 93 per cent respectively.

Classifying Sensors Depending on their IDs to Reduce Power Consumption in Wireless Sensor Networks

Directory of Open Access Journals (Sweden)

Ayman Mohammd Brisha

2010-05-01

Full Text Available Wireless sensor networks produce a large amount of data that needs to be processed, delivered, and assessed according to the application objectives. Cluster-based is an effective architecture for data-gathering in wireless sensor networks. Clustering provides an effective way for prolonging the lifetime of a wireless sensor network. Current clustering algorithms usually utilize two techniques, selecting cluster heads with more residual energy and rotating cluster heads periodically, in order to distribute the energy consumption among nodes in each cluster and extend the network lifetime. Clustering sensors are divided into groups, so that sensors will communicate information only to cluster heads and then the cluster heads will communicate the aggregated information to the processing center, and this may save energy. In this paper we show Two Relay Sensor Algorithm (TRSA, which divide wireless Sensor Network (WSN into unequaled clusters, showing that it can effectively save power for maximizing the life time of the network. Simulation results show that the proposed unequal clustering mechanism (TRSA balances the energy consumption among all sensor nodes and achieves an obvious improvement on the network lifetime.

Systematic construction of kinetic models from genome-scale metabolic networks.

Directory of Open Access Journals (Sweden)

Natalie J Stanford

Full Text Available The quantitative effects of environmental and genetic perturbations on metabolism can be studied in silico using kinetic models. We present a strategy for large-scale model construction based on a logical layering of data such as reaction fluxes, metabolite concentrations, and kinetic constants. The resulting models contain realistic standard rate laws and plausible parameters, adhere to the laws of thermodynamics, and reproduce a predefined steady state. These features have not been simultaneously achieved by previous workflows. We demonstrate the advantages and limitations of the workflow by translating the yeast consensus metabolic network into a kinetic model. Despite crudely selected data, the model shows realistic control behaviour, a stable dynamic, and realistic response to perturbations in extracellular glucose concentrations. The paper concludes by outlining how new data can continuously be fed into the workflow and how iterative model building can assist in directing experiments.

Systematic Construction of Kinetic Models from Genome-Scale Metabolic Networks

Science.gov (United States)

Smallbone, Kieran; Klipp, Edda; Mendes, Pedro; Liebermeister, Wolfram

2013-01-01

The quantitative effects of environmental and genetic perturbations on metabolism can be studied in silico using kinetic models. We present a strategy for large-scale model construction based on a logical layering of data such as reaction fluxes, metabolite concentrations, and kinetic constants. The resulting models contain realistic standard rate laws and plausible parameters, adhere to the laws of thermodynamics, and reproduce a predefined steady state. These features have not been simultaneously achieved by previous workflows. We demonstrate the advantages and limitations of the workflow by translating the yeast consensus metabolic network into a kinetic model. Despite crudely selected data, the model shows realistic control behaviour, a stable dynamic, and realistic response to perturbations in extracellular glucose concentrations. The paper concludes by outlining how new data can continuously be fed into the workflow and how iterative model building can assist in directing experiments. PMID:24324546

A GIS analysis of suitability for construction aggregate recycling sites using regional transportation network and population density features

Science.gov (United States)

Robinson, G.R.; Kapo, K.E.

2004-01-01

Aggregate is used in road and building construction to provide bulk, strength, support, and wear resistance. Reclaimed asphalt pavement (RAP) and reclaimed Portland cement concrete (RPCC) are abundant and available sources of recycled aggregate. In this paper, current aggregate production operations in Virginia, Maryland, and the District of Columbia are used to develop spatial association models for the recycled aggregate industry with regional transportation network and population density features. The cost of construction aggregate to the end user is strongly influenced by the cost of transporting processed aggregate from the production site to the construction site. More than 60% of operations recycling aggregate in the mid-Atlantic study area are located within 4.8 km (3 miles) of an interstate highway. Transportation corridors provide both sites of likely road construction where aggregate is used and an efficient means to move both materials and on-site processing equipment back and forth from various work sites to the recycling operations. Urban and developing areas provide a high market demand for aggregate and a ready source of construction debris that may be processed into recycled aggregate. Most aggregate recycling operators in the study area are sited in counties with population densities exceeding 77 people/km2 (200 people/mile 2). No aggregate recycling operations are sited in counties with less than 19 people/km2 (50 people/mile2), reflecting the lack of sufficient long-term sources of construction debris to be used as an aggregate source, as well as the lack of a sufficient market demand for aggregate in most rural areas to locate a recycling operation there or justify the required investment in the equipment to process and produce recycled aggregate. Weights of evidence analyses (WofE), measuring correlation on an area-normalized basis, and weighted logistic regression (WLR), are used to model the distribution of RAP and RPCC operations relative

Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition

OpenAIRE

Li, Xiangang; Wu, Xihong

2014-01-01

Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical model has turned out to be more efficient than a shallow one. Motivated by previous research on constructing deep recurrent neural networks (RNNs), alternative deep LSTM architectures are proposed an...

Deep learning classification in asteroseismology using an improved neural network

DEFF Research Database (Denmark)

Hon, Marc; Stello, Dennis; Yu, Jie

2018-01-01

Deep learning in the form of 1D convolutional neural networks have previously been shown to be capable of efficiently classifying the evolutionary state of oscillating red giants into red giant branch stars and helium-core burning stars by recognizing visual features in their asteroseismic...... frequency spectra. We elaborate further on the deep learning method by developing an improved convolutional neural network classifier. To make our method useful for current and future space missions such as K2, TESS, and PLATO, we train classifiers that are able to classify the evolutionary states of lower...

Risks Analysis of Logistics Financial Business Based on Evidential Bayesian Network

Directory of Open Access Journals (Sweden)

Ying Yan

2013-01-01

Full Text Available Risks in logistics financial business are identified and classified. Making the failure of the business as the root node, a Bayesian network is constructed to measure the risk levels in the business. Three importance indexes are calculated to find the most important risks in the business. And more, considering the epistemic uncertainties in the risks, evidence theory associate with Bayesian network is used as an evidential network in the risk analysis of logistics finance. To find how much uncertainty in root node is produced by each risk, a new index, epistemic importance, is defined. Numerical examples show that the proposed methods could provide a lot of useful information. With the information, effective approaches could be found to control and avoid these sensitive risks, thus keep logistics financial business working more reliable. The proposed method also gives a quantitative measure of risk levels in logistics financial business, which provides guidance for the selection of financing solutions.

