Deep Belief Networks Learn Context Dependent Behavior

PubMed Central

Raudies, Florian; Zilli, Eric A.; Hasselmo, Michael E.

2014-01-01

With the goal of understanding behavioral mechanisms of generalization, we analyzed the ability of neural networks to generalize across context. We modeled a behavioral task where the correct responses to a set of specific sensory stimuli varied systematically across different contexts. The correct response depended on the stimulus (A,B,C,D) and context quadrant (1,2,3,4). The possible 16 stimulus-context combinations were associated with one of two responses (X,Y), one of which was correct for half of the combinations. The correct responses varied symmetrically across contexts. This allowed responses to previously unseen stimuli (probe stimuli) to be generalized from stimuli that had been presented previously. By testing the simulation on two or more stimuli that the network had never seen in a particular context, we could test whether the correct response on the novel stimuli could be generated based on knowledge of the correct responses in other contexts. We tested this generalization capability with a Deep Belief Network (DBN), Multi-Layer Perceptron (MLP) network, and the combination of a DBN with a linear perceptron (LP). Overall, the combination of the DBN and LP had the highest success rate for generalization. PMID:24671178

Analysis of human tissue optical scattering spectra for the purpose of breast cancer diagnostics using multi-layer perceptron

NASA Astrophysics Data System (ADS)

Nuzhny, Anton S.; Shumsky, Sergey A.; Korzhov, Alexey G.; Lyubynskaya, Tatiana E.

2008-02-01

Optical scattering spectra obtained in the clinical trials of breast cancer diagnostic system were analyzed for the purpose to detect in the dataflow the segments corresponding to malignant tissues. Minimal invasive probe with optical fibers inside delivers white light from the source and collects the scattering light while being moved through the tissue. The sampling rate is 100 Hz and each record contains the results of measurements of scattered light intensity at 184 fixed wavelength points. Large amount of information acquired in each procedure, fuzziness in criteria of 'cancer' family membership and data noisiness make neural networks to be an attractive tool for analysis of these data. To define the dividing rule between 'cancer' and 'non-cancer' spectral families a three-layer perceptron was applied. In the process of perceptron learning back propagation method was used to minimize the learning error. Regularization was done using the Bayesian approach. The learning sample was formed by the experts. End-to-end probability calculation throughout the procedure dataset showed reliable detection of the 'cancer' segments. Much attention was paid on the spectra of the tissues with high blood content. Often the reason is vessel injury caused by the penetrating optical probe. But also it can be a dense vessel net surrounding the malignant tumor. To make the division into 'cancer' and 'non-cancer' families for the tissues with high blood content a special perceptron was learnt exceptionally on such spectra.

The application of neural networks to myoelectric signal analysis: a preliminary study.

PubMed

Kelly, M F; Parker, P A; Scott, R N

1990-03-01

Two neural network implementations are applied to myoelectric signal (MES) analysis tasks. The motivation behind this research is to explore more reliable methods of deriving control for multidegree of freedom arm prostheses. A discrete Hopfield network is used to calculate the time series parameters for a moving average MES model. It is demonstrated that the Hopfield network is capable of generating the same time series parameters as those produced by the conventional sequential least squares (SLS) algorithm. Furthermore, it can be extended to applications utilizing larger amounts of data, and possibly to higher order time series models, without significant degradation in computational efficiency. The second neural network implementation involves using a two-layer perceptron for classifying a single site MES based on two features, specifically the first time series parameter, and the signal power. Using these features, the perceptron is trained to distinguish between four separate arm functions. The two-dimensional decision boundaries used by the perceptron classifier are delineated. It is also demonstrated that the perceptron is able to rapidly compensate for variations when new data are incorporated into the training set. This adaptive quality suggests that perceptrons may provide a useful tool for future MES analysis.

Application of Artificial Neural Network to Predict the use of Runway at Juanda International Airport

NASA Astrophysics Data System (ADS)

Putra, J. C. P.; Safrilah

2017-06-01

Artificial neural network approaches are useful to solve many complicated problems. It solves a number of problems in various areas such as engineering, medicine, business, manufacturing, etc. This paper presents an application of artificial neural network to predict a runway capacity at Juanda International Airport. An artificial neural network model of backpropagation and multi-layer perceptron is adopted to this research to learning process of runway capacity at Juanda International Airport. The results indicate that the training data is successfully recognizing the certain pattern of runway use at Juanda International Airport. Whereas, testing data indicate vice versa. Finally, it can be concluded that the approach of uniformity data and network architecture is the critical part to determine the accuracy of prediction results.

An ANN-Based Smart Tomographic Reconstructor in a Dynamic Environment

PubMed Central

de Cos Juez, Francisco J.; Lasheras, Fernando Sánchez; Roqueñí, Nieves; Osborn, James

2012-01-01

In astronomy, the light emitted by an object travels through the vacuum of space and then the turbulent atmosphere before arriving at a ground based telescope. By passing through the atmosphere a series of turbulent layers modify the light's wave-front in such a way that Adaptive Optics reconstruction techniques are needed to improve the image quality. A novel reconstruction technique based in Artificial Neural Networks (ANN) is proposed. The network is designed to use the local tilts of the wave-front measured by a Shack Hartmann Wave-front Sensor (SHWFS) as inputs and estimate the turbulence in terms of Zernike coefficients. The ANN used is a Multi-Layer Perceptron (MLP) trained with simulated data with one turbulent layer changing in altitude. The reconstructor was tested using three different atmospheric profiles and compared with two existing reconstruction techniques: Least Squares type Matrix Vector Multiplication (LS) and Learn and Apply (L + A). PMID:23012524

Phylogenetic convolutional neural networks in metagenomics.

PubMed

Fioravanti, Diego; Giarratano, Ylenia; Maggio, Valerio; Agostinelli, Claudio; Chierici, Marco; Jurman, Giuseppe; Furlanello, Cesare

2018-03-08

Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user.

Signal processing and neural network toolbox and its application to failure diagnosis and prognosis

NASA Astrophysics Data System (ADS)

Tu, Fang; Wen, Fang; Willett, Peter K.; Pattipati, Krishna R.; Jordan, Eric H.

2001-07-01

Many systems are comprised of components equipped with self-testing capability; however, if the system is complex involving feedback and the self-testing itself may occasionally be faulty, tracing faults to a single or multiple causes is difficult. Moreover, many sensors are incapable of reliable decision-making on their own. In such cases, a signal processing front-end that can match inference needs will be very helpful. The work is concerned with providing an object-oriented simulation environment for signal processing and neural network-based fault diagnosis and prognosis. In the toolbox, we implemented a wide range of spectral and statistical manipulation methods such as filters, harmonic analyzers, transient detectors, and multi-resolution decomposition to extract features for failure events from data collected by data sensors. Then we evaluated multiple learning paradigms for general classification, diagnosis and prognosis. The network models evaluated include Restricted Coulomb Energy (RCE) Neural Network, Learning Vector Quantization (LVQ), Decision Trees (C4.5), Fuzzy Adaptive Resonance Theory (FuzzyArtmap), Linear Discriminant Rule (LDR), Quadratic Discriminant Rule (QDR), Radial Basis Functions (RBF), Multiple Layer Perceptrons (MLP) and Single Layer Perceptrons (SLP). Validation techniques, such as N-fold cross-validation and bootstrap techniques, are employed for evaluating the robustness of network models. The trained networks are evaluated for their performance using test data on the basis of percent error rates obtained via cross-validation, time efficiency, generalization ability to unseen faults. Finally, the usage of neural networks for the prediction of residual life of turbine blades with thermal barrier coatings is described and the results are shown. The neural network toolbox has also been applied to fault diagnosis in mixed-signal circuits.

An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems

DTIC Science & Technology

1991-12-01

neural network and the feedforward neural network studied is the single layer perceptron artificial neural network . The recurrent artificial neural network input...features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input

Heart Rate Variability Dynamics for the Prognosis of Cardiovascular Risk

PubMed Central

Ramirez-Villegas, Juan F.; Lam-Espinosa, Eric; Ramirez-Moreno, David F.; Calvo-Echeverry, Paulo C.; Agredo-Rodriguez, Wilfredo

2011-01-01

Statistical, spectral, multi-resolution and non-linear methods were applied to heart rate variability (HRV) series linked with classification schemes for the prognosis of cardiovascular risk. A total of 90 HRV records were analyzed: 45 from healthy subjects and 45 from cardiovascular risk patients. A total of 52 features from all the analysis methods were evaluated using standard two-sample Kolmogorov-Smirnov test (KS-test). The results of the statistical procedure provided input to multi-layer perceptron (MLP) neural networks, radial basis function (RBF) neural networks and support vector machines (SVM) for data classification. These schemes showed high performances with both training and test sets and many combinations of features (with a maximum accuracy of 96.67%). Additionally, there was a strong consideration for breathing frequency as a relevant feature in the HRV analysis. PMID:21386966

Testing the applicability of artificial intelligence techniques to the subject of erythemal ultraviolet solar radiation. Part two: an intelligent system based on multi-classifier technique.

PubMed

Elminir, Hamdy K; Own, Hala S; Azzam, Yosry A; Riad, A M

2008-03-28

The problem we address here describes the on-going research effort that takes place to shed light on the applicability of using artificial intelligence techniques to predict the local noon erythemal UV irradiance in the plain areas of Egypt. In light of this fact, we use the bootstrap aggregating (bagging) algorithm to improve the prediction accuracy reported by a multi-layer perceptron (MLP) network. The results showed that, the overall prediction accuracy for the MLP network was only 80.9%. When bagging algorithm is used, the accuracy reached 94.8%; an improvement of about 13.9% was achieved. These improvements demonstrate the efficiency of the bagging procedure, and may be used as a promising tool at least for the plain areas of Egypt.

Multilayer perceptron architecture optimization using parallel computing techniques.

PubMed

Castro, Wilson; Oblitas, Jimy; Santa-Cruz, Roberto; Avila-George, Himer

2017-01-01

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time.

Multilayer perceptron architecture optimization using parallel computing techniques

PubMed Central

Castro, Wilson; Oblitas, Jimy; Santa-Cruz, Roberto; Avila-George, Himer

2017-01-01

The objective of this research was to develop a methodology for optimizing multilayer-perceptron-type neural networks by evaluating the effects of three neural architecture parameters, namely, number of hidden layers (HL), neurons per hidden layer (NHL), and activation function type (AF), on the sum of squares error (SSE). The data for the study were obtained from quality parameters (physicochemical and microbiological) of milk samples. Architectures or combinations were organized in groups (G1, G2, and G3) generated upon interspersing one, two, and three layers. Within each group, the networks had three neurons in the input layer, six neurons in the output layer, three to twenty-seven NHL, and three AF (tan-sig, log-sig, and linear) types. The number of architectures was determined using three factorial-type experimental designs, which reached 63, 2 187, and 50 049 combinations for G1, G2 and G3, respectively. Using MATLAB 2015a, a logical sequence was designed and implemented for constructing, training, and evaluating multilayer-perceptron-type neural networks using parallel computing techniques. The results show that HL and NHL have a statistically relevant effect on SSE, and from two hidden layers, AF also has a significant effect; thus, both AF and NHL can be evaluated to determine the optimal combination per group. Moreover, in the three study groups, it is observed that there is an inverse relationship between the number of processors and the total optimization time. PMID:29236744

Adaptive Weibull Multiplicative Model and Multilayer Perceptron Neural Networks for Dark-Spot Detection from SAR Imagery

PubMed Central

Taravat, Alireza; Oppelt, Natascha

2014-01-01

Oil spills represent a major threat to ocean ecosystems and their environmental status. Previous studies have shown that Synthetic Aperture Radar (SAR), as its recording is independent of clouds and weather, can be effectively used for the detection and classification of oil spills. Dark formation detection is the first and critical stage in oil-spill detection procedures. In this paper, a novel approach for automated dark-spot detection in SAR imagery is presented. A new approach from the combination of adaptive Weibull Multiplicative Model (WMM) and MultiLayer Perceptron (MLP) neural networks is proposed to differentiate between dark spots and the background. The results have been compared with the results of a model combining non-adaptive WMM and pulse coupled neural networks. The presented approach overcomes the non-adaptive WMM filter setting parameters by developing an adaptive WMM model which is a step ahead towards a full automatic dark spot detection. The proposed approach was tested on 60 ENVISAT and ERS2 images which contained dark spots. For the overall dataset, an average accuracy of 94.65% was obtained. Our experimental results demonstrate that the proposed approach is very robust and effective where the non-adaptive WMM & pulse coupled neural network (PCNN) model generates poor accuracies. PMID:25474376

Comparison of universal approximators incorporating partial monotonicity by structure.

PubMed

Minin, Alexey; Velikova, Marina; Lang, Bernhard; Daniels, Hennie

2010-05-01

Neural networks applied in control loops and safety-critical domains have to meet more requirements than just the overall best function approximation. On the one hand, a small approximation error is required; on the other hand, the smoothness and the monotonicity of selected input-output relations have to be guaranteed. Otherwise, the stability of most of the control laws is lost. In this article we compare two neural network-based approaches incorporating partial monotonicity by structure, namely the Monotonic Multi-Layer Perceptron (MONMLP) network and the Monotonic MIN-MAX (MONMM) network. We show the universal approximation capabilities of both types of network for partially monotone functions. On a number of datasets, we investigate the advantages and disadvantages of these approaches related to approximation performance, training of the model and convergence. 2009 Elsevier Ltd. All rights reserved.

Obstacle Recognition Based on Machine Learning for On-Chip LiDAR Sensors in a Cyber-Physical System

PubMed Central

Beruvides, Gerardo

2017-01-01

Collision avoidance is an important feature in advanced driver-assistance systems, aimed at providing correct, timely and reliable warnings before an imminent collision (with objects, vehicles, pedestrians, etc.). The obstacle recognition library is designed and implemented to address the design and evaluation of obstacle detection in a transportation cyber-physical system. The library is integrated into a co-simulation framework that is supported on the interaction between SCANeR software and Matlab/Simulink. From the best of the authors’ knowledge, two main contributions are reported in this paper. Firstly, the modelling and simulation of virtual on-chip light detection and ranging sensors in a cyber-physical system, for traffic scenarios, is presented. The cyber-physical system is designed and implemented in SCANeR. Secondly, three specific artificial intelligence-based methods for obstacle recognition libraries are also designed and applied using a sensory information database provided by SCANeR. The computational library has three methods for obstacle detection: a multi-layer perceptron neural network, a self-organization map and a support vector machine. Finally, a comparison among these methods under different weather conditions is presented, with very promising results in terms of accuracy. The best results are achieved using the multi-layer perceptron in sunny and foggy conditions, the support vector machine in rainy conditions and the self-organized map in snowy conditions. PMID:28906450

Obstacle Recognition Based on Machine Learning for On-Chip LiDAR Sensors in a Cyber-Physical System.

PubMed

Castaño, Fernando; Beruvides, Gerardo; Haber, Rodolfo E; Artuñedo, Antonio

2017-09-14

Collision avoidance is an important feature in advanced driver-assistance systems, aimed at providing correct, timely and reliable warnings before an imminent collision (with objects, vehicles, pedestrians, etc.). The obstacle recognition library is designed and implemented to address the design and evaluation of obstacle detection in a transportation cyber-physical system. The library is integrated into a co-simulation framework that is supported on the interaction between SCANeR software and Matlab/Simulink. From the best of the authors' knowledge, two main contributions are reported in this paper. Firstly, the modelling and simulation of virtual on-chip light detection and ranging sensors in a cyber-physical system, for traffic scenarios, is presented. The cyber-physical system is designed and implemented in SCANeR. Secondly, three specific artificial intelligence-based methods for obstacle recognition libraries are also designed and applied using a sensory information database provided by SCANeR. The computational library has three methods for obstacle detection: a multi-layer perceptron neural network, a self-organization map and a support vector machine. Finally, a comparison among these methods under different weather conditions is presented, with very promising results in terms of accuracy. The best results are achieved using the multi-layer perceptron in sunny and foggy conditions, the support vector machine in rainy conditions and the self-organized map in snowy conditions.

Automatic Mexican sign language and digits recognition using normalized central moments

NASA Astrophysics Data System (ADS)

Solís, Francisco; Martínez, David; Espinosa, Oscar; Toxqui, Carina

2016-09-01

This work presents a framework for automatic Mexican sign language and digits recognition based on computer vision system using normalized central moments and artificial neural networks. Images are captured by digital IP camera, four LED reflectors and a green background in order to reduce computational costs and prevent the use of special gloves. 42 normalized central moments are computed per frame and used in a Multi-Layer Perceptron to recognize each database. Four versions per sign and digit were used in training phase. 93% and 95% of recognition rates were achieved for Mexican sign language and digits respectively.

A multilayer perceptron solution to the match phase problem in rule-based artificial intelligence systems

NASA Technical Reports Server (NTRS)

Sartori, Michael A.; Passino, Kevin M.; Antsaklis, Panos J.

1992-01-01

In rule-based AI planning, expert, and learning systems, it is often the case that the left-hand-sides of the rules must be repeatedly compared to the contents of some 'working memory'. The traditional approach to solve such a 'match phase problem' for production systems is to use the Rete Match Algorithm. Here, a new technique using a multilayer perceptron, a particular artificial neural network model, is presented to solve the match phase problem for rule-based AI systems. A syntax for premise formulas (i.e., the left-hand-sides of the rules) is defined, and working memory is specified. From this, it is shown how to construct a multilayer perceptron that finds all of the rules which can be executed for the current situation in working memory. The complexity of the constructed multilayer perceptron is derived in terms of the maximum number of nodes and the required number of layers. A method for reducing the number of layers to at most three is also presented.

Data-driven automated acoustic analysis of human infant vocalizations using neural network tools.

PubMed

Warlaumont, Anne S; Oller, D Kimbrough; Buder, Eugene H; Dale, Rick; Kozma, Robert

2010-04-01

Acoustic analysis of infant vocalizations has typically employed traditional acoustic measures drawn from adult speech acoustics, such as f(0), duration, formant frequencies, amplitude, and pitch perturbation. Here an alternative and complementary method is proposed in which data-derived spectrographic features are central. 1-s-long spectrograms of vocalizations produced by six infants recorded longitudinally between ages 3 and 11 months are analyzed using a neural network consisting of a self-organizing map and a single-layer perceptron. The self-organizing map acquires a set of holistic, data-derived spectrographic receptive fields. The single-layer perceptron receives self-organizing map activations as input and is trained to classify utterances into prelinguistic phonatory categories (squeal, vocant, or growl), identify the ages at which they were produced, and identify the individuals who produced them. Classification performance was significantly better than chance for all three classification tasks. Performance is compared to another popular architecture, the fully supervised multilayer perceptron. In addition, the network's weights and patterns of activation are explored from several angles, for example, through traditional acoustic measurements of the network's receptive fields. Results support the use of this and related tools for deriving holistic acoustic features directly from infant vocalization data and for the automatic classification of infant vocalizations.

Adiabatic superconducting cells for ultra-low-power artificial neural networks.

PubMed

Schegolev, Andrey E; Klenov, Nikolay V; Soloviev, Igor I; Tereshonok, Maxim V

2016-01-01

We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.

The use of neural network technology to model swimming performance.

PubMed

Silva, António José; Costa, Aldo Manuel; Oliveira, Paulo Moura; Reis, Victor Machado; Saavedra, José; Perl, Jurgen; Rouboa, Abel; Marinho, Daniel Almeida

2007-01-01

to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons) and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females) of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility), swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics) and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron) with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8% between true and estimated performances) is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports. Key pointsThe non-linear analysis resulting from the use of feed forward neural network allowed us the development of four performance models.The mean difference between the true and estimated results performed by each one of the four neural network models constructed was low.The neural network tool can be a good approach in the resolution of the performance modeling as an alternative to the standard statistical models that presume well-defined distributions and independence among all inputs.The use of neural networks for sports sciences application allowed us to create very realistic models for swimming performance prediction based on previous selected criterions that were related with the dependent variable (performance).

Seismic activity prediction using computational intelligence techniques in northern Pakistan

NASA Astrophysics Data System (ADS)

Asim, Khawaja M.; Awais, Muhammad; Martínez-Álvarez, F.; Iqbal, Talat

2017-10-01

Earthquake prediction study is carried out for the region of northern Pakistan. The prediction methodology includes interdisciplinary interaction of seismology and computational intelligence. Eight seismic parameters are computed based upon the past earthquakes. Predictive ability of these eight seismic parameters is evaluated in terms of information gain, which leads to the selection of six parameters to be used in prediction. Multiple computationally intelligent models have been developed for earthquake prediction using selected seismic parameters. These models include feed-forward neural network, recurrent neural network, random forest, multi layer perceptron, radial basis neural network, and support vector machine. The performance of every prediction model is evaluated and McNemar's statistical test is applied to observe the statistical significance of computational methodologies. Feed-forward neural network shows statistically significant predictions along with accuracy of 75% and positive predictive value of 78% in context of northern Pakistan.

The effect of imposing 'fractional abundance constraints' onto the multilayer perceptron for sub-pixel land cover classification

NASA Astrophysics Data System (ADS)

Heremans, Stien; Suykens, Johan A. K.; Van Orshoven, Jos

2016-02-01

To be physically interpretable, sub-pixel land cover fractions or abundances should fulfill two constraints, the Abundance Non-negativity Constraint (ANC) and the Abundance Sum-to-one Constraint (ASC). This paper focuses on the effect of imposing these constraints onto the MultiLayer Perceptron (MLP) for a multi-class sub-pixel land cover classification of a time series of low resolution MODIS-images covering the northern part of Belgium. Two constraining modes were compared, (i) an in-training approach that uses 'softmax' as the transfer function in the MLP's output layer and (ii) a post-training approach that linearly rescales the outputs of the unconstrained MLP. Our results demonstrate that the pixel-level prediction accuracy is markedly increased by the explicit enforcement, both in-training and post-training, of the ANC and the ASC. For aggregations of pixels (municipalities), the constrained perceptrons perform at least as well as their unconstrained counterparts. Although the difference in performance between the in-training and post-training approach is small, we recommend the former for integrating the fractional abundance constraints into MLPs meant for sub-pixel land cover estimation, regardless of the targeted level of spatial aggregation.

Unfolding the neutron spectrum of a NE213 scintillator using artificial neural networks.

PubMed

Sharghi Ido, A; Bonyadi, M R; Etaati, G R; Shahriari, M

2009-10-01

Artificial neural networks technology has been applied to unfold the neutron spectra from the pulse height distribution measured with NE213 liquid scintillator. Here, both the single and multi-layer perceptron neural network models have been implemented to unfold the neutron spectrum from an Am-Be neutron source. The activation function and the connectivity of the neurons have been investigated and the results have been analyzed in terms of the network's performance. The simulation results show that the neural network that utilizes the Satlins transfer function has the best performance. In addition, omitting the bias connection of the neurons improve the performance of the network. Also, the SCINFUL code is used for generating the response functions in the training phase of the process. Finally, the results of the neural network simulation have been compared with those of the FORIST unfolding code for both (241)Am-Be and (252)Cf neutron sources. The results of neural network are in good agreement with FORIST code.

An ECG signals compression method and its validation using NNs.

PubMed

Fira, Catalina Monica; Goras, Liviu

2008-04-01

This paper presents a new algorithm for electrocardiogram (ECG) signal compression based on local extreme extraction, adaptive hysteretic filtering and Lempel-Ziv-Welch (LZW) coding. The algorithm has been verified using eight of the most frequent normal and pathological types of cardiac beats and an multi-layer perceptron (MLP) neural network trained with original cardiac patterns and tested with reconstructed ones. Aspects regarding the possibility of using the principal component analysis (PCA) to cardiac pattern classification have been investigated as well. A new compression measure called "quality score," which takes into account both the reconstruction errors and the compression ratio, is proposed.

A conjugate gradients/trust regions algorithms for training multilayer perceptrons for nonlinear mapping

NASA Technical Reports Server (NTRS)

Madyastha, Raghavendra K.; Aazhang, Behnaam; Henson, Troy F.; Huxhold, Wendy L.

1992-01-01

This paper addresses the issue of applying a globally convergent optimization algorithm to the training of multilayer perceptrons, a class of Artificial Neural Networks. The multilayer perceptrons are trained towards the solution of two highly nonlinear problems: (1) signal detection in a multi-user communication network, and (2) solving the inverse kinematics for a robotic manipulator. The research is motivated by the fact that a multilayer perceptron is theoretically capable of approximating any nonlinear function to within a specified accuracy. The algorithm that has been employed in this study combines the merits of two well known optimization algorithms, the Conjugate Gradients and the Trust Regions Algorithms. The performance is compared to a widely used algorithm, the Backpropagation Algorithm, that is basically a gradient-based algorithm, and hence, slow in converging. The performances of the two algorithms are compared with the convergence rate. Furthermore, in the case of the signal detection problem, performances are also benchmarked by the decision boundaries drawn as well as the probability of error obtained in either case.

Benchmark of Machine Learning Methods for Classification of a SENTINEL-2 Image

NASA Astrophysics Data System (ADS)

Pirotti, F.; Sunar, F.; Piragnolo, M.

2016-06-01

Thanks to mainly ESA and USGS, a large bulk of free images of the Earth is readily available nowadays. One of the main goals of remote sensing is to label images according to a set of semantic categories, i.e. image classification. This is a very challenging issue since land cover of a specific class may present a large spatial and spectral variability and objects may appear at different scales and orientations. In this study, we report the results of benchmarking 9 machine learning algorithms tested for accuracy and speed in training and classification of land-cover classes in a Sentinel-2 dataset. The following machine learning methods (MLM) have been tested: linear discriminant analysis, k-nearest neighbour, random forests, support vector machines, multi layered perceptron, multi layered perceptron ensemble, ctree, boosting, logarithmic regression. The validation is carried out using a control dataset which consists of an independent classification in 11 land-cover classes of an area about 60 km2, obtained by manual visual interpretation of high resolution images (20 cm ground sampling distance) by experts. In this study five out of the eleven classes are used since the others have too few samples (pixels) for testing and validating subsets. The classes used are the following: (i) urban (ii) sowable areas (iii) water (iv) tree plantations (v) grasslands. Validation is carried out using three different approaches: (i) using pixels from the training dataset (train), (ii) using pixels from the training dataset and applying cross-validation with the k-fold method (kfold) and (iii) using all pixels from the control dataset. Five accuracy indices are calculated for the comparison between the values predicted with each model and control values over three sets of data: the training dataset (train), the whole control dataset (full) and with k-fold cross-validation (kfold) with ten folds. Results from validation of predictions of the whole dataset (full) show the random forests method with the highest values; kappa index ranging from 0.55 to 0.42 respectively with the most and least number pixels for training. The two neural networks (multi layered perceptron and its ensemble) and the support vector machines - with default radial basis function kernel - methods follow closely with comparable performance.

Performance evaluation of MLP and RBF feed forward neural network for the recognition of off-line handwritten characters

NASA Astrophysics Data System (ADS)

Rishi, Rahul; Choudhary, Amit; Singh, Ravinder; Dhaka, Vijaypal Singh; Ahlawat, Savita; Rao, Mukta

2010-02-01

In this paper we propose a system for classification problem of handwritten text. The system is composed of preprocessing module, supervised learning module and recognition module on a very broad level. The preprocessing module digitizes the documents and extracts features (tangent values) for each character. The radial basis function network is used in the learning and recognition modules. The objective is to analyze and improve the performance of Multi Layer Perceptron (MLP) using RBF transfer functions over Logarithmic Sigmoid Function. The results of 35 experiments indicate that the Feed Forward MLP performs accurately and exhaustively with RBF. With the change in weight update mechanism and feature-drawn preprocessing module, the proposed system is competent with good recognition show.

Elbow joint angle and elbow movement velocity estimation using NARX-multiple layer perceptron neural network model with surface EMG time domain parameters.

PubMed

Raj, Retheep; Sivanandan, K S

2017-01-01

Estimation of elbow dynamics has been the object of numerous investigations. In this work a solution is proposed for estimating elbow movement velocity and elbow joint angle from Surface Electromyography (SEMG) signals. Here the Surface Electromyography signals are acquired from the biceps brachii muscle of human hand. Two time-domain parameters, Integrated EMG (IEMG) and Zero Crossing (ZC), are extracted from the Surface Electromyography signal. The relationship between the time domain parameters, IEMG and ZC with elbow angular displacement and elbow angular velocity during extension and flexion of the elbow are studied. A multiple input-multiple output model is derived for identifying the kinematics of elbow. A Nonlinear Auto Regressive with eXogenous inputs (NARX) structure based multiple layer perceptron neural network (MLPNN) model is proposed for the estimation of elbow joint angle and elbow angular velocity. The proposed NARX MLPNN model is trained using Levenberg-marquardt based algorithm. The proposed model is estimating the elbow joint angle and elbow movement angular velocity with appreciable accuracy. The model is validated using regression coefficient value (R). The average regression coefficient value (R) obtained for elbow angular displacement prediction is 0.9641 and for the elbow anglular velocity prediction is 0.9347. The Nonlinear Auto Regressive with eXogenous inputs (NARX) structure based multiple layer perceptron neural networks (MLPNN) model can be used for the estimation of angular displacement and movement angular velocity of the elbow with good accuracy.

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

A statistical framework for evaluating neural networks to predict recurrent events in breast cancer

NASA Astrophysics Data System (ADS)

Gorunescu, Florin; Gorunescu, Marina; El-Darzi, Elia; Gorunescu, Smaranda

2010-07-01

Breast cancer is the second leading cause of cancer deaths in women today. Sometimes, breast cancer can return after primary treatment. A medical diagnosis of recurrent cancer is often a more challenging task than the initial one. In this paper, we investigate the potential contribution of neural networks (NNs) to support health professionals in diagnosing such events. The NN algorithms are tested and applied to two different datasets. An extensive statistical analysis has been performed to verify our experiments. The results show that a simple network structure for both the multi-layer perceptron and radial basis function can produce equally good results, not all attributes are needed to train these algorithms and, finally, the classification performances of all algorithms are statistically robust. Moreover, we have shown that the best performing algorithm will strongly depend on the features of the datasets, and hence, there is not necessarily a single best classifier.

Comparing success levels of different neural network structures in extracting discriminative information from the response patterns of a temperature-modulated resistive gas sensor

NASA Astrophysics Data System (ADS)

Hosseini-Golgoo, S. M.; Bozorgi, H.; Saberkari, A.

