WorldWideScience

Sample records for network classification model

  1. A Pruning Neural Network Model in Credit Classification Analysis

    Directory of Open Access Journals (Sweden)

    Yajiao Tang

    2018-01-01

    Full Text Available Nowadays, credit classification models are widely applied because they can help financial decision-makers to handle credit classification issues. Among them, artificial neural networks (ANNs have been widely accepted as the convincing methods in the credit industry. In this paper, we propose a pruning neural network (PNN and apply it to solve credit classification problem by adopting the well-known Australian and Japanese credit datasets. The model is inspired by synaptic nonlinearity of a dendritic tree in a biological neural model. And it is trained by an error back-propagation algorithm. The model is capable of realizing a neuronal pruning function by removing the superfluous synapses and useless dendrites and forms a tidy dendritic morphology at the end of learning. Furthermore, we utilize logic circuits (LCs to simulate the dendritic structures successfully which makes PNN be implemented on the hardware effectively. The statistical results of our experiments have verified that PNN obtains superior performance in comparison with other classical algorithms in terms of accuracy and computational efficiency.

  2. Model for Detection and Classification of DDoS Traffic Based on Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    D. Peraković

    2017-06-01

    Full Text Available Detection of DDoS (Distributed Denial of Service traffic is of great importance for the availability protection of services and other information and communication resources. The research presented in this paper shows the application of artificial neural networks in the development of detection and classification model for three types of DDoS attacks and legitimate network traffic. Simulation results of developed model showed accuracy of 95.6% in classification of pre-defined classes of traffic.

  3. Median Filter Noise Reduction of Image and Backpropagation Neural Network Model for Cervical Cancer Classification

    Science.gov (United States)

    Wutsqa, D. U.; Marwah, M.

    2017-06-01

    In this paper, we consider spatial operation median filter to reduce the noise in the cervical images yielded by colposcopy tool. The backpropagation neural network (BPNN) model is applied to the colposcopy images to classify cervical cancer. The classification process requires an image extraction by using a gray level co-occurrence matrix (GLCM) method to obtain image features that are used as inputs of BPNN model. The advantage of noise reduction is evaluated by comparing the performances of BPNN models with and without spatial operation median filter. The experimental result shows that the spatial operation median filter can improve the accuracy of the BPNN model for cervical cancer classification.

  4. Butterfly Classification by HSI and RGB Color Models Using Neural Networks

    Directory of Open Access Journals (Sweden)

    Jorge E. Grajales-Múnera

    2013-11-01

    Full Text Available This study aims the classification of Butterfly species through the implementation of Neural Networks and Image Processing. A total of 9 species of Morpho genre which has blue as a characteristic color are processed. For Butterfly segmentation we used image processing tools such as: Binarization, edge processing and mathematical morphology. For data processing RGB values are obtained for every image which are converted to HSI color model to identify blue pixels and obtain the data to the proposed Neural Networks: Back-Propagation and Perceptron. For analysis and verification of results confusion matrix are built and analyzed with the results of neural networks with the lowest error levels. We obtain error levels close to 1% in classification of some Butterfly species.

  5. Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

    Science.gov (United States)

    Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

    2016-01-01

    Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

  6. Aphasia Classification Using Neural Networks

    DEFF Research Database (Denmark)

    Axer, H.; Jantzen, Jan; Berks, G.

    2000-01-01

    A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests...

  7. 2D Modeling and Classification of Extended Objects in a Network of HRR Radars

    NARCIS (Netherlands)

    Fasoula, A.

    2011-01-01

    In this thesis, the modeling of extended objects with low-dimensional representations of their 2D geometry is addressed. The ultimate objective is the classification of the objects using libraries of such compact 2D object models that are much smaller than in the state-of-the-art classification

  8. 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...

  9. ACOUSTIC CLASSIFICATION OF FRESHWATER FISH SPECIES USING ARTIFICIAL NEURAL NETWORK: EVALUATION OF THE MODEL PERFORMANCE

    Directory of Open Access Journals (Sweden)

    Zulkarnaen Fahmi

    2013-06-01

    Full Text Available Hydroacoustic techniques are a valuable tool for the stock assessments of many fish species. Nonetheless, such techniques are limited by problems of species identification. Several methods and techniques have been used in addressing the problem of acoustic identification species and one of them is Artificial Neural Networks (ANNs. In this paper, Back propagation (BP and Multi Layer Perceptron (MLP of the Artificial Neural Network were used to classify carp (Cyprinus carpio, tilapia (Oreochromis niloticus, and catfish (Pangasius hypothalmus. Classification was done using a set of descriptors extracted from the acoustic data records, i.e. Volume Back scattering (Sv, Target Strength (TS, Area Back scattering Strength, Skewness, Kurtosis, Depth, Height and Relative altitude. The results showed that the Multi Layer Perceptron approach performed better than the Back propagation. The classification rates was 85.7% with the multi layer perceptron (MLP compared to 84.8% with back propagation (BP ANN.

  10. A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification.

    Science.gov (United States)

    Yildirim, Özal

    2018-05-01

    Long-short term memory networks (LSTMs), which have recently emerged in sequential data analysis, are the most widely used type of recurrent neural networks (RNNs) architecture. Progress on the topic of deep learning includes successful adaptations of deep versions of these architectures. In this study, a new model for deep bidirectional LSTM network-based wavelet sequences called DBLSTM-WS was proposed for classifying electrocardiogram (ECG) signals. For this purpose, a new wavelet-based layer is implemented to generate ECG signal sequences. The ECG signals were decomposed into frequency sub-bands at different scales in this layer. These sub-bands are used as sequences for the input of LSTM networks. New network models that include unidirectional (ULSTM) and bidirectional (BLSTM) structures are designed for performance comparisons. Experimental studies have been performed for five different types of heartbeats obtained from the MIT-BIH arrhythmia database. These five types are Normal Sinus Rhythm (NSR), Ventricular Premature Contraction (VPC), Paced Beat (PB), Left Bundle Branch Block (LBBB), and Right Bundle Branch Block (RBBB). The results show that the DBLSTM-WS model gives a high recognition performance of 99.39%. It has been observed that the wavelet-based layer proposed in the study significantly improves the recognition performance of conventional networks. This proposed network structure is an important approach that can be applied to similar signal processing problems. Copyright © 2018 Elsevier Ltd. All rights reserved.

  11. Binary Classification Method of Social Network Users

    Directory of Open Access Journals (Sweden)

    I. A. Poryadin

    2017-01-01

    Full Text Available The subject of research is a binary classification method of social network users based on the data analysis they have placed. Relevance of the task to gain information about a person by examining the content of his/her pages in social networks is exemplified. The most common approach to its solution is a visual browsing. The order of the regional authority in our country illustrates that its using in school education is needed. The article shows restrictions on the visual browsing of pupil’s pages in social networks as a tool for the teacher and the school psychologist and justifies that a process of social network users’ data analysis should be automated. Explores publications, which describe such data acquisition, processing, and analysis methods and considers their advantages and disadvantages. The article also gives arguments to support a proposal to study the classification method of social network users. One such method is credit scoring, which is used in banks and credit institutions to assess the solvency of clients. Based on the high efficiency of the method there is a proposal for significant expansion of its using in other areas of society. The possibility to use logistic regression as the mathematical apparatus of the proposed method of binary classification has been justified. Such an approach enables taking into account the different types of data extracted from social networks. Among them: the personal user data, information about hobbies, friends, graphic and text information, behaviour characteristics. The article describes a number of existing methods of data transformation that can be applied to solve the problem. An experiment of binary gender-based classification of social network users is described. A logistic model obtained for this example includes multiple logical variables obtained by transforming the user surnames. This experiment confirms the feasibility of the proposed method. Further work is to define a system

  12. Gas Classification Using Deep Convolutional Neural Networks

    Science.gov (United States)

    Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

    2018-01-01

    In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP). PMID:29316723

  13. Gas Classification Using Deep Convolutional Neural Networks.

    Science.gov (United States)

    Peng, Pai; Zhao, Xiaojin; Pan, Xiaofang; Ye, Wenbin

    2018-01-08

    In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

  14. Latent classification models

    DEFF Research Database (Denmark)

    Langseth, Helge; Nielsen, Thomas Dyhre

    2005-01-01

    parametric family ofdistributions.  In this paper we propose a new set of models forclassification in continuous domains, termed latent classificationmodels. The latent classification model can roughly be seen ascombining the \\NB model with a mixture of factor analyzers,thereby relaxing the assumptions...... classification model, and wedemonstrate empirically that the accuracy of the proposed model issignificantly higher than the accuracy of other probabilisticclassifiers....

  15. Classification of Beta-lactamases and penicillin binding proteins using ligand-centric network models.

    Directory of Open Access Journals (Sweden)

    Hakime Öztürk

    Full Text Available β-lactamase mediated antibiotic resistance is an important health issue and the discovery of new β-lactam type antibiotics or β-lactamase inhibitors is an area of intense research. Today, there are about a thousand β-lactamases due to the evolutionary pressure exerted by these ligands. While β-lactamases hydrolyse the β-lactam ring of antibiotics, rendering them ineffective, Penicillin-Binding Proteins (PBPs, which share high structural similarity with β-lactamases, also confer antibiotic resistance to their host organism by acquiring mutations that allow them to continue their participation in cell wall biosynthesis. In this paper, we propose a novel approach to include ligand sharing information for classifying and clustering β-lactamases and PBPs in an effort to elucidate the ligand induced evolution of these β-lactam binding proteins. We first present a detailed summary of the β-lactamase and PBP families in the Protein Data Bank, as well as the compounds they bind to. Then, we build two different types of networks in which the proteins are represented as nodes, and two proteins are connected by an edge with a weight that depends on the number of shared identical or similar ligands. These models are analyzed under three different edge weight settings, namely unweighted, weighted, and normalized weighted. A detailed comparison of these six networks showed that the use of ligand sharing information to cluster proteins resulted in modules comprising proteins with not only sequence similarity but also functional similarity. Consideration of ligand similarity highlighted some interactions that were not detected in the identical ligand network. Analysing the β-lactamases and PBPs using ligand-centric network models enabled the identification of novel relationships, suggesting that these models can be used to examine other protein families to obtain information on their ligand induced evolutionary paths.

  16. Deep Recurrent Neural Networks for Supernovae Classification

    Science.gov (United States)

    Charnock, Tom; Moss, Adam

    2017-03-01

    We apply deep recurrent neural networks, which are capable of learning complex sequential information, to classify supernovae (code available at https://github.com/adammoss/supernovae). The observational time and filter fluxes are used as inputs to the network, but since the inputs are agnostic, additional data such as host galaxy information can also be included. Using the Supernovae Photometric Classification Challenge (SPCC) data, we find that deep networks are capable of learning about light curves, however the performance of the network is highly sensitive to the amount of training data. For a training size of 50% of the representational SPCC data set (around 104 supernovae) we obtain a type-Ia versus non-type-Ia classification accuracy of 94.7%, an area under the Receiver Operating Characteristic curve AUC of 0.986 and an SPCC figure-of-merit F 1 = 0.64. When using only the data for the early-epoch challenge defined by the SPCC, we achieve a classification accuracy of 93.1%, AUC of 0.977, and F 1 = 0.58, results almost as good as with the whole light curve. By employing bidirectional neural networks, we can acquire impressive classification results between supernovae types I, II and III at an accuracy of 90.4% and AUC of 0.974. We also apply a pre-trained model to obtain classification probabilities as a function of time and show that it can give early indications of supernovae type. Our method is competitive with existing algorithms and has applications for future large-scale photometric surveys.

  17. 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.

  18. Track classification within wireless sensor network

    Science.gov (United States)

    Doumerc, Robin; Pannetier, Benjamin; Moras, Julien; Dezert, Jean; Canevet, Loic

    2017-05-01

    In this paper, we present our study on track classification by taking into account environmental information and target estimated states. The tracker uses several motion model adapted to different target dynamics (pedestrian, ground vehicle and SUAV, i.e. small unmanned aerial vehicle) and works in centralized architecture. The main idea is to explore both: classification given by heterogeneous sensors and classification obtained with our fusion module. The fusion module, presented in his paper, provides a class on each track according to track location, velocity and associated uncertainty. To model the likelihood on each class, a fuzzy approach is used considering constraints on target capability to move in the environment. Then the evidential reasoning approach based on Dempster-Shafer Theory (DST) is used to perform a time integration of this classifier output. The fusion rules are tested and compared on real data obtained with our wireless sensor network.In order to handle realistic ground target tracking scenarios, we use an autonomous smart computer deposited in the surveillance area. After the calibration step of the heterogeneous sensor network, our system is able to handle real data from a wireless ground sensor network. The performance of this system is evaluated in a real exercise for intelligence operation ("hunter hunt" scenario).

  19. Sentiment classification technology based on Markov logic networks

    Science.gov (United States)

    He, Hui; Li, Zhigang; Yao, Chongchong; Zhang, Weizhe

    2016-07-01

    With diverse online media emerging, there is a growing concern of sentiment classification problem. At present, text sentiment classification mainly utilizes supervised machine learning methods, which feature certain domain dependency. On the basis of Markov logic networks (MLNs), this study proposed a cross-domain multi-task text sentiment classification method rooted in transfer learning. Through many-to-one knowledge transfer, labeled text sentiment classification, knowledge was successfully transferred into other domains, and the precision of the sentiment classification analysis in the text tendency domain was improved. The experimental results revealed the following: (1) the model based on a MLN demonstrated higher precision than the single individual learning plan model. (2) Multi-task transfer learning based on Markov logical networks could acquire more knowledge than self-domain learning. The cross-domain text sentiment classification model could significantly improve the precision and efficiency of text sentiment classification.

  20. Dynamic Latent Classification Model

    DEFF Research Database (Denmark)

    Zhong, Shengtong; Martínez, Ana M.; Nielsen, Thomas Dyhre

    as possible. Motivated by this problem setting, we propose a generative model for dynamic classification in continuous domains. At each time point the model can be seen as combining a naive Bayes model with a mixture of factor analyzers (FA). The latent variables of the FA are used to capture the dynamics...

  1. Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer.

    Science.gov (United States)

    Gutiérrez, Salvador; Tardaguila, Javier; Fernández-Novales, Juan; Diago, María P

    2015-01-01

    The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network's modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves

  2. Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer.

    Directory of Open Access Journals (Sweden)

    Salvador Gutiérrez

    Full Text Available The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network's modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L. varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years

  3. Neural network classification of sweet potato embryos

    Science.gov (United States)

    Molto, Enrique; Harrell, Roy C.

    1993-05-01

    Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

  4. The attractor recurrent neural network based on fuzzy functions: An effective model for the classification of lung abnormalities.

    Science.gov (United States)

    Khodabakhshi, Mohammad Bagher; Moradi, Mohammad Hassan

    2017-05-01

    The respiratory system dynamic is of high significance when it comes to the detection of lung abnormalities, which highlights the importance of presenting a reliable model for it. In this paper, we introduce a novel dynamic modelling method for the characterization of the lung sounds (LS), based on the attractor recurrent neural network (ARNN). The ARNN structure allows the development of an effective LS model. Additionally, it has the capability to reproduce the distinctive features of the lung sounds using its formed attractors. Furthermore, a novel ARNN topology based on fuzzy functions (FFs-ARNN) is developed. Given the utility of the recurrent quantification analysis (RQA) as a tool to assess the nature of complex systems, it was used to evaluate the performance of both the ARNN and the FFs-ARNN models. The experimental results demonstrate the effectiveness of the proposed approaches for multichannel LS analysis. In particular, a classification accuracy of 91% was achieved using FFs-ARNN with sequences of RQA features. Copyright © 2017 Elsevier Ltd. All rights reserved.

  5. Modelling for Understanding AND for Prediction/Classification--The Power of Neural Networks in Research

    Science.gov (United States)

    Cascallar, Eduardo; Musso, Mariel; Kyndt, Eva; Dochy, Filip

    2014-01-01

    Two articles, Edelsbrunner and, Schneider (2013), and Nokelainen and Silander (2014) comment on Musso, Kyndt, Cascallar, and Dochy (2013). Several relevant issues are raised and some important clarifications are made in response to both commentaries. Predictive systems based on artificial neural networks continue to be the focus of current…

  6. Predicting student satisfaction with courses based on log data from a virtual learning environment – a neural network and classification tree model

    Directory of Open Access Journals (Sweden)

    Ivana Đurđević Babić

    2015-03-01

    Full Text Available Student satisfaction with courses in academic institutions is an important issue and is recognized as a form of support in ensuring effective and quality education, as well as enhancing student course experience. This paper investigates whether there is a connection between student satisfaction with courses and log data on student courses in a virtual learning environment. Furthermore, it explores whether a successful classification model for predicting student satisfaction with course can be developed based on course log data and compares the results obtained from implemented methods. The research was conducted at the Faculty of Education in Osijek and included analysis of log data and course satisfaction on a sample of third and fourth year students. Multilayer Perceptron (MLP with different activation functions and Radial Basis Function (RBF neural networks as well as classification tree models were developed, trained and tested in order to classify students into one of two categories of course satisfaction. Type I and type II errors, and input variable importance were used for model comparison and classification accuracy. The results indicate that a successful classification model using tested methods can be created. The MLP model provides the highest average classification accuracy and the lowest preference in misclassification of students with a low level of course satisfaction, although a t-test for the difference in proportions showed that the difference in performance between the compared models is not statistically significant. Student involvement in forum discussions is recognized as a valuable predictor of student satisfaction with courses in all observed models.

  7. Automatic Amharic text news classification: Aneural networks ...

    African Journals Online (AJOL)

    School of Computing and Electrical Engineering, Institute of Technology, Bahir Dar University, Bahir Dar ... The study is on classification of Amharic news automatically using neural networks approach. Learning Vector ... INTRODUCTION.

  8. Classification and Analysis of Computer Network Traffic

    DEFF Research Database (Denmark)

    Bujlow, Tomasz

    2014-01-01

    various classification modes (decision trees, rulesets, boosting, softening thresholds) regarding the classification accuracy and the time required to create the classifier. We showed how to use our VBS tool to obtain per-flow, per-application, and per-content statistics of traffic in computer networks...

  9. Classification of Franchise Networks in the Retail Trade

    Directory of Open Access Journals (Sweden)

    Grygorenko Tetyana M.

    2016-11-01

    Full Text Available The article clarifies the definitions of the concepts of «franchise network», «franchise trade network», «franchise retail network», which is substantiated by the lack of a unified approach to interpretation of these concepts. The classification of franchise networks in the retail trade taking into account peculiarities in the operation of this sub-sector of the market economy is developed; classification attributes are identified and types of franchise retail chains are characterized. The proposed classification of franchise retail networks is adapted to the economic situation in Ukraine and specifics of the national franchise relations. It will facilitate a deeper understanding of the essence of the formation and operation of franchise retail chains and also help Ukrainian entrepreneurs to justify choosing the most suitable for them franchising model and allow to establish such a network with regard to various attributes using a complex approach.

  10. A neural network for noise correlation classification

    Science.gov (United States)

    Paitz, Patrick; Gokhberg, Alexey; Fichtner, Andreas

    2018-02-01

    We present an artificial neural network (ANN) for the classification of ambient seismic noise correlations into two categories, suitable and unsuitable for noise tomography. By using only a small manually classified data subset for network training, the ANN allows us to classify large data volumes with low human effort and to encode the valuable subjective experience of data analysts that cannot be captured by a deterministic algorithm. Based on a new feature extraction procedure that exploits the wavelet-like nature of seismic time-series, we efficiently reduce the dimensionality of noise correlation data, still keeping relevant features needed for automated classification. Using global- and regional-scale data sets, we show that classification errors of 20 per cent or less can be achieved when the network training is performed with as little as 3.5 per cent and 16 per cent of the data sets, respectively. Furthermore, the ANN trained on the regional data can be applied to the global data, and vice versa, without a significant increase of the classification error. An experiment where four students manually classified the data, revealed that the classification error they would assign to each other is substantially larger than the classification error of the ANN (>35 per cent). This indicates that reproducibility would be hampered more by human subjectivity than by imperfections of the ANN.

  11. Cluster Based Text Classification Model

    DEFF Research Database (Denmark)

    Nizamani, Sarwat; Memon, Nasrullah; Wiil, Uffe Kock

    2011-01-01

    We propose a cluster based classification model for suspicious email detection and other text classification tasks. The text classification tasks comprise many training examples that require a complex classification model. Using clusters for classification makes the model simpler and increases...... the accuracy at the same time. The test example is classified using simpler and smaller model. The training examples in a particular cluster share the common vocabulary. At the time of clustering, we do not take into account the labels of the training examples. After the clusters have been created......, the classifier is trained on each cluster having reduced dimensionality and less number of examples. The experimental results show that the proposed model outperforms the existing classification models for the task of suspicious email detection and topic categorization on the Reuters-21578 and 20 Newsgroups...

  12. Classification of Company Performance using Weighted Probabilistic Neural Network

    Science.gov (United States)

    Yasin, Hasbi; Waridi Basyiruddin Arifin, Adi; Warsito, Budi

    2018-05-01

    Classification of company performance can be judged by looking at its financial status, whether good or bad state. Classification of company performance can be achieved by some approach, either parametric or non-parametric. Neural Network is one of non-parametric methods. One of Artificial Neural Network (ANN) models is Probabilistic Neural Network (PNN). PNN consists of four layers, i.e. input layer, pattern layer, addition layer, and output layer. The distance function used is the euclidean distance and each class share the same values as their weights. In this study used PNN that has been modified on the weighting process between the pattern layer and the addition layer by involving the calculation of the mahalanobis distance. This model is called the Weighted Probabilistic Neural Network (WPNN). The results show that the company's performance modeling with the WPNN model has a very high accuracy that reaches 100%.

  13. Latent class models for classification

    NARCIS (Netherlands)

    Vermunt, J.K.; Magidson, J.

    2003-01-01

    An overview is provided of recent developments in the use of latent class (LC) and other types of finite mixture models for classification purposes. Several extensions of existing models are presented. Two basic types of LC models for classification are defined: supervised and unsupervised

  14. Iris Data Classification Using Quantum Neural Networks

    International Nuclear Information System (INIS)

    Sahni, Vishal; Patvardhan, C.

    2006-01-01

    Quantum computing is a novel paradigm that promises to be the future of computing. The performance of quantum algorithms has proved to be stunning. ANN within the context of classical computation has been used for approximation and classification tasks with some success. This paper presents an idea of quantum neural networks along with the training algorithm and its convergence property. It synergizes the unique properties of quantum bits or qubits with the various techniques in vogue in neural networks. An example application of Fisher's Iris data set, a benchmark classification problem has also been presented. The results obtained amply demonstrate the classification capabilities of the quantum neuron and give an idea of their promising capabilities

  15. Chinese Sentence Classification Based on Convolutional Neural Network

    Science.gov (United States)

    Gu, Chengwei; Wu, Ming; Zhang, Chuang

    2017-10-01

    Sentence classification is one of the significant issues in Natural Language Processing (NLP). Feature extraction is often regarded as the key point for natural language processing. Traditional ways based on machine learning can not take high level features into consideration, such as Naive Bayesian Model. The neural network for sentence classification can make use of contextual information to achieve greater results in sentence classification tasks. In this paper, we focus on classifying Chinese sentences. And the most important is that we post a novel architecture of Convolutional Neural Network (CNN) to apply on Chinese sentence classification. In particular, most of the previous methods often use softmax classifier for prediction, we embed a linear support vector machine to substitute softmax in the deep neural network model, minimizing a margin-based loss to get a better result. And we use tanh as an activation function, instead of ReLU. The CNN model improve the result of Chinese sentence classification tasks. Experimental results on the Chinese news title database validate the effectiveness of our model.

  16. Web Page Classification Method Using Neural Networks

    Science.gov (United States)

    Selamat, Ali; Omatu, Sigeru; Yanagimoto, Hidekazu; Fujinaka, Toru; Yoshioka, Michifumi

    Automatic categorization is the only viable method to deal with the scaling problem of the World Wide Web (WWW). In this paper, we propose a news web page classification method (WPCM). The WPCM uses a neural network with inputs obtained by both the principal components and class profile-based features (CPBF). Each news web page is represented by the term-weighting scheme. As the number of unique words in the collection set is big, the principal component analysis (PCA) has been used to select the most relevant features for the classification. Then the final output of the PCA is combined with the feature vectors from the class-profile which contains the most regular words in each class before feeding them to the neural networks. We have manually selected the most regular words that exist in each class and weighted them using an entropy weighting scheme. The fixed number of regular words from each class will be used as a feature vectors together with the reduced principal components from the PCA. These feature vectors are then used as the input to the neural networks for classification. The experimental evaluation demonstrates that the WPCM method provides acceptable classification accuracy with the sports news datasets.

  17. 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.

  18. METHODS OF TEXT INFORMATION CLASSIFICATION ON THE BASIS OF ARTIFICIAL NEURAL AND SEMANTIC NETWORKS

    Directory of Open Access Journals (Sweden)

    L. V. Serebryanaya

    2016-01-01

    Full Text Available The article covers the use of perseptron, Hopfild artificial neural network and semantic network for classification of text information. Network training algorithms are studied. An algorithm of inverse mistake spreading for perceptron network and convergence algorithm for Hopfild network are implemented. On the basis of the offered models and algorithms automatic text classification software is developed and its operation results are evaluated.

  19. Relation Classification via Recurrent Neural Network

    OpenAIRE

    Zhang, Dongxu; Wang, Dong

    2015-01-01

    Deep learning has gained much success in sentence-level relation classification. For example, convolutional neural networks (CNN) have delivered competitive performance without much effort on feature engineering as the conventional pattern-based methods. Thus a lot of works have been produced based on CNN structures. However, a key issue that has not been well addressed by the CNN-based method is the lack of capability to learn temporal features, especially long-distance dependency between no...

  20. Application of Artificial Neural Network Models in Segmentation and Classification of Nodules in Breast Ultrasound Digital Images

    Directory of Open Access Journals (Sweden)

    Karem D. Marcomini

    2016-01-01

    Full Text Available This research presents a methodology for the automatic detection and characterization of breast sonographic findings. We performed the tests in ultrasound images obtained from breast phantoms made of tissue mimicking material. When the results were considerable, we applied the same techniques to clinical examinations. The process was started employing preprocessing (Wiener filter, equalization, and median filter to minimize noise. Then, five segmentation techniques were investigated to determine the most concise representation of the lesion contour, enabling us to consider the neural network SOM as the most relevant. After the delimitation of the object, the most expressive features were defined to the morphological description of the finding, generating the input data to the neural Multilayer Perceptron (MLP classifier. The accuracy achieved during training with simulated images was 94.2%, producing an AUC of 0.92. To evaluating the data generalization, the classification was performed with a group of unknown images to the system, both to simulators and to clinical trials, resulting in an accuracy of 90% and 81%, respectively. The proposed classifier proved to be an important tool for the diagnosis in breast ultrasound.

  1. Traffic sign classification with dataset augmentation and convolutional neural network

    Science.gov (United States)

    Tang, Qing; Kurnianggoro, Laksono; Jo, Kang-Hyun

    2018-04-01

    This paper presents a method for traffic sign classification using a convolutional neural network (CNN). In this method, firstly we transfer a color image into grayscale, and then normalize it in the range (-1,1) as the preprocessing step. To increase robustness of classification model, we apply a dataset augmentation algorithm and create new images to train the model. To avoid overfitting, we utilize a dropout module before the last fully connection layer. To assess the performance of the proposed method, the German traffic sign recognition benchmark (GTSRB) dataset is utilized. Experimental results show that the method is effective in classifying traffic signs.

  2. Schizophrenia classification using functional network features

    Science.gov (United States)

    Rish, Irina; Cecchi, Guillermo A.; Heuton, Kyle

    2012-03-01

    This paper focuses on discovering statistical biomarkers (features) that are predictive of schizophrenia, with a particular focus on topological properties of fMRI functional networks. We consider several network properties, such as node (voxel) strength, clustering coefficients, local efficiency, as well as just a subset of pairwise correlations. While all types of features demonstrate highly significant statistical differences in several brain areas, and close to 80% classification accuracy, the most remarkable results of 93% accuracy are achieved by using a small subset of only a dozen of most-informative (lowest p-value) correlation features. Our results suggest that voxel-level correlations and functional network features derived from them are highly informative about schizophrenia and can be used as statistical biomarkers for the disease.

  3. Convolutional neural network with transfer learning for rice type classification

    Science.gov (United States)

    Patel, Vaibhav Amit; Joshi, Manjunath V.

    2018-04-01

    Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

  4. Classification and Analysis of Computer Network Traffic

    OpenAIRE

    Bujlow, Tomasz

    2014-01-01

    Traffic monitoring and analysis can be done for multiple different reasons: to investigate the usage of network resources, assess the performance of network applications, adjust Quality of Service (QoS) policies in the network, log the traffic to comply with the law, or create realistic models of traffic for academic purposes. We define the objective of this thesis as finding a way to evaluate the performance of various applications in a high-speed Internet infrastructure. To satisfy the obje...

  5. Evolutionary fuzzy ARTMAP neural networks for classification of semiconductor defects.

    Science.gov (United States)

    Tan, Shing Chiang; Watada, Junzo; Ibrahim, Zuwairie; Khalid, Marzuki

    2015-05-01

    Wafer defect detection using an intelligent system is an approach of quality improvement in semiconductor manufacturing that aims to enhance its process stability, increase production capacity, and improve yields. Occasionally, only few records that indicate defective units are available and they are classified as a minority group in a large database. Such a situation leads to an imbalanced data set problem, wherein it engenders a great challenge to deal with by applying machine-learning techniques for obtaining effective solution. In addition, the database may comprise overlapping samples of different classes. This paper introduces two models of evolutionary fuzzy ARTMAP (FAM) neural networks to deal with the imbalanced data set problems in a semiconductor manufacturing operations. In particular, both the FAM models and hybrid genetic algorithms are integrated in the proposed evolutionary artificial neural networks (EANNs) to classify an imbalanced data set. In addition, one of the proposed EANNs incorporates a facility to learn overlapping samples of different classes from the imbalanced data environment. The classification results of the proposed evolutionary FAM neural networks are presented, compared, and analyzed using several classification metrics. The outcomes positively indicate the effectiveness of the proposed networks in handling classification problems with imbalanced data sets.

  6. Robust classification using mixtures of dependency networks

    DEFF Research Database (Denmark)

    Gámez, José A.; Mateo, Juan L.; Nielsen, Thomas Dyhre

    2008-01-01

    Dependency networks have previously been proposed as alternatives to e.g. Bayesian networks by supporting fast algorithms for automatic learning. Recently dependency networks have also been proposed as classification models, but as with e.g. general probabilistic inference, the reported speed......-ups are often obtained at the expense of accuracy. In this paper we try to address this issue through the use of mixtures of dependency networks. To reduce learning time and improve robustness when dealing with data sparse classes, we outline methods for reusing calculations across mixture components. Finally...

  7. Multimodal Hyper-connectivity Networks for MCI Classification.

    Science.gov (United States)

    Li, Yang; Gao, Xinqiang; Jie, Biao; Yap, Pew-Thian; Kim, Min-Jeong; Wee, Chong-Yaw; Shen, Dinggang

    2017-09-01

    Hyper-connectivity network is a network where every edge is connected to more than two nodes, and can be naturally denoted using a hyper-graph. Hyper-connectivity brain network, either based on structural or functional interactions among the brain regions, has been used for brain disease diagnosis. However, the conventional hyper-connectivity network is constructed solely based on single modality data, ignoring potential complementary information conveyed by other modalities. The integration of complementary information from multiple modalities has been shown to provide a more comprehensive representation about the brain disruptions. In this paper, a novel multimodal hyper-network modelling method was proposed for improving the diagnostic accuracy of mild cognitive impairment (MCI). Specifically, we first constructed a multimodal hyper-connectivity network by simultaneously considering information from diffusion tensor imaging and resting-state functional magnetic resonance imaging data. We then extracted different types of network features from the hyper-connectivity network, and further exploited a manifold regularized multi-task feature selection method to jointly select the most discriminative features. Our proposed multimodal hyper-connectivity network demonstrated a better MCI classification performance than the conventional single modality based hyper-connectivity networks.

  8. Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture.

    Science.gov (United States)

    Meszlényi, Regina J; Buza, Krisztian; Vidnyánszky, Zoltán

    2017-01-01

    Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a publicly available dataset for amnestic mild cognitive impairment classification demonstrate that our CCNN model can efficiently distinguish between subject groups. We also show that the connectome-convolutional network is capable to combine information from diverse functional connectivity metrics and that models using a combination of different connectivity descriptors are able to outperform classifiers using only one metric. From this flexibility follows that our proposed CCNN model can be easily adapted to a wide range of connectome based classification or regression tasks, by varying which connectivity descriptor combinations are used to train the network.

  9. Classification of Urinary Calculi using Feed-Forward Neural Networks

    African Journals Online (AJOL)

    NJD

    Genetic algorithms were used for optimization of neural networks and for selection of the ... Urinary calculi, infrared spectroscopy, classification, neural networks, variable ..... note that the best accuracy is obtained for whewellite, weddellite.

  10. Classification of Franchise Networks in the Retail Trade

    OpenAIRE

    Grygorenko Tetyana M.

    2016-01-01

    The article clarifies the definitions of the concepts of «franchise network», «franchise trade network», «franchise retail network», which is substantiated by the lack of a unified approach to interpretation of these concepts. The classification of franchise networks in the retail trade taking into account peculiarities in the operation of this sub-sector of the market economy is developed; classification attributes are identified and types of franchise retail chains are cha...

  11. Neural networks applied to the classification of remotely sensed data

    NARCIS (Netherlands)

    Mulder, Nanno; Spreeuwers, Lieuwe Jan

    1991-01-01

    A neural network with topology 2-8-8 is evaluated against the standard of supervised non-parametric maximum likelihood classification. The purpose of the evaluation is to compare the performance in terms of training speed and quality of classification. Classification is done on multispectral data

  12. Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Martin Längkvist

    2016-04-01

    Full Text Available The availability of high-resolution remote sensing (HRRS data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN can be applied to multispectral orthoimagery and a digital surface model (DSM of a small city for a full, fast and accurate per-pixel classification. The predicted low-level pixel classes are then used to improve the high-level segmentation. Various design choices of the CNN architecture are evaluated and analyzed. The investigated land area is fully manually labeled into five categories (vegetation, ground, roads, buildings and water, and the classification accuracy is compared to other per-pixel classification works on other land areas that have a similar choice of categories. The results of the full classification and segmentation on selected segments of the map show that CNNs are a viable tool for solving both the segmentation and object recognition task for remote sensing data.

  13. A network-based classification model for deriving novel drug-disease associations and assessing their molecular actions.

    Directory of Open Access Journals (Sweden)

    Min Oh

    Full Text Available The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level. Properly selected features of the network representations of existing drug-disease associations can be used to infer novel indications of existing drugs. To find new drug-disease associations, we generated an integrative genetic network using combinations of interactions, including protein-protein interactions and gene regulatory network datasets. Within this network, network adjacencies of drug-drug and disease-disease were quantified using a scored path between target sets of them. Furthermore, the common topological module of drugs or diseases was extracted, and thereby the distance between topological drug-module and disease (or disease-module and drug was quantified. These quantified scores were used as features for the prediction of novel drug-disease associations. Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties. Our predictions and current clinical trials overlap significantly across the different phases of drug development. We also identified and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer's disease. Within the network, those modules show potential pathways that illustrate the mechanisms of new drug indications, including propranolol as a potential anticancer agent and telmisartan as treatment for Alzheimer's disease.

  14. Using DRG to analyze hospital production: a re-classification model based on a linear tree-network topology

    Directory of Open Access Journals (Sweden)

    Achille Lanzarini

    2014-09-01

    Full Text Available Background: Hospital discharge records are widely classified through the Diagnosis Related Group (DRG system; the version currently used in Italy counts 538 different codes, including thousands of diagnosis and procedures. These numbers reflect the considerable effort of simplification, yet the current classification system is of little use to evaluate hospital production and performance.Methods: As the case-mix of a given Hospital Unit (HU is driven by its physicians’ specializations, a grouping of DRGs into a specialization-driven classification system has been conceived through the analysis of HUs discharging and the ICD-9-CM codes. We propose a three-folded classification, based on the analysis of 1,670,755 Hospital Discharge Cards (HDCs produced by Lombardy Hospitals in 2010; it consists of 32 specializations (e.g. Neurosurgery, 124 sub-specialization (e.g. skull surgery and 337 sub-sub-specialization (e.g. craniotomy.Results: We give a practical application of the three-layered approach, based on the production of a Neurosurgical HU; we observe synthetically the profile of production (1,305 hospital discharges for 79 different DRG codes of 16 different MDC are grouped in few groups of homogeneous DRG codes, a more informative production comparison (through process-specific comparisons, rather than crude or case-mix standardized comparisons and a potentially more adequate production planning (considering the Neurosurgical HUs of the same city, those produce a limited quote of the whole neurosurgical production, because the same activity can be realized by non-Neurosugical HUs.Conclusion: Our work may help to evaluate the hospital production for a rational planning of available resources, blunting information asymmetries between physicians and managers. 

  15. Classification of non-performing loans portfolio using Multilayer Perceptron artificial neural networks

    Directory of Open Access Journals (Sweden)

    Flávio Clésio Silva de Souza

    2014-06-01

    Full Text Available The purpose of the present research is to apply a Multilayer Perceptron (MLP neural network technique to create classification models from a portfolio of Non-Performing Loans (NPLs to classify this type of credit derivative. These credit derivatives are characterized as the amount of loans that were not paid and are already overdue more than 90 days. Since these titles are, because of legislative motives, moved by losses, Credit Rights Investment Funds (FDIC performs the purchase of these debts and the recovery of the credits. Using the Multilayer Perceptron (MLP architecture of Artificial Neural Network (ANN, classification models regarding the posterior recovery of these debts were created. To evaluate the performance of the models, evaluation metrics of classification relating to the neural networks with different architectures were presented. The results of the classifications were satisfactory, given the classification models were successful in the presented economics costs structure.

  16. Cough event classification by pretrained deep neural network.

    Science.gov (United States)

    Liu, Jia-Ming; You, Mingyu; Wang, Zheng; Li, Guo-Zheng; Xu, Xianghuai; Qiu, Zhongmin

    2015-01-01

    Cough is an essential symptom in respiratory diseases. In the measurement of cough severity, an accurate and objective cough monitor is expected by respiratory disease society. This paper aims to introduce a better performed algorithm, pretrained deep neural network (DNN), to the cough classification problem, which is a key step in the cough monitor. The deep neural network models are built from two steps, pretrain and fine-tuning, followed by a Hidden Markov Model (HMM) decoder to capture tamporal information of the audio signals. By unsupervised pretraining a deep belief network, a good initialization for a deep neural network is learned. Then the fine-tuning step is a back propogation tuning the neural network so that it can predict the observation probability associated with each HMM states, where the HMM states are originally achieved by force-alignment with a Gaussian Mixture Model Hidden Markov Model (GMM-HMM) on the training samples. Three cough HMMs and one noncough HMM are employed to model coughs and noncoughs respectively. The final decision is made based on viterbi decoding algorihtm that generates the most likely HMM sequence for each sample. A sample is labeled as cough if a cough HMM is found in the sequence. The experiments were conducted on a dataset that was collected from 22 patients with respiratory diseases. Patient dependent (PD) and patient independent (PI) experimental settings were used to evaluate the models. Five criteria, sensitivity, specificity, F1, macro average and micro average are shown to depict different aspects of the models. From overall evaluation criteria, the DNN based methods are superior to traditional GMM-HMM based method on F1 and micro average with maximal 14% and 11% error reduction in PD and 7% and 10% in PI, meanwhile keep similar performances on macro average. They also surpass GMM-HMM model on specificity with maximal 14% error reduction on both PD and PI. In this paper, we tried pretrained deep neural network in

  17. Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

    Science.gov (United States)

    Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

    1990-01-01

    Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

  18. Tongue Images Classification Based on Constrained High Dispersal Network

    Directory of Open Access Journals (Sweden)

    Dan Meng

    2017-01-01

    Full Text Available Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM. However, the majority of the existing tongue image analyses and classification methods are based on the low-level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN, we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high-level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

  19. Classification and Evaluation of Mobility Metrics for Mobility Model Movement Patterns in Mobile Ad-Hoc Networks

    OpenAIRE

    Santosh Kumar S C Sharma Bhupendra Suman

    2011-01-01

    A mobile ad hoc network is collection of self configuring and adaption of wireless link between communicating devices (mobile devices) to form an arbitrary topology and multihop wireless connectivity without the use of existing infrastructure. It requires efficient dynamic routing protocol to determine the routes subsequent to a set of rules that enables two or more devices to communicate with each others. This paper basically classifies and evaluates the mobility metrics into two categories-...

  20. Training strategy for convolutional neural networks in pedestrian gender classification

    Science.gov (United States)

    Ng, Choon-Boon; Tay, Yong-Haur; Goi, Bok-Min

    2017-06-01

    In this work, we studied a strategy for training a convolutional neural network in pedestrian gender classification with limited amount of labeled training data. Unsupervised learning by k-means clustering on pedestrian images was used to learn the filters to initialize the first layer of the network. As a form of pre-training, supervised learning for the related task of pedestrian classification was performed. Finally, the network was fine-tuned for gender classification. We found that this strategy improved the network's generalization ability in gender classification, achieving better test results when compared to random weights initialization and slightly more beneficial than merely initializing the first layer filters by unsupervised learning. This shows that unsupervised learning followed by pre-training with pedestrian images is an effective strategy to learn useful features for pedestrian gender classification.

  1. Classification of breast cancer cytological specimen using convolutional neural network

    Science.gov (United States)

    Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

    2017-01-01

    The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

  2. Compensatory neurofuzzy model for discrete data classification in biomedical

    Science.gov (United States)

    Ceylan, Rahime

    2015-03-01

    Biomedical data is separated to two main sections: signals and discrete data. So, studies in this area are about biomedical signal classification or biomedical discrete data classification. There are artificial intelligence models which are relevant to classification of ECG, EMG or EEG signals. In same way, in literature, many models exist for classification of discrete data taken as value of samples which can be results of blood analysis or biopsy in medical process. Each algorithm could not achieve high accuracy rate on classification of signal and discrete data. In this study, compensatory neurofuzzy network model is presented for classification of discrete data in biomedical pattern recognition area. The compensatory neurofuzzy network has a hybrid and binary classifier. In this system, the parameters of fuzzy systems are updated by backpropagation algorithm. The realized classifier model is conducted to two benchmark datasets (Wisconsin Breast Cancer dataset and Pima Indian Diabetes dataset). Experimental studies show that compensatory neurofuzzy network model achieved 96.11% accuracy rate in classification of breast cancer dataset and 69.08% accuracy rate was obtained in experiments made on diabetes dataset with only 10 iterations.

  3. 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

  4. Functional classification of the Gauteng provincial road network ...

    African Journals Online (AJOL)

    The built environment consists of various land uses and activities connected by a road network. The efficiency and effectiveness of the road network directly impacts economic growth and societal movement. This study involved the functional classification of the Gauteng provincial road network using the South African Road ...

  5. Cooperative Learning for Distributed In-Network Traffic Classification

    Science.gov (United States)

    Joseph, S. B.; Loo, H. R.; Ismail, I.; Andromeda, T.; Marsono, M. N.

    2017-04-01

    Inspired by the concept of autonomic distributed/decentralized network management schemes, we consider the issue of information exchange among distributed network nodes to network performance and promote scalability for in-network monitoring. In this paper, we propose a cooperative learning algorithm for propagation and synchronization of network information among autonomic distributed network nodes for online traffic classification. The results show that network nodes with sharing capability perform better with a higher average accuracy of 89.21% (sharing data) and 88.37% (sharing clusters) compared to 88.06% for nodes without cooperative learning capability. The overall performance indicates that cooperative learning is promising for distributed in-network traffic classification.

  6. Collaborative networks: Reference modeling

    NARCIS (Netherlands)

    Camarinha-Matos, L.M.; Afsarmanesh, H.

    2008-01-01

    Collaborative Networks: Reference Modeling works to establish a theoretical foundation for Collaborative Networks. Particular emphasis is put on modeling multiple facets of collaborative networks and establishing a comprehensive modeling framework that captures and structures diverse perspectives of

  7. Deep neural network and noise classification-based speech enhancement

    Science.gov (United States)

    Shi, Wenhua; Zhang, Xiongwei; Zou, Xia; Han, Wei

    2017-07-01

    In this paper, a speech enhancement method using noise classification and Deep Neural Network (DNN) was proposed. Gaussian mixture model (GMM) was employed to determine the noise type in speech-absent frames. DNN was used to model the relationship between noisy observation and clean speech. Once the noise type was determined, the corresponding DNN model was applied to enhance the noisy speech. GMM was trained with mel-frequency cepstrum coefficients (MFCC) and the parameters were estimated with an iterative expectation-maximization (EM) algorithm. Noise type was updated by spectrum entropy-based voice activity detection (VAD). Experimental results demonstrate that the proposed method could achieve better objective speech quality and smaller distortion under stationary and non-stationary conditions.

  8. Evolutionary Algorithms For Neural Networks Binary And Real Data Classification

    Directory of Open Access Journals (Sweden)

    Dr. Hanan A.R. Akkar

    2015-08-01

    Full Text Available Artificial neural networks are complex networks emulating the way human rational neurons process data. They have been widely used generally in prediction clustering classification and association. The training algorithms that used to determine the network weights are almost the most important factor that influence the neural networks performance. Recently many meta-heuristic and Evolutionary algorithms are employed to optimize neural networks weights to achieve better neural performance. This paper aims to use recently proposed algorithms for optimizing neural networks weights comparing these algorithms performance with other classical meta-heuristic algorithms used for the same purpose. However to evaluate the performance of such algorithms for training neural networks we examine such algorithms to classify four opposite binary XOR clusters and classification of continuous real data sets such as Iris and Ecoli.

  9. Churn classification model for local telecommunication company ...

    African Journals Online (AJOL)

    ... model based on the Rough Set Theory to classify customer churn. The results of the study show that the proposed Rough Set classification model outperforms the existing models and contributes to significant accuracy improvement. Keywords: customer churn; classification model; telecommunication industry; data mining;

  10. Very Deep Convolutional Neural Networks for Morphologic Classification of Erythrocytes.

    Science.gov (United States)

    Durant, Thomas J S; Olson, Eben M; Schulz, Wade L; Torres, Richard

    2017-12-01

    Morphologic profiling of the erythrocyte population is a widely used and clinically valuable diagnostic modality, but one that relies on a slow manual process associated with significant labor cost and limited reproducibility. Automated profiling of erythrocytes from digital images by capable machine learning approaches would augment the throughput and value of morphologic analysis. To this end, we sought to evaluate the performance of leading implementation strategies for convolutional neural networks (CNNs) when applied to classification of erythrocytes based on morphology. Erythrocytes were manually classified into 1 of 10 classes using a custom-developed Web application. Using recent literature to guide architectural considerations for neural network design, we implemented a "very deep" CNN, consisting of >150 layers, with dense shortcut connections. The final database comprised 3737 labeled cells. Ensemble model predictions on unseen data demonstrated a harmonic mean of recall and precision metrics of 92.70% and 89.39%, respectively. Of the 748 cells in the test set, 23 misclassification errors were made, with a correct classification frequency of 90.60%, represented as a harmonic mean across the 10 morphologic classes. These findings indicate that erythrocyte morphology profiles could be measured with a high degree of accuracy with "very deep" CNNs. Further, these data support future efforts to expand classes and optimize practical performance in a clinical environment as a prelude to full implementation as a clinical tool. © 2017 American Association for Clinical Chemistry.

  11. Applying deep neural networks to HEP job classification

    International Nuclear Information System (INIS)

    Wang, L; Shi, J; Yan, X

    2015-01-01

    The cluster of IHEP computing center is a middle-sized computing system which provides 10 thousands CPU cores, 5 PB disk storage, and 40 GB/s IO throughput. Its 1000+ users come from a variety of HEP experiments. In such a system, job classification is an indispensable task. Although experienced administrator can classify a HEP job by its IO pattern, it is unpractical to classify millions of jobs manually. We present how to solve this problem with deep neural networks in a supervised learning way. Firstly, we built a training data set of 320K samples by an IO pattern collection agent and a semi-automatic process of sample labelling. Then we implemented and trained DNNs models with Torch. During the process of model training, several meta-parameters was tuned with cross-validations. Test results show that a 5- hidden-layer DNNs model achieves 96% precision on the classification task. By comparison, it outperforms a linear model by 8% precision. (paper)

  12. Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

    Science.gov (United States)

    Zhang, WenJun

    2007-07-01

    Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance

  13. Automated Stellar Classification for Large Surveys with EKF and RBF Neural Networks

    Institute of Scientific and Technical Information of China (English)

    Ling Bai; Ping Guo; Zhan-Yi Hu

    2005-01-01

    An automated classification technique for large size stellar surveys is proposed. It uses the extended Kalman filter as a feature selector and pre-classifier of the data, and the radial basis function neural networks for the classification.Experiments with real data have shown that the correct classification rate can reach as high as 93%, which is quite satisfactory. When different system models are selected for the extended Kalman filter, the classification results are relatively stable. It is shown that for this particular case the result using extended Kalman filter is better than using principal component analysis.

  14. Automatic Seismic-Event Classification with Convolutional Neural Networks.

    Science.gov (United States)

    Bueno Rodriguez, A.; Titos Luzón, M.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

    2017-12-01

    Active volcanoes exhibit a wide range of seismic signals, providing vast amounts of unlabelled volcano-seismic data that can be analyzed through the lens of artificial intelligence. However, obtaining high-quality labelled data is time-consuming and expensive. Deep neural networks can process data in their raw form, compute high-level features and provide a better representation of the input data distribution. These systems can be deployed to classify seismic data at scale, enhance current early-warning systems and build extensive seismic catalogs. In this research, we aim to classify spectrograms from seven different seismic events registered at "Volcán de Fuego" (Colima, Mexico), during four eruptive periods. Our approach is based on convolutional neural networks (CNNs), a sub-type of deep neural networks that can exploit grid structure from the data. Volcano-seismic signals can be mapped into a grid-like structure using the spectrogram: a representation of the temporal evolution in terms of time and frequency. Spectrograms were computed from the data using Hamming windows with 4 seconds length, 2.5 seconds overlapping and 128 points FFT resolution. Results are compared to deep neural networks, random forest and SVMs. Experiments show that CNNs can exploit temporal and frequency information, attaining a classification accuracy of 93%, similar to deep networks 91% but outperforming SVM and random forest. These results empirically show that CNNs are powerful models to classify a wide range of volcano-seismic signals, and achieve good generalization. Furthermore, volcano-seismic spectrograms contains useful discriminative information for the CNN, as higher layers of the network combine high-level features computed for each frequency band, helping to detect simultaneous events in time. Being at the intersection of deep learning and geophysics, this research enables future studies of how CNNs can be used in volcano monitoring to accurately determine the detection and

  15. Convolutional neural network-based classification system design with compressed wireless sensor network images.

    Science.gov (United States)

    Ahn, Jungmo; Park, JaeYeon; Park, Donghwan; Paek, Jeongyeup; Ko, JeongGil

    2018-01-01

    With the introduction of various advanced deep learning algorithms, initiatives for image classification systems have transitioned over from traditional machine learning algorithms (e.g., SVM) to Convolutional Neural Networks (CNNs) using deep learning software tools. A prerequisite in applying CNN to real world applications is a system that collects meaningful and useful data. For such purposes, Wireless Image Sensor Networks (WISNs), that are capable of monitoring natural environment phenomena using tiny and low-power cameras on resource-limited embedded devices, can be considered as an effective means of data collection. However, with limited battery resources, sending high-resolution raw images to the backend server is a burdensome task that has direct impact on network lifetime. To address this problem, we propose an energy-efficient pre- and post- processing mechanism using image resizing and color quantization that can significantly reduce the amount of data transferred while maintaining the classification accuracy in the CNN at the backend server. We show that, if well designed, an image in its highly compressed form can be well-classified with a CNN model trained in advance using adequately compressed data. Our evaluation using a real image dataset shows that an embedded device can reduce the amount of transmitted data by ∼71% while maintaining a classification accuracy of ∼98%. Under the same conditions, this process naturally reduces energy consumption by ∼71% compared to a WISN that sends the original uncompressed images.