Dynamic ad hoc networks

CERN Document Server

Rashvand, Habib

2013-01-01

Motivated by the exciting new application paradigm of using amalgamated technologies of the Internet and wireless, the next generation communication networks (also called 'ubiquitous', 'complex' and 'unstructured' networking) are changing the way we develop and apply our future systems and services at home and on local, national and global scales. Whatever the interconnection - a WiMAX enabled networked mobile vehicle, MEMS or nanotechnology enabled distributed sensor systems, Vehicular Ad hoc Networking (VANET) or Mobile Ad hoc Networking (MANET) - all can be classified under new networking s

Surrogate-assisted identification of influences of network construction on evolving weighted functional networks

Science.gov (United States)

Stahn, Kirsten; Lehnertz, Klaus

2017-12-01

We aim at identifying factors that may affect the characteristics of evolving weighted networks derived from empirical observations. To this end, we employ various chains of analysis that are often used in field studies for a data-driven derivation and characterization of such networks. As an example, we consider fully connected, weighted functional brain networks before, during, and after epileptic seizures that we derive from multichannel electroencephalographic data recorded from epilepsy patients. For these evolving networks, we estimate clustering coefficient and average shortest path length in a time-resolved manner. Lastly, we make use of surrogate concepts that we apply at various levels of the chain of analysis to assess to what extent network characteristics are dominated by properties of the electroencephalographic recordings and/or the evolving weighted networks, which may be accessible more easily. We observe that characteristics are differently affected by the unavoidable referencing of the electroencephalographic recording, by the time-series-analysis technique used to derive the properties of network links, and whether or not networks were normalized. Importantly, for the majority of analysis settings, we observe temporal evolutions of network characteristics to merely reflect the temporal evolutions of mean interaction strengths. Such a property of the data may be accessible more easily, which would render the weighted network approach—as used here—as an overly complicated description of simple aspects of the data.

The influence of management and construction methods in the repair costs of Spain’s low-volume road network

Directory of Open Access Journals (Sweden)

Eutiquio Gallego

2016-06-01

Full Text Available This paper describes the entire process of the implementation of the Spanish low volume road network, including the design criteria, the construction techniques and the management policies during all the periods. The current situation of low volume roads in Spain was analyzed with respect to the legal framework and their actual condition. In addition, the budget required for the repair of 41 low volume roads throughout Spain was calculated in order to statistically analyze the influence of the pavement materials and the period of construction. The main conclusions were that low volume roads constructed during the 1970´s are currently those in the best state of repair and those requiring the lower repair costs, even lower than those constructed after 1980´s. In addition, low volume roads constructed with higher quality materials and using standardized techniques required five times lower repair costs than those made of lower quality materials.

Application of a neural network for reflectance spectrum classification

Science.gov (United States)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

Using Unsupervised Learning to Improve the Naive Bayes Classifier for Wireless Sensor Networks

NARCIS (Netherlands)

Zwartjes, G.J.; Havinga, Paul J.M.; Smit, Gerardus Johannes Maria; Hurink, Johann L.

2012-01-01

Online processing is essential for many sensor network applications. Sensor nodes can sample far more data than what can practically be transmitted using state of the art sensor network radios. Online processing, however, is complicated due to limited resources of individual nodes. The naive Bayes

Predicting Protein Function via Semantic Integration of Multiple Networks.

Science.gov (United States)

Yu, Guoxian; Fu, Guangyuan; Wang, Jun; Zhu, Hailong

2016-01-01

Determining the biological functions of proteins is one of the key challenges in the post-genomic era. The rapidly accumulated large volumes of proteomic and genomic data drives to develop computational models for automatically predicting protein function in large scale. Recent approaches focus on integrating multiple heterogeneous data sources and they often get better results than methods that use single data source alone. In this paper, we investigate how to integrate multiple biological data sources with the biological knowledge, i.e., Gene Ontology (GO), for protein function prediction. We propose a method, called SimNet, to Semantically integrate multiple functional association Networks derived from heterogenous data sources. SimNet firstly utilizes GO annotations of proteins to capture the semantic similarity between proteins and introduces a semantic kernel based on the similarity. Next, SimNet constructs a composite network, obtained as a weighted summation of individual networks, and aligns the network with the kernel to get the weights assigned to individual networks. Then, it applies a network-based classifier on the composite network to predict protein function. Experiment results on heterogenous proteomic data sources of Yeast, Human, Mouse, and Fly show that, SimNet not only achieves better (or comparable) results than other related competitive approaches, but also takes much less time. The Matlab codes of SimNet are available at https://sites.google.com/site/guoxian85/simnet.

A linear-RBF multikernel SVM to classify big text corpora.

Science.gov (United States)

Romero, R; Iglesias, E L; Borrajo, L

2015-01-01

Support vector machine (SVM) is a powerful technique for classification. However, SVM is not suitable for classification of large datasets or text corpora, because the training complexity of SVMs is highly dependent on the input size. Recent developments in the literature on the SVM and other kernel methods emphasize the need to consider multiple kernels or parameterizations of kernels because they provide greater flexibility. This paper shows a multikernel SVM to manage highly dimensional data, providing an automatic parameterization with low computational cost and improving results against SVMs parameterized under a brute-force search. The model consists in spreading the dataset into cohesive term slices (clusters) to construct a defined structure (multikernel). The new approach is tested on different text corpora. Experimental results show that the new classifier has good accuracy compared with the classic SVM, while the training is significantly faster than several other SVM classifiers.

Network survivability performance

Science.gov (United States)

1993-11-01

This technical report has been developed to address the survivability of telecommunications networks including services. It responds to the need for a common understanding of, and assessment techniques for network survivability, availability, integrity, and reliability. It provides a basis for designing and operating telecommunications networks to user expectations for network survivability and a foundation for continuing industry activities in the subject area. This report focuses on the survivability of both public and private networks and covers a wide range of users. Two frameworks are established for quantifying and categorizing service outages, and for classifying network survivability techniques and measures. The performance of the network survivability techniques is considered; however, recommended objectives are not established for network survivability performance.

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

Directory of Open Access Journals (Sweden)

Julià-Sapé Margarida

2010-02-01

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

AN INITIATIVE FOR CONSTRUCTION OF NEW-GENERATION LUNAR GLOBAL CONTROL NETWORK USING MULTI-MISSION DATA

Directory of Open Access Journals (Sweden)

K. Di

2017-07-01

Full Text Available A lunar global control network provides geodetic datum and control points for mapping of the lunar surface. The widely used Unified Lunar Control Network 2005 (ULCN2005 was built based on a combined photogrammetric solution of Clementine images acquired in 1994 and earlier photographic data. In this research, we propose an initiative for construction of a new-generation lunar global control network using multi-mission data newly acquired in the 21st century, which have much better resolution and precision than the old data acquired in the last century. The new control network will be based on a combined photogrammetric solution of an extended global image and laser altimetry network. The five lunar laser ranging retro-reflectors, which can be identified in LROC NAC images and have cm level 3D position accuracy, will be used as absolute control points in the least squares photogrammetric adjustment. Recently, a new radio total phase ranging method has been developed and used for high-precision positioning of Chang’e-3 lander; this shall offer a new absolute control point. Systematic methods and key techniques will be developed or enhanced, including rigorous and generic geometric modeling of orbital images, multi-scale feature extraction and matching among heterogeneous multi-mission remote sensing data, optimal selection of images at areas of multiple image coverages, and large-scale adjustment computation, etc. Based on the high-resolution new datasets and developed new techniques, the new generation of global control network is expected to have much higher accuracy and point density than the ULCN2005.