2015-06-01

Performances of three neural networks, consisting of a multi-layer perceptron, a radial basis function, and a neuro-fuzzy network with local linear model tree training algorithm, in modeling and extracting discriminative features from the response patterns of a temperature-modulated resistive gas sensor are quantitatively compared. For response pattern recording, a voltage staircase containing five steps each with a 20 s plateau is applied to the micro-heater of the sensor, when 12 different target gases, each at 11 concentration levels, are present. In each test, the hidden layer neuron weights are taken as the discriminatory feature vector of the target gas. These vectors are then mapped to a 3D feature space using linear discriminant analysis. The discriminative information content of the feature vectors are determined by the calculation of the Fisher’s discriminant ratio, affording quantitative comparison among the success rates achieved by the different neural network structures. The results demonstrate a superior discrimination ratio for features extracted from local linear neuro-fuzzy and radial-basis-function networks with recognition rates of 96.27% and 90.74%, respectively.

Financial time series prediction using spiking neural networks.

PubMed

Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam

2014-01-01

In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments.

Cosmic-ray discrimination capabilities of /ΔE-/E silicon nuclear telescopes using neural networks

NASA Astrophysics Data System (ADS)

Ambriola, M.; Bellotti, R.; Cafagna, F.; Castellano, M.; Ciacio, F.; Circella, M.; Marzo, C. N. D.; Montaruli, T.

2000-02-01

An isotope classifier of cosmic-ray events collected by space detectors has been implemented using a multi-layer perceptron neural architecture. In order to handle a great number of different isotopes a modular architecture of the ``mixture of experts'' type is proposed. The performance of this classifier has been tested on simulated data and has been compared with a ``classical'' classifying procedure. The quantitative comparison with traditional techniques shows that the neural approach has classification performances comparable - within /1% - with that of the classical one, with efficiency of the order of /98%. A possible hardware implementation of such a kind of neural architecture in future space missions is considered.

Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks

PubMed Central

Maca, Petr; Pech, Pavel

2016-01-01

The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI) and the standardized precipitation evaporation index (SPEI) and were derived for the period of 1948–2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons. PMID:26880875

Forecasting SPEI and SPI Drought Indices Using the Integrated Artificial Neural Networks.

PubMed

Maca, Petr; Pech, Pavel

2016-01-01

The presented paper compares forecast of drought indices based on two different models of artificial neural networks. The first model is based on feedforward multilayer perceptron, sANN, and the second one is the integrated neural network model, hANN. The analyzed drought indices are the standardized precipitation index (SPI) and the standardized precipitation evaporation index (SPEI) and were derived for the period of 1948-2002 on two US catchments. The meteorological and hydrological data were obtained from MOPEX experiment. The training of both neural network models was made by the adaptive version of differential evolution, JADE. The comparison of models was based on six model performance measures. The results of drought indices forecast, explained by the values of four model performance indices, show that the integrated neural network model was superior to the feedforward multilayer perceptron with one hidden layer of neurons.

The Use of Neural Network Technology to Model Swimming Performance

PubMed Central

Silva, António José; Costa, Aldo Manuel; Oliveira, Paulo Moura; Reis, Victor Machado; Saavedra, José; Perl, Jurgen; Rouboa, Abel; Marinho, Daniel Almeida

2007-01-01

The aims of the present study were: to identify the factors which are able to explain the performance in the 200 meters individual medley and 400 meters front crawl events in young swimmers, to model the performance in those events using non-linear mathematic methods through artificial neural networks (multi-layer perceptrons) and to assess the neural network models precision to predict the performance. A sample of 138 young swimmers (65 males and 73 females) of national level was submitted to a test battery comprising four different domains: kinanthropometric evaluation, dry land functional evaluation (strength and flexibility), swimming functional evaluation (hydrodynamics, hydrostatic and bioenergetics characteristics) and swimming technique evaluation. To establish a profile of the young swimmer non-linear combinations between preponderant variables for each gender and swim performance in the 200 meters medley and 400 meters font crawl events were developed. For this purpose a feed forward neural network was used (Multilayer Perceptron) with three neurons in a single hidden layer. The prognosis precision of the model (error lower than 0.8% between true and estimated performances) is supported by recent evidence. Therefore, we consider that the neural network tool can be a good approach in the resolution of complex problems such as performance modeling and the talent identification in swimming and, possibly, in a wide variety of sports. Key pointsThe non-linear analysis resulting from the use of feed forward neural network allowed us the development of four performance models.The mean difference between the true and estimated results performed by each one of the four neural network models constructed was low.The neural network tool can be a good approach in the resolution of the performance modeling as an alternative to the standard statistical models that presume well-defined distributions and independence among all inputs.The use of neural networks for sports sciences application allowed us to create very realistic models for swimming performance prediction based on previous selected criterions that were related with the dependent variable (performance). PMID:24149233

Predicting wettability behavior of fluorosilica coated metal surface using optimum neural network

NASA Astrophysics Data System (ADS)

Taghipour-Gorjikolaie, Mehran; Valipour Motlagh, Naser

2018-02-01

The interaction between variables, which are effective on the surface wettability, is very complex to predict the contact angles and sliding angles of liquid drops. In this paper, in order to solve this complexity, artificial neural network was used to develop reliable models for predicting the angles of liquid drops. Experimental data are divided into training data and testing data. By using training data and feed forward structure for the neural network and using particle swarm optimization for training the neural network based models, the optimum models were developed. The obtained results showed that regression index for the proposed models for the contact angles and sliding angles are 0.9874 and 0.9920, respectively. As it can be seen, these values are close to unit and it means the reliable performance of the models. Also, it can be inferred from the results that the proposed model have more reliable performance than multi-layer perceptron and radial basis function based models.

Gas Classification Using Deep Convolutional Neural Networks.

PubMed

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).

Gas Classification Using Deep Convolutional Neural Networks

PubMed Central

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

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

PubMed

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.

Cellular computational generalized neuron network for frequency situational intelligence in a multi-machine power system.

PubMed

Wei, Yawei; Venayagamoorthy, Ganesh Kumar

2017-09-01

To prevent large interconnected power system from a cascading failure, brownout or even blackout, grid operators require access to faster than real-time information to make appropriate just-in-time control decisions. However, the communication and computational system limitations of currently used supervisory control and data acquisition (SCADA) system can only deliver delayed information. However, the deployment of synchrophasor measurement devices makes it possible to capture and visualize, in near-real-time, grid operational data with extra granularity. In this paper, a cellular computational network (CCN) approach for frequency situational intelligence (FSI) in a power system is presented. The distributed and scalable computing unit of the CCN framework makes it particularly flexible for customization for a particular set of prediction requirements. Two soft-computing algorithms have been implemented in the CCN framework: a cellular generalized neuron network (CCGNN) and a cellular multi-layer perceptron network (CCMLPN), for purposes of providing multi-timescale frequency predictions, ranging from 16.67 ms to 2 s. These two developed CCGNN and CCMLPN systems were then implemented on two different scales of power systems, one of which installed a large photovoltaic plant. A real-time power system simulator at weather station within the Real-Time Power and Intelligent Systems (RTPIS) laboratory at Clemson, SC, was then used to derive typical FSI results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Chaotic map clustering algorithm for EEG analysis

NASA Astrophysics Data System (ADS)

Bellotti, R.; De Carlo, F.; Stramaglia, S.

2004-03-01

The non-parametric chaotic map clustering algorithm has been applied to the analysis of electroencephalographic signals, in order to recognize the Huntington's disease, one of the most dangerous pathologies of the central nervous system. The performance of the method has been compared with those obtained through parametric algorithms, as K-means and deterministic annealing, and supervised multi-layer perceptron. While supervised neural networks need a training phase, performed by means of data tagged by the genetic test, and the parametric methods require a prior choice of the number of classes to find, the chaotic map clustering gives a natural evidence of the pathological class, without any training or supervision, thus providing a new efficient methodology for the recognition of patterns affected by the Huntington's disease.

Financial Time Series Prediction Using Spiking Neural Networks

PubMed Central

Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam

2014-01-01

In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two “traditional”, rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments. PMID:25170618

Statistical Mechanical Analysis of Online Learning with Weight Normalization in Single Layer Perceptron

NASA Astrophysics Data System (ADS)

Yoshida, Yuki; Karakida, Ryo; Okada, Masato; Amari, Shun-ichi

2017-04-01

Weight normalization, a newly proposed optimization method for neural networks by Salimans and Kingma (2016), decomposes the weight vector of a neural network into a radial length and a direction vector, and the decomposed parameters follow their steepest descent update. They reported that learning with the weight normalization achieves better converging speed in several tasks including image recognition and reinforcement learning than learning with the conventional parameterization. However, it remains theoretically uncovered how the weight normalization improves the converging speed. In this study, we applied a statistical mechanical technique to analyze on-line learning in single layer linear and nonlinear perceptrons with weight normalization. By deriving order parameters of the learning dynamics, we confirmed quantitatively that weight normalization realizes fast converging speed by automatically tuning the effective learning rate, regardless of the nonlinearity of the neural network. This property is realized when the initial value of the radial length is near the global minimum; therefore, our theory suggests that it is important to choose the initial value of the radial length appropriately when using weight normalization.

Automated road marking recognition system

NASA Astrophysics Data System (ADS)

Ziyatdinov, R. R.; Shigabiev, R. R.; Talipov, D. N.

2017-09-01

Development of the automated road marking recognition systems in existing and future vehicles control systems is an urgent task. One way to implement such systems is the use of neural networks. To test the possibility of using neural network software has been developed with the use of a single-layer perceptron. The resulting system based on neural network has successfully coped with the task both when driving in the daytime and at night.

Machine-learning the string landscape

NASA Astrophysics Data System (ADS)

He, Yang-Hui

2017-11-01

We propose a paradigm to apply machine learning various databases which have emerged in the study of the string landscape. In particular, we establish neural networks as both classifiers and predictors and train them with a host of available data ranging from Calabi-Yau manifolds and vector bundles, to quiver representations for gauge theories, using a novel framework of recasting geometrical and physical data as pixelated images. We find that even a relatively simple neural network can learn many significant quantities to astounding accuracy in a matter of minutes and can also predict hithertofore unencountered results, whereby rendering the paradigm a valuable tool in physics as well as pure mathematics. Of course, this paradigm is useful not only to physicists but to also to mathematicians; for instance, could our NN be trained well enough to approximate bundle cohomology calculations? This, and a host of other examples, we will now examine.Methodology  Neural networks are known for their complexity, involving usually a complicated directed graph each node of which is a ;perceptron; (an activation function imitating a neuron) and amongst the multitude of which there are many arrows encoding input/output. Throughout this letter, we will use a rather simple multi-layer perceptron (MLP) consisting of 5 layers, three of which are hidden, with activation functions typically of the form of a logistic sigmoid or a hyperbolic tangent. The input layer is a linear layer of 100 to 1000 nodes, recognizing a tensor (as we will soon see, algebro-geometric objects such as Calabi-Yau manifolds or polytopes are generically configurations of integer tensors) and the output layer is a summation layer giving a number corresponding to a Hodge number, or to rank of a cohomology group, etc. Such an MLP can be implemented, for instance, on the latest versions of Wolfram Mathematica. With 500-1000 training rounds, the running time is merely about 5-20 minutes on an ordinary laptop. It is reassuring and pleasantly surprising that even such a relatively simple NN can achieve the level of accuracy shortly to be presented.This letter is a companion summary of the longer paper[42]where the interested reader can find more details of the computations and the data.

Coarse-graining and self-dissimilarity of complex networks

NASA Astrophysics Data System (ADS)

Itzkovitz, Shalev; Levitt, Reuven; Kashtan, Nadav; Milo, Ron; Itzkovitz, Michael; Alon, Uri

2005-01-01

Can complex engineered and biological networks be coarse-grained into smaller and more understandable versions in which each node represents an entire pattern in the original network? To address this, we define coarse-graining units as connectivity patterns which can serve as the nodes of a coarse-grained network and present algorithms to detect them. We use this approach to systematically reverse-engineer electronic circuits, forming understandable high-level maps from incomprehensible transistor wiring: first, a coarse-grained version in which each node is a gate made of several transistors is established. Then the coarse-grained network is itself coarse-grained, resulting in a high-level blueprint in which each node is a circuit module made of many gates. We apply our approach also to a mammalian protein signal-transduction network, to find a simplified coarse-grained network with three main signaling channels that resemble multi-layered perceptrons made of cross-interacting MAP-kinase cascades. We find that both biological and electronic networks are “self-dissimilar,” with different network motifs at each level. The present approach may be used to simplify a variety of directed and nondirected, natural and designed networks.

LavaNet—Neural network development environment in a general mine planning package

NASA Astrophysics Data System (ADS)

Kapageridis, Ioannis Konstantinou; Triantafyllou, A. G.

2011-04-01

LavaNet is a series of scripts written in Perl that gives access to a neural network simulation environment inside a general mine planning package. A well known and a very popular neural network development environment, the Stuttgart Neural Network Simulator, is used as the base for the development of neural networks. LavaNet runs inside VULCAN™—a complete mine planning package with advanced database, modelling and visualisation capabilities. LavaNet is taking advantage of VULCAN's Perl based scripting environment, Lava, to bring all the benefits of neural network development and application to geologists, mining engineers and other users of the specific mine planning package. LavaNet enables easy development of neural network training data sets using information from any of the data and model structures available, such as block models and drillhole databases. Neural networks can be trained inside VULCAN™ and the results be used to generate new models that can be visualised in 3D. Direct comparison of developed neural network models with conventional and geostatistical techniques is now possible within the same mine planning software package. LavaNet supports Radial Basis Function networks, Multi-Layer Perceptrons and Self-Organised Maps.

Optimization of metformin HCl 500 mg sustained release matrix tablets using Artificial Neural Network (ANN) based on Multilayer Perceptrons (MLP) model.

PubMed

Mandal, Uttam; Gowda, Veeran; Ghosh, Animesh; Bose, Anirbandeep; Bhaumik, Uttam; Chatterjee, Bappaditya; Pal, Tapan Kumar

2008-02-01

The aim of the present study was to apply the simultaneous optimization method incorporating Artificial Neural Network (ANN) using Multi-layer Perceptron (MLP) model to the development of a metformin HCl 500 mg sustained release matrix tablets with an optimized in vitro release profile. The amounts of HPMC K15M and PVP K30 at three levels (-1, 0, +1) for each were selected as casual factors. In vitro dissolution time profiles at four different sampling times (1 h, 2 h, 4 h and 8 h) were chosen as output variables. 13 kinds of metformin matrix tablets were prepared according to a 2(3) factorial design (central composite) with five extra center points, and their dissolution tests were performed. Commercially available STATISTICA Neural Network software (Stat Soft, Inc., Tulsa, OK, U.S.A.) was used throughout the study. The training process of MLP was completed until a satisfactory value of root square mean (RSM) for the test data was obtained using feed forward back propagation method. The root mean square value for the trained network was 0.000097, which indicated that the optimal MLP model was reached. The optimal tablet formulation based on some predetermined release criteria predicted by MLP was 336 mg of HPMC K15M and 130 mg of PVP K30. Calculated difference (f(1) 2.19) and similarity (f(2) 89.79) factors indicated that there was no difference between predicted and experimentally observed drug release profiles for the optimal formulation. This work illustrates the potential for an artificial neural network with MLP, to assist in development of sustained release dosage forms.

Estimates of Storage Capacity of Multilayer Perceptron with Threshold Logic Hidden Units.

PubMed

Kowalczyk, Adam

1997-11-01

We estimate the storage capacity of multilayer perceptron with n inputs, h(1) threshold logic units in the first hidden layer and 1 output. We show that if the network can memorize 50% of all dichotomies of a randomly selected N-tuple of points of R(n) with probability 1, then N

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach.

PubMed

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.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Islam, Md. Shafiqul, E-mail: shafique@eng.ukm.my; Hannan, M.A., E-mail: hannan@eng.ukm.my; Basri, Hassan

Highlights: • Solid waste bin level detection using Dynamic Time Warping (DTW). • Gabor wavelet filter is used to extract the solid waste image features. • Multi-Layer Perceptron classifier network is used for bin image classification. • The classification performance evaluated by ROC curve analysis. - Abstract: The increasing requirement for Solid Waste Management (SWM) has become a significant challenge for municipal authorities. A number of integrated systems and methods have introduced to overcome this challenge. Many researchers have aimed to develop an ideal SWM system, including approaches involving software-based routing, Geographic Information Systems (GIS), Radio-frequency Identification (RFID), or sensormore » intelligent bins. Image processing solutions for the Solid Waste (SW) collection have also been developed; however, during capturing the bin image, it is challenging to position the camera for getting a bin area centralized image. As yet, there is no ideal system which can correctly estimate the amount of SW. This paper briefly discusses an efficient image processing solution to overcome these problems. Dynamic Time Warping (DTW) was used for detecting and cropping the bin area and Gabor wavelet (GW) was introduced for feature extraction of the waste bin image. Image features were used to train the classifier. A Multi-Layer Perceptron (MLP) classifier was used to classify the waste bin level and estimate the amount of waste inside the bin. The area under the Receiver Operating Characteristic (ROC) curves was used to statistically evaluate classifier performance. The results of this developed system are comparable to previous image processing based system. The system demonstration using DTW with GW for feature extraction and an MLP classifier led to promising results with respect to the accuracy of waste level estimation (98.50%). The application can be used to optimize the routing of waste collection based on the estimated bin level.« less

Pattern classification by memristive crossbar circuits using ex situ and in situ training.

PubMed

Alibart, Fabien; Zamanidoost, Elham; Strukov, Dmitri B

2013-01-01

Memristors are memory resistors that promise the efficient implementation of synaptic weights in artificial neural networks. Whereas demonstrations of the synaptic operation of memristors already exist, the implementation of even simple networks is more challenging and has yet to be reported. Here we demonstrate pattern classification using a single-layer perceptron network implemented with a memrisitive crossbar circuit and trained using the perceptron learning rule by ex situ and in situ methods. In the first case, synaptic weights, which are realized as conductances of titanium dioxide memristors, are calculated on a precursor software-based network and then imported sequentially into the crossbar circuit. In the second case, training is implemented in situ, so the weights are adjusted in parallel. Both methods work satisfactorily despite significant variations in the switching behaviour of the memristors. These results give hope for the anticipated efficient implementation of artificial neuromorphic networks and pave the way for dense, high-performance information processing systems.

Pattern classification by memristive crossbar circuits using ex situ and in situ training

NASA Astrophysics Data System (ADS)

Alibart, Fabien; Zamanidoost, Elham; Strukov, Dmitri B.

2013-06-01

Memristors are memory resistors that promise the efficient implementation of synaptic weights in artificial neural networks. Whereas demonstrations of the synaptic operation of memristors already exist, the implementation of even simple networks is more challenging and has yet to be reported. Here we demonstrate pattern classification using a single-layer perceptron network implemented with a memrisitive crossbar circuit and trained using the perceptron learning rule by ex situ and in situ methods. In the first case, synaptic weights, which are realized as conductances of titanium dioxide memristors, are calculated on a precursor software-based network and then imported sequentially into the crossbar circuit. In the second case, training is implemented in situ, so the weights are adjusted in parallel. Both methods work satisfactorily despite significant variations in the switching behaviour of the memristors. These results give hope for the anticipated efficient implementation of artificial neuromorphic networks and pave the way for dense, high-performance information processing systems.

Advanced diagnostic system for piston slap faults in IC engines, based on the non-stationary characteristics of the vibration signals

NASA Astrophysics Data System (ADS)

Chen, Jian; Randall, Robert Bond; Peeters, Bart

2016-06-01

Artificial Neural Networks (ANNs) have the potential to solve the problem of automated diagnostics of piston slap faults, but the critical issue for the successful application of ANN is the training of the network by a large amount of data in various engine conditions (different speed/load conditions in normal condition, and with different locations/levels of faults). On the other hand, the latest simulation technology provides a useful alternative in that the effect of clearance changes may readily be explored without recourse to cutting metal, in order to create enough training data for the ANNs. In this paper, based on some existing simplified models of piston slap, an advanced multi-body dynamic simulation software was used to simulate piston slap faults with different speeds/loads and clearance conditions. Meanwhile, the simulation models were validated and updated by a series of experiments. Three-stage network systems are proposed to diagnose piston faults: fault detection, fault localisation and fault severity identification. Multi Layer Perceptron (MLP) networks were used in the detection stage and severity/prognosis stage and a Probabilistic Neural Network (PNN) was used to identify which cylinder has faults. Finally, it was demonstrated that the networks trained purely on simulated data can efficiently detect piston slap faults in real tests and identify the location and severity of the faults as well.

A Comparison of Artificial Intelligence Methods on Determining Coronary Artery Disease

NASA Astrophysics Data System (ADS)

Babaoğlu, Ismail; Baykan, Ömer Kaan; Aygül, Nazif; Özdemir, Kurtuluş; Bayrak, Mehmet

The aim of this study is to show a comparison of multi-layered perceptron neural network (MLPNN) and support vector machine (SVM) on determination of coronary artery disease existence upon exercise stress testing (EST) data. EST and coronary angiography were performed on 480 patients with acquiring 23 verifying features from each. The robustness of the proposed methods is examined using classification accuracy, k-fold cross-validation method and Cohen's kappa coefficient. The obtained classification accuracies are approximately 78% and 79% for MLPNN and SVM respectively. Both MLPNN and SVM methods are rather satisfactory than human-based method looking to Cohen's kappa coefficients. Besides, SVM is slightly better than MLPNN when looking to the diagnostic accuracy, average of sensitivity and specificity, and also Cohen's kappa coefficient.

Neural architecture design based on extreme learning machine.

PubMed

Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

2013-12-01

Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

Nonlinear channel equalization for QAM signal constellation using artificial neural networks.

PubMed

Patra, J C; Pal, R N; Baliarsingh, R; Panda, G

1999-01-01

Application of artificial neural networks (ANN's) to adaptive channel equalization in a digital communication system with 4-QAM signal constellation is reported in this paper. A novel computationally efficient single layer functional link ANN (FLANN) is proposed for this purpose. This network has a simple structure in which the nonlinearity is introduced by functional expansion of the input pattern by trigonometric polynomials. Because of input pattern enhancement, the FLANN is capable of forming arbitrarily nonlinear decision boundaries and can perform complex pattern classification tasks. Considering channel equalization as a nonlinear classification problem, the FLANN has been utilized for nonlinear channel equalization. The performance of the FLANN is compared with two other ANN structures [a multilayer perceptron (MLP) and a polynomial perceptron network (PPN)] along with a conventional linear LMS-based equalizer for different linear and nonlinear channel models. The effect of eigenvalue ratio (EVR) of input correlation matrix on the equalizer performance has been studied. The comparison of computational complexity involved for the three ANN structures is also provided.

A new algorithm to detect earthquakes outside the seismic network: preliminary results

NASA Astrophysics Data System (ADS)

Giudicepietro, Flora; Esposito, Antonietta Maria; Ricciolino, Patrizia

2017-04-01

In this text we are going to present a new technique for detecting earthquakes outside the seismic network, which are often the cause of fault of automatic analysis system. Our goal is to develop a robust method that provides the discrimination result as quickly as possible. We discriminate local earthquakes from regional earthquakes, both recorded at SGG station, equipped with short period sensors, operated by Osservatorio Vesuviano (INGV) in the Southern Apennines (Italy). The technique uses a Multi Layer Perceptron (MLP) neural network with an architecture composed by an input layer, a hidden layer and a single node output layer. We pre-processed the data using the Linear Predictive Coding (LPC) technique to extract the spectral features of the signals in a compact form. We performed several experiments by shortening the signal window length. In particular, we used windows of 4, 2 and 1 seconds containing the onset of the local and the regional earthquakes. We used a dataset of 103 local earthquakes and 79 regional earthquakes, most of which occurred in Greece, Albania and Crete. We split the dataset into a training set, for the network training, and a testing set to evaluate the network's capacity of discrimination. In order to assess the network stability, we repeated this procedure six times, randomly changing the data composition of the training and testing set and the initial weights of the net. We estimated the performance of this method by calculating the average of correct detection percentages obtained for each of the six permutations. The average performances are 99.02%, 98.04% and 98.53%, which concern respectively the experiments carried out on 4, 2 and 1 seconds signal windows. The results show that our method is able to recognize the earthquakes outside the seismic network using only the first second of the seismic records, with a suitable percentage of correct detection. Therefore, this algorithm can be profitably used to make earthquake automatic analyses more robust and reliable. Finally, with appropriate tuning, it can be integrated in multi-parametric systems for monitoring high natural risk areas.

Planning Training Loads for the 400 M Hurdles in Three-Month Mesocycles using Artificial Neural Networks.

PubMed

Przednowek, Krzysztof; Iskra, Janusz; Wiktorowicz, Krzysztof; Krzeszowski, Tomasz; Maszczyk, Adam

2017-12-01

This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes' training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period.

Hourly air pollution concentrations and their important predictors over Houston, Texas using deep neural networks: case study of DISCOVER-AQ time period

NASA Astrophysics Data System (ADS)

Eslami, E.; Choi, Y.; Roy, A.

2017-12-01

Air quality forecasting carried out by chemical transport models often show significant error. This study uses a deep-learning approach over the Houston-Galveston-Brazoria (HGB) area to overcome this forecasting challenge, for the DISCOVER-AQ period (September 2013). Two approaches, deep neural network (DNN) using a Multi-Layer Perceptron (MLP) and Restricted Boltzmann Machine (RBM) were utilized. The proposed approaches analyzed input data by identifying features abstracted from its previous layer using a stepwise method. The approaches predicted hourly ozone and PM in September 2013 using several predictors of prior three days, including wind fields, temperature, relative humidity, cloud fraction, precipitation along with PM, ozone, and NOx concentrations. Model-measurement comparisons for available monitoring sites reported Indexes of Agreement (IOA) of around 0.95 for both DNN and RBM. A standard artificial neural network (ANN) (IOA=0.90) with similar architecture showed poorer performance than the deep networks, clearly demonstrating the superiority of the deep approaches. Additionally, each network (both deep and standard) performed significantly better than a previous CMAQ study, which showed an IOA of less than 0.80. The most influential input variables were identified using their associated weights, which represented the sensitivity of ozone to input parameters. The results indicate deep learning approaches can achieve more accurate ozone forecasting and identify the important input variables for ozone predictions in metropolitan areas.

Planning Training Loads for the 400 M Hurdles in Three-Month Mesocycles using Artificial Neural Networks

PubMed Central

Iskra, Janusz; Wiktorowicz, Krzysztof; Krzeszowski, Tomasz; Maszczyk, Adam

2017-01-01

Abstract This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes’ training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period. PMID:29339998

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach

PubMed Central

Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

2017-01-01

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. PMID:28629202

Development of module for neural network identification of attacks on applications and services in multi-cloud platforms

NASA Astrophysics Data System (ADS)

Parfenov, D. I.; Bolodurina, I. P.

2018-05-01

The article presents the results of developing an approach to detecting and protecting against network attacks on the corporate infrastructure deployed on the multi-cloud platform. The proposed approach is based on the combination of two technologies: a softwareconfigurable network and virtualization of network functions. The approach for searching for anomalous traffic is to use a hybrid neural network consisting of a self-organizing Kohonen network and a multilayer perceptron. The study of the work of the prototype of the system for detecting attacks, the method of forming a learning sample, and the course of experiments are described. The study showed that using the proposed approach makes it possible to increase the effectiveness of the obfuscation of various types of attacks and at the same time does not reduce the performance of the network

Audio Classification in Speech and Music: A Comparison between a Statistical and a Neural Approach

NASA Astrophysics Data System (ADS)

Bugatti, Alessandro; Flammini, Alessandra; Migliorati, Pierangelo

2002-12-01

We focus the attention on the problem of audio classification in speech and music for multimedia applications. In particular, we present a comparison between two different techniques for speech/music discrimination. The first method is based on Zero crossing rate and Bayesian classification. It is very simple from a computational point of view, and gives good results in case of pure music or speech. The simulation results show that some performance degradation arises when the music segment contains also some speech superimposed on music, or strong rhythmic components. To overcome these problems, we propose a second method, that uses more features, and is based on neural networks (specifically a multi-layer Perceptron). In this case we obtain better performance, at the expense of a limited growth in the computational complexity. In practice, the proposed neural network is simple to be implemented if a suitable polynomial is used as the activation function, and a real-time implementation is possible even if low-cost embedded systems are used.

Algorithm for Training a Recurrent Multilayer Perceptron

NASA Technical Reports Server (NTRS)

Parlos, Alexander G.; Rais, Omar T.; Menon, Sunil K.; Atiya, Amir F.

2004-01-01

An improved algorithm has been devised for training a recurrent multilayer perceptron (RMLP) for optimal performance in predicting the behavior of a complex, dynamic, and noisy system multiple time steps into the future. [An RMLP is a computational neural network with self-feedback and cross-talk (both delayed by one time step) among neurons in hidden layers]. Like other neural-network-training algorithms, this algorithm adjusts network biases and synaptic-connection weights according to a gradient-descent rule. The distinguishing feature of this algorithm is a combination of global feedback (the use of predictions as well as the current output value in computing the gradient at each time step) and recursiveness. The recursive aspect of the algorithm lies in the inclusion of the gradient of predictions at each time step with respect to the predictions at the preceding time step; this recursion enables the RMLP to learn the dynamics. It has been conjectured that carrying the recursion to even earlier time steps would enable the RMLP to represent a noisier, more complex system.

Hybrid Feature Extraction-based Approach for Facial Parts Representation and Recognition

NASA Astrophysics Data System (ADS)

Rouabhia, C.; Tebbikh, H.

2008-06-01

Face recognition is a specialized image processing which has attracted a considerable attention in computer vision. In this article, we develop a new facial recognition system from video sequences images dedicated to person identification whose face is partly occulted. This system is based on a hybrid image feature extraction technique called ACPDL2D (Rouabhia et al. 2007), it combines two-dimensional principal component analysis and two-dimensional linear discriminant analysis with neural network. We performed the feature extraction task on the eyes and the nose images separately then a Multi-Layers Perceptron classifier is used. Compared to the whole face, the results of simulation are in favor of the facial parts in terms of memory capacity and recognition (99.41% for the eyes part, 98.16% for the nose part and 97.25 % for the whole face).

Accelerating global optimization of aerodynamic shapes using a new surrogate-assisted parallel genetic algorithm

NASA Astrophysics Data System (ADS)

Ebrahimi, Mehdi; Jahangirian, Alireza

2017-12-01

An efficient strategy is presented for global shape optimization of wing sections with a parallel genetic algorithm. Several computational techniques are applied to increase the convergence rate and the efficiency of the method. A variable fidelity computational evaluation method is applied in which the expensive Navier-Stokes flow solver is complemented by an inexpensive multi-layer perceptron neural network for the objective function evaluations. A population dispersion method that consists of two phases, of exploration and refinement, is developed to improve the convergence rate and the robustness of the genetic algorithm. Owing to the nature of the optimization problem, a parallel framework based on the master/slave approach is used. The outcomes indicate that the method is able to find the global optimum with significantly lower computational time in comparison to the conventional genetic algorithm.