  16. Classification Method in Integrated Information Network Using Vector Image Comparison

    Directory of Open Access Journals (Sweden)

    Zhou Yuan

    2014-05-01

    Full Text Available Wireless Integrated Information Network (WMN consists of integrated information that can get data from its surrounding, such as image, voice. To transmit information, large resource is required which decreases the service time of the network. In this paper we present a Classification Approach based on Vector Image Comparison (VIC for WMN that improve the service time of the network. The available methods for sub-region selection and conversion are also proposed.

  17. Real-time network traffic classification technique for wireless local area networks based on compressed sensing

    Science.gov (United States)

    Balouchestani, Mohammadreza

    2017-05-01

    Network traffic or data traffic in a Wireless Local Area Network (WLAN) is the amount of network packets moving across a wireless network from each wireless node to another wireless node, which provide the load of sampling in a wireless network. WLAN's Network traffic is the main component for network traffic measurement, network traffic control and simulation. Traffic classification technique is an essential tool for improving the Quality of Service (QoS) in different wireless networks in the complex applications such as local area networks, wireless local area networks, wireless personal area networks, wireless metropolitan area networks, and wide area networks. Network traffic classification is also an essential component in the products for QoS control in different wireless network systems and applications. Classifying network traffic in a WLAN allows to see what kinds of traffic we have in each part of the network, organize the various kinds of network traffic in each path into different classes in each path, and generate network traffic matrix in order to Identify and organize network traffic which is an important key for improving the QoS feature. To achieve effective network traffic classification, Real-time Network Traffic Classification (RNTC) algorithm for WLANs based on Compressed Sensing (CS) is presented in this paper. The fundamental goal of this algorithm is to solve difficult wireless network management problems. The proposed architecture allows reducing False Detection Rate (FDR) to 25% and Packet Delay (PD) to 15 %. The proposed architecture is also increased 10 % accuracy of wireless transmission, which provides a good background for establishing high quality wireless local area networks.

  18. Pixel-Wise Classification Method for High Resolution Remote Sensing Imagery Using Deep Neural Networks

    Directory of Open Access Journals (Sweden)

    Rui Guo

    2018-03-01

    Full Text Available Considering the classification of high spatial resolution remote sensing imagery, this paper presents a novel classification method for such imagery using deep neural networks. Deep learning methods, such as a fully convolutional network (FCN model, achieve state-of-the-art performance in natural image semantic segmentation when provided with large-scale datasets and respective labels. To use data efficiently in the training stage, we first pre-segment training images and their labels into small patches as supplements of training data using graph-based segmentation and the selective search method. Subsequently, FCN with atrous convolution is used to perform pixel-wise classification. In the testing stage, post-processing with fully connected conditional random fields (CRFs is used to refine results. Extensive experiments based on the Vaihingen dataset demonstrate that our method performs better than the reference state-of-the-art networks when applied to high-resolution remote sensing imagery classification.

  19. Multi-Temporal Land Cover Classification with Long Short-Term Memory Neural Networks

    Science.gov (United States)

    Rußwurm, M.; Körner, M.

    2017-05-01

    Land cover classification (LCC) is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM) neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN), with a classical non-temporal convolutional neural network (CNN) model and an additional support vector machine (SVM) baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

  20. MULTI-TEMPORAL LAND COVER CLASSIFICATION WITH LONG SHORT-TERM MEMORY NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    M. Rußwurm

    2017-05-01

    Full Text Available Land cover classification (LCC is a central and wide field of research in earth observation and has already put forth a variety of classification techniques. Many approaches are based on classification techniques considering observation at certain points in time. However, some land cover classes, such as crops, change their spectral characteristics due to environmental influences and can thus not be monitored effectively with classical mono-temporal approaches. Nevertheless, these temporal observations should be utilized to benefit the classification process. After extensive research has been conducted on modeling temporal dynamics by spectro-temporal profiles using vegetation indices, we propose a deep learning approach to utilize these temporal characteristics for classification tasks. In this work, we show how long short-term memory (LSTM neural networks can be employed for crop identification purposes with SENTINEL 2A observations from large study areas and label information provided by local authorities. We compare these temporal neural network models, i.e., LSTM and recurrent neural network (RNN, with a classical non-temporal convolutional neural network (CNN model and an additional support vector machine (SVM baseline. With our rather straightforward LSTM variant, we exceeded state-of-the-art classification performance, thus opening promising potential for further research.

  1. Automatic classification of DMSA scans using an artificial neural network

    Science.gov (United States)

    Wright, J. W.; Duguid, R.; Mckiddie, F.; Staff, R. T.

    2014-04-01

    DMSA imaging is carried out in nuclear medicine to assess the level of functional renal tissue in patients. This study investigated the use of an artificial neural network to perform diagnostic classification of these scans. Using the radiological report as the gold standard, the network was trained to classify DMSA scans as positive or negative for defects using a representative sample of 257 previously reported images. The trained network was then independently tested using a further 193 scans and achieved a binary classification accuracy of 95.9%. The performance of the network was compared with three qualified expert observers who were asked to grade each scan in the 193 image testing set on a six point defect scale, from ‘definitely normal’ to ‘definitely abnormal’. A receiver operating characteristic analysis comparison between a consensus operator, generated from the scores of the three expert observers, and the network revealed a statistically significant increase (α quality assurance assistant in clinical practice.

  2. Neural attractor network for application in visual field data classification

    International Nuclear Information System (INIS)

    Fink, Wolfgang

    2004-01-01

    The purpose was to introduce a novel method for computer-based classification of visual field data derived from perimetric examination, that may act as a ' counsellor', providing an independent 'second opinion' to the diagnosing physician. The classification system consists of a Hopfield-type neural attractor network that obtains its input data from perimetric examination results. An iterative relaxation process determines the states of the neurons dynamically. Therefore, even 'noisy' perimetric output, e.g., early stages of a disease, may eventually be classified correctly according to the predefined idealized visual field defect (scotoma) patterns, stored as attractors of the network, that are found with diseases of the eye, optic nerve and the central nervous system. Preliminary tests of the classification system on real visual field data derived from perimetric examinations have shown a classification success of over 80%. Some of the main advantages of the Hopfield-attractor-network-based approach over feed-forward type neural networks are: (1) network architecture is defined by the classification problem; (2) no training is required to determine the neural coupling strengths; (3) assignment of an auto-diagnosis confidence level is possible by means of an overlap parameter and the Hamming distance. In conclusion, the novel method for computer-based classification of visual field data, presented here, furnishes a valuable first overview and an independent 'second opinion' in judging perimetric examination results, pointing towards a final diagnosis by a physician. It should not be considered a substitute for the diagnosing physician. Thanks to the worldwide accessibility of the Internet, the classification system offers a promising perspective towards modern computer-assisted diagnosis in both medicine and tele-medicine, for example and in particular, with respect to non-ophthalmic clinics or in communities where perimetric expertise is not readily available

  3. Classification of urine sediment based on convolution neural network

    Science.gov (United States)

    Pan, Jingjing; Jiang, Cunbo; Zhu, Tiantian

    2018-04-01

    By designing a new convolution neural network framework, this paper breaks the constraints of the original convolution neural network framework requiring large training samples and samples of the same size. Move and cropping the input images, generate the same size of the sub-graph. And then, the generated sub-graph uses the method of dropout, increasing the diversity of samples and preventing the fitting generation. Randomly select some proper subset in the sub-graphic set and ensure that the number of elements in the proper subset is same and the proper subset is not the same. The proper subsets are used as input layers for the convolution neural network. Through the convolution layer, the pooling, the full connection layer and output layer, we can obtained the classification loss rate of test set and training set. In the red blood cells, white blood cells, calcium oxalate crystallization classification experiment, the classification accuracy rate of 97% or more.

  4. Multispectral Image classification using the theories of neural networks

    International Nuclear Information System (INIS)

    Ardisasmita, M.S.; Subki, M.I.R.

    1997-01-01

    Image classification is the one of the important part of digital image analysis. the objective of image classification is to identify and regroup the features occurring in an image into one or several classes in terms of the object. basic to the understanding of multispectral classification is the concept of the spectral response of an object as a function of the electromagnetic radiation and the wavelength of the spectrum. new approaches to classification has been developed to improve the result of analysis, these state-of-the-art classifiers are based upon the theories of neural networks. Neural network classifiers are algorithmes which mimic the computational abilities of the human brain. Artificial neurons are simple emulation's of biological neurons; they take in information from sensors or other artificial neurons, perform very simple operations on this data, and pass the result to other recognize the spectral signature of each image pixel. Neural network image classification has been divided into supervised and unsupervised training procedures. In the supervised approach, examples of each cover type can be located and the computer can compute spectral signatures to categorize all pixels in a digital image into several land cover classes. In supervised classification, spectral signatures are generated by mathematically grouping and it does not require analyst-specified training data. Thus, in the supervised approach we define useful information categories and then examine their spectral reparability; in the unsupervised approach the computer determines spectrally sapable classes and then we define thei information value

  5. Neural network classification of gamma-ray bursts

    International Nuclear Information System (INIS)

    Balastegui, A.; Canal, R.

    2005-01-01

    From a cluster analysis it appeared that a three-class classification of GRBs could be preferable to just the classic separation of short/hard and long/soft GRBs (Balastegui A., Ruiz-Lapuente, P. and Canal, R. MNRAS 328 (2001) 283). A new classification of GRBs obtained via a neural network is presented, with a short/hard class, an intermediate-duration/soft class, and a long/soft class, the latter being a brighter and more inhomogeneous class than the intermediate duration one. A possible physical meaning of this new classification is also outlined

  6. A novel neural network based image reconstruction model with scale and rotation invariance for target identification and classification for Active millimetre wave imaging

    Science.gov (United States)

    Agarwal, Smriti; Bisht, Amit Singh; Singh, Dharmendra; Pathak, Nagendra Prasad

    2014-12-01

    Millimetre wave imaging (MMW) is gaining tremendous interest among researchers, which has potential applications for security check, standoff personal screening, automotive collision-avoidance, and lot more. Current state-of-art imaging techniques viz. microwave and X-ray imaging suffers from lower resolution and harmful ionizing radiation, respectively. In contrast, MMW imaging operates at lower power and is non-ionizing, hence, medically safe. Despite these favourable attributes, MMW imaging encounters various challenges as; still it is very less explored area and lacks suitable imaging methodology for extracting complete target information. Keeping in view of these challenges, a MMW active imaging radar system at 60 GHz was designed for standoff imaging application. A C-scan (horizontal and vertical scanning) methodology was developed that provides cross-range resolution of 8.59 mm. The paper further details a suitable target identification and classification methodology. For identification of regular shape targets: mean-standard deviation based segmentation technique was formulated and further validated using a different target shape. For classification: probability density function based target material discrimination methodology was proposed and further validated on different dataset. Lastly, a novel artificial neural network based scale and rotation invariant, image reconstruction methodology has been proposed to counter the distortions in the image caused due to noise, rotation or scale variations. The designed neural network once trained with sample images, automatically takes care of these deformations and successfully reconstructs the corrected image for the test targets. Techniques developed in this paper are tested and validated using four different regular shapes viz. rectangle, square, triangle and circle.

  7. Vehicle classification in WAMI imagery using deep network

    Science.gov (United States)

    Yi, Meng; Yang, Fan; Blasch, Erik; Sheaff, Carolyn; Liu, Kui; Chen, Genshe; Ling, Haibin

    2016-05-01

    Humans have always had a keen interest in understanding activities and the surrounding environment for mobility, communication, and survival. Thanks to recent progress in photography and breakthroughs in aviation, we are now able to capture tens of megapixels of ground imagery, namely Wide Area Motion Imagery (WAMI), at multiple frames per second from unmanned aerial vehicles (UAVs). WAMI serves as a great source for many applications, including security, urban planning and route planning. These applications require fast and accurate image understanding which is time consuming for humans, due to the large data volume and city-scale area coverage. Therefore, automatic processing and understanding of WAMI imagery has been gaining attention in both industry and the research community. This paper focuses on an essential step in WAMI imagery analysis, namely vehicle classification. That is, deciding whether a certain image patch contains a vehicle or not. We collect a set of positive and negative sample image patches, for training and testing the detector. Positive samples are 64 × 64 image patches centered on annotated vehicles. We generate two sets of negative images. The first set is generated from positive images with some location shift. The second set of negative patches is generated from randomly sampled patches. We also discard those patches if a vehicle accidentally locates at the center. Both positive and negative samples are randomly divided into 9000 training images and 3000 testing images. We propose to train a deep convolution network for classifying these patches. The classifier is based on a pre-trained AlexNet Model in the Caffe library, with an adapted loss function for vehicle classification. The performance of our classifier is compared to several traditional image classifier methods using Support Vector Machine (SVM) and Histogram of Oriented Gradient (HOG) features. While the SVM+HOG method achieves an accuracy of 91.2%, the accuracy of our deep

  8. Classification hierarchies for product data modelling

    NARCIS (Netherlands)

    Pels, H.J.

    2006-01-01

    Abstraction is an essential element in data modelling that appears mainly in one of the following forms: generalisation, classification or aggregation. In the design of complex products classification hierarchies can be found product families that are viewed as classes of product types, while

  9. Optimized Neural Network for Fault Diagnosis and Classification

    International Nuclear Information System (INIS)

    Elaraby, S.M.

    2005-01-01

    This paper presents a developed and implemented toolbox for optimizing neural network structure of fault diagnosis and classification. Evolutionary algorithm based on hierarchical genetic algorithm structure is used for optimization. The simplest feed-forward neural network architecture is selected. Developed toolbox has friendly user interface. Multiple solutions are generated. The performance and applicability of the proposed toolbox is verified with benchmark data patterns and accident diagnosis of Egyptian Second research reactor (ETRR-2)

  10. Agent Collaborative Target Localization and Classification in Wireless Sensor Networks

    Directory of Open Access Journals (Sweden)

    Sheng Wang

    2007-07-01

    Full Text Available Wireless sensor networks (WSNs are autonomous networks that have beenfrequently deployed to collaboratively perform target localization and classification tasks.Their autonomous and collaborative features resemble the characteristics of agents. Suchsimilarities inspire the development of heterogeneous agent architecture for WSN in thispaper. The proposed agent architecture views WSN as multi-agent systems and mobileagents are employed to reduce in-network communication. According to the architecture,an energy based acoustic localization algorithm is proposed. In localization, estimate oftarget location is obtained by steepest descent search. The search algorithm adapts tomeasurement environments by dynamically adjusting its termination condition. With theagent architecture, target classification is accomplished by distributed support vectormachine (SVM. Mobile agents are employed for feature extraction and distributed SVMlearning to reduce communication load. Desirable learning performance is guaranteed bycombining support vectors and convex hull vectors. Fusion algorithms are designed tomerge SVM classification decisions made from various modalities. Real world experimentswith MICAz sensor nodes are conducted for vehicle localization and classification.Experimental results show the proposed agent architecture remarkably facilitates WSNdesigns and algorithm implementation. The localization and classification algorithms alsoprove to be accurate and energy efficient.

  11. Automated classification of computer network attacks

    CSIR Research Space (South Africa)

    Van Heerden, R

    2013-11-01

    Full Text Available according to the relevant types of attack scenarios depicted in the ontology. The two network attack instances are the Distributed Denial of Service attack on SpamHaus in 2013 and the theft of 42 million Rand ($6.7 million) from South African Postbank...

  12. Fast Fingerprint Classification with Deep Neural Network

    DEFF Research Database (Denmark)

    Michelsanti, Daniel; Guichi, Yanis; Ene, Andreea-Daniela

    2018-01-01

    . In this work we evaluate the performance of two pre-trained convolutional neural networks fine-tuned on the NIST SD4 benchmark database. The obtained results show that this approach is comparable with other results in the literature, with the advantage of a fast feature extraction stage....

  13. A Soft Intelligent Risk Evaluation Model for Credit Scoring Classification

    Directory of Open Access Journals (Sweden)

    Mehdi Khashei

    2015-09-01

    Full Text Available Risk management is one of the most important branches of business and finance. Classification models are the most popular and widely used analytical group of data mining approaches that can greatly help financial decision makers and managers to tackle credit risk problems. However, the literature clearly indicates that, despite proposing numerous classification models, credit scoring is often a difficult task. On the other hand, there is no universal credit-scoring model in the literature that can be accurately and explanatorily used in all circumstances. Therefore, the research for improving the efficiency of credit-scoring models has never stopped. In this paper, a hybrid soft intelligent classification model is proposed for credit-scoring problems. In the proposed model, the unique advantages of the soft computing techniques are used in order to modify the performance of the traditional artificial neural networks in credit scoring. Empirical results of Australian credit card data classifications indicate that the proposed hybrid model outperforms its components, and also other classification models presented for credit scoring. Therefore, the proposed model can be considered as an appropriate alternative tool for binary decision making in business and finance, especially in high uncertainty conditions.

  14. Operational experiences with automated acoustic burst classification by neural networks

    International Nuclear Information System (INIS)

    Olma, B.; Ding, Y.; Enders, R.

    1996-01-01

    Monitoring of Loose Parts Monitoring System sensors for signal bursts associated with metallic impacts of loose parts has proved as an useful methodology for on-line assessing the mechanical integrity of components in the primary circuit of nuclear power plants. With the availability of neural networks new powerful possibilities for classification and diagnosis of burst signals can be realized for acoustic monitoring with the online system RAMSES. In order to look for relevant burst signals an automated classification is needed, that means acoustic signature analysis and assessment has to be performed automatically on-line. A back propagation neural network based on five pre-calculated signal parameter values has been set up for identification of different signal types. During a three-month monitoring program of medium-operated check valves burst signals have been measured and classified separately according to their cause. The successful results of the three measurement campaigns with an automated burst type classification are presented. (author)

  15. An analysis of network traffic classification for botnet detection

    DEFF Research Database (Denmark)

    Stevanovic, Matija; Pedersen, Jens Myrup

    2015-01-01

    of detecting botnet network traffic using three methods that target protocols widely considered as the main carriers of botnet Command and Control (C&C) and attack traffic, i.e. TCP, UDP and DNS. We propose three traffic classification methods based on capable Random Forests classifier. The proposed methods...

  16. A Novel Computer Virus Propagation Model under Security Classification

    Directory of Open Access Journals (Sweden)

    Qingyi Zhu

    2017-01-01

    Full Text Available In reality, some computers have specific security classification. For the sake of safety and cost, the security level of computers will be upgraded with increasing of threats in networks. Here we assume that there exists a threshold value which determines when countermeasures should be taken to level up the security of a fraction of computers with low security level. And in some specific realistic environments the propagation network can be regarded as fully interconnected. Inspired by these facts, this paper presents a novel computer virus dynamics model considering the impact brought by security classification in full interconnection network. By using the theory of dynamic stability, the existence of equilibria and stability conditions is analysed and proved. And the above optimal threshold value is given analytically. Then, some numerical experiments are made to justify the model. Besides, some discussions and antivirus measures are given.

  17. Generative Adversarial Networks for Improving Face Classification

    OpenAIRE

    Natten, Jonas

    2017-01-01

    Master's thesis Information- and communication technology IKT590 - University of Agder 2017 Facial recognition can be applied in a wide variety of cases, including entertainment purposes and biometric security. In this thesis we take a look at improving the results of an existing facial recognition approach by utilizing generative adversarial networks to improve the existing dataset. The training data was taken from the LFW dataset[4] and was preprocessed using OpenCV[2] for...

  18. Automatic classification of DMSA scans using an artificial neural network

    International Nuclear Information System (INIS)

    Wright, J W; Duguid, R; Mckiddie, F; Staff, R T

    2014-01-01

    DMSA imaging is carried out in nuclear medicine to assess the level of functional renal tissue in patients. This study investigated the use of an artificial neural network to perform diagnostic classification of these scans. Using the radiological report as the gold standard, the network was trained to classify DMSA scans as positive or negative for defects using a representative sample of 257 previously reported images. The trained network was then independently tested using a further 193 scans and achieved a binary classification accuracy of 95.9%. The performance of the network was compared with three qualified expert observers who were asked to grade each scan in the 193 image testing set on a six point defect scale, from ‘definitely normal’ to ‘definitely abnormal’. A receiver operating characteristic analysis comparison between a consensus operator, generated from the scores of the three expert observers, and the network revealed a statistically significant increase (α < 0.05) in performance between the network and operators. A further result from this work was that when suitably optimized, a negative predictive value of 100% for renal defects was achieved by the network, while still managing to identify 93% of the negative cases in the dataset. These results are encouraging for application of such a network as a screening tool or quality assurance assistant in clinical practice. (paper)

  19. SEVERITY CLASSIFICATION OF MICROANEURYSMS USING NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    Shree Divya R

    2014-01-01

    Full Text Available Diabetic Retinopathy is one of the most common causes of blindness that leads to the loss of vision to the human eye. Several methods have been proposed to detect several defects of the human eye like hemorrhages, exudates etc. which are to be considered as the major symptoms. Among them, Microaneurysms should be considered as one of the severe condition for the early blindness. Several techniques have been proposed based on this, but they have certain drawbacks. A new technique called neural network taken for presentation, helps to detect and determine the severity of Microaneurysms which would be able to give a better performance than the existing techniques.

  20. Emotion models for textual emotion classification

    Science.gov (United States)

    Bruna, O.; Avetisyan, H.; Holub, J.

    2016-11-01

    This paper deals with textual emotion classification which gained attention in recent years. Emotion classification is used in user experience, product evaluation, national security, and tutoring applications. It attempts to detect the emotional content in the input text and based on different approaches establish what kind of emotional content is present, if any. Textual emotion classification is the most difficult to handle, since it relies mainly on linguistic resources and it introduces many challenges to assignment of text to emotion represented by a proper model. A crucial part of each emotion detector is emotion model. Focus of this paper is to introduce emotion models used for classification. Categorical and dimensional models of emotion are explained and some more advanced approaches are mentioned.

  1. Electroencephalography epilepsy classifications using hybrid cuckoo search and neural network

    Science.gov (United States)

    Pratiwi, A. B.; Damayanti, A.; Miswanto

    2017-07-01

    Epilepsy is a condition that affects the brain and causes repeated seizures. This seizure is episodes that can vary and nearly undetectable to long periods of vigorous shaking or brain contractions. Epilepsy often can be confirmed with an electrocephalography (EEG). Neural Networks has been used in biomedic signal analysis, it has successfully classified the biomedic signal, such as EEG signal. In this paper, a hybrid cuckoo search and neural network are used to recognize EEG signal for epilepsy classifications. The weight of the multilayer perceptron is optimized by the cuckoo search algorithm based on its error. The aim of this methods is making the network faster to obtained the local or global optimal then the process of classification become more accurate. Based on the comparison results with the traditional multilayer perceptron, the hybrid cuckoo search and multilayer perceptron provides better performance in term of error convergence and accuracy. The purpose methods give MSE 0.001 and accuracy 90.0 %.

  2. Modeling Network Interdiction Tasks

    Science.gov (United States)

    2015-09-17

    118 xiii Table Page 36 Computation times for weighted, 100-node random networks for GAND Approach testing in Python ...in Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120 38 Accuracy measures for weighted, 100-node random networks for GAND...networks [15:p. 1]. A common approach to modeling network interdiction is to formulate the problem in terms of a two-stage strategic game between two

  3. Comparison Of Power Quality Disturbances Classification Based On Neural Network

    Directory of Open Access Journals (Sweden)

    Nway Nway Kyaw Win

    2015-07-01

    Full Text Available Abstract Power quality disturbances PQDs result serious problems in the reliability safety and economy of power system network. In order to improve electric power quality events the detection and classification of PQDs must be made type of transient fault. Software analysis of wavelet transform with multiresolution analysis MRA algorithm and feed forward neural network probabilistic and multilayer feed forward neural network based methodology for automatic classification of eight types of PQ signals flicker harmonics sag swell impulse fluctuation notch and oscillatory will be presented. The wavelet family Db4 is chosen in this system to calculate the values of detailed energy distributions as input features for classification because it can perform well in detecting and localizing various types of PQ disturbances. This technique classifies the types of PQDs problem sevents.The classifiers classify and identify the disturbance type according to the energy distribution. The results show that the PNN can analyze different power disturbance types efficiently. Therefore it can be seen that PNN has better classification accuracy than MLFF.

  4. FULLY CONVOLUTIONAL NETWORKS FOR GROUND CLASSIFICATION FROM LIDAR POINT CLOUDS

    Directory of Open Access Journals (Sweden)

    A. Rizaldy

    2018-05-01

    Full Text Available Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs. In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN, a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher. The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.

  5. Fully Convolutional Networks for Ground Classification from LIDAR Point Clouds

    Science.gov (United States)

    Rizaldy, A.; Persello, C.; Gevaert, C. M.; Oude Elberink, S. J.

    2018-05-01

    Deep Learning has been massively used for image classification in recent years. The use of deep learning for ground classification from LIDAR point clouds has also been recently studied. However, point clouds need to be converted into an image in order to use Convolutional Neural Networks (CNNs). In state-of-the-art techniques, this conversion is slow because each point is converted into a separate image. This approach leads to highly redundant computation during conversion and classification. The goal of this study is to design a more efficient data conversion and ground classification. This goal is achieved by first converting the whole point cloud into a single image. The classification is then performed by a Fully Convolutional Network (FCN), a modified version of CNN designed for pixel-wise image classification. The proposed method is significantly faster than state-of-the-art techniques. On the ISPRS Filter Test dataset, it is 78 times faster for conversion and 16 times faster for classification. Our experimental analysis on the same dataset shows that the proposed method results in 5.22 % of total error, 4.10 % of type I error, and 15.07 % of type II error. Compared to the previous CNN-based technique and LAStools software, the proposed method reduces the total error and type I error (while type II error is slightly higher). The method was also tested on a very high point density LIDAR point clouds resulting in 4.02 % of total error, 2.15 % of type I error and 6.14 % of type II error.

  6. Ge Detector Data Classification with Neural Networks

    Science.gov (United States)

    Wilson, Carly; Martin, Ryan; Majorana Collaboration

    2014-09-01

    The Majorana Demonstrator experiment is searching for neutrinoless double beta-decay using p-type point contact PPC germanium detectors at the Sanford Underground Research Facility, in South Dakota. Pulse shape discrimination can be used in PPC detectors to distinguish signal-like events from backgrounds. This research program explored the possibility of building a self-organizing map that takes data collected from germanium detectors and classifies the events as either signal or background. Self organizing maps are a type of neural network that are self-learning and less susceptible to being biased from imperfect training data. We acknowledge support from the Office of Nuclear Physics in the DOE Office of Science, the Particle and Nuclear Astrophysics Program of the National Science Foundation and the Russian Foundation for Basic Research.

  7. Subsurface Event Detection and Classification Using Wireless Signal Networks

    Directory of Open Access Journals (Sweden)

    Muhannad T. Suleiman

    2012-11-01

    Full Text Available 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.

  8. 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.

  9. Dimensionality-varied deep convolutional neural network for spectral-spatial classification of hyperspectral data

    Science.gov (United States)

    Qu, Haicheng; Liang, Xuejian; Liang, Shichao; Liu, Wanjun

    2018-01-01

    Many methods of hyperspectral image classification have been proposed recently, and the convolutional neural network (CNN) achieves outstanding performance. However, spectral-spatial classification of CNN requires an excessively large model, tremendous computations, and complex network, and CNN is generally unable to use the noisy bands caused by water-vapor absorption. A dimensionality-varied CNN (DV-CNN) is proposed to address these issues. There are four stages in DV-CNN and the dimensionalities of spectral-spatial feature maps vary with the stages. DV-CNN can reduce the computation and simplify the structure of the network. All feature maps are processed by more kernels in higher stages to extract more precise features. DV-CNN also improves the classification accuracy and enhances the robustness to water-vapor absorption bands. The experiments are performed on data sets of Indian Pines and Pavia University scene. The classification performance of DV-CNN is compared with state-of-the-art methods, which contain the variations of CNN, traditional, and other deep learning methods. The experiment of performance analysis about DV-CNN itself is also carried out. The experimental results demonstrate that DV-CNN outperforms state-of-the-art methods for spectral-spatial classification and it is also robust to water-vapor absorption bands. Moreover, reasonable parameters selection is effective to improve classification accuracy.

  10. Hydro-geomorphological characterization and classification of Chilean river networks using horizontal, vertical and climatological properties

    Science.gov (United States)

    Pereira, A. A.; Gironas, J. A.; Passalacqua, P.; Mejia, A.; Niemann, J. D.

    2017-12-01

    Previous work has shown that lithological, tectonic and climatic processes have a major influence in shaping the geomorphology of river networks. Accordingly, quantitative classification methods have been developed to identify and characterize network types (dendritic, parallel, pinnate, rectangular and trellis) based solely on the self-affinity of their planform properties, computed from available Digital Elevation Model (DEM) data. In contrast, this research aim is to include both horizontal and vertical properties to evaluate a quantitative classification method for river networks. We include vertical properties to consider the unique surficial conditions (e.g., large and steep height drops, volcanic activity, and complexity of stream networks) of the Andes Mountains. Furthermore, the goal of the research is also to explain the implications and possible relations between the hydro-geomorphological properties and climatic conditions. The classification method is applied to 42 basins in the southern Andes in Chile, ranging in size from 208 Km2 to 8,000 Km2. The planform metrics include the incremental drainage area, stream course irregularity and junction angles, while the vertical metrics include the hypsometric curve and the slope-area relationship. We introduce new network structures (Brush, Funnel and Low Sinuosity Rectangular), possibly unique to the Andes, that can be quantitatively differentiated from previous networks identified in other geographic regions. Then, this research evaluates the effect that excluding different Strahler order streams has on the horizontal properties and therefore in the classification. We found that climatic conditions are not only linked to horizontal parameters, but also to vertical ones, finding significant correlation between climatic variables (average near-surface temperature and rainfall) and vertical measures (parameters associated with the hypsometric curve and slope-area relation). The proposed classification shows

  11. Link prediction boosted psychiatry disorder classification for functional connectivity network

    Science.gov (United States)

    Li, Weiwei; Mei, Xue; Wang, Hao; Zhou, Yu; Huang, Jiashuang

    2017-02-01

    Functional connectivity network (FCN) is an effective tool in psychiatry disorders classification, and represents cross-correlation of the regional blood oxygenation level dependent signal. However, FCN is often incomplete for suffering from missing and spurious edges. To accurate classify psychiatry disorders and health control with the incomplete FCN, we first `repair' the FCN with link prediction, and then exact the clustering coefficients as features to build a weak classifier for every FCN. Finally, we apply a boosting algorithm to combine these weak classifiers for improving classification accuracy. Our method tested by three datasets of psychiatry disorder, including Alzheimer's Disease, Schizophrenia and Attention Deficit Hyperactivity Disorder. The experimental results show our method not only significantly improves the classification accuracy, but also efficiently reconstructs the incomplete FCN.

  12. Bioelectric signal classification using a recurrent probabilistic neural network with time-series discriminant component analysis.

    Science.gov (United States)

    Hayashi, Hideaki; Shima, Keisuke; Shibanoki, Taro; Kurita, Yuichi; Tsuji, Toshio

    2013-01-01

    This paper outlines a probabilistic neural network developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower-dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model that incorporates a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into a neural network so that parameters can be obtained appropriately as network coefficients according to backpropagation-through-time-based training algorithm. The network is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. In the experiments conducted during the study, the validity of the proposed network was demonstrated for EEG signals.

  13. Neural network classification of quark and gluon jets

    International Nuclear Information System (INIS)

    Graham, M.A.; Jones, L.M.; Herbin, S.

    1995-01-01

    We demonstrate that there are characteristics common to quark jets and to gluon jets regardless of the interaction that produced them. The classification technique we use depends on the mass of the jet as well as the center-of-mass energy of the hard subprocess that produces the jet. In addition, we present the quark-gluon separability results of an artificial neural network trained on three-jet e + e - events at the Z 0 mass, using a back-propagation algorithm. The inputs to the network are the longitudinal momenta of the leading hadrons in the jet. We tested the network with quark and gluon jets from both e + e - →3 jets and bar pp→2 jets. Finally, we compare the performance of the artificial neural network with the results of making well chosen physical cuts

  14. Terrain Mapping and Classification in Outdoor Environments Using Neural Networks

    OpenAIRE

    Alberto Yukinobu Hata; Denis Fernando Wolf; Gustavo Pessin; Fernando Osório

    2009-01-01

    This paper describes a three-dimensional terrain mapping and classification technique to allow the operation of mobile robots in outdoor environments using laser range finders. We propose the use of a multi-layer perceptron neural network to classify the terrain into navigable, partially navigable, and non-navigable. The maps generated by our approach can be used for path planning, navigation, and local obstacle avoidance. Experimental tests using an outdoor robot and a laser sensor demonstra...

  15. High-Performance Neural Networks for Visual Object Classification

    OpenAIRE

    Cireşan, Dan C.; Meier, Ueli; Masci, Jonathan; Gambardella, Luca M.; Schmidhuber, Jürgen

    2011-01-01

    We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in a supervised way. Our deep hierarchical architectures achieve the best published results on benchmarks for object classification (NORB, CIFAR10) and handwritten digit recognition (MNIST), with error rates of 2.53%, 19.51%, 0.35%, respectively. Deep nets trained by simple back-propagation perform better ...

  16. A Hierarchical Convolutional Neural Network for vesicle fusion event classification.

    Science.gov (United States)

    Li, Haohan; Mao, Yunxiang; Yin, Zhaozheng; Xu, Yingke

    2017-09-01

    Quantitative analysis of vesicle exocytosis and classification of different modes of vesicle fusion from the fluorescence microscopy are of primary importance for biomedical researches. In this paper, we propose a novel Hierarchical Convolutional Neural Network (HCNN) method to automatically identify vesicle fusion events in time-lapse Total Internal Reflection Fluorescence Microscopy (TIRFM) image sequences. Firstly, a detection and tracking method is developed to extract image patch sequences containing potential fusion events. Then, a Gaussian Mixture Model (GMM) is applied on each image patch of the patch sequence with outliers rejected for robust Gaussian fitting. By utilizing the high-level time-series intensity change features introduced by GMM and the visual appearance features embedded in some key moments of the fusion process, the proposed HCNN architecture is able to classify each candidate patch sequence into three classes: full fusion event, partial fusion event and non-fusion event. Finally, we validate the performance of our method on 9 challenging datasets that have been annotated by cell biologists, and our method achieves better performances when comparing with three previous methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

  17. Cell dynamic morphology classification using deep convolutional neural networks.

    Science.gov (United States)

    Li, Heng; Pang, Fengqian; Shi, Yonggang; Liu, Zhiwen

    2018-05-15

    Cell morphology is often used as a proxy measurement of cell status to understand cell physiology. Hence, interpretation of cell dynamic morphology is a meaningful task in biomedical research. Inspired by the recent success of deep learning, we here explore the application of convolutional neural networks (CNNs) to cell dynamic morphology classification. An innovative strategy for the implementation of CNNs is introduced in this study. Mouse lymphocytes were collected to observe the dynamic morphology, and two datasets were thus set up to investigate the performances of CNNs. Considering the installation of deep learning, the classification problem was simplified from video data to image data, and was then solved by CNNs in a self-taught manner with the generated image data. CNNs were separately performed in three installation scenarios and compared with existing methods. Experimental results demonstrated the potential of CNNs in cell dynamic morphology classification, and validated the effectiveness of the proposed strategy. CNNs were successfully applied to the classification problem, and outperformed the existing methods in the classification accuracy. For the installation of CNNs, transfer learning was proved to be a promising scheme. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

  18. Evaluation of Current Approaches to Stream Classification and a Heuristic Guide to Developing Classifications of Integrated Aquatic Networks

    Science.gov (United States)

    Melles, S. J.; Jones, N. E.; Schmidt, B. J.

    2014-03-01

    Conservation and management of fresh flowing waters involves evaluating and managing effects of cumulative impacts on the aquatic environment from disturbances such as: land use change, point and nonpoint source pollution, the creation of dams and reservoirs, mining, and fishing. To assess effects of these changes on associated biotic communities it is necessary to monitor and report on the status of lotic ecosystems. A variety of stream classification methods are available to assist with these tasks, and such methods attempt to provide a systematic approach to modeling and understanding complex aquatic systems at various spatial and temporal scales. Of the vast number of approaches that exist, it is useful to group them into three main types. The first involves modeling longitudinal species turnover patterns within large drainage basins and relating these patterns to environmental predictors collected at reach and upstream catchment scales; the second uses regionalized hierarchical classification to create multi-scale, spatially homogenous aquatic ecoregions by grouping adjacent catchments together based on environmental similarities; and the third approach groups sites together on the basis of similarities in their environmental conditions both within and between catchments, independent of their geographic location. We review the literature with a focus on more recent classifications to examine the strengths and weaknesses of the different approaches. We identify gaps or problems with the current approaches, and we propose an eight-step heuristic process that may assist with development of more flexible and integrated aquatic classifications based on the current understanding, network thinking, and theoretical underpinnings.

  19. Training Small Networks for Scene Classification of Remote Sensing Images via Knowledge Distillation

    Directory of Open Access Journals (Sweden)

    Guanzhou Chen

    2018-05-01

    Full Text Available Scene classification, aiming to identify the land-cover categories of remotely sensed image patches, is now a fundamental task in the remote sensing image analysis field. Deep-learning-model-based algorithms are widely applied in scene classification and achieve remarkable performance, but these high-level methods are computationally expensive and time-consuming. Consequently in this paper, we introduce a knowledge distillation framework, currently a mainstream model compression method, into remote sensing scene classification to improve the performance of smaller and shallower network models. Our knowledge distillation training method makes the high-temperature softmax output of a small and shallow student model match the large and deep teacher model. In our experiments, we evaluate knowledge distillation training method for remote sensing scene classification on four public datasets: AID dataset, UCMerced dataset, NWPU-RESISC dataset, and EuroSAT dataset. Results show that our proposed training method was effective and increased overall accuracy (3% in AID experiments, 5% in UCMerced experiments, 1% in NWPU-RESISC and EuroSAT experiments for small and shallow models. We further explored the performance of the student model on small and unbalanced datasets. Our findings indicate that knowledge distillation can improve the performance of small network models on datasets with lower spatial resolution images, numerous categories, as well as fewer training samples.

  20. A Feature Selection Method for Large-Scale Network Traffic Classification Based on Spark

    Directory of Open Access Journals (Sweden)

    Yong Wang

    2016-02-01

    Full Text Available Currently, with the rapid increasing of data scales in network traffic classifications, how to select traffic features efficiently is becoming a big challenge. Although a number of traditional feature selection methods using the Hadoop-MapReduce framework have been proposed, the execution time was still unsatisfactory with numeral iterative computations during the processing. To address this issue, an efficient feature selection method for network traffic based on a new parallel computing framework called Spark is proposed in this paper. In our approach, the complete feature set is firstly preprocessed based on Fisher score, and a sequential forward search strategy is employed for subsets. The optimal feature subset is then selected using the continuous iterations of the Spark computing framework. The implementation demonstrates that, on the precondition of keeping the classification accuracy, our method reduces the time cost of modeling and classification, and improves the execution efficiency of feature selection significantly.

  1. Detection and classification of power quality disturbances using S-transform and modular neural network

    Energy Technology Data Exchange (ETDEWEB)

    Bhende, C.N.; Mishra, S.; Panigrahi, B.K. [Department of Electrical Engineering, Indian Institute of Technology, New Delhi 110016 (India)

    2008-01-15

    This paper presents an S-transform based modular neural network (NN) classifier for recognition of power quality disturbances. The excellent time - frequency resolution characteristics of the S-transform makes it an attractive candidate for the analysis of power quality (PQ) disturbances under noisy condition and has the ability to detect the disturbance correctly. On the other hand, the performance of wavelet transform (WT) degrades while detecting and localizing the disturbances in the presence of noise. Features extracted by using the S-transform are applied to a modular NN for automatic classification of the PQ disturbances that solves a relatively complex problem by decomposing it into simpler subtasks. Modularity of neural network provides better classification, model complexity reduction and better learning capability, etc. Eleven types of PQ disturbances are considered for the classification. The simulation results show that the combination of the S-transform and a modular NN can effectively detect and classify different power quality disturbances. (author)

  2. Modelling computer networks

    International Nuclear Information System (INIS)

    Max, G

    2011-01-01

    Traffic models in computer networks can be described as a complicated system. These systems show non-linear features and to simulate behaviours of these systems are also difficult. Before implementing network equipments users wants to know capability of their computer network. They do not want the servers to be overloaded during temporary traffic peaks when more requests arrive than the server is designed for. As a starting point for our study a non-linear system model of network traffic is established to exam behaviour of the network planned. The paper presents setting up a non-linear simulation model that helps us to observe dataflow problems of the networks. This simple model captures the relationship between the competing traffic and the input and output dataflow. In this paper, we also focus on measuring the bottleneck of the network, which was defined as the difference between the link capacity and the competing traffic volume on the link that limits end-to-end throughput. We validate the model using measurements on a working network. The results show that the initial model estimates well main behaviours and critical parameters of the network. Based on this study, we propose to develop a new algorithm, which experimentally determines and predict the available parameters of the network modelled.

  3. Global Optimization Ensemble Model for Classification Methods

    Science.gov (United States)

    Anwar, Hina; Qamar, Usman; Muzaffar Qureshi, Abdul Wahab

    2014-01-01

    Supervised learning is the process of data mining for deducing rules from training datasets. A broad array of supervised learning algorithms exists, every one of them with its own advantages and drawbacks. There are some basic issues that affect the accuracy of classifier while solving a supervised learning problem, like bias-variance tradeoff, dimensionality of input space, and noise in the input data space. All these problems affect the accuracy of classifier and are the reason that there is no global optimal method for classification. There is not any generalized improvement method that can increase the accuracy of any classifier while addressing all the problems stated above. This paper proposes a global optimization ensemble model for classification methods (GMC) that can improve the overall accuracy for supervised learning problems. The experimental results on various public datasets showed that the proposed model improved the accuracy of the classification models from 1% to 30% depending upon the algorithm complexity. PMID:24883382

  4. Global Optimization Ensemble Model for Classification Methods

    Directory of Open Access Journals (Sweden)

    Hina Anwar

    2014-01-01

    Full Text Available Supervised learning is the process of data mining for deducing rules from training datasets. A broad array of supervised learning algorithms exists, every one of them with its own advantages and drawbacks. There are some basic issues that affect the accuracy of classifier while solving a supervised learning problem, like bias-variance tradeoff, dimensionality of input space, and noise in the input data space. All these problems affect the accuracy of classifier and are the reason that there is no global optimal method for classification. There is not any generalized improvement method that can increase the accuracy of any classifier while addressing all the problems stated above. This paper proposes a global optimization ensemble model for classification methods (GMC that can improve the overall accuracy for supervised learning problems. The experimental results on various public datasets showed that the proposed model improved the accuracy of the classification models from 1% to 30% depending upon the algorithm complexity.

  5. Yarn-dyed fabric defect classification based on convolutional neural network

    Science.gov (United States)

    Jing, Junfeng; Dong, Amei; Li, Pengfei; Zhang, Kaibing

    2017-09-01

    Considering that manual inspection of the yarn-dyed fabric can be time consuming and inefficient, we propose a yarn-dyed fabric defect classification method by using a convolutional neural network (CNN) based on a modified AlexNet. CNN shows powerful ability in performing feature extraction and fusion by simulating the learning mechanism of human brain. The local response normalization layers in AlexNet are replaced by the batch normalization layers, which can enhance both the computational efficiency and classification accuracy. In the training process of the network, the characteristics of the defect are extracted step by step and the essential features of the image can be obtained from the fusion of the edge details with several convolution operations. Then the max-pooling layers, the dropout layers, and the fully connected layers are employed in the classification model to reduce the computation cost and extract more precise features of the defective fabric. Finally, the results of the defect classification are predicted by the softmax function. The experimental results show promising performance with an acceptable average classification rate and strong robustness on yarn-dyed fabric defect classification.

  6. ADHD classification using bag of words approach on network features

    Science.gov (United States)

    Solmaz, Berkan; Dey, Soumyabrata; Rao, A. Ravishankar; Shah, Mubarak

    2012-02-01

    Attention Deficit Hyperactivity Disorder (ADHD) is receiving lots of attention nowadays mainly because it is one of the common brain disorders among children and not much information is known about the cause of this disorder. In this study, we propose to use a novel approach for automatic classification of ADHD conditioned subjects and control subjects using functional Magnetic Resonance Imaging (fMRI) data of resting state brains. For this purpose, we compute the correlation between every possible voxel pairs within a subject and over the time frame of the experimental protocol. A network of voxels is constructed by representing a high correlation value between any two voxels as an edge. A Bag-of-Words (BoW) approach is used to represent each subject as a histogram of network features; such as the number of degrees per voxel. The classification is done using a Support Vector Machine (SVM). We also investigate the use of raw intensity values in the time series for each voxel. Here, every subject is represented as a combined histogram of network and raw intensity features. Experimental results verified that the classification accuracy improves when the combined histogram is used. We tested our approach on a highly challenging dataset released by NITRC for ADHD-200 competition and obtained promising results. The dataset not only has a large size but also includes subjects from different demography and edge groups. To the best of our knowledge, this is the first paper to propose BoW approach in any functional brain disorder classification and we believe that this approach will be useful in analysis of many brain related conditions.

  7. Classification of conductance traces with recurrent neural networks

    Science.gov (United States)

    Lauritzen, Kasper P.; Magyarkuti, András; Balogh, Zoltán; Halbritter, András; Solomon, Gemma C.

    2018-02-01

    We present a new automated method for structural classification of the traces obtained in break junction experiments. Using recurrent neural networks trained on the traces of minimal cross-sectional area in molecular dynamics simulations, we successfully separate the traces into two classes: point contact or nanowire. This is done without any assumptions about the expected features of each class. The trained neural network is applied to experimental break junction conductance traces, and it separates the classes as well as the previously used experimental methods. The effect of using partial conductance traces is explored, and we show that the method performs equally well using full or partial traces (as long as the trace just prior to breaking is included). When only the initial part of the trace is included, the results are still better than random chance. Finally, we show that the neural network classification method can be used to classify experimental conductance traces without using simulated results for training, but instead training the network on a few representative experimental traces. This offers a tool to recognize some characteristic motifs of the traces, which can be hard to find by simple data selection algorithms.

  8. The Importance of Classification to Business Model Research

    OpenAIRE

    Susan Lambert

    2015-01-01

    Purpose: To bring to the fore the scientific significance of classification and its role in business model theory building. To propose a method by which existing classifications of business models can be analyzed and new ones developed. Design/Methodology/Approach: A review of the scholarly literature relevant to classifications of business models is presented along with a brief overview of classification theory applicable to business model research. Existing business model classification...

  9. Modeling the citation network by network cosmology.

    Science.gov (United States)

    Xie, Zheng; Ouyang, Zhenzheng; Zhang, Pengyuan; Yi, Dongyun; Kong, Dexing

    2015-01-01

    Citation between papers can be treated as a causal relationship. In addition, some citation networks have a number of similarities to the causal networks in network cosmology, e.g., the similar in-and out-degree distributions. Hence, it is possible to model the citation network using network cosmology. The casual network models built on homogenous spacetimes have some restrictions when describing some phenomena in citation networks, e.g., the hot papers receive more citations than other simultaneously published papers. We propose an inhomogenous causal network model to model the citation network, the connection mechanism of which well expresses some features of citation. The node growth trend and degree distributions of the generated networks also fit those of some citation networks well.

  10. Brain Network Modelling

    DEFF Research Database (Denmark)

    Andersen, Kasper Winther

    Three main topics are presented in this thesis. The first and largest topic concerns network modelling of functional Magnetic Resonance Imaging (fMRI) and Diffusion Weighted Imaging (DWI). In particular nonparametric Bayesian methods are used to model brain networks derived from resting state f...... for their ability to reproduce node clustering and predict unseen data. Comparing the models on whole brain networks, BCD and IRM showed better reproducibility and predictability than IDM, suggesting that resting state networks exhibit community structure. This also points to the importance of using models, which...... allow for complex interactions between all pairs of clusters. In addition, it is demonstrated how the IRM can be used for segmenting brain structures into functionally coherent clusters. A new nonparametric Bayesian network model is presented. The model builds upon the IRM and can be used to infer...

  11. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

    Science.gov (United States)

    Huo, Guanying

    2017-01-01

    As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases. PMID:28316614

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

    KAUST Repository

    Aljaafari, Nura

    2018-04-15

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

  13. Modeling Epidemic Network Failures

    DEFF Research Database (Denmark)

    Ruepp, Sarah Renée; Fagertun, Anna Manolova

    2013-01-01

    This paper presents the implementation of a failure propagation model for transport networks when multiple failures occur resulting in an epidemic. We model the Susceptible Infected Disabled (SID) epidemic model and validate it by comparing it to analytical solutions. Furthermore, we evaluate...... the SID model’s behavior and impact on the network performance, as well as the severity of the infection spreading. The simulations are carried out in OPNET Modeler. The model provides an important input to epidemic connection recovery mechanisms, and can due to its flexibility and versatility be used...... to evaluate multiple epidemic scenarios in various network types....

  14. A quantum-implementable neural network model

    Science.gov (United States)

    Chen, Jialin; Wang, Lingli; Charbon, Edoardo

    2017-10-01

    A quantum-implementable neural network, namely quantum probability neural network (QPNN) model, is proposed in this paper. QPNN can use quantum parallelism to trace all possible network states to improve the result. Due to its unique quantum nature, this model is robust to several quantum noises under certain conditions, which can be efficiently implemented by the qubus quantum computer. Another advantage is that QPNN can be used as memory to retrieve the most relevant data and even to generate new data. The MATLAB experimental results of Iris data classification and MNIST handwriting recognition show that much less neuron resources are required in QPNN to obtain a good result than the classical feedforward neural network. The proposed QPNN model indicates that quantum effects are useful for real-life classification tasks.

  15. Classification using Hierarchical Naive Bayes models

    DEFF Research Database (Denmark)

    Langseth, Helge; Dyhre Nielsen, Thomas

    2006-01-01

    Classification problems have a long history in the machine learning literature. One of the simplest, and yet most consistently well-performing set of classifiers is the Naïve Bayes models. However, an inherent problem with these classifiers is the assumption that all attributes used to describe......, termed Hierarchical Naïve Bayes models. Hierarchical Naïve Bayes models extend the modeling flexibility of Naïve Bayes models by introducing latent variables to relax some of the independence statements in these models. We propose a simple algorithm for learning Hierarchical Naïve Bayes models...

  16. Data fusion for target tracking and classification with wireless sensor network

    Science.gov (United States)

    Pannetier, Benjamin; Doumerc, Robin; Moras, Julien; Dezert, Jean; Canevet, Loic

    2016-10-01

    In this paper, we address the problem of multiple ground target tracking and classification with information obtained from a unattended wireless sensor network. A multiple target tracking (MTT) algorithm, taking into account road and vegetation information, is proposed based on a centralized architecture. One of the key issue is how to adapt classical MTT approach to satisfy embedded processing. Based on track statistics, the classification algorithm uses estimated location, velocity and acceleration to help to classify targets. The algorithms enables tracking human and vehicles driving both on and off road. We integrate road or trail width and vegetation cover, as constraints in target motion models to improve performance of tracking under constraint with classification fusion. Our algorithm also presents different dynamic models, to palliate the maneuvers of targets. The tracking and classification algorithms are integrated into an operational platform (the fusion node). In order to handle realistic ground target tracking scenarios, we use an autonomous smart computer deposited in the surveillance area. After the calibration step of the heterogeneous sensor network, our system is able to handle real data from a wireless ground sensor network. The performance of system is evaluated in a real exercise for intelligence operation ("hunter hunt" scenario).