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

Science.gov (United States)

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

2017-08-01

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

Combining Biometric Fractal Pattern and Particle Swarm Optimization-Based Classifier for Fingerprint Recognition

Directory of Open Access Journals (Sweden)

Chia-Hung Lin

2010-01-01

Full Text Available This paper proposes combining the biometric fractal pattern and particle swarm optimization (PSO-based classifier for fingerprint recognition. Fingerprints have arch, loop, whorl, and accidental morphologies, and embed singular points, resulting in the establishment of fingerprint individuality. An automatic fingerprint identification system consists of two stages: digital image processing (DIP and pattern recognition. DIP is used to convert to binary images, refine out noise, and locate the reference point. For binary images, Katz's algorithm is employed to estimate the fractal dimension (FD from a two-dimensional (2D image. Biometric features are extracted as fractal patterns using different FDs. Probabilistic neural network (PNN as a classifier performs to compare the fractal patterns among the small-scale database. A PSO algorithm is used to tune the optimal parameters and heighten the accuracy. For 30 subjects in the laboratory, the proposed classifier demonstrates greater efficiency and higher accuracy in fingerprint recognition.

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

Directory of Open Access Journals (Sweden)

Aslam Pervez Memon

2013-04-01

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

Massively Multi-core Acceleration of a Document-Similarity Classifier to Detect Web Attacks

Energy Technology Data Exchange (ETDEWEB)

Ulmer, C; Gokhale, M; Top, P; Gallagher, B; Eliassi-Rad, T

2010-01-14

This paper describes our approach to adapting a text document similarity classifier based on the Term Frequency Inverse Document Frequency (TFIDF) metric to two massively multi-core hardware platforms. The TFIDF classifier is used to detect web attacks in HTTP data. In our parallel hardware approaches, we design streaming, real time classifiers by simplifying the sequential algorithm and manipulating the classifier's model to allow decision information to be represented compactly. Parallel implementations on the Tilera 64-core System on Chip and the Xilinx Virtex 5-LX FPGA are presented. For the Tilera, we employ a reduced state machine to recognize dictionary terms without requiring explicit tokenization, and achieve throughput of 37MB/s at slightly reduced accuracy. For the FPGA, we have developed a set of software tools to help automate the process of converting training data to synthesizable hardware and to provide a means of trading off between accuracy and resource utilization. The Xilinx Virtex 5-LX implementation requires 0.2% of the memory used by the original algorithm. At 166MB/s (80X the software) the hardware implementation is able to achieve Gigabit network throughput at the same accuracy as the original algorithm.

Unexpected properties of bandwidth choice when smoothing discrete data for constructing a functional data classifier

KAUST Repository

Carroll, Raymond J.

2013-12-01

The data functions that are studied in the course of functional data analysis are assembled from discrete data, and the level of smoothing that is used is generally that which is appropriate for accurate approximation of the conceptually smooth functions that were not actually observed. Existing literature shows that this approach is effective, and even optimal, when using functional data methods for prediction or hypothesis testing. However, in the present paper we show that this approach is not effective in classification problems. There a useful rule of thumb is that undersmoothing is often desirable, but there are several surprising qualifications to that approach. First, the effect of smoothing the training data can be more significant than that of smoothing the new data set to be classified; second, undersmoothing is not always the right approach, and in fact in some cases using a relatively large bandwidth can be more effective; and third, these perverse results are the consequence of very unusual properties of error rates, expressed as functions of smoothing parameters. For example, the orders of magnitude of optimal smoothing parameter choices depend on the signs and sizes of terms in an expansion of error rate, and those signs and sizes can vary dramatically from one setting to another, even for the same classifier.

Unexpected properties of bandwidth choice when smoothing discrete data for constructing a functional data classifier

KAUST Repository

Carroll, Raymond J.; Delaigle, Aurore; Hall, Peter

2013-01-01

The data functions that are studied in the course of functional data analysis are assembled from discrete data, and the level of smoothing that is used is generally that which is appropriate for accurate approximation of the conceptually smooth functions that were not actually observed. Existing literature shows that this approach is effective, and even optimal, when using functional data methods for prediction or hypothesis testing. However, in the present paper we show that this approach is not effective in classification problems. There a useful rule of thumb is that undersmoothing is often desirable, but there are several surprising qualifications to that approach. First, the effect of smoothing the training data can be more significant than that of smoothing the new data set to be classified; second, undersmoothing is not always the right approach, and in fact in some cases using a relatively large bandwidth can be more effective; and third, these perverse results are the consequence of very unusual properties of error rates, expressed as functions of smoothing parameters. For example, the orders of magnitude of optimal smoothing parameter choices depend on the signs and sizes of terms in an expansion of error rate, and those signs and sizes can vary dramatically from one setting to another, even for the same classifier.

Discriminative topological features reveal biological network mechanisms

Directory of Open Access Journals (Sweden)

Levovitz Chaya

2004-11-01

Full Text Available Abstract Background Recent genomic and bioinformatic advances have motivated the development of numerous network models intending to describe graphs of biological, technological, and sociological origin. In most cases the success of a model has been evaluated by how well it reproduces a few key features of the real-world data, such as degree distributions, mean geodesic lengths, and clustering coefficients. Often pairs of models can reproduce these features with indistinguishable fidelity despite being generated by vastly different mechanisms. In such cases, these few target features are insufficient to distinguish which of the different models best describes real world networks of interest; moreover, it is not clear a priori that any of the presently-existing algorithms for network generation offers a predictive description of the networks inspiring them. Results We present a method to assess systematically which of a set of proposed network generation algorithms gives the most accurate description of a given biological network. To derive discriminative classifiers, we construct a mapping from the set of all graphs to a high-dimensional (in principle infinite-dimensional "word space". This map defines an input space for classification schemes which allow us to state unambiguously which models are most descriptive of a given network of interest. Our training sets include networks generated from 17 models either drawn from the literature or introduced in this work. We show that different duplication-mutation schemes best describe the E. coli genetic network, the S. cerevisiae protein interaction network, and the C. elegans neuronal network, out of a set of network models including a linear preferential attachment model and a small-world model. Conclusions Our method is a first step towards systematizing network models and assessing their predictability, and we anticipate its usefulness for a number of communities.

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier.