Interacting neural networks.

PubMed

Metzler, R; Kinzel, W; Kanter, I

2000-08-01

Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

Interacting neural networks

NASA Astrophysics Data System (ADS)

Metzler, R.; Kinzel, W.; Kanter, I.

2000-08-01

Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

Detection of inter-turn short-circuit at start-up of induction machine based on torque analysis

NASA Astrophysics Data System (ADS)

Pietrowski, Wojciech; Górny, Konrad

2017-12-01

Recently, interest in new diagnostics methods in a field of induction machines was observed. Research presented in the paper shows the diagnostics of induction machine based on torque pulsation, under inter-turn short-circuit, during start-up of a machine. In the paper three numerical techniques were used: finite element analysis, signal analysis and artificial neural networks (ANN). The elaborated numerical model of faulty machine consists of field, circuit and motion equations. Voltage excited supply allowed to determine the torque waveform during start-up. The inter-turn short-circuit was treated as a galvanic connection between two points of the stator winding. The waveforms were calculated for different amounts of shorted-turns from 0 to 55. Due to the non-stationary waveforms a wavelet packet decomposition was used to perform an analysis of the torque. The obtained results of analysis were used as input vector for ANN. The response of the neural network was the number of shorted-turns in the stator winding. Special attention was paid to compare response of general regression neural network (GRNN) and multi-layer perceptron neural network (MLP). Based on the results of the research, the efficiency of the developed algorithm can be inferred.

Neural network and letter recognition

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lee, Hue Yeon.

Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C-layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken themore » on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the Gabor transform. Pattern dependent choice of center and wavelengths of Gabor filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets.« less

Forecasting PM10 in Algiers: efficacy of multilayer perceptron networks.

PubMed

Abderrahim, Hamza; Chellali, Mohammed Reda; Hamou, Ahmed

2016-01-01

Air quality forecasting system has acquired high importance in atmospheric pollution due to its negative impacts on the environment and human health. The artificial neural network is one of the most common soft computing methods that can be pragmatic for carving such complex problem. In this paper, we used a multilayer perceptron neural network to forecast the daily averaged concentration of the respirable suspended particulates with aerodynamic diameter of not more than 10 μm (PM10) in Algiers, Algeria. The data for training and testing the network are based on the data sampled from 2002 to 2006 collected by SAMASAFIA network center at El Hamma station. The meteorological data, air temperature, relative humidity, and wind speed, are used as inputs network parameters in the formation of model. The training patterns used correspond to 41 days data. The performance of the developed models was evaluated on the basis index of agreement and other statistical parameters. It was seen that the overall performance of model with 15 neurons is better than the ones with 5 and 10 neurons. The results of multilayer network with as few as one hidden layer and 15 neurons were quite reasonable than the ones with 5 and 10 neurons. Finally, an error around 9% has been reached.

Investigating the management performance of disinfection analysis of water distribution networks using data mining approaches.

PubMed

Zounemat-Kermani, Mohammad; Ramezani-Charmahineh, Abdollah; Adamowski, Jan; Kisi, Ozgur

2018-06-13

Chlorination, the basic treatment utilized for drinking water sources, is widely used for water disinfection and pathogen elimination in water distribution networks. Thereafter, the proper prediction of chlorine consumption is of great importance in water distribution network performance. In this respect, data mining techniques-which have the ability to discover the relationship between dependent variable(s) and independent variables-can be considered as alternative approaches in comparison to conventional methods (e.g., numerical methods). This study examines the applicability of three key methods, based on the data mining approach, for predicting chlorine levels in four water distribution networks. ANNs (artificial neural networks, including the multi-layer perceptron neural network, MLPNN, and radial basis function neural network, RBFNN), SVM (support vector machine), and CART (classification and regression tree) methods were used to estimate the concentration of residual chlorine in distribution networks for three villages in Kerman Province, Iran. Produced water (flow), chlorine consumption, and residual chlorine were collected daily for 3 years. An assessment of the studied models using several statistical criteria (NSC, RMSE, R 2 , and SEP) indicated that, in general, MLPNN has the greatest capability for predicting chlorine levels followed by CART, SVM, and RBF-ANN. Weaker performance of the data-driven methods in the water distribution networks, in some cases, could be attributed to improper chlorination management rather than the methods' capability.

Spatial interpolation and radiological mapping of ambient gamma dose rate by using artificial neural networks and fuzzy logic methods.

PubMed

Yeşilkanat, Cafer Mert; Kobya, Yaşar; Taşkın, Halim; Çevik, Uğur

2017-09-01

The aim of this study was to determine spatial risk dispersion of ambient gamma dose rate (AGDR) by using both artificial neural network (ANN) and fuzzy logic (FL) methods, compare the performances of methods, make dose estimations for intermediate stations with no previous measurements and create dose rate risk maps of the study area. In order to determine the dose distribution by using artificial neural networks, two main networks and five different network structures were used; feed forward ANN; Multi-layer perceptron (MLP), Radial basis functional neural network (RBFNN), Quantile regression neural network (QRNN) and recurrent ANN; Jordan networks (JN), Elman networks (EN). In the evaluation of estimation performance obtained for the test data, all models appear to give similar results. According to the cross-validation results obtained for explaining AGDR distribution, Pearson's r coefficients were calculated as 0.94, 0.91, 0.89, 0.91, 0.91 and 0.92 and RMSE values were calculated as 34.78, 43.28, 63.92, 44.86, 46.77 and 37.92 for MLP, RBFNN, QRNN, JN, EN and FL, respectively. In addition, spatial risk maps showing distributions of AGDR of the study area were created by all models and results were compared with geological, topological and soil structure. Copyright © 2017 Elsevier Ltd. All rights reserved.

A novel method for pediatric heart sound segmentation without using the ECG.

PubMed

Sepehri, Amir A; Gharehbaghi, Arash; Dutoit, Thierry; Kocharian, Armen; Kiani, A

2010-07-01

In this paper, we propose a novel method for pediatric heart sounds segmentation by paying special attention to the physiological effects of respiration on pediatric heart sounds. The segmentation is accomplished in three steps. First, the envelope of a heart sounds signal is obtained with emphasis on the first heart sound (S(1)) and the second heart sound (S(2)) by using short time spectral energy and autoregressive (AR) parameters of the signal. Then, the basic heart sounds are extracted taking into account the repetitive and spectral characteristics of S(1) and S(2) sounds by using a Multi-Layer Perceptron (MLP) neural network classifier. In the final step, by considering the diastolic and systolic intervals variations due to the effect of a child's respiration, a complete and precise heart sounds end-pointing and segmentation is achieved. Copyright 2009 Elsevier Ireland Ltd. All rights reserved.

Rotation, scale, and translation invariant pattern recognition using feature extraction

NASA Astrophysics Data System (ADS)

Prevost, Donald; Doucet, Michel; Bergeron, Alain; Veilleux, Luc; Chevrette, Paul C.; Gingras, Denis J.

1997-03-01

A rotation, scale and translation invariant pattern recognition technique is proposed.It is based on Fourier- Mellin Descriptors (FMD). Each FMD is taken as an independent feature of the object, and a set of those features forms a signature. FMDs are naturally rotation invariant. Translation invariance is achieved through pre- processing. A proper normalization of the FMDs gives the scale invariance property. This approach offers the double advantage of providing invariant signatures of the objects, and a dramatic reduction of the amount of data to process. The compressed invariant feature signature is next presented to a multi-layered perceptron neural network. This final step provides some robustness to the classification of the signatures, enabling good recognition behavior under anamorphically scaled distortion. We also present an original feature extraction technique, adapted to optical calculation of the FMDs. A prototype optical set-up was built, and experimental results are presented.

An integrated prediction and optimization model of biogas production system at a wastewater treatment facility.

PubMed

Akbaş, Halil; Bilgen, Bilge; Turhan, Aykut Melih

2015-11-01

This study proposes an integrated prediction and optimization model by using multi-layer perceptron neural network and particle swarm optimization techniques. Three different objective functions are formulated. The first one is the maximization of methane percentage with single output. The second one is the maximization of biogas production with single output. The last one is the maximization of biogas quality and biogas production with two outputs. Methane percentage, carbon dioxide percentage, and other contents' percentage are used as the biogas quality criteria. Based on the formulated models and data from a wastewater treatment facility, optimal values of input variables and their corresponding maximum output values are found out for each model. It is expected that the application of the integrated prediction and optimization models increases the biogas production and biogas quality, and contributes to the quantity of electricity production at the wastewater treatment facility. Copyright © 2015 Elsevier Ltd. All rights reserved.

Artificial neural networks can be effectively used to model changes of intracranial pressure (ICP) during spinal surgery using different non invasive ICP surrogate estimators.

PubMed

Watad, Abdulla; Bragazzi, Nicola L; Bacigaluppi, Susanna; Amital, Howard; Watad, Samaa; Sharif, Kassem; Bisharat, Bishara; Siri, Anna; Mahamid, Ala; Abu Ras, Hakim; Nasr, Ahmed; Bilotta, Federico; Robba, Chiara; Adawi, Mohammad

2018-02-23

Artificial Intelligence (AI) techniques play a major role in anesthesiology, even though their importance is often overlooked. In the extant literature, AI approaches, such as Artificial Neural Networks (ANNs), have been underutilized, mainly being used to model patient's consciousness state, to predict the precise amount of anesthetic gases, the level of analgesia, or the need of anesthesiological blocks, among others. In the field of neurosurgery, ANNs have been effectively applied to the diagnosis and prognosis of cerebral tumors, seizures, low back pain, and also to the monitoring of intracranial pressure (ICP). A MultiLayer Perceptron (MLP), which is a feedforward ANN, with hyperbolic tangent as activation function in the input/hidden layers, softmax as activation function in the output layer, and cross-entropy as error function, was used to model the impact of prone versus supine position and the use of positive end expiratory pressure (PEEP) on ICP in a sample of 30 patients undergoing spinal surgery. Different non invasive surrogate estimations of ICP have been used and compared: namely, mean optic nerve sheath diameter (ONSD), non invasive estimated cerebral perfusion pressure (NCPP), pulsatility index (PI), ICP derived from PI (ICP-PI), and flow velocity diastolic formula (FVDICP). ONSD proved to be a more robust surrogate estimation of ICP, with a predictive power of 75%, whilst the power of NCPP, ICP-PI, PI, and FVDICP were 60.5%, 54.8%, 53.1%, and 47.7%, respectively. Our MLP analysis confirmed our findings previously obtained with regression, correlation, multivariate Receiving Operator Curve (multi-ROC) analyses. ANNs can be successfully used to predict the effects of prone versus supine position and PEEP on ICP in patients undergoing spinal surgery using different non invasive surrogate estimators of ICP.

Prediction of S-wave velocity using complete ensemble empirical mode decomposition and neural networks

NASA Astrophysics Data System (ADS)

Gaci, Said; Hachay, Olga; Zaourar, Naima

2017-04-01

One of the key elements in hydrocarbon reservoirs characterization is the S-wave velocity (Vs). Since the traditional estimating methods often fail to accurately predict this physical parameter, a new approach that takes into account its non-stationary and non-linear properties is needed. In this view, a prediction model based on complete ensemble empirical mode decomposition (CEEMD) and a multiple layer perceptron artificial neural network (MLP ANN) is suggested to compute Vs from P-wave velocity (Vp). Using a fine-to-coarse reconstruction algorithm based on CEEMD, the Vp log data is decomposed into a high frequency (HF) component, a low frequency (LF) component and a trend component. Then, different combinations of these components are used as inputs of the MLP ANN algorithm for estimating Vs log. Applications on well logs taken from different geological settings illustrate that the predicted Vs values using MLP ANN with the combinations of HF, LF and trend in inputs are more accurate than those obtained with the traditional estimating methods. Keywords: S-wave velocity, CEEMD, multilayer perceptron neural networks.

Lectures in Complex Systems (1991)

DTIC Science & Technology

1992-08-05

momentum term and the line required to reach termination criterion. Fig- ture 2 shows this function for the case where Lcarninglate = 1.0. Peeling and...Soc. Am., in press. 17. Peeling , S. M., and R. K. Moore. "Isolated Digit Recognition Experiments using the Multi-Layer Perceptron." Speech Comm. 7...surfaces which form the focal conic defects seen in Figure 1. These are the cyclides of Dupin. The surfaces go from banana -shaped to squashed doughnuts to

Monthly monsoon rainfall forecasting using artificial neural networks

NASA Astrophysics Data System (ADS)

Ganti, Ravikumar

2014-10-01

Indian agriculture sector heavily depends on monsoon rainfall for successful harvesting. In the past, prediction of rainfall was mainly performed using regression models, which provide reasonable accuracy in the modelling and forecasting of complex physical systems. Recently, Artificial Neural Networks (ANNs) have been proposed as efficient tools for modelling and forecasting. A feed-forward multi-layer perceptron type of ANN architecture trained using the popular back-propagation algorithm was employed in this study. Other techniques investigated for modeling monthly monsoon rainfall include linear and non-linear regression models for comparison purposes. The data employed in this study include monthly rainfall and monthly average of the daily maximum temperature in the North Central region in India. Specifically, four regression models and two ANN model's were developed. The performance of various models was evaluated using a wide variety of standard statistical parameters and scatter plots. The results obtained in this study for forecasting monsoon rainfalls using ANNs have been encouraging. India's economy and agricultural activities can be effectively managed with the help of the availability of the accurate monsoon rainfall forecasts.

Neural Networks and other Techniques for Fault Identification and Isolation of Aircraft Systems

NASA Technical Reports Server (NTRS)

Innocenti, M.; Napolitano, M.

2003-01-01

Fault identification, isolation, and accomodation have become critical issues in the overall performance of advanced aircraft systems. Neural Networks have shown to be a very attractive alternative to classic adaptation methods for identification and control of non-linear dynamic systems. The purpose of this paper is to show the improvements in neural network applications achievable through the use of learning algorithms more efficient than the classic Back-Propagation, and through the implementation of the neural schemes in parallel hardware. The results of the analysis of a scheme for Sensor Failure, Detection, Identification and Accommodation (SFDIA) using experimental flight data of a research aircraft model are presented. Conventional approaches to the problem are based on observers and Kalman Filters while more recent methods are based on neural approximators. The work described in this paper is based on the use of neural networks (NNs) as on-line learning non-linear approximators. The performances of two different neural architectures were compared. The first architecture is based on a Multi Layer Perceptron (MLP) NN trained with the Extended Back Propagation algorithm (EBPA). The second architecture is based on a Radial Basis Function (RBF) NN trained with the Extended-MRAN (EMRAN) algorithms. In addition, alternative methods for communications links fault detection and accomodation are presented, relative to multiple unmanned aircraft applications.

Forecasting of natural gas consumption with neural network and neuro fuzzy system

NASA Astrophysics Data System (ADS)

Kaynar, Oguz; Yilmaz, Isik; Demirkoparan, Ferhan

2010-05-01

The prediction of natural gas consumption is crucial for Turkey which follows foreign-dependent policy in point of providing natural gas and whose stock capacity is only 5% of internal total consumption. Prediction accuracy of demand is one of the elements which has an influence on sectored investments and agreements about obtaining natural gas, so on development of sector. In recent years, new techniques, such as artificial neural networks and fuzzy inference systems, have been widely used in natural gas consumption prediction in addition to classical time series analysis. In this study, weekly natural gas consumption of Turkey has been predicted by means of three different approaches. The first one is Autoregressive Integrated Moving Average (ARIMA), which is classical time series analysis method. The second approach is the Artificial Neural Network. Two different ANN models, which are Multi Layer Perceptron (MLP) and Radial Basis Function Network (RBFN), are employed to predict natural gas consumption. The last is Adaptive Neuro Fuzzy Inference System (ANFIS), which combines ANN and Fuzzy Inference System. Different prediction models have been constructed and one model, which has the best forecasting performance, is determined for each method. Then predictions are made by using these models and results are compared. Keywords: ANN, ANFIS, ARIMA, Natural Gas, Forecasting

Fully automatic oil spill detection from COSMO-SkyMed imagery using a neural network approach

NASA Astrophysics Data System (ADS)

Avezzano, Ruggero G.; Del Frate, Fabio; Latini, Daniele

2012-09-01

The increased amount of available Synthetic Aperture Radar (SAR) images acquired over the ocean represents an extraordinary potential for improving oil spill detection activities. On the other side this involves a growing workload on the operators at analysis centers. In addition, even if the operators go through extensive training to learn manual oil spill detection, they can provide different and subjective responses. Hence, the upgrade and improvements of algorithms for automatic detection that can help in screening the images and prioritizing the alarms are of great benefit. In the framework of an ASI Announcement of Opportunity for the exploitation of COSMO-SkyMed data, a research activity (ASI contract L/020/09/0) aiming at studying the possibility to use neural networks architectures to set up fully automatic processing chains using COSMO-SkyMed imagery has been carried out and results are presented in this paper. The automatic identification of an oil spill is seen as a three step process based on segmentation, feature extraction and classification. We observed that a PCNN (Pulse Coupled Neural Network) was capable of providing a satisfactory performance in the different dark spots extraction, close to what it would be produced by manual editing. For the classification task a Multi-Layer Perceptron (MLP) Neural Network was employed.

A neural network device for on-line particle identification in cosmic ray experiments

NASA Astrophysics Data System (ADS)

Scrimaglio, R.; Finetti, N.; D'Altorio, L.; Rantucci, E.; Raso, M.; Segreto, E.; Tassoni, A.; Cardarilli, G. C.

2004-05-01

On-line particle identification is one of the main goals of many experiments in space both for rare event studies and for optimizing measurements along the orbital trajectory. Neural networks can be a useful tool for signal processing and real time data analysis in such experiments. In this document we report on the performances of a programmable neural device which was developed in VLSI analog/digital technology. Neurons and synapses were accomplished by making use of Operational Transconductance Amplifier (OTA) structures. In this paper we report on the results of measurements performed in order to verify the agreement of the characteristic curves of each elementary cell with simulations and on the device performances obtained by implementing simple neural structures on the VLSI chip. A feed-forward neural network (Multi-Layer Perceptron, MLP) was implemented on the VLSI chip and trained to identify particles by processing the signals of two-dimensional position-sensitive Si detectors. The radiation monitoring device consisted of three double-sided silicon strip detectors. From the analysis of a set of simulated data it was found that the MLP implemented on the neural device gave results comparable with those obtained with the standard method of analysis confirming that the implemented neural network could be employed for real time particle identification.

[Application of artificial neural networks on the prediction of surface ozone concentrations].

PubMed

Shen, Lu-Lu; Wang, Yu-Xuan; Duan, Lei

2011-08-01

Ozone is an important secondary air pollutant in the lower atmosphere. In order to predict the hourly maximum ozone one day in advance based on the meteorological variables for the Wanqingsha site in Guangzhou, Guangdong province, a neural network model (Multi-Layer Perceptron) and a multiple linear regression model were used and compared. Model inputs are meteorological parameters (wind speed, wind direction, air temperature, relative humidity, barometric pressure and solar radiation) of the next day and hourly maximum ozone concentration of the previous day. The OBS (optimal brain surgeon) was adopted to prune the neutral work, to reduce its complexity and to improve its generalization ability. We find that the pruned neural network has the capacity to predict the peak ozone, with an agreement index of 92.3%, the root mean square error of 0.0428 mg/m3, the R-square of 0.737 and the success index of threshold exceedance 77.0% (the threshold O3 mixing ratio of 0.20 mg/m3). When the neural classifier was added to the neural network model, the success index of threshold exceedance increased to 83.6%. Through comparison of the performance indices between the multiple linear regression model and the neural network model, we conclud that that neural network is a better choice to predict peak ozone from meteorological forecast, which may be applied to practical prediction of ozone concentration.

Artificial Neural Networks: A Novel Approach to Analysing the Nutritional Ecology of a Blowfly Species, Chrysomya megacephala

PubMed Central

Bianconi, André; Zuben, Cláudio J. Von; Serapião, Adriane B. de S.; Govone, José S.

2010-01-01

Bionomic features of blowflies may be clarified and detailed by the deployment of appropriate modelling techniques such as artificial neural networks, which are mathematical tools widely applied to the resolution of complex biological problems. The principal aim of this work was to use three well-known neural networks, namely Multi-Layer Perceptron (MLP), Radial Basis Function (RBF), and Adaptive Neural Network-Based Fuzzy Inference System (ANFIS), to ascertain whether these tools would be able to outperform a classical statistical method (multiple linear regression) in the prediction of the number of resultant adults (survivors) of experimental populations of Chrysomya megacephala (F.) (Diptera: Calliphoridae), based on initial larval density (number of larvae), amount of available food, and duration of immature stages. The coefficient of determination (R2) derived from the RBF was the lowest in the testing subset in relation to the other neural networks, even though its R2 in the training subset exhibited virtually a maximum value. The ANFIS model permitted the achievement of the best testing performance. Hence this model was deemed to be more effective in relation to MLP and RBF for predicting the number of survivors. All three networks outperformed the multiple linear regression, indicating that neural models could be taken as feasible techniques for predicting bionomic variables concerning the nutritional dynamics of blowflies. PMID:20569135

A Computer Simulation of Braitenberg Vehicles

DTIC Science & Technology

1991-03-01

first believed. In 1969 Marvin Minsky published his now famous (infamous?) proof of the inability of single layer networks to solve many simple problems...and Behavior. Englewood, NJ: Prentice-Hall, 1986. Minsky , Marvin and S. Papert. Perceptrons. Cambridge, MA, MIT Press, 1969. Porter, Kent and Mike...such as that of the exclusive-or gate ( Minsky and Papert, 1969). Many researchers gave up work in the artificial neuron field based on the impact of

Summer Research Program (1992). High School Apprenticeship Program (HSAP) Reports. Volume 14. Rome Laboratory.

DTIC Science & Technology

1992-12-28

analysis. Marvin Minsky , carefully applying mathematical techniques, developed rigo.,ous theorems regarding netwcrk operation. His research led to the...electrical circuits but was later convened to computer simulation, which is still commonly used today. Early success by - Marvirn Minsky , Frank...publication of the book Perceptrons ( Minsky and Papert 1969), in which he and Seymore Papert proved that the single-layer networks then in use were

Retrieval of ice thickness from polarimetric SAR data

NASA Technical Reports Server (NTRS)

Kwok, R.; Yueh, S. H.; Nghiem, S. V.; Huynh, D. D.

1993-01-01

We describe a potential procedure for retrieving ice thickness from multi-frequency polarimetric SAR data for thin ice. This procedure includes first masking out the thicker ice types with a simple classifier and then deriving the thickness of the remaining pixels using a model-inversion technique. The technique used to derive ice thickness from polarimetric observations is provided by a numerical estimator or neural network. A three-layer perceptron implemented with the backpropagation algorithm is used in this investigation with several improved aspects for a faster convergence rate and a better accuracy of the neural network. These improvements include weight initialization, normalization of the output range, the selection of offset constant, and a heuristic learning algorithm. The performance of the neural network is demonstrated by using training data generated by a theoretical scattering model for sea ice matched to the database of interest. The training data are comprised of the polarimetric backscattering coefficients of thin ice and the corresponding input ice parameters to the scattering model. The retrieved ice thickness from the theoretical backscattering coefficients is compare with the input ice thickness to the scattering model to illustrate the accuracy of the inversion method. Results indicate that the network convergence rate and accuracy are higher when multi-frequency training sets are presented. In addition, the dominant backscattering coefficients in retrieving ice thickness are found by comparing the behavior of the network trained backscattering data at various incidence angels. After the neural network is trained with the theoretical backscattering data at various incidence anges, the interconnection weights between nodes are saved and applied to the experimental data to be investigated. In this paper, we illustrate the effectiveness of this technique using polarimetric SAR data collected by the JPL DC-8 radar over a sea ice scene.

Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning

NASA Astrophysics Data System (ADS)

Florios, Kostas; Kontogiannis, Ioannis; Park, Sung-Hong; Guerra, Jordan A.; Benvenuto, Federico; Bloomfield, D. Shaun; Georgoulis, Manolis K.

2018-02-01

We propose a forecasting approach for solar flares based on data from Solar Cycle 24, taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) mission. In particular, we use the Space-weather HMI Active Region Patches (SHARP) product that facilitates cut-out magnetograms of solar active regions (AR) in the Sun in near-realtime (NRT), taken over a five-year interval (2012 - 2016). Our approach utilizes a set of thirteen predictors, which are not included in the SHARP metadata, extracted from line-of-sight and vector photospheric magnetograms. We exploit several machine learning (ML) and conventional statistics techniques to predict flares of peak magnitude {>} M1 and {>} C1 within a 24 h forecast window. The ML methods used are multi-layer perceptrons (MLP), support vector machines (SVM), and random forests (RF). We conclude that random forests could be the prediction technique of choice for our sample, with the second-best method being multi-layer perceptrons, subject to an entropy objective function. A Monte Carlo simulation showed that the best-performing method gives accuracy ACC=0.93(0.00), true skill statistic TSS=0.74(0.02), and Heidke skill score HSS=0.49(0.01) for {>} M1 flare prediction with probability threshold 15% and ACC=0.84(0.00), TSS=0.60(0.01), and HSS=0.59(0.01) for {>} C1 flare prediction with probability threshold 35%.

MIMO transmit scheme based on morphological perceptron with competitive learning.

PubMed

Valente, Raul Ambrozio; Abrão, Taufik

2016-08-01

This paper proposes a new multi-input multi-output (MIMO) transmit scheme aided by artificial neural network (ANN). The morphological perceptron with competitive learning (MP/CL) concept is deployed as a decision rule in the MIMO detection stage. The proposed MIMO transmission scheme is able to achieve double spectral efficiency; hence, in each time-slot the receiver decodes two symbols at a time instead one as Alamouti scheme. Other advantage of the proposed transmit scheme with MP/CL-aided detector is its polynomial complexity according to modulation order, while it becomes linear when the data stream length is greater than modulation order. The performance of the proposed scheme is compared to the traditional MIMO schemes, namely Alamouti scheme and maximum-likelihood MIMO (ML-MIMO) detector. Also, the proposed scheme is evaluated in a scenario with variable channel information along the frame. Numerical results have shown that the diversity gain under space-time coding Alamouti scheme is partially lost, which slightly reduces the bit-error rate (BER) performance of the proposed MP/CL-NN MIMO scheme. Copyright © 2016 Elsevier Ltd. All rights reserved.

A fresh look at functional link neural network for motor imagery-based brain-computer interface.

PubMed

Hettiarachchi, Imali T; Babaei, Toktam; Nguyen, Thanh; Lim, Chee P; Nahavandi, Saeid

2018-05-04

Artificial neural networks (ANNs) are one of the widely used classifiers in the brain-computer interface (BCI) systems-based on noninvasive electroencephalography (EEG) signals. Among the different ANN architectures, the most commonly applied for BCI classifiers is the multilayer perceptron (MLP). When appropriately designed with optimal number of neuron layers and number of neurons per layer, the ANN can act as a universal approximator. However, due to the low signal-to-noise ratio of EEG signal data, overtraining problem may become an inherent issue, causing these universal approximators to fail in real-time applications. In this study we introduce a higher order neural network, namely the functional link neural network (FLNN) as a classifier for motor imagery (MI)-based BCI systems, to remedy the drawbacks in MLP. We compare the proposed method with competing classifiers such as linear decomposition analysis, naïve Bayes, k-nearest neighbours, support vector machine and three MLP architectures. Two multi-class benchmark datasets from the BCI competitions are used. Common spatial pattern algorithm is utilized for feature extraction to build classification models. FLNN reports the highest average Kappa value over multiple subjects for both the BCI competition datasets, under similarly preprocessed data and extracted features. Further, statistical comparison results over multiple subjects show that the proposed FLNN classification method yields the best performance among the competing classifiers. Findings from this study imply that the proposed method, which has less computational complexity compared to the MLP, can be implemented effectively in practical MI-based BCI systems. Copyright © 2018 Elsevier B.V. All rights reserved.

Using Bayesian neural networks to classify forest scenes

NASA Astrophysics Data System (ADS)

Vehtari, Aki; Heikkonen, Jukka; Lampinen, Jouko; Juujarvi, Jouni

1998-10-01

We present results that compare the performance of Bayesian learning methods for neural networks on the task of classifying forest scenes into trees and background. Classification task is demanding due to the texture richness of the trees, occlusions of the forest scene objects and diverse lighting conditions under operation. This makes it difficult to determine which are optimal image features for the classification. A natural way to proceed is to extract many different types of potentially suitable features, and to evaluate their usefulness in later processing stages. One approach to cope with large number of features is to use Bayesian methods to control the model complexity. Bayesian learning uses a prior on model parameters, combines this with evidence from a training data, and the integrates over the resulting posterior to make predictions. With this method, we can use large networks and many features without fear of overfitting. For this classification task we compare two Bayesian learning methods for multi-layer perceptron (MLP) neural networks: (1) The evidence framework of MacKay uses a Gaussian approximation to the posterior weight distribution and maximizes with respect to hyperparameters. (2) In a Markov Chain Monte Carlo (MCMC) method due to Neal, the posterior distribution of the network parameters is numerically integrated using the MCMC method. As baseline classifiers for comparison we use (3) MLP early stop committee, (4) K-nearest-neighbor and (5) Classification And Regression Tree.

Algorithm for predicting the evolution of series of dynamics of complex systems in solving information problems

NASA Astrophysics Data System (ADS)

Kasatkina, T. I.; Dushkin, A. V.; Pavlov, V. A.; Shatovkin, R. R.

2018-03-01

In the development of information, systems and programming to predict the series of dynamics, neural network methods have recently been applied. They are more flexible, in comparison with existing analogues and are capable of taking into account the nonlinearities of the series. In this paper, we propose a modified algorithm for predicting the series of dynamics, which includes a method for training neural networks, an approach to describing and presenting input data, based on the prediction by the multilayer perceptron method. To construct a neural network, the values of a series of dynamics at the extremum points and time values corresponding to them, formed based on the sliding window method, are used as input data. The proposed algorithm can act as an independent approach to predicting the series of dynamics, and be one of the parts of the forecasting system. The efficiency of predicting the evolution of the dynamics series for a short-term one-step and long-term multi-step forecast by the classical multilayer perceptron method and a modified algorithm using synthetic and real data is compared. The result of this modification was the minimization of the magnitude of the iterative error that arises from the previously predicted inputs to the inputs to the neural network, as well as the increase in the accuracy of the iterative prediction of the neural network.