  17. Extension of mixture-of-experts networks for binary classification of hierarchical data.

    Science.gov (United States)

    Ng, Shu-Kay; McLachlan, Geoffrey J

    2007-09-01

    For many applied problems in the context of medically relevant artificial intelligence, the data collected exhibit a hierarchical or clustered structure. Ignoring the interdependence between hierarchical data can result in misleading classification. In this paper, we extend the mechanism for mixture-of-experts (ME) networks for binary classification of hierarchical data. Another extension is to quantify cluster-specific information on data hierarchy by random effects via the generalized linear mixed-effects model (GLMM). The extension of ME networks is implemented by allowing for correlation in the hierarchical data in both the gating and expert networks via the GLMM. The proposed model is illustrated using a real thyroid disease data set. In our study, we consider 7652 thyroid diagnosis records from 1984 to early 1987 with complete information on 20 attribute values. We obtain 10 independent random splits of the data into a training set and a test set in the proportions 85% and 15%. The test sets are used to assess the generalization performance of the proposed model, based on the percentage of misclassifications. For comparison, the results obtained from the ME network with independence assumption are also included. With the thyroid disease data, the misclassification rate on test sets for the extended ME network is 8.9%, compared to 13.9% for the ME network. In addition, based on model selection methods described in Section 2, a network with two experts is selected. These two expert networks can be considered as modeling two groups of patients with high and low incidence rates. Significant variation among the predicted cluster-specific random effects is detected in the patient group with low incidence rate. It is shown that the extended ME network outperforms the ME network for binary classification of hierarchical data. With the thyroid disease data, useful information on the relative log odds of patients with diagnosed conditions at different periods can be

  18. Artificial neural network modelling

    CERN Document Server

    Samarasinghe, Sandhya

    2016-01-01

    This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .

  19. Sequential Classification of Palm Gestures Based on A* Algorithm and MLP Neural Network for Quadrocopter Control

    Directory of Open Access Journals (Sweden)

    Wodziński Marek

    2017-06-01

    Full Text Available This paper presents an alternative approach to the sequential data classification, based on traditional machine learning algorithms (neural networks, principal component analysis, multivariate Gaussian anomaly detector and finding the shortest path in a directed acyclic graph, using A* algorithm with a regression-based heuristic. Palm gestures were used as an example of the sequential data and a quadrocopter was the controlled object. The study includes creation of a conceptual model and practical construction of a system using the GPU to ensure the realtime operation. The results present the classification accuracy of chosen gestures and comparison of the computation time between the CPU- and GPU-based solutions.

  20. A Robust Geometric Model for Argument Classification

    Science.gov (United States)

    Giannone, Cristina; Croce, Danilo; Basili, Roberto; de Cao, Diego

    Argument classification is the task of assigning semantic roles to syntactic structures in natural language sentences. Supervised learning techniques for frame semantics have been recently shown to benefit from rich sets of syntactic features. However argument classification is also highly dependent on the semantics of the involved lexicals. Empirical studies have shown that domain dependence of lexical information causes large performance drops in outside domain tests. In this paper a distributional approach is proposed to improve the robustness of the learning model against out-of-domain lexical phenomena.

  1. Classification of behavior using unsupervised temporal neural networks

    International Nuclear Information System (INIS)

    Adair, K.L.

    1998-03-01

    Adding recurrent connections to unsupervised neural networks used for clustering creates a temporal neural network which clusters a sequence of inputs as they appear over time. The model presented combines the Jordan architecture with the unsupervised learning technique Adaptive Resonance Theory, Fuzzy ART. The combination yields a neural network capable of quickly clustering sequential pattern sequences as the sequences are generated. The applicability of the architecture is illustrated through a facility monitoring problem

  2. Fault Tolerant Neural Network for ECG Signal Classification Systems

    Directory of Open Access Journals (Sweden)

    MERAH, M.

    2011-08-01

    Full Text Available The aim of this paper is to apply a new robust hardware Artificial Neural Network (ANN for ECG classification systems. This ANN includes a penalization criterion which makes the performances in terms of robustness. Specifically, in this method, the ANN weights are normalized using the auto-prune method. Simulations performed on the MIT ? BIH ECG signals, have shown that significant robustness improvements are obtained regarding potential hardware artificial neuron failures. Moreover, we show that the proposed design achieves better generalization performances, compared to the standard back-propagation algorithm.

  3. Deep neural networks for texture classification-A theoretical analysis.

    Science.gov (United States)

    Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

    2018-01-01

    We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

  4. General regression and representation model for classification.

    Directory of Open Access Journals (Sweden)

    Jianjun Qian

    Full Text Available Recently, the regularized coding-based classification methods (e.g. SRC and CRC show a great potential for pattern classification. However, most existing coding methods assume that the representation residuals are uncorrelated. In real-world applications, this assumption does not hold. In this paper, we take account of the correlations of the representation residuals and develop a general regression and representation model (GRR for classification. GRR not only has advantages of CRC, but also takes full use of the prior information (e.g. the correlations between representation residuals and representation coefficients and the specific information (weight matrix of image pixels to enhance the classification performance. GRR uses the generalized Tikhonov regularization and K Nearest Neighbors to learn the prior information from the training data. Meanwhile, the specific information is obtained by using an iterative algorithm to update the feature (or image pixel weights of the test sample. With the proposed model as a platform, we design two classifiers: basic general regression and representation classifier (B-GRR and robust general regression and representation classifier (R-GRR. The experimental results demonstrate the performance advantages of proposed methods over state-of-the-art algorithms.

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

    Science.gov (United States)

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

    2018-04-12

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

  6. Artificial Immune Networks: Models and Applications

    Directory of Open Access Journals (Sweden)

    Xian Shen

    2008-06-01

    Full Text Available Artificial Immune Systems (AIS, which is inspired by the nature immune system, has been applied for solving complex computational problems in classification, pattern rec- ognition, and optimization. In this paper, the theory of the natural immune system is first briefly introduced. Next, we compare some well-known AIS and their applications. Several representative artificial immune networks models are also dis- cussed. Moreover, we demonstrate the applications of artificial immune networks in various engineering fields.

  7. An alternative respiratory sounds classification system utilizing artificial neural networks

    Directory of Open Access Journals (Sweden)

    Rami J Oweis

    2015-04-01

    Full Text Available Background: Computerized lung sound analysis involves recording lung sound via an electronic device, followed by computer analysis and classification based on specific signal characteristics as non-linearity and nonstationarity caused by air turbulence. An automatic analysis is necessary to avoid dependence on expert skills. Methods: This work revolves around exploiting autocorrelation in the feature extraction stage. All process stages were implemented in MATLAB. The classification process was performed comparatively using both artificial neural networks (ANNs and adaptive neuro-fuzzy inference systems (ANFIS toolboxes. The methods have been applied to 10 different respiratory sounds for classification. Results: The ANN was superior to the ANFIS system and returned superior performance parameters. Its accuracy, specificity, and sensitivity were 98.6%, 100%, and 97.8%, respectively. The obtained parameters showed superiority to many recent approaches. Conclusions: The promising proposed method is an efficient fast tool for the intended purpose as manifested in the performance parameters, specifically, accuracy, specificity, and sensitivity. Furthermore, it may be added that utilizing the autocorrelation function in the feature extraction in such applications results in enhanced performance and avoids undesired computation complexities compared to other techniques.

  8. Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification

    Science.gov (United States)

    Anwer, Rao Muhammad; Khan, Fahad Shahbaz; van de Weijer, Joost; Molinier, Matthieu; Laaksonen, Jorma

    2018-04-01

    Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene classification.

  9. Convolutional deep belief network with feature encoding for classification of neuroblastoma histological images

    Directory of Open Access Journals (Sweden)

    Soheila Gheisari

    2018-01-01

    Full Text Available Background: Neuroblastoma is the most common extracranial solid tumor in children younger than 5 years old. Optimal management of neuroblastic tumors depends on many factors including histopathological classification. The gold standard for classification of neuroblastoma histological images is visual microscopic assessment. In this study, we propose and evaluate a deep learning approach to classify high-resolution digital images of neuroblastoma histology into five different classes determined by the Shimada classification. Subjects and Methods: We apply a combination of convolutional deep belief network (CDBN with feature encoding algorithm that automatically classifies digital images of neuroblastoma histology into five different classes. We design a three-layer CDBN to extract high-level features from neuroblastoma histological images and combine with a feature encoding model to extract features that are highly discriminative in the classification task. The extracted features are classified into five different classes using a support vector machine classifier. Data: We constructed a dataset of 1043 neuroblastoma histological images derived from Aperio scanner from 125 patients representing different classes of neuroblastoma tumors. Results: The weighted average F-measure of 86.01% was obtained from the selected high-level features, outperforming state-of-the-art methods. Conclusion: The proposed computer-aided classification system, which uses the combination of deep architecture and feature encoding to learn high-level features, is highly effective in the classification of neuroblastoma histological images.

  10. Classification of breast cancer histology images using Convolutional Neural Networks.

    Directory of Open Access Journals (Sweden)

    Teresa Araújo

    Full Text Available Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

  11. Spectral-spatial classification of hyperspectral image using three-dimensional convolution network

    Science.gov (United States)

    Liu, Bing; Yu, Xuchu; Zhang, Pengqiang; Tan, Xiong; Wang, Ruirui; Zhi, Lu

    2018-01-01

    Recently, hyperspectral image (HSI) classification has become a focus of research. However, the complex structure of an HSI makes feature extraction difficult to achieve. Most current methods build classifiers based on complex handcrafted features computed from the raw inputs. The design of an improved 3-D convolutional neural network (3D-CNN) model for HSI classification is described. This model extracts features from both the spectral and spatial dimensions through the application of 3-D convolutions, thereby capturing the important discrimination information encoded in multiple adjacent bands. The designed model views the HSI cube data altogether without relying on any pre- or postprocessing. In addition, the model is trained in an end-to-end fashion without any handcrafted features. The designed model was applied to three widely used HSI datasets. The experimental results demonstrate that the 3D-CNN-based method outperforms conventional methods even with limited labeled training samples.

  12. High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.

    Science.gov (United States)

    Rajkomar, Alvin; Lingam, Sneha; Taylor, Andrew G; Blum, Michael; Mongan, John

    2017-02-01

    The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73-100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.

  13. Latent Classification Models for Binary Data

    DEFF Research Database (Denmark)

    Langseth, Helge; Nielsen, Thomas Dyhre

    2009-01-01

    One of the simplest, and yet most consistently well-performing set of classifiers is the naive Bayes models (a special class of Bayesian network models). However, these models rely on the (naive) assumption that all the attributes used to describe an instance are conditionally independent given t...

  14. Land Cover Classification via Multitemporal Spatial Data by Deep Recurrent Neural Networks

    Science.gov (United States)

    Ienco, Dino; Gaetano, Raffaele; Dupaquier, Claire; Maurel, Pierre

    2017-10-01

    Nowadays, modern earth observation programs produce huge volumes of satellite images time series (SITS) that can be useful to monitor geographical areas through time. How to efficiently analyze such kind of information is still an open question in the remote sensing field. Recently, deep learning methods proved suitable to deal with remote sensing data mainly for scene classification (i.e. Convolutional Neural Networks - CNNs - on single images) while only very few studies exist involving temporal deep learning approaches (i.e Recurrent Neural Networks - RNNs) to deal with remote sensing time series. In this letter we evaluate the ability of Recurrent Neural Networks, in particular the Long-Short Term Memory (LSTM) model, to perform land cover classification considering multi-temporal spatial data derived from a time series of satellite images. We carried out experiments on two different datasets considering both pixel-based and object-based classification. The obtained results show that Recurrent Neural Networks are competitive compared to state-of-the-art classifiers, and may outperform classical approaches in presence of low represented and/or highly mixed classes. We also show that using the alternative feature representation generated by LSTM can improve the performances of standard classifiers.

  15. Classification of CT brain images based on deep learning networks.

    Science.gov (United States)

    Gao, Xiaohong W; Hui, Rui; Tian, Zengmin

    2017-01-01

    While computerised tomography (CT) may have been the first imaging tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimer's disease (AD). On the other hand, with the nature of being prevalent, inexpensive and non-invasive, CT does present diagnostic features of AD to a great extent. This study explores the significance and impact on the application of the burgeoning deep learning techniques to the task of classification of CT brain images, in particular utilising convolutional neural network (CNN), aiming at providing supplementary information for the early diagnosis of Alzheimer's disease. Towards this end, three categories of CT images (N = 285) are clustered into three groups, which are AD, lesion (e.g. tumour) and normal ageing. In addition, considering the characteristics of this collection with larger thickness along the direction of depth (z) (~3-5 mm), an advanced CNN architecture is established integrating both 2D and 3D CNN networks. The fusion of the two CNN networks is subsequently coordinated based on the average of Softmax scores obtained from both networks consolidating 2D images along spatial axial directions and 3D segmented blocks respectively. As a result, the classification accuracy rates rendered by this elaborated CNN architecture are 85.2%, 80% and 95.3% for classes of AD, lesion and normal respectively with an average of 87.6%. Additionally, this improved CNN network appears to outperform the others when in comparison with 2D version only of CNN network as well as a number of state of the art hand-crafted approaches. As a result, these approaches deliver accuracy rates in percentage of 86.3, 85.6 ± 1.10, 86.3 ± 1.04, 85.2 ± 1.60, 83.1 ± 0.35 for 2D CNN, 2D SIFT, 2D KAZE, 3D SIFT and 3D KAZE respectively. The two major contributions of the paper constitute a new 3-D approach while applying deep learning technique to extract signature information

  16. Text document classification based on mixture models

    Czech Academy of Sciences Publication Activity Database

    Novovičová, Jana; Malík, Antonín

    2004-01-01

    Roč. 40, č. 3 (2004), s. 293-304 ISSN 0023-5954 R&D Projects: GA AV ČR IAA2075302; GA ČR GA102/03/0049; GA AV ČR KSK1019101 Institutional research plan: CEZ:AV0Z1075907 Keywords : text classification * text categorization * multinomial mixture model Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 0.224, year: 2004

  17. Nonlinear Inertia Classification Model and Application

    Directory of Open Access Journals (Sweden)

    Mei Wang

    2014-01-01

    Full Text Available Classification model of support vector machine (SVM overcomes the problem of a big number of samples. But the kernel parameter and the punishment factor have great influence on the quality of SVM model. Particle swarm optimization (PSO is an evolutionary search algorithm based on the swarm intelligence, which is suitable for parameter optimization. Accordingly, a nonlinear inertia convergence classification model (NICCM is proposed after the nonlinear inertia convergence (NICPSO is developed in this paper. The velocity of NICPSO is firstly defined as the weighted velocity of the inertia PSO, and the inertia factor is selected to be a nonlinear function. NICPSO is used to optimize the kernel parameter and a punishment factor of SVM. Then, NICCM classifier is trained by using the optical punishment factor and the optical kernel parameter that comes from the optimal particle. Finally, NICCM is applied to the classification of the normal state and fault states of online power cable. It is experimentally proved that the iteration number for the proposed NICPSO to reach the optimal position decreases from 15 to 5 compared with PSO; the training duration is decreased by 0.0052 s and the recognition precision is increased by 4.12% compared with SVM.

  18. Fuzzy One-Class Classification Model Using Contamination Neighborhoods

    Directory of Open Access Journals (Sweden)

    Lev V. Utkin

    2012-01-01

    Full Text Available A fuzzy classification model is studied in the paper. It is based on the contaminated (robust model which produces fuzzy expected risk measures characterizing classification errors. Optimal classification parameters of the models are derived by minimizing the fuzzy expected risk. It is shown that an algorithm for computing the classification parameters is reduced to a set of standard support vector machine tasks with weighted data points. Experimental results with synthetic data illustrate the proposed fuzzy model.

  19. 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%.

  20. Malware Classification Based on the Behavior Analysis and Back Propagation Neural Network

    Directory of Open Access Journals (Sweden)

    Pan Zhi-Peng

    2016-01-01

    Full Text Available With the development of the Internet, malwares have also been expanded on the network systems rapidly. In order to deal with the diversity and amount of the variants, a number of automated behavior analysis tools have emerged as the time requires. Yet these tools produce detailed behavior reports of the malwares, it still needs to specify its category and judge its criticality manually. In this paper, we propose an automated malware classification approach based on the behavior analysis. We firstly perform dynamic analyses to obtain the detailed behavior profiles of the malwares, which are then used to abstract the main features of the malwares and serve as the inputs of the Back Propagation (BP Neural Network model.The experimental results demonstrate that our classification technique is able to classify the malware variants effectively and detect malware accurately.

  1. Recurrent Neural Networks to Correct Satellite Image Classification Maps

    Science.gov (United States)

    Maggiori, Emmanuel; Charpiat, Guillaume; Tarabalka, Yuliya; Alliez, Pierre

    2017-09-01

    While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the proper nature of the most common CNN architectures makes them good at recognizing but poor at localizing objects precisely. This problem is magnified in the context of aerial and satellite image labeling, where a spatially fine object outlining is of paramount importance. Different iterative enhancement algorithms have been presented in the literature to progressively improve the coarse CNN outputs, seeking to sharpen object boundaries around real image edges. However, one must carefully design, choose and tune such algorithms. Instead, our goal is to directly learn the iterative process itself. For this, we formulate a generic iterative enhancement process inspired from partial differential equations, and observe that it can be expressed as a recurrent neural network (RNN). Consequently, we train such a network from manually labeled data for our enhancement task. In a series of experiments we show that our RNN effectively learns an iterative process that significantly improves the quality of satellite image classification maps.

  2. A classification of event sequences in the influence network

    Science.gov (United States)

    Walsh, James Lyons; Knuth, Kevin H.

    2017-06-01

    We build on the classification in [1] of event sequences in the influence network as respecting collinearity or not, so as to determine in future work what phenomena arise in each case. Collinearity enables each observer to uniquely associate each particle event of influencing with one of the observer's own events, even in the case of events of influencing the other observer. We further classify events as to whether they are spacetime events that obey in the fine-grained case the coarse-grained conditions of [2], finding that Newton's First and Second Laws of motion are obeyed at spacetime events. A proof of Newton's Third Law under particular circumstances is also presented.

  3. Reducing Spatial Data Complexity for Classification Models

    International Nuclear Information System (INIS)

    Ruta, Dymitr; Gabrys, Bogdan

    2007-01-01

    Intelligent data analytics gradually becomes a day-to-day reality of today's businesses. However, despite rapidly increasing storage and computational power current state-of-the-art predictive models still can not handle massive and noisy corporate data warehouses. What is more adaptive and real-time operational environment requires multiple models to be frequently retrained which further hinders their use. Various data reduction techniques ranging from data sampling up to density retention models attempt to address this challenge by capturing a summarised data structure, yet they either do not account for labelled data or degrade the classification performance of the model trained on the condensed dataset. Our response is a proposition of a new general framework for reducing the complexity of labelled data by means of controlled spatial redistribution of class densities in the input space. On the example of Parzen Labelled Data Compressor (PLDC) we demonstrate a simulatory data condensation process directly inspired by the electrostatic field interaction where the data are moved and merged following the attracting and repelling interactions with the other labelled data. The process is controlled by the class density function built on the original data that acts as a class-sensitive potential field ensuring preservation of the original class density distributions, yet allowing data to rearrange and merge joining together their soft class partitions. As a result we achieved a model that reduces the labelled datasets much further than any competitive approaches yet with the maximum retention of the original class densities and hence the classification performance. PLDC leaves the reduced dataset with the soft accumulative class weights allowing for efficient online updates and as shown in a series of experiments if coupled with Parzen Density Classifier (PDC) significantly outperforms competitive data condensation methods in terms of classification performance at the

  4. Reducing Spatial Data Complexity for Classification Models

    Science.gov (United States)

    Ruta, Dymitr; Gabrys, Bogdan

    2007-11-01

    Intelligent data analytics gradually becomes a day-to-day reality of today's businesses. However, despite rapidly increasing storage and computational power current state-of-the-art predictive models still can not handle massive and noisy corporate data warehouses. What is more adaptive and real-time operational environment requires multiple models to be frequently retrained which further hinders their use. Various data reduction techniques ranging from data sampling up to density retention models attempt to address this challenge by capturing a summarised data structure, yet they either do not account for labelled data or degrade the classification performance of the model trained on the condensed dataset. Our response is a proposition of a new general framework for reducing the complexity of labelled data by means of controlled spatial redistribution of class densities in the input space. On the example of Parzen Labelled Data Compressor (PLDC) we demonstrate a simulatory data condensation process directly inspired by the electrostatic field interaction where the data are moved and merged following the attracting and repelling interactions with the other labelled data. The process is controlled by the class density function built on the original data that acts as a class-sensitive potential field ensuring preservation of the original class density distributions, yet allowing data to rearrange and merge joining together their soft class partitions. As a result we achieved a model that reduces the labelled datasets much further than any competitive approaches yet with the maximum retention of the original class densities and hence the classification performance. PLDC leaves the reduced dataset with the soft accumulative class weights allowing for efficient online updates and as shown in a series of experiments if coupled with Parzen Density Classifier (PDC) significantly outperforms competitive data condensation methods in terms of classification performance at the

  5. Multilabel user classification using the community structure of online networks.

    Science.gov (United States)

    Rizos, Georgios; Papadopoulos, Symeon; Kompatsiaris, Yiannis

    2017-01-01

    We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE), an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user's graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score.

  6. Multilabel user classification using the community structure of online networks.

    Directory of Open Access Journals (Sweden)

    Georgios Rizos

    Full Text Available We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE, an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user's graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score.

  7. Classification of crystal structure using a convolutional neural network.

    Science.gov (United States)

    Park, Woon Bae; Chung, Jiyong; Jung, Jaeyoung; Sohn, Keemin; Singh, Satendra Pal; Pyo, Myoungho; Shin, Namsoo; Sohn, Kee-Sun

    2017-07-01

    A deep machine-learning technique based on a convolutional neural network (CNN) is introduced. It has been used for the classification of powder X-ray diffraction (XRD) patterns in terms of crystal system, extinction group and space group. About 150 000 powder XRD patterns were collected and used as input for the CNN with no handcrafted engineering involved, and thereby an appropriate CNN architecture was obtained that allowed determination of the crystal system, extinction group and space group. In sharp contrast with the traditional use of powder XRD pattern analysis, the CNN never treats powder XRD patterns as a deconvoluted and discrete peak position or as intensity data, but instead the XRD patterns are regarded as nothing but a pattern similar to a picture. The CNN interprets features that humans cannot recognize in a powder XRD pattern. As a result, accuracy levels of 81.14, 83.83 and 94.99% were achieved for the space-group, extinction-group and crystal-system classifications, respectively. The well trained CNN was then used for symmetry identification of unknown novel inorganic compounds.

  8. A neural network approach for radiographic image classification in NDT

    International Nuclear Information System (INIS)

    Lavayssiere, B.

    1993-05-01

    Radiography is used by EDF for pipe inspection in nuclear power plants in order to detect defects. The radiographs obtained are then digitized in a well-defined protocol. The aim of EDF consists of developing a non destructive testing system for recognizing defects. In this note, we describe the recognition procedure of areas with defects. We first present the digitization protocol, specifies the poor quality of images under study and propose a procedure to enhance defects. We then examine the problem raised by the choice of good features for classification. After having proved that statistical or standard textural features such as homogeneity, entropy or contrast are not relevant, we develop a geometrical-statistical approach based on the cooperation between signal correlations study and regional extrema analysis. The principle consists of analysing and comparing for areas with defects and without any defect, the evolution of conditional probabilities matrices for increasing neighbourhood sizes, the shape of variograms and the location of regional minima. We demonstrate that anisotropy and surface of series of 'comet tails' associated with probability matrices, variograms slope and statistical indices, regional extrema location, are features able to discriminate areas with defects from areas without any. The classification is then realized by a neural network, which structure, properties and learning mechanisms are detailed. Finally we discuss the results. (author). 5 figs., 21 refs

  9. A simple and robust method for automated photometric classification of supernovae using neural networks

    Science.gov (United States)

    Karpenka, N. V.; Feroz, F.; Hobson, M. P.

    2013-02-01

    A method is presented for automated photometric classification of supernovae (SNe) as Type Ia or non-Ia. A two-step approach is adopted in which (i) the SN light curve flux measurements in each observing filter are fitted separately to an analytical parametrized function that is sufficiently flexible to accommodate virtually all types of SNe and (ii) the fitted function parameters and their associated uncertainties, along with the number of flux measurements, the maximum-likelihood value of the fit and Bayesian evidence for the model, are used as the input feature vector to a classification neural network that outputs the probability that the SN under consideration is of Type Ia. The method is trained and tested using data released following the Supernova Photometric Classification Challenge (SNPCC), consisting of light curves for 20 895 SNe in total. We consider several random divisions of the data into training and testing sets: for instance, for our sample D_1 (D_4), a total of 10 (40) per cent of the data are involved in training the algorithm and the remainder used for blind testing of the resulting classifier; we make no selection cuts. Assigning a canonical threshold probability of pth = 0.5 on the network output to class an SN as Type Ia, for the sample D_1 (D_4) we obtain a completeness of 0.78 (0.82), purity of 0.77 (0.82) and SNPCC figure of merit of 0.41 (0.50). Including the SN host-galaxy redshift and its uncertainty as additional inputs to the classification network results in a modest 5-10 per cent increase in these values. We find that the quality of the classification does not vary significantly with SN redshift. Moreover, our probabilistic classification method allows one to calculate the expected completeness, purity and figure of merit (or other measures of classification quality) as a function of the threshold probability pth, without knowing the true classes of the SNe in the testing sample, as is the case in the classification of real SNe

  10. 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.

  11. Collaborative classification of hyperspectral and visible images with convolutional neural network

    Science.gov (United States)

    Zhang, Mengmeng; Li, Wei; Du, Qian

    2017-10-01

    Recent advances in remote sensing technology have made multisensor data available for the same area, and it is well-known that remote sensing data processing and analysis often benefit from multisource data fusion. Specifically, low spatial resolution of hyperspectral imagery (HSI) degrades the quality of the subsequent classification task while using visible (VIS) images with high spatial resolution enables high-fidelity spatial analysis. A collaborative classification framework is proposed to fuse HSI and VIS images for finer classification. First, the convolutional neural network model is employed to extract deep spectral features for HSI classification. Second, effective binarized statistical image features are learned as contextual basis vectors for the high-resolution VIS image, followed by a classifier. The proposed approach employs diversified data in a decision fusion, leading to an integration of the rich spectral information, spatial information, and statistical representation information. In particular, the proposed approach eliminates the potential problems of the curse of dimensionality and excessive computation time. The experiments evaluated on two standard data sets demonstrate better classification performance offered by this framework.

  12. Classification of data patterns using an autoassociative neural network topology

    Science.gov (United States)

    Dietz, W. E.; Kiech, E. L.; Ali, M.

    1989-01-01

    A diagnostic expert system based on neural networks is developed and applied to the real-time diagnosis of jet and rocket engines. The expert system methodologies are based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. The approach addresses deficiencies inherent in many feedforward neural network models and greatly reduces the number of networks necessary to identify the existence of a fault condition and estimate the duration and severity of the identified fault. The network topology used in the present implementation of the diagnostic system is described, as well as the training regimen used and the response of the system to inputs representing both previously observed and unknown fault scenarios. Noise effects on the integrity of the diagnosis are also evaluated.

  13. Graphical Model Theory for Wireless Sensor Networks

    International Nuclear Information System (INIS)

    Davis, William B.

    2002-01-01

    Information processing in sensor networks, with many small processors, demands a theory of computation that allows the minimization of processing effort, and the distribution of this effort throughout the network. Graphical model theory provides a probabilistic theory of computation that explicitly addresses complexity and decentralization for optimizing network computation. The junction tree algorithm, for decentralized inference on graphical probability models, can be instantiated in a variety of applications useful for wireless sensor networks, including: sensor validation and fusion; data compression and channel coding; expert systems, with decentralized data structures, and efficient local queries; pattern classification, and machine learning. Graphical models for these applications are sketched, and a model of dynamic sensor validation and fusion is presented in more depth, to illustrate the junction tree algorithm

  14. Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification.

    Science.gov (United States)

    Rueckauer, Bodo; Lungu, Iulia-Alexandra; Hu, Yuhuang; Pfeiffer, Michael; Liu, Shih-Chii

    2017-01-01

    Spiking neural networks (SNNs) can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs) can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications.

  15. Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

    Directory of Open Access Journals (Sweden)

    Bodo Rueckauer

    2017-12-01

    Full Text Available Spiking neural networks (SNNs can potentially offer an efficient way of doing inference because the neurons in the networks are sparsely activated and computations are event-driven. Previous work showed that simple continuous-valued deep Convolutional Neural Networks (CNNs can be converted into accurate spiking equivalents. These networks did not include certain common operations such as max-pooling, softmax, batch-normalization and Inception-modules. This paper presents spiking equivalents of these operations therefore allowing conversion of nearly arbitrary CNN architectures. We show conversion of popular CNN architectures, including VGG-16 and Inception-v3, into SNNs that produce the best results reported to date on MNIST, CIFAR-10 and the challenging ImageNet dataset. SNNs can trade off classification error rate against the number of available operations whereas deep continuous-valued neural networks require a fixed number of operations to achieve their classification error rate. From the examples of LeNet for MNIST and BinaryNet for CIFAR-10, we show that with an increase in error rate of a few percentage points, the SNNs can achieve more than 2x reductions in operations compared to the original CNNs. This highlights the potential of SNNs in particular when deployed on power-efficient neuromorphic spiking neuron chips, for use in embedded applications.

  16. Classification of stroke disease using convolutional neural network

    Science.gov (United States)

    Marbun, J. T.; Seniman; Andayani, U.

    2018-03-01

    Stroke is a condition that occurs when the blood supply stop flowing to the brain because of a blockage or a broken blood vessel. A symptoms that happen when experiencing stroke, some of them is a dropped consciousness, disrupted vision and paralyzed body. The general examination is being done to get a picture of the brain part that have stroke using Computerized Tomography (CT) Scan. The image produced from CT will be manually checked and need a proper lighting by doctor to get a type of stroke. That is why it needs a method to classify stroke from CT image automatically. A method proposed in this research is Convolutional Neural Network. CT image of the brain is used as the input for image processing. The stage before classification are image processing (Grayscaling, Scaling, Contrast Limited Adaptive Histogram Equalization, then the image being classified with Convolutional Neural Network. The result then showed that the method significantly conducted was able to be used as a tool to classify stroke disease in order to distinguish the type of stroke from CT image.

  17. a Novel Deep Convolutional Neural Network for Spectral-Spatial Classification of Hyperspectral Data

    Science.gov (United States)

    Li, N.; Wang, C.; Zhao, H.; Gong, X.; Wang, D.

    2018-04-01

    Spatial and spectral information are obtained simultaneously by hyperspectral remote sensing. Joint extraction of these information of hyperspectral image is one of most import methods for hyperspectral image classification. In this paper, a novel deep convolutional neural network (CNN) is proposed, which extracts spectral-spatial information of hyperspectral images correctly. The proposed model not only learns sufficient knowledge from the limited number of samples, but also has powerful generalization ability. The proposed framework based on three-dimensional convolution can extract spectral-spatial features of labeled samples effectively. Though CNN has shown its robustness to distortion, it cannot extract features of different scales through the traditional pooling layer that only have one size of pooling window. Hence, spatial pyramid pooling (SPP) is introduced into three-dimensional local convolutional filters for hyperspectral classification. Experimental results with a widely used hyperspectral remote sensing dataset show that the proposed model provides competitive performance.

  18. Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images.

    Science.gov (United States)

    Huang, Yue; Zheng, Han; Liu, Chi; Ding, Xinghao; Rohde, Gustavo K

    2017-11-01

    Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our paper assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.

  19. Artificial neural networks as classification and diagnostic tools for lymph node-negative breast cancers

    Energy Technology Data Exchange (ETDEWEB)

    Eswari J, Satya; Chandrakar, Neha [National Institute of Technology Raipur, Raipur (India)

    2016-04-15

    Artificial neural networks (ANNs) can be used to develop a technique to classify lymph node negative breast cancer that is prone to distant metastases based on gene expression signatures. The neural network used is a multilayered feed forward network that employs back propagation algorithm. Once trained with DNA microarraybased gene expression profiles of genes that were predictive of distant metastasis recurrence of lymph node negative breast cancer, the ANNs became capable of correctly classifying all samples and recognizing the genes most appropriate to the classification. To test the ability of the trained ANN models in recognizing lymph node negative breast cancer, we analyzed additional idle samples that were not used beforehand for the training procedure and obtained the correctly classified result in the validation set. For more substantial result, bootstrapping of training and testing dataset was performed as external validation. This study illustrates the potential application of ANN for breast tumor diagnosis and the identification of candidate targets in patients for therapy.

  20. Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery

    Directory of Open Access Journals (Sweden)

    Fan Hu

    2015-11-01

    Full Text Available Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineered features or unsupervised feature learning, can only generate mid-level image features with limited representative ability, which essentially prevents them from achieving better performance. Recently, the deep convolutional neural networks (CNNs, which are hierarchical architectures trained on large-scale datasets, have shown astounding performance in object recognition and detection. However, it is still not clear how to use these deep convolutional neural networks for high-resolution remote sensing (HRRS scene classification. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for HRRS scene classification. We propose two scenarios for generating image features via extracting CNN features from different layers. In the first scenario, the activation vectors extracted from fully-connected layers are regarded as the final image features; in the second scenario, we extract dense features from the last convolutional layer at multiple scales and then encode the dense features into global image features through commonly used feature coding approaches. Extensive experiments on two public scene classification datasets demonstrate that the image features obtained by the two proposed scenarios, even with a simple linear classifier, can result in remarkable performance and improve the state-of-the-art by a significant margin. The results reveal that the features from pre-trained CNNs generalize well to HRRS datasets and are more expressive than the low- and mid-level features. Moreover, we tentatively combine features extracted from different CNN models for better performance.

  1. Conceptualising Business Models: Definitions, Frameworks and Classifications

    Directory of Open Access Journals (Sweden)

    Erwin Fielt

    2013-12-01

    Full Text Available The business model concept is gaining traction in different disciplines but is still criticized for being fuzzy and vague and lacking consensus on its definition and compositional elements. In this paper we set out to advance our understanding of the business model concept by addressing three areas of foundational research: business model definitions, business model elements, and business model archetypes. We define a business model as a representation of the value logic of an organization in terms of how it creates and captures customer value. This abstract and generic definition is made more specific and operational by the compositional elements that need to address the customer, value proposition, organizational architecture (firm and network level and economics dimensions. Business model archetypes complement the definition and elements by providing a more concrete and empirical understanding of the business model concept. The main contributions of this paper are (1 explicitly including the customer value concept in the business model definition and focussing on value creation, (2 presenting four core dimensions that business model elements need to cover, (3 arguing for flexibility by adapting and extending business model elements to cater for different purposes and contexts (e.g. technology, innovation, strategy (4 stressing a more systematic approach to business model archetypes by using business model elements for their description, and (5 suggesting to use business model archetype research for the empirical exploration and testing of business model elements and their relationships.

  2. Statistical Models for Social Networks

    NARCIS (Netherlands)

    Snijders, Tom A. B.; Cook, KS; Massey, DS

    2011-01-01

    Statistical models for social networks as dependent variables must represent the typical network dependencies between tie variables such as reciprocity, homophily, transitivity, etc. This review first treats models for single (cross-sectionally observed) networks and then for network dynamics. For

  3. Can surgical simulation be used to train detection and classification of neural networks?

    Science.gov (United States)

    Zisimopoulos, Odysseas; Flouty, Evangello; Stacey, Mark; Muscroft, Sam; Giataganas, Petros; Nehme, Jean; Chow, Andre; Stoyanov, Danail

    2017-10-01

    Computer-assisted interventions (CAI) aim to increase the effectiveness, precision and repeatability of procedures to improve surgical outcomes. The presence and motion of surgical tools is a key information input for CAI surgical phase recognition algorithms. Vision-based tool detection and recognition approaches are an attractive solution and can be designed to take advantage of the powerful deep learning paradigm that is rapidly advancing image recognition and classification. The challenge for such algorithms is the availability and quality of labelled data used for training. In this Letter, surgical simulation is used to train tool detection and segmentation based on deep convolutional neural networks and generative adversarial networks. The authors experiment with two network architectures for image segmentation in tool classes commonly encountered during cataract surgery. A commercially-available simulator is used to create a simulated cataract dataset for training models prior to performing transfer learning on real surgical data. To the best of authors' knowledge, this is the first attempt to train deep learning models for surgical instrument detection on simulated data while demonstrating promising results to generalise on real data. Results indicate that simulated data does have some potential for training advanced classification methods for CAI systems.

  4. Joint Multi-scale Convolution Neural Network for Scene Classification of High Resolution Remote Sensing Imagery

    Directory of Open Access Journals (Sweden)

    ZHENG Zhuo

    2018-05-01

    Full Text Available High resolution remote sensing imagery scene classification is important for automatic complex scene recognition, which is the key technology for military and disaster relief, etc. In this paper, we propose a novel joint multi-scale convolution neural network (JMCNN method using a limited amount of image data for high resolution remote sensing imagery scene classification. Different from traditional convolutional neural network, the proposed JMCNN is an end-to-end training model with joint enhanced high-level feature representation, which includes multi-channel feature extractor, joint multi-scale feature fusion and Softmax classifier. Multi-channel and scale convolutional extractors are used to extract scene middle features, firstly. Then, in order to achieve enhanced high-level feature representation in a limit dataset, joint multi-scale feature fusion is proposed to combine multi-channel and scale features using two feature fusions. Finally, enhanced high-level feature representation can be used for classification by Softmax. Experiments were conducted using two limit public UCM and SIRI datasets. Compared to state-of-the-art methods, the JMCNN achieved improved performance and great robustness with average accuracies of 89.3% and 88.3% on the two datasets.

  5. Improving ECG classification accuracy using an ensemble of neural network modules.

    Directory of Open Access Journals (Sweden)

    Mehrdad Javadi

    Full Text Available This paper illustrates the use of a combined neural network model based on Stacked Generalization method for classification of electrocardiogram (ECG beats. In conventional Stacked Generalization method, the combiner learns to map the base classifiers' outputs to the target data. We claim adding the input pattern to the base classifiers' outputs helps the combiner to obtain knowledge about the input space and as the result, performs better on the same task. Experimental results support our claim that the additional knowledge according to the input space, improves the performance of the proposed method which is called Modified Stacked Generalization. In particular, for classification of 14966 ECG beats that were not previously seen during training phase, the Modified Stacked Generalization method reduced the error rate for 12.41% in comparison with the best of ten popular classifier fusion methods including Max, Min, Average, Product, Majority Voting, Borda Count, Decision Templates, Weighted Averaging based on Particle Swarm Optimization and Stacked Generalization.

  6. Classification of time-series images using deep convolutional neural networks

    Science.gov (United States)

    Hatami, Nima; Gavet, Yann; Debayle, Johan

    2018-04-01

    Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.

  7. Hybrid Model Based on Genetic Algorithms and SVM Applied to Variable Selection within Fruit Juice Classification

    Directory of Open Access Journals (Sweden)

    C. Fernandez-Lozano

    2013-01-01

    Full Text Available Given the background of the use of Neural Networks in problems of apple juice classification, this paper aim at implementing a newly developed method in the field of machine learning: the Support Vector Machines (SVM. Therefore, a hybrid model that combines genetic algorithms and support vector machines is suggested in such a way that, when using SVM as a fitness function of the Genetic Algorithm (GA, the most representative variables for a specific classification problem can be selected.

  8. Classification of mammographic masses using generalized dynamic fuzzy neural networks

    International Nuclear Information System (INIS)

    Lim, Wei Keat; Er, Meng Joo

    2004-01-01

    In this article, computer-aided classification of mammographic masses using generalized dynamic fuzzy neural networks (GDFNN) is presented. The texture parameters, derived from first-order gradient distribution and gray-level co-occurrence matrices, were computed from the regions of interest. A total of 343 images containing 180 benign masses and 163 malignant masses from the Digital Database for Screening Mammography were analyzed. A fast approach of automatically generating fuzzy rules from training samples was implemented to classify tumors. This work is novel in that it alleviates the problem of requiring a designer to examine all the input-output relationships of a training database in order to obtain the most appropriate structure for the classifier in a conventional computer-aided diagnosis. In this approach, not only the connection weights can be adjusted, but also the structure can be self-adaptive during the learning process. By virtue of the automatic generation of the classifier by the GDFNN learning algorithm, the area under the receiver-operating characteristic curve, A z , attains 0.868±0.020, which corresponds to a true-positive fraction of 95.0% at a false positive fraction of 52.8%. The corresponding accuracy is 70.0%, the positive predictive value is 62.0%, and the negative predictive value is 91.4%

  9. 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.

  10. NEURAL NETWORKS AS A CLASSIFICATION TOOL BIOTECHNOLOGICAL SYSTEMS (FOR EXAMPLE FLOUR PRODUCTION

    Directory of Open Access Journals (Sweden)

    V. K. Bitykov

    2015-01-01

    Full Text Available Summary. To date, artificial intelligence systems are the most common type to classify objects of different quality. The proposed modeling technology to predict the quality of flour products by using artificial neural networks allows to solve problems of analysis of the factors determining the quality of the products. Interest in artificial neural networks has grown due to the fact that they can change their behavior depending on external environment. This factor more than any other responsible for the interest that they cause. After the presentation of input signals (possibly together with the desired outputs, they self-configurable to provide the desired reaction. We developed a set of training algorithms, each with their own strengths and weaknesses. The solution to the problem of classification is one of the most important applications of neural networks, which represents a problem of attributing the sample to one of several non-intersecting sets. To solve this problem developed algorithms for synthesis of NA with the use of nonlinear activation functions, the algorithms for training the network. Training the NS involves determining the weights of layers of neurons. Training the NA occurs with the teacher, that is, the network must meet the values of both input and desired output signals, and it is according to some internal algorithm adjusts the weights of their synaptic connections. The work was built an artificial neural network, multilayer perceptron example. With the help of correlation analysis in total sample revealed that the traits are correlated at the significance level of 0.01 with grade quality bread. The classification accuracy exceeds 90%.

  11. Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification

    Directory of Open Access Journals (Sweden)

    Srdjan Sladojevic

    2016-01-01

    Full Text Available The latest generation of convolutional neural networks (CNNs has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodology used facilitate a quick and easy system implementation in practice. The developed model is able to recognize 13 different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our knowledge, this method for plant disease recognition has been proposed for the first time. All essential steps required for implementing this disease recognition model are fully described throughout the paper, starting from gathering images in order to create a database, assessed by agricultural experts. Caffe, a deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training. The experimental results on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%.

  12. Security Modeling on the Supply Chain Networks

    Directory of Open Access Journals (Sweden)

    Marn-Ling Shing

    2007-10-01

    Full Text Available In order to keep the price down, a purchaser sends out the request for quotation to a group of suppliers in a supply chain network. The purchaser will then choose a supplier with the best combination of price and quality. A potential supplier will try to collect the related information about other suppliers so he/she can offer the best bid to the purchaser. Therefore, confidentiality becomes an important consideration for the design of a supply chain network. Chen et al. have proposed the application of the Bell-LaPadula model in the design of a secured supply chain network. In the Bell-LaPadula model, a subject can be in one of different security clearances and an object can be in one of various security classifications. All the possible combinations of (Security Clearance, Classification pair in the Bell-LaPadula model can be thought as different states in the Markov Chain model. This paper extends the work done by Chen et al., provides more details on the Markov Chain model and illustrates how to use it to monitor the security state transition in the supply chain network.

  13. Hybrid Collaborative Learning for Classification and Clustering in Sensor Networks

    Science.gov (United States)

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

    2012-01-01

    Traditionally, nodes in a sensor network simply collect data and then pass it on to a centralized node that archives, distributes, and possibly analyzes the data. However, analysis at the individual nodes could enable faster detection of anomalies or other interesting events as well as faster responses, such as sending out alerts or increasing the data collection rate. There is an additional opportunity for increased performance if learners at individual nodes can communicate with their neighbors. In previous work, methods were developed by which classification algorithms deployed at sensor nodes can communicate information about event labels to each other, building on prior work with co-training, self-training, and active learning. The idea of collaborative learning was extended to function for clustering algorithms as well, similar to ideas from penta-training and consensus clustering. However, collaboration between these learner types had not been explored. A new protocol was developed by which classifiers and clusterers can share key information about their observations and conclusions as they learn. This is an active collaboration in which learners of either type can query their neighbors for information that they then use to re-train or re-learn the concept they are studying. The protocol also supports broadcasts from the classifiers and clusterers to the rest of the network to announce new discoveries. Classifiers observe an event and assign it a label (type). Clusterers instead group observations into clusters without assigning them a label, and they collaborate in terms of pairwise constraints between two events [same-cluster (mustlink) or different-cluster (cannot-link)]. Fundamentally, these two learner types speak different languages. To bridge this gap, the new communication protocol provides four types of exchanges: hybrid queries for information, hybrid "broadcasts" of learned information, each specified for classifiers-to-clusterers, and clusterers

  14. Neural Networks Technique, Lithofacies Classifications and Analysis and Depositional Environment Interpretation for 3-D Reservoir Geological Modeling and Exploration Studies (X Example)

    International Nuclear Information System (INIS)

    Iloghalu, E.; Chin, A.; Ebong, U.

    2003-01-01

    The value of borehole geology in Petroleum Exploration and Production cannot be over-emphasized. Reservoir characterization in mature fields and indeed mature basins requires high-resolution and high precision tools to determine the Stratigraphy and sedimentology of the areas of interest. The aim of reservoir studies is usually to determine the heterogeneity and the internal architecture of the reservoirs and the resulting model is simulated to derive the reservoir engineering properties, which impacts on quality decisions for optimal exploitation of the hydrocarbon in place. The point issues or challenges usually encountered in reservoir studies and management are baffles, barriers to flow, thief zones and other uncertainties that come about due to inadequate understanding of the sedimentology of the reservoirs in question. (Issues like preferential flow direction which significantly impact on secondary recovery and affect the costs). Recent advancements in borehole geology image and dips data helps to effectively itemize these uncertainties, and significantly reduce them to the barrest minimum. This work shows processed and interpreted image and dips data from a field, integrated with other petrophysical data and then incorporated into a field-wide study in the X-field. This was done using the most recent technological advancements in logging tools and in interpretation processes. The achievements include cost saving, higher precision results and reduced time or interpretation

  15. A recurrent neural network for classification of unevenly sampled variable stars

    Science.gov (United States)

    Naul, Brett; Bloom, Joshua S.; Pérez, Fernando; van der Walt, Stéfan

    2018-02-01

    Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time (`light curves'). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints1-5. With nightly observations of millions of variable stars and transients from upcoming surveys4,6, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference tasks on such data traditionally requires the laborious hand-coding of domain-specific numerical summaries of raw data (`features')7. Here, we present a novel unsupervised autoencoding recurrent neural network8 that makes explicit use of sampling times and known heteroskedastic noise properties. When trained on optical variable star catalogues, this network produces supervised classification models that rival other best-in-class approaches. We find that autoencoded features learned in one time-domain survey perform nearly as well when applied to another survey. These networks can continue to learn from new unlabelled observations and may be used in other unsupervised tasks, such as forecasting and anomaly detection.

  16. Quality Evaluation of Land-Cover Classification Using Convolutional Neural Network

    Science.gov (United States)

    Dang, Y.; Zhang, J.; Zhao, Y.; Luo, F.; Ma, W.; Yu, F.

    2018-04-01

    Land-cover classification is one of the most important products of earth observation, which focuses mainly on profiling the physical characters of the land surface with temporal and distribution attributes and contains the information of both natural and man-made coverage elements, such as vegetation, soil, glaciers, rivers, lakes, marsh wetlands and various man-made structures. In recent years, the amount of high-resolution remote sensing data has increased sharply. Accordingly, the volume of land-cover classification products increases, as well as the need to evaluate such frequently updated products that is a big challenge. Conventionally, the automatic quality evaluation of land-cover classification is made through pixel-based classifying algorithms, which lead to a much trickier task and consequently hard to keep peace with the required updating frequency. In this paper, we propose a novel quality evaluation approach for evaluating the land-cover classification by a scene classification method Convolutional Neural Network (CNN) model. By learning from remote sensing data, those randomly generated kernels that serve as filter matrixes evolved to some operators that has similar functions to man-crafted operators, like Sobel operator or Canny operator, and there are other kernels learned by the CNN model that are much more complex and can't be understood as existing filters. The method using CNN approach as the core algorithm serves quality-evaluation tasks well since it calculates a bunch of outputs which directly represent the image's membership grade to certain classes. An automatic quality evaluation approach for the land-cover DLG-DOM coupling data (DLG for Digital Line Graphic, DOM for Digital Orthophoto Map) will be introduced in this paper. The CNN model as an robustness method for image evaluation, then brought out the idea of an automatic quality evaluation approach for land-cover classification. Based on this experiment, new ideas of quality evaluation

  17. Algorithms for Hyperspectral Endmember Extraction and Signature Classification with Morphological Dendritic Networks

    Science.gov (United States)

    Schmalz, M.; Ritter, G.

    Accurate multispectral or hyperspectral signature classification is key to the nonimaging detection and recognition of space objects. Additionally, signature classification accuracy depends on accurate spectral endmember determination [1]. Previous approaches to endmember computation and signature classification were based on linear operators or neural networks (NNs) expressed in terms of the algebra (R, +, x) [1,2]. Unfortunately, class separation in these methods tends to be suboptimal, and the number of signatures that can be accurately classified often depends linearly on the number of NN inputs. This can lead to poor endmember distinction, as well as potentially significant classification errors in the presence of noise or densely interleaved signatures. In contrast to traditional CNNs, autoassociative morphological memories (AMM) are a construct similar to Hopfield autoassociatived memories defined on the (R, +, ?,?) lattice algebra [3]. Unlimited storage and perfect recall of noiseless real valued patterns has been proven for AMMs [4]. However, AMMs suffer from sensitivity to specific noise models, that can be characterized as erosive and dilative noise. On the other hand, the prior definition of a set of endmembers corresponds to material spectra lying on vertices of the minimum convex region covering the image data. These vertices can be characterized as morphologically independent patterns. It has further been shown that AMMs can be based on dendritic computation [3,6]. These techniques yield improved accuracy and class segmentation/separation ability in the presence of highly interleaved signature data. In this paper, we present a procedure for endmember determination based on AMM noise sensitivity, which employs morphological dendritic computation. We show that detected endmembers can be exploited by AMM based classification techniques, to achieve accurate signature classification in the presence of noise, closely spaced or interleaved signatures, and

  18. Bayesian network modelling of upper gastrointestinal bleeding

    Science.gov (United States)

    Aisha, Nazziwa; Shohaimi, Shamarina; Adam, Mohd Bakri

    2013-09-01

    Bayesian networks are graphical probabilistic models that represent causal and other relationships between domain variables. In the context of medical decision making, these models have been explored to help in medical diagnosis and prognosis. In this paper, we discuss the Bayesian network formalism in building medical support systems and we learn a tree augmented naive Bayes Network (TAN) from gastrointestinal bleeding data. The accuracy of the TAN in classifying the source of gastrointestinal bleeding into upper or lower source is obtained. The TAN achieves a high classification accuracy of 86% and an area under curve of 92%. A sensitivity analysis of the model shows relatively high levels of entropy reduction for color of the stool, history of gastrointestinal bleeding, consistency and the ratio of blood urea nitrogen to creatinine. The TAN facilitates the identification of the source of GIB and requires further validation.

  19. Coevolutionary modeling in network formation

    KAUST Repository

    Al-Shyoukh, Ibrahim

    2014-12-03

    Network coevolution, the process of network topology evolution in feedback with dynamical processes over the network nodes, is a common feature of many engineered and natural networks. In such settings, the change in network topology occurs at a comparable time scale to nodal dynamics. Coevolutionary modeling offers the possibility to better understand how and why network structures emerge. For example, social networks can exhibit a variety of structures, ranging from almost uniform to scale-free degree distributions. While current models of network formation can reproduce these structures, coevolutionary modeling can offer a better understanding of the underlying dynamics. This paper presents an overview of recent work on coevolutionary models of network formation, with an emphasis on the following three settings: (i) dynamic flow of benefits and costs, (ii) transient link establishment costs, and (iii) latent preferential attachment.

  20. Coevolutionary modeling in network formation

    KAUST Repository

    Al-Shyoukh, Ibrahim; Chasparis, Georgios; Shamma, Jeff S.

    2014-01-01

    Network coevolution, the process of network topology evolution in feedback with dynamical processes over the network nodes, is a common feature of many engineered and natural networks. In such settings, the change in network topology occurs at a comparable time scale to nodal dynamics. Coevolutionary modeling offers the possibility to better understand how and why network structures emerge. For example, social networks can exhibit a variety of structures, ranging from almost uniform to scale-free degree distributions. While current models of network formation can reproduce these structures, coevolutionary modeling can offer a better understanding of the underlying dynamics. This paper presents an overview of recent work on coevolutionary models of network formation, with an emphasis on the following three settings: (i) dynamic flow of benefits and costs, (ii) transient link establishment costs, and (iii) latent preferential attachment.