Science.gov (United States)

Li, Qiang; Gu, Yu; Jia, Jing

2017-01-30

Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS) and support vector machine (SVM) algorithms in a quartz crystal microbalance (QCM)-based electronic nose (e-nose) we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3%) showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN) classifier (93.3%) and moving average-linear discriminant analysis (MA-LDA) classifier (87.6%). The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization) performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier

Directory of Open Access Journals (Sweden)

Qiang Li

2017-01-01

Full Text Available Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS and support vector machine (SVM algorithms in a quartz crystal microbalance (QCM-based electronic nose (e-nose we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3% showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN classifier (93.3% and moving average-linear discriminant analysis (MA-LDA classifier (87.6%. The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

A template for constructing Bayesian networks in forensic biology cases when considering activity level propositions.

Science.gov (United States)

Taylor, Duncan; Biedermann, Alex; Hicks, Tacha; Champod, Christophe

2018-03-01

The hierarchy of propositions has been accepted amongst the forensic science community for some time. It is also accepted that the higher up the hierarchy the propositions are, against which the scientist are competent to evaluate their results, the more directly useful the testimony will be to the court. Because each case represents a unique set of circumstances and findings, it is difficult to come up with a standard structure for evaluation. One common tool that assists in this task is Bayesian networks (BNs). There is much diversity in the way that BN can be constructed. In this work, we develop a template for BN construction that allows sufficient flexibility to address most cases, but enough commonality and structure that the flow of information in the BN is readily recognised at a glance. We provide seven steps that can be used to construct BNs within this structure and demonstrate how they can be applied, using a case example. Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

A Pattern Construction Scheme for Neural Network-Based Cognitive Communication

Directory of Open Access Journals (Sweden)

Ozgur Orcay

2011-01-01

Full Text Available Inefficient utilization of the frequency spectrum due to conventional regulatory limitations and physical performance limiting factors, mainly the Signal to Noise Ratio (SNR, are prominent restrictions in digital wireless communication. Pattern Based Communication System (PBCS is an adaptive and perceptual communication method based on a Cognitive Radio (CR approach. It intends an SNR oriented cognition mechanism in the physical layer for improvement of Link Spectral Efficiency (LSE. The key to this system is construction of optimal communication signals, which consist of encoded data in different pattern forms (waveforms depending on spectral availabilities. The signals distorted in the communication medium are recovered according to the pre-trained pattern glossary by the perceptual receiver. In this study, we have shown that it is possible to improve the bandwidth efficiency when largely uncorrelated signal patterns are chosen in order to form a glossary that represents symbols for different length data groups and the information can be recovered by the Artificial Neural Network (ANN in the receiver site.

An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network.

Science.gov (United States)

Shen, Xiaolei; Zhang, Jiachi; Yan, Chenjun; Zhou, Hong

2018-04-11

In this paper, we present a new automatic diagnosis method for facial acne vulgaris which is based on convolutional neural networks (CNNs). To overcome the shortcomings of previous methods which were the inability to classify enough types of acne vulgaris. The core of our method is to extract features of images based on CNNs and achieve classification by classifier. A binary-classifier of skin-and-non-skin is used to detect skin area and a seven-classifier is used to achieve the classification task of facial acne vulgaris and healthy skin. In the experiments, we compare the effectiveness of our CNN and the VGG16 neural network which is pre-trained on the ImageNet data set. We use a ROC curve to evaluate the performance of binary-classifier and use a normalized confusion matrix to evaluate the performance of seven-classifier. The results of our experiments show that the pre-trained VGG16 neural network is effective in extracting features from facial acne vulgaris images. And the features are very useful for the follow-up classifiers. Finally, we try applying the classifiers both based on the pre-trained VGG16 neural network to assist doctors in facial acne vulgaris diagnosis.

Quantum ensembles of quantum classifiers.

Science.gov (United States)

Schuld, Maria; Petruccione, Francesco

2018-02-09

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

Deep Classifiers-Based License Plate Detection, Localization and Recognition on GPU-Powered Mobile Platform

Directory of Open Access Journals (Sweden)

Syed Tahir Hussain Rizvi

2017-10-01

Full Text Available The realization of a deep neural architecture on a mobile platform is challenging, but can open up a number of possibilities for visual analysis applications. A neural network can be realized on a mobile platform by exploiting the computational power of the embedded GPU and simplifying the flow of a neural architecture trained on the desktop workstation or a GPU server. This paper presents an embedded platform-based Italian license plate detection and recognition system using deep neural classifiers. In this work, trained parameters of a highly precise automatic license plate recognition (ALPR system are imported and used to replicate the same neural classifiers on a Nvidia Shield K1 tablet. A CUDA-based framework is used to realize these neural networks. The flow of the trained architecture is simplified to perform the license plate recognition in real-time. Results show that the tasks of plate and character detection and localization can be performed in real-time on a mobile platform by simplifying the flow of the trained architecture. However, the accuracy of the simplified architecture would be decreased accordingly.

A neural network construction method for surrogate modeling of physics-based analysis

Science.gov (United States)

Sung, Woong Je

In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of

Recognition of power quality events by using multiwavelet-based neural networks

Energy Technology Data Exchange (ETDEWEB)

Kaewarsa, Suriya; Attakitmongcol, Kitti; Kulworawanichpong, Thanatchai [School of Electrical Engineering, Suranaree University of Technology, 111 University Avenue, Muang District, Nakhon Ratchasima 30000 (Thailand)

2008-05-15

Recognition of power quality events by analyzing the voltage and current waveform disturbances is a very important task for the power system monitoring. This paper presents a novel approach for the recognition of power quality disturbances using multiwavelet transform and neural networks. The proposed method employs the multiwavelet transform using multiresolution signal decomposition techniques working together with multiple neural networks using a learning vector quantization network as a powerful classifier. Various transient events are tested, such as voltage sag, swell, interruption, notching, impulsive transient, and harmonic distortion show that the classifier can detect and classify different power quality signal types efficiency. (author)

Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

Science.gov (United States)

Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

2018-04-02

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

Content-rich biological network constructed by mining PubMed abstracts

Directory of Open Access Journals (Sweden)

Sharp Burt M

2004-10-01

Full Text Available Abstract Background The integration of the rapidly expanding corpus of information about the genome, transcriptome, and proteome, engendered by powerful technological advances, such as microarrays, and the availability of genomic sequence from multiple species, challenges the grasp and comprehension of the scientific community. Despite the existence of text-mining methods that identify biological relationships based on the textual co-occurrence of gene/protein terms or similarities in abstract texts, knowledge of the underlying molecular connections on a large scale, which is prerequisite to understanding novel biological processes, lags far behind the accumulation of data. While computationally efficient, the co-occurrence-based approaches fail to characterize (e.g., inhibition or stimulation, directionality biological interactions. Programs with natural language processing (NLP capability have been created to address these limitations, however, they are in general not readily accessible to the public. Results We present a NLP-based text-mining approach, Chilibot, which constructs content-rich relationship networks among biological concepts, genes, proteins, or drugs. Amongst its features, suggestions for new hypotheses can be generated. Lastly, we provide evidence that the connectivity of molecular networks extracted from the biological literature follows the power-law distribution, indicating scale-free topologies consistent with the results of previous experimental analyses. Conclusions Chilibot distills scientific relationships from knowledge available throughout a wide range of biological domains and presents these in a content-rich graphical format, thus integrating general biomedical knowledge with the specialized knowledge and interests of the user. Chilibot http://www.chilibot.net can be accessed free of charge to academic users.