Gas demand forecasting by a new artificial intelligent algorithm

NASA Astrophysics Data System (ADS)

Khatibi. B, Vahid; Khatibi, Elham

2012-01-01

Energy demand forecasting is a key issue for consumers and generators in all energy markets in the world. This paper presents a new forecasting algorithm for daily gas demand prediction. This algorithm combines a wavelet transform and forecasting models such as multi-layer perceptron (MLP), linear regression or GARCH. The proposed method is applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the proposed method.

An oil fraction neural sensor developed using electrical capacitance tomography sensor data.

PubMed

Zainal-Mokhtar, Khursiah; Mohamad-Saleh, Junita

2013-08-26

This paper presents novel research on the development of a generic intelligent oil fraction sensor based on Electrical Capacitance Tomography (ECT) data. An artificial Neural Network (ANN) has been employed as the intelligent system to sense and estimate oil fractions from the cross-sections of two-component flows comprising oil and gas in a pipeline. Previous works only focused on estimating the oil fraction in the pipeline based on fixed ECT sensor parameters. With fixed ECT design sensors, an oil fraction neural sensor can be trained to deal with ECT data based on the particular sensor parameters, hence the neural sensor is not generic. This work focuses on development of a generic neural oil fraction sensor based on training a Multi-Layer Perceptron (MLP) ANN with various ECT sensor parameters. On average, the proposed oil fraction neural sensor has shown to be able to give a mean absolute error of 3.05% for various ECT sensor sizes.

An Oil Fraction Neural Sensor Developed Using Electrical capacitance Tomography Sensor Data

PubMed Central

Zainal-Mokhtar, Khursiah; Mohamad-Saleh, Junita

2013-01-01

This paper presents novel research on the development of a generic intelligent oil fraction sensor based on Electrical capacitance Tomography (ECT) data. An artificial Neural Network (ANN) has been employed as the intelligent system to sense and estimate oil fractions from the cross-sections of two-component flows comprising oil and gas in a pipeline. Previous works only focused on estimating the oil fraction in the pipeline based on fixed ECT sensor parameters. With fixed ECT design sensors, an oil fraction neural sensor can be trained to deal with ECT data based on the particular sensor parameters, hence the neural sensor is not generic. This work focuses on development of a generic neural oil fraction sensor based on training a Multi-Layer Perceptron (MLP) ANN with various ECT sensor parameters. On average, the proposed oil fraction neural sensor has shown to be able to give a mean absolute error of 3.05% for various ECT sensor sizes. PMID:24064598

Application of neural models as controllers in mobile robot velocity control loop

NASA Astrophysics Data System (ADS)

Cerkala, Jakub; Jadlovska, Anna

2017-01-01

This paper presents the application of an inverse neural models used as controllers in comparison to classical PI controllers for velocity tracking control task used in two-wheel, differentially driven mobile robot. The PI controller synthesis is based on linear approximation of actuators with equivalent load. In order to obtain relevant datasets for training of feed-forward multi-layer perceptron based neural network used as neural model, the mathematical model of mobile robot, that combines its kinematic and dynamic properties such as chassis dimensions, center of gravity offset, friction and actuator parameters is used. Neural models are trained off-line to act as an inverse dynamics of DC motors with particular load using data collected in simulation experiment for motor input voltage step changes within bounded operating area. The performances of PI controllers versus inverse neural models in mobile robot internal velocity control loops are demonstrated and compared in simulation experiment of navigation control task for line segment motion in plane.

Using "big data" to optimally model hydrology and water quality across expansive regions

USGS Publications Warehouse

Roehl, E.A.; Cook, J.B.; Conrads, P.A.

2009-01-01

This paper describes a new divide and conquer approach that leverages big environmental data, utilizing all available categorical and time-series data without subjectivity, to empirically model hydrologic and water-quality behaviors across expansive regions. The approach decomposes large, intractable problems into smaller ones that are optimally solved; decomposes complex signals into behavioral components that are easier to model with "sub- models"; and employs a sequence of numerically optimizing algorithms that include time-series clustering, nonlinear, multivariate sensitivity analysis and predictive modeling using multi-layer perceptron artificial neural networks, and classification for selecting the best sub-models to make predictions at new sites. This approach has many advantages over traditional modeling approaches, including being faster and less expensive, more comprehensive in its use of available data, and more accurate in representing a system's physical processes. This paper describes the application of the approach to model groundwater levels in Florida, stream temperatures across Western Oregon and Wisconsin, and water depths in the Florida Everglades. ?? 2009 ASCE.

Modeling neural circuits in Parkinson's disease.

PubMed

Psiha, Maria; Vlamos, Panayiotis

2015-01-01

Parkinson's disease (PD) is caused by abnormal neural activity of the basal ganglia which are connected to the cerebral cortex in the brain surface through complex neural circuits. For a better understanding of the pathophysiological mechanisms of PD, it is important to identify the underlying PD neural circuits, and to pinpoint the precise nature of the crucial aberrations in these circuits. In this paper, the general architecture of a hybrid Multilayer Perceptron (MLP) network for modeling the neural circuits in PD is presented. The main idea of the proposed approach is to divide the parkinsonian neural circuitry system into three discrete subsystems: the external stimuli subsystem, the life-threatening events subsystem, and the basal ganglia subsystem. The proposed model, which includes the key roles of brain neural circuit in PD, is based on both feed-back and feed-forward neural networks. Specifically, a three-layer MLP neural network with feedback in the second layer was designed. The feedback in the second layer of this model simulates the dopamine modulatory effect of compacta on striatum.

Layered Ensemble Architecture for Time Series Forecasting.

PubMed

Rahman, Md Mustafizur; Islam, Md Monirul; Murase, Kazuyuki; Yao, Xin

2016-01-01

Time series forecasting (TSF) has been widely used in many application areas such as science, engineering, and finance. The phenomena generating time series are usually unknown and information available for forecasting is only limited to the past values of the series. It is, therefore, necessary to use an appropriate number of past values, termed lag, for forecasting. This paper proposes a layered ensemble architecture (LEA) for TSF problems. Our LEA consists of two layers, each of which uses an ensemble of multilayer perceptron (MLP) networks. While the first ensemble layer tries to find an appropriate lag, the second ensemble layer employs the obtained lag for forecasting. Unlike most previous work on TSF, the proposed architecture considers both accuracy and diversity of the individual networks in constructing an ensemble. LEA trains different networks in the ensemble by using different training sets with an aim of maintaining diversity among the networks. However, it uses the appropriate lag and combines the best trained networks to construct the ensemble. This indicates LEAs emphasis on accuracy of the networks. The proposed architecture has been tested extensively on time series data of neural network (NN)3 and NN5 competitions. It has also been tested on several standard benchmark time series data. In terms of forecasting accuracy, our experimental results have revealed clearly that LEA is better than other ensemble and nonensemble methods.

Minimal perceptrons for memorizing complex patterns

NASA Astrophysics Data System (ADS)

Pastor, Marissa; Song, Juyong; Hoang, Danh-Tai; Jo, Junghyo

2016-11-01

Feedforward neural networks have been investigated to understand learning and memory, as well as applied to numerous practical problems in pattern classification. It is a rule of thumb that more complex tasks require larger networks. However, the design of optimal network architectures for specific tasks is still an unsolved fundamental problem. In this study, we consider three-layered neural networks for memorizing binary patterns. We developed a new complexity measure of binary patterns, and estimated the minimal network size for memorizing them as a function of their complexity. We formulated the minimal network size for regular, random, and complex patterns. In particular, the minimal size for complex patterns, which are neither ordered nor disordered, was predicted by measuring their Hamming distances from known ordered patterns. Our predictions agree with simulations based on the back-propagation algorithm.

Convolutional Neural Network for Multi-Source Deep Learning Crop Classification in Ukraine

NASA Astrophysics Data System (ADS)

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 3196-3231, 2016. 3. S. Skakun et al., "Efficiency assessment of multitemporal C-band Radarsat-2 intensity and Landsat-8 surface reflectance satellite imagery for crop classification in Ukraine," IEEE Journal of Selected Topics in Applied Earth Observ. and Rem. Sens., 2015, DOI: 10.1109/JSTARS.2015.2454297.

Non-intrusive reduced order modeling of nonlinear problems using neural networks

NASA Astrophysics Data System (ADS)

Hesthaven, J. S.; Ubbiali, S.

2018-06-01

We develop a non-intrusive reduced basis (RB) method for parametrized steady-state partial differential equations (PDEs). The method extracts a reduced basis from a collection of high-fidelity solutions via a proper orthogonal decomposition (POD) and employs artificial neural networks (ANNs), particularly multi-layer perceptrons (MLPs), to accurately approximate the coefficients of the reduced model. The search for the optimal number of neurons and the minimum amount of training samples to avoid overfitting is carried out in the offline phase through an automatic routine, relying upon a joint use of the Latin hypercube sampling (LHS) and the Levenberg-Marquardt (LM) training algorithm. This guarantees a complete offline-online decoupling, leading to an efficient RB method - referred to as POD-NN - suitable also for general nonlinear problems with a non-affine parametric dependence. Numerical studies are presented for the nonlinear Poisson equation and for driven cavity viscous flows, modeled through the steady incompressible Navier-Stokes equations. Both physical and geometrical parametrizations are considered. Several results confirm the accuracy of the POD-NN method and show the substantial speed-up enabled at the online stage as compared to a traditional RB strategy.

Interactive learning in 2×2 normal form games by neural network agents

NASA Astrophysics Data System (ADS)

Spiliopoulos, Leonidas

2012-11-01

This paper models the learning process of populations of randomly rematched tabula rasa neural network (NN) agents playing randomly generated 2×2 normal form games of all strategic classes. This approach has greater external validity than the existing models in the literature, each of which is usually applicable to narrow subsets of classes of games (often a single game) and/or to fixed matching protocols. The learning prowess of NNs with hidden layers was impressive as they learned to play unique pure strategy equilibria with near certainty, adhered to principles of dominance and iterated dominance, and exhibited a preference for risk-dominant equilibria. In contrast, perceptron NNs were found to perform significantly worse than hidden layer NN agents and human subjects in experimental studies.

Application of Multilayer Perceptron with Automatic Relevance Determination on Weed Mapping Using UAV Multispectral Imagery

PubMed Central

Tamouridou, Afroditi A.; Lagopodi, Anastasia L.; Kashefi, Javid; Kasampalis, Dimitris; Kontouris, Georgios; Moshou, Dimitrios

2017-01-01

Remote sensing techniques are routinely used in plant species discrimination and of weed mapping. In the presented work, successful Silybum marianum detection and mapping using multilayer neural networks is demonstrated. A multispectral camera (green-red-near infrared) attached on a fixed wing unmanned aerial vehicle (UAV) was utilized for the acquisition of high-resolution images (0.1 m resolution). The Multilayer Perceptron with Automatic Relevance Determination (MLP-ARD) was used to identify the S. marianum among other vegetation, mostly Avena sterilis L. The three spectral bands of Red, Green, Near Infrared (NIR) and the texture layer resulting from local variance were used as input. The S. marianum identification rates using MLP-ARD reached an accuracy of 99.54%. Τhe study had an one year duration, meaning that the results are specific, although the accuracy shows the interesting potential of S. marianum mapping with MLP-ARD on multispectral UAV imagery. PMID:29019957

Application of Multilayer Perceptron with Automatic Relevance Determination on Weed Mapping Using UAV Multispectral Imagery.

PubMed

Tamouridou, Afroditi A; Alexandridis, Thomas K; Pantazi, Xanthoula E; Lagopodi, Anastasia L; Kashefi, Javid; Kasampalis, Dimitris; Kontouris, Georgios; Moshou, Dimitrios

2017-10-11

Remote sensing techniques are routinely used in plant species discrimination and of weed mapping. In the presented work, successful Silybum marianum detection and mapping using multilayer neural networks is demonstrated. A multispectral camera (green-red-near infrared) attached on a fixed wing unmanned aerial vehicle (UAV) was utilized for the acquisition of high-resolution images (0.1 m resolution). The Multilayer Perceptron with Automatic Relevance Determination (MLP-ARD) was used to identify the S. marianum among other vegetation, mostly Avena sterilis L. The three spectral bands of Red, Green, Near Infrared (NIR) and the texture layer resulting from local variance were used as input. The S. marianum identification rates using MLP-ARD reached an accuracy of 99.54%. Τhe study had an one year duration, meaning that the results are specific, although the accuracy shows the interesting potential of S. marianum mapping with MLP-ARD on multispectral UAV imagery.

Local residue coupling strategies by neural network for InSAR phase unwrapping

NASA Astrophysics Data System (ADS)

Refice, Alberto; Satalino, Giuseppe; Chiaradia, Maria T.

1997-12-01

Phase unwrapping is one of the toughest problems in interferometric SAR processing. The main difficulties arise from the presence of point-like error sources, called residues, which occur mainly in close couples due to phase noise. We present an assessment of a local approach to the resolution of these problems by means of a neural network. Using a multi-layer perceptron, trained with the back- propagation scheme on a series of simulated phase images, fashion the best pairing strategies for close residue couples. Results show that god efficiencies and accuracies can have been obtained, provided a sufficient number of training examples are supplied. Results show that good efficiencies and accuracies can be obtained, provided a sufficient number of training examples are supplied. The technique is tested also on real SAR ERS-1/2 tandem interferometric images of the Matera test site, showing a good reduction of the residue density. The better results obtained by use of the neural network as far as local criteria are adopted appear justified given the probabilistic nature of the noise process on SAR interferometric phase fields and allows to outline a specifically tailored implementation of the neural network approach as a very fast pre-processing step intended to decrease the residue density and give sufficiently clean images to be processed further by more conventional techniques.

Stable modeling based control methods using a new RBF network.

PubMed

Beyhan, Selami; Alci, Musa

2010-10-01

This paper presents a novel model with radial basis functions (RBFs), which is applied successively for online stable identification and control of nonlinear discrete-time systems. First, the proposed model is utilized for direct inverse modeling of the plant to generate the control input where it is assumed that inverse plant dynamics exist. Second, it is employed for system identification to generate a sliding-mode control input. Finally, the network is employed to tune PID (proportional + integrative + derivative) controller parameters automatically. The adaptive learning rate (ALR), which is employed in the gradient descent (GD) method, provides the global convergence of the modeling errors. Using the Lyapunov stability approach, the boundedness of the tracking errors and the system parameters are shown both theoretically and in real time. To show the superiority of the new model with RBFs, its tracking results are compared with the results of a conventional sigmoidal multi-layer perceptron (MLP) neural network and the new model with sigmoid activation functions. To see the real-time capability of the new model, the proposed network is employed for online identification and control of a cascaded parallel two-tank liquid-level system. Even though there exist large disturbances, the proposed model with RBFs generates a suitable control input to track the reference signal better than other methods in both simulations and real time. Copyright © 2010 ISA. Published by Elsevier Ltd. All rights reserved.

Separate the inseparable one-layer mapping

NASA Astrophysics Data System (ADS)

Hu, Chia-Lun J.

2000-04-01

When the input-output mapping of a one-layered perceptron (OLP) does NOT meet the PLI condition which is the if-and- only-if, or 'IFF, condition that the mapping can be realized by a OLP, then no matter what learning rule we use, a OLP just cannot realize this mapping at all. However, because of the nature of the PLI, one can still construct a parallel- cascaded, two-layered perceptron system to realize this `illegal' mapping. Theory and design example of this novel design will be reported in detail in this paper.

Use long short-term memory to enhance Internet of Things for combined sewer overflow monitoring

NASA Astrophysics Data System (ADS)

Zhang, Duo; Lindholm, Geir; Ratnaweera, Harsha

2018-01-01

Combined sewer overflow causes severe water pollution, urban flooding and reduced treatment plant efficiency. Understanding the behavior of CSO structures is vital for urban flooding prevention and overflow control. Neural networks have been extensively applied in water resource related fields. In this study, we collect data from an Internet of Things monitoring CSO structure and build different neural network models for simulating and predicting the water level of the CSO structure. Through a comparison of four different neural networks, namely multilayer perceptron (MLP), wavelet neural network (WNN), long short-term memory (LSTM) and gated recurrent unit (GRU), the LSTM and GRU present superior capabilities for multi-step-ahead time series prediction. Furthermore, GRU achieves prediction performances similar to LSTM with a quicker learning curve.

An Intelligent Approach to Educational Data: Performance Comparison of the Multilayer Perceptron and the Radial Basis Function Artificial Neural Networks

ERIC Educational Resources Information Center

Kayri, Murat

2015-01-01

The objective of this study is twofold: (1) to investigate the factors that affect the success of university students by employing two artificial neural network methods (i.e., multilayer perceptron [MLP] and radial basis function [RBF]); and (2) to compare the effects of these methods on educational data in terms of predictive ability. The…

Artificial neural networks in Space Station optimal attitude control

NASA Astrophysics Data System (ADS)

Kumar, Renjith R.; Seywald, Hans; Deshpande, Samir M.; Rahman, Zia

1992-08-01

Innovative techniques of using 'Artificial Neural Networks' (ANN) for improving the performance of the pitch axis attitude control system of Space Station Freedom using Control Moment Gyros (CMGs) are investigated. The first technique uses a feedforward ANN with multilayer perceptrons to obtain an on-line controller which improves the performance of the control system via a model following approach. The second techique uses a single layer feedforward ANN with a modified back propagation scheme to estimate the internal plant variations and the external disturbances separately. These estimates are then used to solve two differential Riccati equations to obtain time varying gains which improve the control system performance in successive orbits.

Alternative sensor system and MLP neural network for vehicle pedal activity estimation.

PubMed

Wefky, Ahmed M; Espinosa, Felipe; Jiménez, José A; Santiso, Enrique; Rodríguez, José M; Fernández, Alfredo J

2010-01-01

It is accepted that the activity of the vehicle pedals (i.e., throttle, brake, clutch) reflects the driver's behavior, which is at least partially related to the fuel consumption and vehicle pollutant emissions. This paper presents a solution to estimate the driver activity regardless of the type, model, and year of fabrication of the vehicle. The solution is based on an alternative sensor system (regime engine, vehicle speed, frontal inclination and linear acceleration) that reflects the activity of the pedals in an indirect way, to estimate that activity by means of a multilayer perceptron neural network with a single hidden layer.

Alternative Sensor System and MLP Neural Network for Vehicle Pedal Activity Estimation

PubMed Central

Wefky, Ahmed M.; Espinosa, Felipe; Jiménez, José A.; Santiso, Enrique; Rodríguez, José M.; Fernández, Alfredo J.

2010-01-01

It is accepted that the activity of the vehicle pedals (i.e., throttle, brake, clutch) reflects the driver’s behavior, which is at least partially related to the fuel consumption and vehicle pollutant emissions. This paper presents a solution to estimate the driver activity regardless of the type, model, and year of fabrication of the vehicle. The solution is based on an alternative sensor system (regime engine, vehicle speed, frontal inclination and linear acceleration) that reflects the activity of the pedals in an indirect way, to estimate that activity by means of a multilayer perceptron neural network with a single hidden layer. PMID:22319326

Optimized hardware framework of MLP with random hidden layers for classification applications

NASA Astrophysics Data System (ADS)

Zyarah, Abdullah M.; Ramesh, Abhishek; Merkel, Cory; Kudithipudi, Dhireesha

2016-05-01

Multilayer Perceptron Networks with random hidden layers are very efficient at automatic feature extraction and offer significant performance improvements in the training process. They essentially employ large collection of fixed, random features, and are expedient for form-factor constrained embedded platforms. In this work, a reconfigurable and scalable architecture is proposed for the MLPs with random hidden layers with a customized building block based on CORDIC algorithm. The proposed architecture also exploits fixed point operations for area efficiency. The design is validated for classification on two different datasets. An accuracy of ~ 90% for MNIST dataset and 75% for gender classification on LFW dataset was observed. The hardware has 299 speed-up over the corresponding software realization.

Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees.

PubMed

Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele; Đurić, Zorica

2012-05-30

The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release. Copyright © 2012 Elsevier B.V. All rights reserved.

Neural Network and Letter Recognition.

NASA Astrophysics Data System (ADS)

Lee, Hue Yeon

Neural net architectures and learning algorithms that recognize hand written 36 alphanumeric characters are studied. The thin line input patterns written in 32 x 32 binary array are used. The system is comprised of two major components, viz. a preprocessing unit and a Recognition unit. The preprocessing unit in turn consists of three layers of neurons; the U-layer, the V-layer, and the C -layer. The functions of the U-layer is to extract local features by template matching. The correlation between the detected local features are considered. Through correlating neurons in a plane with their neighboring neurons, the V-layer would thicken the on-cells or lines that are groups of on-cells of the previous layer. These two correlations would yield some deformation tolerance and some of the rotational tolerance of the system. The C-layer then compresses data through the 'Gabor' transform. Pattern dependent choice of center and wavelengths of 'Gabor' filters is the cause of shift and scale tolerance of the system. Three different learning schemes had been investigated in the recognition unit, namely; the error back propagation learning with hidden units, a simple perceptron learning, and a competitive learning. Their performances were analyzed and compared. Since sometimes the network fails to distinguish between two letters that are inherently similar, additional ambiguity resolving neural nets are introduced on top of the above main neural net. The two dimensional Fourier transform is used as the preprocessing and the perceptron is used as the recognition unit of the ambiguity resolver. One hundred different person's handwriting sets are collected. Some of these are used as the training sets and the remainders are used as the test sets. The correct recognition rate of the system increases with the number of training sets and eventually saturates at a certain value. Similar recognition rates are obtained for the above three different learning algorithms. The minimum error rate, 4.9% is achieved for alphanumeric sets when 50 sets are trained. With the ambiguity resolver, it is reduced to 2.5%. In case that only numeral sets are trained and tested, 2.0% error rate is achieved. When only alphabet sets are considered, the error rate is reduced to 1.1%.

Towards Optimal Connectivity on Multi-layered Networks.

PubMed

Chen, Chen; He, Jingrui; Bliss, Nadya; Tong, Hanghang

2017-10-01

Networks are prevalent in many high impact domains. Moreover, cross-domain interactions are frequently observed in many applications, which naturally form the dependencies between different networks. Such kind of highly coupled network systems are referred to as multi-layered networks , and have been used to characterize various complex systems, including critical infrastructure networks, cyber-physical systems, collaboration platforms, biological systems and many more. Different from single-layered networks where the functionality of their nodes is mainly affected by within-layer connections, multi-layered networks are more vulnerable to disturbance as the impact can be amplified through cross-layer dependencies, leading to the cascade failure to the entire system. To manipulate the connectivity in multi-layered networks, some recent methods have been proposed based on two-layered networks with specific types of connectivity measures. In this paper, we address the above challenges in multiple dimensions. First, we propose a family of connectivity measures (SUBLINE) that unifies a wide range of classic network connectivity measures. Third, we reveal that the connectivity measures in SUBLINE family enjoy diminishing returns property , which guarantees a near-optimal solution with linear complexity for the connectivity optimization problem. Finally, we evaluate our proposed algorithm on real data sets to demonstrate its effectiveness and efficiency.

Electroencephalography epilepsy classifications using hybrid cuckoo search and neural network

NASA Astrophysics Data System (ADS)

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 %.

Experimental and artificial neural network based prediction of performance and emission characteristics of DI diesel engine using Calophyllum inophyllum methyl ester at different nozzle opening pressure

NASA Astrophysics Data System (ADS)

Vairamuthu, G.; Thangagiri, B.; Sundarapandian, S.

2018-01-01

The present work investigates the effect of varying Nozzle Opening Pressures (NOP) from 220 bar to 250 bar on performance, emissions and combustion characteristics of Calophyllum inophyllum Methyl Ester (CIME) in a constant speed, Direct Injection (DI) diesel engine using Artificial Neural Network (ANN) approach. An ANN model has been developed to predict a correlation between specific fuel consumption (SFC), brake thermal efficiency (BTE), exhaust gas temperature (EGT), Unburnt hydrocarbon (UBHC), CO, CO2, NOx and smoke density using load, blend (B0 and B100) and NOP as input data. A standard Back-Propagation Algorithm (BPA) for the engine is used in this model. A Multi Layer Perceptron network (MLP) is used for nonlinear mapping between the input and the output parameters. An ANN model can predict the performance of diesel engine and the exhaust emissions with correlation coefficient (R2) in the range of 0.98-1. Mean Relative Errors (MRE) values are in the range of 0.46-5.8%, while the Mean Square Errors (MSE) are found to be very low. It is evident that the ANN models are reliable tools for the prediction of DI diesel engine performance and emissions. The test results show that the optimum NOP is 250 bar with B100.

Automatic Detection of Landslides at Stromboli Volcano

NASA Astrophysics Data System (ADS)

Giudicepietro, F.; Esposito, A. M.; D'Auria, L.; Peluso, R.; Martini, M.

2011-12-01

In this work we present an automatic system for the landslide detection at Stromboli volcano that has proved to be effective both during the 2007 effusive eruption and in the recent (2 August 2011) volcanic activity. The study of the landslides at Stromboli is important because they could be considered short-term precursors of effusive eruptions, as seen during the 2007 eruption, and in addition they allow to improve the monitoring of the gravitational instabilities of the Sciara del Fuoco flank. The proposed system uses a two-class MLP (Multi Layer Perceptron) neural network in order to discriminate the landslides from other seismic signals usually recorded at Stromboli, such as explosion-quakes and volcanic tremor. To train and test the network we used a dataset of 537 signals, including 267 landslides and 270 other events (130 explosion-quakes and 140 tremor signals). The net performance is of 98.7%, if averaged over different net configurations, and of 99.5% for the best net performance. Based on the neural network response, the automatic system calculates a Landslide Percentage Index (LPI) defined on the number of signals identified as landslides by the net on a given temporal interval in order to recognize anomalies in the landslide rate. This system was sensitive to the signals produced by the flow of lava front during a recent mild effusive episode on the "La Sciara del Fuoco" slope.

Neural analysis of bovine ovaries ultrasound images in the identification process of the corpus luteum

NASA Astrophysics Data System (ADS)

Górna, K.; Jaśkowski, B. M.; Okoń, P.; Czechlowski, M.; Koszela, K.; Zaborowicz, M.; Idziaszek, P.

2017-07-01

The aim of the paper is to shown the neural image analysis as a method useful for identifying the development stage of the domestic bovine corpus luteum on digital USG (UltraSonoGraphy) images. Corpus luteum (CL) is a transient endocrine gland that develops after ovulation from the follicle secretory cells. The aim of CL is the production of progesterone, which regulates many reproductive functions. In the presented studies, identification of the corpus luteum was carried out on the basis of information contained in ultrasound digital images. Development stage of the corpus luteum was considered in two aspects: just before and middle of domination phase and luteolysis and degradation phase. Prior to the classification, the ultrasound images have been processed using a GLCM (Gray Level Co-occurence Matrix). To generate a classification model, a Neural Networks module implemented in the STATISTICA was used. Five representative parameters describing the ultrasound image were used as learner variables. On the output of the artificial neural network was generated information about the development stage of the corpus luteum. Results of this study indicate that neural image analysis combined with GLCM texture analysis may be a useful tool for identifying the bovine corpus luteum in the context of its development phase. Best-generated artificial neural network model was the structure of MLP (Multi Layer Perceptron) 5:5-17-1:1.

Design of a universal two-layered neural network derived from the PLI theory

NASA Astrophysics Data System (ADS)

Hu, Chia-Lun J.

2004-05-01

The if-and-only-if (IFF) condition that a set of M analog-to-digital vector-mapping relations can be learned by a one-layered-feed-forward neural network (OLNN) is that all the input analog vectors dichotomized by the i-th output bit must be positively, linearly independent, or PLI. If they are not PLI, then the OLNN just cannot learn no matter what learning rules is employed because the solution of the connection matrix does not exist mathematically. However, in this case, one can still design a parallel-cascaded, two-layered, perceptron (PCTLP) to acheive this general mapping goal. The design principle of this "universal" neural network is derived from the major mathematical properties of the PLI theory - changing the output bits of the dependent relations existing among the dichotomized input vectors to make the PLD relations PLI. Then with a vector concatenation technique, the required mapping can still be learned by this PCTLP system with very high efficiency. This paper will report in detail the mathematical derivation of the general design principle and the design procedures of the PCTLP neural network system. It then will be verified in general by a practical numerical example.

Neural computing for numeric-to-symbolic conversion in control systems

NASA Technical Reports Server (NTRS)

Passino, Kevin M.; Sartori, Michael A.; Antsaklis, Panos J.

1989-01-01

A type of neural network, the multilayer perceptron, is used to classify numeric data and assign appropriate symbols to various classes. This numeric-to-symbolic conversion results in a type of information extraction, which is similar to what is called data reduction in pattern recognition. The use of the neural network as a numeric-to-symbolic converter is introduced, its application in autonomous control is discussed, and several applications are studied. The perceptron is used as a numeric-to-symbolic converter for a discrete-event system controller supervising a continuous variable dynamic system. It is also shown how the perceptron can implement fault trees, which provide useful information (alarms) in a biological system and information for failure diagnosis and control purposes in an aircraft example.

Estimating Top-of-Atmosphere Thermal Infrared Radiance Using MERRA-2 Atmospheric Data

NASA Astrophysics Data System (ADS)

Kleynhans, Tania

Space borne thermal infrared sensors have been extensively used for environmental research as well as cross-calibration of other thermal sensing systems. Thermal infrared data from satellites such as Landsat and Terra/MODIS have limited temporal resolution (with a repeat cycle of 1 to 2 days for Terra/MODIS, and 16 days for Landsat). Thermal instruments with finer temporal resolution on geostationary satellites have limited utility for cross-calibration due to their large view angles. Reanalysis atmospheric data is available on a global spatial grid at three hour intervals making it a potential alternative to existing satellite image data. This research explores using the Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) reanalysis data product to predict top-of-atmosphere (TOA) thermal infrared radiance globally at time scales finer than available satellite data. The MERRA-2 data product provides global atmospheric data every three hours from 1980 to the present. Due to the high temporal resolution of the MERRA-2 data product, opportunities for novel research and applications are presented. While MERRA-2 has been used in renewable energy and hydrological studies, this work seeks to leverage the model to predict TOA thermal radiance. Two approaches have been followed, namely physics-based approach and a supervised learning approach, using Terra/MODIS band 31 thermal infrared data as reference. The first physics-based model uses forward modeling to predict TOA thermal radiance. The second model infers the presence of clouds from the MERRA-2 atmospheric data, before applying an atmospheric radiative transfer model. The last physics-based model parameterized the previous model to minimize computation time. The second approach applied four different supervised learning algorithms to the atmospheric data. The algorithms included a linear least squares regression model, a non-linear support vector regression (SVR) model, a multi-layer perceptron (MLP), and a convolutional neural network (CNN). This research found that the multi-layer perceptron model produced the lowest error rates overall, with an RMSE of 1.22W / m2 sr mum when compared to actual Terra/MODIS band 31 image data. This research further aimed to characterize the errors associated with each method so that any potential user will have the best information available should they wish to apply these methods towards their own application.