  1. A Novel Approach to ECG Classification Based upon Two-Layered HMMs in Body Sensor Networks

    Directory of Open Access Journals (Sweden)

    Wei Liang

    2014-03-01

    Full Text Available This paper presents a novel approach to ECG signal filtering and classification. Unlike the traditional techniques which aim at collecting and processing the ECG signals with the patient being still, lying in bed in hospitals, our proposed algorithm is intentionally designed for monitoring and classifying the patient’s ECG signals in the free-living environment. The patients are equipped with wearable ambulatory devices the whole day, which facilitates the real-time heart attack detection. In ECG preprocessing, an integral-coefficient-band-stop (ICBS filter is applied, which omits time-consuming floating-point computations. In addition, two-layered Hidden Markov Models (HMMs are applied to achieve ECG feature extraction and classification. The periodic ECG waveforms are segmented into ISO intervals, P subwave, QRS complex and T subwave respectively in the first HMM layer where expert-annotation assisted Baum-Welch algorithm is utilized in HMM modeling. Then the corresponding interval features are selected and applied to categorize the ECG into normal type or abnormal type (PVC, APC in the second HMM layer. For verifying the effectiveness of our algorithm on abnormal signal detection, we have developed an ECG body sensor network (BSN platform, whereby real-time ECG signals are collected, transmitted, displayed and the corresponding classification outcomes are deduced and shown on the BSN screen.

  2. A Novel Approach to ECG Classification Based upon Two-Layered HMMs in Body Sensor Networks

    Science.gov (United States)

    Liang, Wei; Zhang, Yinlong; Tan, Jindong; Li, Yang

    2014-01-01

    This paper presents a novel approach to ECG signal filtering and classification. Unlike the traditional techniques which aim at collecting and processing the ECG signals with the patient being still, lying in bed in hospitals, our proposed algorithm is intentionally designed for monitoring and classifying the patient's ECG signals in the free-living environment. The patients are equipped with wearable ambulatory devices the whole day, which facilitates the real-time heart attack detection. In ECG preprocessing, an integral-coefficient-band-stop (ICBS) filter is applied, which omits time-consuming floating-point computations. In addition, two-layered Hidden Markov Models (HMMs) are applied to achieve ECG feature extraction and classification. The periodic ECG waveforms are segmented into ISO intervals, P subwave, QRS complex and T subwave respectively in the first HMM layer where expert-annotation assisted Baum-Welch algorithm is utilized in HMM modeling. Then the corresponding interval features are selected and applied to categorize the ECG into normal type or abnormal type (PVC, APC) in the second HMM layer. For verifying the effectiveness of our algorithm on abnormal signal detection, we have developed an ECG body sensor network (BSN) platform, whereby real-time ECG signals are collected, transmitted, displayed and the corresponding classification outcomes are deduced and shown on the BSN screen. PMID:24681668

  3. Planning pesticides usage for herbal and animal pests based on intelligent classification system with image processing and neural networks

    Directory of Open Access Journals (Sweden)

    Dimililer Kamil

    2018-01-01

    Full Text Available Pests are divided into two as herbal and animal pests in agriculture, and detection and use of minimum pesticides are quite challenging task. Last three decades, researchers have been improving their studies on these manners. Therefore, effective, efficient, and as well as intelligent systems are designed and modelled. In this paper, an intelligent classification system is designed for detecting pests as herbal or animal to use of proper pesticides accordingly. The designed system suggests two main stages. Firstly, images are processed using different image processing techniques that images have specific distinguishing geometric patterns. The second stage is neural network phase for classification. A backpropagation neural network is used for training and testing with processed images. System is tested, and experiment results show efficiency and effective classification rate. Autonomy and time efficiency within the pesticide usage are also discussed.

  4. Seafloor classification using acoustic backscatter echo-waveform - Artificial neural network applications

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Mahale, V.; Navelkar, G.S.; Desai, R.G.P.

    In this paper seafloor classifications system based on artificial neural network (ANN) has been designed. The ANN architecture employed here is a combination of Self Organizing Feature Map (SOFM) and Linear Vector Quantization (LVQ1). Currently...

  5. Challenges to the Use of Artificial Neural Networks for Diagnostic Classifications with Student Test Data

    Science.gov (United States)

    Briggs, Derek C.; Circi, Ruhan

    2017-01-01

    Artificial Neural Networks (ANNs) have been proposed as a promising approach for the classification of students into different levels of a psychological attribute hierarchy. Unfortunately, because such classifications typically rely upon internally produced item response patterns that have not been externally validated, the instability of ANN…

  6. Computerized Classification Testing with the Rasch Model

    Science.gov (United States)

    Eggen, Theo J. H. M.

    2011-01-01

    If classification in a limited number of categories is the purpose of testing, computerized adaptive tests (CATs) with algorithms based on sequential statistical testing perform better than estimation-based CATs (e.g., Eggen & Straetmans, 2000). In these computerized classification tests (CCTs), the Sequential Probability Ratio Test (SPRT) (Wald,…

  7. Improved head direction command classification using an optimised Bayesian neural network.

    Science.gov (United States)

    Nguyen, Son T; Nguyen, Hung T; Taylor, Philip B; Middleton, James

    2006-01-01

    Assistive technologies have recently emerged to improve the quality of life of severely disabled people by enhancing their independence in daily activities. Since many of those individuals have limited or non-existing control from the neck downward, alternative hands-free input modalities have become very important for these people to access assistive devices. In hands-free control, head movement has been proved to be a very effective user interface as it can provide a comfortable, reliable and natural way to access the device. Recently, neural networks have been shown to be useful not only for real-time pattern recognition but also for creating user-adaptive models. Since multi-layer perceptron neural networks trained using standard back-propagation may cause poor generalisation, the Bayesian technique has been proposed to improve the generalisation and robustness of these networks. This paper describes the use of Bayesian neural networks in developing a hands-free wheelchair control system. The experimental results show that with the optimised architecture, classification Bayesian neural networks can detect head commands of wheelchair users accurately irrespective to their levels of injuries.

  8. Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network.

    Science.gov (United States)

    Zhang, Junming; Wu, Yan

    2018-03-28

    Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

  9. Classification of remotely sensed data using OCR-inspired neural network techniques. [Optical Character Recognition

    Science.gov (United States)

    Kiang, Richard K.

    1992-01-01

    Neural networks have been applied to classifications of remotely sensed data with some success. To improve the performance of this approach, an examination was made of how neural networks are applied to the optical character recognition (OCR) of handwritten digits and letters. A three-layer, feedforward network, along with techniques adopted from OCR, was used to classify Landsat-4 Thematic Mapper data. Good results were obtained. To overcome the difficulties that are characteristic of remote sensing applications and to attain significant improvements in classification accuracy, a special network architecture may be required.

  10. Energy-efficient algorithm for classification of states of wireless sensor network using machine learning methods

    Science.gov (United States)

    Yuldashev, M. N.; Vlasov, A. I.; Novikov, A. N.

    2018-05-01

    This paper focuses on the development of an energy-efficient algorithm for classification of states of a wireless sensor network using machine learning methods. The proposed algorithm reduces energy consumption by: 1) elimination of monitoring of parameters that do not affect the state of the sensor network, 2) reduction of communication sessions over the network (the data are transmitted only if their values can affect the state of the sensor network). The studies of the proposed algorithm have shown that at classification accuracy close to 100%, the number of communication sessions can be reduced by 80%.

  11. Twitter classification model: the ABC of two million fitness tweets.

    Science.gov (United States)

    Vickey, Theodore A; Ginis, Kathleen Martin; Dabrowski, Maciej

    2013-09-01

    The purpose of this project was to design and test data collection and management tools that can be used to study the use of mobile fitness applications and social networking within the context of physical activity. This project was conducted over a 6-month period and involved collecting publically shared Twitter data from five mobile fitness apps (Nike+, RunKeeper, MyFitnessPal, Endomondo, and dailymile). During that time, over 2.8 million tweets were collected, processed, and categorized using an online tweet collection application and a customized JavaScript. Using the grounded theory, a classification model was developed to categorize and understand the types of information being shared by application users. Our data show that by tracking mobile fitness app hashtags, a wealth of information can be gathered to include but not limited to daily use patterns, exercise frequency, location-based workouts, and overall workout sentiment.

  12. DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS

    Directory of Open Access Journals (Sweden)

    Y. B. Abdullin

    2017-01-01

    Full Text Available Sentiment analysis of short texts such as Twitter messages and comments in news portals is challenging due to the lack of contextual information. We propose a deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of languages. We apply our approach to two corpora of two different language pairs: English-Russian and Russian-Kazakh. We show how to train a classifier in one language and predict in another. Our approach achieves 73% accuracy for English and 74% accuracy for Russian. For Kazakh sentiment analysis, we propose a baseline method, that achieves 60% accuracy; and a method to learn bilingual embeddings from a large unlabeled corpus using a bilingual word pairs.

  13. Modeling online social signed networks

    Science.gov (United States)

    Li, Le; Gu, Ke; Zeng, An; Fan, Ying; Di, Zengru

    2018-04-01

    People's online rating behavior can be modeled by user-object bipartite networks directly. However, few works have been devoted to reveal the hidden relations between users, especially from the perspective of signed networks. We analyze the signed monopartite networks projected by the signed user-object bipartite networks, finding that the networks are highly clustered with obvious community structure. Interestingly, the positive clustering coefficient is remarkably higher than the negative clustering coefficient. Then, a Signed Growing Network model (SGN) based on local preferential attachment is proposed to generate a user's signed network that has community structure and high positive clustering coefficient. Other structural properties of the modeled networks are also found to be similar to the empirical networks.

  14. Histopathological Breast-Image Classification Using Local and Frequency Domains by Convolutional Neural Network

    Directory of Open Access Journals (Sweden)

    Abdullah-Al Nahid

    2018-01-01

    Full Text Available Identification of the malignancy of tissues from Histopathological images has always been an issue of concern to doctors and radiologists. This task is time-consuming, tedious and moreover very challenging. Success in finding malignancy from Histopathological images primarily depends on long-term experience, though sometimes experts disagree on their decisions. However, Computer Aided Diagnosis (CAD techniques help the radiologist to give a second opinion that can increase the reliability of the radiologist’s decision. Among the different image analysis techniques, classification of the images has always been a challenging task. Due to the intense complexity of biomedical images, it is always very challenging to provide a reliable decision about an image. The state-of-the-art Convolutional Neural Network (CNN technique has had great success in natural image classification. Utilizing advanced engineering techniques along with the CNN, in this paper, we have classified a set of Histopathological Breast-Cancer (BC images utilizing a state-of-the-art CNN model containing a residual block. Conventional CNN operation takes raw images as input and extracts the global features; however, the object oriented local features also contain significant information—for example, the Local Binary Pattern (LBP represents the effective textural information, Histogram represent the pixel strength distribution, Contourlet Transform (CT gives much detailed information about the smoothness about the edges, and Discrete Fourier Transform (DFT derives frequency-domain information from the image. Utilizing these advantages, along with our proposed novel CNN model, we have examined the performance of the novel CNN model as Histopathological image classifier. To do so, we have introduced five cases: (a Convolutional Neural Network Raw Image (CNN-I; (b Convolutional Neural Network CT Histogram (CNN-CH; (c Convolutional Neural Network CT LBP (CNN-CL; (d Convolutional

  15. A neighbourhood evolving network model

    International Nuclear Information System (INIS)

    Cao, Y.J.; Wang, G.Z.; Jiang, Q.Y.; Han, Z.X.

    2006-01-01

    Many social, technological, biological and economical systems are best described by evolved network models. In this short Letter, we propose and study a new evolving network model. The model is based on the new concept of neighbourhood connectivity, which exists in many physical complex networks. The statistical properties and dynamics of the proposed model is analytically studied and compared with those of Barabasi-Albert scale-free model. Numerical simulations indicate that this network model yields a transition between power-law and exponential scaling, while the Barabasi-Albert scale-free model is only one of its special (limiting) cases. Particularly, this model can be used to enhance the evolving mechanism of complex networks in the real world, such as some social networks development

  16. Classification of Land Cover and Land Use Based on Convolutional Neural Networks

    Science.gov (United States)

    Yang, Chun; Rottensteiner, Franz; Heipke, Christian

    2018-04-01

    Land cover describes the physical material of the earth's surface, whereas land use describes the socio-economic function of a piece of land. Land use information is typically collected in geospatial databases. As such databases become outdated quickly, an automatic update process is required. This paper presents a new approach to determine land cover and to classify land use objects based on convolutional neural networks (CNN). The input data are aerial images and derived data such as digital surface models. Firstly, we apply a CNN to determine the land cover for each pixel of the input image. We compare different CNN structures, all of them based on an encoder-decoder structure for obtaining dense class predictions. Secondly, we propose a new CNN-based methodology for the prediction of the land use label of objects from a geospatial database. In this context, we present a strategy for generating image patches of identical size from the input data, which are classified by a CNN. Again, we compare different CNN architectures. Our experiments show that an overall accuracy of up to 85.7 % and 77.4 % can be achieved for land cover and land use, respectively. The classification of land cover has a positive contribution to the classification of the land use classification.

  17. Inter Genre Similarity Modelling For Automatic Music Genre Classification

    OpenAIRE

    Bagci, Ulas; Erzin, Engin

    2009-01-01

    Music genre classification is an essential tool for music information retrieval systems and it has been finding critical applications in various media platforms. Two important problems of the automatic music genre classification are feature extraction and classifier design. This paper investigates inter-genre similarity modelling (IGS) to improve the performance of automatic music genre classification. Inter-genre similarity information is extracted over the mis-classified feature population....

  18. EEG classification of emotions using emotion-specific brain functional network.

    Science.gov (United States)

    Gonuguntla, V; Shafiq, G; Wang, Y; Veluvolu, K C

    2015-08-01

    The brain functional network perspective forms the basis to relate mechanisms of brain functions. This work analyzes the network mechanisms related to human emotion based on synchronization measure - phase-locking value in EEG to formulate the emotion specific brain functional network. Based on network dissimilarities between emotion and rest tasks, most reactive channel pairs and the reactive band corresponding to emotions are identified. With the identified most reactive pairs, the subject-specific functional network is formed. The identified subject-specific and emotion-specific dynamic network pattern show significant synchrony variation in line with the experiment protocol. The same network pattern are then employed for classification of emotions. With the study conducted on the 4 subjects, an average classification accuracy of 62 % was obtained with the proposed technique.

  19. CLASSIFICATION OF ENTREPRENEURIAL INTENTIONS BY NEURAL NETWORKS, DECISION TREES AND SUPPORT VECTOR MACHINES

    Directory of Open Access Journals (Sweden)

    Marijana Zekić-Sušac

    2010-12-01

    Full Text Available Entrepreneurial intentions of students are important to recognize during the study in order to provide those students with educational background that will support such intentions and lead them to successful entrepreneurship after the study. The paper aims to develop a model that will classify students according to their entrepreneurial intentions by benchmarking three machine learning classifiers: neural networks, decision trees, and support vector machines. A survey was conducted at a Croatian university including a sample of students at the first year of study. Input variables described students’ demographics, importance of business objectives, perception of entrepreneurial carrier, and entrepreneurial predispositions. Due to a large dimension of input space, a feature selection method was used in the pre-processing stage. For comparison reasons, all tested models were validated on the same out-of-sample dataset, and a cross-validation procedure for testing generalization ability of the models was conducted. The models were compared according to its classification accuracy, as well according to input variable importance. The results show that although the best neural network model produced the highest average hit rate, the difference in performance is not statistically significant. All three models also extract similar set of features relevant for classifying students, which can be suggested to be taken into consideration by universities while designing their academic programs.

  20. Adaptive Naive Bayes classification for wireless sensor networks

    NARCIS (Netherlands)

    Zwartjes, G.J.

    2017-01-01

    Wireless Sensor Networks are tiny devices equipped with sensors and wireless communication. These devices observe environments and communicatie about these observations. Machine Learning techniques are of interest for Wireless Sensor Network applications since they can reduce the amount of needed

  1. Analysis and Classification of Traffic in Wireless Sensor Network

    National Research Council Canada - National Science Library

    Beng, Wang W

    2007-01-01

    .... Specifically, this thesis studied the traffic generated by wireless sensor networks by setting up two different commonly used network topologies, namely a direct connection to the base and a daisy...

  2. The Performance of EEG-P300 Classification using Backpropagation Neural Networks

    Directory of Open Access Journals (Sweden)

    Arjon Turnip

    2013-12-01

    Full Text Available Electroencephalogram (EEG recordings signal provide an important function of brain-computer communication, but the accuracy of their classification is very limited in unforeseeable signal variations relating to artifacts. In this paper, we propose a classification method entailing time-series EEG-P300 signals using backpropagation neural networks to predict the qualitative properties of a subject’s mental tasks by extracting useful information from the highly multivariate non-invasive recordings of brain activity. To test the improvement in the EEG-P300 classification performance (i.e., classification accuracy and transfer rate with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis (BLDA. Finally, the result of the experiment showed that the average of the classification accuracy was 97% and the maximum improvement of the average transfer rate is 42.4%, indicating the considerable potential of the using of EEG-P300 for the continuous classification of mental tasks.

  3. Study on the forward-feed neural network used for the classification of high energy particles

    International Nuclear Information System (INIS)

    Luo Guangxuan; Dai Guiliang

    1997-01-01

    Neural network has been applied in the field of high energy physics experiment for the classification of particles and gained good results. The author emphasizes the systematic analysis of the fundamental principle of the forward-feed neural network and discusses the problems and solving methods in application

  4. A joint classification method to integrate scientific and social networks

    NARCIS (Netherlands)

    Neshati, Mahmood; Asgari, Ehsaneddin; Hiemstra, Djoerd; Beigy, Hamid

    In this paper, we address the problem of scientific-social network integration to find a matching relationship between members of these networks. Utilizing several name similarity patterns and contextual properties of these networks, we design a focused crawler to find high probable matching pairs,

  5. Calibration of a Plastic Classification System with the Ccw Model

    International Nuclear Information System (INIS)

    Barcala Riveira, J. M.; Fernandez Marron, J. L.; Alberdi Primicia, J.; Navarrete Marin, J. J.; Oller Gonzalez, J. C.

    2003-01-01

    This document describes the calibration of a plastic Classification system with the Ccw model (Classification by Quantum's built with Wavelet Coefficients). The method is applied to spectra of plastics usually present in domestic wastes. Obtained results are showed. (Author) 16 refs

  6. Wearable-Sensor-Based Classification Models of Faller Status in Older Adults.

    Directory of Open Access Journals (Sweden)

    Jennifer Howcroft

    Full Text Available Wearable sensors have potential for quantitative, gait-based, point-of-care fall risk assessment that can be easily and quickly implemented in clinical-care and older-adult living environments. This investigation generated models for wearable-sensor based fall-risk classification in older adults and identified the optimal sensor type, location, combination, and modelling method; for walking with and without a cognitive load task. A convenience sample of 100 older individuals (75.5 ± 6.7 years; 76 non-fallers, 24 fallers based on 6 month retrospective fall occurrence walked 7.62 m under single-task and dual-task conditions while wearing pressure-sensing insoles and tri-axial accelerometers at the head, pelvis, and left and right shanks. Participants also completed the Activities-specific Balance Confidence scale, Community Health Activities Model Program for Seniors questionnaire, six minute walk test, and ranked their fear of falling. Fall risk classification models were assessed for all sensor combinations and three model types: multi-layer perceptron neural network, naïve Bayesian, and support vector machine. The best performing model was a multi-layer perceptron neural network with input parameters from pressure-sensing insoles and head, pelvis, and left shank accelerometers (accuracy = 84%, F1 score = 0.600, MCC score = 0.521. Head sensor-based models had the best performance of the single-sensor models for single-task gait assessment. Single-task gait assessment models outperformed models based on dual-task walking or clinical assessment data. Support vector machines and neural networks were the best modelling technique for fall risk classification. Fall risk classification models developed for point-of-care environments should be developed using support vector machines and neural networks, with a multi-sensor single-task gait assessment.

  7. STUDY ON THE CLASSIFICATION OF GAOFEN-3 POLARIMETRIC SAR IMAGES USING DEEP NEURAL NETWORK

    Directory of Open Access Journals (Sweden)

    J. Zhang

    2018-04-01

    Full Text Available Polarimetric Synthetic Aperture Radar(POLSAR) imaging principle determines that the image quality will be affected by speckle noise. So the recognition accuracy of traditional image classification methods will be reduced by the effect of this interference. Since the date of submission, Deep Convolutional Neural Network impacts on the traditional image processing methods and brings the field of computer vision to a new stage with the advantages of a strong ability to learn deep features and excellent ability to fit large datasets. Based on the basic characteristics of polarimetric SAR images, the paper studied the types of the surface cover by using the method of Deep Learning. We used the fully polarimetric SAR features of different scales to fuse RGB images to the GoogLeNet model based on convolution neural network Iterative training, and then use the trained model to test the classification of data validation.First of all, referring to the optical image, we mark the surface coverage type of GF-3 POLSAR image with 8m resolution, and then collect the samples according to different categories. To meet the GoogLeNet model requirements of 256 × 256 pixel image input and taking into account the lack of full-resolution SAR resolution, the original image should be pre-processed in the process of resampling. In this paper, POLSAR image slice samples of different scales with sampling intervals of 2 m and 1 m to be trained separately and validated by the verification dataset. Among them, the training accuracy of GoogLeNet model trained with resampled 2-m polarimetric SAR image is 94.89 %, and that of the trained SAR image with resampled 1 m is 92.65 %.

  8. Study on the Classification of GAOFEN-3 Polarimetric SAR Images Using Deep Neural Network

    Science.gov (United States)

    Zhang, J.; Zhang, J.; Zhao, Z.

    2018-04-01

    Polarimetric Synthetic Aperture Radar (POLSAR) imaging principle determines that the image quality will be affected by speckle noise. So the recognition accuracy of traditional image classification methods will be reduced by the effect of this interference. Since the date of submission, Deep Convolutional Neural Network impacts on the traditional image processing methods and brings the field of computer vision to a new stage with the advantages of a strong ability to learn deep features and excellent ability to fit large datasets. Based on the basic characteristics of polarimetric SAR images, the paper studied the types of the surface cover by using the method of Deep Learning. We used the fully polarimetric SAR features of different scales to fuse RGB images to the GoogLeNet model based on convolution neural network Iterative training, and then use the trained model to test the classification of data validation.First of all, referring to the optical image, we mark the surface coverage type of GF-3 POLSAR image with 8m resolution, and then collect the samples according to different categories. To meet the GoogLeNet model requirements of 256 × 256 pixel image input and taking into account the lack of full-resolution SAR resolution, the original image should be pre-processed in the process of resampling. In this paper, POLSAR image slice samples of different scales with sampling intervals of 2 m and 1 m to be trained separately and validated by the verification dataset. Among them, the training accuracy of GoogLeNet model trained with resampled 2-m polarimetric SAR image is 94.89 %, and that of the trained SAR image with resampled 1 m is 92.65 %.

  9. Organizational information assets classification model and security architecture methodology

    Directory of Open Access Journals (Sweden)

    Mostafa Tamtaji

    2015-12-01

    Full Text Available Today's, Organizations are exposed with huge and diversity of information and information assets that are produced in different systems shuch as KMS, financial and accounting systems, official and industrial automation sysytems and so on and protection of these information is necessary. Cloud computing is a model for enabling ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources that can be rapidly provisioned and released.several benefits of this model cuses that organization has a great trend to implementing Cloud computing. Maintaining and management of information security is the main challenges in developing and accepting of this model. In this paper, at first, according to "design science research methodology" and compatible with "design process at information systems research", a complete categorization of organizational assets, including 355 different types of information assets in 7 groups and 3 level, is presented to managers be able to plan corresponding security controls according to importance of each groups. Then, for directing of organization to architect it’s information security in cloud computing environment, appropriate methodology is presented. Presented cloud computing security architecture , resulted proposed methodology, and presented classification model according to Delphi method and expers comments discussed and verified.

  10. Agile convolutional neural network for pulmonary nodule classification using CT images.

    Science.gov (United States)

    Zhao, Xinzhuo; Liu, Liyao; Qi, Shouliang; Teng, Yueyang; Li, Jianhua; Qian, Wei

    2018-04-01

    To distinguish benign from malignant pulmonary nodules using CT images is critical for their precise diagnosis and treatment. A new Agile convolutional neural network (CNN) framework is proposed to conquer the challenges of a small-scale medical image database and the small size of the nodules, and it improves the performance of pulmonary nodule classification using CT images. A hybrid CNN of LeNet and AlexNet is constructed through combining the layer settings of LeNet and the parameter settings of AlexNet. A dataset with 743 CT image nodule samples is built up based on the 1018 CT scans of LIDC to train and evaluate the Agile CNN model. Through adjusting the parameters of the kernel size, learning rate, and other factors, the effect of these parameters on the performance of the CNN model is investigated, and an optimized setting of the CNN is obtained finally. After finely optimizing the settings of the CNN, the estimation accuracy and the area under the curve can reach 0.822 and 0.877, respectively. The accuracy of the CNN is significantly dependent on the kernel size, learning rate, training batch size, dropout, and weight initializations. The best performance is achieved when the kernel size is set to [Formula: see text], the learning rate is 0.005, the batch size is 32, and dropout and Gaussian initialization are used. This competitive performance demonstrates that our proposed CNN framework and the optimization strategy of the CNN parameters are suitable for pulmonary nodule classification characterized by small medical datasets and small targets. The classification model might help diagnose and treat pulmonary nodules effectively.

  11. PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications

    OpenAIRE

    Pasquier, Claude; Promponas, Vasilis; Hamodrakas, Stavros

    2009-01-01

    International audience; A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the av...

  12. Multi-agent Negotiation Mechanisms for Statistical Target Classification in Wireless Multimedia Sensor Networks

    Science.gov (United States)

    Wang, Xue; Bi, Dao-wei; Ding, Liang; Wang, Sheng

    2007-01-01

    The recent availability of low cost and miniaturized hardware has allowed wireless sensor networks (WSNs) to retrieve audio and video data in real world applications, which has fostered the development of wireless multimedia sensor networks (WMSNs). Resource constraints and challenging multimedia data volume make development of efficient algorithms to perform in-network processing of multimedia contents imperative. This paper proposes solving problems in the domain of WMSNs from the perspective of multi-agent systems. The multi-agent framework enables flexible network configuration and efficient collaborative in-network processing. The focus is placed on target classification in WMSNs where audio information is retrieved by microphones. To deal with the uncertainties related to audio information retrieval, the statistical approaches of power spectral density estimates, principal component analysis and Gaussian process classification are employed. A multi-agent negotiation mechanism is specially developed to efficiently utilize limited resources and simultaneously enhance classification accuracy and reliability. The negotiation is composed of two phases, where an auction based approach is first exploited to allocate the classification task among the agents and then individual agent decisions are combined by the committee decision mechanism. Simulation experiments with real world data are conducted and the results show that the proposed statistical approaches and negotiation mechanism not only reduce memory and computation requirements in WMSNs but also significantly enhance classification accuracy and reliability. PMID:28903223

  13. Modularization of biochemical networks based on classification of Petri net t-invariants.

    Science.gov (United States)

    Grafahrend-Belau, Eva; Schreiber, Falk; Heiner, Monika; Sackmann, Andrea; Junker, Björn H; Grunwald, Stefanie; Speer, Astrid; Winder, Katja; Koch, Ina

    2008-02-08

    Structural analysis of biochemical networks is a growing field in bioinformatics and systems biology. The availability of an increasing amount of biological data from molecular biological networks promises a deeper understanding but confronts researchers with the problem of combinatorial explosion. The amount of qualitative network data is growing much faster than the amount of quantitative data, such as enzyme kinetics. In many cases it is even impossible to measure quantitative data because of limitations of experimental methods, or for ethical reasons. Thus, a huge amount of qualitative data, such as interaction data, is available, but it was not sufficiently used for modeling purposes, until now. New approaches have been developed, but the complexity of data often limits the application of many of the methods. Biochemical Petri nets make it possible to explore static and dynamic qualitative system properties. One Petri net approach is model validation based on the computation of the system's invariant properties, focusing on t-invariants. T-invariants correspond to subnetworks, which describe the basic system behavior.With increasing system complexity, the basic behavior can only be expressed by a huge number of t-invariants. According to our validation criteria for biochemical Petri nets, the necessary verification of the biological meaning, by interpreting each subnetwork (t-invariant) manually, is not possible anymore. Thus, an automated, biologically meaningful classification would be helpful in analyzing t-invariants, and supporting the understanding of the basic behavior of the considered biological system. Here, we introduce a new approach to automatically classify t-invariants to cope with network complexity. We apply clustering techniques such as UPGMA, Complete Linkage, Single Linkage, and Neighbor Joining in combination with different distance measures to get biologically meaningful clusters (t-clusters), which can be interpreted as modules. To find

  14. Modularization of biochemical networks based on classification of Petri net t-invariants

    Directory of Open Access Journals (Sweden)

    Grunwald Stefanie

    2008-02-01

    Full Text Available Abstract Background Structural analysis of biochemical networks is a growing field in bioinformatics and systems biology. The availability of an increasing amount of biological data from molecular biological networks promises a deeper understanding but confronts researchers with the problem of combinatorial explosion. The amount of qualitative network data is growing much faster than the amount of quantitative data, such as enzyme kinetics. In many cases it is even impossible to measure quantitative data because of limitations of experimental methods, or for ethical reasons. Thus, a huge amount of qualitative data, such as interaction data, is available, but it was not sufficiently used for modeling purposes, until now. New approaches have been developed, but the complexity of data often limits the application of many of the methods. Biochemical Petri nets make it possible to explore static and dynamic qualitative system properties. One Petri net approach is model validation based on the computation of the system's invariant properties, focusing on t-invariants. T-invariants correspond to subnetworks, which describe the basic system behavior. With increasing system complexity, the basic behavior can only be expressed by a huge number of t-invariants. According to our validation criteria for biochemical Petri nets, the necessary verification of the biological meaning, by interpreting each subnetwork (t-invariant manually, is not possible anymore. Thus, an automated, biologically meaningful classification would be helpful in analyzing t-invariants, and supporting the understanding of the basic behavior of the considered biological system. Methods Here, we introduce a new approach to automatically classify t-invariants to cope with network complexity. We apply clustering techniques such as UPGMA, Complete Linkage, Single Linkage, and Neighbor Joining in combination with different distance measures to get biologically meaningful clusters (t

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

    KAUST Repository

    Aljaafari, Nura

    2018-01-01

    . This method is time-consuming and requires a high level of experience. The recent advances in AI have helped to solve and automate several difficult tasks which motivated us to develop a classification tool for ichthyoplankton. We show that using machine

  16. Classification

    Science.gov (United States)

    Clary, Renee; Wandersee, James

    2013-01-01

    In this article, Renee Clary and James Wandersee describe the beginnings of "Classification," which lies at the very heart of science and depends upon pattern recognition. Clary and Wandersee approach patterns by first telling the story of the "Linnaean classification system," introduced by Carl Linnacus (1707-1778), who is…

  17. 3D multi-view convolutional neural networks for lung nodule classification

    Science.gov (United States)

    Kang, Guixia; Hou, Beibei; Zhang, Ningbo

    2017-01-01

    The 3D convolutional neural network (CNN) is able to make full use of the spatial 3D context information of lung nodules, and the multi-view strategy has been shown to be useful for improving the performance of 2D CNN in classifying lung nodules. In this paper, we explore the classification of lung nodules using the 3D multi-view convolutional neural networks (MV-CNN) with both chain architecture and directed acyclic graph architecture, including 3D Inception and 3D Inception-ResNet. All networks employ the multi-view-one-network strategy. We conduct a binary classification (benign and malignant) and a ternary classification (benign, primary malignant and metastatic malignant) on Computed Tomography (CT) images from Lung Image Database Consortium and Image Database Resource Initiative database (LIDC-IDRI). All results are obtained via 10-fold cross validation. As regards the MV-CNN with chain architecture, results show that the performance of 3D MV-CNN surpasses that of 2D MV-CNN by a significant margin. Finally, a 3D Inception network achieved an error rate of 4.59% for the binary classification and 7.70% for the ternary classification, both of which represent superior results for the corresponding task. We compare the multi-view-one-network strategy with the one-view-one-network strategy. The results reveal that the multi-view-one-network strategy can achieve a lower error rate than the one-view-one-network strategy. PMID:29145492

  18. Classification rates: non‐parametric verses parametric models using ...

    African Journals Online (AJOL)

    This research sought to establish if non parametric modeling achieves a higher correct classification ratio than a parametric model. The local likelihood technique was used to model fit the data sets. The same sets of data were modeled using parametric logit and the abilities of the two models to correctly predict the binary ...

  19. Classification of Exacerbation Frequency in the COPDGene Cohort Using Deep Learning with Deep Belief Networks.

    Science.gov (United States)

    Ying, Jun; Dutta, Joyita; Guo, Ning; Hu, Chenhui; Zhou, Dan; Sitek, Arkadiusz; Li, Quanzheng

    2016-12-21

    This study aims to develop an automatic classifier based on deep learning for exacerbation frequency in patients with chronic obstructive pulmonary disease (COPD). A threelayer deep belief network (DBN) with two hidden layers and one visible layer was employed to develop classification models and the models' robustness to exacerbation was analyzed. Subjects from the COPDGene cohort were labeled with exacerbation frequency, defined as the number of exacerbation events per year. 10,300 subjects with 361 features each were included in the analysis. After feature selection and parameter optimization, the proposed classification method achieved an accuracy of 91.99%, using a 10-fold cross validation experiment. The analysis of DBN weights showed that there was a good visual spatial relationship between the underlying critical features of different layers. Our findings show that the most sensitive features obtained from the DBN weights are consistent with the consensus showed by clinical rules and standards for COPD diagnostics. We thus demonstrate that DBN is a competitive tool for exacerbation risk assessment for patients suffering from COPD.

  20. Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks.

    Science.gov (United States)

    Wu, Miao; Yan, Chuanbo; Liu, Huiqiang; Liu, Qian

    2018-06-29

    Ovarian cancer is one of the most common gynecologic malignancies. Accurate classification of ovarian cancer types (serous carcinoma, mucous carcinoma, endometrioid carcinoma, transparent cell carcinoma) is an essential part in the different diagnosis. Computer-aided diagnosis (CADx) can provide useful advice for pathologists to determine the diagnosis correctly. In our study, we employed a Deep Convolutional Neural Networks (DCNN) based on AlexNet to automatically classify the different types of ovarian cancers from cytological images. The DCNN consists of five convolutional layers, three max pooling layers, and two full reconnect layers. Then we trained the model by two group input data separately, one was original image data and the other one was augmented image data including image enhancement and image rotation. The testing results are obtained by the method of 10-fold cross-validation, showing that the accuracy of classification models has been improved from 72.76 to 78.20% by using augmented images as training data. The developed scheme was useful for classifying ovarian cancers from cytological images. © 2018 The Author(s).

  1. Clustering-based classification of road traffic accidents using hierarchical clustering and artificial neural networks.

    Science.gov (United States)

    Taamneh, Madhar; Taamneh, Salah; Alkheder, Sharaf

    2017-09-01

    Artificial neural networks (ANNs) have been widely used in predicting the severity of road traffic crashes. All available information about previously occurred accidents is typically used for building a single prediction model (i.e., classifier). Too little attention has been paid to the differences between these accidents, leading, in most cases, to build less accurate predictors. Hierarchical clustering is a well-known clustering method that seeks to group data by creating a hierarchy of clusters. Using hierarchical clustering and ANNs, a clustering-based classification approach for predicting the injury severity of road traffic accidents was proposed. About 6000 road accidents occurred over a six-year period from 2008 to 2013 in Abu Dhabi were used throughout this study. In order to reduce the amount of variation in data, hierarchical clustering was applied on the data set to organize it into six different forms, each with different number of clusters (i.e., clusters from 1 to 6). Two ANN models were subsequently built for each cluster of accidents in each generated form. The first model was built and validated using all accidents (training set), whereas only 66% of the accidents were used to build the second model, and the remaining 34% were used to test it (percentage split). Finally, the weighted average accuracy was computed for each type of models in each from of data. The results show that when testing the models using the training set, clustering prior to classification achieves (11%-16%) more accuracy than without using clustering, while the percentage split achieves (2%-5%) more accuracy. The results also suggest that partitioning the accidents into six clusters achieves the best accuracy if both types of models are taken into account.

  2. Developing Personal Network Business Models

    DEFF Research Database (Denmark)

    Saugstrup, Dan; Henten, Anders

    2006-01-01

    The aim of the paper is to examine the issue of business modeling in relation to personal networks, PNs. The paper builds on research performed on business models in the EU 1ST MAGNET1 project (My personal Adaptive Global NET). The paper presents the Personal Network concept and briefly reports...

  3. Plant species classification using deep convolutional neural network

    DEFF Research Database (Denmark)

    Dyrmann, Mads; Karstoft, Henrik; Midtiby, Henrik Skov

    2016-01-01

    Information on which weed species are present within agricultural fields is important for site specific weed management. This paper presents a method that is capable of recognising plant species in colour images by using a convolutional neural network. The network is built from scratch trained an...

  4. Classification framework of knowledge transfer issues across value networks

    NARCIS (Netherlands)

    Bagheri, S.; Kusters, R.J.; Trienekens, J.J.M.; van der Zandt, Hugo; Cavalieri, S.; Ceretti, E.; Tolio, T.; Pezzotta, G.

    2016-01-01

    Co-creating integrated solutions with customers requires collaboration of different partners within a value network. In this emerging context, knowledge is considered as a foundation for value co-creation. Therefore, identifying different types of issues, with which value network actors in knowledge

  5. Learning classification models with soft-label information.

    Science.gov (United States)

    Nguyen, Quang; Valizadegan, Hamed; Hauskrecht, Milos

    2014-01-01

    Learning of classification models in medicine often relies on data labeled by a human expert. Since labeling of clinical data may be time-consuming, finding ways of alleviating the labeling costs is critical for our ability to automatically learn such models. In this paper we propose a new machine learning approach that is able to learn improved binary classification models more efficiently by refining the binary class information in the training phase with soft labels that reflect how strongly the human expert feels about the original class labels. Two types of methods that can learn improved binary classification models from soft labels are proposed. The first relies on probabilistic/numeric labels, the other on ordinal categorical labels. We study and demonstrate the benefits of these methods for learning an alerting model for heparin induced thrombocytopenia. The experiments are conducted on the data of 377 patient instances labeled by three different human experts. The methods are compared using the area under the receiver operating characteristic curve (AUC) score. Our AUC results show that the new approach is capable of learning classification models more efficiently compared to traditional learning methods. The improvement in AUC is most remarkable when the number of examples we learn from is small. A new classification learning framework that lets us learn from auxiliary soft-label information provided by a human expert is a promising new direction for learning classification models from expert labels, reducing the time and cost needed to label data.

  6. Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks

    OpenAIRE

    Khalifa, Nour Eldeen M.; Taha, Mohamed Hamed N.; Hassanien, Aboul Ella; Selim, I. M.

    2017-01-01

    In this paper, a deep convolutional neural network architecture for galaxies classification is presented. The galaxy can be classified based on its features into main three categories Elliptical, Spiral, and Irregular. The proposed deep galaxies architecture consists of 8 layers, one main convolutional layer for features extraction with 96 filters, followed by two principles fully connected layers for classification. It is trained over 1356 images and achieved 97.272% in testing accuracy. A c...

  7. Seafloor classification using echo- waveforms: A method employing hybrid neural network architecture

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Mahale, V.; DeSouza, C.; Das, P.

    , neural network architecture, seafloor classification, self-organizing feature map (SOFM). I. INTRODUCTION S EAFLOOR classification and characterization using re- mote high-frequency acoustic system has been recognized as a useful tool (see [1...] and references therein). The seafloor’s characteristics are extremely complicated due to variations of the many parameters at different scales. The parameters include sediment grain size, relief height at the water–sediment inter- face, and variations within...

  8. Mathematical Modelling Plant Signalling Networks

    KAUST Repository

    Muraro, D.; Byrne, H.M.; King, J.R.; Bennett, M.J.

    2013-01-01

    methods for modelling gene and signalling networks and their application in plants. We then describe specific models of hormonal perception and cross-talk in plants. This mathematical analysis of sub-cellular molecular mechanisms paves the way for more

  9. Automatic Classification of volcano-seismic events based on Deep Neural Networks.

    Science.gov (United States)

    Titos Luzón, M.; Bueno Rodriguez, A.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

    2017-12-01

    Seismic monitoring of active volcanoes is a popular remote sensing technique to detect seismic activity, often associated to energy exchanges between the volcano and the environment. As a result, seismographs register a wide range of volcano-seismic signals that reflect the nature and underlying physics of volcanic processes. Machine learning and signal processing techniques provide an appropriate framework to analyze such data. In this research, we propose a new classification framework for seismic events based on deep neural networks. Deep neural networks are composed by multiple processing layers, and can discover intrinsic patterns from the data itself. Internal parameters can be initialized using a greedy unsupervised pre-training stage, leading to an efficient training of fully connected architectures. We aim to determine the robustness of these architectures as classifiers of seven different types of seismic events recorded at "Volcán de Fuego" (Colima, Mexico). Two deep neural networks with different pre-training strategies are studied: stacked denoising autoencoder and deep belief networks. Results are compared to existing machine learning algorithms (SVM, Random Forest, Multilayer Perceptron). We used 5 LPC coefficients over three non-overlapping segments as training features in order to characterize temporal evolution, avoid redundancy and encode the signal, regardless of its duration. Experimental results show that deep architectures can classify seismic events with higher accuracy than classical algorithms, attaining up to 92% recognition accuracy. Pre-training initialization helps these models to detect events that occur simultaneously in time (such explosions and rockfalls), increase robustness against noisy inputs, and provide better generalization. These results demonstrate deep neural networks are robust classifiers, and can be deployed in real-environments to monitor the seismicity of restless volcanoes.

  10. Fault detection and classification in electrical power transmission system using artificial neural network.

    Science.gov (United States)

    Jamil, Majid; Sharma, Sanjeev Kumar; Singh, Rajveer

    2015-01-01

    This paper focuses on the detection and classification of the faults on electrical power transmission line using artificial neural networks. The three phase currents and voltages of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. A detailed analysis with varying number of hidden layers has been performed to validate the choice of the neural network. The simulation results concluded that the present method based on the neural network is efficient in detecting and classifying the faults on transmission lines with satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The proposed method can be extended to the Distribution network of the Power System. The various simulations and analysis of signals is done in the MATLAB(®) environment.

  11. Complex Networks in Psychological Models

    Science.gov (United States)

    Wedemann, R. S.; Carvalho, L. S. A. V. D.; Donangelo, R.

    We develop schematic, self-organizing, neural-network models to describe mechanisms associated with mental processes, by a neurocomputational substrate. These models are examples of real world complex networks with interesting general topological structures. Considering dopaminergic signal-to-noise neuronal modulation in the central nervous system, we propose neural network models to explain development of cortical map structure and dynamics of memory access, and unify different mental processes into a single neurocomputational substrate. Based on our neural network models, neurotic behavior may be understood as an associative memory process in the brain, and the linguistic, symbolic associative process involved in psychoanalytic working-through can be mapped onto a corresponding process of reconfiguration of the neural network. The models are illustrated through computer simulations, where we varied dopaminergic modulation and observed the self-organizing emergent patterns at the resulting semantic map, interpreting them as different manifestations of mental functioning, from psychotic through to normal and neurotic behavior, and creativity.

  12. Classification of a Driver's cognitive workload levels using artificial neural network on ECG signals.

    Science.gov (United States)

    Tjolleng, Amir; Jung, Kihyo; Hong, Wongi; Lee, Wonsup; Lee, Baekhee; You, Heecheon; Son, Joonwoo; Park, Seikwon

    2017-03-01

    An artificial neural network (ANN) model was developed in the present study to classify the level of a driver's cognitive workload based on electrocardiography (ECG). ECG signals were measured on 15 male participants while they performed a simulated driving task as a primary task with/without an N-back task as a secondary task. Three time-domain ECG measures (mean inter-beat interval (IBI), standard deviation of IBIs, and root mean squared difference of adjacent IBIs) and three frequencydomain ECG measures (power in low frequency, power in high frequency, and ratio of power in low and high frequencies) were calculated. To compensate for individual differences in heart response during the driving tasks, a three-step data processing procedure was performed to ECG signals of each participant: (1) selection of two most sensitive ECG measures, (2) definition of three (low, medium, and high) cognitive workload levels, and (3) normalization of the selected ECG measures. An ANN model was constructed using a feed-forward network and scaled conjugate gradient as a back-propagation learning rule. The accuracy of the ANN classification model was found satisfactory for learning data (95%) and testing data (82%). Copyright © 2016 Elsevier Ltd. All rights reserved.

  13. Deep multi-scale convolutional neural network for hyperspectral image classification

    Science.gov (United States)

    Zhang, Feng-zhe; Yang, Xia

    2018-04-01

    In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

  14. 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...

  15. Classification

    DEFF Research Database (Denmark)

    Hjørland, Birger

    2017-01-01

    This article presents and discusses definitions of the term “classification” and the related concepts “Concept/conceptualization,”“categorization,” “ordering,” “taxonomy” and “typology.” It further presents and discusses theories of classification including the influences of Aristotle...... and Wittgenstein. It presents different views on forming classes, including logical division, numerical taxonomy, historical classification, hermeneutical and pragmatic/critical views. Finally, issues related to artificial versus natural classification and taxonomic monism versus taxonomic pluralism are briefly...

  16. Formalization of the classification pattern: survey of classification modeling in information systems engineering.

    Science.gov (United States)

    Partridge, Chris; de Cesare, Sergio; Mitchell, Andrew; Odell, James

    2018-01-01

    Formalization is becoming more common in all stages of the development of information systems, as a better understanding of its benefits emerges. Classification systems are ubiquitous, no more so than in domain modeling. The classification pattern that underlies these systems provides a good case study of the move toward formalization in part because it illustrates some of the barriers to formalization, including the formal complexity of the pattern and the ontological issues surrounding the "one and the many." Powersets are a way of characterizing the (complex) formal structure of the classification pattern, and their formalization has been extensively studied in mathematics since Cantor's work in the late nineteenth century. One can use this formalization to develop a useful benchmark. There are various communities within information systems engineering (ISE) that are gradually working toward a formalization of the classification pattern. However, for most of these communities, this work is incomplete, in that they have not yet arrived at a solution with the expressiveness of the powerset benchmark. This contrasts with the early smooth adoption of powerset by other information systems communities to, for example, formalize relations. One way of understanding the varying rates of adoption is recognizing that the different communities have different historical baggage. Many conceptual modeling communities emerged from work done on database design, and this creates hurdles to the adoption of the high level of expressiveness of powersets. Another relevant factor is that these communities also often feel, particularly in the case of domain modeling, a responsibility to explain the semantics of whatever formal structures they adopt. This paper aims to make sense of the formalization of the classification pattern in ISE and surveys its history through the literature, starting from the relevant theoretical works of the mathematical literature and gradually shifting focus

  17. AN APPLICATION OF FUNCTIONAL MULTIVARIATE REGRESSION MODEL TO MULTICLASS CLASSIFICATION

    OpenAIRE

    Krzyśko, Mirosław; Smaga, Łukasz

    2017-01-01

    In this paper, the scale response functional multivariate regression model is considered. By using the basis functions representation of functional predictors and regression coefficients, this model is rewritten as a multivariate regression model. This representation of the functional multivariate regression model is used for multiclass classification for multivariate functional data. Computational experiments performed on real labelled data sets demonstrate the effectiveness of the proposed ...

  18. 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.

  19. A model of coauthorship networks

    Science.gov (United States)

    Zhou, Guochang; Li, Jianping; Xie, Zonglin

    2017-10-01

    A natural way of representing the coauthorship of authors is to use a generalization of graphs known as hypergraphs. A random geometric hypergraph model is proposed here to model coauthorship networks, which is generated by placing nodes on a region of Euclidean space randomly and uniformly, and connecting some nodes if the nodes satisfy particular geometric conditions. Two kinds of geometric conditions are designed to model the collaboration patterns of academic authorities and basic researches respectively. The conditions give geometric expressions of two causes of coauthorship: the authority and similarity of authors. By simulation and calculus, we show that the forepart of the degree distribution of the network generated by the model is mixture Poissonian, and the tail is power-law, which are similar to these of some coauthorship networks. Further, we show more similarities between the generated network and real coauthorship networks: the distribution of cardinalities of hyperedges, high clustering coefficient, assortativity, and small-world property

  20. Vertebrae classification models - Validating classification models that use morphometrics to identify ancient salmonid (Oncorhynchus spp.) vertebrae to species

    Data.gov (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Using morphometric characteristics of modern salmonid (Oncorhynchus spp.) vertebrae, we have developed classification models to identify salmonid vertebrae to the...

  1. Classification of dried vegetables using computer image analysis and artificial neural networks

    Science.gov (United States)

    Koszela, K.; Łukomski, M.; Mueller, W.; Górna, K.; Okoń, P.; Boniecki, P.; Zaborowicz, M.; Wojcieszak, D.

    2017-07-01

    In the recent years, there has been a continuously increasing demand for vegetables and dried vegetables. This trend affects the growth of the dehydration industry in Poland helping to exploit excess production. More and more often dried vegetables are used in various sectors of the food industry, both due to their high nutritional qualities and changes in consumers' food preferences. As we observe an increase in consumer awareness regarding a healthy lifestyle and a boom in health food, there is also an increase in the consumption of such food, which means that the production and crop area can increase further. Among the dried vegetables, dried carrots play a strategic role due to their wide application range and high nutritional value. They contain high concentrations of carotene and sugar which is present in the form of crystals. Carrots are also the vegetables which are most often subjected to a wide range of dehydration processes; this makes it difficult to perform a reliable qualitative assessment and classification of this dried product. The many qualitative properties of dried carrots determining their positive or negative quality assessment include colour and shape. The aim of the research was to develop and implement the model of a computer system for the recognition and classification of freeze-dried, convection-dried and microwave vacuum dried products using the methods of computer image analysis and artificial neural networks.

  2. 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.

  3. Acute leukemia classification by ensemble particle swarm model selection.

    Science.gov (United States)

    Escalante, Hugo Jair; Montes-y-Gómez, Manuel; González, Jesús A; Gómez-Gil, Pilar; Altamirano, Leopoldo; Reyes, Carlos A; Reta, Carolina; Rosales, Alejandro

    2012-07-01

    Acute leukemia is a malignant disease that affects a large proportion of the world population. Different types and subtypes of acute leukemia require different treatments. In order to assign the correct treatment, a physician must identify the leukemia type or subtype. Advanced and precise methods are available for identifying leukemia types, but they are very expensive and not available in most hospitals in developing countries. Thus, alternative methods have been proposed. An option explored in this paper is based on the morphological properties of bone marrow images, where features are extracted from medical images and standard machine learning techniques are used to build leukemia type classifiers. This paper studies the use of ensemble particle swarm model selection (EPSMS), which is an automated tool for the selection of classification models, in the context of acute leukemia classification. EPSMS is the application of particle swarm optimization to the exploration of the search space of ensembles that can be formed by heterogeneous classification models in a machine learning toolbox. EPSMS does not require prior domain knowledge and it is able to select highly accurate classification models without user intervention. Furthermore, specific models can be used for different classification tasks. We report experimental results for acute leukemia classification with real data and show that EPSMS outperformed the best results obtained using manually designed classifiers with the same data. The highest performance using EPSMS was of 97.68% for two-type classification problems and of 94.21% for more than two types problems. To the best of our knowledge, these are the best results reported for this data set. Compared with previous studies, these improvements were consistent among different type/subtype classification tasks, different features extracted from images, and different feature extraction regions. The performance improvements were statistically significant

  4. Comparison of models of automatic classification of textural patterns of mineral presents in Colombian coals

    International Nuclear Information System (INIS)

    Lopez Carvajal, Jaime; Branch Bedoya, John Willian

    2005-01-01

    The automatic classification of objects is a very interesting approach under several problem domains. This paper outlines some results obtained under different classification models to categorize textural patterns of minerals using real digital images. The data set used was characterized by a small size and noise presence. The implemented models were the Bayesian classifier, Neural Network (2-5-1), support vector machine, decision tree and 3-nearest neighbors. The results after applying crossed validation show that the Bayesian model (84%) proved better predictive capacity than the others, mainly due to its noise robustness behavior. The neuronal network (68%) and the SVM (67%) gave promising results, because they could be improved increasing the data amount used, while the decision tree (55%) and K-NN (54%) did not seem to be adequate for this problem, because of their sensibility to noise

  5. Digital image classification with the help of artificial neural network by simple histogram.

    Science.gov (United States)

    Dey, Pranab; Banerjee, Nirmalya; Kaur, Rajwant

    2016-01-01

    Visual image classification is a great challenge to the cytopathologist in routine day-to-day work. Artificial neural network (ANN) may be helpful in this matter. In this study, we have tried to classify digital images of malignant and benign cells in effusion cytology smear with the help of simple histogram data and ANN. A total of 404 digital images consisting of 168 benign cells and 236 malignant cells were selected for this study. The simple histogram data was extracted from these digital images and an ANN was constructed with the help of Neurointelligence software [Alyuda Neurointelligence 2.2 (577), Cupertino, California, USA]. The network architecture was 6-3-1. The images were classified as training set (281), validation set (63), and test set (60). The on-line backpropagation training algorithm was used for this study. A total of 10,000 iterations were done to train the ANN system with the speed of 609.81/s. After the adequate training of this ANN model, the system was able to identify all 34 malignant cell images and 24 out of 26 benign cells. The ANN model can be used for the identification of the individual malignant cells with the help of simple histogram data. This study will be helpful in the future to identify malignant cells in unknown situations.