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

Science.gov (United States)

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

2015-11-01

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

Thai Finger-Spelling Recognition Using a Cascaded Classifier Based on Histogram of Orientation Gradient Features

Directory of Open Access Journals (Sweden)

Kittasil Silanon

2017-01-01

Full Text Available Hand posture recognition is an essential module in applications such as human-computer interaction (HCI, games, and sign language systems, in which performance and robustness are the primary requirements. In this paper, we proposed automatic classification to recognize 21 hand postures that represent letters in Thai finger-spelling based on Histogram of Orientation Gradient (HOG feature (which is applied with more focus on the information within certain region of the image rather than each single pixel and Adaptive Boost (i.e., AdaBoost learning technique to select the best weak classifier and to construct a strong classifier that consists of several weak classifiers to be cascaded in detection architecture. We collected 21 static hand posture images from 10 subjects for testing and training in Thai letters finger-spelling. The parameters for the training process have been adjusted in three experiments, false positive rates (FPR, true positive rates (TPR, and number of training stages (N, to achieve the most suitable training model for each hand posture. All cascaded classifiers are loaded into the system simultaneously to classify different hand postures. A correlation coefficient is computed to distinguish the hand postures that are similar. The system achieves approximately 78% accuracy on average on all classifier experiments.

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

Directory of Open Access Journals (Sweden)

Chernoded Andrey

2017-01-01

Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

Construction and analysis of a genome-scale metabolic network for Bacillus licheniformis WX-02.

Science.gov (United States)

Guo, Jing; Zhang, Hong; Wang, Cheng; Chang, Ji-Wei; Chen, Ling-Ling

2016-05-01

We constructed the genome-scale metabolic network of Bacillus licheniformis (B. licheniformis) WX-02 by combining genomic annotation, high-throughput phenotype microarray (PM) experiments and literature-based metabolic information. The accuracy of the metabolic network was assessed by an OmniLog PM experiment. The final metabolic model iWX1009 contains 1009 genes, 1141 metabolites and 1762 reactions, and the predicted metabolic phenotypes showed an agreement rate of 76.8% with experimental PM data. In addition, key metabolic features such as growth yield, utilization of different substrates and essential genes were identified by flux balance analysis. A total of 195 essential genes were predicted from LB medium, among which 149 were verified with the experimental essential gene set of B. subtilis 168. With the removal of 5 reactions from the network, pathways for poly-γ-glutamic acid (γ-PGA) synthesis were optimized and the γ-PGA yield reached 83.8 mmol/h. Furthermore, the important metabolites and pathways related to γ-PGA synthesis and bacterium growth were comprehensively analyzed. The present study provides valuable clues for exploring the metabolisms and metabolic regulation of γ-PGA synthesis in B. licheniformis WX-02. Copyright © 2016 Institut Pasteur. Published by Elsevier Masson SAS. All rights reserved.

Novel Two-Step Classifier for Torsades de Pointes Risk Stratification from Direct Features

Directory of Open Access Journals (Sweden)

Jaimit Parikh

2017-11-01

Full Text Available While pre-clinical Torsades de Pointes (TdP risk classifiers had initially been based on drug-induced block of hERG potassium channels, it is now well established that improved risk prediction can be achieved by considering block of non-hERG ion channels. The current multi-channel TdP classifiers can be categorized into two classes. First, the classifiers that take as input the values of drug-induced block of ion channels (direct features. Second, the classifiers that are built on features extracted from output of the drug-induced multi-channel blockage simulations in the in-silico models (derived features. The classifiers built on derived features have thus far not consistently provided increased prediction accuracies, and hence casts doubt on the value of such approaches given the cost of including biophysical detail. Here, we propose a new two-step method for TdP risk classification, referred to as Multi-Channel Blockage at Early After Depolarization (MCB@EAD. In the first step, we classified the compound that produced insufficient hERG block as non-torsadogenic. In the second step, the role of non-hERG channels to modulate TdP risk are considered by constructing classifiers based on direct or derived features at critical hERG block concentrations that generates EADs in the computational cardiac cell models. MCB@EAD provides comparable or superior TdP risk classification of the drugs from the direct features in tests against published methods. TdP risk for the drugs highly correlated to the propensity to generate EADs in the model. However, the derived features of the biophysical models did not improve the predictive capability for TdP risk assessment.

Construction and analysis of lncRNA-lncRNA synergistic networks to reveal clinically relevant lncRNAs in cancer.

Science.gov (United States)

Li, Yongsheng; Chen, Juan; Zhang, Jinwen; Wang, Zishan; Shao, Tingting; Jiang, Chunjie; Xu, Juan; Li, Xia

2015-09-22

Long non-coding RNAs (lncRNAs) play key roles in diverse biological processes. Moreover, the development and progression of cancer often involves the combined actions of several lncRNAs. Here we propose a multi-step method for constructing lncRNA-lncRNA functional synergistic networks (LFSNs) through co-regulation of functional modules having three features: common coexpressed genes of lncRNA pairs, enrichment in the same functional category and close proximity within protein interaction networks. Applied to three cancers, we constructed cancer-specific LFSNs and found that they exhibit a scale free and modular architecture. In addition, cancer-associated lncRNAs tend to be hubs and are enriched within modules. Although there is little synergistic pairing of lncRNAs across cancers, lncRNA pairs involved in the same cancer hallmarks by regulating same or different biological processes. Finally, we identify prognostic biomarkers within cancer lncRNA expression datasets using modules derived from LFSNs. In summary, this proof-of-principle study indicates synergistic lncRNA pairs can be identified through integrative analysis of genome-wide expression data sets and functional information.

Understanding characteristics in multivariate traffic flow time series from complex network structure

Science.gov (United States)

Yan, Ying; Zhang, Shen; Tang, Jinjun; Wang, Xiaofei

2017-07-01

Discovering dynamic characteristics in traffic flow is the significant step to design effective traffic managing and controlling strategy for relieving traffic congestion in urban cities. A new method based on complex network theory is proposed to study multivariate traffic flow time series. The data were collected from loop detectors on freeway during a year. In order to construct complex network from original traffic flow, a weighted Froenius norm is adopt to estimate similarity between multivariate time series, and Principal Component Analysis is implemented to determine the weights. We discuss how to select optimal critical threshold for networks at different hour in term of cumulative probability distribution of degree. Furthermore, two statistical properties of networks: normalized network structure entropy and cumulative probability of degree, are utilized to explore hourly variation in traffic flow. The results demonstrate these two statistical quantities express similar pattern to traffic flow parameters with morning and evening peak hours. Accordingly, we detect three traffic states: trough, peak and transitional hours, according to the correlation between two aforementioned properties. The classifying results of states can actually represent hourly fluctuation in traffic flow by analyzing annual average hourly values of traffic volume, occupancy and speed in corresponding hours.