Estimation of Scale Deposition in the Water Walls of an Operating Indian Coal Fired Boiler: Predictive Modeling Approach Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Kumari, Amrita; Das, Suchandan Kumar; Srivastava, Prem Kumar

2016-04-01

Application of computational intelligence for predicting industrial processes has been in extensive use in various industrial sectors including power sector industry. An ANN model using multi-layer perceptron philosophy has been proposed in this paper to predict the deposition behaviors of oxide scale on waterwall tubes of a coal fired boiler. The input parameters comprises of boiler water chemistry and associated operating parameters, such as, pH, alkalinity, total dissolved solids, specific conductivity, iron and dissolved oxygen concentration of the feed water and local heat flux on boiler tube. An efficient gradient based network optimization algorithm has been employed to minimize neural predictions errors. Effects of heat flux, iron content, pH and the concentrations of total dissolved solids in feed water and other operating variables on the scale deposition behavior have been studied. It has been observed that heat flux, iron content and pH of the feed water have a relatively prime influence on the rate of oxide scale deposition in water walls of an Indian boiler. Reasonably good agreement between ANN model predictions and the measured values of oxide scale deposition rate has been observed which is corroborated by the regression fit between these values.

Fouling resistance prediction using artificial neural network nonlinear auto-regressive with exogenous input model based on operating conditions and fluid properties correlations

DOE Office of Scientific and Technical Information (OSTI.GOV)

Biyanto, Totok R.

Fouling in a heat exchanger in Crude Preheat Train (CPT) refinery is an unsolved problem that reduces the plant efficiency, increases fuel consumption and CO{sub 2} emission. The fouling resistance behavior is very complex. It is difficult to develop a model using first principle equation to predict the fouling resistance due to different operating conditions and different crude blends. In this paper, Artificial Neural Networks (ANN) MultiLayer Perceptron (MLP) with input structure using Nonlinear Auto-Regressive with eXogenous (NARX) is utilized to build the fouling resistance model in shell and tube heat exchanger (STHX). The input data of the model aremore » flow rates and temperatures of the streams of the heat exchanger, physical properties of product and crude blend data. This model serves as a predicting tool to optimize operating conditions and preventive maintenance of STHX. The results show that the model can capture the complexity of fouling characteristics in heat exchanger due to thermodynamic conditions and variations in crude oil properties (blends). It was found that the Root Mean Square Error (RMSE) are suitable to capture the nonlinearity and complexity of the STHX fouling resistance during phases of training and validation.« less

Using artificial neural networks to classify unknown volatile chemicals from the firings of insect olfactory sensory neurons.

PubMed

Bachtiar, Luqman R; Unsworth, Charles P; Newcomb, Richard D; Crampin, Edmund J

2011-01-01

The olfactory system detects volatile chemical compounds, known as odour molecules or odorants. Such odorants have a diverse chemical structure which in turn interact with the receptors of the olfactory system. The insect olfactory system provides a unique opportunity to directly measure the firing rates that are generated by the individual olfactory sensory neurons (OSNs) which have been stimulated by odorants in order to use this data to inform their classification. In this work, we demonstrate that it is possible to use the firing rates from an array of OSNs of the vinegar fly, Drosophila melanogaster, to train an Artificial Neural Network (ANN), as a series of a Multi-Layer Perceptrons (MLPs), to differentiate between eight distinct chemical classes. We demonstrate that the MLPs when trained on 108 odorants, for both clean and 10% noise injected data, can reliably identify 87% of an unseen validation set of chemicals using noise injection. In addition, the noise injected MLPs provide a more accurate level of identification. This demonstrates that a 10% noise injected series of MLPs provides a robust method for classifying chemicals from the firing rates of OSNs and paves the way to a future realisation of an artificial olfactory biosensor.

Design and optimisation of novel configurations of stormwater constructed wetlands

NASA Astrophysics Data System (ADS)

Kiiza, Christopher

2017-04-01

Constructed wetlands (CWs) are recognised as a cost-effective technology for wastewater treatment. CWs have been deployed and could be retrofitted into existing urban drainage systems to prevent surface water pollution, attenuate floods and act as sources for reusable water. However, there exist numerous criteria for design configuration and operation of CWs. The aim of the study was to examine effects of design and operational variables on performance of CWs. To achieve this, 8 novel designs of vertical flow CWs were continuously operated and monitored (weekly) for 2years. Pollutant removal efficiency in each CW unit was evaluated from physico-chemical analyses of influent and effluent water samples. Hybrid optimised multi-layer perceptron artificial neural networks (MLP ANNs) were applied to simulate treatment efficiency in the CWs. Subsequently, predictive and analytical models were developed for each design unit. Results show models have sound generalisation abilities; with various design configurations and operational variables influencing performance of CWs. Although some design configurations attained faster and higher removal efficiencies than others; all 8 CW designs produced effluents permissible for discharge into watercourses with strict regulatory standards.

Heterogeneous data fusion and intelligent techniques embedded in a mobile application for real-time chronic disease management.

PubMed

Bellos, Christos; Papadopoulos, Athanassios; Rosso, Roberto; Fotiadis, Dimitrios I

2011-01-01

CHRONIOUS system is an integrated platform aiming at the management of chronic disease patients. One of the most important components of the system is a Decision Support System (DSS) that has been developed in a Smart Device (SD). This component decides on patient's current health status by combining several data, which are acquired either by wearable sensors or manually inputted by the patient or retrieved from the specific database. In case no abnormal situation has been tracked, the DSS takes no action and remains deactivated until next abnormal situation pack of data are being acquired or next scheduled data being transmitted. The DSS that has been implemented is an integrated classification system with two parallel classifiers, combining an expert system (rule-based system) and a supervised classifier, such as Support Vector Machines (SVM), Random Forests, artificial Neural Networks (aNN like the Multi-Layer Perceptron), Decision Trees and Naïve Bayes. The above categorized system is useful for providing critical information about the health status of the patient.

The use of wavelet packet transform and artificial neural networks in analysis and classification of dysphonic voices.

PubMed

Crovato, César David Paredes; Schuck, Adalberto

2007-10-01

This paper presents a dysphonic voice classification system using the wavelet packet transform and the best basis algorithm (BBA) as dimensionality reductor and 06 artificial neural networks (ANN) acting as specialist systems. Each ANN was a 03-layer multilayer perceptron with 64 input nodes, 01 output node and in the intermediary layer the number of neurons depends on the related training pathology group. The dysphonic voice database was separated in five pathology groups and one healthy control group. Each ANN was trained and associated with one of the 06 groups, and fed by the best base tree (BBT) nodes' entropy values, using the multiple cross validation (MCV) method and the leave-one-out (LOO) variation technique and success rates obtained were 87.5%, 95.31%, 87.5%, 100%, 96.87% and 89.06% for the groups 01 to 06, respectively.

Probability matching in perceptrons: Effects of conditional dependence and linear nonseparability.

PubMed

Dawson, Michael R W; Gupta, Maya

2017-01-01

Probability matching occurs when the behavior of an agent matches the likelihood of occurrence of events in the agent's environment. For instance, when artificial neural networks match probability, the activity in their output unit equals the past probability of reward in the presence of a stimulus. Our previous research demonstrated that simple artificial neural networks (perceptrons, which consist of a set of input units directly connected to a single output unit) learn to match probability when presented different cues in isolation. The current paper extends this research by showing that perceptrons can match probabilities when presented simultaneous cues, with each cue signaling different reward likelihoods. In our first simulation, we presented up to four different cues simultaneously; the likelihood of reward signaled by the presence of one cue was independent of the likelihood of reward signaled by other cues. Perceptrons learned to match reward probabilities by treating each cue as an independent source of information about the likelihood of reward. In a second simulation, we violated the independence between cues by making some reward probabilities depend upon cue interactions. We did so by basing reward probabilities on a logical combination (AND or XOR) of two of the four possible cues. We also varied the size of the reward associated with the logical combination. We discovered that this latter manipulation was a much better predictor of perceptron performance than was the logical structure of the interaction between cues. This indicates that when perceptrons learn to match probabilities, they do so by assuming that each signal of a reward is independent of any other; the best predictor of perceptron performance is a quantitative measure of the independence of these input signals, and not the logical structure of the problem being learned.

Probability matching in perceptrons: Effects of conditional dependence and linear nonseparability

PubMed Central

2017-01-01

Probability matching occurs when the behavior of an agent matches the likelihood of occurrence of events in the agent’s environment. For instance, when artificial neural networks match probability, the activity in their output unit equals the past probability of reward in the presence of a stimulus. Our previous research demonstrated that simple artificial neural networks (perceptrons, which consist of a set of input units directly connected to a single output unit) learn to match probability when presented different cues in isolation. The current paper extends this research by showing that perceptrons can match probabilities when presented simultaneous cues, with each cue signaling different reward likelihoods. In our first simulation, we presented up to four different cues simultaneously; the likelihood of reward signaled by the presence of one cue was independent of the likelihood of reward signaled by other cues. Perceptrons learned to match reward probabilities by treating each cue as an independent source of information about the likelihood of reward. In a second simulation, we violated the independence between cues by making some reward probabilities depend upon cue interactions. We did so by basing reward probabilities on a logical combination (AND or XOR) of two of the four possible cues. We also varied the size of the reward associated with the logical combination. We discovered that this latter manipulation was a much better predictor of perceptron performance than was the logical structure of the interaction between cues. This indicates that when perceptrons learn to match probabilities, they do so by assuming that each signal of a reward is independent of any other; the best predictor of perceptron performance is a quantitative measure of the independence of these input signals, and not the logical structure of the problem being learned. PMID:28212422

An ensemble of dynamic neural network identifiers for fault detection and isolation of gas turbine engines.

PubMed

Amozegar, M; Khorasani, K

2016-04-01

In this paper, a new approach for Fault Detection and Isolation (FDI) of gas turbine engines is proposed by developing an ensemble of dynamic neural network identifiers. For health monitoring of the gas turbine engine, its dynamics is first identified by constructing three separate or individual dynamic neural network architectures. Specifically, a dynamic multi-layer perceptron (MLP), a dynamic radial-basis function (RBF) neural network, and a dynamic support vector machine (SVM) are trained to individually identify and represent the gas turbine engine dynamics. Next, three ensemble-based techniques are developed to represent the gas turbine engine dynamics, namely, two heterogeneous ensemble models and one homogeneous ensemble model. It is first shown that all ensemble approaches do significantly improve the overall performance and accuracy of the developed system identification scheme when compared to each of the stand-alone solutions. The best selected stand-alone model (i.e., the dynamic RBF network) and the best selected ensemble architecture (i.e., the heterogeneous ensemble) in terms of their performances in achieving an accurate system identification are then selected for solving the FDI task. The required residual signals are generated by using both a single model-based solution and an ensemble-based solution under various gas turbine engine health conditions. Our extensive simulation studies demonstrate that the fault detection and isolation task achieved by using the residuals that are obtained from the dynamic ensemble scheme results in a significantly more accurate and reliable performance as illustrated through detailed quantitative confusion matrix analysis and comparative studies. Copyright © 2016 Elsevier Ltd. All rights reserved.

Models of Acetylcholine and Dopamine Signals Differentially Improve Neural Representations

PubMed Central

Holca-Lamarre, Raphaël; Lücke, Jörg; Obermayer, Klaus

2017-01-01

Biological and artificial neural networks (ANNs) represent input signals as patterns of neural activity. In biology, neuromodulators can trigger important reorganizations of these neural representations. For instance, pairing a stimulus with the release of either acetylcholine (ACh) or dopamine (DA) evokes long lasting increases in the responses of neurons to the paired stimulus. The functional roles of ACh and DA in rearranging representations remain largely unknown. Here, we address this question using a Hebbian-learning neural network model. Our aim is both to gain a functional understanding of ACh and DA transmission in shaping biological representations and to explore neuromodulator-inspired learning rules for ANNs. We model the effects of ACh and DA on synaptic plasticity and confirm that stimuli coinciding with greater neuromodulator activation are over represented in the network. We then simulate the physiological release schedules of ACh and DA. We measure the impact of neuromodulator release on the network's representation and on its performance on a classification task. We find that ACh and DA trigger distinct changes in neural representations that both improve performance. The putative ACh signal redistributes neural preferences so that more neurons encode stimulus classes that are challenging for the network. The putative DA signal adapts synaptic weights so that they better match the classes of the task at hand. Our model thus offers a functional explanation for the effects of ACh and DA on cortical representations. Additionally, our learning algorithm yields performances comparable to those of state-of-the-art optimisation methods in multi-layer perceptrons while requiring weaker supervision signals and interacting with synaptically-local weight updates. PMID:28690509

Effectiveness of feature and classifier algorithms in character recognition systems

NASA Astrophysics Data System (ADS)

Wilson, Charles L.

1993-04-01

At the first Census Optical Character Recognition Systems Conference, NIST generated accuracy data for more than character recognition systems. Most systems were tested on the recognition of isolated digits and upper and lower case alphabetic characters. The recognition experiments were performed on sample sizes of 58,000 digits, and 12,000 upper and lower case alphabetic characters. The algorithms used by the 26 conference participants included rule-based methods, image-based methods, statistical methods, and neural networks. The neural network methods included Multi-Layer Perceptron's, Learned Vector Quantitization, Neocognitrons, and cascaded neural networks. In this paper 11 different systems are compared using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition, and comparing the writer dependence of recognition. This comparison shows that methods that used different algorithms for feature extraction and recognition performed with very high levels of correlation. This is true for neural network systems, hybrid systems, and statistically based systems, and leads to the conclusion that neural networks have not yet demonstrated a clear superiority to more conventional statistical methods. Comparison of these results with the models of Vapnick (for estimation problems), MacKay (for Bayesian statistical models), Moody (for effective parameterization), and Boltzmann models (for information content) demonstrate that as the limits of training data variance are approached, all classifier systems have similar statistical properties. The limiting condition can only be approached for sufficiently rich feature sets because the accuracy limit is controlled by the available information content of the training set, which must pass through the feature extraction process prior to classification.

Inversion of surface parameters using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.

1992-01-01

A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.

Neural Network Modeling for Gallium Arsenide IC Fabrication Process and Device Characteristics.

NASA Astrophysics Data System (ADS)

Creech, Gregory Lee, I.

This dissertation presents research focused on the utilization of neurocomputing technology to achieve enhanced yield and effective yield prediction in integrated circuit (IC) manufacturing. Artificial neural networks are employed to model complex relationships between material and device characteristics at critical stages of the semiconductor fabrication process. Whole wafer testing was performed on the starting substrate material and during wafer processing at four critical steps: Ohmic or Post-Contact, Post-Recess, Post-Gate and Final, i.e., at completion of fabrication. Measurements taken and subsequently used in modeling include, among others, doping concentrations, layer thicknesses, planar geometries, layer-to-layer alignments, resistivities, device voltages, and currents. The neural network architecture used in this research is the multilayer perceptron neural network (MLPNN). The MLPNN is trained in the supervised mode using the generalized delta learning rule. It has one hidden layer and uses continuous perceptrons. The research focuses on a number of different aspects. First is the development of inter-process stage models. Intermediate process stage models are created in a progressive fashion. Measurements of material and process/device characteristics taken at a specific processing stage and any previous stages are used as input to the model of the next processing stage characteristics. As the wafer moves through the fabrication process, measurements taken at all previous processing stages are used as input to each subsequent process stage model. Secondly, the development of neural network models for the estimation of IC parametric yield is demonstrated. Measurements of material and/or device characteristics taken at earlier fabrication stages are used to develop models of the final DC parameters. These characteristics are computed with the developed models and compared to acceptance windows to estimate the parametric yield. A sensitivity analysis is performed on the models developed during this yield estimation effort. This is accomplished by analyzing the total disturbance of network outputs due to perturbed inputs. When an input characteristic bears no, or little, statistical or deterministic relationship to the output characteristics, it can be removed as an input. Finally, neural network models are developed in the inverse direction. Characteristics measured after the final processing step are used as the input to model critical in-process characteristics. The modeled characteristics are used for whole wafer mapping and its statistical characterization. It is shown that this characterization can be accomplished with minimal in-process testing. The concepts and methodologies used in the development of the neural network models are presented. The modeling results are provided and compared to the actual measured values of each characteristic. An in-depth discussion of these results and ideas for future research are presented.

Dynamic clustering scheme based on the coordination of management and control in multi-layer and multi-region intelligent optical network

NASA Astrophysics Data System (ADS)

Niu, Xiaoliang; Yuan, Fen; Huang, Shanguo; Guo, Bingli; Gu, Wanyi

2011-12-01

A Dynamic clustering scheme based on coordination of management and control is proposed to reduce network congestion rate and improve the blocking performance of hierarchical routing in Multi-layer and Multi-region intelligent optical network. Its implement relies on mobile agent (MA) technology, which has the advantages of efficiency, flexibility, functional and scalability. The paper's major contribution is to adjust dynamically domain when the performance of working network isn't in ideal status. And the incorporation of centralized NMS and distributed MA control technology migrate computing process to control plane node which releases the burden of NMS and improves process efficiently. Experiments are conducted on Multi-layer and multi-region Simulation Platform for Optical Network (MSPON) to assess the performance of the scheme.

Face recognition: a convolutional neural-network approach.

PubMed

Lawrence, S; Giles, C L; Tsoi, A C; Back, A D

1997-01-01

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.

Regional shape-based feature space for segmenting biomedical images using neural networks

NASA Astrophysics Data System (ADS)

Sundaramoorthy, Gopal; Hoford, John D.; Hoffman, Eric A.

1993-07-01

In biomedical images, structure of interest, particularly the soft tissue structures, such as the heart, airways, bronchial and arterial trees often have grey-scale and textural characteristics similar to other structures in the image, making it difficult to segment them using only gray- scale and texture information. However, these objects can be visually recognized by their unique shapes and sizes. In this paper we discuss, what we believe to be, a novel, simple scheme for extracting features based on regional shapes. To test the effectiveness of these features for image segmentation (classification), we use an artificial neural network and a statistical cluster analysis technique. The proposed shape-based feature extraction algorithm computes regional shape vectors (RSVs) for all pixels that meet a certain threshold criteria. The distance from each such pixel to a boundary is computed in 8 directions (or in 26 directions for a 3-D image). Together, these 8 (or 26) values represent the pixel's (or voxel's) RSV. All RSVs from an image are used to train a multi-layered perceptron neural network which uses these features to 'learn' a suitable classification strategy. To clearly distinguish the desired object from other objects within an image, several examples from inside and outside the desired object are used for training. Several examples are presented to illustrate the strengths and weaknesses of our algorithm. Both synthetic and actual biomedical images are considered. Future extensions to this algorithm are also discussed.

Statistical downscaling of sub-daily (6-hour) temperature in Romania, by means of artificial neural networks

NASA Astrophysics Data System (ADS)

Birsan, Marius-Victor; Dumitrescu, Alexandru; Cǎrbunaru, Felicia

2016-04-01

The role of statistical downscaling is to model the relationship between large-scale atmospheric circulation and climatic variables on a regional and sub-regional scale, making use of the predictions of future circulation generated by General Circulation Models (GCMs) in order to capture the effects of climate change on smaller areas. The study presents a statistical downscaling model based on a neural network-based approach, by means of multi-layer perceptron networks. Sub-daily temperature data series from 81 meteorological stations over Romania, with full data records are used as predictands. As large-scale predictor, the NCEP/NCAD air temperature data at 850 hPa over the domain 20-30E / 40-50N was used, at a spatial resolution of 2.5×2.5 degrees. The period 1961-1990 was used for calibration, while the validation was realized over the 1991-2010 interval. Further, in order to estimate future changes in air temperature for 2021-2050 and 2071-2100, air temperature data at 850 hPa corresponding to the IPCC A1B scenario was extracted from the CNCM33 model (Meteo-France) and used as predictor. This work has been realized within the research project "Changes in climate extremes and associated impact in hydrological events in Romania" (CLIMHYDEX), code PN II-ID-2011-2-0073, financed by the Romanian Executive Agency for Higher Education Research, Development and Innovation Funding (UEFISCDI).

Low-cost autonomous perceptron neural network inspired by quantum computation

NASA Astrophysics Data System (ADS)

Zidan, Mohammed; Abdel-Aty, Abdel-Haleem; El-Sadek, Alaa; Zanaty, E. A.; Abdel-Aty, Mahmoud

2017-11-01

Achieving low cost learning with reliable accuracy is one of the important goals to achieve intelligent machines to save time, energy and perform learning process over limited computational resources machines. In this paper, we propose an efficient algorithm for a perceptron neural network inspired by quantum computing composite from a single neuron to classify inspirable linear applications after a single training iteration O(1). The algorithm is applied over a real world data set and the results are outer performs the other state-of-the art algorithms.

BCC skin cancer diagnosis based on texture analysis techniques

NASA Astrophysics Data System (ADS)

Chuang, Shao-Hui; Sun, Xiaoyan; Chang, Wen-Yu; Chen, Gwo-Shing; Huang, Adam; Li, Jiang; McKenzie, Frederic D.

2011-03-01

In this paper, we present a texture analysis based method for diagnosing the Basal Cell Carcinoma (BCC) skin cancer using optical images taken from the suspicious skin regions. We first extracted the Run Length Matrix and Haralick texture features from the images and used a feature selection algorithm to identify the most effective feature set for the diagnosis. We then utilized a Multi-Layer Perceptron (MLP) classifier to classify the images to BCC or normal cases. Experiments showed that detecting BCC cancer based on optical images is feasible. The best sensitivity and specificity we achieved on our data set were 94% and 95%, respectively.

Neural networks in data analysis and modeling for detecting littoral oil-spills by airborne laser fluorosensor remote sensing

NASA Astrophysics Data System (ADS)

Lin, Bin; An, Jubai; Brown, Carl E.; Chen, Weiwei

2003-05-01

In this paper an artificial neural network (ANN) approach, which is based on flexible nonlinear models for a very broad class of transfer functions, is applied for multi-spectral data analysis and modeling of airborne laser fluorosensor in order to differentiate between classes of oil on water surface. We use three types of algorithm: Perceptron Network, Back-Propagation (B-P) Network and Self-Organizing feature Maps (SOM) Network. Using the data in form of 64-channel spectra as inputs, the ANN presents the analysis and estimation results of the oil type on the basis of the type of background materials as outputs. The ANN is trained and tested using sample data set to the network. The results of the above 3 types of network are compared in this paper. It is proved that the training has developed a network that not only fits the training data, but also fits real-world data that the network will process operationally. The ANN model would play a significant role in the ocean oil-spill identification in the future.

Cross-Dependency Inference in Multi-Layered Networks: A Collaborative Filtering Perspective.

PubMed

Chen, Chen; Tong, Hanghang; Xie, Lei; Ying, Lei; He, Qing

2017-08-01

The increasingly connected world has catalyzed the fusion of networks from different domains, which facilitates the emergence of a new network model-multi-layered networks. Examples of such kind of network systems include critical infrastructure networks, biological systems, organization-level collaborations, cross-platform e-commerce, and so forth. One crucial structure that distances multi-layered network from other network models is its cross-layer dependency, which describes the associations between the nodes from different layers. Needless to say, the cross-layer dependency in the network plays an essential role in many data mining applications like system robustness analysis and complex network control. However, it remains a daunting task to know the exact dependency relationships due to noise, limited accessibility, and so forth. In this article, we tackle the cross-layer dependency inference problem by modeling it as a collective collaborative filtering problem. Based on this idea, we propose an effective algorithm Fascinate that can reveal unobserved dependencies with linear complexity. Moreover, we derive Fascinate-ZERO, an online variant of Fascinate that can respond to a newly added node timely by checking its neighborhood dependencies. We perform extensive evaluations on real datasets to substantiate the superiority of our proposed approaches.

Perceptron ensemble of graph-based positive-unlabeled learning for disease gene identification.

PubMed

Jowkar, Gholam-Hossein; Mansoori, Eghbal G

2016-10-01

Identification of disease genes, using computational methods, is an important issue in biomedical and bioinformatics research. According to observations that diseases with the same or similar phenotype have the same biological characteristics, researchers have tried to identify genes by using machine learning tools. In recent attempts, some semi-supervised learning methods, called positive-unlabeled learning, is used for disease gene identification. In this paper, we present a Perceptron ensemble of graph-based positive-unlabeled learning (PEGPUL) on three types of biological attributes: gene ontologies, protein domains and protein-protein interaction networks. In our method, a reliable set of positive and negative genes are extracted using co-training schema. Then, the similarity graph of genes is built using metric learning by concentrating on multi-rank-walk method to perform inference from labeled genes. At last, a Perceptron ensemble is learned from three weighted classifiers: multilevel support vector machine, k-nearest neighbor and decision tree. The main contributions of this paper are: (i) incorporating the statistical properties of gene data through choosing proper metrics, (ii) statistical evaluation of biological features, and (iii) noise robustness characteristic of PEGPUL via using multilevel schema. In order to assess PEGPUL, we have applied it on 12950 disease genes with 949 positive genes from six class of diseases and 12001 unlabeled genes. Compared with some popular disease gene identification methods, the experimental results show that PEGPUL has reasonable performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Learning to classify in large committee machines

NASA Astrophysics Data System (ADS)

O'kane, Dominic; Winther, Ole

1994-10-01

The ability of a two-layer neural network to learn a specific non-linearly-separable classification task, the proximity problem, is investigated using a statistical mechanics approach. Both the tree and fully connected architectures are investigated in the limit where the number K of hidden units is large, but still much smaller than the number N of inputs. Both have continuous weights. Within the replica symmetric ansatz, we find that for zero temperature training, the tree architecture exhibits a strong overtraining effect. For nonzero temperature the asymptotic error is lowered, but it is still higher than the corresponding value for the simple perceptron. The fully connected architecture is considered for two regimes. First, for a finite number of examples we find a symmetry among the hidden units as each performs equally well. The asymptotic generalization error is finite, and minimal for T-->∞ where it goes to the same value as for the simple perceptron. For a large number of examples we find a continuous transition to a phase with broken hidden-unit symmetry, which has an asymptotic generalization error equal to zero.

Automatic QRS complex detection using two-level convolutional neural network.

PubMed

Xiang, Yande; Lin, Zhitao; Meng, Jianyi

2018-01-29

The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

Determination of combustion parameters using engine crankshaft speed

NASA Astrophysics Data System (ADS)

Taglialatela, F.; Lavorgna, M.; Mancaruso, E.; Vaglieco, B. M.

2013-07-01

Electronic engine controls based on real time diagnosis of combustion process can significantly help in complying with the stricter and stricter regulations on pollutants emissions and fuel consumption. The most important parameter for the evaluation of combustion quality in internal combustion engines is the in-cylinder pressure, but its direct measurement is very expensive and involves an intrusive approach to the cylinder. Previous researches demonstrated the direct relationship existing between in-cylinder pressure and engine crankshaft speed and several authors tried to reconstruct the pressure cycle on the basis of the engine speed signal. In this paper we propose the use of a Multi-Layer Perceptron neural network to model the relationship between the engine crankshaft speed and some parameters derived from the in-cylinder pressure cycle. This allows to have a non-intrusive estimation of cylinder pressure and a real time evaluation of combustion quality. The structure of the model and the training procedure is outlined in the paper. A possible combustion controller using the information extracted from the crankshaft speed information is also proposed. The application of the neural network model is demonstrated on a single-cylinder spark ignition engine tested in a wide range of speeds and loads. Results confirm that a good estimation of some combustion pressure parameters can be obtained by means of a suitable processing of crankshaft speed signal.

A novel single neuron perceptron with universal approximation and XOR computation properties.

PubMed

Lotfi, Ehsan; Akbarzadeh-T, M-R

2014-01-01

We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous system. The resulting architecture of SNP can be trained by supervised excitatory and inhibitory online learning rules. The main features of proposed single layer perceptron are universal approximation property and low computational complexity. The method is tested on 6 UCI (University of California, Irvine) pattern recognition and classification datasets. Various comparisons with multilayer perceptron (MLP) with gradient decent backpropagation (GDBP) learning algorithm indicate the superiority of the approach in terms of higher accuracy, lower time, and spatial complexity, as well as faster training. Hence, we believe the proposed approach can be generally applicable to various problems such as in pattern recognition and classification.

Identifing Atmospheric Pollutant Sources Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Paes, F. F.; Campos, H. F.; Luz, E. P.; Carvalho, A. R.

2008-05-01

The estimation of the area source pollutant strength is a relevant issue for atmospheric environment. This characterizes an inverse problem in the atmospheric pollution dispersion. In the inverse analysis, an area source domain is considered, where the strength of such area source term is assumed unknown. The inverse problem is solved by using a supervised artificial neural network: multi-layer perceptron. The conection weights of the neural network are computed from delta rule - learning process. The neural network inversion is compared with results from standard inverse analysis (regularized inverse solution). In the regularization method, the inverse problem is formulated as a non-linear optimization approach, whose the objective function is given by the square difference between the measured pollutant concentration and the mathematical models, associated with a regularization operator. In our numerical experiments, the forward problem is addressed by a source-receptor scheme, where a regressive Lagrangian model is applied to compute the transition matrix. The second order maximum entropy regularization is used, and the regularization parameter is calculated by the L-curve technique. The objective function is minimized employing a deterministic scheme (a quasi-Newton algorithm) [1] and a stochastic technique (PSO: particle swarm optimization) [2]. The inverse problem methodology is tested with synthetic observational data, from six measurement points in the physical domain. The best inverse solutions were obtained with neural networks. References: [1] D. R. Roberti, D. Anfossi, H. F. Campos Velho, G. A. Degrazia (2005): Estimating Emission Rate and Pollutant Source Location, Ciencia e Natura, p. 131-134. [2] E.F.P. da Luz, H.F. de Campos Velho, J.C. Becceneri, D.R. Roberti (2007): Estimating Atmospheric Area Source Strength Through Particle Swarm Optimization. Inverse Problems, Desing and Optimization Symposium IPDO-2007, April 16-18, Miami (FL), USA, vol 1, p. 354-359.