  6. Telecommunications network modelling, planning and design

    CERN Document Server

    Evans, Sharon

    2003-01-01

    Telecommunication Network Modelling, Planning and Design addresses sophisticated modelling techniques from the perspective of the communications industry and covers some of the major issues facing telecommunications network engineers and managers today. Topics covered include network planning for transmission systems, modelling of SDH transport network structures and telecommunications network design and performance modelling, as well as network costs and ROI modelling and QoS in 3G networks.

  7. Active Learning of Classification Models with Likert-Scale Feedback.

    Science.gov (United States)

    Xue, Yanbing; Hauskrecht, Milos

    2017-01-01

    Annotation of classification data by humans can be a time-consuming and tedious process. Finding ways of reducing the annotation effort is critical for building the classification models in practice and for applying them to a variety of classification tasks. In this paper, we develop a new active learning framework that combines two strategies to reduce the annotation effort. First, it relies on label uncertainty information obtained from the human in terms of the Likert-scale feedback. Second, it uses active learning to annotate examples with the greatest expected change. We propose a Bayesian approach to calculate the expectation and an incremental SVM solver to reduce the time complexity of the solvers. We show the combination of our active learning strategy and the Likert-scale feedback can learn classification models more rapidly and with a smaller number of labeled instances than methods that rely on either Likert-scale labels or active learning alone.

  8. Signal classification using global dynamical models, Part I: Theory

    International Nuclear Information System (INIS)

    Kadtke, J.; Kremliovsky, M.

    1996-01-01

    Detection and classification of signals is one of the principal areas of signal processing, and the utilization of nonlinear information has long been considered as a way of improving performance beyond standard linear (e.g. spectral) techniques. Here, we develop a method for using global models of chaotic dynamical systems theory to define a signal classification processing chain, which is sensitive to nonlinear correlations in the data. We use it to demonstrate classification in high noise regimes (negative SNR), and argue that classification probabilities can be directly computed from ensemble statistics in the model coefficient space. We also develop a modification for non-stationary signals (i.e. transients) using non-autonomous ODEs. In Part II of this paper, we demonstrate the analysis on actual open ocean acoustic data from marine biologics. copyright 1996 American Institute of Physics

  9. Polarimetric SAR image classification based on discriminative dictionary learning model

    Science.gov (United States)

    Sang, Cheng Wei; Sun, Hong

    2018-03-01

    Polarimetric SAR (PolSAR) image classification is one of the important applications of PolSAR remote sensing. It is a difficult high-dimension nonlinear mapping problem, the sparse representations based on learning overcomplete dictionary have shown great potential to solve such problem. The overcomplete dictionary plays an important role in PolSAR image classification, however for PolSAR image complex scenes, features shared by different classes will weaken the discrimination of learned dictionary, so as to degrade classification performance. In this paper, we propose a novel overcomplete dictionary learning model to enhance the discrimination of dictionary. The learned overcomplete dictionary by the proposed model is more discriminative and very suitable for PolSAR classification.

  10. 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.

  11. Classification of brain compartments and head injury lesions by neural networks applied to MRI

    International Nuclear Information System (INIS)

    Kischell, E.R.; Kehtarnavaz, N.; Hillman, G.R.; Levin, H.; Lilly, M.; Kent, T.A.

    1995-01-01

    An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and 'unknown'. A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classifications of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician's report used to train the neural network. (orig.)

  12. Classification of brain compartments and head injury lesions by neural networks applied to MRI

    Energy Technology Data Exchange (ETDEWEB)

    Kischell, E R [Dept. of Electrical Engineering, Texas A and M Univ., College Station, TX (United States); Kehtarnavaz, N [Dept. of Electrical Engineering, Texas A and M Univ., College Station, TX (United States); Hillman, G R [Dept. of Pharmacology, Univ. of Texas Medical Branch, Galveston, TX (United States); Levin, H [Dept. of Neurosurgery, Univ. of Texas Medical Branch, Galveston, TX (United States); Lilly, M [Dept. of Neurosurgery, Univ. of Texas Medical Branch, Galveston, TX (United States); Kent, T A [Dept. of Neurology and Psychiatry, Univ. of Texas Medical Branch, Galveston, TX (United States)

    1995-10-01

    An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and `unknown`. A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classifications of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician`s report used to train the neural network. (orig.)

  13. Campus network security model study

    Science.gov (United States)

    Zhang, Yong-ku; Song, Li-ren

    2011-12-01

    Campus network security is growing importance, Design a very effective defense hacker attacks, viruses, data theft, and internal defense system, is the focus of the study in this paper. This paper compared the firewall; IDS based on the integrated, then design of a campus network security model, and detail the specific implementation principle.

  14. 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...

  15. Co-occurrence Models in Music Genre Classification

    DEFF Research Database (Denmark)

    Ahrendt, Peter; Goutte, Cyril; Larsen, Jan

    2005-01-01

    Music genre classification has been investigated using many different methods, but most of them build on probabilistic models of feature vectors x\\_r which only represent the short time segment with index r of the song. Here, three different co-occurrence models are proposed which instead consider...... genre data set with a variety of modern music. The basis was a so-called AR feature representation of the music. Besides the benefit of having proper probabilistic models of the whole song, the lowest classification test errors were found using one of the proposed models....

  16. Conjugate-Gradient Neural Networks in Classification of Multisource and Very-High-Dimensional Remote Sensing Data

    Science.gov (United States)

    Benediktsson, J. A.; Swain, P. H.; Ersoy, O. K.

    1993-01-01

    Application of neural networks to classification of remote sensing data is discussed. Conventional two-layer backpropagation is found to give good results in classification of remote sensing data but is not efficient in training. A more efficient variant, based on conjugate-gradient optimization, is used for classification of multisource remote sensing and geographic data and very-high-dimensional data. The conjugate-gradient neural networks give excellent performance in classification of multisource data, but do not compare as well with statistical methods in classification of very-high-dimentional data.

  17. A web-based system for neural network based classification in temporomandibular joint osteoarthritis.

    Science.gov (United States)

    de Dumast, Priscille; Mirabel, Clément; Cevidanes, Lucia; Ruellas, Antonio; Yatabe, Marilia; Ioshida, Marcos; Ribera, Nina Tubau; Michoud, Loic; Gomes, Liliane; Huang, Chao; Zhu, Hongtu; Muniz, Luciana; Shoukri, Brandon; Paniagua, Beatriz; Styner, Martin; Pieper, Steve; Budin, Francois; Vimort, Jean-Baptiste; Pascal, Laura; Prieto, Juan Carlos

    2018-07-01

    The purpose of this study is to describe the methodological innovations of a web-based system for storage, integration and computation of biomedical data, using a training imaging dataset to remotely compute a deep neural network classifier of temporomandibular joint osteoarthritis (TMJOA). This study imaging dataset consisted of three-dimensional (3D) surface meshes of mandibular condyles constructed from cone beam computed tomography (CBCT) scans. The training dataset consisted of 259 condyles, 105 from control subjects and 154 from patients with diagnosis of TMJ OA. For the image analysis classification, 34 right and left condyles from 17 patients (39.9 ± 11.7 years), who experienced signs and symptoms of the disease for less than 5 years, were included as the testing dataset. For the integrative statistical model of clinical, biological and imaging markers, the sample consisted of the same 17 test OA subjects and 17 age and sex matched control subjects (39.4 ± 15.4 years), who did not show any sign or symptom of OA. For these 34 subjects, a standardized clinical questionnaire, blood and saliva samples were also collected. The technological methodologies in this study include a deep neural network classifier of 3D condylar morphology (ShapeVariationAnalyzer, SVA), and a flexible web-based system for data storage, computation and integration (DSCI) of high dimensional imaging, clinical, and biological data. The DSCI system trained and tested the neural network, indicating 5 stages of structural degenerative changes in condylar morphology in the TMJ with 91% close agreement between the clinician consensus and the SVA classifier. The DSCI remotely ran with a novel application of a statistical analysis, the Multivariate Functional Shape Data Analysis, that computed high dimensional correlations between shape 3D coordinates, clinical pain levels and levels of biological markers, and then graphically displayed the computation results. The findings of this

  18. User profiling and classification for fraud detection in mobile communications networks

    OpenAIRE

    Hollmén, Jaakko

    2000-01-01

    The topic of this thesis is fraud detection in mobile communications networks by means of user profiling and classification techniques. The goal is to first identify relevant user groups based on call data and then to assign a user to a relevant group. Fraud may be defined as a dishonest or illegal use of services, with the intention to avoid service charges. Fraud detection is an important application, since network operators lose a relevant portion of their revenue to fraud. Whereas the int...

  19. ALADDIN: a neural model for event classification in dynamic processes

    International Nuclear Information System (INIS)

    Roverso, Davide

    1998-02-01

    ALADDIN is a prototype system which combines fuzzy clustering techniques and artificial neural network (ANN) models in a novel approach to the problem of classifying events in dynamic processes. The main motivation for the development of such a system derived originally from the problem of finding new principled methods to perform alarm structuring/suppression in a nuclear power plant (NPP) alarm system. One such method consists in basing the alarm structuring/suppression on a fast recognition of the event generating the alarms, so that a subset of alarms sufficient to efficiently handle the current fault can be selected to be presented to the operator, minimizing in this way the operator's workload in a potentially stressful situation. The scope of application of a system like ALADDIN goes however beyond alarm handling, to include diagnostic tasks in general. The eventual application of the system to domains other than NPPs was also taken into special consideration during the design phase. In this document we report on the first phase of the ALADDIN project which consisted mainly in a comparative study of a series of ANN-based approaches to event classification, and on the proposal of a first system prototype which is to undergo further tests and, eventually, be integrated in existing alarm, diagnosis, and accident management systems such as CASH, IDS, and CAMS. (author)

  20. Definition and Classification of Terms for HVDC Networks

    DEFF Research Database (Denmark)

    Vrana, Til Kristian; Bell, Keith; Sørensen, Poul Ejnar

    2015-01-01

    A systematic terminology for the field of HVDC networks has been developed, closing the gap between the well-established terminologies from AC power systems and HVDC technology. The most relevant items, topologies and concepts have been given clear and unique defined names, and these have been cl...

  1. A neural network based seafloor classification using acoustic backscatter

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.

    This paper presents a study results of the Artificial Neural Network (ANN) architectures [Self-Organizing Map (SOM) and Multi-Layer Perceptron (MLP)] using single beam echosounding data. The single beam echosounder, operable at 12 kHz, has been used...

  2. Networking and distance learning for teachers: A classification of possibilities

    NARCIS (Netherlands)

    Collis, Betty

    1995-01-01

    Computer based communication technologies, or what could be more conveniently called networking, are bringing new possibilities into teacher education in many different ways. As with distance education more generally they can facilitate flexibility in time and place of learning, but the range of

  3. Classification of networks of automata by dynamical mean field theory

    International Nuclear Information System (INIS)

    Burda, Z.; Jurkiewicz, J.; Flyvbjerg, H.

    1990-01-01

    Dynamical mean field theory is used to classify the 2 24 =65,536 different networks of binary automata on a square lattice with nearest neighbour interactions. Application of mean field theory gives 700 different mean field classes, which fall in seven classes of different asymptotic dynamics characterized by fixed points and two-cycles. (orig.)

  4. Generalized Network Psychometrics : Combining Network and Latent Variable Models

    NARCIS (Netherlands)

    Epskamp, S.; Rhemtulla, M.; Borsboom, D.

    2017-01-01

    We introduce the network model as a formal psychometric model, conceptualizing the covariance between psychometric indicators as resulting from pairwise interactions between observable variables in a network structure. This contrasts with standard psychometric models, in which the covariance between

  5. Classification of ion mobility spectra by functional groups using neural networks

    Science.gov (United States)

    Bell, S.; Nazarov, E.; Wang, Y. F.; Eiceman, G. A.

    1999-01-01

    Neural networks were trained using whole ion mobility spectra from a standardized database of 3137 spectra for 204 chemicals at various concentrations. Performance of the network was measured by the success of classification into ten chemical classes. Eleven stages for evaluation of spectra and of spectral pre-processing were employed and minimums established for response thresholds and spectral purity. After optimization of the database, network, and pre-processing routines, the fraction of successful classifications by functional group was 0.91 throughout a range of concentrations. Network classification relied on a combination of features, including drift times, number of peaks, relative intensities, and other factors apparently including peak shape. The network was opportunistic, exploiting different features within different chemical classes. Application of neural networks in a two-tier design where chemicals were first identified by class and then individually eliminated all but one false positive out of 161 test spectra. These findings establish that ion mobility spectra, even with low resolution instrumentation, contain sufficient detail to permit the development of automated identification systems.

  6. A review and analysis of neural networks for classification of remotely sensed multispectral imagery

    Science.gov (United States)

    Paola, Justin D.; Schowengerdt, Robert A.

    1993-01-01

    A literature survey and analysis of the use of neural networks for the classification of remotely sensed multispectral imagery is presented. As part of a brief mathematical review, the backpropagation algorithm, which is the most common method of training multi-layer networks, is discussed with an emphasis on its application to pattern recognition. The analysis is divided into five aspects of neural network classification: (1) input data preprocessing, structure, and encoding; (2) output encoding and extraction of classes; (3) network architecture, (4) training algorithms; and (5) comparisons to conventional classifiers. The advantages of the neural network method over traditional classifiers are its non-parametric nature, arbitrary decision boundary capabilities, easy adaptation to different types of data and input structures, fuzzy output values that can enhance classification, and good generalization for use with multiple images. The disadvantages of the method are slow training time, inconsistent results due to random initial weights, and the requirement of obscure initialization values (e.g., learning rate and hidden layer size). Possible techniques for ameliorating these problems are discussed. It is concluded that, although the neural network method has several unique capabilities, it will become a useful tool in remote sensing only if it is made faster, more predictable, and easier to use.

  7. Neural network modeling of emotion

    Science.gov (United States)

    Levine, Daniel S.

    2007-03-01

    This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.

  8. Modeling of fluctuating reaction networks

    International Nuclear Information System (INIS)

    Lipshtat, A.; Biham, O.

    2004-01-01

    Full Text:Various dynamical systems are organized as reaction networks, where the population size of one component affects the populations of all its neighbors. Such networks can be found in interstellar surface chemistry, cell biology, thin film growth and other systems. I cases where the populations of reactive species are large, the network can be modeled by rate equations which provide all reaction rates within mean field approximation. However, in small systems that are partitioned into sub-micron size, these populations strongly fluctuate. Under these conditions rate equations fail and the master equation is needed for modeling these reactions. However, the number of equations in the master equation grows exponentially with the number of reactive species, severely limiting its feasibility for complex networks. Here we present a method which dramatically reduces the number of equations, thus enabling the incorporation of the master equation in complex reaction networks. The method is examplified in the context of reaction network on dust grains. Its applicability for genetic networks will be discussed. 1. Efficient simulations of gas-grain chemistry in interstellar clouds. Azi Lipshtat and Ofer Biham, Phys. Rev. Lett. 93 (2004), 170601. 2. Modeling of negative autoregulated genetic networks in single cells. Azi Lipshtat, Hagai B. Perets, Nathalie Q. Balaban and Ofer Biham, Gene: evolutionary genomics (2004), In press

  9. Classification of CITES-listed and other neotropical Meliaceae wood images using convolutional neural networks.

    Science.gov (United States)

    Ravindran, Prabu; Costa, Adriana; Soares, Richard; Wiedenhoeft, Alex C

    2018-01-01

    The current state-of-the-art for field wood identification to combat illegal logging relies on experienced practitioners using hand lenses, specialized identification keys, atlases of woods, and field manuals. Accumulation of this expertise is time-consuming and access to training is relatively rare compared to the international demand for field wood identification. A reliable, consistent and cost effective field screening method is necessary for effective global scale enforcement of international treaties such as the Convention on the International Trade in Endagered Species (CITES) or national laws (e.g. the US Lacey Act) governing timber trade and imports. We present highly effective computer vision classification models, based on deep convolutional neural networks, trained via transfer learning, to identify the woods of 10 neotropical species in the family Meliaceae, including CITES-listed Swietenia macrophylla , Swietenia mahagoni , Cedrela fissilis , and Cedrela odorata . We build and evaluate models to classify the 10 woods at the species and genus levels, with image-level model accuracy ranging from 87.4 to 97.5%, with the strongest performance by the genus-level model. Misclassified images are attributed to classes consistent with traditional wood anatomical results, and our species-level accuracy greatly exceeds the resolution of traditional wood identification. The end-to-end trained image classifiers that we present discriminate the woods based on digital images of the transverse surface of solid wood blocks, which are surfaces and images that can be prepared and captured in the field. Hence this work represents a strong proof-of-concept for using computer vision and convolutional neural networks to develop practical models for field screening timber and wood products to combat illegal logging.

  10. Wireless Magnetic Sensor Network for Road Traffic Monitoring and Vehicle Classification

    Directory of Open Access Journals (Sweden)

    Velisavljevic Vladan

    2016-12-01

    Full Text Available Efficiency of transportation of people and goods is playing a vital role in economic growth. A key component for enabling effective planning of transportation networks is the deployment and operation of autonomous monitoring and traffic analysis tools. For that reason, such systems have been developed to register and classify road traffic usage. In this paper, we propose a novel system for road traffic monitoring and classification based on highly energy efficient wireless magnetic sensor networks. We develop novel algorithms for vehicle speed and length estimation and vehicle classification that use multiple magnetic sensors. We also demonstrate that, using such a low-cost system with simplified installation and maintenance compared to current solutions, it is possible to achieve highly accurate estimation and a high rate of positive vehicle classification.

  11. Conceptualising Business Models: Definitions, Frameworks and Classifications

    OpenAIRE

    Erwin Fielt

    2013-01-01

    The business model concept is gaining traction in different disciplines but is still criticized for being fuzzy and vague and lacking consensus on its definition and compositional elements. In this paper we set out to advance our understanding of the business model concept by addressing three areas of foundational research: business model definitions, business model elements, and business model archetypes. We define a business model as a representation of the value logic of an organization in...

  12. Classification of clinical autofluorescence spectra of oral leukoplakia using an artificial neural network : a pilot study

    NARCIS (Netherlands)

    van Staveren, HJ; van Veen, RLP; Speelman, OC; Witjes, MJH; Roodenburg, JLN

    The performance of an artificial neural network was evaluated as an alternative classification technique of autofluorescence spectra of oral leukoplakia, which may reflect the grade of tissue dysplasia. Twenty-two visible lesions of 21 patients suffering from oral leukoplakia and six locations on

  13. Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation

    CSIR Research Space (South Africa)

    Ngwangwa, HM

    2010-04-01

    Full Text Available -1 Journal of Terramechanics Volume 47, Issue 2, April 2010, Pages 97-111 Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation H.M. Ngwangwaa, P.S. Heynsa, , , F...

  14. Astrophysical Information from Objective Prism Digitized Images: Classification with an Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Bratsolis Emmanuel

    2005-01-01

    Full Text Available Stellar spectral classification is not only a tool for labeling individual stars but is also useful in studies of stellar population synthesis. Extracting the physical quantities from the digitized spectral plates involves three main stages: detection, extraction, and classification of spectra. Low-dispersion objective prism images have been used and automated methods have been developed. The detection and extraction problems have been presented in previous works. In this paper, we present a classification method based on an artificial neural network (ANN. We make a brief presentation of the entire automated system and we compare the new classification method with the previously used method of maximum correlation coefficient (MCC. Digitized photographic material has been used here. The method can also be used on CCD spectral images.

  15. Performance Analysis of Classification Methods for Indoor Localization in Vlc Networks

    Science.gov (United States)

    Sánchez-Rodríguez, D.; Alonso-González, I.; Sánchez-Medina, J.; Ley-Bosch, C.; Díaz-Vilariño, L.

    2017-09-01

    Indoor localization has gained considerable attention over the past decade because of the emergence of numerous location-aware services. Research works have been proposed on solving this problem by using wireless networks. Nevertheless, there is still much room for improvement in the quality of the proposed classification models. In the last years, the emergence of Visible Light Communication (VLC) brings a brand new approach to high quality indoor positioning. Among its advantages, this new technology is immune to electromagnetic interference and has the advantage of having a smaller variance of received signal power compared to RF based technologies. In this paper, a performance analysis of seventeen machine leaning classifiers for indoor localization in VLC networks is carried out. The analysis is accomplished in terms of accuracy, average distance error, computational cost, training size, precision and recall measurements. Results show that most of classifiers harvest an accuracy above 90 %. The best tested classifier yielded a 99.0 % accuracy, with an average error distance of 0.3 centimetres.

  16. A Hypergraph and Arithmetic Residue-based Probabilistic Neural Network for classification in Intrusion Detection Systems.

    Science.gov (United States)

    Raman, M R Gauthama; Somu, Nivethitha; Kirthivasan, Kannan; Sriram, V S Shankar

    2017-08-01

    Over the past few decades, the design of an intelligent Intrusion Detection System (IDS) remains an open challenge to the research community. Continuous efforts by the researchers have resulted in the development of several learning models based on Artificial Neural Network (ANN) to improve the performance of the IDSs. However, there exists a tradeoff with respect to the stability of ANN architecture and the detection rate for less frequent attacks. This paper presents a novel approach based on Helly property of Hypergraph and Arithmetic Residue-based Probabilistic Neural Network (HG AR-PNN) to address the classification problem in IDS. The Helly property of Hypergraph was exploited for the identification of the optimal feature subset and the arithmetic residue of the optimal feature subset was used to train the PNN. The performance of HG AR-PNN was evaluated using KDD CUP 1999 intrusion dataset. Experimental results prove the dominance of HG AR-PNN classifier over the existing classifiers with respect to the stability and improved detection rate for less frequent attacks. Copyright © 2017 Elsevier Ltd. All rights reserved.

  17. Histopathological Breast Cancer Image Classification by Deep Neural Network Techniques Guided by Local Clustering.

    Science.gov (United States)

    Nahid, Abdullah-Al; Mehrabi, Mohamad Ali; Kong, Yinan

    2018-01-01

    Breast Cancer is a serious threat and one of the largest causes of death of women throughout the world. The identification of cancer largely depends on digital biomedical photography analysis such as histopathological images by doctors and physicians. Analyzing histopathological images is a nontrivial task, and decisions from investigation of these kinds of images always require specialised knowledge. However, Computer Aided Diagnosis (CAD) techniques can help the doctor make more reliable decisions. The state-of-the-art Deep Neural Network (DNN) has been recently introduced for biomedical image analysis. Normally each image contains structural and statistical information. This paper classifies a set of biomedical breast cancer images (BreakHis dataset) using novel DNN techniques guided by structural and statistical information derived from the images. Specifically a Convolutional Neural Network (CNN), a Long-Short-Term-Memory (LSTM), and a combination of CNN and LSTM are proposed for breast cancer image classification. Softmax and Support Vector Machine (SVM) layers have been used for the decision-making stage after extracting features utilising the proposed novel DNN models. In this experiment the best Accuracy value of 91.00% is achieved on the 200x dataset, the best Precision value 96.00% is achieved on the 40x dataset, and the best F -Measure value is achieved on both the 40x and 100x datasets.

  18. PERFORMANCE ANALYSIS OF CLASSIFICATION METHODS FOR INDOOR LOCALIZATION IN VLC NETWORKS

    Directory of Open Access Journals (Sweden)

    D. Sánchez-Rodríguez

    2017-09-01

    Full Text Available Indoor localization has gained considerable attention over the past decade because of the emergence of numerous location-aware services. Research works have been proposed on solving this problem by using wireless networks. Nevertheless, there is still much room for improvement in the quality of the proposed classification models. In the last years, the emergence of Visible Light Communication (VLC brings a brand new approach to high quality indoor positioning. Among its advantages, this new technology is immune to electromagnetic interference and has the advantage of having a smaller variance of received signal power compared to RF based technologies. In this paper, a performance analysis of seventeen machine leaning classifiers for indoor localization in VLC networks is carried out. The analysis is accomplished in terms of accuracy, average distance error, computational cost, training size, precision and recall measurements. Results show that most of classifiers harvest an accuracy above 90 %. The best tested classifier yielded a 99.0 % accuracy, with an average error distance of 0.3 centimetres.

  19. Lean waste classification model to support the sustainable operational practice

    Science.gov (United States)

    Sutrisno, A.; Vanany, I.; Gunawan, I.; Asjad, M.

    2018-04-01

    Driven by growing pressure for a more sustainable operational practice, improvement on the classification of non-value added (waste) is one of the prerequisites to realize sustainability of a firm. While the use of the 7 (seven) types of the Ohno model now becoming a versatile tool to reveal the lean waste occurrence. In many recent investigations, the use of the Seven Waste model of Ohno is insufficient to cope with the types of waste occurred in industrial practices at various application levels. Intended to a narrowing down this limitation, this paper presented an improved waste classification model based on survey to recent studies discussing on waste at various operational stages. Implications on the waste classification model to the body of knowledge and industrial practices are provided.

  20. Music genre classification via likelihood fusion from multiple feature models

    Science.gov (United States)

    Shiu, Yu; Kuo, C.-C. J.

    2005-01-01

    Music genre provides an efficient way to index songs in a music database, and can be used as an effective means to retrieval music of a similar type, i.e. content-based music retrieval. A new two-stage scheme for music genre classification is proposed in this work. At the first stage, we examine a couple of different features, construct their corresponding parametric models (e.g. GMM and HMM) and compute their likelihood functions to yield soft classification results. In particular, the timbre, rhythm and temporal variation features are considered. Then, at the second stage, these soft classification results are integrated to result in a hard decision for final music genre classification. Experimental results are given to demonstrate the performance of the proposed scheme.

  1. Sensor network based vehicle classification and license plate identification system

    Energy Technology Data Exchange (ETDEWEB)

    Frigo, Janette Rose [Los Alamos National Laboratory; Brennan, Sean M [Los Alamos National Laboratory; Rosten, Edward J [Los Alamos National Laboratory; Raby, Eric Y [Los Alamos National Laboratory; Kulathumani, Vinod K [WEST VIRGINIA UNIV.

    2009-01-01

    Typically, for energy efficiency and scalability purposes, sensor networks have been used in the context of environmental and traffic monitoring applications in which operations at the sensor level are not computationally intensive. But increasingly, sensor network applications require data and compute intensive sensors such video cameras and microphones. In this paper, we describe the design and implementation of two such systems: a vehicle classifier based on acoustic signals and a license plate identification system using a camera. The systems are implemented in an energy-efficient manner to the extent possible using commercially available hardware, the Mica motes and the Stargate platform. Our experience in designing these systems leads us to consider an alternate more flexible, modular, low-power mote architecture that uses a combination of FPGAs, specialized embedded processing units and sensor data acquisition systems.

  2. Rock images classification by using deep convolution neural network

    Science.gov (United States)

    Cheng, Guojian; Guo, Wenhui

    2017-08-01

    Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability.

  3. Wavelet neural networks with applications in financial engineering, chaos, and classification

    CERN Document Server

    Alexandridis, Antonios K

    2014-01-01

    Through extensive examples and case studies, Wavelet Neural Networks provides a step-by-step introduction to modeling, training, and forecasting using wavelet networks. The acclaimed authors present a statistical model identification framework to successfully apply wavelet networks in various applications, specifically, providing the mathematical and statistical framework needed for model selection, variable selection, wavelet network construction, initialization, training, forecasting and prediction, confidence intervals, prediction intervals, and model adequacy testing. The text is ideal for

  4. SEMIPARAMETRIC VERSUS PARAMETRIC CLASSIFICATION MODELS - AN APPLICATION TO DIRECT MARKETING

    NARCIS (Netherlands)

    BULT, [No Value

    In this paper we are concerned with estimation of a classification model using semiparametric and parametric methods. Benefits and limitations of semiparametric models in general, and of Manski's maximum score method in particular, are discussed. The maximum score method yields consistent estimates

  5. Latent Partially Ordered Classification Models and Normal Mixtures

    Science.gov (United States)

    Tatsuoka, Curtis; Varadi, Ferenc; Jaeger, Judith

    2013-01-01

    Latent partially ordered sets (posets) can be employed in modeling cognitive functioning, such as in the analysis of neuropsychological (NP) and educational test data. Posets are cognitively diagnostic in the sense that classification states in these models are associated with detailed profiles of cognitive functioning. These profiles allow for…

  6. Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

    Science.gov (United States)

    Graves, Alex; Schmidhuber, Jürgen

    2005-01-01

    In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

  7. A classification of open string models

    International Nuclear Information System (INIS)

    Nahm, W.

    1985-12-01

    Open string models are classified using modular invariance. No good candidates for new models are found, though the existence of an E 8 invariant model in Rsup(17,1), a similar one in Rsup(5,1) and of a supersymmetric model in Rsup(2,1) cannot be excluded by this technique. An intriguing relation between the left moving and right moving sectors of the heterotic string emerges. (orig.)

  8. Seismic network based detection, classification and location of volcanic tremors

    Science.gov (United States)

    Nikolai, S.; Soubestre, J.; Seydoux, L.; de Rosny, J.; Droznin, D.; Droznina, S.; Senyukov, S.; Gordeev, E.

    2017-12-01

    Volcanic tremors constitute an important attribute of volcanic unrest in many volcanoes, and their detection and characterization is a challenging issue of volcano monitoring. The main goal of the present work is to develop a network-based method to automatically classify volcanic tremors, to locate their sources and to estimate the associated wave speed. The method is applied to four and a half years of seismic data continuously recorded by 19 permanent seismic stations in the vicinity of the Klyuchevskoy volcanic group (KVG) in Kamchatka (Russia), where five volcanoes were erupting during the considered time period. The method is based on the analysis of eigenvalues and eigenvectors of the daily array covariance matrix. As a first step, following Seydoux et al. (2016), most coherent signals corresponding to dominating tremor sources are detected based on the width of the covariance matrix eigenvalues distribution. With this approach, the volcanic tremors of the two volcanoes known as most active during the considered period, Klyuchevskoy and Tolbachik, are efficiently detected. As a next step, we consider the array covariance matrix's first eigenvectors computed every day. The main hypothesis of our analysis is that these eigenvectors represent the principal component of the daily seismic wavefield and, for days with tremor activity, characterize the dominant tremor sources. Those first eigenvectors can therefore be used as network-based fingerprints of tremor sources. A clustering process is developed to analyze this collection of first eigenvectors, using correlation coefficient as a measure of their similarity. Then, we locate tremor sources based on cross-correlations amplitudes. We characterize seven tremor sources associated with different periods of activity of four volcanoes: Tolbachik, Klyuchevskoy, Shiveluch, and Kizimen. The developed method does not require a priori knowledge, is fully automatic and the database of network-based tremor fingerprints

  9. Hydrological network and classification of lakes on the Third Pole

    Science.gov (United States)

    Gao, Yang; Wang, Weicai; Yao, Tandong; Lu, Ning; Lu, Anxin

    2018-05-01

    The intensity and form of changes in closed lakes, upstream lakes and outflow lakes on the Third Pole (TP) differ based on their drainage mode. Researchers' insufficient understanding of the hydrological networks associated with lakes hampers studies of the relationship between lakes and climate. In this study, we establish a comprehensive hydrological network for each lake (>1 km2) on the TP using 106 Landsat images, 236 Chinese topographic maps, and SRTM DEM. Three-hundred-ninety-seven closed lakes, 488 upstream lakes and 317 outflow lakes totaling 3,5498.49 km2, 7,378.82 km2, and 3,382.29 km2, respectively, were identified on the TP using 2010 data. Two-hundred-thirty-four closed lakes were found to not be linked to upstream lakes. The remaining 163 closed lakes were connected to and fed by the 488 upstream lakes. The object-oriented analyses within this study indicated that more rapid changes occurred in the surface extent of closed lakes than in upstream lakes or outflow lakes on the TP from 1970 s to 2010. Furthermore, the water volume of the examined closed lakes was almost nine times greater than that of the upstream lakes from 2003 to 2009. All the examined closed lakes exhibited an obvious water volume change compared to the corresponding upstream lakes in the same basin. Furthermore, two case studies illustrate that the annual and seasonal dynamics associated with the changes in closed lakes may reflect climate change patterns, while the upstream lake dynamics may be more controlled by the lakeshore terrain and drainage characteristics. The lake inventory and hydrological network catalogued in this study provide a basis for developing a better understanding of lake response to climate change on the TP.

  10. Extruded Bread Classification on the Basis of Acoustic Emission Signal With Application of Artificial Neural Networks

    Science.gov (United States)

    Świetlicka, Izabela; Muszyński, Siemowit; Marzec, Agata

    2015-04-01

    The presented work covers the problem of developing a method of extruded bread classification with the application of artificial neural networks. Extruded flat graham, corn, and rye breads differening in water activity were used. The breads were subjected to the compression test with simultaneous registration of acoustic signal. The amplitude-time records were analyzed both in time and frequency domains. Acoustic emission signal parameters: single energy, counts, amplitude, and duration acoustic emission were determined for the breads in four water activities: initial (0.362 for rye, 0.377 for corn, and 0.371 for graham bread), 0.432, 0.529, and 0.648. For classification and the clustering process, radial basis function, and self-organizing maps (Kohonen network) were used. Artificial neural networks were examined with respect to their ability to classify or to cluster samples according to the bread type, water activity value, and both of them. The best examination results were achieved by the radial basis function network in classification according to water activity (88%), while the self-organizing maps network yielded 81% during bread type clustering.

  11. Smart-phone based electrocardiogram wavelet decomposition and neural network classification

    International Nuclear Information System (INIS)

    Jannah, N; Hadjiloucas, S; Hwang, F; Galvão, R K H

    2013-01-01

    This paper discusses ECG classification after parametrizing the ECG waveforms in the wavelet domain. The aim of the work is to develop an accurate classification algorithm that can be used to diagnose cardiac beat abnormalities detected using a mobile platform such as smart-phones. Continuous time recurrent neural network classifiers are considered for this task. Records from the European ST-T Database are decomposed in the wavelet domain using discrete wavelet transform (DWT) filter banks and the resulting DWT coefficients are filtered and used as inputs for training the neural network classifier. Advantages of the proposed methodology are the reduced memory requirement for the signals which is of relevance to mobile applications as well as an improvement in the ability of the neural network in its generalization ability due to the more parsimonious representation of the signal to its inputs.

  12. Visualization of Nonlinear Classification Models in Neuroimaging - Signed Sensitivity Maps

    DEFF Research Database (Denmark)

    Rasmussen, Peter Mondrup; Schmah, Tanya; Madsen, Kristoffer Hougaard

    2012-01-01

    Classification models are becoming increasing popular tools in the analysis of neuroimaging data sets. Besides obtaining good prediction accuracy, a competing goal is to interpret how the classifier works. From a neuroscientific perspective, we are interested in the brain pattern reflecting...... the underlying neural encoding of an experiment defining multiple brain states. In this relation there is a great desire for the researcher to generate brain maps, that highlight brain locations of importance to the classifiers decisions. Based on sensitivity analysis, we develop further procedures for model...... direction the individual locations influence the classification. We illustrate the visualization procedure on a real data from a simple functional magnetic resonance imaging experiment....

  13. Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound.

    Science.gov (United States)

    Kesharaju, Manasa; Nagarajah, Romesh

    2015-09-01

    The motivation for this research stems from a need for providing a non-destructive testing method capable of detecting and locating any defects and microstructural variations within armour ceramic components before issuing them to the soldiers who rely on them for their survival. The development of an automated ultrasonic inspection based classification system would make possible the checking of each ceramic component and immediately alert the operator about the presence of defects. Generally, in many classification problems a choice of features or dimensionality reduction is significant and simultaneously very difficult, as a substantial computational effort is required to evaluate possible feature subsets. In this research, a combination of artificial neural networks and genetic algorithms are used to optimize the feature subset used in classification of various defects in reaction-sintered silicon carbide ceramic components. Initially wavelet based feature extraction is implemented from the region of interest. An Artificial Neural Network classifier is employed to evaluate the performance of these features. Genetic Algorithm based feature selection is performed. Principal Component Analysis is a popular technique used for feature selection and is compared with the genetic algorithm based technique in terms of classification accuracy and selection of optimal number of features. The experimental results confirm that features identified by Principal Component Analysis lead to improved performance in terms of classification percentage with 96% than Genetic algorithm with 94%. Copyright © 2015 Elsevier B.V. All rights reserved.

  14. Echo-waveform classification using model and model free techniques: Experimental study results from central western continental shelf of India

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Navelkar, G.S.; Desai, R.G.P.; Janakiraman, G.; Mahale, V.; Fernandes, W.A.; Rao, N.

    seafloor of India, but unable to provide a suitable means for seafloor classification. This paper also suggests a hybrid artificial neural network (ANN) architecture i.e. Learning Vector Quantisation (LVQ) for seafloor classification. An analysis...

  15. Comparison of the applicability of neural networks and cluster classification methods on the example company's financial situation

    Directory of Open Access Journals (Sweden)

    Oldřich Trenz

    2010-01-01

    Full Text Available The paper is focused on comparing the classification ability of the model with self-learning neutral network and methods from cluster analysis. The emphasis is particularly on the comparison of different approaches to a specific application example of the commitment, the classification of then financial situation. The aim is to critically evaluate different approaches at the level of application and deployment options.The verify the classification capability of the different approaches were used financial data from the database „Credit Info“, in particular data describing the financial situation of the two hundred eleven farms of homogeneous and uniform primary field.Input data were from the methods used, modified and evaluated by appropriate methodology. Found the final solution showed that the used approaches do not show significant differences, and they can say that they are equivalent. Based on this finding can formulate the conclusion that the approach of artificial intelligence (self-learning neural network is as effective as a partial methods in the field of cluster analysis. In both cases, these approaches can be an invaluable tool in decision making.When the financial situation is evaluated by the expert, the calculation of liquidity, profitability and other financial indicators are making some simplification. In this respect, neural networks perform better, since these simplifications in them selves are not natively included. They can better assess and somewhat ambiguous cases, including businesses with undefined financial situation, the so-called data in the border region. In this respect, support and representation of the graphical layout of the resulting situation sorted out objects using software implemented neural network model.

  16. SUSTAIN: a network model of category learning.

    Science.gov (United States)

    Love, Bradley C; Medin, Douglas L; Gureckis, Todd M

    2004-04-01

    SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

  17. A Dirichlet process mixture model for brain MRI tissue classification.

    Science.gov (United States)

    Ferreira da Silva, Adelino R

    2007-04-01

    Accurate classification of magnetic resonance images according to tissue type or region of interest has become a critical requirement in diagnosis, treatment planning, and cognitive neuroscience. Several authors have shown that finite mixture models give excellent results in the automated segmentation of MR images of the human normal brain. However, performance and robustness of finite mixture models deteriorate when the models have to deal with a variety of anatomical structures. In this paper, we propose a nonparametric Bayesian model for tissue classification of MR images of the brain. The model, known as Dirichlet process mixture model, uses Dirichlet process priors to overcome the limitations of current parametric finite mixture models. To validate the accuracy and robustness of our method we present the results of experiments carried out on simulated MR brain scans, as well as on real MR image data. The results are compared with similar results from other well-known MRI segmentation methods.

  18. Dimensionality-varied convolutional neural network for spectral-spatial classification of hyperspectral data

    Science.gov (United States)

    Liu, Wanjun; Liang, Xuejian; Qu, Haicheng

    2017-11-01

    Hyperspectral image (HSI) classification is one of the most popular topics in remote sensing community. Traditional and deep learning-based classification methods were proposed constantly in recent years. In order to improve the classification accuracy and robustness, a dimensionality-varied convolutional neural network (DVCNN) was proposed in this paper. DVCNN was a novel deep architecture based on convolutional neural network (CNN). The input of DVCNN was a set of 3D patches selected from HSI which contained spectral-spatial joint information. In the following feature extraction process, each patch was transformed into some different 1D vectors by 3D convolution kernels, which were able to extract features from spectral-spatial data. The rest of DVCNN was about the same as general CNN and processed 2D matrix which was constituted by by all 1D data. So that the DVCNN could not only extract more accurate and rich features than CNN, but also fused spectral-spatial information to improve classification accuracy. Moreover, the robustness of network on water-absorption bands was enhanced in the process of spectral-spatial fusion by 3D convolution, and the calculation was simplified by dimensionality varied convolution. Experiments were performed on both Indian Pines and Pavia University scene datasets, and the results showed that the classification accuracy of DVCNN improved by 32.87% on Indian Pines and 19.63% on Pavia University scene than spectral-only CNN. The maximum accuracy improvement of DVCNN achievement was 13.72% compared with other state-of-the-art HSI classification methods, and the robustness of DVCNN on water-absorption bands noise was demonstrated.

  19. Do pre-trained deep learning models improve computer-aided classification of digital mammograms?

    Science.gov (United States)

    Aboutalib, Sarah S.; Mohamed, Aly A.; Zuley, Margarita L.; Berg, Wendie A.; Luo, Yahong; Wu, Shandong

    2018-02-01

    Digital mammography screening is an important exam for the early detection of breast cancer and reduction in mortality. False positives leading to high recall rates, however, results in unnecessary negative consequences to patients and health care systems. In order to better aid radiologists, computer-aided tools can be utilized to improve distinction between image classifications and thus potentially reduce false recalls. The emergence of deep learning has shown promising results in the area of biomedical imaging data analysis. This study aimed to investigate deep learning and transfer learning methods that can improve digital mammography classification performance. In particular, we evaluated the effect of pre-training deep learning models with other imaging datasets in order to boost classification performance on a digital mammography dataset. Two types of datasets were used for pre-training: (1) a digitized film mammography dataset, and (2) a very large non-medical imaging dataset. By using either of these datasets to pre-train the network initially, and then fine-tuning with the digital mammography dataset, we found an increase in overall classification performance in comparison to a model without pre-training, with the very large non-medical dataset performing the best in improving the classification accuracy.

  20. A Classification of PLC Models and Applications

    NARCIS (Netherlands)

    Mader, Angelika H.; Boel, R.; Stremersch, G.

    In the past years there is an increasing interest in analysing PLC applications with formal methods. The first step to this end is to get formal models of PLC applications. Meanwhile, various models for PLCs have already been introduced in the literature. In our paper we discuss several

  1. Network model of security system

    Directory of Open Access Journals (Sweden)

    Adamczyk Piotr

    2016-01-01

    Full Text Available The article presents the concept of building a network security model and its application in the process of risk analysis. It indicates the possibility of a new definition of the role of the network models in the safety analysis. Special attention was paid to the development of the use of an algorithm describing the process of identifying the assets, vulnerability and threats in a given context. The aim of the article is to present how this algorithm reduced the complexity of the problem by eliminating from the base model these components that have no links with others component and as a result and it was possible to build a real network model corresponding to reality.

  2. Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery

    Directory of Open Access Journals (Sweden)

    Xi Gong

    2018-03-01

    Full Text Available Remote sensing (RS scene classification is important for RS imagery semantic interpretation. Although tremendous strides have been made in RS scene classification, one of the remaining open challenges is recognizing RS scenes in low quality variance (e.g., various scales and noises. This paper proposes a deep salient feature based anti-noise transfer network (DSFATN method that effectively enhances and explores the high-level features for RS scene classification in different scales and noise conditions. In DSFATN, a novel discriminative deep salient feature (DSF is introduced by saliency-guided DSF extraction, which conducts a patch-based visual saliency (PBVS algorithm using “visual attention” mechanisms to guide pre-trained CNNs for producing the discriminative high-level features. Then, an anti-noise network is proposed to learn and enhance the robust and anti-noise structure information of RS scene by directly propagating the label information to fully-connected layers. A joint loss is used to minimize the anti-noise network by integrating anti-noise constraint and a softmax classification loss. The proposed network architecture can be easily trained with a limited amount of training data. The experiments conducted on three different scale RS scene datasets show that the DSFATN method has achieved excellent performance and great robustness in different scales and noise conditions. It obtains classification accuracy of 98.25%, 98.46%, and 98.80%, respectively, on the UC Merced Land Use Dataset (UCM, the Google image dataset of SIRI-WHU, and the SAT-6 dataset, advancing the state-of-the-art substantially.

  3. Comparison and classification of all-optical CDMA systems for future telecommunication networks

    Science.gov (United States)

    Iversen, Kay; Hampicke, Dirk

    1995-12-01

    This paper shows the state of the art in fiber optical code-division multiple-access (CDMA). Recent work in this area for both, systems and sequences is reviewed and analyzed. For that purpose a classification of systems, corresponding to the manner of signal processing and a classification of known (0,1)-sequences are presented. It is shown that due to the limits by currently available device technology especially two techniques are promising for implementation in broadband telecommunication networks: spectral encoding with integrated optical filters and CDMA in combination with wavelength multiple access schemes. Further an overview about some important experiments in this field is given.

  4. Current approaches to gene regulatory network modelling

    Directory of Open Access Journals (Sweden)

    Brazma Alvis

    2007-09-01

    Full Text Available Abstract Many different approaches have been developed to model and simulate gene regulatory networks. We proposed the following categories for gene regulatory network models: network parts lists, network topology models, network control logic models, and dynamic models. Here we will describe some examples for each of these categories. We will study the topology of gene regulatory networks in yeast in more detail, comparing a direct network derived from transcription factor binding data and an indirect network derived from genome-wide expression data in mutants. Regarding the network dynamics we briefly describe discrete and continuous approaches to network modelling, then describe a hybrid model called Finite State Linear Model and demonstrate that some simple network dynamics can be simulated in this model.

  5. Multi-agent Negotiation Mechanisms for Statistical Target Classification in Wireless Multimedia Sensor Networks

    Directory of Open Access Journals (Sweden)

    Sheng Wang

    2007-10-01

    Full Text Available The recent availability of low cost and miniaturized hardware has allowedwireless sensor networks (WSNs to retrieve audio and video data in real worldapplications, which has fostered the development of wireless multimedia sensor networks(WMSNs. Resource constraints and challenging multimedia data volume makedevelopment of efficient algorithms to perform in-network processing of multimediacontents imperative. This paper proposes solving problems in the domain of WMSNs fromthe perspective of multi-agent systems. The multi-agent framework enables flexible networkconfiguration and efficient collaborative in-network processing. The focus is placed ontarget classification in WMSNs where audio information is retrieved by microphones. Todeal with the uncertainties related to audio information retrieval, the statistical approachesof power spectral density estimates, principal component analysis and Gaussian processclassification are employed. A multi-agent negotiation mechanism is specially developed toefficiently utilize limited resources and simultaneously enhance classification accuracy andreliability. The negotiation is composed of two phases, where an auction based approach isfirst exploited to allocate the classification task among the agents and then individual agentdecisions are combined by the committee decision mechanism. Simulation experiments withreal world data are conducted and the results show that the proposed statistical approachesand negotiation mechanism not only reduce memory and computation requi

  6. Recurrent neural networks for breast lesion classification based on DCE-MRIs

    Science.gov (United States)

    Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

    2018-02-01

    Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

  7. Defect detection and classification of galvanized stamping parts based on fully convolution neural network

    Science.gov (United States)

    Xiao, Zhitao; Leng, Yanyi; Geng, Lei; Xi, Jiangtao

    2018-04-01

    In this paper, a new convolution neural network method is proposed for the inspection and classification of galvanized stamping parts. Firstly, all workpieces are divided into normal and defective by image processing, and then the defective workpieces extracted from the region of interest (ROI) area are input to the trained fully convolutional networks (FCN). The network utilizes an end-to-end and pixel-to-pixel training convolution network that is currently the most advanced technology in semantic segmentation, predicts result of each pixel. Secondly, we mark the different pixel values of the workpiece, defect and background for the training image, and use the pixel value and the number of pixels to realize the recognition of the defects of the output picture. Finally, the defect area's threshold depended on the needs of the project is set to achieve the specific classification of the workpiece. The experiment results show that the proposed method can successfully achieve defect detection and classification of galvanized stamping parts under ordinary camera and illumination conditions, and its accuracy can reach 99.6%. Moreover, it overcomes the problem of complex image preprocessing and difficult feature extraction and performs better adaptability.

  8. HEART ABNORMALITY CLASSIFICATIONS USING FOURIER TRANSFORMS METHOD AND NEURAL NETWORKS

    Directory of Open Access Journals (Sweden)

    Endah Purwanti

    2014-05-01

    Full Text Available Health problems with cardiovascular system disorder are still ranked high globally. One way to detect abnormalities in the cardiovascular system especially in the heart is through the electrocardiogram (ECG reading. However, reading ECG recording needs experience and expertise, software-based neural networks has designed to help identify any abnormalities ofthe heart through electrocardiogram digital image. This image is processed using image processing methods to obtain ordinate chart which representing the heart’s electrical potential. Feature extraction using Fourier transforms which are divided into several numbers of coefficients. As the software input, Fourier transforms coefficient have been normalized. Output of this software is divided into three classes, namely heart with atrial fibrillation, coronary heart disease and normal. Maximum accuracy rate ofthis software is 95.45%, with the distribution of the Fourier transform coefficients 1/8 and number of nodes 5, while minimum accuracy rate of this software at least 68.18% by distribution of the Fourier transform coefficients 1/32 and the number of nodes 32. Overall result accuracy rate of this software has an average of86.05% and standard deviation of7.82.

  9. Bayesian Recurrent Neural Network for Language Modeling.

    Science.gov (United States)

    Chien, Jen-Tzung; Ku, Yuan-Chu

    2016-02-01

    A language model (LM) is calculated as the probability of a word sequence that provides the solution to word prediction for a variety of information systems. A recurrent neural network (RNN) is powerful to learn the large-span dynamics of a word sequence in the continuous space. However, the training of the RNN-LM is an ill-posed problem because of too many parameters from a large dictionary size and a high-dimensional hidden layer. This paper presents a Bayesian approach to regularize the RNN-LM and apply it for continuous speech recognition. We aim to penalize the too complicated RNN-LM by compensating for the uncertainty of the estimated model parameters, which is represented by a Gaussian prior. The objective function in a Bayesian classification network is formed as the regularized cross-entropy error function. The regularized model is constructed not only by calculating the regularized parameters according to the maximum a posteriori criterion but also by estimating the Gaussian hyperparameter by maximizing the marginal likelihood. A rapid approximation to a Hessian matrix is developed to implement the Bayesian RNN-LM (BRNN-LM) by selecting a small set of salient outer-products. The proposed BRNN-LM achieves a sparser model than the RNN-LM. Experiments on different corpora show the robustness of system performance by applying the rapid BRNN-LM under different conditions.

  10. Target-Centric Network Modeling

    DEFF Research Database (Denmark)

    Mitchell, Dr. William L.; Clark, Dr. Robert M.