Construction of Gene Regulatory Networks Using Recurrent Neural Networks and Swarm Intelligence.

Science.gov (United States)

Khan, Abhinandan; Mandal, Sudip; Pal, Rajat Kumar; Saha, Goutam

2016-01-01

We have proposed a methodology for the reverse engineering of biologically plausible gene regulatory networks from temporal genetic expression data. We have used established information and the fundamental mathematical theory for this purpose. We have employed the Recurrent Neural Network formalism to extract the underlying dynamics present in the time series expression data accurately. We have introduced a new hybrid swarm intelligence framework for the accurate training of the model parameters. The proposed methodology has been first applied to a small artificial network, and the results obtained suggest that it can produce the best results available in the contemporary literature, to the best of our knowledge. Subsequently, we have implemented our proposed framework on experimental (in vivo) datasets. Finally, we have investigated two medium sized genetic networks (in silico) extracted from GeneNetWeaver, to understand how the proposed algorithm scales up with network size. Additionally, we have implemented our proposed algorithm with half the number of time points. The results indicate that a reduction of 50% in the number of time points does not have an effect on the accuracy of the proposed methodology significantly, with a maximum of just over 15% deterioration in the worst case.

Constructing a two bands optical code-division multiple-access network of bipolar optical access codecs using Walsh-coded liquid crystal modulators

Science.gov (United States)

Yen, Chih-Ta; Huang, Jen-Fa; Chih, Ping-En

2014-08-01

We propose and experimentally demonstrated the two bands optical code-division multiple-access (OCDMA) network over bipolar Walsh-coded liquid-crystal modulators (LCMs) and driven by green light and red light lasers. Achieving system performance depends on the construction of a decoder that implements a true bipolar correlation using only unipolar signals and intensity detection for each band. We took advantage of the phase delay characteristics of LCMs to construct a prototype optical coder/decoder (codec). Matched and unmatched Walsh signature codes were evaluated to detect correlations among multiuser data in the access network. By using LCMs, a red and green laser light source was spectrally encoded and the summed light dots were complementary decoded. Favorable contrast on auto- and cross-correlations indicates that binary information symbols can be properly recovered using a balanced photodetector.

DETECTION OF CLAMPING FORCES ON MOUNTING A CONSTRUCTION VIA NEURAL NETWORK FOR THE FINITE-ELEMENT MODEL OF COMPRESSOR-CONDENSING UNIT

Directory of Open Access Journals (Sweden)

S. V. Krasnovskaya

2017-01-01

Full Text Available The article provides a brief review of a condensing unit and problems of mathematic simulation. It examines the influence of pretension on the strain-stress state of a construction by means of finiteelement modeling. The arrangement of a set of input-output data for neural network is also considered. The article investigates a possibility to predict mounting precision via neural networks; by analogy with the above calculations it examines the option to detect clamping forces on mounting compressorcondensing unit. 

Analysis of unintended events in hospitals: inter-rater reliability of constructing causal trees and classifying root causes

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, de H.C.W.; Zwaan, L.; Timmermans, D.R.M.; Groenewegen, P.P.; Wagner, C.

2009-01-01

BACKGROUND: Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis: is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

Analysis of unintended events in hospitals : inter-rater reliability of constructing causal trees and classifying root causes

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, R. de; Zwaan, L.; Groenewegen, P.P.; Timmermans, D.

2009-01-01

Background. Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis) is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

Analysis of unintended events in hospitals: inter-rater reliability of constructing causal trees and classifying root causes.

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, R. de; Zwaan, L.; Timmermans, D.; Groenewegen, P.; Wagner, C.

2009-01-01

Background: Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis) is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

PERFORMANCE COMPARISON FOR INTRUSION DETECTION SYSTEM USING NEURAL NETWORK WITH KDD DATASET

Directory of Open Access Journals (Sweden)

S. Devaraju

2014-04-01

Full Text Available Intrusion Detection Systems are challenging task for finding the user as normal user or attack user in any organizational information systems or IT Industry. The Intrusion Detection System is an effective method to deal with the kinds of problem in networks. Different classifiers are used to detect the different kinds of attacks in networks. In this paper, the performance of intrusion detection is compared with various neural network classifiers. In the proposed research the four types of classifiers used are Feed Forward Neural Network (FFNN, Generalized Regression Neural Network (GRNN, Probabilistic Neural Network (PNN and Radial Basis Neural Network (RBNN. The performance of the full featured KDD Cup 1999 dataset is compared with that of the reduced featured KDD Cup 1999 dataset. The MATLAB software is used to train and test the dataset and the efficiency and False Alarm Rate is measured. It is proved that the reduced dataset is performing better than the full featured dataset.

Immune system and zinc are associated with recurrent aphthous stomatitis. An assessment using a network-based approach.

Directory of Open Access Journals (Sweden)

César Rivera

2017-09-01

Full Text Available Objective: The aim of this research was to identify genes, proteins and processes from the biomedical information published on recurrent aphthous stomatitis (RAS using network-based foci. Methods: The clinical context was defined using MeSH terms for RAS and biomarkers, combined with words associated with risk. A set of protein coding genes was prioritized using the Génie web server and classified with PANTHER. For defining biologically relevant proteins, protein-protein interaction networks were constructed using Reactome database and Cytoscape. Top 20 proteins were then subjected to functional enrichment using STRING. Results: From 1,075,576 gene-abstract links, 1,491 genes were prioritized. Proteins were related to signaling molecule proteins (n=221, receptor proteins (n=221 and nucleic acid binding proteins (n=169. The network constructed with these proteins included 3,963 nodes and functional analysis showed that main processes involved immune system and zinc ion binding function. Conclusions: For the first time, bioinformatics tools were used for integrating pathways and networks associated with RAS. Molecules and processes associated with immune system recur robustly in all analyzed information. The molecular zinc ion binding function could be an area for exploring more specific and effective therapeutic interventions.