Perceptron Genetic to Recognize Openning Strategy Ruy Lopez

NASA Astrophysics Data System (ADS)

Azmi, Zulfian; Mawengkang, Herman

2018-01-01

The application of Perceptron method is not effective for coding on hardware based systems because it is not real time learning. With Genetic algorithm approach in calculating and searching the best weight (fitness value) system will do learning only one iteration. And the results of this analysis were tested in the case of the introduction of the opening pattern of chess Ruy Lopez. The Analysis with Perceptron Model with Algorithm Approach Genetics from group Artificial Neural Network for open Ruy Lopez. The data is processed with base open chess, with step eight a position white Pion from end open chess. Using perceptron method have many input and one output process many weight and refraction until output equal goal. Data trained and test with software Matlab and system can recognize the chess opening Ruy Lopez or Not open Ruy Lopez with Real time.

A Framework for Supporting Survivability, Network Planning and Cross-Layer Optimization in Future Multi-Domain Terabit Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Baldin, Ilya; Huang, Shu; Gopidi, Rajesh

This final project report describes the accomplishments, products and publications from the award. It includes the overview of the project goals to devise a framework for managing resources in multi-domain, multi-layer networks, as well the details of the mathematical problem formulation and the description of the prototype built to prove the concept.

Classification of reflected signals from cavitated tooth surfaces using an artificial intelligence technique incorporating a fiber optic displacement sensor

NASA Astrophysics Data System (ADS)

Rahman, Husna Abdul; Harun, Sulaiman Wadi; Arof, Hamzah; Irawati, Ninik; Musirin, Ismail; Ibrahim, Fatimah; Ahmad, Harith

2014-05-01

An enhanced dental cavity diameter measurement mechanism using an intensity-modulated fiber optic displacement sensor (FODS) scanning and imaging system, fuzzy logic as well as a single-layer perceptron (SLP) neural network, is presented. The SLP network was employed for the classification of the reflected signals, which were obtained from the surfaces of teeth samples and captured using FODS. Two features were used for the classification of the reflected signals with one of them being the output of a fuzzy logic. The test results showed that the combined fuzzy logic and SLP network methodology contributed to a 100% classification accuracy of the network. The high-classification accuracy significantly demonstrates the suitability of the proposed features and classification using SLP networks for classifying the reflected signals from teeth surfaces, enabling the sensor to accurately measure small diameters of tooth cavity of up to 0.6 mm. The method remains simple enough to allow its easy integration in existing dental restoration support systems.

Macrocell path loss prediction using artificial intelligence techniques

NASA Astrophysics Data System (ADS)

Usman, Abraham U.; Okereke, Okpo U.; Omizegba, Elijah E.

2014-04-01

The prediction of propagation loss is a practical non-linear function approximation problem which linear regression or auto-regression models are limited in their ability to handle. However, some computational Intelligence techniques such as artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFISs) have been shown to have great ability to handle non-linear function approximation and prediction problems. In this study, the multiple layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and an ANFIS network were trained using actual signal strength measurement taken at certain suburban areas of Bauchi metropolis, Nigeria. The trained networks were then used to predict propagation losses at the stated areas under differing conditions. The predictions were compared with the prediction accuracy of the popular Hata model. It was observed that ANFIS model gave a better fit in all cases having higher R2 values in each case and on average is more robust than MLP and RBF models as it generalises better to a different data.

Classification of reflected signals from cavitated tooth surfaces using an artificial intelligence technique incorporating a fiber optic displacement sensor.

PubMed

Rahman, Husna Abdul; Harun, Sulaiman Wadi; Arof, Hamzah; Irawati, Ninik; Musirin, Ismail; Ibrahim, Fatimah; Ahmad, Harith

2014-05-01

An enhanced dental cavity diameter measurement mechanism using an intensity-modulated fiber optic displacement sensor (FODS) scanning and imaging system, fuzzy logic as well as a single-layer perceptron (SLP) neural network, is presented. The SLP network was employed for the classification of the reflected signals, which were obtained from the surfaces of teeth samples and captured using FODS. Two features were used for the classification of the reflected signals with one of them being the output of a fuzzy logic. The test results showed that the combined fuzzy logic and SLP network methodology contributed to a 100% classification accuracy of the network. The high-classification accuracy significantly demonstrates the suitability of the proposed features and classification using SLP networks for classifying the reflected signals from teeth surfaces, enabling the sensor to accurately measure small diameters of tooth cavity of up to 0.6 mm. The method remains simple enough to allow its easy integration in existing dental restoration support systems.

Distributed Grooming in Multi-Domain IP/MPLS-DWDM Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Liu, Qing

2009-12-01

This paper studies distributed multi-domain, multilayer provisioning (grooming) in IP/MPLS-DWDM networks. Although many multi-domain studies have emerged over the years, these have primarily considered 'homogeneous' network layers. Meanwhile, most grooming studies have assumed idealized settings with 'global' link state across all layers. Hence there is a critical need to develop practical distributed grooming schemes for real-world networks consisting of multiple domains and technology layers. Along these lines, a detailed hierarchical framework is proposed to implement inter-layer routing, distributed grooming, and setup signaling. The performance of this solution is analyzed in detail using simulation studies and future work directions are alsomore » high-lighted.« less

Simulation of a Multidimensional Input Quantum Perceptron

NASA Astrophysics Data System (ADS)

Yamamoto, Alexandre Y.; Sundqvist, Kyle M.; Li, Peng; Harris, H. Rusty

2018-06-01

In this work, we demonstrate the improved data separation capabilities of the Multidimensional Input Quantum Perceptron (MDIQP), a fundamental cell for the construction of more complex Quantum Artificial Neural Networks (QANNs). This is done by using input controlled alterations of ancillary qubits in combination with phase estimation and learning algorithms. The MDIQP is capable of processing quantum information and classifying multidimensional data that may not be linearly separable, extending the capabilities of the classical perceptron. With this powerful component, we get much closer to the achievement of a feedforward multilayer QANN, which would be able to represent and classify arbitrary sets of data (both quantum and classical).

Advances in Artificial Neural Networks - Methodological Development and Application

USDA-ARS?s Scientific Manuscript database

Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...

Collision avoidance using neural networks

NASA Astrophysics Data System (ADS)

Sugathan, Shilpa; Sowmya Shree, B. V.; Warrier, Mithila R.; Vidhyapathi, C. M.

2017-11-01

Now a days, accidents on roads are caused due to the negligence of drivers and pedestrians or due to unexpected obstacles that come into the vehicle’s path. In this paper, a model (robot) is developed to assist drivers for a smooth travel without accidents. It reacts to the real time obstacles on the four critical sides of the vehicle and takes necessary action. The sensor used for detecting the obstacle was an IR proximity sensor. A single layer perceptron neural network is used to train and test all possible combinations of sensors result by using Matlab (offline). A microcontroller (ARM Cortex-M3 LPC1768) is used to control the vehicle through the output data which is received from Matlab via serial communication. Hence, the vehicle becomes capable of reacting to any combination of real time obstacles.

Multivariate Time Series Forecasting of Crude Palm Oil Price Using Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Kanchymalay, Kasturi; Salim, N.; Sukprasert, Anupong; Krishnan, Ramesh; Raba'ah Hashim, Ummi

2017-08-01

The aim of this paper was to study the correlation between crude palm oil (CPO) price, selected vegetable oil prices (such as soybean oil, coconut oil, and olive oil, rapeseed oil and sunflower oil), crude oil and the monthly exchange rate. Comparative analysis was then performed on CPO price forecasting results using the machine learning techniques. Monthly CPO prices, selected vegetable oil prices, crude oil prices and monthly exchange rate data from January 1987 to February 2017 were utilized. Preliminary analysis showed a positive and high correlation between the CPO price and soy bean oil price and also between CPO price and crude oil price. Experiments were conducted using multi-layer perception, support vector regression and Holt Winter exponential smoothing techniques. The results were assessed by using criteria of root mean square error (RMSE), means absolute error (MAE), means absolute percentage error (MAPE) and Direction of accuracy (DA). Among these three techniques, support vector regression(SVR) with Sequential minimal optimization (SMO) algorithm showed relatively better results compared to multi-layer perceptron and Holt Winters exponential smoothing method.

Multi-Sensor Fusion for Enhanced Contextual Awareness of Everyday Activities with Ubiquitous Devices

PubMed Central

Guiry, John J.; van de Ven, Pepijn; Nelson, John

2014-01-01

In this paper, the authors investigate the role that smart devices, including smartphones and smartwatches, can play in identifying activities of daily living. A feasibility study involving N = 10 participants was carried out to evaluate the devices' ability to differentiate between nine everyday activities. The activities examined include walking, running, cycling, standing, sitting, elevator ascents, elevator descents, stair ascents and stair descents. The authors also evaluated the ability of these devices to differentiate indoors from outdoors, with the aim of enhancing contextual awareness. Data from this study was used to train and test five well known machine learning algorithms: C4.5, CART, Naïve Bayes, Multi-Layer Perceptrons and finally Support Vector Machines. Both single and multi-sensor approaches were examined to better understand the role each sensor in the device can play in unobtrusive activity recognition. The authors found overall results to be promising, with some models correctly classifying up to 100% of all instances. PMID:24662406

Multi-sensor fusion for enhanced contextual awareness of everyday activities with ubiquitous devices.

PubMed

Guiry, John J; van de Ven, Pepijn; Nelson, John

2014-03-21

In this paper, the authors investigate the role that smart devices, including smartphones and smartwatches, can play in identifying activities of daily living. A feasibility study involving N = 10 participants was carried out to evaluate the devices' ability to differentiate between nine everyday activities. The activities examined include walking, running, cycling, standing, sitting, elevator ascents, elevator descents, stair ascents and stair descents. The authors also evaluated the ability of these devices to differentiate indoors from outdoors, with the aim of enhancing contextual awareness. Data from this study was used to train and test five well known machine learning algorithms: C4.5, CART, Naïve Bayes, Multi-Layer Perceptrons and finally Support Vector Machines. Both single and multi-sensor approaches were examined to better understand the role each sensor in the device can play in unobtrusive activity recognition. The authors found overall results to be promising, with some models correctly classifying up to 100% of all instances.

Post interaural neural net-based vowel recognition

NASA Astrophysics Data System (ADS)

Jouny, Ismail I.

2001-10-01

Interaural head related transfer functions are used to process speech signatures prior to neural net based recognition. Data representing the head related transfer function of a dummy has been collected at MIT and made available on the Internet. This data is used to pre-process vowel signatures to mimic the effects of human ear on speech perception. Signatures representing various vowels of the English language are then presented to a multi-layer perceptron trained using the back propagation algorithm for recognition purposes. The focus in this paper is to assess the effects of human interaural system on vowel recognition performance particularly when using a classification system that mimics the human brain such as a neural net.

[Prognosis of the IVF ICSI/ET procedure efficiency with the use of artificial neural networks among patients of the Department of Reproduction and Gynecological Endocrinology].

PubMed

Milewski, Robert; Jamiołkowski, Jacek; Milewska Anna, Justyna; Domitrz, Jan; Szamatowicz, Jacek; Wołczyński, Sławomir

2009-12-01

Prognosis of pregnancy for patients treated with IVF ICSI/ET methods, using artificial neural networks. Retrospective study of 1007 cycles of infertility treatment of 899 patients of Department of Reproduction and Gynecological Endocrinology in Bialystok. The subjects were treated with IVF ICSI/ET method from August 2005 to September 2008. Classifying artificial neural network is described in the paper Architecture of the network is three-layered perceptron consisting of 45 neurons in the input layer 14 neurons in the hidden layer and a single output neuron. The source data for the network are 36 variables. 24 of them are nominal variables and the rest are quantitative variables. Among non-pregnancy cases only 59 prognosis of the network were incorrect. The results of treatment were correctly forecast in 68.5% of cases. The pregnancy was accurately confirmed in 49.1% of cases and lack of pregnancy in 86.5% of cases. Treatment of infertility with the use of in vitro fertilization methods continues to have too low efficiency per one treatment cycle. To improve this indicator it is necessary to find dependencies, which describe the model of IVF treatment. The application of advanced methods of bioinformatics allows to predict the result of the treatment more effectively With the help of artificial neural networks, we are able to forecast the failure of the treatment using IFV ICSI/ET procedure with almost 90% probability of certainty These possibilities can be used to predict negative cases.

A New Approach to Develop Computer-aided Diagnosis Scheme of Breast Mass Classification Using Deep Learning Technology

PubMed Central

Qiu, Yuchen; Yan, Shiju; Gundreddy, Rohith Reddy; Wang, Yunzhi; Cheng, Samuel; Liu, Hong; Zheng, Bin

2017-01-01

PURPOSE To develop and test a deep learning based computer-aided diagnosis (CAD) scheme of mammograms for classifying between malignant and benign masses. METHODS An image dataset involving 560 regions of interest (ROIs) extracted from digital mammograms was used. After down-sampling each ROI from 512×512 to 64×64 pixel size, we applied an 8 layer deep learning network that involves 3 pairs of convolution-max-pooling layers for automatic feature extraction and a multiple layer perceptron (MLP) classifier for feature categorization to process ROIs. The 3 pairs of convolution layers contain 20, 10, and 5 feature maps, respectively. Each convolution layer is connected with a max-pooling layer to improve the feature robustness. The output of the sixth layer is fully connected with a MLP classifier, which is composed of one hidden layer and one logistic regression layer. The network then generates a classification score to predict the likelihood of ROI depicting a malignant mass. A four-fold cross validation method was applied to train and test this deep learning network. RESULTS The results revealed that this CAD scheme yields an area under the receiver operation characteristic curve (AUC) of 0.696±0.044, 0.802±0.037, 0.836±0.036, and 0.822±0.035 for fold 1 to 4 testing datasets, respectively. The overall AUC of the entire dataset is 0.790±0.019. CONCLUSIONS This study demonstrates the feasibility of applying a deep learning based CAD scheme to classify between malignant and benign breast masses without a lesion segmentation, image feature computation and selection process. PMID:28436410

A new approach to develop computer-aided diagnosis scheme of breast mass classification using deep learning technology.

PubMed

Qiu, Yuchen; Yan, Shiju; Gundreddy, Rohith Reddy; Wang, Yunzhi; Cheng, Samuel; Liu, Hong; Zheng, Bin

2017-01-01

To develop and test a deep learning based computer-aided diagnosis (CAD) scheme of mammograms for classifying between malignant and benign masses. An image dataset involving 560 regions of interest (ROIs) extracted from digital mammograms was used. After down-sampling each ROI from 512×512 to 64×64 pixel size, we applied an 8 layer deep learning network that involves 3 pairs of convolution-max-pooling layers for automatic feature extraction and a multiple layer perceptron (MLP) classifier for feature categorization to process ROIs. The 3 pairs of convolution layers contain 20, 10, and 5 feature maps, respectively. Each convolution layer is connected with a max-pooling layer to improve the feature robustness. The output of the sixth layer is fully connected with a MLP classifier, which is composed of one hidden layer and one logistic regression layer. The network then generates a classification score to predict the likelihood of ROI depicting a malignant mass. A four-fold cross validation method was applied to train and test this deep learning network. The results revealed that this CAD scheme yields an area under the receiver operation characteristic curve (AUC) of 0.696±0.044, 0.802±0.037, 0.836±0.036, and 0.822±0.035 for fold 1 to 4 testing datasets, respectively. The overall AUC of the entire dataset is 0.790±0.019. This study demonstrates the feasibility of applying a deep learning based CAD scheme to classify between malignant and benign breast masses without a lesion segmentation, image feature computation and selection process.

Meta-modeling of the pesticide fate model MACRO for groundwater exposure assessments using artificial neural networks

NASA Astrophysics Data System (ADS)

Stenemo, Fredrik; Lindahl, Anna M. L.; Gärdenäs, Annemieke; Jarvis, Nicholas

2007-08-01

Several simple index methods that use easily accessible data have been developed and included in decision-support systems to estimate pesticide leaching across larger areas. However, these methods often lack important process descriptions (e.g. macropore flow), which brings into question their reliability. Descriptions of macropore flow have been included in simulation models, but these are too complex and demanding for spatial applications. To resolve this dilemma, a neural network simulation meta-model of the dual-permeability macropore flow model MACRO was created for pesticide groundwater exposure assessment. The model was parameterized using pedotransfer functions that require as input the clay and sand content of the topsoil and subsoil, and the topsoil organic carbon content. The meta-model also requires the topsoil pesticide half-life and the soil organic carbon sorption coefficient as input. A fully connected feed-forward multilayer perceptron classification network with two hidden layers, linked to fully connected feed-forward multilayer perceptron neural networks with one hidden layer, trained on sub-sets of the target variable, was shown to be a suitable meta-model for the intended purpose. A Fourier amplitude sensitivity test showed that the model output (the 80th percentile average yearly pesticide concentration at 1 m depth for a 20 year simulation period) was sensitive to all input parameters. The two input parameters related to pesticide characteristics (i.e. soil organic carbon sorption coefficient and topsoil pesticide half-life) were the most influential, but texture in the topsoil was also quite important since it was assumed to control the mass exchange coefficient that regulates the strength of macropore flow. This is in contrast to models based on the advection-dispersion equation where soil texture is relatively unimportant. The use of the meta-model is exemplified with a case-study where the spatial variability of pesticide leaching is mapped for a small field. It was shown that the area of the field that contributes most to leaching depends on the properties of the compound in question. It is concluded that the simulation meta-model of MACRO should prove useful for mapping relative pesticide leaching risks at large scales.

Modeling multi-process connectivity in river deltas: extending the single layer network analysis to a coupled multilayer network framework

NASA Astrophysics Data System (ADS)

Tejedor, A.; Longjas, A.; Foufoula-Georgiou, E.

2017-12-01

Previous work [e.g. Tejedor et al., 2016 - GRL] has demonstrated the potential of using graph theory to study key properties of the structure and dynamics of river delta channel networks. Although the distribution of fluxes in river deltas is mostly driven by the connectivity of its channel network a significant part of the fluxes might also arise from connectivity between the channels and islands due to overland flow and seepage. This channel-island-subsurface interaction creates connectivity pathways which facilitate or inhibit transport depending on their degree of coupling. The question we pose here is how to collectively study system connectivity that emerges from the aggregated action of different processes (different in nature, intensity and time scales). Single-layer graphs as those introduced for delta channel networks are inadequate as they lack the ability to represent coupled processes, and neglecting across-process interactions can lead to mis-representation of the overall system dynamics. We present here a framework that generalizes the traditional representation of networks (single-layer graphs) to the so-called multi-layer networks or multiplex. A multi-layer network conceptualizes the overall connectivity arising from different processes as distinct graphs (layers), while allowing at the same time to represent interactions between layers by introducing interlayer links (across process interactions). We illustrate this framework using a study of the joint connectivity that arises from the coupling of the confined flow on the channel network and the overland flow on islands, on a prototype delta. We show the potential of the multi-layer framework to answer quantitatively questions related to the characteristic time scales to steady-state transport in the system as a whole when different levels of channel-island coupling are modulated by different magnitudes of discharge rates.

Cross-Layer Scheme to Control Contention Window for Per-Flow in Asymmetric Multi-Hop Networks

NASA Astrophysics Data System (ADS)

Giang, Pham Thanh; Nakagawa, Kenji

The IEEE 802.11 MAC standard for wireless ad hoc networks adopts Binary Exponential Back-off (BEB) mechanism to resolve bandwidth contention between stations. BEB mechanism controls the bandwidth allocation for each station by choosing a back-off value from one to CW according to the uniform random distribution, where CW is the contention window size. However, in asymmetric multi-hop networks, some stations are disadvantaged in opportunity of access to the shared channel and may suffer severe throughput degradation when the traffic load is large. Then, the network performance is degraded in terms of throughput and fairness. In this paper, we propose a new cross-layer scheme aiming to solve the per-flow unfairness problem and achieve good throughput performance in IEEE 802.11 multi-hop ad hoc networks. Our cross-layer scheme collects useful information from the physical, MAC and link layers of own station. This information is used to determine the optimal Contention Window (CW) size for per-station fairness. We also use this information to adjust CW size for each flow in the station in order to achieve per-flow fairness. Performance of our cross-layer scheme is examined on various asymmetric multi-hop network topologies by using Network Simulator (NS-2).

Deep neural mapping support vector machines.

PubMed

Li, Yujian; Zhang, Ting

2017-09-01

The choice of kernel has an important effect on the performance of a support vector machine (SVM). The effect could be reduced by NEUROSVM, an architecture using multilayer perceptron for feature extraction and SVM for classification. In binary classification, a general linear kernel NEUROSVM can be theoretically simplified as an input layer, many hidden layers, and an SVM output layer. As a feature extractor, the sub-network composed of the input and hidden layers is first trained together with a virtual ordinary output layer by backpropagation, then with the output of its last hidden layer taken as input of the SVM classifier for further training separately. By taking the sub-network as a kernel mapping from the original input space into a feature space, we present a novel model, called deep neural mapping support vector machine (DNMSVM), from the viewpoint of deep learning. This model is also a new and general kernel learning method, where the kernel mapping is indeed an explicit function expressed as a sub-network, different from an implicit function induced by a kernel function traditionally. Moreover, we exploit a two-stage procedure of contrastive divergence learning and gradient descent for DNMSVM to jointly training an adaptive kernel mapping instead of a kernel function, without requirement of kernel tricks. As a whole of the sub-network and the SVM classifier, the joint training of DNMSVM is done by using gradient descent to optimize the objective function with the sub-network layer-wise pre-trained via contrastive divergence learning of restricted Boltzmann machines. Compared to the separate training of NEUROSVM, the joint training is a new algorithm for DNMSVM to have advantages over NEUROSVM. Experimental results show that DNMSVM can outperform NEUROSVM and RBFSVM (i.e., SVM with the kernel of radial basis function), demonstrating its effectiveness. Copyright © 2017 Elsevier Ltd. All rights reserved.

Perceptrons and Pattern Recognition

DTIC Science & Technology

1967-09-01

invariant ~isual patterns. Rosenblatt, F •. , !t_i~ip_les of Neurodynamics , Spartan Books, 1962. Introg~ces and discusses many parallel-network...classification ;of the patterns -th~selves, and their r~ cognition by per~eptrons. It· would b~ too much to ask for an absolute classification of "patt~’""’ls...function-of the level of existing cognitive structure. 0.5 Seductive Aspects of Perceptro~a, II: Parallel Computation The perceptron was conceived

Modeling the variations of reflection coefficient of Earth's lower ionosphere using very low frequency radio wave data by artificial neural network

NASA Astrophysics Data System (ADS)

Ghanbari, Keyvan; Khakian Ghomi, Mehdi; Mohammadi, Mohammad; Marbouti, Marjan; Tan, Le Minh

2016-08-01

The ionized atmosphere lying from 50 to 600 km above surface, known as ionosphere, contains high amount of electrons and ions. Very Low Frequency (VLF) radio waves with frequencies between 3 and 30 kHz are reflected from the lower ionosphere specifically D-region. A lot of applications in long range communications and navigation systems have been inspired by this characteristic of ionosphere. There are several factors which affect the ionization rate in this region, such as: time of day (presence of sun in the sky), solar zenith angle (seasons) and solar activities. Due to nonlinear response of ionospheric reflection coefficient to these factors, finding an accurate relation between these parameters and reflection coefficient is an arduous task. In order to model these kinds of nonlinear functionalities, some numerical methods are employed. One of these methods is artificial neural network (ANN). In this paper, the VLF radio wave data of 4 sudden ionospheric disturbance (SID) stations are given to a multi-layer perceptron ANN in order to simulate the variations of reflection coefficient of D region ionosphere. After training, validation and testing the ANN, outputs of ANN and observed values are plotted together for 2 random cases of each station. By evaluating the results using 2 parameters of pearson correlation coefficient and root mean square error, a satisfying agreement was found between ANN outputs and real observed data.

Predicting coronary artery disease using different artificial neural network models.

PubMed

Colak, M Cengiz; Colak, Cemil; Kocatürk, Hasan; Sağiroğlu, Seref; Barutçu, Irfan

2008-08-01

Eight different learning algorithms used for creating artificial neural network (ANN) models and the different ANN models in the prediction of coronary artery disease (CAD) are introduced. This work was carried out as a retrospective case-control study. Overall, 124 consecutive patients who had been diagnosed with CAD by coronary angiography (at least 1 coronary stenosis > 50% in major epicardial arteries) were enrolled in the work. Angiographically, the 113 people (group 2) with normal coronary arteries were taken as control subjects. Multi-layered perceptrons ANN architecture were applied. The ANN models trained with different learning algorithms were performed in 237 records, divided into training (n=171) and testing (n=66) data sets. The performance of prediction was evaluated by sensitivity, specificity and accuracy values based on standard definitions. The results have demonstrated that ANN models trained with eight different learning algorithms are promising because of high (greater than 71%) sensitivity, specificity and accuracy values in the prediction of CAD. Accuracy, sensitivity and specificity values varied between 83.63%-100%, 86.46%-100% and 74.67%-100% for training, respectively. For testing, the values were more than 71% for sensitivity, 76% for specificity and 81% for accuracy. It may be proposed that the use of different learning algorithms other than backpropagation and larger sample sizes can improve the performance of prediction. The proposed ANN models trained with these learning algorithms could be used a promising approach for predicting CAD without the need for invasive diagnostic methods and could help in the prognostic clinical decision.

Beam Diagnostics of the Compton Scattering Chamber in Jefferson Lab's Hall C

NASA Astrophysics Data System (ADS)

Faulkner, Adam; I&C Group Collaboration

2013-10-01

Upcoming experimental runs in Hall C will utilize Compton scattering, involving the construction and installation of a rectangular beam enclosure. Conventional cylindrical stripline-style Beam Position Monitors (BPMs) are not appropriate due to their form factor; therefore to facilitate measurement of position, button-style BPMs are being considered due to the ease of placement within the new beam enclosure. Button BPM experience is limited at JLAB, so preliminary measurements are needed to characterize the field response, and guide the development of appropriate algorithms for the Analog to Digital receiver systems. -field mapping is performed using a Goubau Line (G-Line), which employs a surface wave to mimic the electron beam, helping to avoid problems associated with vacuum systems. Potential algorithms include simplistic 1/r modeling (-field mapping), look-up-tables, as well as a potential third order power series fit. In addition, the use of neural networks specifically the multi-layer Perceptron will be examined. The models, sensor field maps, and utility of the neural network will be presented. Next steps include: modification of the control algorithm, as well as to run an in-situ test of the four Button electrodes inside of a mock beam enclosure. The analysis of the field response using Matlab suggests the button BPMs are accurate to within 10 mm, and may be successful for beam diagnostics in Hall C. More testing is necessary to ascertain the limitations of the new electrodes. The National Science Foundation, Old Dominion University, The Department of Energy, and Jefferson Lab.

Multi-layer service function chaining scheduling based on auxiliary graph in IP over optical network

NASA Astrophysics Data System (ADS)

Li, Yixuan; Li, Hui; Liu, Yuze; Ji, Yuefeng

2017-10-01

Software Defined Optical Network (SDON) can be considered as extension of Software Defined Network (SDN) in optical networks. SDON offers a unified control plane and makes optical network an intelligent transport network with dynamic flexibility and service adaptability. For this reason, a comprehensive optical transmission service, able to achieve service differentiation all the way down to the optical transport layer, can be provided to service function chaining (SFC). IP over optical network, as a promising networking architecture to interconnect data centers, is the most widely used scenarios of SFC. In this paper, we offer a flexible and dynamic resource allocation method for diverse SFC service requests in the IP over optical network. To do so, we firstly propose the concept of optical service function (OSF) and a multi-layer SFC model. OSF represents the comprehensive optical transmission service (e.g., multicast, low latency, quality of service, etc.), which can be achieved in multi-layer SFC model. OSF can also be considered as a special SF. Secondly, we design a resource allocation algorithm, which we call OSF-oriented optical service scheduling algorithm. It is able to address multi-layer SFC optical service scheduling and provide comprehensive optical transmission service, while meeting multiple optical transmission requirements (e.g., bandwidth, latency, availability). Moreover, the algorithm exploits the concept of Auxiliary Graph. Finally, we compare our algorithm with the Baseline algorithm in simulation. And simulation results show that our algorithm achieves superior performance than Baseline algorithm in low traffic load condition.

High variation subarctic topsoil pollutant concentration prediction using neural network residual kriging

NASA Astrophysics Data System (ADS)

Sergeev, A. P.; Tarasov, D. A.; Buevich, A. G.; Subbotina, I. E.; Shichkin, A. V.; Sergeeva, M. V.; Lvova, O. A.

2017-06-01

The work deals with the application of neural networks residual kriging (NNRK) to the spatial prediction of the abnormally distributed soil pollutant (Cr). It is known that combination of geostatistical interpolation approaches (kriging) and neural networks leads to significantly better prediction accuracy and productivity. Generalized regression neural networks and multilayer perceptrons are classes of neural networks widely used for the continuous function mapping. Each network has its own pros and cons; however both demonstrated fast training and good mapping possibilities. In the work, we examined and compared two combined techniques: generalized regression neural network residual kriging (GRNNRK) and multilayer perceptron residual kriging (MLPRK). The case study is based on the real data sets on surface contamination by chromium at a particular location of the subarctic Novy Urengoy, Russia, obtained during the previously conducted screening. The proposed models have been built, implemented and validated using ArcGIS and MATLAB environments. The networks structures have been chosen during a computer simulation based on the minimization of the RMSE. MLRPK showed the best predictive accuracy comparing to the geostatistical approach (kriging) and even to GRNNRK.

Global multi-layer network of human mobility

PubMed Central

Belyi, Alexander; Bojic, Iva; Sobolevsky, Stanislav; Sitko, Izabela; Hawelka, Bartosz; Rudikova, Lada; Kurbatski, Alexander; Ratti, Carlo

2017-01-01

ABSTRACT Recent availability of geo-localized data capturing individual human activity together with the statistical data on international migration opened up unprecedented opportunities for a study on global mobility. In this paper, we consider it from the perspective of a multi-layer complex network, built using a combination of three datasets: Twitter, Flickr and official migration data. Those datasets provide different, but equally important insights on the global mobility – while the first two highlight short-term visits of people from one country to another, the last one – migration – shows the long-term mobility perspective, when people relocate for good. The main purpose of the paper is to emphasize importance of this multi-layer approach capturing both aspects of human mobility at the same time. On the one hand, we show that although the general properties of different layers of the global mobility network are similar, there are important quantitative differences among them. On the other hand, we demonstrate that consideration of mobility from a multi-layer perspective can reveal important global spatial patterns in a way more consistent with those observed in other available relevant sources of international connections, in comparison to the spatial structure inferred from each network layer taken separately. PMID:28553155

Detection of gene communities in multi-networks reveals cancer drivers

NASA Astrophysics Data System (ADS)

Cantini, Laura; Medico, Enzo; Fortunato, Santo; Caselle, Michele

2015-12-01

We propose a new multi-network-based strategy to integrate different layers of genomic information and use them in a coordinate way to identify driving cancer genes. The multi-networks that we consider combine transcription factor co-targeting, microRNA co-targeting, protein-protein interaction and gene co-expression networks. The rationale behind this choice is that gene co-expression and protein-protein interactions require a tight coregulation of the partners and that such a fine tuned regulation can be obtained only combining both the transcriptional and post-transcriptional layers of regulation. To extract the relevant biological information from the multi-network we studied its partition into communities. To this end we applied a consensus clustering algorithm based on state of art community detection methods. Even if our procedure is valid in principle for any pathology in this work we concentrate on gastric, lung, pancreas and colorectal cancer and identified from the enrichment analysis of the multi-network communities a set of candidate driver cancer genes. Some of them were already known oncogenes while a few are new. The combination of the different layers of information allowed us to extract from the multi-network indications on the regulatory pattern and functional role of both the already known and the new candidate driver genes.