    In Target-Centric Network Modeling: Case Studies in Analyzing Complex Intelligence Issues, authors Robert Clark and William Mitchell take an entirely new approach to teaching intelligence analysis. Unlike any other book on the market, it offers case study scenarios using actual intelligence...... reporting formats, along with a tested process that facilitates the production of a wide range of analytical products for civilian, military, and hybrid intelligence environments. Readers will learn how to perform the specific actions of problem definition modeling, target network modeling......, and collaborative sharing in the process of creating a high-quality, actionable intelligence product. The case studies reflect the complexity of twenty-first century intelligence issues by dealing with multi-layered target networks that cut across political, economic, social, technological, and military issues...

  11. Habitat classification modelling with incomplete data: Pushing the habitat envelope

    Science.gov (United States)

    Phoebe L. Zarnetske; Thomas C. Edwards; Gretchen G. Moisen

    2007-01-01

    Habitat classification models (HCMs) are invaluable tools for species conservation, land-use planning, reserve design, and metapopulation assessments, particularly at broad spatial scales. However, species occurrence data are often lacking and typically limited to presence points at broad scales. This lack of absence data precludes the use of many statistical...

  12. Modeling and evaluating repeatability and reproducibility of ordinal classifications

    NARCIS (Netherlands)

    de Mast, J.; van Wieringen, W.N.

    2010-01-01

    This paper argues that currently available methods for the assessment of the repeatability and reproducibility of ordinal classifications are not satisfactory. The paper aims to study whether we can modify a class of models from Item Response Theory, well established for the study of the reliability

  13. A Multi-Dimensional Classification Model for Scientific Workflow Characteristics

    Energy Technology Data Exchange (ETDEWEB)

    Ramakrishnan, Lavanya; Plale, Beth

    2010-04-05

    Workflows have been used to model repeatable tasks or operations in manufacturing, business process, and software. In recent years, workflows are increasingly used for orchestration of science discovery tasks that use distributed resources and web services environments through resource models such as grid and cloud computing. Workflows have disparate re uirements and constraints that affects how they might be managed in distributed environments. In this paper, we present a multi-dimensional classification model illustrated by workflow examples obtained through a survey of scientists from different domains including bioinformatics and biomedical, weather and ocean modeling, astronomy detailing their data and computational requirements. The survey results and classification model contribute to the high level understandingof scientific workflows.

  14. Structural classification and a binary structure model for superconductors

    Institute of Scientific and Technical Information of China (English)

    Dong Cheng

    2006-01-01

    Based on structural and bonding features, a new classification scheme of superconductors is proposed to classify conductors can be partitioned into two parts, a superconducting active component and a supplementary component.Partially metallic covalent bonding is found to be a common feature in all superconducting active components, and the electron states of the atoms in the active components usually make a dominant contribution to the energy band near the Fermi surface. Possible directions to explore new superconductors are discussed based on the structural classification and the binary structure model.

  15. Hyperspectral Image Classification With Markov Random Fields and a Convolutional Neural Network

    Science.gov (United States)

    Cao, Xiangyong; Zhou, Feng; Xu, Lin; Meng, Deyu; Xu, Zongben; Paisley, John

    2018-05-01

    This paper presents a new supervised classification algorithm for remotely sensed hyperspectral image (HSI) which integrates spectral and spatial information in a unified Bayesian framework. First, we formulate the HSI classification problem from a Bayesian perspective. Then, we adopt a convolutional neural network (CNN) to learn the posterior class distributions using a patch-wise training strategy to better use the spatial information. Next, spatial information is further considered by placing a spatial smoothness prior on the labels. Finally, we iteratively update the CNN parameters using stochastic gradient decent (SGD) and update the class labels of all pixel vectors using an alpha-expansion min-cut-based algorithm. Compared with other state-of-the-art methods, the proposed classification method achieves better performance on one synthetic dataset and two benchmark HSI datasets in a number of experimental settings.

  16. Multi-National Banknote Classification Based on Visible-light Line Sensor and Convolutional Neural Network.

    Science.gov (United States)

    Pham, Tuyen Danh; Lee, Dong Eun; Park, Kang Ryoung

    2017-07-08

    Automatic recognition of banknotes is applied in payment facilities, such as automated teller machines (ATMs) and banknote counters. Besides the popular approaches that focus on studying the methods applied to various individual types of currencies, there have been studies conducted on simultaneous classification of banknotes from multiple countries. However, their methods were conducted with limited numbers of banknote images, national currencies, and denominations. To address this issue, we propose a multi-national banknote classification method based on visible-light banknote images captured by a one-dimensional line sensor and classified by a convolutional neural network (CNN) considering the size information of each denomination. Experiments conducted on the combined banknote image database of six countries with 62 denominations gave a classification accuracy of 100%, and results show that our proposed algorithm outperforms previous methods.

  17. Identifying colon cancer risk modules with better classification performance based on human signaling network.

    Science.gov (United States)

    Qu, Xiaoli; Xie, Ruiqiang; Chen, Lina; Feng, Chenchen; Zhou, Yanyan; Li, Wan; Huang, Hao; Jia, Xu; Lv, Junjie; He, Yuehan; Du, Youwen; Li, Weiguo; Shi, Yuchen; He, Weiming

    2014-10-01

    Identifying differences between normal and tumor samples from a modular perspective may help to improve our understanding of the mechanisms responsible for colon cancer. Many cancer studies have shown that signaling transduction and biological pathways are disturbed in disease states, and expression profiles can distinguish variations in diseases. In this study, we integrated a weighted human signaling network and gene expression profiles to select risk modules associated with tumor conditions. Risk modules as classification features by our method had a better classification performance than other methods, and one risk module for colon cancer had a good classification performance for distinguishing between normal/tumor samples and between tumor stages. All genes in the module were annotated to the biological process of positive regulation of cell proliferation, and were highly associated with colon cancer. These results suggested that these genes might be the potential risk genes for colon cancer. Copyright © 2013. Published by Elsevier Inc.

  18. 基于BP神经网络的音乐情感分类及评价模型%Music emotion classification and evaluation model based on BP neural network

    Institute of Scientific and Technical Information of China (English)

    赵伟

    2015-01-01

    针对多音轨MIDI文件,提出一种多音轨MIDI音乐主旋律识别方法,通过对表征音乐旋律特征的音高、音长、音色、速度和力度5个特征向量的提取,构建基于BP神经网络的情感模型,并且用200首不同情感特征的歌曲对其进行训练和验证。实验结果显示取得了较好的效果。%The audio track of music melody includes a lot of useful information of music melody, which is the basic of music character recognition and also the premise work in the design of the performance plan of music foundation .Five eigenvectors:pitch, length, tone tempo and strength are extracted for the expression of music melody, by which, the basic music character recognition system can be set up. A emotion model is formed by using BP neural network.200 songs with different emotional characteristic songs will be used as the sample data for the training and validation of the neural network. The results of validation shows the effectiveness of the emotion model.

  19. Classification of Networks in Higher Education: A Marketing Analysis of the Club of Ten (Russia

    Directory of Open Access Journals (Sweden)

    Irina V.

    2018-03-01

    Full Text Available Introduction: the networking as a development practice in business has not yet become widespread. Moreover, there are very few studies of network interactions in the field of science and education. Advances in marketing evaluation of network entities are very rare. The goal of this article is to develop methodological criteria for such an assessment. These methods were tested on findings from the network partnership established by federal universities in Russia. Materials and Methods: to study and generalise real-world experience, a case study method was used, which the authors understand as an empirical research method aimed at studying phenomena in real time and in the context of real life. Results: the authors proposed a comprehensive methodology for estimation of networks. The application of this method of analysis enabled identification of the key problems and barriers to the implementation of the project. One of the main problems is the lack of marketing analysis, lack of understanding of its target audience, and, accordingly, the lack of a transparent vision of development. Besides, the authors have developed a classification of network partnerships. Тhe analysis empowers classification of the network of Russian universities as an inter-organisational polycentric partnership of a quasi-integration type, based on a neoclassical contract with relational elements. The analysis of the network development has revealed significant deviations of the results from the initially claimed ones. Discussion and Conclusions: the theoretical significance of the work consists in the application of the network theory to an atypical object for the economic theory, i.e. the analysis of the sphere of higher education. Practical significance lies in the possibility of application of results obtained through real projects in real-time mode. The results of the study are applicable to educational systems for practically all countries with a transition type of

  20. A Hierarchical Feature Extraction Model for Multi-Label Mechanical Patent Classification

    Directory of Open Access Journals (Sweden)

    Jie Hu

    2018-01-01

    Full Text Available Various studies have focused on feature extraction methods for automatic patent classification in recent years. However, most of these approaches are based on the knowledge from experts in related domains. Here we propose a hierarchical feature extraction model (HFEM for multi-label mechanical patent classification, which is able to capture both local features of phrases as well as global and temporal semantics. First, a n-gram feature extractor based on convolutional neural networks (CNNs is designed to extract salient local lexical-level features. Next, a long dependency feature extraction model based on the bidirectional long–short-term memory (BiLSTM neural network model is proposed to capture sequential correlations from higher-level sequence representations. Then the HFEM algorithm and its hierarchical feature extraction architecture are detailed. We establish the training, validation and test datasets, containing 72,532, 18,133, and 2679 mechanical patent documents, respectively, and then check the performance of HFEMs. Finally, we compared the results of the proposed HFEM and three other single neural network models, namely CNN, long–short-term memory (LSTM, and BiLSTM. The experimental results indicate that our proposed HFEM outperforms the other compared models in both precision and recall.

  1. Non-invasive classification of gas–liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network

    International Nuclear Information System (INIS)

    Abbagoni, Baba Musa; Yeung, Hoi

    2016-01-01

    The identification of flow pattern is a key issue in multiphase flow which is encountered in the petrochemical industry. It is difficult to identify the gas–liquid flow regimes objectively with the gas–liquid two-phase flow. This paper presents the feasibility of a clamp-on instrument for an objective flow regime classification of two-phase flow using an ultrasonic Doppler sensor and an artificial neural network, which records and processes the ultrasonic signals reflected from the two-phase flow. Experimental data is obtained on a horizontal test rig with a total pipe length of 21 m and 5.08 cm internal diameter carrying air-water two-phase flow under slug, elongated bubble, stratified-wavy and, stratified flow regimes. Multilayer perceptron neural networks (MLPNNs) are used to develop the classification model. The classifier requires features as an input which is representative of the signals. Ultrasound signal features are extracted by applying both power spectral density (PSD) and discrete wavelet transform (DWT) methods to the flow signals. A classification scheme of ‘1-of-C coding method for classification’ was adopted to classify features extracted into one of four flow regime categories. To improve the performance of the flow regime classifier network, a second level neural network was incorporated by using the output of a first level networks feature as an input feature. The addition of the two network models provided a combined neural network model which has achieved a higher accuracy than single neural network models. Classification accuracies are evaluated in the form of both the PSD and DWT features. The success rates of the two models are: (1) using PSD features, the classifier missed 3 datasets out of 24 test datasets of the classification and scored 87.5% accuracy; (2) with the DWT features, the network misclassified only one data point and it was able to classify the flow patterns up to 95.8% accuracy. This approach has demonstrated the

  2. Non-invasive classification of gas-liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network

    Science.gov (United States)

    Musa Abbagoni, Baba; Yeung, Hoi

    2016-08-01

    The identification of flow pattern is a key issue in multiphase flow which is encountered in the petrochemical industry. It is difficult to identify the gas-liquid flow regimes objectively with the gas-liquid two-phase flow. This paper presents the feasibility of a clamp-on instrument for an objective flow regime classification of two-phase flow using an ultrasonic Doppler sensor and an artificial neural network, which records and processes the ultrasonic signals reflected from the two-phase flow. Experimental data is obtained on a horizontal test rig with a total pipe length of 21 m and 5.08 cm internal diameter carrying air-water two-phase flow under slug, elongated bubble, stratified-wavy and, stratified flow regimes. Multilayer perceptron neural networks (MLPNNs) are used to develop the classification model. The classifier requires features as an input which is representative of the signals. Ultrasound signal features are extracted by applying both power spectral density (PSD) and discrete wavelet transform (DWT) methods to the flow signals. A classification scheme of ‘1-of-C coding method for classification’ was adopted to classify features extracted into one of four flow regime categories. To improve the performance of the flow regime classifier network, a second level neural network was incorporated by using the output of a first level networks feature as an input feature. The addition of the two network models provided a combined neural network model which has achieved a higher accuracy than single neural network models. Classification accuracies are evaluated in the form of both the PSD and DWT features. The success rates of the two models are: (1) using PSD features, the classifier missed 3 datasets out of 24 test datasets of the classification and scored 87.5% accuracy; (2) with the DWT features, the network misclassified only one data point and it was able to classify the flow patterns up to 95.8% accuracy. This approach has demonstrated the

  3. Classification of Weed Species Using Artificial Neural Networks Based on Color Leaf Texture Feature

    Science.gov (United States)

    Li, Zhichen; An, Qiu; Ji, Changying

    The potential impact of herbicide utilization compel people to use new method of weed control. Selective herbicide application is optimal method to reduce herbicide usage while maintain weed control. The key of selective herbicide is how to discriminate weed exactly. The HIS color co-occurrence method (CCM) texture analysis techniques was used to extract four texture parameters: Angular second moment (ASM), Entropy(E), Inertia quadrature (IQ), and Inverse difference moment or local homogeneity (IDM).The weed species selected for studying were Arthraxon hispidus, Digitaria sanguinalis, Petunia, Cyperus, Alternanthera Philoxeroides and Corchoropsis psilocarpa. The software of neuroshell2 was used for designing the structure of the neural network, training and test the data. It was found that the 8-40-1 artificial neural network provided the best classification performance and was capable of classification accuracies of 78%.

  4. Combined principal component preprocessing and n-tuple neural networks for improved classification

    DEFF Research Database (Denmark)

    Høskuldsson, Agnar; Linneberg, Christian

    2000-01-01

    We present a combined principal component analysis/neural network scheme for classification. The data used to illustrate the method consist of spectral fluorescence recordings from seven different production facilities, and the task is to relate an unknown sample to one of these seven factories....... The data are first preprocessed by performing an individual principal component analysis on each of the seven groups of data. The components found are then used for classifying the data, but instead of making a single multiclass classifier, we follow the ideas of turning a multiclass problem into a number...... of two-class problems. For each possible pair of classes we further apply a transformation to the calculated principal components in order to increase the separation between the classes. Finally we apply the so-called n-tuple neural network to the transformed data in order to give the classification...

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

    Directory of Open Access Journals (Sweden)

    Zhi He

    2017-10-01

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

  6. Semantic Segmentation of Convolutional Neural Network for Supervised Classification of Multispectral Remote Sensing

    Science.gov (United States)

    Xue, L.; Liu, C.; Wu, Y.; Li, H.

    2018-04-01

    Semantic segmentation is a fundamental research in remote sensing image processing. Because of the complex maritime environment, the classification of roads, vegetation, buildings and water from remote Sensing Imagery is a challenging task. Although the neural network has achieved excellent performance in semantic segmentation in the last years, there are a few of works using CNN for ground object segmentation and the results could be further improved. This paper used convolution neural network named U-Net, its structure has a contracting path and an expansive path to get high resolution output. In the network , We added BN layers, which is more conducive to the reverse pass. Moreover, after upsampling convolution , we add dropout layers to prevent overfitting. They are promoted to get more precise segmentation results. To verify this network architecture, we used a Kaggle dataset. Experimental results show that U-Net achieved good performance compared with other architectures, especially in high-resolution remote sensing imagery.

  7. Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification

    OpenAIRE

    Hwang, Kyuyeon; Sung, Wonyong

    2015-01-01

    Connectionist temporal classification (CTC) based supervised sequence training of recurrent neural networks (RNNs) has shown great success in many machine learning areas including end-to-end speech and handwritten character recognition. For the CTC training, however, it is required to unroll (or unfold) the RNN by the length of an input sequence. This unrolling requires a lot of memory and hinders a small footprint implementation of online learning or adaptation. Furthermore, the length of tr...

  8. A Comparative Classification of Wheat Grains for Artificial Neural Network and Extreme Learning Machine

    OpenAIRE

    ASLAN, Muhammet Fatih; SABANCI, Kadir; YİĞİT, Enes; KAYABAŞI, Ahmet; TOKTAŞ, Abdurrahim; DUYSAK, Hüseyin

    2018-01-01

    In this study, classification of two types of wheat grainsinto bread and durum was carried out. The species of wheat grains in thisdataset are bread and durum and these species have equal samples in the datasetas 100 instances. Seven features, including width, height, area, perimeter,roundness, width and perimeter/area were extracted from each wheat grains. Classificationwas separately conducted by Artificial Neural Network (ANN) and Extreme Learning Machine (ELM)artificial intelligence techn...

  9. EEG signal classification based on artificial neural networks and amplitude spectra features

    Science.gov (United States)

    Chojnowski, K.; FrÄ czek, J.

    BCI (called Brain-Computer Interface) is an interface that allows direct communication between human brain and an external device. It bases on EEG signal collection, processing and classification. In this paper a complete BCI system is presented which classifies EEG signal using artificial neural networks. For this purpose we used a multi-layered perceptron architecture trained with the RProp algorithm. Furthermore a simple multi-threaded method for automatic network structure optimizing was shown. We presented the results of our system in the opening and closing eyes recognition task. We also showed how our system could be used for controlling devices basing on imaginary hand movements.

  10. 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.

  11. Neural Networks for the Classification of Building Use from Street-View Imagery

    Science.gov (United States)

    Laupheimer, D.; Tutzauer, P.; Haala, N.; Spicker, M.

    2018-05-01

    Within this paper we propose an end-to-end approach for classifying terrestrial images of building facades into five different utility classes (commercial, hybrid, residential, specialUse, underConstruction) by using Convolutional Neural Networks (CNNs). For our examples we use images provided by Google Street View. These images are automatically linked to a coarse city model, including the outlines of the buildings as well as their respective use classes. By these means an extensive dataset is available for training and evaluation of our Deep Learning pipeline. The paper describes the implemented end-to-end approach for classifying street-level images of building facades and discusses our experiments with various CNNs. In addition to the classification results, so-called Class Activation Maps (CAMs) are evaluated. These maps give further insights into decisive facade parts that are learned as features during the training process. Furthermore, they can be used for the generation of abstract presentations which facilitate the comprehension of semantic image content. The abstract representations are a result of the stippling method, an importance-based image rendering.

  12. Indian Classical Dance Action Identification and Classification with Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    P. V. V. Kishore

    2018-01-01

    Full Text Available Extracting and recognizing complex human movements from unconstrained online/offline video sequence is a challenging task in computer vision. This paper proposes the classification of Indian classical dance actions using a powerful artificial intelligence tool: convolutional neural networks (CNN. In this work, human action recognition on Indian classical dance videos is performed on recordings from both offline (controlled recording and online (live performances, YouTube data. The offline data is created with ten different subjects performing 200 familiar dance mudras/poses from different Indian classical dance forms under various background environments. The online dance data is collected from YouTube for ten different subjects. Each dance pose is occupied for 60 frames or images in a video in both the cases. CNN training is performed with 8 different sample sizes, each consisting of multiple sets of subjects. The remaining 2 samples are used for testing the trained CNN. Different CNN architectures were designed and tested with our data to obtain a better accuracy in recognition. We achieved a 93.33% recognition rate compared to other classifier models reported on the same dataset.

  13. HEp-2 cell image classification method based on very deep convolutional networks with small datasets

    Science.gov (United States)

    Lu, Mengchi; Gao, Long; Guo, Xifeng; Liu, Qiang; Yin, Jianping

    2017-07-01

    Human Epithelial-2 (HEp-2) cell images staining patterns classification have been widely used to identify autoimmune diseases by the anti-Nuclear antibodies (ANA) test in the Indirect Immunofluorescence (IIF) protocol. Because manual test is time consuming, subjective and labor intensive, image-based Computer Aided Diagnosis (CAD) systems for HEp-2 cell classification are developing. However, methods proposed recently are mostly manual features extraction with low accuracy. Besides, the scale of available benchmark datasets is small, which does not exactly suitable for using deep learning methods. This issue will influence the accuracy of cell classification directly even after data augmentation. To address these issues, this paper presents a high accuracy automatic HEp-2 cell classification method with small datasets, by utilizing very deep convolutional networks (VGGNet). Specifically, the proposed method consists of three main phases, namely image preprocessing, feature extraction and classification. Moreover, an improved VGGNet is presented to address the challenges of small-scale datasets. Experimental results over two benchmark datasets demonstrate that the proposed method achieves superior performance in terms of accuracy compared with existing methods.

  14. APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN CLASSIFICATION OF HIGH RESOLUTION AGRICULTURAL REMOTE SENSING IMAGES

    Directory of Open Access Journals (Sweden)

    C. Yao

    2017-09-01

    Full Text Available With the rapid development of Precision Agriculture (PA promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN. For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

  15. Seafloor classification using artificial neural network architecture from central western continental shelf of India

    Science.gov (United States)

    Mahale, Vasudev; Chakraborty, Bishwajit; Navelkar, Gajanan S.; Prabhu Desai, R. G.

    2005-04-01

    Seafloor classification studies are carried out at the central western continental shelf of India employing two frequency normal incidence single beam echo-sounder backscatter data. Echo waveform data from different seafloor sediment areas are utilized for present study. Three artificial neural network (ANN) architectures, e.g., Self-Organization Feature Maps (SOFM), Multi-Layer Perceptron (MLP), and Learning Vector Quantization (LVQ) are applied for seafloor classifications. In case of MLP, features are extracted from the received echo signal, on the basis of which, classification is carried out. In the case of the SOFM, a simple moving average echo waveform pre-processing technique is found to yield excellent classification results. Finally, LVQ, which is known as ANN of hybrid architecture is found to be the efficient seafloor classifier especially from the point of view of the real-time application. The simultaneously acquired sediment sample, multi-beam bathymetry and side scan sonar and echo waveform based seafloor classifications results are indicative of the depositional (inner shelf), non-depositional or erosion (outer shelf) environment and combination of both in the transition zone. [Work supported by DIT.

  16. Lidar-based individual tree species classification using convolutional neural network

    Science.gov (United States)

    Mizoguchi, Tomohiro; Ishii, Akira; Nakamura, Hiroyuki; Inoue, Tsuyoshi; Takamatsu, Hisashi

    2017-06-01

    Terrestrial lidar is commonly used for detailed documentation in the field of forest inventory investigation. Recent improvements of point cloud processing techniques enabled efficient and precise computation of an individual tree shape parameters, such as breast-height diameter, height, and volume. However, tree species are manually specified by skilled workers to date. Previous works for automatic tree species classification mainly focused on aerial or satellite images, and few works have been reported for classification techniques using ground-based sensor data. Several candidate sensors can be considered for classification, such as RGB or multi/hyper spectral cameras. Above all candidates, we use terrestrial lidar because it can obtain high resolution point cloud in the dark forest. We selected bark texture for the classification criteria, since they clearly represent unique characteristics of each tree and do not change their appearance under seasonable variation and aged deterioration. In this paper, we propose a new method for automatic individual tree species classification based on terrestrial lidar using Convolutional Neural Network (CNN). The key component is the creation step of a depth image which well describe the characteristics of each species from a point cloud. We focus on Japanese cedar and cypress which cover the large part of domestic forest. Our experimental results demonstrate the effectiveness of our proposed method.

  17. Optimal Non-Invasive Fault Classification Model for Packaged Ceramic Tile Quality Monitoring Using MMW Imaging

    Science.gov (United States)

    Agarwal, Smriti; Singh, Dharmendra

    2016-04-01

    Millimeter wave (MMW) frequency has emerged as an efficient tool for different stand-off imaging applications. In this paper, we have dealt with a novel MMW imaging application, i.e., non-invasive packaged goods quality estimation for industrial quality monitoring applications. An active MMW imaging radar operating at 60 GHz has been ingeniously designed for concealed fault estimation. Ceramic tiles covered with commonly used packaging cardboard were used as concealed targets for undercover fault classification. A comparison of computer vision-based state-of-the-art feature extraction techniques, viz, discrete Fourier transform (DFT), wavelet transform (WT), principal component analysis (PCA), gray level co-occurrence texture (GLCM), and histogram of oriented gradient (HOG) has been done with respect to their efficient and differentiable feature vector generation capability for undercover target fault classification. An extensive number of experiments were performed with different ceramic tile fault configurations, viz., vertical crack, horizontal crack, random crack, diagonal crack along with the non-faulty tiles. Further, an independent algorithm validation was done demonstrating classification accuracy: 80, 86.67, 73.33, and 93.33 % for DFT, WT, PCA, GLCM, and HOG feature-based artificial neural network (ANN) classifier models, respectively. Classification results show good capability for HOG feature extraction technique towards non-destructive quality inspection with appreciably low false alarm as compared to other techniques. Thereby, a robust and optimal image feature-based neural network classification model has been proposed for non-invasive, automatic fault monitoring for a financially and commercially competent industrial growth.

  18. 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.

  19. Two-Stage Approach to Image Classification by Deep Neural Networks

    Directory of Open Access Journals (Sweden)

    Ososkov Gennady

    2018-01-01

    Full Text Available The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

  20. Two-Stage Approach to Image Classification by Deep Neural Networks

    Science.gov (United States)

    Ososkov, Gennady; Goncharov, Pavel

    2018-02-01

    The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

  1. A patch-based convolutional neural network for remote sensing image classification.

    Science.gov (United States)

    Sharma, Atharva; Liu, Xiuwen; Yang, Xiaojun; Shi, Di

    2017-11-01

    Availability of accurate land cover information over large areas is essential to the global environment sustainability; digital classification using medium-resolution remote sensing data would provide an effective method to generate the required land cover information. However, low accuracy of existing per-pixel based classification methods for medium-resolution data is a fundamental limiting factor. While convolutional neural networks (CNNs) with deep layers have achieved unprecedented improvements in object recognition applications that rely on fine image structures, they cannot be applied directly to medium-resolution data due to lack of such fine structures. In this paper, considering the spatial relation of a pixel to its neighborhood, we propose a new deep patch-based CNN system tailored for medium-resolution remote sensing data. The system is designed by incorporating distinctive characteristics of medium-resolution data; in particular, the system computes patch-based samples from multidimensional top of atmosphere reflectance data. With a test site from the Florida Everglades area (with a size of 771 square kilometers), the proposed new system has outperformed pixel-based neural network, pixel-based CNN and patch-based neural network by 24.36%, 24.23% and 11.52%, respectively, in overall classification accuracy. By combining the proposed deep CNN and the huge collection of medium-resolution remote sensing data, we believe that much more accurate land cover datasets can be produced over large areas. Copyright © 2017 Elsevier Ltd. All rights reserved.

  2. Sparse Representation Based Binary Hypothesis Model for Hyperspectral Image Classification

    Directory of Open Access Journals (Sweden)

    Yidong Tang

    2016-01-01

    Full Text Available The sparse representation based classifier (SRC and its kernel version (KSRC have been employed for hyperspectral image (HSI classification. However, the state-of-the-art SRC often aims at extended surface objects with linear mixture in smooth scene and assumes that the number of classes is given. Considering the small target with complex background, a sparse representation based binary hypothesis (SRBBH model is established in this paper. In this model, a query pixel is represented in two ways, which are, respectively, by background dictionary and by union dictionary. The background dictionary is composed of samples selected from the local dual concentric window centered at the query pixel. Thus, for each pixel the classification issue becomes an adaptive multiclass classification problem, where only the number of desired classes is required. Furthermore, the kernel method is employed to improve the interclass separability. In kernel space, the coding vector is obtained by using kernel-based orthogonal matching pursuit (KOMP algorithm. Then the query pixel can be labeled by the characteristics of the coding vectors. Instead of directly using the reconstruction residuals, the different impacts the background dictionary and union dictionary have on reconstruction are used for validation and classification. It enhances the discrimination and hence improves the performance.

  3. River network and watershed morphology analysis with potential implications towards basin classification

    Science.gov (United States)

    Bugaets, Andrey; Gartsman, Boris; Bugaets, Nadezhda

    2013-04-01

    process, the energy is dissipated from the system. The rate of energy dissipation is defined as the work that a fluid element needs to perform to overcome friction at the unit area. Appling the product of local slope and watershed area, i.e. calculating the total energy index at the different distance from outlet, one gets the watershed "energy function" E(x). Application results indicate that the proposed method could be used for watersheds classification, regionalization and paleoreconstructions. NASA-SRTM DEM of 3" resolution has been employed to analyze the 24 watersheds within Amur River Basin with area 20-70 thousand km2 (7-8 order). The study was carried out, in particular, to assess the limitation of SRTM DEM data, especially in flat terrains. The study also revealed that some of regularities investigated are described satisfactorily by well-known simplest model of drainage networks, so-called Peano's basin.

  4. Continuum Model for River Networks

    Science.gov (United States)

    Giacometti, Achille; Maritan, Amos; Banavar, Jayanth R.

    1995-07-01

    The effects of erosion, avalanching, and random precipitation are captured in a simple stochastic partial differential equation for modeling the evolution of river networks. Our model leads to a self-organized structured landscape and to abstraction and piracy of the smaller tributaries as the evolution proceeds. An algebraic distribution of the average basin areas and a power law relationship between the drainage basin area and the river length are found.

  5. A strategy learning model for autonomous agents based on classification

    Directory of Open Access Journals (Sweden)

    Śnieżyński Bartłomiej

    2015-09-01

    Full Text Available In this paper we propose a strategy learning model for autonomous agents based on classification. In the literature, the most commonly used learning method in agent-based systems is reinforcement learning. In our opinion, classification can be considered a good alternative. This type of supervised learning can be used to generate a classifier that allows the agent to choose an appropriate action for execution. Experimental results show that this model can be successfully applied for strategy generation even if rewards are delayed. We compare the efficiency of the proposed model and reinforcement learning using the farmer-pest domain and configurations of various complexity. In complex environments, supervised learning can improve the performance of agents much faster that reinforcement learning. If an appropriate knowledge representation is used, the learned knowledge may be analyzed by humans, which allows tracking the learning process

  6. Establishing structure-property correlations and classification of base oils using statistical techniques and artificial neural networks

    International Nuclear Information System (INIS)

    Kapur, G.S.; Sastry, M.I.S.; Jaiswal, A.K.; Sarpal, A.S.

    2004-01-01

    The present paper describes various classification techniques like cluster analysis, principal component (PC)/factor analysis to classify different types of base stocks. The API classification of base oils (Group I-III) has been compared to a more detailed NMR derived chemical compositional and molecular structural parameters based classification in order to point out the similarities of the base oils in the same group and the differences between the oils placed in different groups. The detailed compositional parameters have been generated using 1 H and 13 C nuclear magnetic resonance (NMR) spectroscopic methods. Further, oxidation stability, measured in terms of rotating bomb oxidation test (RBOT) life, of non-conventional base stocks and their blends with conventional base stocks, has been quantitatively correlated with their 1 H NMR and elemental (sulphur and nitrogen) data with the help of multiple linear regression (MLR) and artificial neural networks (ANN) techniques. The MLR based model developed using NMR and elemental data showed a high correlation between the 'measured' and 'estimated' RBOT values for both training (R=0.859) and validation (R=0.880) data sets. The ANN based model, developed using fewer number of input variables (only 1 H NMR data) also showed high correlation between the 'measured' and 'estimated' RBOT values for training (R=0.881), validation (R=0.860) and test (R=0.955) data sets

  7. Multiclass classification of obstructive sleep apnea/hypopnea based on a convolutional neural network from a single-lead electrocardiogram.

    Science.gov (United States)

    Urtnasan, Erdenebayar; Park, Jong-Uk; Lee, Kyoung-Joung

    2018-05-24

    In this paper, we propose a convolutional neural network (CNN)-based deep learning architecture for multiclass classification of obstructive sleep apnea and hypopnea (OSAH) using single-lead electrocardiogram (ECG) recordings. OSAH is the most common sleep-related breathing disorder. Many subjects who suffer from OSAH remain undiagnosed; thus, early detection of OSAH is important. In this study, automatic classification of three classes-normal, hypopnea, and apnea-based on a CNN is performed. An optimal six-layer CNN model is trained on a training dataset (45,096 events) and evaluated on a test dataset (11,274 events). The training set (69 subjects) and test set (17 subjects) were collected from 86 subjects with length of approximately 6 h and segmented into 10 s durations. The proposed CNN model reaches a mean -score of 93.0 for the training dataset and 87.0 for the test dataset. Thus, proposed deep learning architecture achieved a high performance for multiclass classification of OSAH using single-lead ECG recordings. The proposed method can be employed in screening of patients suspected of having OSAH. © 2018 Institute of Physics and Engineering in Medicine.

  8. Application of artificial neural networks to segmentation and classification of topographic profiles of ridge-flank seafloor

    Digital Repository Service at National Institute of Oceanography (India)

    Chakraborty, B.; Lourenco, E.; Kodagali, V.N.; Baracho, J.

    In this paper, we have utilized Artificial Neural Networks (ANN) for seafloor topographic data segmentation and roughness classification using the multibeam- Hydrosweep system (installed onboard ocean research vessel Sagar Kanya) data. Bathymetric...

  9. Music Genre Classification using an Auditory Memory Model

    DEFF Research Database (Denmark)

    Jensen, Kristoffer

    2011-01-01

    Audio feature estimation is potentially improved by including higher- level models. One such model is the Auditory Short Term Memory (STM) model. A new paradigm of audio feature estimation is obtained by adding the influence of notes in the STM. These notes are identified when the perceptual...... results, and an initial experiment with sensory dissonance has been undertaken with good results. The parameters obtained form the auditory memory model, along with the dissonance measure, are shown here to be of interest in genre classification....

  10. Assimilation of a knowledge base and physical models to reduce errors in passive-microwave classifications of sea ice

    Science.gov (United States)

    Maslanik, J. A.; Key, J.

    1992-01-01

    An expert system framework has been developed to classify sea ice types using satellite passive microwave data, an operational classification algorithm, spatial and temporal information, ice types estimated from a dynamic-thermodynamic model, output from a neural network that detects the onset of melt, and knowledge about season and region. The rule base imposes boundary conditions upon the ice classification, modifies parameters in the ice algorithm, determines a `confidence' measure for the classified data, and under certain conditions, replaces the algorithm output with model output. Results demonstrate the potential power of such a system for minimizing overall error in the classification and for providing non-expert data users with a means of assessing the usefulness of the classification results for their applications.

  11. A Classification Methodology and Retrieval Model to Support Software Reuse

    Science.gov (United States)

    1988-01-01

    Dewey Decimal Classification ( DDC 18), an enumerative scheme, occupies 40 pages [Buchanan 19791. Langridge [19731 states that the facets listed in the...sense of historical importance or wide spread use. The schemes are: Dewey Decimal Classification ( DDC ), Universal Decimal Classification (UDC...Classification Systems ..... ..... 2.3.3 Library Classification__- .52 23.3.1 Dewey Decimal Classification -53 2.33.2 Universal Decimal Classification 55 2333

  12. Biological transportation networks: Modeling and simulation

    KAUST Repository

    Albi, Giacomo

    2015-09-15

    We present a model for biological network formation originally introduced by Cai and Hu [Adaptation and optimization of biological transport networks, Phys. Rev. Lett. 111 (2013) 138701]. The modeling of fluid transportation (e.g., leaf venation and angiogenesis) and ion transportation networks (e.g., neural networks) is explained in detail and basic analytical features like the gradient flow structure of the fluid transportation network model and the impact of the model parameters on the geometry and topology of network formation are analyzed. We also present a numerical finite-element based discretization scheme and discuss sample cases of network formation simulations.

  13. Application of Convolution Neural Network to the forecasts of flare classification and occurrence using SOHO MDI data

    Science.gov (United States)

    Park, Eunsu; Moon, Yong-Jae

    2017-08-01

    A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.86 for flare classification and 0.84 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

  14. Network modelling methods for FMRI.

    Science.gov (United States)

    Smith, Stephen M; Miller, Karla L; Salimi-Khorshidi, Gholamreza; Webster, Matthew; Beckmann, Christian F; Nichols, Thomas E; Ramsey, Joseph D; Woolrich, Mark W

    2011-01-15

    There is great interest in estimating brain "networks" from FMRI data. This is often attempted by identifying a set of functional "nodes" (e.g., spatial ROIs or ICA maps) and then conducting a connectivity analysis between the nodes, based on the FMRI timeseries associated with the nodes. Analysis methods range from very simple measures that consider just two nodes at a time (e.g., correlation between two nodes' timeseries) to sophisticated approaches that consider all nodes simultaneously and estimate one global network model (e.g., Bayes net models). Many different methods are being used in the literature, but almost none has been carefully validated or compared for use on FMRI timeseries data. In this work we generate rich, realistic simulated FMRI data for a wide range of underlying networks, experimental protocols and problematic confounds in the data, in order to compare different connectivity estimation approaches. Our results show that in general correlation-based approaches can be quite successful, methods based on higher-order statistics are less sensitive, and lag-based approaches perform very poorly. More specifically: there are several methods that can give high sensitivity to network connection detection on good quality FMRI data, in particular, partial correlation, regularised inverse covariance estimation and several Bayes net methods; however, accurate estimation of connection directionality is more difficult to achieve, though Patel's τ can be reasonably successful. With respect to the various confounds added to the data, the most striking result was that the use of functionally inaccurate ROIs (when defining the network nodes and extracting their associated timeseries) is extremely damaging to network estimation; hence, results derived from inappropriate ROI definition (such as via structural atlases) should be regarded with great caution. Copyright © 2010 Elsevier Inc. All rights reserved.

  15. Classification of teeth in cone-beam CT using deep convolutional neural network.

    Science.gov (United States)

    Miki, Yuma; Muramatsu, Chisako; Hayashi, Tatsuro; Zhou, Xiangrong; Hara, Takeshi; Katsumata, Akitoshi; Fujita, Hiroshi

    2017-01-01

    Dental records play an important role in forensic identification. To this end, postmortem dental findings and teeth conditions are recorded in a dental chart and compared with those of antemortem records. However, most dentists are inexperienced at recording the dental chart for corpses, and it is a physically and mentally laborious task, especially in large scale disasters. Our goal is to automate the dental filing process by using dental x-ray images. In this study, we investigated the application of a deep convolutional neural network (DCNN) for classifying tooth types on dental cone-beam computed tomography (CT) images. Regions of interest (ROIs) including single teeth were extracted from CT slices. Fifty two CT volumes were randomly divided into 42 training and 10 test cases, and the ROIs obtained from the training cases were used for training the DCNN. For examining the sampling effect, random sampling was performed 3 times, and training and testing were repeated. We used the AlexNet network architecture provided in the Caffe framework, which consists of 5 convolution layers, 3 pooling layers, and 2 full connection layers. For reducing the overtraining effect, we augmented the data by image rotation and intensity transformation. The test ROIs were classified into 7 tooth types by the trained network. The average classification accuracy using the augmented training data by image rotation and intensity transformation was 88.8%. Compared with the result without data augmentation, data augmentation resulted in an approximately 5% improvement in classification accuracy. This indicates that the further improvement can be expected by expanding the CT dataset. Unlike the conventional methods, the proposed method is advantageous in obtaining high classification accuracy without the need for precise tooth segmentation. The proposed tooth classification method can be useful in automatic filing of dental charts for forensic identification. Copyright © 2016 Elsevier Ltd

  16. Classification of customer lifetime value models using Markov chain

    Science.gov (United States)

    Permana, Dony; Pasaribu, Udjianna S.; Indratno, Sapto W.; Suprayogi

    2017-10-01

    A firm’s potential reward in future time from a customer can be determined by customer lifetime value (CLV). There are some mathematic methods to calculate it. One method is using Markov chain stochastic model. Here, a customer is assumed through some states. Transition inter the states follow Markovian properties. If we are given some states for a customer and the relationships inter states, then we can make some Markov models to describe the properties of the customer. As Markov models, CLV is defined as a vector contains CLV for a customer in the first state. In this paper we make a classification of Markov Models to calculate CLV. Start from two states of customer model, we make develop in many states models. The development a model is based on weaknesses in previous model. Some last models can be expected to describe how real characters of customers in a firm.

  17. Evolutionary image simplification for lung nodule classification with convolutional neural networks.

    Science.gov (United States)

    Lückehe, Daniel; von Voigt, Gabriele

    2018-05-29

    Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

  18. Group-Based Active Learning of Classification Models.

    Science.gov (United States)

    Luo, Zhipeng; Hauskrecht, Milos

    2017-05-01

    Learning of classification models from real-world data often requires additional human expert effort to annotate the data. However, this process can be rather costly and finding ways of reducing the human annotation effort is critical for this task. The objective of this paper is to develop and study new ways of providing human feedback for efficient learning of classification models by labeling groups of examples. Briefly, unlike traditional active learning methods that seek feedback on individual examples, we develop a new group-based active learning framework that solicits label information on groups of multiple examples. In order to describe groups in a user-friendly way, conjunctive patterns are used to compactly represent groups. Our empirical study on 12 UCI data sets demonstrates the advantages and superiority of our approach over both classic instance-based active learning work, as well as existing group-based active-learning methods.

  19. Research on the model of home networking

    Science.gov (United States)

    Yun, Xiang; Feng, Xiancheng

    2007-11-01

    It is the research hotspot of current broadband network to combine voice service, data service and broadband audio-video service by IP protocol to transport various real time and mutual services to terminal users (home). Home Networking is a new kind of network and application technology which can provide various services. Home networking is called as Digital Home Network. It means that PC, home entertainment equipment, home appliances, Home wirings, security, illumination system were communicated with each other by some composing network technology, constitute a networking internal home, and connect with WAN by home gateway. It is a new network technology and application technology, and can provide many kinds of services inside home or between homes. Currently, home networking can be divided into three kinds: Information equipment, Home appliances, Communication equipment. Equipment inside home networking can exchange information with outer networking by home gateway, this information communication is bidirectional, user can get information and service which provided by public networking by using home networking internal equipment through home gateway connecting public network, meantime, also can get information and resource to control the internal equipment which provided by home networking internal equipment. Based on the general network model of home networking, there are four functional entities inside home networking: HA, HB, HC, and HD. (1) HA (Home Access) - home networking connects function entity; (2) HB (Home Bridge) Home networking bridge connects function entity; (3) HC (Home Client) - Home networking client function entity; (4) HD (Home Device) - decoder function entity. There are many physical ways to implement four function entities. Based on theses four functional entities, there are reference model of physical layer, reference model of link layer, reference model of IP layer and application reference model of high layer. In the future home network

  20. Mathematical Modelling Plant Signalling Networks

    KAUST Repository

    Muraro, D.

    2013-01-01

    During the last two decades, molecular genetic studies and the completion of the sequencing of the Arabidopsis thaliana genome have increased knowledge of hormonal regulation in plants. These signal transduction pathways act in concert through gene regulatory and signalling networks whose main components have begun to be elucidated. Our understanding of the resulting cellular processes is hindered by the complex, and sometimes counter-intuitive, dynamics of the networks, which may be interconnected through feedback controls and cross-regulation. Mathematical modelling provides a valuable tool to investigate such dynamics and to perform in silico experiments that may not be easily carried out in a laboratory. In this article, we firstly review general methods for modelling gene and signalling networks and their application in plants. We then describe specific models of hormonal perception and cross-talk in plants. This mathematical analysis of sub-cellular molecular mechanisms paves the way for more comprehensive modelling studies of hormonal transport and signalling in a multi-scale setting. © EDP Sciences, 2013.

  1. Classification and prediction of the critical heat flux using fuzzy theory and artificial neural networks

    International Nuclear Information System (INIS)

    Moon, Sang Ki; Chang, Soon Heung

    1994-01-01

    A new method to predict the critical heat flux (CHF) is proposed, based on the fuzzy clustering and artificial neural network. The fuzzy clustering classifies the experimental CHF data into a few data clusters (data groups) according to the data characteristics. After classification of the experimental data, the characteristics of the resulting clusters are discussed with emphasis on the distribution of the experimental conditions and physical mechanism. The CHF data in each group are trained in an artificial neural network to predict the CHF. The artificial neural network adjusts the weight so as to minimize the prediction error within the corresponding cluster. Application of the proposed method to the KAIST CHF data bank shows good prediction capability of the CHF, better than other existing methods. ((orig.))

  2. The applications of deep neural networks to sdBV classification

    Science.gov (United States)

    Boudreaux, Thomas M.

    2017-12-01

    With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in industry for years now, allows for advanced feature detection in minimally prepared datasets at very high speeds; however, despite the advantages of this method, its application to astrophysics has not yet been extensively explored. This dearth may be due to a lack of training data available to researchers. Here we generate synthetic data loosely mimicking the properties of acoustic mode pulsating stars and we show that two separate paradigms of deep learning - the Artificial Neural Network And the Convolutional Neural Network - can both be used to classify this synthetic data effectively. And that additionally this classification can be performed at relatively high levels of accuracy with minimal time spent adjusting network hyperparameters.

  3. Various forms of indexing HDMR for modelling multivariate classification problems

    Energy Technology Data Exchange (ETDEWEB)

    Aksu, Çağrı [Bahçeşehir University, Information Technologies Master Program, Beşiktaş, 34349 İstanbul (Turkey); Tunga, M. Alper [Bahçeşehir University, Software Engineering Department, Beşiktaş, 34349 İstanbul (Turkey)

    2014-12-10

    The Indexing HDMR method was recently developed for modelling multivariate interpolation problems. The method uses the Plain HDMR philosophy in partitioning the given multivariate data set into less variate data sets and then constructing an analytical structure through these partitioned data sets to represent the given multidimensional problem. Indexing HDMR makes HDMR be applicable to classification problems having real world data. Mostly, we do not know all possible class values in the domain of the given problem, that is, we have a non-orthogonal data structure. However, Plain HDMR needs an orthogonal data structure in the given problem to be modelled. In this sense, the main idea of this work is to offer various forms of Indexing HDMR to successfully model these real life classification problems. To test these different forms, several well-known multivariate classification problems given in UCI Machine Learning Repository were used and it was observed that the accuracy results lie between 80% and 95% which are very satisfactory.

  4. Classification of protein-protein interaction full-text documents using text and citation network features.

    Science.gov (United States)

    Kolchinsky, Artemy; Abi-Haidar, Alaa; Kaur, Jasleen; Hamed, Ahmed Abdeen; Rocha, Luis M

    2010-01-01

    We participated (as Team 9) in the Article Classification Task of the Biocreative II.5 Challenge: binary classification of full-text documents relevant for protein-protein interaction. We used two distinct classifiers for the online and offline challenges: 1) the lightweight Variable Trigonometric Threshold (VTT) linear classifier we successfully introduced in BioCreative 2 for binary classification of abstracts and 2) a novel Naive Bayes classifier using features from the citation network of the relevant literature. We supplemented the supplied training data with full-text documents from the MIPS database. The lightweight VTT classifier was very competitive in this new full-text scenario: it was a top-performing submission in this task, taking into account the rank product of the Area Under the interpolated precision and recall Curve, Accuracy, Balanced F-Score, and Matthew's Correlation Coefficient performance measures. The novel citation network classifier for the biomedical text mining domain, while not a top performing classifier in the challenge, performed above the central tendency of all submissions, and therefore indicates a promising new avenue to investigate further in bibliome informatics.

  5. Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization

    Directory of Open Access Journals (Sweden)

    Philipp Kainz

    2017-10-01

    Full Text Available Segmentation of histopathology sections is a necessary preprocessing step for digital pathology. Due to the large variability of biological tissue, machine learning techniques have shown superior performance over conventional image processing methods. Here we present our deep neural network-based approach for segmentation and classification of glands in tissue of benign and malignant colorectal cancer, which was developed to participate in the GlaS@MICCAI2015 colon gland segmentation challenge. We use two distinct deep convolutional neural networks (CNN for pixel-wise classification of Hematoxylin-Eosin stained images. While the first classifier separates glands from background, the second classifier identifies gland-separating structures. In a subsequent step, a figure-ground segmentation based on weighted total variation produces the final segmentation result by regularizing the CNN predictions. We present both quantitative and qualitative segmentation results on the recently released and publicly available Warwick-QU colon adenocarcinoma dataset associated with the GlaS@MICCAI2015 challenge and compare our approach to the simultaneously developed other approaches that participated in the same challenge. On two test sets, we demonstrate our segmentation performance and show that we achieve a tissue classification accuracy of 98% and 95%, making use of the inherent capability of our system to distinguish between benign and malignant tissue. Our results show that deep learning approaches can yield highly accurate and reproducible results for biomedical image analysis, with the potential to significantly improve the quality and speed of medical diagnoses.

  6. Impacts of Sample Design for Validation Data on the Accuracy of Feedforward Neural Network Classification

    Directory of Open Access Journals (Sweden)

    Giles M. Foody

    2017-08-01

    Full Text Available Validation data are often used to evaluate the performance of a trained neural network and used in the selection of a network deemed optimal for the task at-hand. Optimality is commonly assessed with a measure, such as overall classification accuracy. The latter is often calculated directly from a confusion matrix showing the counts of cases in the validation set with particular labelling properties. The sample design used to form the validation set can, however, influence the estimated magnitude of the accuracy. Commonly, the validation set is formed with a stratified sample to give balanced classes, but also via random sampling, which reflects class abundance. It is suggested that if the ultimate aim is to accurately classify a dataset in which the classes do vary in abundance, a validation set formed via random, rather than stratified, sampling is preferred. This is illustrated with the classification of simulated and remotely-sensed datasets. With both datasets, statistically significant differences in the accuracy with which the data could be classified arose from the use of validation sets formed via random and stratified sampling (z = 2.7 and 1.9 for the simulated and real datasets respectively, for both p < 0.05%. The accuracy of the classifications that used a stratified sample in validation were smaller, a result of cases of an abundant class being commissioned into a rarer class. Simple means to address the issue are suggested.

  7. Modulation Classification of Satellite Communication Signals Using Cumulants and Neural Networks

    Science.gov (United States)

    Smith, Aaron; Evans, Michael; Downey, Joseph

    2017-01-01

    National Aeronautics and Space Administration (NASA)'s future communication architecture is evaluating cognitive technologies and increased system intelligence. These technologies are expected to reduce the operational complexity of the network, increase science data return, and reduce interference to self and others. In order to increase situational awareness, signal classification algorithms could be applied to identify users and distinguish sources of interference. A significant amount of previous work has been done in the area of automatic signal classification for military and commercial applications. As a preliminary step, we seek to develop a system with the ability to discern signals typically encountered in satellite communication. Proposed is an automatic modulation classifier which utilizes higher order statistics (cumulants) and an estimate of the signal-to-noise ratio. These features are extracted from baseband symbols and then processed by a neural network for classification. The modulation types considered are phase-shift keying (PSK), amplitude and phase-shift keying (APSK),and quadrature amplitude modulation (QAM). Physical layer properties specific to the Digital Video Broadcasting - Satellite- Second Generation (DVB-S2) standard, such as pilots and variable ring ratios, are also considered. This paper will provide simulation results of a candidate modulation classifier, and performance will be evaluated over a range of signal-to-noise ratios, frequency offsets, and nonlinear amplifier distortions.

  8. Energy modelling in sensor networks

    Science.gov (United States)

    Schmidt, D.; Krämer, M.; Kuhn, T.; Wehn, N.

    2007-06-01

    Wireless sensor networks are one of the key enabling technologies for the vision of ambient intelligence. Energy resources for sensor nodes are very scarce. A key challenge is the design of energy efficient communication protocols. Models of the energy consumption are needed to accurately simulate the efficiency of a protocol or application design, and can also be used for automatic energy optimizations in a model driven design process. We propose a novel methodology to create models for sensor nodes based on few simple measurements. In a case study the methodology was used to create models for MICAz nodes. The models were integrated in a simulation environment as well as in a SDL runtime framework of a model driven design process. Measurements on a test application that was created automatically from an SDL specification showed an 80% reduction in energy consumption compared to an implementation without power saving strategies.

  9. Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network.

    Science.gov (United States)

    Adak, M Fatih; Yumusak, Nejat

    2016-02-27

    Electronic nose technology is used in many areas, and frequently in the beverage industry for classification and quality-control purposes. In this study, four different aroma data (strawberry, lemon, cherry, and melon) were obtained using a MOSES II electronic nose for the purpose of fruit classification. To improve the performance of the classification, the training phase of the neural network with two hidden layers was optimized using artificial bee colony algorithm (ABC), which is known to be successful in exploration. Test data were given to two different neural networks, each of which were trained separately with backpropagation (BP) and ABC, and average test performances were measured as 60% for the artificial neural network trained with BP and 76.39% for the artificial neural network trained with ABC. Training and test phases were repeated 30 times to obtain these average performance measurements. This level of performance shows that the artificial neural network trained with ABC is successful in classifying aroma data.