Functional enrichment analyses and construction of functional similarity networks with high confidence function prediction by PFP

Directory of Open Access Journals (Sweden)

Kihara Daisuke

2010-05-01

Full Text Available Abstract Background A new paradigm of biological investigation takes advantage of technologies that produce large high throughput datasets, including genome sequences, interactions of proteins, and gene expression. The ability of biologists to analyze and interpret such data relies on functional annotation of the included proteins, but even in highly characterized organisms many proteins can lack the functional evidence necessary to infer their biological relevance. Results Here we have applied high confidence function predictions from our automated prediction system, PFP, to three genome sequences, Escherichia coli, Saccharomyces cerevisiae, and Plasmodium falciparum (malaria. The number of annotated genes is increased by PFP to over 90% for all of the genomes. Using the large coverage of the function annotation, we introduced the functional similarity networks which represent the functional space of the proteomes. Four different functional similarity networks are constructed for each proteome, one each by considering similarity in a single Gene Ontology (GO category, i.e. Biological Process, Cellular Component, and Molecular Function, and another one by considering overall similarity with the funSim score. The functional similarity networks are shown to have higher modularity than the protein-protein interaction network. Moreover, the funSim score network is distinct from the single GO-score networks by showing a higher clustering degree exponent value and thus has a higher tendency to be hierarchical. In addition, examining function assignments to the protein-protein interaction network and local regions of genomes has identified numerous cases where subnetworks or local regions have functionally coherent proteins. These results will help interpreting interactions of proteins and gene orders in a genome. Several examples of both analyses are highlighted. Conclusion The analyses demonstrate that applying high confidence predictions from PFP

Dynamic Response Genes in CD4+ T Cells Reveal a Network of Interactive Proteins that Classifies Disease Activity in Multiple Sclerosis

Directory of Open Access Journals (Sweden)

Sandra Hellberg

2016-09-01

Full Text Available Multiple sclerosis (MS is a chronic inflammatory disease of the CNS and has a varying disease course as well as variable response to treatment. Biomarkers may therefore aid personalized treatment. We tested whether in vitro activation of MS patient-derived CD4+ T cells could reveal potential biomarkers. The dynamic gene expression response to activation was dysregulated in patient-derived CD4+ T cells. By integrating our findings with genome-wide association studies, we constructed a highly connected MS gene module, disclosing cell activation and chemotaxis as central components. Changes in several module genes were associated with differences in protein levels, which were measurable in cerebrospinal fluid and were used to classify patients from control individuals. In addition, these measurements could predict disease activity after 2 years and distinguish low and high responders to treatment in two additional, independent cohorts. While further validation is needed in larger cohorts prior to clinical implementation, we have uncovered a set of potentially promising biomarkers.

Competitive Learning Neural Network Ensemble Weighted by Predicted Performance

Science.gov (United States)

Ye, Qiang

2010-01-01

Ensemble approaches have been shown to enhance classification by combining the outputs from a set of voting classifiers. Diversity in error patterns among base classifiers promotes ensemble performance. Multi-task learning is an important characteristic for Neural Network classifiers. Introducing a secondary output unit that receives different…

Link prediction in multiplex online social networks

Science.gov (United States)

Jalili, Mahdi; Orouskhani, Yasin; Asgari, Milad; Alipourfard, Nazanin; Perc, Matjaž

2017-02-01

Online social networks play a major role in modern societies, and they have shaped the way social relationships evolve. Link prediction in social networks has many potential applications such as recommending new items to users, friendship suggestion and discovering spurious connections. Many real social networks evolve the connections in multiple layers (e.g. multiple social networking platforms). In this article, we study the link prediction problem in multiplex networks. As an example, we consider a multiplex network of Twitter (as a microblogging service) and Foursquare (as a location-based social network). We consider social networks of the same users in these two platforms and develop a meta-path-based algorithm for predicting the links. The connectivity information of the two layers is used to predict the links in Foursquare network. Three classical classifiers (naive Bayes, support vector machines (SVM) and K-nearest neighbour) are used for the classification task. Although the networks are not highly correlated in the layers, our experiments show that including the cross-layer information significantly improves the prediction performance. The SVM classifier results in the best performance with an average accuracy of 89%.

Subsurface event detection and classification using Wireless Signal Networks.

Science.gov (United States)

Yoon, Suk-Un; Ghazanfari, Ehsan; Cheng, Liang; Pamukcu, Sibel; Suleiman, Muhannad T

2012-11-05

Subsurface environment sensing and monitoring applications such as detection of water intrusion or a landslide, which could significantly change the physical properties of the host soil, can be accomplished using a novel concept, Wireless Signal Networks (WSiNs). The wireless signal networks take advantage of the variations of radio signal strength on the distributed underground sensor nodes of WSiNs to monitor and characterize the sensed area. To characterize subsurface environments for event detection and classification, this paper provides a detailed list and experimental data of soil properties on how radio propagation is affected by soil properties in subsurface communication environments. Experiments demonstrated that calibrated wireless signal strength variations can be used as indicators to sense changes in the subsurface environment. The concept of WSiNs for the subsurface event detection is evaluated with applications such as detection of water intrusion, relative density change, and relative motion using actual underground sensor nodes. To classify geo-events using the measured signal strength as a main indicator of geo-events, we propose a window-based minimum distance classifier based on Bayesian decision theory. The window-based classifier for wireless signal networks has two steps: event detection and event classification. With the event detection, the window-based classifier classifies geo-events on the event occurring regions that are called a classification window. The proposed window-based classification method is evaluated with a water leakage experiment in which the data has been measured in laboratory experiments. In these experiments, the proposed detection and classification method based on wireless signal network can detect and classify subsurface events.

Bayesian state space models for dynamic genetic network construction across multiple tissues.

Science.gov (United States)

Liang, Yulan; Kelemen, Arpad

2016-08-01

Construction of gene-gene interaction networks and potential pathways is a challenging and important problem in genomic research for complex diseases while estimating the dynamic changes of the temporal correlations and non-stationarity are the keys in this process. In this paper, we develop dynamic state space models with hierarchical Bayesian settings to tackle this challenge for inferring the dynamic profiles and genetic networks associated with disease treatments. We treat both the stochastic transition matrix and the observation matrix time-variant and include temporal correlation structures in the covariance matrix estimations in the multivariate Bayesian state space models. The unevenly spaced short time courses with unseen time points are treated as hidden state variables. Hierarchical Bayesian approaches with various prior and hyper-prior models with Monte Carlo Markov Chain and Gibbs sampling algorithms are used to estimate the model parameters and the hidden state variables. We apply the proposed Hierarchical Bayesian state space models to multiple tissues (liver, skeletal muscle, and kidney) Affymetrix time course data sets following corticosteroid (CS) drug administration. Both simulation and real data analysis results show that the genomic changes over time and gene-gene interaction in response to CS treatment can be well captured by the proposed models. The proposed dynamic Hierarchical Bayesian state space modeling approaches could be expanded and applied to other large scale genomic data, such as next generation sequence (NGS) combined with real time and time varying electronic health record (EHR) for more comprehensive and robust systematic and network based analysis in order to transform big biomedical data into predictions and diagnostics for precision medicine and personalized healthcare with better decision making and patient outcomes.