Deep Visual Attention Prediction

NASA Astrophysics Data System (ADS)

Wang, Wenguan; Shen, Jianbing

2018-05-01

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve CNN based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark datasets demonstrate our method yields state-of-the-art performance with competitive inference time.

A novel multi-band SAR data technique for fully automatic oil spill detection in the ocean

NASA Astrophysics Data System (ADS)

Del Frate, Fabio; Latini, Daniele; Taravat, Alireza; Jones, Cathleen E.

2013-10-01

With the launch of the Italian constellation of small satellites for the Mediterranean basin observation COSMO-SkyMed and the German TerraSAR-X missions, the delivery of very high-resolution SAR data to observe the Earth day or night has remarkably increased. In particular, also taking into account other ongoing missions such as Radarsat or those no longer working such as ALOS PALSAR, ERS-SAR and ENVISAT the amount of information, at different bands, available for users interested in oil spill analysis has become highly massive. Moreover, future SAR missions such as Sentinel-1 are scheduled for launch in the very next years while additional support can be provided by Uninhabited Aerial Vehicle (UAV) SAR systems. Considering the opportunity represented by all these missions, the challenge is to find suitable and adequate image processing multi-band procedures able to fully exploit the huge amount of data available. In this paper we present a new fast, robust and effective automated approach for oil-spill monitoring starting from data collected at different bands, polarizations and spatial resolutions. A combination of Weibull Multiplicative Model (WMM), Pulse Coupled Neural Network (PCNN) and Multi-Layer Perceptron (MLP) techniques is proposed for achieving the aforementioned goals. One of the most innovative ideas is to separate the dark spot detection process into two main steps, WMM enhancement and PCNN segmentation. The complete processing chain has been applied to a data set containing C-band (ERS-SAR, ENVISAT ASAR), X-band images (Cosmo-SkyMed and TerraSAR-X) and L-band images (UAVSAR) for an overall number of more than 200 images considered.

Neural network modeling for surgical decisions on traumatic brain injury patients.

PubMed

Li, Y C; Liu, L; Chiu, W T; Jian, W S

2000-01-01

Computerized medical decision support systems have been a major research topic in recent years. Intelligent computer programs were implemented to aid physicians and other medical professionals in making difficult medical decisions. This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS). These models were developed based on a large TBI patient database. This MDSS accepts a set of patient data such as the types of skull fracture, Glasgow Coma Scale (GCS), episode of convulsion and return the chance that a neurosurgeon would recommend an open-skull surgery for this patient. The three mathematical models described in this report including a logistic regression model, a multi-layer perceptron (MLP) neural network and a radial-basis-function (RBF) neural network. From the 12,640 patients selected from the database. A randomly drawn 9480 cases were used as the training group to develop/train our models. The other 3160 cases were in the validation group which we used to evaluate the performance of these models. We used sensitivity, specificity, areas under receiver-operating characteristics (ROC) curve and calibration curves as the indicator of how accurate these models are in predicting a neurosurgeon's decision on open-skull surgery. The results showed that, assuming equal importance of sensitivity and specificity, the logistic regression model had a (sensitivity, specificity) of (73%, 68%), compared to (80%, 80%) from the RBF model and (88%, 80%) from the MLP model. The resultant areas under ROC curve for logistic regression, RBF and MLP neural networks are 0.761, 0.880 and 0.897, respectively (P < 0.05). Among these models, the logistic regression has noticeably poorer calibration. This study demonstrated the feasibility of applying neural networks as the mechanism for TBI decision support systems based on clinical databases. The results also suggest that neural networks may be a better solution for complex, non-linear medical decision support systems than conventional statistical techniques such as logistic regression.

Reconstruction of sub-surface archaeological remains from magnetic data using neural computing.

NASA Astrophysics Data System (ADS)

Bescoby, D. J.; Cawley, G. C.; Chroston, P. N.

2003-04-01

The remains of a former Roman colonial settlement, once part of the classical city of Butrint in southern Albania have been the subject of a high resolution magnetic survey using a caesium-vapour magnetometer. The survey revealed the surviving remains of an extensive planned settlement and a number of outlying buildings, today buried beneath over 0.5 m of alluvial deposits. The aim of the current research is to derive a sub-surface model from the magnetic survey measurements, allowing an enhanced archaeological interpretation of the data. Neural computing techniques are used to perform the non-linear mapping between magnetic data and corresponding sub-surface model parameters. The adoption of neural computing paradigms potentially holds several advantages over other modelling techniques, allowing fast solutions for complex data, while having a high tolerance to noise. A multi-layer perceptron network with a feed-forward architecture is trained to estimate the shape and burial depth of wall foundations using a series of representative models as training data. Parameters used to forward model the training data sets are derived from a number of trial trench excavations targeted over features identified by the magnetic survey. The training of the network was optimized by first applying it to synthetic test data of known source parameters. Pre-processing of the network input data, including the use of a rotationally invariant transform, enhanced network performance and the efficiency of the training data. The approach provides good results when applied to real magnetic data, accurately predicting the depths and layout of wall foundations within the former settlement, verified by subsequent excavation. The resulting sub-surface model is derived from the averaged outputs of a ‘committee’ of five networks, trained with individualized training sets. Fuzzy logic inference has also been used to combine individual network outputs through correlation with data from a second geophysical technique, allowing the integration of data from a separate series of measurements.

Identifying the Community Structure of the Food-Trade International Multi-Network

NASA Technical Reports Server (NTRS)

Torreggiani, S.; Mangioni, G.

2018-01-01

Achieving international food security requires improved understanding of how international trade networks connect countries around the world through the import-export flows of food commodities. The properties of international food trade networks are still poorly documented, especially from a multi-network perspective. In particular, nothing is known about the multi-network's community structure. Here we find that the individual crop-specific layers of the multi-network have densely connected trading groups, a consistent characteristic over the period 2001-2011. Further, the multi-network is characterized by low variability over this period but with substantial heterogeneity across layers in each year. In particular, the layers are mostly assortative: more-intensively connected countries tend to import from and export to countries that are themselves more connected. We also fit econometric models to identify social, economic and geographic factors explaining the probability that any two countries are co-present in the same community. Our estimates indicate that the probability of country pairs belonging to the same food trade community depends more on geopolitical and economic factors-such as geographical proximity and trade-agreement co-membership-than on country economic size and/or income. These community-structure findings of the multi-network are especially valuable for efforts to understand past and emerging dynamics in the global food system, especially those that examine potential 'shocks' to global food trade.

An inference method from multi-layered structure of biomedical data.

PubMed

Kim, Myungjun; Nam, Yonghyun; Shin, Hyunjung

2017-05-18

Biological system is a multi-layered structure of omics with genome, epigenome, transcriptome, metabolome, proteome, etc., and can be further stretched to clinical/medical layers such as diseasome, drugs, and symptoms. One advantage of omics is that we can figure out an unknown component or its trait by inferring from known omics components. The component can be inferred by the ones in the same level of omics or the ones in different levels. To implement the inference process, an algorithm that can be applied to the multi-layered complex system is required. In this study, we develop a semi-supervised learning algorithm that can be applied to the multi-layered complex system. In order to verify the validity of the inference, it was applied to the prediction problem of disease co-occurrence with a two-layered network composed of symptom-layer and disease-layer. The symptom-disease layered network obtained a fairly high value of AUC, 0.74, which is regarded as noticeable improvement when comparing 0.59 AUC of single-layered disease network. If further stretched to whole layered structure of omics, the proposed method is expected to produce more promising results. This research has novelty in that it is a new integrative algorithm that incorporates the vertical structure of omics data, on contrary to other existing methods that integrate the data in parallel fashion. The results can provide enhanced guideline for disease co-occurrence prediction, thereby serve as a valuable tool for inference process of multi-layered biological system.

A Facile CD Protocol for Rapid Determination of Enantiomeric Excess and Concentration of Chiral Primary Amines

PubMed Central

Nieto, Sonia; Dragna, Justin M.; Anslyn, Eric V.

2010-01-01

A protocol for the rapid determination of the absolute configuration and enantiomeric excess of α-chiral primary amines with potential applications in asymmetric reaction discovery has been developed. The protocol requires derivatization of α-chiral primary amines via condensation with pyridine carboxaldehyde to quantitatively yield the corresponding imine. The Cu(I) complex with 2,2'-bis (diphenylphosphino)-1,1'-dinaphthyl (BINAP -CuI) with the imine yields a metal-to-ligand-charge-transfer band (MLCT) in the visible region of the circular dichroism spectrum upon binding. Diastereomeric host-guest complexes give CD signals of the same signs, but different amplitudes, allowing for differentiation of enantiomers. Processing the primary optical data from the CD spectrum with linear discriminant analysis (LDA) allows for the determination of absolute configuration and identification of the amines, and processing with a supervised multi-layer perceptron artifical neural network (MLP-ANN) allows for the simultaneous determination of ee and concentration. The primary optical data necessary to determine the ee of unknown samples is obtained in 2 minutes per sample. To demonstrate the utility of the protocol in asymmetric reaction discovery, the ee's and concentrations for an asymmetric metal catalyzed reaction are determined. The potential of the protocol's application in high-throughput screening (HTS) of ee is discussed. PMID:19946914

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs

PubMed Central

Erdakov, Ivan Nikolaevich; Taha, Mohamed~Adel; Soliman, Mahmoud Sayed; El Rayes, Magdy Mostafa

2018-01-01

Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth–Pareto optimization of an artificial neural network (ANN) is presented in this paper for surface roughness (Ra) prediction of one component in computer numerical control (CNC) turning over minimal machining time (Tm) and at prime machining costs (C). An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP), to predict Ra, Tm, and C, in relation to cutting speed, vc, depth of cut, ap, and feed per revolution, fr. For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values vc, ap, and fr. The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, Tm = 0.358 min/cm3, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed vc = 250 m/min, cutting depth ap = 1.0 mm, and feed per revolution fr = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness. PMID:29772670

Escherichia coli's water load affects zebrafish (Danio rerio) behavior.

PubMed

Amorim, João; Fernandes, Miguel; Abreu, Isabel; Tavares, Fernando; Oliva-Teles, Luis

2018-05-01

Traditional physico-chemical sensors are becoming an obsolete tool for environmental quality assessment. Biomonitoring techniques, such as biological early warning systems present the advantage of being sensitivity, fast, non-invasive and ecologically relevant. In this work, we applied a video tracking system, developed with zebrafish (Danio rerio), to detect microbiological contamination in water. Using the fishs' behavior response, the system was able to detect the presence of a non-pathogenic environmental strain of Escherichia coli, at three different levels of contamination: 600, 1800 and 5000 CFU/100 mL (colony forming units/100 mL). Data was collected during 50 min of exposure and analyzed with the artificial neural networks Self-organizing Map and Multi-layer Perceptron. The behavior of exposed fish was more erratic, with pronounced and rapid changes on movement direction and with significant less exploratory activity. The accuracy, sensitivity and specificity values regarding the detection capability (distinction between presence or absence of contamination) ranged from 89 to 100%. Regarding the classification capability (distinction between experimental conditions), the values ranged from 67 to 89%. This research may be a valuable contribution to improve water monitoring and management strategies, by taking as reference the effects on biosensors, without a biased anthropocentric perspective. Copyright © 2018 Elsevier B.V. All rights reserved.

Separation of pulsar signals from noise using supervised machine learning algorithms

NASA Astrophysics Data System (ADS)

Bethapudi, S.; Desai, S.

2018-04-01

We evaluate the performance of four different machine learning (ML) algorithms: an Artificial Neural Network Multi-Layer Perceptron (ANN MLP), Adaboost, Gradient Boosting Classifier (GBC), and XGBoost, for the separation of pulsars from radio frequency interference (RFI) and other sources of noise, using a dataset obtained from the post-processing of a pulsar search pipeline. This dataset was previously used for the cross-validation of the SPINN-based machine learning engine, obtained from the reprocessing of the HTRU-S survey data (Morello et al., 2014). We have used the Synthetic Minority Over-sampling Technique (SMOTE) to deal with high-class imbalance in the dataset. We report a variety of quality scores from all four of these algorithms on both the non-SMOTE and SMOTE datasets. For all the above ML methods, we report high accuracy and G-mean for both the non-SMOTE and SMOTE cases. We study the feature importances using Adaboost, GBC, and XGBoost and also from the minimum Redundancy Maximum Relevance approach to report algorithm-agnostic feature ranking. From these methods, we find that the signal to noise of the folded profile to be the best feature. We find that all the ML algorithms report FPRs about an order of magnitude lower than the corresponding FPRs obtained in Morello et al. (2014), for the same recall value.

LETTER TO THE EDITOR: Dynamics of interacting neural networks

NASA Astrophysics Data System (ADS)

Kinzel, W.; Metzler, R.; Kanter, I.

2000-04-01

The dynamics of interacting perceptrons is solved analytically. For a directed flow of information the system runs into a state which has a higher symmetry than the topology of the model. A symmetry-breaking phase transition is found with increasing learning rate. In addition, it is shown that a system of interacting perceptrons which is trained on the history of its minority decisions develops a good strategy for the problem of adaptive competition known as the bar problem or minority game.

Neural network classification of myoelectric signal for prosthesis control.

PubMed

Kelly, M F; Parker, P A; Scott, R N

1991-12-01

An alternate approach to deriving control for multidegree of freedom prosthetic arms is considered. By analyzing a single-channel myoelectric signal (MES), we can extract information that can be used to identify different contraction patterns in the upper arm. These contraction patterns are generated by subjects without previous training and are naturally associated with specific functions. Using a set of normalized MES spectral features, we can identify contraction patterns for four arm functions, specifically extension and flexion of the elbow and pronation and supination of the forearm. Performing identification independent of signal power is advantageous because this can then be used as a means for deriving proportional rate control for a prosthesis. An artificial neural network implementation is applied in the classification task. By using three single-layer perceptron networks, the MES is classified, with the spectral representations as input features. Trials performed on five subjects with normal limbs resulted in an average classification performance level of 85% for the four functions. Copyright © 1991. Published by Elsevier Ltd.

Artificial Neural Network Based Mission Planning Mechanism for Spacecraft

NASA Astrophysics Data System (ADS)

Li, Zhaoyu; Xu, Rui; Cui, Pingyuan; Zhu, Shengying

2018-04-01

The ability to plan and react fast in dynamic space environments is central to intelligent behavior of spacecraft. For space and robotic applications, many planners have been used. But it is difficult to encode the domain knowledge and directly use existing techniques such as heuristic to improve the performance of the application systems. Therefore, regarding planning as an advanced control problem, this paper first proposes an autonomous mission planning and action selection mechanism through a multiple layer perceptron neural network approach to select actions in planning process and improve efficiency. To prove the availability and effectiveness, we use autonomous mission planning problems of the spacecraft, which is a sophisticated system with complex subsystems and constraints as an example. Simulation results have shown that artificial neural networks (ANNs) are usable for planning problems. Compared with the existing planning method in EUROPA, the mechanism using ANNs is more efficient and can guarantee stable performance. Therefore, the mechanism proposed in this paper is more suitable for planning problems of spacecraft that require real time and stability.

Gas Sensors Characterization and Multilayer Perceptron (MLP) Hardware Implementation for Gas Identification Using a Field Programmable Gate Array (FPGA)

PubMed Central

Benrekia, Fayçal; Attari, Mokhtar; Bouhedda, Mounir

2013-01-01

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. PMID:23529119

Identifying the community structure of the food-trade international multi-network

NASA Astrophysics Data System (ADS)

Torreggiani, S.; Mangioni, G.; Puma, M. J.; Fagiolo, G.

2018-05-01

Achieving international food security requires improved understanding of how international trade networks connect countries around the world through the import-export flows of food commodities. The properties of international food trade networks are still poorly documented, especially from a multi-network perspective. In particular, nothing is known about the multi-network’s community structure. Here we find that the individual crop-specific layers of the multi-network have densely connected trading groups, a consistent characteristic over the period 2001–2011. Further, the multi-network is characterized by low variability over this period but with substantial heterogeneity across layers in each year. In particular, the layers are mostly assortative: more-intensively connected countries tend to import from and export to countries that are themselves more connected. We also fit econometric models to identify social, economic and geographic factors explaining the probability that any two countries are co-present in the same community. Our estimates indicate that the probability of country pairs belonging to the same food trade community depends more on geopolitical and economic factors—such as geographical proximity and trade-agreement co-membership—than on country economic size and/or income. These community-structure findings of the multi-network are especially valuable for efforts to understand past and emerging dynamics in the global food system, especially those that examine potential ‘shocks’ to global food trade.

A multi-layer steganographic method based on audio time domain segmented and network steganography

NASA Astrophysics Data System (ADS)

Xue, Pengfei; Liu, Hanlin; Hu, Jingsong; Hu, Ronggui

2018-05-01

Both audio steganography and network steganography are belong to modern steganography. Audio steganography has a large capacity. Network steganography is difficult to detect or track. In this paper, a multi-layer steganographic method based on the collaboration of them (MLS-ATDSS&NS) is proposed. MLS-ATDSS&NS is realized in two covert layers (audio steganography layer and network steganography layer) by two steps. A new audio time domain segmented steganography (ATDSS) method is proposed in step 1, and the collaboration method of ATDSS and NS is proposed in step 2. The experimental results showed that the advantage of MLS-ATDSS&NS over others is better trade-off between capacity, anti-detectability and robustness, that means higher steganographic capacity, better anti-detectability and stronger robustness.

Intercomparison of air quality data using principal component analysis, and forecasting of PM₁₀ and PM₂.₅ concentrations using artificial neural networks, in Thessaloniki and Helsinki.

PubMed

Voukantsis, Dimitris; Karatzas, Kostas; Kukkonen, Jaakko; Räsänen, Teemu; Karppinen, Ari; Kolehmainen, Mikko

2011-03-01

In this paper we propose a methodology consisting of specific computational intelligence methods, i.e. principal component analysis and artificial neural networks, in order to inter-compare air quality and meteorological data, and to forecast the concentration levels for environmental parameters of interest (air pollutants). We demonstrate these methods to data monitored in the urban areas of Thessaloniki and Helsinki in Greece and Finland, respectively. For this purpose, we applied the principal component analysis method in order to inter-compare the patterns of air pollution in the two selected cities. Then, we proceeded with the development of air quality forecasting models for both studied areas. On this basis, we formulated and employed a novel hybrid scheme in the selection process of input variables for the forecasting models, involving a combination of linear regression and artificial neural networks (multi-layer perceptron) models. The latter ones were used for the forecasting of the daily mean concentrations of PM₁₀ and PM₂.₅ for the next day. Results demonstrated an index of agreement between measured and modelled daily averaged PM₁₀ concentrations, between 0.80 and 0.85, while the kappa index for the forecasting of the daily averaged PM₁₀ concentrations reached 60% for both cities. Compared with previous corresponding studies, these statistical parameters indicate an improved performance of air quality parameters forecasting. It was also found that the performance of the models for the forecasting of the daily mean concentrations of PM₁₀ was not substantially different for both cities, despite the major differences of the two urban environments under consideration. Copyright © 2011 Elsevier B.V. All rights reserved.

On-line determination of transient stability status using multilayer perceptron neural network

NASA Astrophysics Data System (ADS)

Frimpong, Emmanuel Asuming; Okyere, Philip Yaw; Asumadu, Johnson

2018-01-01

A scheme to predict transient stability status following a disturbance is presented. The scheme is activated upon the tripping of a line or bus and operates as follows: Two samples of frequency deviation values at all generator buses are obtained. At each generator bus, the maximum frequency deviation within the two samples is extracted. A vector is then constructed from the extracted maximum frequency deviations. The Euclidean norm of the constructed vector is calculated and then fed as input to a trained multilayer perceptron neural network which predicts the stability status of the system. The scheme was tested using data generated from the New England test system. The scheme successfully predicted the stability status of all two hundred and five disturbance test cases.

Multilayer perceptron, fuzzy sets, and classification

NASA Technical Reports Server (NTRS)

Pal, Sankar K.; Mitra, Sushmita

1992-01-01

A fuzzy neural network model based on the multilayer perceptron, using the back-propagation algorithm, and capable of fuzzy classification of patterns is described. The input vector consists of membership values to linguistic properties while the output vector is defined in terms of fuzzy class membership values. This allows efficient modeling of fuzzy or uncertain patterns with appropriate weights being assigned to the backpropagated errors depending upon the membership values at the corresponding outputs. During training, the learning rate is gradually decreased in discrete steps until the network converges to a minimum error solution. The effectiveness of the algorithm is demonstrated on a speech recognition problem. The results are compared with those of the conventional MLP, the Bayes classifier, and the other related models.

Training and operation of an integrated neuromorphic network based on metal-oxide memristors.

PubMed

Prezioso, M; Merrikh-Bayat, F; Hoskins, B D; Adam, G C; Likharev, K K; Strukov, D B

2015-05-07

Despite much progress in semiconductor integrated circuit technology, the extreme complexity of the human cerebral cortex, with its approximately 10(14) synapses, makes the hardware implementation of neuromorphic networks with a comparable number of devices exceptionally challenging. To provide comparable complexity while operating much faster and with manageable power dissipation, networks based on circuits combining complementary metal-oxide-semiconductors (CMOSs) and adjustable two-terminal resistive devices (memristors) have been developed. In such circuits, the usual CMOS stack is augmented with one or several crossbar layers, with memristors at each crosspoint. There have recently been notable improvements in the fabrication of such memristive crossbars and their integration with CMOS circuits, including first demonstrations of their vertical integration. Separately, discrete memristors have been used as artificial synapses in neuromorphic networks. Very recently, such experiments have been extended to crossbar arrays of phase-change memristive devices. The adjustment of such devices, however, requires an additional transistor at each crosspoint, and hence these devices are much harder to scale than metal-oxide memristors, whose nonlinear current-voltage curves enable transistor-free operation. Here we report the experimental implementation of transistor-free metal-oxide memristor crossbars, with device variability sufficiently low to allow operation of integrated neural networks, in a simple network: a single-layer perceptron (an algorithm for linear classification). The network can be taught in situ using a coarse-grain variety of the delta rule algorithm to perform the perfect classification of 3 × 3-pixel black/white images into three classes (representing letters). This demonstration is an important step towards much larger and more complex memristive neuromorphic networks.

Two algorithms for neural-network design and training with application to channel equalization.

PubMed

Sweatman, C Z; Mulgrew, B; Gibson, G J

1998-01-01

We describe two algorithms for designing and training neural-network classifiers. The first, the linear programming slab algorithm (LPSA), is motivated by the problem of reconstructing digital signals corrupted by passage through a dispersive channel and by additive noise. It constructs a multilayer perceptron (MLP) to separate two disjoint sets by using linear programming methods to identify network parameters. The second, the perceptron learning slab algorithm (PLSA), avoids the computational costs of linear programming by using an error-correction approach to identify parameters. Both algorithms operate in highly constrained parameter spaces and are able to exploit symmetry in the classification problem. Using these algorithms, we develop a number of procedures for the adaptive equalization of a complex linear 4-quadrature amplitude modulation (QAM) channel, and compare their performance in a simulation study. Results are given for both stationary and time-varying channels, the latter based on the COST 207 GSM propagation model.

The Use of Artificial Neural Network for Prediction of Dissolution Kinetics

PubMed Central

Elçiçek, H.; Akdoğan, E.; Karagöz, S.

2014-01-01

Colemanite is a preferred boron mineral in industry, such as boric acid production, fabrication of heat resistant glass, and cleaning agents. Dissolution of the mineral is one of the most important processes for these industries. In this study, dissolution of colemanite was examined in water saturated with carbon dioxide solutions. Also, prediction of dissolution rate was determined using artificial neural networks (ANNs) which are based on the multilayered perceptron. Reaction temperature, total pressure, stirring speed, solid/liquid ratio, particle size, and reaction time were selected as input parameters to predict the dissolution rate. Experimental dataset was used to train multilayer perceptron (MLP) networks to allow for prediction of dissolution kinetics. Developing ANNs has provided highly accurate predictions in comparison with an obtained mathematical model used through regression method. We conclude that ANNs may be a preferred alternative approach instead of conventional statistical methods for prediction of boron minerals. PMID:25028674

Reformulated Neural Network (ReNN): a New Alternative for Data-driven Modelling in Hydrology and Water Resources Engineering

NASA Astrophysics Data System (ADS)

Razavi, S.; Tolson, B.; Burn, D.; Seglenieks, F.

2012-04-01

Reformulated Neural Network (ReNN) has been recently developed as an efficient and more effective alternative to feedforward multi-layer perceptron (MLP) neural networks [Razavi, S., and Tolson, B. A. (2011). "A new formulation for feedforward neural networks." IEEE Transactions on Neural Networks, 22(10), 1588-1598, DOI: 1510.1109/TNN.2011.2163169]. This presentation initially aims to introduce the ReNN to the water resources community and then demonstrates ReNN applications to water resources related problems. ReNN is essentially equivalent to a single-hidden-layer MLP neural network but defined on a new set of network variables which is more effective than the traditional set of network weights and biases. The main features of the new network variables are that they are geometrically interpretable and each variable has a distinct role in forming the network response. ReNN is more efficiently trained as it has a less complex error response surface. In addition to the ReNN training efficiency, the interpretability of the ReNN variables enables the users to monitor and understand the internal behaviour of the network while training. Regularization in the ReNN response can be also directly measured and controlled. This feature improves the generalization ability of the network. The appeal of the ReNN is demonstrated with two ReNN applications to water resources engineering problems. In the first application, the ReNN is used to model the rainfall-runoff relationships in multiple watersheds in the Great Lakes basin located in northeastern North America. Modelling inflows to the Great Lakes are of great importance to the management of the Great Lakes system. Due to the lack of some detailed physical data about existing control structures in many subwatersheds of this huge basin, the data-driven approach to modelling such as the ReNN are required to replace predictions from a physically-based rainfall runoff model. Unlike traditional MLPs, the ReNN does not necessarily require an independent set of data for validation as the ReNN has the capability to control and verify the network degree of regularization. As such, the ReNN can be very beneficial in this case study as the data available in this case study is limited. In the second application, ReNN is fitted on the response function of the SWAT hydrologic model to act as a fast-to-run response surface surrogate (i.e., metamodel) of the original computationally intensive SWAT model. Besides the training efficiency gains, the ReNN applications demonstrate how the ReNN interpretability could help users develop more reliable networks which perform predictably better in terms of generalization.

Smart management of sample dilution using an artificial neural network to achieve streamlined processes and saving resources: the automated nephelometric testing of serum free light chain as case study.

PubMed

Ialongo, Cristiano; Pieri, Massimo; Bernardini, Sergio

2017-02-01

Saving resources is a paramount issue for the modern laboratory, and new trainable as well as smart technologies can be used to allow the automated instrumentation to manage samples more efficiently in order to achieve streamlined processes. In this regard the serum free light chain (sFLC) testing represents an interesting challenge, as it usually causes using a number of assays before achieving an acceptable result within the analytical range. An artificial neural network based on the multi-layer perceptron (MLP-ANN) was used to infer the starting dilution status of sFLC samples based on the information available through the laboratory information system (LIS). After the learning phase, the MLP-ANN simulation was applied to the nephelometric testing routinely performed in our laboratory on a BN ProSpec® System analyzer (Siemens Helathcare) using the N Latex FLC kit. The MLP-ANN reduced the serum kappa free light chain (κ-FLC) and serum lambda free light chain (λ-FLC) wasted tests by 69.4% and 70.8% with respect to the naïve stepwise dilution scheme used by the automated analyzer, and by 64.9% and 66.9% compared to a "rational" dilution scheme based on a 4-step dilution. Although it was restricted to follow-up samples, the MLP-ANN showed good predictive performance, which alongside the possibility to implement it in any automated system, made it a suitable solution for achieving streamlined laboratory processes and saving resources.

Neuro-genetic system for optimization of GMI samples sensitivity.

PubMed

Pitta Botelho, A C O; Vellasco, M M B R; Hall Barbosa, C R; Costa Silva, E

2016-03-01

Magnetic sensors are largely used in several engineering areas. Among them, magnetic sensors based on the Giant Magnetoimpedance (GMI) effect are a new family of magnetic sensing devices that have a huge potential for applications involving measurements of ultra-weak magnetic fields. The sensitivity of magnetometers is directly associated with the sensitivity of their sensing elements. The GMI effect is characterized by a large variation of the impedance (magnitude and phase) of a ferromagnetic sample, when subjected to a magnetic field. Recent studies have shown that phase-based GMI magnetometers have the potential to increase the sensitivity by about 100 times. The sensitivity of GMI samples depends on several parameters, such as sample length, external magnetic field, DC level and frequency of the excitation current. However, this dependency is yet to be sufficiently well-modeled in quantitative terms. So, the search for the set of parameters that optimizes the samples sensitivity is usually empirical and very time consuming. This paper deals with this problem by proposing a new neuro-genetic system aimed at maximizing the impedance phase sensitivity of GMI samples. A Multi-Layer Perceptron (MLP) Neural Network is used to model the impedance phase and a Genetic Algorithm uses the information provided by the neural network to determine which set of parameters maximizes the impedance phase sensitivity. The results obtained with a data set composed of four different GMI sample lengths demonstrate that the neuro-genetic system is able to correctly and automatically determine the set of conditioning parameters responsible for maximizing their phase sensitivities. Copyright © 2015 Elsevier Ltd. All rights reserved.

Suspect screening of large numbers of emerging contaminants in environmental waters using artificial neural networks for chromatographic retention time prediction and high resolution mass spectrometry data analysis.