  10. Training echo state networks for rotation-invariant bone marrow cell classification.

    Science.gov (United States)

    Kainz, Philipp; Burgsteiner, Harald; Asslaber, Martin; Ahammer, Helmut

    2017-01-01

    The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.

  11. Multi-Pixel Simultaneous Classification of PolSAR Image Using Convolutional Neural Networks

    Science.gov (United States)

    Xu, Xin; Gui, Rong; Pu, Fangling

    2018-01-01

    Convolutional neural networks (CNN) have achieved great success in the optical image processing field. Because of the excellent performance of CNN, more and more methods based on CNN are applied to polarimetric synthetic aperture radar (PolSAR) image classification. Most CNN-based PolSAR image classification methods can only classify one pixel each time. Because all the pixels of a PolSAR image are classified independently, the inherent interrelation of different land covers is ignored. We use a fixed-feature-size CNN (FFS-CNN) to classify all pixels in a patch simultaneously. The proposed method has several advantages. First, FFS-CNN can classify all the pixels in a small patch simultaneously. When classifying a whole PolSAR image, it is faster than common CNNs. Second, FFS-CNN is trained to learn the interrelation of different land covers in a patch, so it can use the interrelation of land covers to improve the classification results. The experiments of FFS-CNN are evaluated on a Chinese Gaofen-3 PolSAR image and other two real PolSAR images. Experiment results show that FFS-CNN is comparable with the state-of-the-art PolSAR image classification methods. PMID:29510499

  12. Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-Trained Using Attention-Guided Sparse Filters

    Directory of Open Access Journals (Sweden)

    Jingbo Chen

    2018-02-01

    Full Text Available Semantic-level land-use scene classification is a challenging problem, in which deep learning methods, e.g., convolutional neural networks (CNNs, have shown remarkable capacity. However, a lack of sufficient labeled images has proved a hindrance to increasing the land-use scene classification accuracy of CNNs. Aiming at this problem, this paper proposes a CNN pre-training method under the guidance of a human visual attention mechanism. Specifically, a computational visual attention model is used to automatically extract salient regions in unlabeled images. Then, sparse filters are adopted to learn features from these salient regions, with the learnt parameters used to initialize the convolutional layers of the CNN. Finally, the CNN is further fine-tuned on labeled images. Experiments are performed on the UCMerced and AID datasets, which show that when combined with a demonstrative CNN, our method can achieve 2.24% higher accuracy than a plain CNN and can obtain an overall accuracy of 92.43% when combined with AlexNet. The results indicate that the proposed method can effectively improve CNN performance using easy-to-access unlabeled images and thus will enhance the performance of land-use scene classification especially when a large-scale labeled dataset is unavailable.

  13. Biological transportation networks: Modeling and simulation

    KAUST Repository

    Albi, Giacomo; Artina, Marco; Foransier, Massimo; Markowich, Peter A.

    2015-01-01

    We present a model for biological network formation originally introduced by Cai and Hu [Adaptation and optimization of biological transport networks, Phys. Rev. Lett. 111 (2013) 138701]. The modeling of fluid transportation (e.g., leaf venation

  14. A Novel User Classification Method for Femtocell Network by Using Affinity Propagation Algorithm and Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Afaz Uddin Ahmed

    2014-01-01

    Full Text Available An artificial neural network (ANN and affinity propagation (AP algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation.

  15. A Novel User Classification Method for Femtocell Network by Using Affinity Propagation Algorithm and Artificial Neural Network

    Science.gov (United States)

    Ahmed, Afaz Uddin; Tariqul Islam, Mohammad; Ismail, Mahamod; Kibria, Salehin; Arshad, Haslina

    2014-01-01

    An artificial neural network (ANN) and affinity propagation (AP) algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation. PMID:25133214

  16. BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

    Science.gov (United States)

    Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

    2018-04-11

    The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes

  17. Clustering and artificial neural networks: classification of variable lengths of Helminth antigens in set of domains

    Directory of Open Access Journals (Sweden)

    Thiago de Souza Rodrigues

    2004-01-01

    Full Text Available A new scheme for representing proteins of different lengths in number of amino acids that can be presented to a fixed number of inputs Artificial Neural Networks (ANNs speel-out classification is described. K-Means's clustering of the new vectors with subsequent classification was then possible with the dimension reduction technique Principal Component Analysis applied previously. The new representation scheme was applied to a set of 112 antigens sequences from several parasitic helminths, selected in the National Center for Biotechnology Information and classified into fourth different groups. This bioinformatic tool permitted the establishment of a good correlation with domains that are already well characterized, regardless of the differences between the sequences that were confirmed by the PFAM database. Additionally, sequences were grouped according to their similarity, confirmed by hierarchical clustering using ClustalW.

  18. A probablistic neural network classification system for signal and image processing

    Energy Technology Data Exchange (ETDEWEB)

    Bowman, B. [Lawrence Livermore National Lab., CA (United States)

    1994-11-15

    The Acoustical Heart Valve Analysis Package is a system for signal and image processing and classification. It is being developed in both Matlab and C, to provide an interactive, interpreted environment, and has been optimized for large scale matrix operations. It has been used successfully to classify acoustic signals from implanted prosthetic heart valves in human patients, and will be integrated into a commercial Heart Valve Screening Center. The system uses several standard signal processing algorithms, as well as supervised learning techniques using the probabilistic neural network (PNN). Although currently used for the acoustic heart valve application, the algorithms and modular design allow it to be used for other applications, as well. We will describe the signal classification system, and show results from a set of test valves.

  19. Classification of EMG signals using artificial neural networks for virtual hand prosthesis control.

    Science.gov (United States)

    Mattioli, Fernando E R; Lamounier, Edgard A; Cardoso, Alexandre; Soares, Alcimar B; Andrade, Adriano O

    2011-01-01

    Computer-based training systems have been widely studied in the field of human rehabilitation. In health applications, Virtual Reality presents itself as an appropriate tool to simulate training environments without exposing the patients to risks. In particular, virtual prosthetic devices have been used to reduce the great mental effort needed by patients fitted with myoelectric prosthesis, during the training stage. In this paper, the application of Virtual Reality in a hand prosthesis training system is presented. To achieve this, the possibility of exploring Neural Networks in a real-time classification system is discussed. The classification technique used in this work resulted in a 95% success rate when discriminating 4 different hand movements.

  20. Modeling Wireless Sensor Networks for Monitoring in Biological Processes

    DEFF Research Database (Denmark)

    Nadimi, Esmaeil

    parameters, as the use of wired sensors is impractical. In this thesis, a ZigBee based wireless sensor network was employed and only a part of the herd was monitored, as monitoring each individual animal in a large herd under practical conditions is inefficient. Investigations to show that the monitored...... (MMAE) approach to the data resulted in the highest classification success rate, due to the use of precise forth-order mathematical models which relate the feed offer to the pitch angle of the neck. This thesis shows that wireless sensor networks can be successfully employed to monitor the behavior...

  1. An evolving network model with community structure

    International Nuclear Information System (INIS)

    Li Chunguang; Maini, Philip K

    2005-01-01

    Many social and biological networks consist of communities-groups of nodes within which connections are dense, but between which connections are sparser. Recently, there has been considerable interest in designing algorithms for detecting community structures in real-world complex networks. In this paper, we propose an evolving network model which exhibits community structure. The network model is based on the inner-community preferential attachment and inter-community preferential attachment mechanisms. The degree distributions of this network model are analysed based on a mean-field method. Theoretical results and numerical simulations indicate that this network model has community structure and scale-free properties

  2. Brand Marketing Model on Social Networks

    Directory of Open Access Journals (Sweden)

    Jolita Jezukevičiūtė

    2014-04-01

    Full Text Available The paper analyzes the brand and its marketing solutions onsocial networks. This analysis led to the creation of improvedbrand marketing model on social networks, which will contributeto the rapid and cheap organization brand recognition, increasecompetitive advantage and enhance consumer loyalty. Therefore,the brand and a variety of social networks are becoming a hotresearch area for brand marketing model on social networks.The world‘s most successful brand marketing models exploratoryanalysis of a single case study revealed a brand marketingsocial networking tools that affect consumers the most. Basedon information analysis and methodological studies, develop abrand marketing model on social networks.

  3. Tissue classification and segmentation of pressure injuries using convolutional neural networks.

    Science.gov (United States)

    Zahia, Sofia; Sierra-Sosa, Daniel; Garcia-Zapirain, Begonya; Elmaghraby, Adel

    2018-06-01

    This paper presents a new approach for automatic tissue classification in pressure injuries. These wounds are localized skin damages which need frequent diagnosis and treatment. Therefore, a reliable and accurate systems for segmentation and tissue type identification are needed in order to achieve better treatment results. Our proposed system is based on a Convolutional Neural Network (CNN) devoted to performing optimized segmentation of the different tissue types present in pressure injuries (granulation, slough, and necrotic tissues). A preprocessing step removes the flash light and creates a set of 5x5 sub-images which are used as input for the CNN network. The network output will classify every sub-image of the validation set into one of the three classes studied. The metrics used to evaluate our approach show an overall average classification accuracy of 92.01%, an average total weighted Dice Similarity Coefficient of 91.38%, and an average precision per class of 97.31% for granulation tissue, 96.59% for necrotic tissue, and 77.90% for slough tissue. Our system has been proven to make recognition of complicated structures in biomedical images feasible. Copyright © 2018 Elsevier B.V. All rights reserved.

  4. Classification and prediction of river network ephemerality and its relevance for waterborne disease epidemiology

    Science.gov (United States)

    Perez-Saez, Javier; Mande, Theophile; Larsen, Joshua; Ceperley, Natalie; Rinaldo, Andrea

    2017-12-01

    The transmission of waterborne diseases hinges on the interactions between hydrology and ecology of hosts, vectors and parasites, with the long-term absence of water constituting a strict lower bound. However, the link between spatio-temporal patterns of hydrological ephemerality and waterborne disease transmission is poorly understood and difficult to account for. The use of limited biophysical and hydroclimate information from otherwise data scarce regions is therefore needed to characterize, classify, and predict river network ephemerality in a spatially explicit framework. Here, we develop a novel large-scale ephemerality classification and prediction methodology based on monthly discharge data, water and energy availability, and remote-sensing measures of vegetation, that is relevant to epidemiology, and maintains a mechanistic link to catchment hydrologic processes. Specifically, with reference to the context of Burkina Faso in sub-Saharan Africa, we extract a relevant set of catchment covariates that include the aridity index, annual runoff estimation using the Budyko framework, and hysteretical relations between precipitation and vegetation. Five ephemerality classes, from permanent to strongly ephemeral, are defined from the duration of 0-flow periods that also accounts for the sensitivity of river discharge to the long-lasting drought of the 70's-80's in West Africa. Using such classes, a gradient-boosted tree-based prediction yielded three distinct geographic regions of ephemerality. Importantly, we observe a strong epidemiological association between our predictions of hydrologic ephemerality and the known spatial patterns of schistosomiasis, an endemic parasitic waterborne disease in which infection occurs with human-water contact, and requires aquatic snails as an intermediate host. The general nature of our approach and its relevance for predicting the hydrologic controls on schistosomiasis occurrence provides a pathway for the explicit inclusion of

  5. Computerized Classification of Pneumoconiosis on Digital Chest Radiography Artificial Neural Network with Three Stages.

    Science.gov (United States)

    Okumura, Eiichiro; Kawashita, Ikuo; Ishida, Takayuki

    2017-08-01

    It is difficult for radiologists to classify pneumoconiosis from category 0 to category 3 on chest radiographs. Therefore, we have developed a computer-aided diagnosis (CAD) system based on a three-stage artificial neural network (ANN) method for classification based on four texture features. The image database consists of 36 chest radiographs classified as category 0 to category 3. Regions of interest (ROIs) with a matrix size of 32 × 32 were selected from chest radiographs. We obtained a gray-level histogram, histogram of gray-level difference, gray-level run-length matrix (GLRLM) feature image, and gray-level co-occurrence matrix (GLCOM) feature image in each ROI. For ROI-based classification, the first ANN was trained with each texture feature. Next, the second ANN was trained with output patterns obtained from the first ANN. Finally, we obtained a case-based classification for distinguishing among four categories with the third ANN method. We determined the performance of the third ANN by receiver operating characteristic (ROC) analysis. The areas under the ROC curve (AUC) of the highest category (severe pneumoconiosis) case and the lowest category (early pneumoconiosis) case were 0.89 ± 0.09 and 0.84 ± 0.12, respectively. The three-stage ANN with four texture features showed the highest performance for classification among the four categories. Our CAD system would be useful for assisting radiologists in classification of pneumoconiosis from category 0 to category 3.

  6. A novel Direct Small World network model

    Directory of Open Access Journals (Sweden)

    LIN Tao

    2016-10-01

    Full Text Available There is a certain degree of redundancy and low efficiency of existing computer networks.This paper presents a novel Direct Small World network model in order to optimize networks.In this model,several nodes construct a regular network.Then,randomly choose and replot some nodes to generate Direct Small World network iteratively.There is no change in average distance and clustering coefficient.However,the network performance,such as hops,is improved.The experiments prove that compared to traditional small world network,the degree,average of degree centrality and average of closeness centrality are lower in Direct Small World network.This illustrates that the nodes in Direct Small World networks are closer than Watts-Strogatz small world network model.The Direct Small World can be used not only in the communication of the community information,but also in the research of epidemics.

  7. RMBNToolbox: random models for biochemical networks

    Directory of Open Access Journals (Sweden)

    Niemi Jari

    2007-05-01

    Full Text Available Abstract Background There is an increasing interest to model biochemical and cell biological networks, as well as to the computational analysis of these models. The development of analysis methodologies and related software is rapid in the field. However, the number of available models is still relatively small and the model sizes remain limited. The lack of kinetic information is usually the limiting factor for the construction of detailed simulation models. Results We present a computational toolbox for generating random biochemical network models which mimic real biochemical networks. The toolbox is called Random Models for Biochemical Networks. The toolbox works in the Matlab environment, and it makes it possible to generate various network structures, stoichiometries, kinetic laws for reactions, and parameters therein. The generation can be based on statistical rules and distributions, and more detailed information of real biochemical networks can be used in situations where it is known. The toolbox can be easily extended. The resulting network models can be exported in the format of Systems Biology Markup Language. Conclusion While more information is accumulating on biochemical networks, random networks can be used as an intermediate step towards their better understanding. Random networks make it possible to study the effects of various network characteristics to the overall behavior of the network. Moreover, the construction of artificial network models provides the ground truth data needed in the validation of various computational methods in the fields of parameter estimation and data analysis.

  8. Fuzzy Continuous Review Inventory Model using ABC Multi-Criteria Classification Approach: A Single Case Study

    Directory of Open Access Journals (Sweden)

    Meriastuti - Ginting

    2015-07-01

    Full Text Available Abstract. Inventory is considered as the most expensive, yet important,to any companies. It representsapproximately 50% of the total investment. Inventory cost has become one of the majorcontributorsto inefficiency, therefore it should be managed effectively. This study aims to propose an alternative inventory model,  by using ABC multi-criteria classification approach to minimize total cost. By combining FANP (Fuzzy Analytical Network Process and TOPSIS (Technique of Order Preferences by Similarity to the Ideal Solution, the ABC multi-criteria classification approach identified 12 items of 69 inventory items as “outstanding important class” that contributed to 80% total inventory cost. This finding  is then used as the basis to determine the proposed continuous review inventory model.This study found that by using fuzzy trapezoidal cost, the inventory  turnover ratio can be increased, and inventory cost can be decreased by 78% for each item in “class A” inventory.Keywords:ABC multi-criteria classification, FANP-TOPSIS, continuous review inventory model lead-time demand distribution, trapezoidal fuzzy number 

  9. Parsimonious classification of binary lacunarity data computed from food surface images using kernel principal component analysis and artificial neural networks.

    Science.gov (United States)

    Iqbal, Abdullah; Valous, Nektarios A; Sun, Da-Wen; Allen, Paul

    2011-02-01

    Lacunarity is about quantifying the degree of spatial heterogeneity in the visual texture of imagery through the identification of the relationships between patterns and their spatial configurations in a two-dimensional setting. The computed lacunarity data can designate a mathematical index of spatial heterogeneity, therefore the corresponding feature vectors should possess the necessary inter-class statistical properties that would enable them to be used for pattern recognition purposes. The objectives of this study is to construct a supervised parsimonious classification model of binary lacunarity data-computed by Valous et al. (2009)-from pork ham slice surface images, with the aid of kernel principal component analysis (KPCA) and artificial neural networks (ANNs), using a portion of informative salient features. At first, the dimension of the initial space (510 features) was reduced by 90% in order to avoid any noise effects in the subsequent classification. Then, using KPCA, the first nineteen kernel principal components (99.04% of total variance) were extracted from the reduced feature space, and were used as input in the ANN. An adaptive feedforward multilayer perceptron (MLP) classifier was employed to obtain a suitable mapping from the input dataset. The correct classification percentages for the training, test and validation sets were 86.7%, 86.7%, and 85.0%, respectively. The results confirm that the classification performance was satisfactory. The binary lacunarity spatial metric captured relevant information that provided a good level of differentiation among pork ham slice images. Copyright © 2010 The American Meat Science Association. Published by Elsevier Ltd. All rights reserved.

  10. Rough set soft computing cancer classification and network: one stone, two birds.

    Science.gov (United States)

    Zhang, Yue

    2010-07-15

    Gene expression profiling provides tremendous information to help unravel the complexity of cancer. The selection of the most informative genes from huge noise for cancer classification has taken centre stage, along with predicting the function of such identified genes and the construction of direct gene regulatory networks at different system levels with a tuneable parameter. A new study by Wang and Gotoh described a novel Variable Precision Rough Sets-rooted robust soft computing method to successfully address these problems and has yielded some new insights. The significance of this progress and its perspectives will be discussed in this article.

  11. Classification and Extraction of Resting State Networks Using Healthy and Epilepsy fMRI Data

    Directory of Open Access Journals (Sweden)

    Svyatoslav Vergun

    2016-09-01

    Full Text Available Functional magnetic resonance imaging studies have significantly expanded the field’s understanding of functional brain activity of healthy and patient populations. Resting state (rs- fMRI, which does not require subjects to perform a task, eliminating confounds of task difficulty, allows examination of neural activity and offers valuable functional mapping information. The purpose of this work was to develop an automatic resting state network (RNS labeling method which offers value in clinical workflow during rs-fMRI mapping by organizing and quickly labeling spatial maps into functional networks. Here independent component analysis (ICA and machine learning were applied to rs-fMRI data with the goal of developing a method for the clinically oriented task of extracting and classifying spatial maps into auditory, visual, default-mode, sensorimotor and executive control resting state networks from 23 epilepsy patients (and for general comparison, separately for 30 healthy subjects. ICA revealed distinct and consistent functional network components across patients and healthy subjects. Network classification was successful, achieving 88% accuracy for epilepsy patients with a naïve Bayes algorithm (and 90% accuracy for healthy subjects with a perceptron. The method’s utility to researchers and clinicians is the provided RSN spatial maps and their functional labeling which offer complementary functional information to clinicians’ expert interpretation.

  12. Classification of dry-cured hams according to the maturation time using near infrared spectra and artificial neural networks.

    Science.gov (United States)

    Prevolnik, M; Andronikov, D; Žlender, B; Font-i-Furnols, M; Novič, M; Škorjanc, D; Čandek-Potokar, M

    2014-01-01

    An attempt to classify dry-cured hams according to the maturation time on the basis of near infrared (NIR) spectra was studied. The study comprised 128 samples of biceps femoris (BF) muscle from dry-cured hams matured for 10 (n=32), 12 (n=32), 14 (n=32) or 16 months (n=32). Samples were minced and scanned in the wavelength range from 400 to 2500 nm using spectrometer NIR System model 6500 (Silver Spring, MD, USA). Spectral data were used for i) splitting of samples into the training and test set using 2D Kohonen artificial neural networks (ANN) and for ii) construction of classification models using counter-propagation ANN (CP-ANN). Different models were tested, and the one selected was based on the lowest percentage of misclassified test samples (external validation). Overall correctness of the classification was 79.7%, which demonstrates practical relevance of using NIR spectroscopy and ANN for dry-cured ham processing control. Copyright © 2013 Elsevier Ltd. All rights reserved.

  13. Fabric Weave Pattern and Yarn Color Recognition and Classification Using a Deep ELM Network

    Directory of Open Access Journals (Sweden)

    Babar Khan

    2017-10-01

    Full Text Available Usually, a fabric weave pattern is recognized using methods which identify the warp floats and weft floats. Although these methods perform well for uniform or repetitive weave patterns, in the case of complex weave patterns, these methods become computationally complex and the classification error rates are comparatively higher. Furthermore, the fault-tolerance (invariance and stability (selectivity of the existing methods are still to be enhanced. We present a novel biologically-inspired method to invariantly recognize the fabric weave pattern (fabric texture and yarn color from the color image input. We proposed a model in which the fabric weave pattern descriptor is based on the HMAX model for computer vision inspired by the hierarchy in the visual cortex, the color descriptor is based on the opponent color channel inspired by the classical opponent color theory of human vision, and the classification stage is composed of a multi-layer (deep extreme learning machine. Since the weave pattern descriptor, yarn color descriptor, and the classification stage are all biologically inspired, we propose a method which is completely biologically plausible. The classification performance of the proposed algorithm indicates that the biologically-inspired computer-aided-vision models might provide accurate, fast, reliable and cost-effective solution to industrial automation.

  14. Brand Marketing Model on Social Networks

    OpenAIRE

    Jolita Jezukevičiūtė; Vida Davidavičienė

    2014-01-01

    The paper analyzes the brand and its marketing solutions onsocial networks. This analysis led to the creation of improvedbrand marketing model on social networks, which will contributeto the rapid and cheap organization brand recognition, increasecompetitive advantage and enhance consumer loyalty. Therefore,the brand and a variety of social networks are becoming a hotresearch area for brand marketing model on social networks.The world‘s most successful brand marketing models exploratoryanalys...

  15. Brand marketing model on social networks

    OpenAIRE

    Jezukevičiūtė, Jolita; Davidavičienė, Vida

    2014-01-01

    Paper analyzes the brand and its marketing solutions on social networks. This analysis led to the creation of improved brand marketing model on social networks, which will contribute to the rapid and cheap organization brand recognition, increase competitive advantage and enhance consumer loyalty. Therefore, the brand and a variety of social networks are becoming a hot research area for brand marketing model on social networks. The world‘s most successful brand marketing models exploratory an...

  16. Application of Neural Networks for classification of Patau, Edwards, Down, Turner and Klinefelter Syndrome based on first trimester maternal serum screening data, ultrasonographic findings and patient demographics.

    Science.gov (United States)

    Catic, Aida; Gurbeta, Lejla; Kurtovic-Kozaric, Amina; Mehmedbasic, Senad; Badnjevic, Almir

    2018-02-13

    The usage of Artificial Neural Networks (ANNs) for genome-enabled classifications and establishing genome-phenotype correlations have been investigated more extensively over the past few years. The reason for this is that ANNs are good approximates of complex functions, so classification can be performed without the need for explicitly defined input-output model. This engineering tool can be applied for optimization of existing methods for disease/syndrome classification. Cytogenetic and molecular analyses are the most frequent tests used in prenatal diagnostic for the early detection of Turner, Klinefelter, Patau, Edwards and Down syndrome. These procedures can be lengthy, repetitive; and often employ invasive techniques so a robust automated method for classifying and reporting prenatal diagnostics would greatly help the clinicians with their routine work. The database consisted of data collected from 2500 pregnant woman that came to the Institute of Gynecology, Infertility and Perinatology "Mehmedbasic" for routine antenatal care between January 2000 and December 2016. During first trimester all women were subject to screening test where values of maternal serum pregnancy-associated plasma protein A (PAPP-A) and free beta human chorionic gonadotropin (β-hCG) were measured. Also, fetal nuchal translucency thickness and the presence or absence of the nasal bone was observed using ultrasound. The architectures of linear feedforward and feedback neural networks were investigated for various training data distributions and number of neurons in hidden layer. Feedback neural network architecture out performed feedforward neural network architecture in predictive ability for all five aneuploidy prenatal syndrome classes. Feedforward neural network with 15 neurons in hidden layer achieved classification sensitivity of 92.00%. Classification sensitivity of feedback (Elman's) neural network was 99.00%. Average accuracy of feedforward neural network was 89.6% and for

  17. Fuzzy classification of phantom parent groups in an animal model

    Directory of Open Access Journals (Sweden)

    Fikse Freddy

    2009-09-01

    Full Text Available Abstract Background Genetic evaluation models often include genetic groups to account for unequal genetic level of animals with unknown parentage. The definition of phantom parent groups usually includes a time component (e.g. years. Combining several time periods to ensure sufficiently large groups may create problems since all phantom parents in a group are considered contemporaries. Methods To avoid the downside of such distinct classification, a fuzzy logic approach is suggested. A phantom parent can be assigned to several genetic groups, with proportions between zero and one that sum to one. Rules were presented for assigning coefficients to the inverse of the relationship matrix for fuzzy-classified genetic groups. This approach was illustrated with simulated data from ten generations of mass selection. Observations and pedigree records were randomly deleted. Phantom parent groups were defined on the basis of gender and generation number. In one scenario, uncertainty about generation of birth was simulated for some animals with unknown parents. In the distinct classification, one of the two possible generations of birth was randomly chosen to assign phantom parents to genetic groups for animals with simulated uncertainty, whereas the phantom parents were assigned to both possible genetic groups in the fuzzy classification. Results The empirical prediction error variance (PEV was somewhat lower for fuzzy-classified genetic groups. The ranking of animals with unknown parents was more correct and less variable across replicates in comparison with distinct genetic groups. In another scenario, each phantom parent was assigned to three groups, one pertaining to its gender, and two pertaining to the first and last generation, with proportion depending on the (true generation of birth. Due to the lower number of groups, the empirical PEV of breeding values was smaller when genetic groups were fuzzy-classified. Conclusion Fuzzy-classification

  18. Network Bandwidth Utilization Forecast Model on High Bandwidth Network

    Energy Technology Data Exchange (ETDEWEB)

    Yoo, Wucherl; Sim, Alex

    2014-07-07

    With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2percent. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.

  19. Network bandwidth utilization forecast model on high bandwidth networks

    Energy Technology Data Exchange (ETDEWEB)

    Yoo, Wuchert (William) [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Sim, Alex [Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

    2015-03-30

    With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2%. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.

  20. ISBDD Model for Classification of Hyperspectral Remote Sensing Imagery

    Directory of Open Access Journals (Sweden)

    Na Li

    2018-03-01

    Full Text Available The diverse density (DD algorithm was proposed to handle the problem of low classification accuracy when training samples contain interference such as mixed pixels. The DD algorithm can learn a feature vector from training bags, which comprise instances (pixels. However, the feature vector learned by the DD algorithm cannot always effectively represent one type of ground cover. To handle this problem, an instance space-based diverse density (ISBDD model that employs a novel training strategy is proposed in this paper. In the ISBDD model, DD values of each pixel are computed instead of learning a feature vector, and as a result, the pixel can be classified according to its DD values. Airborne hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS sensor and the Push-broom Hyperspectral Imager (PHI are applied to evaluate the performance of the proposed model. Results show that the overall classification accuracy of ISBDD model on the AVIRIS and PHI images is up to 97.65% and 89.02%, respectively, while the kappa coefficient is up to 0.97 and 0.88, respectively.

  1. Statistical control chart and neural network classification for improving human fall detection

    KAUST Repository

    Harrou, Fouzi; Zerrouki, Nabil; Sun, Ying; Houacine, Amrane

    2017-01-01

    This paper proposes a statistical approach to detect and classify human falls based on both visual data from camera and accelerometric data captured by accelerometer. Specifically, we first use a Shewhart control chart to detect the presence of potential falls by using accelerometric data. Unfortunately, this chart cannot distinguish real falls from fall-like actions, such as lying down. To bypass this difficulty, a neural network classifier is then applied only on the detected cases through visual data. To assess the performance of the proposed method, experiments are conducted on the publicly available fall detection databases: the University of Rzeszow's fall detection (URFD) dataset. Results demonstrate that the detection phase play a key role in reducing the number of sequences used as input into the neural network classifier for classification, significantly reducing computational burden and achieving better accuracy.

  2. Statistical control chart and neural network classification for improving human fall detection

    KAUST Repository

    Harrou, Fouzi

    2017-01-05

    This paper proposes a statistical approach to detect and classify human falls based on both visual data from camera and accelerometric data captured by accelerometer. Specifically, we first use a Shewhart control chart to detect the presence of potential falls by using accelerometric data. Unfortunately, this chart cannot distinguish real falls from fall-like actions, such as lying down. To bypass this difficulty, a neural network classifier is then applied only on the detected cases through visual data. To assess the performance of the proposed method, experiments are conducted on the publicly available fall detection databases: the University of Rzeszow\\'s fall detection (URFD) dataset. Results demonstrate that the detection phase play a key role in reducing the number of sequences used as input into the neural network classifier for classification, significantly reducing computational burden and achieving better accuracy.

  3. MODEL-BASED CLUSTERING FOR CLASSIFICATION OF AQUATIC SYSTEMS AND DIAGNOSIS OF ECOLOGICAL STRESS

    Science.gov (United States)

    Clustering approaches were developed using the classification likelihood, the mixture likelihood, and also using a randomization approach with a model index. Using a clustering approach based on the mixture and classification likelihoods, we have developed an algorithm that...

  4. Using different classification models in wheat grading utilizing visual features

    Science.gov (United States)

    Basati, Zahra; Rasekh, Mansour; Abbaspour-Gilandeh, Yousef

    2018-04-01

    Wheat is one of the most important strategic crops in Iran and in the world. The major component that distinguishes wheat from other grains is the gluten section. In Iran, sunn pest is one of the most important factors influencing the characteristics of wheat gluten and in removing it from a balanced state. The existence of bug-damaged grains in wheat will reduce the quality and price of the product. In addition, damaged grains reduce the enrichment of wheat and the quality of bread products. In this study, after preprocessing and segmentation of images, 25 features including 9 colour features, 10 morphological features, and 6 textual statistical features were extracted so as to classify healthy and bug-damaged wheat grains of Azar cultivar of four levels of moisture content (9, 11.5, 14 and 16.5% w.b.) and two lighting colours (yellow light, the composition of yellow and white lights). Using feature selection methods in the WEKA software and the CfsSubsetEval evaluator, 11 features were chosen as inputs of artificial neural network, decision tree and discriment analysis classifiers. The results showed that the decision tree with the J.48 algorithm had the highest classification accuracy of 90.20%. This was followed by artificial neural network classifier with the topology of 11-19-2 and discrimient analysis classifier at 87.46 and 81.81%, respectively

  5. Learning Supervised Topic Models for Classification and Regression from Crowds.

    Science.gov (United States)

    Rodrigues, Filipe; Lourenco, Mariana; Ribeiro, Bernardete; Pereira, Francisco C

    2017-12-01

    The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state-of-the-art approaches.

  6. Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Jinhee Park

    2016-11-01

    Full Text Available Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost.

  7. Neural network and wavelet average framing percentage energy for atrial fibrillation classification.

    Science.gov (United States)

    Daqrouq, K; Alkhateeb, A; Ajour, M N; Morfeq, A

    2014-03-01

    ECG signals are an important source of information in the diagnosis of atrial conduction pathology. Nevertheless, diagnosis by visual inspection is a difficult task. This work introduces a novel wavelet feature extraction method for atrial fibrillation derived from the average framing percentage energy (AFE) of terminal wavelet packet transform (WPT) sub signals. Probabilistic neural network (PNN) is used for classification. The presented method is shown to be a potentially effective discriminator in an automated diagnostic process. The ECG signals taken from the MIT-BIH database are used to classify different arrhythmias together with normal ECG. Several published methods were investigated for comparison. The best recognition rate selection was obtained for AFE. The classification performance achieved accuracy 97.92%. It was also suggested to analyze the presented system in an additive white Gaussian noise (AWGN) environment; 55.14% for 0dB and 92.53% for 5dB. It was concluded that the proposed approach of automating classification is worth pursuing with larger samples to validate and extend the present study. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

  8. A Neural-Network-Based Approach to White Blood Cell Classification

    Directory of Open Access Journals (Sweden)

    Mu-Chun Su

    2014-01-01

    Full Text Available This paper presents a new white blood cell classification system for the recognition of five types of white blood cells. We propose a new segmentation algorithm for the segmentation of white blood cells from smear images. The core idea of the proposed segmentation algorithm is to find a discriminating region of white blood cells on the HSI color space. Pixels with color lying in the discriminating region described by an ellipsoidal region will be regarded as the nucleus and granule of cytoplasm of a white blood cell. Then, through a further morphological process, we can segment a white blood cell from a smear image. Three kinds of features (i.e., geometrical features, color features, and LDP-based texture features are extracted from the segmented cell. These features are fed into three different kinds of neural networks to recognize the types of the white blood cells. To test the effectiveness of the proposed white blood cell classification system, a total of 450 white blood cells images were used. The highest overall correct recognition rate could reach 99.11% correct. Simulation results showed that the proposed white blood cell classification system was very competitive to some existing systems.

  9. Classification of schizophrenia patients based on resting-state functional network connectivity

    Directory of Open Access Journals (Sweden)

    Mohammad Reza Arbabshirani

    2013-07-01

    Full Text Available There is a growing interest in automatic classification of mental disorders based on neuroimaging data. Small training data sets (subjects and very large amount of high dimensional data make it a challenging task to design robust and accurate classifiers for heterogeneous disorders such as schizophrenia. Most previous studies considered structural MRI, diffusion tensor imaging and task-based fMRI for this purpose. However, resting-state data has been rarely used in discrimination of schizophrenia patients from healthy controls. Resting data are of great interest, since they are relatively easy to collect, and not confounded by behavioral performance on a task. Several linear and non-linear classification methods were trained using a training dataset and evaluate with a separate testing dataset. Results show that classification with high accuracy is achievable using simple non-linear discriminative methods such as k-nearest neighbors which is very promising. We compare and report detailed results of each classifier as well as statistical analysis and evaluation of each single feature. To our knowledge our effects represent the first use of resting-state functional network connectivity features to classify schizophrenia.

  10. Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach

    Directory of Open Access Journals (Sweden)

    Íñigo Molina

    2012-11-01

    Full Text Available This paper proposes the optimization relaxation approach based on the analogue Hopfield Neural Network (HNN for cluster refinement of pre-classified Polarimetric Synthetic Aperture Radar (PolSAR image data. We consider the initial classification provided by the maximum-likelihood classifier based on the complex Wishart distribution, which is then supplied to the HNN optimization approach. The goal is to improve the classification results obtained by the Wishart approach. The classification improvement is verified by computing a cluster separability coefficient and a measure of homogeneity within the clusters. During the HNN optimization process, for each iteration and for each pixel, two consistency coefficients are computed, taking into account two types of relations between the pixel under consideration and its corresponding neighbors. Based on these coefficients and on the information coming from the pixel itself, the pixel under study is re-classified. Different experiments are carried out to verify that the proposed approach outperforms other strategies, achieving the best results in terms of separability and a trade-off with the homogeneity preserving relevant structures in the image. The performance is also measured in terms of computational central processing unit (CPU times.

  11. An acoustical model based monitoring network

    NARCIS (Netherlands)

    Wessels, P.W.; Basten, T.G.H.; Eerden, F.J.M. van der

    2010-01-01

    In this paper the approach for an acoustical model based monitoring network is demonstrated. This network is capable of reconstructing a noise map, based on the combination of measured sound levels and an acoustic model of the area. By pre-calculating the sound attenuation within the network the

  12. A Categorical Framework for Model Classification in the Geosciences

    Science.gov (United States)

    Hauhs, Michael; Trancón y Widemann, Baltasar; Lange, Holger

    2016-04-01

    Models have a mixed record of success in the geosciences. In meteorology, model development and implementation has been among the first and most successful examples of triggering computer technology in science. On the other hand, notorious problems such as the 'equifinality issue' in hydrology lead to a rather mixed reputation of models in other areas. The most successful models in geosciences are applications of dynamic systems theory to non-living systems or phenomena. Thus, we start from the hypothesis that the success of model applications relates to the influence of life on the phenomenon under study. We thus focus on the (formal) representation of life in models. The aim is to investigate whether disappointment in model performance is due to system properties such as heterogeneity and historicity of ecosystems, or rather reflects an abstraction and formalisation problem at a fundamental level. As a formal framework for this investigation, we use category theory as applied in computer science to specify behaviour at an interface. Its methods have been developed for translating and comparing formal structures among different application areas and seems highly suited for a classification of the current "model zoo" in the geosciences. The approach is rather abstract, with a high degree of generality but a low level of expressibility. Here, category theory will be employed to check the consistency of assumptions about life in different models. It will be shown that it is sufficient to distinguish just four logical cases to check for consistency of model content. All four cases can be formalised as variants of coalgebra-algebra homomorphisms. It can be demonstrated that transitions between the four variants affect the relevant observations (time series or spatial maps), the formalisms used (equations, decision trees) and the test criteria of success (prediction, classification) of the resulting model types. We will present examples from hydrology and ecology in

  13. Learning Supervised Topic Models for Classification and Regression from Crowds

    DEFF Research Database (Denmark)

    Rodrigues, Filipe; Lourenco, Mariana; Ribeiro, Bernardete

    2017-01-01

    problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages...... annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression...

  14. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

  15. Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

    Science.gov (United States)

    Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

    2016-01-01

    Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

  16. Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

    Science.gov (United States)

    Lavreniuk, M. S.

    2016-12-01

    Land cover and crop type maps are one of the most essential inputs when dealing with environmental and agriculture monitoring tasks [1]. During long time neural network (NN) approach was one of the most efficient and popular approach for most applications, including crop classification using remote sensing data, with high an overall accuracy (OA) [2]. In the last years the most popular and efficient method for multi-sensor and multi-temporal land cover classification is convolution neural networks (CNNs). Taking into account presence clouds in optical data, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of optical imagery from Landsat-8 satellite. After missing data restoration, optical data from Landsat-8 was merged with Sentinel-1A radar data for better crop types discrimination [3]. An ensemble of CNNs is proposed for multi-temporal satellite images supervised classification. Each CNN in the corresponding ensemble is a 1-d CNN with 4 layers implemented using the Google's library TensorFlow. The efficiency of the proposed approach was tested on a time-series of Landsat-8 and Sentinel-1A images over the JECAM test site (Kyiv region) in Ukraine in 2015. Overall classification accuracy for ensemble of CNNs was 93.5% that outperformed an ensemble of multi-layer perceptrons (MLPs) by +0.8% and allowed us to better discriminate summer crops, in particular maize and soybeans. For 2016 we would like to validate this method using Sentinel-1 and Sentinel-2 data for Ukraine territory within ESA project on country level demonstration Sen2Agri. 1. A. Kolotii et al., "Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine," The Int. Arch. of Photogram., Rem. Sens. and Spatial Inform. Scie., vol. 40, no. 7, pp. 39-44, 2015. 2. F. Waldner et al., "Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity," Int. Journal of Rem. Sens. vol. 37, no. 14, pp

  17. Protein Structure Classification and Loop Modeling Using Multiple Ramachandran Distributions

    KAUST Repository

    Najibi, Seyed Morteza

    2017-02-08

    Recently, the study of protein structures using angular representations has attracted much attention among structural biologists. The main challenge is how to efficiently model the continuous conformational space of the protein structures based on the differences and similarities between different Ramachandran plots. Despite the presence of statistical methods for modeling angular data of proteins, there is still a substantial need for more sophisticated and faster statistical tools to model the large-scale circular datasets. To address this need, we have developed a nonparametric method for collective estimation of multiple bivariate density functions for a collection of populations of protein backbone angles. The proposed method takes into account the circular nature of the angular data using trigonometric spline which is more efficient compared to existing methods. This collective density estimation approach is widely applicable when there is a need to estimate multiple density functions from different populations with common features. Moreover, the coefficients of adaptive basis expansion for the fitted densities provide a low-dimensional representation that is useful for visualization, clustering, and classification of the densities. The proposed method provides a novel and unique perspective to two important and challenging problems in protein structure research: structure-based protein classification and angular-sampling-based protein loop structure prediction.

  18. Protein Structure Classification and Loop Modeling Using Multiple Ramachandran Distributions

    KAUST Repository

    Najibi, Seyed Morteza; Maadooliat, Mehdi; Zhou, Lan; Huang, Jianhua Z.; Gao, Xin

    2017-01-01

    Recently, the study of protein structures using angular representations has attracted much attention among structural biologists. The main challenge is how to efficiently model the continuous conformational space of the protein structures based on the differences and similarities between different Ramachandran plots. Despite the presence of statistical methods for modeling angular data of proteins, there is still a substantial need for more sophisticated and faster statistical tools to model the large-scale circular datasets. To address this need, we have developed a nonparametric method for collective estimation of multiple bivariate density functions for a collection of populations of protein backbone angles. The proposed method takes into account the circular nature of the angular data using trigonometric spline which is more efficient compared to existing methods. This collective density estimation approach is widely applicable when there is a need to estimate multiple density functions from different populations with common features. Moreover, the coefficients of adaptive basis expansion for the fitted densities provide a low-dimensional representation that is useful for visualization, clustering, and classification of the densities. The proposed method provides a novel and unique perspective to two important and challenging problems in protein structure research: structure-based protein classification and angular-sampling-based protein loop structure prediction.

  19. Likelihood ratio model for classification of forensic evidence

    Energy Technology Data Exchange (ETDEWEB)

    Zadora, G., E-mail: gzadora@ies.krakow.pl [Institute of Forensic Research, Westerplatte 9, 31-033 Krakow (Poland); Neocleous, T., E-mail: tereza@stats.gla.ac.uk [University of Glasgow, Department of Statistics, 15 University Gardens, Glasgow G12 8QW (United Kingdom)

    2009-05-29

    One of the problems of analysis of forensic evidence such as glass fragments, is the determination of their use-type category, e.g. does a glass fragment originate from an unknown window or container? Very small glass fragments arise during various accidents and criminal offences, and could be carried on the clothes, shoes and hair of participants. It is therefore necessary to obtain information on their physicochemical composition in order to solve the classification problem. Scanning Electron Microscopy coupled with an Energy Dispersive X-ray Spectrometer and the Glass Refractive Index Measurement method are routinely used in many forensic institutes for the investigation of glass. A natural form of glass evidence evaluation for forensic purposes is the likelihood ratio-LR = p(E|H{sub 1})/p(E|H{sub 2}). The main aim of this paper was to study the performance of LR models for glass object classification which considered one or two sources of data variability, i.e. between-glass-object variability and(or) within-glass-object variability. Within the proposed model a multivariate kernel density approach was adopted for modelling the between-object distribution and a multivariate normal distribution was adopted for modelling within-object distributions. Moreover, a graphical method of estimating the dependence structure was employed to reduce the highly multivariate problem to several lower-dimensional problems. The performed analysis showed that the best likelihood model was the one which allows to include information about between and within-object variability, and with variables derived from elemental compositions measured by SEM-EDX, and refractive values determined before (RI{sub b}) and after (RI{sub a}) the annealing process, in the form of dRI = log{sub 10}|RI{sub a} - RI{sub b}|. This model gave better results than the model with only between-object variability considered. In addition, when dRI and variables derived from elemental compositions were used, this

  20. Likelihood ratio model for classification of forensic evidence

    International Nuclear Information System (INIS)

    Zadora, G.; Neocleous, T.

    2009-01-01

    One of the problems of analysis of forensic evidence such as glass fragments, is the determination of their use-type category, e.g. does a glass fragment originate from an unknown window or container? Very small glass fragments arise during various accidents and criminal offences, and could be carried on the clothes, shoes and hair of participants. It is therefore necessary to obtain information on their physicochemical composition in order to solve the classification problem. Scanning Electron Microscopy coupled with an Energy Dispersive X-ray Spectrometer and the Glass Refractive Index Measurement method are routinely used in many forensic institutes for the investigation of glass. A natural form of glass evidence evaluation for forensic purposes is the likelihood ratio-LR = p(E|H 1 )/p(E|H 2 ). The main aim of this paper was to study the performance of LR models for glass object classification which considered one or two sources of data variability, i.e. between-glass-object variability and(or) within-glass-object variability. Within the proposed model a multivariate kernel density approach was adopted for modelling the between-object distribution and a multivariate normal distribution was adopted for modelling within-object distributions. Moreover, a graphical method of estimating the dependence structure was employed to reduce the highly multivariate problem to several lower-dimensional problems. The performed analysis showed that the best likelihood model was the one which allows to include information about between and within-object variability, and with variables derived from elemental compositions measured by SEM-EDX, and refractive values determined before (RI b ) and after (RI a ) the annealing process, in the form of dRI = log 10 |RI a - RI b |. This model gave better results than the model with only between-object variability considered. In addition, when dRI and variables derived from elemental compositions were used, this model outperformed two other

  1. Robust Automatic Modulation Classification Technique for Fading Channels via Deep Neural Network

    Directory of Open Access Journals (Sweden)

    Jung Hwan Lee

    2017-08-01

    Full Text Available In this paper, we propose a deep neural network (DNN-based automatic modulation classification (AMC for digital communications. While conventional AMC techniques perform well for additive white Gaussian noise (AWGN channels, classification accuracy degrades for fading channels where the amplitude and phase of channel gain change in time. The key contributions of this paper are in two phases. First, we analyze the effectiveness of a variety of statistical features for AMC task in fading channels. We reveal that the features that are shown to be effective for fading channels are different from those known to be good for AWGN channels. Second, we introduce a new enhanced AMC technique based on DNN method. We use the extensive and diverse set of statistical features found in our study for the DNN-based classifier. The fully connected feedforward network with four hidden layers are trained to classify the modulation class for several fading scenarios. Numerical evaluation shows that the proposed technique offers significant performance gain over the existing AMC methods in fading channels.

  2. Pre-optimization of radiotherapy treatment planning: an artificial neural network classification aided technique

    International Nuclear Information System (INIS)

    Hosseini-Ashrafi, M.E.; Bagherebadian, H.; Yahaqi, E.

    1999-01-01

    A method has been developed which, by using the geometric information from treatment sample cases, selects from a given data set an initial treatment plan as a step for treatment plan optimization. The method uses an artificial neural network (ANN) classification technique to select a best matching plan from the 'optimized' ANN database. Separate back-propagation ANN classifiers were trained using 50, 60 and 77 examples for three groups of treatment case classes (up to 21 examples from each class were used). The performance of the classifiers in selecting the correct treatment class was tested using the leave-one-out method; the networks were optimized with respect their architecture. For the three groups used in this study, successful classification fractions of 0.83, 0.98 and 0.93 were achieved by the optimized ANN classifiers. The automated response of the ANN may be used to arrive at a pre-plan where many treatment parameters may be identified and therefore a significant reduction in the steps required to arrive at the optimum plan may be achieved. Treatment planning 'experience' and also results from lengthy calculations may be used for training the ANN. (author)

  3. Classification of polycystic ovary based on ultrasound images using competitive neural network

    Science.gov (United States)

    Dewi, R. M.; Adiwijaya; Wisesty, U. N.; Jondri

    2018-03-01

    Infertility in the women reproduction system due to inhibition of follicles maturation process causing the number of follicles which is called polycystic ovaries (PCO). PCO detection is still operated manually by a gynecologist by counting the number and size of follicles in the ovaries, so it takes a long time and needs high accuracy. In general, PCO can be detected by calculating stereology or feature extraction and classification. In this paper, we designed a system to classify PCO by using the feature extraction (Gabor Wavelet method) and Competitive Neural Network (CNN). CNN was selected because this method is the combination between Hemming Net and The Max Net so that the data classification can be performed based on the specific characteristics of ultrasound data. Based on the result of system testing, Competitive Neural Network obtained the highest accuracy is 80.84% and the time process is 60.64 seconds (when using 32 feature vectors as well as weight and bias values respectively of 0.03 and 0.002).

  4. Spinal Cord Injury Model System Information Network

    Science.gov (United States)

    ... the UAB-SCIMS More The UAB-SCIMS Information Network The University of Alabama at Birmingham Spinal Cord Injury Model System (UAB-SCIMS) maintains this Information Network as a resource to promote knowledge in the ...

  5. Eight challenges for network epidemic models

    Directory of Open Access Journals (Sweden)

    Lorenzo Pellis

    2015-03-01

    Full Text Available Networks offer a fertile framework for studying the spread of infection in human and animal populations. However, owing to the inherent high-dimensionality of networks themselves, modelling transmission through networks is mathematically and computationally challenging. Even the simplest network epidemic models present unanswered questions. Attempts to improve the practical usefulness of network models by including realistic features of contact networks and of host–pathogen biology (e.g. waning immunity have made some progress, but robust analytical results remain scarce. A more general theory is needed to understand the impact of network structure on the dynamics and control of infection. Here we identify a set of challenges that provide scope for active research in the field of network epidemic models.

  6. Models of parallel computation :a survey and classification

    Institute of Scientific and Technical Information of China (English)

    ZHANG Yunquan; CHEN Guoliang; SUN Guangzhong; MIAO Qiankun

    2007-01-01

    In this paper,the state-of-the-art parallel computational model research is reviewed.We will introduce various models that were developed during the past decades.According to their targeting architecture features,especially memory organization,we classify these parallel computational models into three generations.These models and their characteristics are discussed based on three generations classification.We believe that with the ever increasing speed gap between the CPU and memory systems,incorporating non-uniform memory hierarchy into computational models will become unavoidable.With the emergence of multi-core CPUs,the parallelism hierarchy of current computing platforms becomes more and more complicated.Describing this complicated parallelism hierarchy in future computational models becomes more and more important.A semi-automatic toolkit that can extract model parameters and their values on real computers can reduce the model analysis complexity,thus allowing more complicated models with more parameters to be adopted.Hierarchical memory and hierarchical parallelism will be two very important features that should be considered in future model design and research.

  7. A neural network-based optimal spatial filter design method for motor imagery classification.

    Directory of Open Access Journals (Sweden)

    Ayhan Yuksel

    Full Text Available In this study, a novel spatial filter design method is introduced. Spatial filtering is an important processing step for feature extraction in motor imagery-based brain-computer interfaces. This paper introduces a new motor imagery signal classification method combined with spatial filter optimization. We simultaneously train the spatial filter and the classifier using a neural network approach. The proposed spatial filter network (SFN is composed of two layers: a spatial filtering layer and a classifier layer. These two layers are linked to each other with non-linear mapping functions. The proposed method addresses two shortcomings of the common spatial patterns (CSP algorithm. First, CSP aims to maximize the between-classes variance while ignoring the minimization of within-classes variances. Consequently, the features obtained using the CSP method may have large within-classes variances. Second, the maximizing optimization function of CSP increases the classification accuracy indirectly because an independent classifier is used after the CSP method. With SFN, we aimed to maximize the between-classes variance while minimizing within-classes variances and simultaneously optimizing the spatial filter and the classifier. To classify motor imagery EEG signals, we modified the well-known feed-forward structure and derived forward and backward equations that correspond to the proposed structure. We tested our algorithm on simple toy data. Then, we compared the SFN with conventional CSP and its multi-class version, called one-versus-rest CSP, on two data sets from BCI competition III. The evaluation results demonstrate that SFN is a good alternative for classifying motor imagery EEG signals with increased classification accuracy.

  8. Classification of brain MRI with big data and deep 3D convolutional neural networks

    Science.gov (United States)

    Wegmayr, Viktor; Aitharaju, Sai; Buhmann, Joachim

    2018-02-01

    Our ever-aging society faces the growing problem of neurodegenerative diseases, in particular dementia. Magnetic Resonance Imaging provides a unique tool for non-invasive investigation of these brain diseases. However, it is extremely difficult for neurologists to identify complex disease patterns from large amounts of three-dimensional images. In contrast, machine learning excels at automatic pattern recognition from large amounts of data. In particular, deep learning has achieved impressive results in image classification. Unfortunately, its application to medical image classification remains difficult. We consider two reasons for this difficulty: First, volumetric medical image data is considerably scarcer than natural images. Second, the complexity of 3D medical images is much higher compared to common 2D images. To address the problem of small data set size, we assemble the largest dataset ever used for training a deep 3D convolutional neural network to classify brain images as healthy (HC), mild cognitive impairment (MCI) or Alzheimers disease (AD). We use more than 20.000 images from subjects of these three classes, which is almost 9x the size of the previously largest data set. The problem of high dimensionality is addressed by using a deep 3D convolutional neural network, which is state-of-the-art in large-scale image classification. We exploit its ability to process the images directly, only with standard preprocessing, but without the need for elaborate feature engineering. Compared to other work, our workflow is considerably simpler, which increases clinical applicability. Accuracy is measured on the ADNI+AIBL data sets, and the independent CADDementia benchmark.