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

2012-01-01

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

Comparative analysis of instance selection algorithms for instance-based classifiers in the context of medical decision support

International Nuclear Information System (INIS)

Mazurowski, Maciej A; Tourassi, Georgia D; Malof, Jordan M

2011-01-01

When constructing a pattern classifier, it is important to make best use of the instances (a.k.a. cases, examples, patterns or prototypes) available for its development. In this paper we present an extensive comparative analysis of algorithms that, given a pool of previously acquired instances, attempt to select those that will be the most effective to construct an instance-based classifier in terms of classification performance, time efficiency and storage requirements. We evaluate seven previously proposed instance selection algorithms and compare their performance to simple random selection of instances. We perform the evaluation using k-nearest neighbor classifier and three classification problems: one with simulated Gaussian data and two based on clinical databases for breast cancer detection and diagnosis, respectively. Finally, we evaluate the impact of the number of instances available for selection on the performance of the selection algorithms and conduct initial analysis of the selected instances. The experiments show that for all investigated classification problems, it was possible to reduce the size of the original development dataset to less than 3% of its initial size while maintaining or improving the classification performance. Random mutation hill climbing emerges as the superior selection algorithm. Furthermore, we show that some previously proposed algorithms perform worse than random selection. Regarding the impact of the number of instances available for the classifier development on the performance of the selection algorithms, we confirm that the selection algorithms are generally more effective as the pool of available instances increases. In conclusion, instance selection is generally beneficial for instance-based classifiers as it can improve their performance, reduce their storage requirements and improve their response time. However, choosing the right selection algorithm is crucial.

Fine-grained vehicle type recognition based on deep convolution neural networks

Directory of Open Access Journals (Sweden)

Hongcai CHEN

2017-12-01

Full Text Available Public security and traffic department put forward higher requirements for real-time performance and accuracy of vehicle type recognition in complex traffic scenes. Aiming at the problems of great plice forces occupation, low retrieval efficiency, and lacking of intelligence for dealing with false license, fake plate vehicles and vehicles without plates, this paper proposes a vehicle type fine-grained recognition method based GoogleNet deep convolution neural networks. The filter size and numbers of convolution neural network are designed, the activation function and vehicle type classifier are optimally selected, and a new network framework is constructed for vehicle type fine-grained recognition. The experimental results show that the proposed method has 97% accuracy for vehicle type fine-grained recognition and has greater improvement than the original GoogleNet model. Moreover, the new model effectively reduces the number of training parameters, and saves computer memory. Fine-grained vehicle type recognition can be used in intelligent traffic management area, and has important theoretical research value and practical significance.

IAEA safeguards and classified materials

International Nuclear Information System (INIS)

Pilat, J.F.; Eccleston, G.W.; Fearey, B.L.; Nicholas, N.J.; Tape, J.W.; Kratzer, M.

1997-01-01

The international community in the post-Cold War period has suggested that the International Atomic Energy Agency (IAEA) utilize its expertise in support of the arms control and disarmament process in unprecedented ways. The pledges of the US and Russian presidents to place excess defense materials, some of which are classified, under some type of international inspections raises the prospect of using IAEA safeguards approaches for monitoring classified materials. A traditional safeguards approach, based on nuclear material accountancy, would seem unavoidably to reveal classified information. However, further analysis of the IAEA's safeguards approaches is warranted in order to understand fully the scope and nature of any problems. The issues are complex and difficult, and it is expected that common technical understandings will be essential for their resolution. Accordingly, this paper examines and compares traditional safeguards item accounting of fuel at a nuclear power station (especially spent fuel) with the challenges presented by inspections of classified materials. This analysis is intended to delineate more clearly the problems as well as reveal possible approaches, techniques, and technologies that could allow the adaptation of safeguards to the unprecedented task of inspecting classified materials. It is also hoped that a discussion of these issues can advance ongoing political-technical debates on international inspections of excess classified materials

Building a glaucoma interaction network using a text mining approach.

Science.gov (United States)

Soliman, Maha; Nasraoui, Olfa; Cooper, Nigel G F

2016-01-01

The volume of biomedical literature and its underlying knowledge base is rapidly expanding, making it beyond the ability of a single human being to read through all the literature. Several automated methods have been developed to help make sense of this dilemma. The present study reports on the results of a text mining approach to extract gene interactions from the data warehouse of published experimental results which are then used to benchmark an interaction network associated with glaucoma. To the best of our knowledge, there is, as yet, no glaucoma interaction network derived solely from text mining approaches. The presence of such a network could provide a useful summative knowledge base to complement other forms of clinical information related to this disease. A glaucoma corpus was constructed from PubMed Central and a text mining approach was applied to extract genes and their relations from this corpus. The extracted relations between genes were checked using reference interaction databases and classified generally as known or new relations. The extracted genes and relations were then used to construct a glaucoma interaction network. Analysis of the resulting network indicated that it bears the characteristics of a small world interaction network. Our analysis showed the presence of seven glaucoma linked genes that defined the network modularity. A web-based system for browsing and visualizing the extracted glaucoma related interaction networks is made available at http://neurogene.spd.louisville.edu/GlaucomaINViewer/Form1.aspx. This study has reported the first version of a glaucoma interaction network using a text mining approach. The power of such an approach is in its ability to cover a wide range of glaucoma related studies published over many years. Hence, a bigger picture of the disease can be established. To the best of our knowledge, this is the first glaucoma interaction network to summarize the known literature. The major findings were a set of

[Terahertz Spectroscopic Identification with Deep Belief Network].

Science.gov (United States)

Ma, Shuai; Shen, Tao; Wang, Rui-qi; Lai, Hua; Yu, Zheng-tao

2015-12-01

Feature extraction and classification are the key issues of terahertz spectroscopy identification. Because many materials have no apparent absorption peaks in the terahertz band, it is difficult to extract theirs terahertz spectroscopy feature and identify. To this end, a novel of identify terahertz spectroscopy approach with Deep Belief Network (DBN) was studied in this paper, which combines the advantages of DBN and K-Nearest Neighbors (KNN) classifier. Firstly, cubic spline interpolation and S-G filter were used to normalize the eight kinds of substances (ATP, Acetylcholine Bromide, Bifenthrin, Buprofezin, Carbazole, Bleomycin, Buckminster and Cylotriphosphazene) terahertz transmission spectra in the range of 0.9-6 THz. Secondly, the DBN model was built by two restricted Boltzmann machine (RBM) and then trained layer by layer using unsupervised approach. Instead of using handmade features, the DBN was employed to learn suitable features automatically with raw input data. Finally, a KNN classifier was applied to identify the terahertz spectrum. Experimental results show that using the feature learned by DBN can identify the terahertz spectrum of different substances with the recognition rate of over 90%, which demonstrates that the proposed method can automatically extract the effective features of terahertz spectrum. Furthermore, this KNN classifier was compared with others (BP neural network, SOM neural network and RBF neural network). Comparisons showed that the recognition rate of KNN classifier is better than the other three classifiers. Using the approach that automatic extract terahertz spectrum features by DBN can greatly reduce the workload of feature extraction. This proposed method shows a promising future in the application of identifying the mass terahertz spectroscopy.