  9. Bone Turnover Status: Classification Model and Clinical Implications

    Science.gov (United States)

    Fisher, Alexander; Fisher, Leon; Srikusalanukul, Wichat; Smith, Paul N

    2018-01-01

    Aim: To develop a practical model for classification bone turnover status and evaluate its clinical usefulness. Methods: Our classification of bone turnover status is based on internationally recommended biomarkers of both bone formation (N-terminal propeptide of type1 procollagen, P1NP) and bone resorption (beta C-terminal cross-linked telopeptide of type I collagen, bCTX), using the cutoffs proposed as therapeutic targets. The relationships between turnover subtypes and clinical characteristic were assessed in1223 hospitalised orthogeriatric patients (846 women, 377 men; mean age 78.1±9.50 years): 451(36.9%) subjects with hip fracture (HF), 396(32.4%) with other non-vertebral (non-HF) fractures (HF) and 376 (30.7%) patients without fractures. Resalts: Six subtypes of bone turnover status were identified: 1 - normal turnover (P1NP>32 μg/L, bCTX≤0.250 μg/L and P1NP/bCTX>100.0[(median value]); 2- low bone formation (P1NP ≤32 μg/L), normal bone resorption (bCTX≤0.250 μg/L) and P1NP/bCTX>100.0 (subtype2A) or P1NP/bCTX0.250 μg/L) and P1NP/bCTXturnover (both markers elevated ) and P1NP/bCTX>100.0 (subtype 4A) or P1NP/bCTX75 years and hyperparathyroidism. Hypoalbuminaemia and not using osteoporotic therapy were two independent indicators common for subtypes 3, 4A and 4B; these three subtypes were associated with in-hospital mortality. Subtype 3 was associated with fractures (OR 1.7, for HF OR 2.4), age>75 years, chronic heart failure (CHF), anaemia, and history of malignancy, and predicted post-operative myocardial injury, high inflammatory response and length of hospital stay (LOS) above10 days. Subtype 4A was associated with chronic kidney disease (CKD), anaemia, history of malignancy and walking aids use and predicted LOS>20 days, but was not discriminative for fractures. Subtype 4B was associated with fractures (OR 2.1, for HF OR 2.5), age>75 years, CKD and indicated risks of myocardial injury, high inflammatory response and LOS>10 days. Conclusions: We

  10. Best Practices in Academic Management. Study Programs Classification Model

    Directory of Open Access Journals (Sweden)

    Ofelia Ema Aleca

    2016-05-01

    Full Text Available This article proposes and tests a set of performance indicators for the assessment of Bachelor and Master studies, from two perspectives: the study programs and the disciplines. The academic performance at the level of a study program shall be calculated based on success and efficiency rates, and at discipline level, on the basis of rates of efficiency, success and absenteeism. This research proposes a model of classification of the study programs within a Bachelor and Master cycle based on the education performance and efficiency. What recommends this model as a best practice model in academic management is the possibility of grouping a study program or a discipline in a particular category of efficiency

  11. Entropy Characterization of Random Network Models

    Directory of Open Access Journals (Sweden)

    Pedro J. Zufiria

    2017-06-01

    Full Text Available This paper elaborates on the Random Network Model (RNM as a mathematical framework for modelling and analyzing the generation of complex networks. Such framework allows the analysis of the relationship between several network characterizing features (link density, clustering coefficient, degree distribution, connectivity, etc. and entropy-based complexity measures, providing new insight on the generation and characterization of random networks. Some theoretical and computational results illustrate the utility of the proposed framework.

  12. The model of social crypto-network

    Directory of Open Access Journals (Sweden)

    Марк Миколайович Орел

    2015-06-01

    Full Text Available The article presents the theoretical model of social network with the enhanced mechanism of privacy policy. It covers the problems arising in the process of implementing the mentioned type of network. There are presented the methods of solving problems arising in the process of building the social network with privacy policy. It was built a theoretical model of social networks with enhanced information protection methods based on information and communication blocks

  13. Introducing Synchronisation in Deterministic Network Models

    DEFF Research Database (Denmark)

    Schiøler, Henrik; Jessen, Jan Jakob; Nielsen, Jens Frederik D.

    2006-01-01

    The paper addresses performance analysis for distributed real time systems through deterministic network modelling. Its main contribution is the introduction and analysis of models for synchronisation between tasks and/or network elements. Typical patterns of synchronisation are presented leading...... to the suggestion of suitable network models. An existing model for flow control is presented and an inherent weakness is revealed and remedied. Examples are given and numerically analysed through deterministic network modelling. Results are presented to highlight the properties of the suggested models...

  14. Neural network modeling of chaotic dynamics in nuclear reactor flows

    International Nuclear Information System (INIS)

    Welstead, S.T.

    1992-01-01

    Neural networks have many scientific applications in areas such as pattern classification and time series prediction. The universal approximation property of these networks, however, can also be exploited to provide researchers with tool for modeling observed nonlinear phenomena. It has been shown that multilayer feed forward networks can capture important global nonlinear properties, such as chaotic dynamics, merely by training the network on a finite set of observed data. The network itself then provides a model of the process that generated the data. Characterizations such as the existence and general shape of a strange attractor and the sign of the largest Lyapunov exponent can then be extracted from the neural network model. In this paper, the author applies this idea to data generated from a nonlinear process that is representative of convective flows that can arise in nuclear reactor applications. Such flows play a role in forced convection heat removal from pressurized water reactors and boiling water reactors, and decay heat removal from liquid-metal-cooled reactors, either by natural convection or by thermosyphons

  15. Classification of boreal forest by satellite and inventory data using neural network approach

    Science.gov (United States)

    Romanov, A. A.

    2012-12-01

    The main objective of this research was to develop methodology for boreal (Siberian Taiga) land cover classification in a high accuracy level. The study area covers the territories of Central Siberian several parts along the Yenisei River (60-62 degrees North Latitude): the right bank includes mixed forest and dark taiga, the left - pine forests; so were taken as a high heterogeneity and statistically equal surfaces concerning spectral characteristics. Two main types of data were used: time series of middle spatial resolution satellite images (Landsat 5, 7 and SPOT4) and inventory datasets from the nature fieldworks (used for training samples sets preparation). Method of collecting field datasets included a short botany description (type/species of vegetation, density, compactness of the crowns, individual height and max/min diameters representative of each type, surface altitude of the plot), at the same time the geometric characteristic of each training sample unit corresponded to the spatial resolution of satellite images and geo-referenced (prepared datasets both of the preliminary processing and verification). The network of test plots was planned as irregular and determined by the landscape oriented approach. The main focus of the thematic data processing has been allocated for the use of neural networks (fuzzy logic inc.); therefore, the results of field studies have been converting input parameter of type / species of vegetation cover of each unit and the degree of variability. Proposed approach involves the processing of time series separately for each image mainly for the verification: shooting parameters taken into consideration (time, albedo) and thus expected to assess the quality of mapping. So the input variables for the networks were sensor bands, surface altitude, solar angels and land surface temperature (for a few experiments); also given attention to the formation of the formula class on the basis of statistical pre-processing of results of

  16. Classification of Incomplete Data Based on Evidence Theory and an Extreme Learning Machine in Wireless Sensor Networks.

    Science.gov (United States)

    Zhang, Yang; Liu, Yun; Chao, Han-Chieh; Zhang, Zhenjiang; Zhang, Zhiyuan

    2018-03-30

    In wireless sensor networks, the classification of incomplete data reported by sensor nodes is an open issue because it is difficult to accurately estimate the missing values. In many cases, the misclassification is unacceptable considering that it probably brings catastrophic damages to the data users. In this paper, a novel classification approach of incomplete data is proposed to reduce the misclassification errors. This method uses the regularized extreme learning machine to estimate the potential values of missing data at first, and then it converts the estimations into multiple classification results on the basis of the distance between interval numbers. Finally, an evidential reasoning rule is adopted to fuse these classification results. The final decision is made according to the combined basic belief assignment. The experimental results show that this method has better performance than other traditional classification methods of incomplete data.

  17. Bayesian Network Webserver: a comprehensive tool for biological network modeling.

    Science.gov (United States)

    Ziebarth, Jesse D; Bhattacharya, Anindya; Cui, Yan

    2013-11-01

    The Bayesian Network Webserver (BNW) is a platform for comprehensive network modeling of systems genetics and other biological datasets. It allows users to quickly and seamlessly upload a dataset, learn the structure of the network model that best explains the data and use the model to understand relationships between network variables. Many datasets, including those used to create genetic network models, contain both discrete (e.g. genotype) and continuous (e.g. gene expression traits) variables, and BNW allows for modeling hybrid datasets. Users of BNW can incorporate prior knowledge during structure learning through an easy-to-use structural constraint interface. After structure learning, users are immediately presented with an interactive network model, which can be used to make testable hypotheses about network relationships. BNW, including a downloadable structure learning package, is available at http://compbio.uthsc.edu/BNW. (The BNW interface for adding structural constraints uses HTML5 features that are not supported by current version of Internet Explorer. We suggest using other browsers (e.g. Google Chrome or Mozilla Firefox) when accessing BNW). ycui2@uthsc.edu. Supplementary data are available at Bioinformatics online.

  18. Real-time classification and sensor fusion with a spiking deep belief network.

    Science.gov (United States)

    O'Connor, Peter; Neil, Daniel; Liu, Shih-Chii; Delbruck, Tobi; Pfeiffer, Michael

    2013-01-01

    Deep Belief Networks (DBNs) have recently shown impressive performance on a broad range of classification problems. Their generative properties allow better understanding of the performance, and provide a simpler solution for sensor fusion tasks. However, because of their inherent need for feedback and parallel update of large numbers of units, DBNs are expensive to implement on serial computers. This paper proposes a method based on the Siegert approximation for Integrate-and-Fire neurons to map an offline-trained DBN onto an efficient event-driven spiking neural network suitable for hardware implementation. The method is demonstrated in simulation and by a real-time implementation of a 3-layer network with 2694 neurons used for visual classification of MNIST handwritten digits with input from a 128 × 128 Dynamic Vision Sensor (DVS) silicon retina, and sensory-fusion using additional input from a 64-channel AER-EAR silicon cochlea. The system is implemented through the open-source software in the jAER project and runs in real-time on a laptop computer. It is demonstrated that the system can recognize digits in the presence of distractions, noise, scaling, translation and rotation, and that the degradation of recognition performance by using an event-based approach is less than 1%. Recognition is achieved in an average of 5.8 ms after the onset of the presentation of a digit. By cue integration from both silicon retina and cochlea outputs we show that the system can be biased to select the correct digit from otherwise ambiguous input.

  19. Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

    Science.gov (United States)

    Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

    2017-11-01

    Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

  20. A comparative study of deep learning models for medical image classification

    Science.gov (United States)

    Dutta, Suvajit; Manideep, B. C. S.; Rai, Shalva; Vijayarajan, V.

    2017-11-01

    Deep Learning(DL) techniques are conquering over the prevailing traditional approaches of neural network, when it comes to the huge amount of dataset, applications requiring complex functions demanding increase accuracy with lower time complexities. Neurosciences has already exploited DL techniques, thus portrayed itself as an inspirational source for researchers exploring the domain of Machine learning. DL enthusiasts cover the areas of vision, speech recognition, motion planning and NLP as well, moving back and forth among fields. This concerns with building models that can successfully solve variety of tasks requiring intelligence and distributed representation. The accessibility to faster CPUs, introduction of GPUs-performing complex vector and matrix computations, supported agile connectivity to network. Enhanced software infrastructures for distributed computing worked in strengthening the thought that made researchers suffice DL methodologies. The paper emphases on the following DL procedures to traditional approaches which are performed manually for classifying medical images. The medical images are used for the study Diabetic Retinopathy(DR) and computed tomography (CT) emphysema data. Both DR and CT data diagnosis is difficult task for normal image classification methods. The initial work was carried out with basic image processing along with K-means clustering for identification of image severity levels. After determining image severity levels ANN has been applied on the data to get the basic classification result, then it is compared with the result of DNNs (Deep Neural Networks), which performed efficiently because of its multiple hidden layer features basically which increases accuracy factors, but the problem of vanishing gradient in DNNs made to consider Convolution Neural Networks (CNNs) as well for better results. The CNNs are found to be providing better outcomes when compared to other learning models aimed at classification of images. CNNs are

  1. How to model wireless mesh networks topology

    International Nuclear Information System (INIS)

    Sanni, M L; Hashim, A A; Anwar, F; Ali, S; Ahmed, G S M

    2013-01-01

    The specification of network connectivity model or topology is the beginning of design and analysis in Computer Network researches. Wireless Mesh Networks is an autonomic network that is dynamically self-organised, self-configured while the mesh nodes establish automatic connectivity with the adjacent nodes in the relay network of wireless backbone routers. Researches in Wireless Mesh Networks range from node deployment to internetworking issues with sensor, Internet and cellular networks. These researches require modelling of relationships and interactions among nodes including technical characteristics of the links while satisfying the architectural requirements of the physical network. However, the existing topology generators model geographic topologies which constitute different architectures, thus may not be suitable in Wireless Mesh Networks scenarios. The existing methods of topology generation are explored, analysed and parameters for their characterisation are identified. Furthermore, an algorithm for the design of Wireless Mesh Networks topology based on square grid model is proposed in this paper. The performance of the topology generated is also evaluated. This research is particularly important in the generation of a close-to-real topology for ensuring relevance of design to the intended network and validity of results obtained in Wireless Mesh Networks researches

  2. Model checking mobile ad hoc networks

    NARCIS (Netherlands)

    Ghassemi, Fatemeh; Fokkink, Wan

    2016-01-01

    Modeling arbitrary connectivity changes within mobile ad hoc networks (MANETs) makes application of automated formal verification challenging. We use constrained labeled transition systems as a semantic model to represent mobility. To model check MANET protocols with respect to the underlying

  3. PRED-CLASS: cascading neural networks for generalized protein classification and genome-wide applications.

    Science.gov (United States)

    Pasquier, C; Promponas, V J; Hamodrakas, S J

    2001-08-15

    A cascading system of hierarchical, artificial neural networks (named PRED-CLASS) is presented for the generalized classification of proteins into four distinct classes-transmembrane, fibrous, globular, and mixed-from information solely encoded in their amino acid sequences. The architecture of the individual component networks is kept very simple, reducing the number of free parameters (network synaptic weights) for faster training, improved generalization, and the avoidance of data overfitting. Capturing information from as few as 50 protein sequences spread among the four target classes (6 transmembrane, 10 fibrous, 13 globular, and 17 mixed), PRED-CLASS was able to obtain 371 correct predictions out of a set of 387 proteins (success rate approximately 96%) unambiguously assigned into one of the target classes. The application of PRED-CLASS to several test sets and complete proteomes of several organisms demonstrates that such a method could serve as a valuable tool in the annotation of genomic open reading frames with no functional assignment or as a preliminary step in fold recognition and ab initio structure prediction methods. Detailed results obtained for various data sets and completed genomes, along with a web sever running the PRED-CLASS algorithm, can be accessed over the World Wide Web at http://o2.biol.uoa.gr/PRED-CLASS.

  4. EEG signal classification using PSO trained RBF neural network for epilepsy identification

    Directory of Open Access Journals (Sweden)

    Sandeep Kumar Satapathy

    Full Text Available The electroencephalogram (EEG is a low amplitude signal generated in the brain, as a result of information flow during the communication of several neurons. Hence, careful analysis of these signals could be useful in understanding many human brain disorder diseases. One such disease topic is epileptic seizure identification, which can be identified via a classification process of the EEG signal after preprocessing with the discrete wavelet transform (DWT. To classify the EEG signal, we used a radial basis function neural network (RBFNN. As shown herein, the network can be trained to optimize the mean square error (MSE by using a modified particle swarm optimization (PSO algorithm. The key idea behind the modification of PSO is to introduce a method to overcome the problem of slow searching in and around the global optimum solution. The effectiveness of this procedure was verified by an experimental analysis on a benchmark dataset which is publicly available. The result of our experimental analysis revealed that the improvement in the algorithm is significant with respect to RBF trained by gradient descent and canonical PSO. Here, two classes of EEG signals were considered: the first being an epileptic and the other being non-epileptic. The proposed method produced a maximum accuracy of 99% as compared to the other techniques. Keywords: Electroencephalography, Radial basis function neural network, Particle swarm optimization, Discrete wavelet transform, Machine learning

  5. Characterization of Schizophrenia Adverse Drug Interactions through a Network Approach and Drug Classification

    Directory of Open Access Journals (Sweden)

    Jingchun Sun

    2013-01-01

    Full Text Available Antipsychotic drugs are medications commonly for schizophrenia (SCZ treatment, which include two groups: typical and atypical. SCZ patients have multiple comorbidities, and the coadministration of drugs is quite common. This may result in adverse drug-drug interactions, which are events that occur when the effect of a drug is altered by the coadministration of another drug. Therefore, it is important to provide a comprehensive view of these interactions for further coadministration improvement. Here, we extracted SCZ drugs and their adverse drug interactions from the DrugBank and compiled a SCZ-specific adverse drug interaction network. This network included 28 SCZ drugs, 241 non-SCZs, and 991 interactions. By integrating the Anatomical Therapeutic Chemical (ATC classification with the network analysis, we characterized those interactions. Our results indicated that SCZ drugs tended to have more adverse drug interactions than other drugs. Furthermore, SCZ typical drugs had significant interactions with drugs of the “alimentary tract and metabolism” category while SCZ atypical drugs had significant interactions with drugs of the categories “nervous system” and “antiinfectives for systemic uses.” This study is the first to characterize the adverse drug interactions in the course of SCZ treatment and might provide useful information for the future SCZ treatment.

  6. MetaNetter 2: A Cytoscape plugin for ab initio network analysis and metabolite feature classification.

    Science.gov (United States)

    Burgess, K E V; Borutzki, Y; Rankin, N; Daly, R; Jourdan, F

    2017-12-15

    Metabolomics frequently relies on the use of high resolution mass spectrometry data. Classification and filtering of this data remain a challenging task due to the plethora of complex mass spectral artefacts, chemical noise, adducts and fragmentation that occur during ionisation and analysis. Additionally, the relationships between detected compounds can provide a wealth of information about the nature of the samples and the biochemistry that gave rise to them. We present a biochemical networking tool: MetaNetter 2 that is based on the original MetaNetter, a Cytoscape plugin that creates ab initio networks. The new version supports two major improvements: the generation of adduct networks and the creation of tables that map adduct or transformation patterns across multiple samples, providing a readout of compound relationships. We have applied this tool to the analysis of adduct patterns in the same sample separated under two different chromatographies, allowing inferences to be made about the effect of different buffer conditions on adduct detection, and the application of the chemical transformation analysis to both a single fragmentation analysis and an all-ions fragmentation dataset. Finally, we present an analysis of a dataset derived from anaerobic and aerobic growth of the organism Staphylococcus aureus demonstrating the utility of the tool for biological analysis. Copyright © 2017 The Author(s). Published by Elsevier B.V. All rights reserved.

  7. Nuclear power plant transient diagnostics using artificial neural networks that allow ''don't-know'' classifications

    International Nuclear Information System (INIS)

    Bartal, Y.; Lin, J.; Uhrig, R.E.

    1995-01-01

    A nuclear power plant's (NPP's) status is usually monitored by a human operator. Any classifier system used to enhance the operator's capability to diagnose a safety-critical system like an NPP should classify a novel transient as ''don't-know'' if it is not contained within its accumulated knowledge base. In particular, the classifier needs some kind of proximity measure between the new data and its training set. Artificial neural networks have been proposed as NPP classifiers, the most popular ones being the multilayered perceptron (MLP) type. However, MLPs do not have a proximity measure, while learning vector quantization, probabilistic neural networks (PNNs), and some others do. This proximity measure may also serve as an explanation to the classifier's decision in the way that case-based-reasoning expert systems do. The capability of a PNN network as a classifier is demonstrated using simulator data for the three-loop 436-MW(electric) Westinghouse San Onofre unit 1 pressurized water reactor. A transient's classification history is used in an ''evidence accumulation'' technique to enhance a classifier's accuracy as well as its consistency

  8. Neural network multispectral satellite images classification of volcanic ash plumes in a cloudy scenario

    Directory of Open Access Journals (Sweden)

    Matteo Picchiani

    2015-03-01

    Full Text Available This work shows the potential use of neural networks in the characterization of eruptive events monitored by satellite, through fast and automatic classification of multispectral images. The algorithm has been developed for the MODIS instrument and can easily be extended to other similar sensors. Six classes have been defined paying particular attention to image regions that represent the different surfaces that could possibly be found under volcanic ash clouds. Complex cloudy scenarios composed by images collected during the Icelandic eruptions of the Eyjafjallajökull (2010 and Grimsvötn (2011 volcanoes have been considered as test cases. A sensitivity analysis on the MODIS TIR and VIS channels has been performed to optimize the algorithm. The neural network has been trained with the first image of the dataset, while the remaining data have been considered as independent validation sets. Finally, the neural network classifier’s results have been compared with maps classified with several interactive procedures performed in a consolidated operational framework. This comparison shows that the automatic methodology proposed achieves a very promising performance, showing an overall accuracy greater than 84%, for the Eyjafjalla - jökull event, and equal to 74% for the Grimsvötn event. 

  9. Comparison between Possibilistic c-Means (PCM and Artificial Neural Network (ANN Classification Algorithms in Land use/ Land cover Classification

    Directory of Open Access Journals (Sweden)

    Ganchimeg Ganbold

    2017-03-01

    Full Text Available There are several statistical classification algorithms available for landuse/land cover classification. However, each has a certain bias orcompromise. Some methods like the parallel piped approach in supervisedclassification, cannot classify continuous regions within a feature. Onthe other hand, while unsupervised classification method takes maximumadvantage of spectral variability in an image, the maximally separableclusters in spectral space may not do much for our perception of importantclasses in a given study area. In this research, the output of an ANNalgorithm was compared with the Possibilistic c-Means an improvementof the fuzzy c-Means on both moderate resolutions Landsat8 and a highresolution Formosat 2 images. The Formosat 2 image comes with an8m spectral resolution on the multispectral data. This multispectral imagedata was resampled to 10m in order to maintain a uniform ratio of1:3 against Landsat 8 image. Six classes were chosen for analysis including:Dense forest, eucalyptus, water, grassland, wheat and riverine sand. Using a standard false color composite (FCC, the six features reflecteddifferently in the infrared region with wheat producing the brightestpixel values. Signature collection per class was therefore easily obtainedfor all classifications. The output of both ANN and FCM, were analyzedseparately for accuracy and an error matrix generated to assess the qualityand accuracy of the classification algorithms. When you compare theresults of the two methods on a per-class-basis, ANN had a crisperoutput compared to PCM which yielded clusters with pixels especiallyon the moderate resolution Landsat 8 imagery.

  10. Agent-based modeling and network dynamics

    CERN Document Server

    Namatame, Akira

    2016-01-01

    The book integrates agent-based modeling and network science. It is divided into three parts, namely, foundations, primary dynamics on and of social networks, and applications. The book begins with the network origin of agent-based models, known as cellular automata, and introduce a number of classic models, such as Schelling’s segregation model and Axelrod’s spatial game. The essence of the foundation part is the network-based agent-based models in which agents follow network-based decision rules. Under the influence of the substantial progress in network science in late 1990s, these models have been extended from using lattices into using small-world networks, scale-free networks, etc. The book also shows that the modern network science mainly driven by game-theorists and sociophysicists has inspired agent-based social scientists to develop alternative formation algorithms, known as agent-based social networks. The book reviews a number of pioneering and representative models in this family. Upon the gi...

  11. Curriculum Assessment Using Artificial Neural Network and Support Vector Machine Modeling Approaches: A Case Study. IR Applications. Volume 29

    Science.gov (United States)

    Chen, Chau-Kuang

    2010-01-01

    Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…

  12. Thyroid Nodule Classification in Ultrasound Images by Fine-Tuning Deep Convolutional Neural Network.

    Science.gov (United States)

    Chi, Jianning; Walia, Ekta; Babyn, Paul; Wang, Jimmy; Groot, Gary; Eramian, Mark

    2017-08-01

    With many thyroid nodules being incidentally detected, it is important to identify as many malignant nodules as possible while excluding those that are highly likely to be benign from fine needle aspiration (FNA) biopsies or surgeries. This paper presents a computer-aided diagnosis (CAD) system for classifying thyroid nodules in ultrasound images. We use deep learning approach to extract features from thyroid ultrasound images. Ultrasound images are pre-processed to calibrate their scale and remove the artifacts. A pre-trained GoogLeNet model is then fine-tuned using the pre-processed image samples which leads to superior feature extraction. The extracted features of the thyroid ultrasound images are sent to a Cost-sensitive Random Forest classifier to classify the images into "malignant" and "benign" cases. The experimental results show the proposed fine-tuned GoogLeNet model achieves excellent classification performance, attaining 98.29% classification accuracy, 99.10% sensitivity and 93.90% specificity for the images in an open access database (Pedraza et al. 16), while 96.34% classification accuracy, 86% sensitivity and 99% specificity for the images in our local health region database.

  13. Nonparametric Bayesian Modeling of Complex Networks

    DEFF Research Database (Denmark)

    Schmidt, Mikkel Nørgaard; Mørup, Morten

    2013-01-01

    an infinite mixture model as running example, we go through the steps of deriving the model as an infinite limit of a finite parametric model, inferring the model parameters by Markov chain Monte Carlo, and checking the model?s fit and predictive performance. We explain how advanced nonparametric models......Modeling structure in complex networks using Bayesian nonparametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This article provides a gentle introduction to nonparametric Bayesian modeling of complex networks: Using...

  14. Automated method for identification and artery-venous classification of vessel trees in retinal vessel networks.

    Science.gov (United States)

    Joshi, Vinayak S; Reinhardt, Joseph M; Garvin, Mona K; Abramoff, Michael D

    2014-01-01

    The separation of the retinal vessel network into distinct arterial and venous vessel trees is of high interest. We propose an automated method for identification and separation of retinal vessel trees in a retinal color image by converting a vessel segmentation image into a vessel segment map and identifying the individual vessel trees by graph search. Orientation, width, and intensity of each vessel segment are utilized to find the optimal graph of vessel segments. The separated vessel trees are labeled as primary vessel or branches. We utilize the separated vessel trees for arterial-venous (AV) classification, based on the color properties of the vessels in each tree graph. We applied our approach to a dataset of 50 fundus images from 50 subjects. The proposed method resulted in an accuracy of 91.44% correctly classified vessel pixels as either artery or vein. The accuracy of correctly classified major vessel segments was 96.42%.

  15. Classification of physical exercises using a triaxial accelerometer in a smartphone and an artificial neural network

    Directory of Open Access Journals (Sweden)

    Cakić Nikola

    2017-01-01

    Full Text Available The prevalence of smartphones and their adequate computer skills can be used for detecting everyday physical exercises. Acquired information on performed exercises can be used in the field of Health Informatics. For identification of particular physical activity a number of sensors and their repositioning during exercises are needed. This paper presents a way to classify the type of exercise using only triaxial built-in accelerometric sensor in the smartphone. The smartphone itself is free to move inside the subject pocket. The problem of using a number of sensors and their repositioning during exercise is solved by raw signal filtering and by defining a set of signal descriptors. Nine characteristic exercises have been analyzed for different programs and levels of exercise. To filter the raw accelerometer signal a low-pass 10-th order Butterworth filter is used. The filtered signals are described in terms of five descriptors which are used to train an artificial neural network (ANN. Classification of the type of exercise is performed using ANN with an error of 0.7%. Some exercises can be performed with only left or right leg. The classification accuracy of proposed approach is tested in a way that the smartphone was always in the subject's right pocket even when the exercise is performed using left leg only.

  16. Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients.

    Science.gov (United States)

    Ebrahimi, Farideh; Mikaeili, Mohammad; Estrada, Edson; Nazeran, Homer

    2008-01-01

    Currently in the world there is an alarming number of people who suffer from sleep disorders. A number of biomedical signals, such as EEG, EMG, ECG and EOG are used in sleep labs among others for diagnosis and treatment of sleep related disorders. The usual method for sleep stage classification is visual inspection by a sleep specialist. This is a very time consuming and laborious exercise. Automatic sleep stage classification can facilitate this process. The definition of sleep stages and the sleep literature show that EEG signals are similar in Stage 1 of non-rapid eye movement (NREM) sleep and rapid eye movement (REM) sleep. Therefore, in this work an attempt was made to classify four sleep stages consisting of Awake, Stage 1 + REM, Stage 2 and Slow Wave Stage based on the EEG signal alone. Wavelet packet coefficients and artificial neural networks were deployed for this purpose. Seven all night recordings from Physionet database were used in the study. The results demonstrated that these four sleep stages could be automatically discriminated from each other with a specificity of 94.4 +/- 4.5%, a of sensitivity 84.2+3.9% and an accuracy of 93.0 +/- 4.0%.

  17. Classification by a neural network approach applied to non destructive testing

    International Nuclear Information System (INIS)

    Lefevre, M.; Preteux, F.; Lavayssiere, B.

    1995-01-01

    Radiography is used by EDF for pipe inspection in nuclear power plants in order to detect defects. The radiographs obtained are then digitized in a well-defined protocol. The aim of EDF consists of developing a non destructive testing system for recognizing defects. In this paper, we describe the recognition procedure of areas with defects. We first present the digitization protocol, specifies the poor quality of images under study and propose a procedure to enhance defects. We then examine the problem raised by the choice of good features for classification. After having proved that statistical or standard textural features such as homogeneity, entropy or contrast are not relevant, we develop a geometrical-statistical approach based on the cooperation between signal correlations study and regional extrema analysis. The principle consists of analysing and comparing for areas with defects and without any defect, the evolution of conditional probabilities matrices for increasing neighborhood sizes, the shape of variograms and the location of regional minima. We demonstrate that anisotropy and surface of series of 'comet tails' associated with probability matrices, variograms slope and statistical indices, regional extrema location, are features able to discriminate areas with defects from areas without any. The classification is then realized by a neural network, which structure, properties and learning mechanisms are detailed. Finally we discuss the results. (authors). 21 refs., 5 figs

  18. Site classification of Indian strong motion network using response spectra ratios

    Science.gov (United States)

    Chopra, Sumer; Kumar, Vikas; Choudhury, Pallabee; Yadav, R. B. S.

    2018-03-01

    In the present study, we tried to classify the Indian strong motion sites spread all over Himalaya and adjoining region, located on varied geological formations, based on response spectral ratio. A total of 90 sites were classified based on 395 strong motion records from 94 earthquakes recorded at these sites. The magnitude of these earthquakes are between 2.3 and 7.7 and the hypocentral distance for most of the cases is less than 50 km. The predominant period obtained from response spectral ratios is used to classify these sites. It was found that the shape and predominant peaks of the spectra at these sites match with those in Japan, Italy, Iran, and at some of the sites in Europe and the same classification scheme can be applied to Indian strong motion network. We found that the earlier schemes based on description of near-surface geology, geomorphology, and topography were not able to capture the effect of sediment thickness. The sites are classified into seven classes (CL-I to CL-VII) with varying predominant periods and ranges as proposed by Alessandro et al. (Bull Seismol Soc Am 102:680-695 2012). The effect of magnitudes and hypocentral distances on the shape and predominant peaks were also studied and found to be very small. The classification scheme is robust and cost-effective and can be used in region-specific attenuation relationships for accounting local site effect.

  19. Localization and Classification of Paddy Field Pests using a Saliency Map and Deep Convolutional Neural Network

    Science.gov (United States)

    Liu, Ziyi; Gao, Junfeng; Yang, Guoguo; Zhang, Huan; He, Yong

    2016-01-01

    We present a pipeline for the visual localization and classification of agricultural pest insects by computing a saliency map and applying deep convolutional neural network (DCNN) learning. First, we used a global contrast region-based approach to compute a saliency map for localizing pest insect objects. Bounding squares containing targets were then extracted, resized to a fixed size, and used to construct a large standard database called Pest ID. This database was then utilized for self-learning of local image features which were, in turn, used for classification by DCNN. DCNN learning optimized the critical parameters, including size, number and convolutional stride of local receptive fields, dropout ratio and the final loss function. To demonstrate the practical utility of using DCNN, we explored different architectures by shrinking depth and width, and found effective sizes that can act as alternatives for practical applications. On the test set of paddy field images, our architectures achieved a mean Accuracy Precision (mAP) of 0.951, a significant improvement over previous methods. PMID:26864172

  20. A comparative study of machine learning models for ethnicity classification

    Science.gov (United States)

    Trivedi, Advait; Bessie Amali, D. Geraldine

    2017-11-01

    This paper endeavours to adopt a machine learning approach to solve the problem of ethnicity recognition. Ethnicity identification is an important vision problem with its use cases being extended to various domains. Despite the multitude of complexity involved, ethnicity identification comes naturally to humans. This meta information can be leveraged to make several decisions, be it in target marketing or security. With the recent development of intelligent systems a sub module to efficiently capture ethnicity would be useful in several use cases. Several attempts to identify an ideal learning model to represent a multi-ethnic dataset have been recorded. A comparative study of classifiers such as support vector machines, logistic regression has been documented. Experimental results indicate that the logical classifier provides a much accurate classification than the support vector machine.

  1. Familial or Sporadic Idiopathic Scoliosis – classification based on artificial neural network and GAPDH and ACTB transcription profile

    Science.gov (United States)

    2013-01-01

    Background Importance of hereditary factors in the etiology of Idiopathic Scoliosis is widely accepted. In clinical practice some of the IS patients present with positive familial history of the deformity and some do not. Traditionally about 90% of patients have been considered as sporadic cases without familial recurrence. However the exact proportion of Familial and Sporadic Idiopathic Scoliosis is still unknown. Housekeeping genes encode proteins that are usually essential for the maintenance of basic cellular functions. ACTB and GAPDH are two housekeeping genes encoding respectively a cytoskeletal protein β-actin, and glyceraldehyde-3-phosphate dehydrogenase, an enzyme of glycolysis. Although their expression levels can fluctuate between different tissues and persons, human housekeeping genes seem to exhibit a preserved tissue-wide expression ranking order. It was hypothesized that expression ranking order of two representative housekeeping genes ACTB and GAPDH might be disturbed in the tissues of patients with Familial Idiopathic Scoliosis (with positive family history of idiopathic scoliosis) opposed to the patients with no family members affected (Sporadic Idiopathic Scoliosis). An artificial neural network (ANN) was developed that could serve to differentiate between familial and sporadic cases of idiopathic scoliosis based on the expression levels of ACTB and GAPDH in different tissues of scoliotic patients. The aim of the study was to investigate whether the expression levels of ACTB and GAPDH in different tissues of idiopathic scoliosis patients could be used as a source of data for specially developed artificial neural network in order to predict the positive family history of index patient. Results The comparison of developed models showed, that the most satisfactory classification accuracy was achieved for ANN model with 18 nodes in the first hidden layer and 16 nodes in the second hidden layer. The classification accuracy for positive Idiopathic

  2. Network structure exploration via Bayesian nonparametric models

    International Nuclear Information System (INIS)

    Chen, Y; Wang, X L; Xiang, X; Tang, B Z; Bu, J Z

    2015-01-01

    Complex networks provide a powerful mathematical representation of complex systems in nature and society. To understand complex networks, it is crucial to explore their internal structures, also called structural regularities. The task of network structure exploration is to determine how many groups there are in a complex network and how to group the nodes of the network. Most existing structure exploration methods need to specify either a group number or a certain type of structure when they are applied to a network. In the real world, however, the group number and also the certain type of structure that a network has are usually unknown in advance. To explore structural regularities in complex networks automatically, without any prior knowledge of the group number or the certain type of structure, we extend a probabilistic mixture model that can handle networks with any type of structure but needs to specify a group number using Bayesian nonparametric theory. We also propose a novel Bayesian nonparametric model, called the Bayesian nonparametric mixture (BNPM) model. Experiments conducted on a large number of networks with different structures show that the BNPM model is able to explore structural regularities in networks automatically with a stable, state-of-the-art performance. (paper)

  3. Nearest patch matching for color image segmentation supporting neural network classification in pulmonary tuberculosis identification

    Science.gov (United States)

    Rulaningtyas, Riries; Suksmono, Andriyan B.; Mengko, Tati L. R.; Saptawati, Putri

    2016-03-01

    Pulmonary tuberculosis is a deadly infectious disease which occurs in many countries in Asia and Africa. In Indonesia, many people with tuberculosis disease are examined in the community health center. Examination of pulmonary tuberculosis is done through sputum smear with Ziehl - Neelsen staining using conventional light microscope. The results of Ziehl - Neelsen staining will give effect to the appearance of tuberculosis (TB) bacteria in red color and sputum background in blue color. The first examination is to detect the presence of TB bacteria from its color, then from the morphology of the TB bacteria itself. The results of Ziehl - Neelsen staining in sputum smear give the complex color images, so that the clinicians have difficulty when doing slide examination manually because it is time consuming and needs highly training to detect the presence of TB bacteria accurately. The clinicians have heavy workload to examine many sputum smear slides from the patients. To assist the clinicians when reading the sputum smear slide, this research built computer aided diagnose with color image segmentation, feature extraction, and classification method. This research used K-means clustering with patch technique to segment digital sputum smear images which separated the TB bacteria images from the background images. This segmentation method gave the good accuracy 97.68%. Then, feature extraction based on geometrical shape of TB bacteria was applied to this research. The last step, this research used neural network with back propagation method to classify TB bacteria and non TB bacteria images in sputum slides. The classification result of neural network back propagation are learning time (42.69±0.02) second, the number of epoch 5000, error rate of learning 15%, learning accuracy (98.58±0.01)%, and test accuracy (96.54±0.02)%.

  4. Neurons from the adult human dentate nucleus: neural networks in the neuron classification.

    Science.gov (United States)

    Grbatinić, Ivan; Marić, Dušica L; Milošević, Nebojša T

    2015-04-07

    Topological (central vs. border neuron type) and morphological classification of adult human dentate nucleus neurons according to their quantified histomorphological properties using neural networks on real and virtual neuron samples. In the real sample 53.1% and 14.1% of central and border neurons, respectively, are classified correctly with total of 32.8% of misclassified neurons. The most important result present 62.2% of misclassified neurons in border neurons group which is even greater than number of correctly classified neurons (37.8%) in that group, showing obvious failure of network to classify neurons correctly based on computational parameters used in our study. On the virtual sample 97.3% of misclassified neurons in border neurons group which is much greater than number of correctly classified neurons (2.7%) in that group, again confirms obvious failure of network to classify neurons correctly. Statistical analysis shows that there is no statistically significant difference in between central and border neurons for each measured parameter (p>0.05). Total of 96.74% neurons are morphologically classified correctly by neural networks and each one belongs to one of the four histomorphological types: (a) neurons with small soma and short dendrites, (b) neurons with small soma and long dendrites, (c) neuron with large soma and short dendrites, (d) neurons with large soma and long dendrites. Statistical analysis supports these results (pneurons can be classified in four neuron types according to their quantitative histomorphological properties. These neuron types consist of two neuron sets, small and large ones with respect to their perykarions with subtypes differing in dendrite length i.e. neurons with short vs. long dendrites. Besides confirmation of neuron classification on small and large ones, already shown in literature, we found two new subtypes i.e. neurons with small soma and long dendrites and with large soma and short dendrites. These neurons are

  5. Automated radial basis function neural network based image classification system for diabetic retinopathy detection in retinal images

    Science.gov (United States)

    Anitha, J.; Vijila, C. Kezi Selva; Hemanth, D. Jude

    2010-02-01

    Diabetic retinopathy (DR) is a chronic eye disease for which early detection is highly essential to avoid any fatal results. Image processing of retinal images emerge as a feasible tool for this early diagnosis. Digital image processing techniques involve image classification which is a significant technique to detect the abnormality in the eye. Various automated classification systems have been developed in the recent years but most of them lack high classification accuracy. Artificial neural networks are the widely preferred artificial intelligence technique since it yields superior results in terms of classification accuracy. In this work, Radial Basis function (RBF) neural network based bi-level classification system is proposed to differentiate abnormal DR Images and normal retinal images. The results are analyzed in terms of classification accuracy, sensitivity and specificity. A comparative analysis is performed with the results of the probabilistic classifier namely Bayesian classifier to show the superior nature of neural classifier. Experimental results show promising results for the neural classifier in terms of the performance measures.

  6. Classification of NLO operators for composite Higgs models

    Science.gov (United States)

    Alanne, Tommi; Bizot, Nicolas; Cacciapaglia, Giacomo; Sannino, Francesco

    2018-04-01

    We provide a general classification of template operators, up to next-to-leading order, that appear in chiral perturbation theories based on the two flavor patterns of spontaneous symmetry breaking SU (NF)/Sp (NF) and SU (NF)/SO (NF). All possible explicit-breaking sources parametrized by spurions transforming in the fundamental and in the two-index representations of the flavor symmetry are included. While our general framework can be applied to any model of strong dynamics, we specialize to composite-Higgs models, where the main explicit breaking sources are a current mass, the gauging of flavor symmetries, and the Yukawa couplings (for the top). For the top, we consider both bilinear couplings and linear ones à la partial compositeness. Our templates provide a basis for lattice calculations in specific models. As a special example, we consider the SU (4 )/Sp (4 )≅SO (6 )/SO (5 ) pattern which corresponds to the minimal fundamental composite-Higgs model. We further revisit issues related to the misalignment of the vacuum. In particular, we shed light on the physical properties of the singlet η , showing that it cannot develop a vacuum expectation value without explicit C P violation in the underlying theory.

  7. Modelling the structure of complex networks

    DEFF Research Database (Denmark)

    Herlau, Tue

    networks has been independently studied as mathematical objects in their own right. As such, there has been both an increased demand for statistical methods for complex networks as well as a quickly growing mathematical literature on the subject. In this dissertation we explore aspects of modelling complex....... The next chapters will treat some of the various symmetries, representer theorems and probabilistic structures often deployed in the modelling complex networks, the construction of sampling methods and various network models. The introductory chapters will serve to provide context for the included written...

  8. Model sparsity and brain pattern interpretation of classification models in neuroimaging

    DEFF Research Database (Denmark)

    Rasmussen, Peter Mondrup; Madsen, Kristoffer Hougaard; Churchill, Nathan W

    2012-01-01

    Interest is increasing in applying discriminative multivariate analysis techniques to the analysis of functional neuroimaging data. Model interpretation is of great importance in the neuroimaging context, and is conventionally based on a ‘brain map’ derived from the classification model. In this ...

  9. Effects of sample survey design on the accuracy of classification tree models in species distribution models

    Science.gov (United States)

    Thomas C. Edwards; D. Richard Cutler; Niklaus E. Zimmermann; Linda Geiser; Gretchen G. Moisen

    2006-01-01

    We evaluated the effects of probabilistic (hereafter DESIGN) and non-probabilistic (PURPOSIVE) sample surveys on resultant classification tree models for predicting the presence of four lichen species in the Pacific Northwest, USA. Models derived from both survey forms were assessed using an independent data set (EVALUATION). Measures of accuracy as gauged by...

  10. Packet Classification by Multilevel Cutting of the Classification Space: An Algorithmic-Architectural Solution for IP Packet Classification in Next Generation Networks

    Directory of Open Access Journals (Sweden)

    Motasem Aldiab

    2008-01-01

    Full Text Available Traditionally, the Internet provides only a “best-effort” service, treating all packets going to the same destination equally. However, providing differentiated services for different users based on their quality requirements is increasingly becoming a demanding issue. For this, routers need to have the capability to distinguish and isolate traffic belonging to different flows. This ability to determine the flow each packet belongs to is called packet classification. Technology vendors are reluctant to support algorithmic solutions for classification due to their nondeterministic performance. Although content addressable memories (CAMs are favoured by technology vendors due to their deterministic high-lookup rates, they suffer from the problems of high-power consumption and high-silicon cost. This paper provides a new algorithmic-architectural solution for packet classification that mixes CAMs with algorithms based on multilevel cutting of the classification space into smaller spaces. The provided solution utilizes the geometrical distribution of rules in the classification space. It provides the deterministic performance of CAMs, support for dynamic updates, and added flexibility for system designers.

  11. Building functional networks of spiking model neurons.

    Science.gov (United States)

    Abbott, L F; DePasquale, Brian; Memmesheimer, Raoul-Martin

    2016-03-01

    Most of the networks used by computer scientists and many of those studied by modelers in neuroscience represent unit activities as continuous variables. Neurons, however, communicate primarily through discontinuous spiking. We review methods for transferring our ability to construct interesting networks that perform relevant tasks from the artificial continuous domain to more realistic spiking network models. These methods raise a number of issues that warrant further theoretical and experimental study.

  12. Modeling, Optimization & Control of Hydraulic Networks

    DEFF Research Database (Denmark)

    Tahavori, Maryamsadat

    2014-01-01

    . The nonlinear network model is derived based on the circuit theory. A suitable projection is used to reduce the state vector and to express the model in standard state-space form. Then, the controllability of nonlinear nonaffine hydraulic networks is studied. The Lie algebra-based controllability matrix is used......Water supply systems consist of a number of pumping stations, which deliver water to the customers via pipeline networks and elevated reservoirs. A huge amount of drinking water is lost before it reaches to end-users due to the leakage in pipe networks. A cost effective solution to reduce leakage...... in water network is pressure management. By reducing the pressure in the water network, the leakage can be reduced significantly. Also it reduces the amount of energy consumption in water networks. The primary purpose of this work is to develop control algorithms for pressure control in water supply...

  13. A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach.

    Science.gov (United States)

    Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

    2017-06-19

    A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification.

  14. Design of a hybrid model for cardiac arrhythmia classification based on Daubechies wavelet transform.

    Science.gov (United States)

    Rajagopal, Rekha; Ranganathan, Vidhyapriya

    2018-06-05

    Automation in cardiac arrhythmia classification helps medical professionals make accurate decisions about the patient's health. The aim of this work was to design a hybrid classification model to classify cardiac arrhythmias. The design phase of the classification model comprises the following stages: preprocessing of the cardiac signal by eliminating detail coefficients that contain noise, feature extraction through Daubechies wavelet transform, and arrhythmia classification using a collaborative decision from the K nearest neighbor classifier (KNN) and a support vector machine (SVM). The proposed model is able to classify 5 arrhythmia classes as per the ANSI/AAMI EC57: 1998 classification standard. Level 1 of the proposed model involves classification using the KNN and the classifier is trained with examples from all classes. Level 2 involves classification using an SVM and is trained specifically to classify overlapped classes. The final classification of a test heartbeat pertaining to a particular class is done using the proposed KNN/SVM hybrid model. The experimental results demonstrated that the average sensitivity of the proposed model was 92.56%, the average specificity 99.35%, the average positive predictive value 98.13%, the average F-score 94.5%, and the average accuracy 99.78%. The results obtained using the proposed model were compared with the results of discriminant, tree, and KNN classifiers. The proposed model is able to achieve a high classification accuracy.

  15. Artificial Neural Network classification of operator workload with an assessment of time variation and noise-enhancement to increase performance

    Directory of Open Access Journals (Sweden)

    Alexander James Casson

    2014-12-01

    Full Text Available Workload classification---the determination of whether a human operator is in a high or low workload state to allow their working environment to be optimized---is an emerging application of passive Brain-Computer Interface (BCI systems. Practical systems must not only accurately detect the current workload state, but also have good temporal performance: requiring little time to set up and train the classifier, and ensuring that the reported performance level is consistent and predictable over time. This paper investigates the temporal performance of an Artificial Neural Network based classification system. For networks trained on little EEG data good classification accuracies (86% are achieved over very short time frames, but substantial decreases in accuracy are found as the time gap between the network training and the actual use is increased. Noise-enhanced processing, where artificially generated noise is deliberately added to the testing signals, is investigated as a potential technique to mitigate this degradation without requiring the network to be re-trained using more data. Small stochastic resonance effects are demonstrated whereby the classification process gets better in the presence of more noise. The effect is small and does not eliminate the need for re-training, but it is consistent, and this is the first demonstration of such effects for non-evoked/free-running EEG signals suitable for passive BCI.

  16. Bayesian networks of age estimation and classification based on dental evidence: A study on the third molar mineralization.

    Science.gov (United States)

    Sironi, Emanuele; Pinchi, Vilma; Pradella, Francesco; Focardi, Martina; Bozza, Silvia; Taroni, Franco

    2018-04-01

    Not only does the Bayesian approach offer a rational and logical environment for evidence evaluation in a forensic framework, but it also allows scientists to coherently deal with uncertainty related to a collection of multiple items of evidence, due to its flexible nature. Such flexibility might come at the expense of elevated computational complexity, which can be handled by using specific probabilistic graphical tools, namely Bayesian networks. In the current work, such probabilistic tools are used for evaluating dental evidence related to the development of third molars. A set of relevant properties characterizing the graphical models are discussed and Bayesian networks are implemented to deal with the inferential process laying beyond the estimation procedure, as well as to provide age estimates. Such properties include operationality, flexibility, coherence, transparence and sensitivity. A data sample composed of Italian subjects was employed for the analysis; results were in agreement with previous studies in terms of point estimate and age classification. The influence of the prior probability elicitation in terms of Bayesian estimate and classifies was also analyzed. Findings also supported the opportunity to take into consideration multiple teeth in the evaluative procedure, since it can be shown this results in an increased robustness towards the prior probability elicitation process, as well as in more favorable outcomes from a forensic perspective. Copyright © 2018 Elsevier Ltd and Faculty of Forensic and Legal Medicine. All rights reserved.

  17. SampleCNN: End-to-End Deep Convolutional Neural Networks Using Very Small Filters for Music Classification

    Directory of Open Access Journals (Sweden)

    Jongpil Lee

    2018-01-01

    Full Text Available Convolutional Neural Networks (CNN have been applied to diverse machine learning tasks for different modalities of raw data in an end-to-end fashion. In the audio domain, a raw waveform-based approach has been explored to directly learn hierarchical characteristics of audio. However, the majority of previous studies have limited their model capacity by taking a frame-level structure similar to short-time Fourier transforms. We previously proposed a CNN architecture which learns representations using sample-level filters beyond typical frame-level input representations. The architecture showed comparable performance to the spectrogram-based CNN model in music auto-tagging. In this paper, we extend the previous work in three ways. First, considering the sample-level model requires much longer training time, we progressively downsample the input signals and examine how it affects the performance. Second, we extend the model using multi-level and multi-scale feature aggregation technique and subsequently conduct transfer learning for several music classification tasks. Finally, we visualize filters learned by the sample-level CNN in each layer to identify hierarchically learned features and show that they are sensitive to log-scaled frequency.

  18. Port Hamiltonian modeling of Power Networks

    NARCIS (Netherlands)

    van Schaik, F.; van der Schaft, Abraham; Scherpen, Jacquelien M.A.; Zonetti, Daniele; Ortega, R

    2012-01-01

    In this talk a full nonlinear model for the power network in port–Hamiltonian framework is derived to study its stability properties. For this we use the modularity approach i.e., we first derive the models of individual components in power network as port-Hamiltonian systems and then we combine all

  19. Modelling traffic congestion using queuing networks

    Indian Academy of Sciences (India)

    Flow-density curves; uninterrupted traffic; Jackson networks. ... ness - also suffer from a big handicap vis-a-vis the Indian scenario: most of these models do .... more well-known queuing network models and onsite data, a more exact Road Cell ...

  20. Settings in Social Networks : a Measurement Model

    NARCIS (Netherlands)

    Schweinberger, Michael; Snijders, Tom A.B.

    2003-01-01

    A class of statistical models is proposed that aims to recover latent settings structures in social networks. Settings may be regarded as clusters of vertices. The measurement model is based on two assumptions. (1) The observed network is generated by hierarchically nested latent transitive