PubMed

Bade, Richard; Bijlsma, Lubertus; Miller, Thomas H; Barron, Leon P; Sancho, Juan Vicente; Hernández, Felix

2015-12-15

The recent development of broad-scope high resolution mass spectrometry (HRMS) screening methods has resulted in a much improved capability for new compound identification in environmental samples. However, positive identifications at the ng/L concentration level rely on analytical reference standards for chromatographic retention time (tR) and mass spectral comparisons. Chromatographic tR prediction can play a role in increasing confidence in suspect screening efforts for new compounds in the environment, especially when standards are not available, but reliable methods are lacking. The current work focuses on the development of artificial neural networks (ANNs) for tR prediction in gradient reversed-phase liquid chromatography and applied along with HRMS data to suspect screening of wastewater and environmental surface water samples. Based on a compound tR dataset of >500 compounds, an optimized 4-layer back-propagation multi-layer perceptron model enabled predictions for 85% of all compounds to within 2min of their measured tR for training (n=344) and verification (n=100) datasets. To evaluate the ANN ability for generalization to new data, the model was further tested using 100 randomly selected compounds and revealed 95% prediction accuracy within the 2-minute elution interval. Given the increasing concern on the presence of drug metabolites and other transformation products (TPs) in the aquatic environment, the model was applied along with HRMS data for preliminary identification of pharmaceutically-related compounds in real samples. Examples of compounds where reference standards were subsequently acquired and later confirmed are also presented. To our knowledge, this work presents for the first time, the successful application of an accurate retention time predictor and HRMS data-mining using the largest number of compounds to preliminarily identify new or emerging contaminants in wastewater and surface waters. Copyright © 2015 Elsevier B.V. All rights reserved.

Interdependent Multi-Layer Networks: Modeling and Survivability Analysis with Applications to Space-Based Networks

PubMed Central

Castet, Jean-Francois; Saleh, Joseph H.

2013-01-01

This article develops a novel approach and algorithmic tools for the modeling and survivability analysis of networks with heterogeneous nodes, and examines their application to space-based networks. Space-based networks (SBNs) allow the sharing of spacecraft on-orbit resources, such as data storage, processing, and downlink. Each spacecraft in the network can have different subsystem composition and functionality, thus resulting in node heterogeneity. Most traditional survivability analyses of networks assume node homogeneity and as a result, are not suited for the analysis of SBNs. This work proposes that heterogeneous networks can be modeled as interdependent multi-layer networks, which enables their survivability analysis. The multi-layer aspect captures the breakdown of the network according to common functionalities across the different nodes, and it allows the emergence of homogeneous sub-networks, while the interdependency aspect constrains the network to capture the physical characteristics of each node. Definitions of primitives of failure propagation are devised. Formal characterization of interdependent multi-layer networks, as well as algorithmic tools for the analysis of failure propagation across the network are developed and illustrated with space applications. The SBN applications considered consist of several networked spacecraft that can tap into each other's Command and Data Handling subsystem, in case of failure of its own, including the Telemetry, Tracking and Command, the Control Processor, and the Data Handling sub-subsystems. Various design insights are derived and discussed, and the capability to perform trade-space analysis with the proposed approach for various network characteristics is indicated. The select results here shown quantify the incremental survivability gains (with respect to a particular class of threats) of the SBN over the traditional monolith spacecraft. Failure of the connectivity between nodes is also examined, and the results highlight the importance of the reliability of the wireless links between spacecraft (nodes) to enable any survivability improvements for space-based networks. PMID:23599835

Interdependent multi-layer networks: modeling and survivability analysis with applications to space-based networks.

PubMed

Castet, Jean-Francois; Saleh, Joseph H

2013-01-01

This article develops a novel approach and algorithmic tools for the modeling and survivability analysis of networks with heterogeneous nodes, and examines their application to space-based networks. Space-based networks (SBNs) allow the sharing of spacecraft on-orbit resources, such as data storage, processing, and downlink. Each spacecraft in the network can have different subsystem composition and functionality, thus resulting in node heterogeneity. Most traditional survivability analyses of networks assume node homogeneity and as a result, are not suited for the analysis of SBNs. This work proposes that heterogeneous networks can be modeled as interdependent multi-layer networks, which enables their survivability analysis. The multi-layer aspect captures the breakdown of the network according to common functionalities across the different nodes, and it allows the emergence of homogeneous sub-networks, while the interdependency aspect constrains the network to capture the physical characteristics of each node. Definitions of primitives of failure propagation are devised. Formal characterization of interdependent multi-layer networks, as well as algorithmic tools for the analysis of failure propagation across the network are developed and illustrated with space applications. The SBN applications considered consist of several networked spacecraft that can tap into each other's Command and Data Handling subsystem, in case of failure of its own, including the Telemetry, Tracking and Command, the Control Processor, and the Data Handling sub-subsystems. Various design insights are derived and discussed, and the capability to perform trade-space analysis with the proposed approach for various network characteristics is indicated. The select results here shown quantify the incremental survivability gains (with respect to a particular class of threats) of the SBN over the traditional monolith spacecraft. Failure of the connectivity between nodes is also examined, and the results highlight the importance of the reliability of the wireless links between spacecraft (nodes) to enable any survivability improvements for space-based networks.

Optimized planning methodologies of ASON implementation

NASA Astrophysics Data System (ADS)

Zhou, Michael M.; Tamil, Lakshman S.

2005-02-01

Advanced network planning concerns effective network-resource allocation for dynamic and open business environment. Planning methodologies of ASON implementation based on qualitative analysis and mathematical modeling are presented in this paper. The methodology includes method of rationalizing technology and architecture, building network and nodal models, and developing dynamic programming for multi-period deployment. The multi-layered nodal architecture proposed here can accommodate various nodal configurations for a multi-plane optical network and the network modeling presented here computes the required network elements for optimizing resource allocation.

Predicting multicellular function through multi-layer tissue networks

PubMed Central

Zitnik, Marinka; Leskovec, Jure

2017-01-01

Abstract Motivation: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine. Results: Here, we present OhmNet, a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, where each layer represents molecular interactions in a different human tissue. OhmNet then automatically learns a mapping of proteins, represented as nodes, to a neural embedding-based low-dimensional space of features. OhmNet encourages sharing of similar features among proteins with similar network neighborhoods and among proteins activated in similar tissues. The algorithm generalizes prior work, which generally ignores relationships between tissues, by modeling tissue organization with a rich multiscale tissue hierarchy. We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues. In 48 tissues with known tissue-specific cellular functions, OhmNet provides more accurate predictions of cellular function than alternative approaches, and also generates more accurate hypotheses about tissue-specific protein actions. We show that taking into account the tissue hierarchy leads to improved predictive power. Remarkably, we also demonstrate that it is possible to leverage the tissue hierarchy in order to effectively transfer cellular functions to a functionally uncharacterized tissue. Overall, OhmNet moves from flat networks to multiscale models able to predict a range of phenotypes spanning cellular subsystems. Availability and implementation: Source code and datasets are available at http://snap.stanford.edu/ohmnet. Contact: jure@cs.stanford.edu PMID:28881986

The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Behrang, M.A.; Assareh, E.; Ghanbarzadeh, A.

2010-08-15

The main objective of present study is to predict daily global solar radiation (GSR) on a horizontal surface, based on meteorological variables, using different artificial neural network (ANN) techniques. Daily mean air temperature, relative humidity, sunshine hours, evaporation, and wind speed values between 2002 and 2006 for Dezful city in Iran (32 16'N, 48 25'E), are used in this study. In order to consider the effect of each meteorological variable on daily GSR prediction, six following combinations of input variables are considered: (I)Day of the year, daily mean air temperature and relative humidity as inputs and daily GSR as output.more » (II)Day of the year, daily mean air temperature and sunshine hours as inputs and daily GSR as output. (III)Day of the year, daily mean air temperature, relative humidity and sunshine hours as inputs and daily GSR as output. (IV)Day of the year, daily mean air temperature, relative humidity, sunshine hours and evaporation as inputs and daily GSR as output. (V)Day of the year, daily mean air temperature, relative humidity, sunshine hours and wind speed as inputs and daily GSR as output. (VI)Day of the year, daily mean air temperature, relative humidity, sunshine hours, evaporation and wind speed as inputs and daily GSR as output. Multi-layer perceptron (MLP) and radial basis function (RBF) neural networks are applied for daily GSR modeling based on six proposed combinations. The measured data between 2002 and 2005 are used to train the neural networks while the data for 214 days from 2006 are used as testing data. The comparison of obtained results from ANNs and different conventional GSR prediction (CGSRP) models shows very good improvements (i.e. the predicted values of best ANN model (MLP-V) has a mean absolute percentage error (MAPE) about 5.21% versus 10.02% for best CGSRP model (CGSRP 5)). (author)« less

Multi-layer electrode with nano-Li4Ti5O12 aggregates sandwiched between carbon nanotube and graphene networks for high power Li-ion batteries.

PubMed

Choi, Jin-Hoon; Ryu, Won-Hee; Park, Kyusung; Jo, Jeong-Dai; Jo, Sung-Moo; Lim, Dae-Soon; Kim, Il-Doo

2014-12-05

Self-aggregated Li4Ti5O12 particles sandwiched between graphene nanosheets (GNSs) and single-walled carbon nanotubes (SWCNTs) network are reported as new hybrid electrodes for high power Li-ion batteries. The multi-layer electrodes are fabricated by sequential process comprising air-spray coating of GNSs layer and the following electrostatic spray (E-spray) coating of well-dispersed colloidal Li4Ti5O12 nanoparticles, and subsequent air-spray coating of SWCNTs layer once again. In multi-stacked electrodes of GNSs/nanoporous Li4Ti5O12 aggregates/SWCNTs networks, GNSs and SWCNTs serve as conducting bridges, effectively interweaving the nanoporous Li4Ti5O12 aggregates, and help achieve superior rate capability as well as improved mechanical stability of the composite electrode by holding Li4Ti5O12 tightly without a binder. The multi-stacked electrodes deliver a specific capacity that maintains an impressively high capacity of 100 mA h g(-1) at a high rate of 100C even after 1000 cycles.

Out-of-equilibrium dynamical mean-field equations for the perceptron model

NASA Astrophysics Data System (ADS)

Agoritsas, Elisabeth; Biroli, Giulio; Urbani, Pierfrancesco; Zamponi, Francesco

2018-02-01

Perceptrons are the building blocks of many theoretical approaches to a wide range of complex systems, ranging from neural networks and deep learning machines, to constraint satisfaction problems, glasses and ecosystems. Despite their applicability and importance, a detailed study of their Langevin dynamics has never been performed yet. Here we derive the mean-field dynamical equations that describe the continuous random perceptron in the thermodynamic limit, in a very general setting with arbitrary noise and friction kernels, not necessarily related by equilibrium relations. We derive the equations in two ways: via a dynamical cavity method, and via a path-integral approach in its supersymmetric formulation. The end point of both approaches is the reduction of the dynamics of the system to an effective stochastic process for a representative dynamical variable. Because the perceptron is formally very close to a system of interacting particles in a high dimensional space, the methods we develop here can be transferred to the study of liquid and glasses in high dimensions. Potentially interesting applications are thus the study of the glass transition in active matter, the study of the dynamics around the jamming transition, and the calculation of rheological properties in driven systems.

Multilayer motif analysis of brain networks

NASA Astrophysics Data System (ADS)

Battiston, Federico; Nicosia, Vincenzo; Chavez, Mario; Latora, Vito

2017-04-01

In the last decade, network science has shed new light both on the structural (anatomical) and on the functional (correlations in the activity) connectivity among the different areas of the human brain. The analysis of brain networks has made possible to detect the central areas of a neural system and to identify its building blocks by looking at overabundant small subgraphs, known as motifs. However, network analysis of the brain has so far mainly focused on anatomical and functional networks as separate entities. The recently developed mathematical framework of multi-layer networks allows us to perform an analysis of the human brain where the structural and functional layers are considered together. In this work, we describe how to classify the subgraphs of a multiplex network, and we extend the motif analysis to networks with an arbitrary number of layers. We then extract multi-layer motifs in brain networks of healthy subjects by considering networks with two layers, anatomical and functional, respectively, obtained from diffusion and functional magnetic resonance imaging. Results indicate that subgraphs in which the presence of a physical connection between brain areas (links at the structural layer) coexists with a non-trivial positive correlation in their activities are statistically overabundant. Finally, we investigate the existence of a reinforcement mechanism between the two layers by looking at how the probability to find a link in one layer depends on the intensity of the connection in the other one. Showing that functional connectivity is non-trivially constrained by the underlying anatomical network, our work contributes to a better understanding of the interplay between the structure and function in the human brain.

Modelling hourly dissolved oxygen concentration (DO) using dynamic evolving neural-fuzzy inference system (DENFIS)-based approach: case study of Klamath River at Miller Island Boat Ramp, OR, USA.

PubMed

Heddam, Salim

2014-01-01

In this study, we present application of an artificial intelligence (AI) technique model called dynamic evolving neural-fuzzy inference system (DENFIS) based on an evolving clustering method (ECM), for modelling dissolved oxygen concentration in a river. To demonstrate the forecasting capability of DENFIS, a one year period from 1 January 2009 to 30 December 2009, of hourly experimental water quality data collected by the United States Geological Survey (USGS Station No: 420853121505500) station at Klamath River at Miller Island Boat Ramp, OR, USA, were used for model development. Two DENFIS-based models are presented and compared. The two DENFIS systems are: (1) offline-based system named DENFIS-OF, and (2) online-based system, named DENFIS-ON. The input variables used for the two models are water pH, temperature, specific conductance, and sensor depth. The performances of the models are evaluated using root mean square errors (RMSE), mean absolute error (MAE), Willmott index of agreement (d) and correlation coefficient (CC) statistics. The lowest root mean square error and highest correlation coefficient values were obtained with the DENFIS-ON method. The results obtained with DENFIS models are compared with linear (multiple linear regression, MLR) and nonlinear (multi-layer perceptron neural networks, MLPNN) methods. This study demonstrates that DENFIS-ON investigated herein outperforms all the proposed techniques for DO modelling.

Dynamic time warping and machine learning for signal quality assessment of pulsatile signals.

PubMed

Li, Q; Clifford, G D

2012-09-01

In this work, we describe a beat-by-beat method for assessing the clinical utility of pulsatile waveforms, primarily recorded from cardiovascular blood volume or pressure changes, concentrating on the photoplethysmogram (PPG). Physiological blood flow is nonstationary, with pulses changing in height, width and morphology due to changes in heart rate, cardiac output, sensor type and hardware or software pre-processing requirements. Moreover, considerable inter-individual and sensor-location variability exists. Simple template matching methods are therefore inappropriate, and a patient-specific adaptive initialization is therefore required. We introduce dynamic time warping to stretch each beat to match a running template and combine it with several other features related to signal quality, including correlation and the percentage of the beat that appeared to be clipped. The features were then presented to a multi-layer perceptron neural network to learn the relationships between the parameters in the presence of good- and bad-quality pulses. An expert-labeled database of 1055 segments of PPG, each 6 s long, recorded from 104 separate critical care admissions during both normal and verified arrhythmic events, was used to train and test our algorithms. An accuracy of 97.5% on the training set and 95.2% on test set was found. The algorithm could be deployed as a stand-alone signal quality assessment algorithm for vetting the clinical utility of PPG traces or any similar quasi-periodic signal.

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

NASA Astrophysics Data System (ADS)

Cornejo-Bueno, L.; Casanova-Mateo, C.; Sanz-Justo, J.; Cerro-Prada, E.; Salcedo-Sanz, S.

2017-11-01

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is {>}1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ({<}500 m). However, we show improved results of all the methods when data from a neighbouring meteorological tower are included, and also with a pre-processing scheme using a wavelet transform. Also presented are results of the algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs.

PubMed

Abbas, Adel Taha; Pimenov, Danil Yurievich; Erdakov, Ivan Nikolaevich; Taha, Mohamed Adel; Soliman, Mahmoud Sayed; El Rayes, Magdy Mostafa

2018-05-16

Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth⁻Pareto optimization of an artificial neural network (ANN) is presented in this paper for surface roughness ( Ra ) prediction of one component in computer numerical control (CNC) turning over minimal machining time ( T m ) and at prime machining costs ( C ). An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP), to predict Ra , T m , and C , in relation to cutting speed, v c , depth of cut, a p , and feed per revolution, f r . For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values v c , a p , and f r . The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, T m = 0.358 min/cm³, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed v c = 250 m/min, cutting depth a p = 1.0 mm, and feed per revolution f r = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness.

Fusion of ECG and ABP signals based on wavelet transform for cardiac arrhythmias classification.

PubMed

Arvanaghi, Roghayyeh; Daneshvar, Sabalan; Seyedarabi, Hadi; Goshvarpour, Atefeh

2017-11-01

Each of Electrocardiogram (ECG) and Atrial Blood Pressure (ABP) signals contain information of cardiac status. This information can be used for diagnosis and monitoring of diseases. The majority of previously proposed methods rely only on ECG signal to classify heart rhythms. In this paper, ECG and ABP were used to classify five different types of heart rhythms. To this end, two mentioned signals (ECG and ABP) have been fused. These physiological signals have been used from MINIC physioNet database. ECG and ABP signals have been fused together on the basis of the proposed Discrete Wavelet Transformation fusion technique. Then, some frequency features were extracted from the fused signal. To classify the different types of cardiac arrhythmias, these features were given to a multi-layer perceptron neural network. In this study, the best results for the proposed fusion algorithm were obtained. In this case, the accuracy rates of 96.6%, 96.9%, 95.6% and 93.9% were achieved for two, three, four and five classes, respectively. However, the maximum classification rate of 89% was obtained for two classes on the basis of ECG features. It has been found that the higher accuracy rates were acquired by using the proposed fusion technique. The results confirmed the importance of fusing features from different physiological signals to gain more accurate assessments. Copyright © 2017 Elsevier B.V. All rights reserved.

Three learning phases for radial-basis-function networks.

PubMed

Schwenker, F; Kestler, H A; Palm, G

2001-05-01

In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase learning schemes. Two-phase RBF learning is a very common learning scheme. The two layers of an RBF network are learnt separately; first the RBF layer is trained, including the adaptation of centers and scaling parameters, and then the weights of the output layer are adapted. RBF centers may be trained by clustering, vector quantization and classification tree algorithms, and the output layer by supervised learning (through gradient descent or pseudo inverse solution). Results from numerical experiments of RBF classifiers trained by two-phase learning are presented in three completely different pattern recognition applications: (a) the classification of 3D visual objects; (b) the recognition hand-written digits (2D objects); and (c) the categorization of high-resolution electrocardiograms given as a time series (ID objects) and as a set of features extracted from these time series. In these applications, it can be observed that the performance of RBF classifiers trained with two-phase learning can be improved through a third backpropagation-like training phase of the RBF network, adapting the whole set of parameters (RBF centers, scaling parameters, and output layer weights) simultaneously. This, we call three-phase learning in RBF networks. A practical advantage of two- and three-phase learning in RBF networks is the possibility to use unlabeled training data for the first training phase. Support vector (SV) learning in RBF networks is a different learning approach. SV learning can be considered, in this context of learning, as a special type of one-phase learning, where only the output layer weights of the RBF network are calculated, and the RBF centers are restricted to be a subset of the training data. Numerical experiments with several classifier schemes including k-nearest-neighbor, learning vector quantization and RBF classifiers trained through two-phase, three-phase and support vector learning are given. The performance of the RBF classifiers trained through SV learning and three-phase learning are superior to the results of two-phase learning, but SV learning often leads to complex network structures, since the number of support vectors is not a small fraction of the total number of data points.

Classification of Magneto-Optic Images using Neural Networks

NASA Technical Reports Server (NTRS)

Nath, Shridhar; Wincheski, Buzz; Fulton, Jim; Namkung, Min

1994-01-01

A real time imaging system with a neural network classifier has been incorporated on a Macintosh computer in conjunction with an MOI system. This system images rivets on aircraft aluminium structures using eddy currents and magnetic imaging. Moment invariant functions from the image of a rivet is used to train a multilayer perceptron neural network to classify the rivets as good or bad (rivets with cracks).

VizieR Online Data Catalog: SDSS-DR9 photometric redshifts (Brescia+, 2014)

NASA Astrophysics Data System (ADS)

Brescia, M.; Cavuoti, S.; Longo, G.; de Stefano, V.

2014-07-01

We present an application of a machine learning method to the estimation of photometric redshifts for the galaxies in the SDSS Data Release 9 (SDSS-DR9). Photometric redshifts for more than 143 million galaxies were produced. The MLPQNA (Multi Layer Perceptron with Quasi Newton Algorithm) model provided within the framework of the DAMEWARE (DAta Mining and Exploration Web Application REsource) is an interpolative method derived from machine learning models. The obtained redshifts have an overall uncertainty of σ=0.023 with a very small average bias of about 3x10-5 and a fraction of catastrophic outliers of about 5%. After removal of the catastrophic outliers, the uncertainty is about σ=0.017. The catalogue files report in their name the range of DEC degrees related to the included objects. (60 data files).

Probing many-body localization with neural networks

NASA Astrophysics Data System (ADS)

Schindler, Frank; Regnault, Nicolas; Neupert, Titus

2017-06-01

We show that a simple artificial neural network trained on entanglement spectra of individual states of a many-body quantum system can be used to determine the transition between a many-body localized and a thermalizing regime. Specifically, we study the Heisenberg spin-1/2 chain in a random external field. We employ a multilayer perceptron with a single hidden layer, which is trained on labeled entanglement spectra pertaining to the fully localized and fully thermal regimes. We then apply this network to classify spectra belonging to states in the transition region. For training, we use a cost function that contains, in addition to the usual error and regularization parts, a term that favors a confident classification of the transition region states. The resulting phase diagram is in good agreement with the one obtained by more conventional methods and can be computed for small systems. In particular, the neural network outperforms conventional methods in classifying individual eigenstates pertaining to a single disorder realization. It allows us to map out the structure of these eigenstates across the transition with spatial resolution. Furthermore, we analyze the network operation using the dreaming technique to show that the neural network correctly learns by itself the power-law structure of the entanglement spectra in the many-body localized regime.

Optimal source coding, removable noise elimination, and natural coordinate system construction for general vector sources using replicator neural networks

NASA Astrophysics Data System (ADS)

Hecht-Nielsen, Robert

1997-04-01

A new universal one-chart smooth manifold model for vector information sources is introduced. Natural coordinates (a particular type of chart) for such data manifolds are then defined. Uniformly quantized natural coordinates form an optimal vector quantization code for a general vector source. Replicator neural networks (a specialized type of multilayer perceptron with three hidden layers) are the introduced. As properly configured examples of replicator networks approach minimum mean squared error (e.g., via training and architecture adjustment using randomly chosen vectors from the source), these networks automatically develop a mapping which, in the limit, produces natural coordinates for arbitrary source vectors. The new concept of removable noise (a noise model applicable to a wide variety of real-world noise processes) is then discussed. Replicator neural networks, when configured to approach minimum mean squared reconstruction error (e.g., via training and architecture adjustment on randomly chosen examples from a vector source, each with randomly chosen additive removable noise contamination), in the limit eliminate removable noise and produce natural coordinates for the data vector portions of the noise-corrupted source vectors. Consideration regarding selection of the dimension of a data manifold source model and the training/configuration of replicator neural networks are discussed.

Cross Layered Multi-Meshed Tree Scheme for Cognitive Networks

DTIC Science & Technology

2011-06-01

Meshed Tree Routing protocol wireless ad hoc networks ,” Second IEEE International Workshop on Enabling Technologies and Standards for Wireless Mesh ...and Sensor Networks , 2004 43. Chen G.; Stojmenovic I., “Clustering and routing in mobile wireless networks ,” Technical Report TR-99-05, SITE, June...Cross-layer optimization, intra-cluster routing , packet forwarding, inter-cluster routing , mesh network communications,

BELM: Bayesian extreme learning machine.

PubMed

Soria-Olivas, Emilio; Gómez-Sanchis, Juan; Martín, José D; Vila-Francés, Joan; Martínez, Marcelino; Magdalena, José R; Serrano, Antonio J

2011-03-01

The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities. Bayesian ELM is benchmarked against classical ELM in several artificial and real datasets that are widely used for the evaluation of machine learning algorithms. Achieved results show that the proposed approach produces a competitive accuracy with some additional advantages, namely, automatic production of CIs, reduction of probability of model overfitting, and use of a priori knowledge.

Artificial neural network techniques to improve the ability of optical coherence tomography to detect optic neuritis.

PubMed

Garcia-Martin, Elena; Herrero, Raquel; Bambo, Maria P; Ara, Jose R; Martin, Jesus; Polo, Vicente; Larrosa, Jose M; Garcia-Feijoo, Julian; Pablo, Luis E

2015-01-01

To analyze the ability of Spectralis optical coherence tomography (OCT) to detect multiple sclerosis (MS) and to distinguish MS eyes with antecedent optic neuritis (ON). To analyze the capability of artificial neural network (ANN) techniques to improve the diagnostic precision. MS patients and controls were enrolled (n = 217). OCT was used to determine the 768 retinal nerve fiber layer thicknesses. Sensitivity and specificity were evaluated to test the ability of OCT to discriminate between MS and healthy eyes, and between MS with and without antecedent ON using ANN. Using ANN technique multilayer perceptrons, OCT could detect MS with a sensitivity of 89.3%, a specificity of 87.6%, and a diagnostic precision of 88.5%. Compared with the OCT-provided parameters, the ANN had a better sensitivity-specificity balance. ANN technique improves the capability of Spectralis OCT to detect MS disease and to distinguish MS eyes with or without antecedent ON.

[Rapid Identification of Epicarpium Citri Grandis via Infrared Spectroscopy and Fluorescence Spectrum Imaging Technology Combined with Neural Network].

PubMed

Pan, Sha-sha; Huang, Fu-rong; Xiao, Chi; Xian, Rui-yi; Ma, Zhi-guo

2015-10-01

To explore rapid reliable methods for detection of Epicarpium citri grandis (ECG), the experiment using Fourier Transform Attenuated Total Reflection Infrared Spectroscopy (FTIR/ATR) and Fluorescence Spectrum Imaging Technology combined with Multilayer Perceptron (MLP) Neural Network pattern recognition, for the identification of ECG, and the two methods are compared. Infrared spectra and fluorescence spectral images of 118 samples, 81 ECG and 37 other kinds of ECG, are collected. According to the differences in tspectrum, the spectra data in the 550-1 800 cm(-1) wavenumber range and 400-720 nm wavelength are regarded as the study objects of discriminant analysis. Then principal component analysis (PCA) is applied to reduce the dimension of spectroscopic data of ECG and MLP Neural Network is used in combination to classify them. During the experiment were compared the effects of different methods of data preprocessing on the model: multiplicative scatter correction (MSC), standard normal variable correction (SNV), first-order derivative(FD), second-order derivative(SD) and Savitzky-Golay (SG). The results showed that: after the infrared spectra data via the Savitzky-Golay (SG) pretreatment through the MLP Neural Network with the hidden layer function as sigmoid, we can get the best discrimination of ECG, the correct percent of training set and testing set are both 100%. Using fluorescence spectral imaging technology, corrected by the multiple scattering (MSC) results in the pretreatment is the most ideal. After data preprocessing, the three layers of the MLP Neural Network of the hidden layer function as sigmoid function can get 100% correct percent of training set and 96.7% correct percent of testing set. It was shown that the FTIR/ATR and fluorescent spectral imaging technology combined with MLP Neural Network can be used for the identification study of ECG and has the advantages of rapid, reliable effect.

Neural Networks: An Overview

DTIC Science & Technology

1991-05-01

Hall, 1967. 6. Rosenblatt, F., Principles of Neurodynamics , Spartan Books, 1962. 7. Minsky, M. and Papert, S., Perceptrons, MIT Press, Revised Edition...sentations by Error Propagation, Rumelhart and McClelland (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Vol

Cloud-based application for rice moisture content measurement using image processing technique and perceptron neural network

NASA Astrophysics Data System (ADS)

Cruz, Febus Reidj G.; Padilla, Dionis A.; Hortinela, Carlos C.; Bucog, Krissel C.; Sarto, Mildred C.; Sia, Nirlu Sebastian A.; Chung, Wen-Yaw

2017-02-01

This study is about the determination of moisture content of milled rice using image processing technique and perceptron neural network algorithm. The algorithm involves several inputs that produces an output which is the moisture content of the milled rice. Several types of milled rice are used in this study, namely: Jasmine, Kokuyu, 5-Star, Ifugao, Malagkit, and NFA rice. The captured images are processed using MATLAB R2013a software. There is a USB dongle connected to the router which provided internet connection for online web access. The GizDuino IOT-644 is used for handling the temperature and humidity sensor, and for sending and receiving of data from computer to the cloud storage. The result is compared to the actual moisture content range using a moisture tester for milled rice. Based on results, this study provided accurate data in determining the moisture content of the milled rice.

Implementation of a smartphone as a wireless gyroscope platform for quantifying reduced arm swing in hemiplegie gait with machine learning classification by multilayer perceptron neural network.

PubMed

LeMoyne, Robert; Mastroianni, Timothy

2016-08-01

Natural gait consists of synchronous and rhythmic patterns for both the lower and upper limb. People with hemiplegia can experience reduced arm swing, which can negatively impact the quality of gait. Wearable and wireless sensors, such as through a smartphone, have demonstrated the ability to quantify various features of gait. With a software application the smartphone (iPhone) can function as a wireless gyroscope platform capable of conveying a gyroscope signal recording as an email attachment by wireless connectivity to the Internet. The gyroscope signal recordings of the affected hemiplegic arm with reduced arm swing arm and the unaffected arm are post-processed into a feature set for machine learning. Using a multilayer perceptron neural network a considerable degree of classification accuracy is attained to distinguish between the affected hemiplegic arm with reduced arm swing arm and the unaffected arm.

Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors.

PubMed

Godino-Llorente, J I; Gómez-Vilda, P

2004-02-01

It is well known that vocal and voice diseases do not necessarily cause perceptible changes in the acoustic voice signal. Acoustic analysis is a useful tool to diagnose voice diseases being a complementary technique to other methods based on direct observation of the vocal folds by laryngoscopy. Through the present paper two neural-network based classification approaches applied to the automatic detection of voice disorders will be studied. Structures studied are multilayer perceptron and learning vector quantization fed using short-term vectors calculated accordingly to the well-known Mel Frequency Coefficient cepstral parameterization. The paper shows that these architectures allow the detection of voice disorders--including glottic cancer--under highly reliable conditions. Within this context, the Learning Vector quantization methodology demonstrated to be more reliable than the multilayer perceptron architecture yielding 96% frame accuracy under similar working conditions.

Long-range forecast of all India summer monsoon rainfall using adaptive neuro-fuzzy inference system: skill comparison with CFSv2 model simulation and real-time forecast for the year 2015

NASA Astrophysics Data System (ADS)

Chaudhuri, S.; Das, D.; Goswami, S.; Das, S. K.

2016-11-01

All India summer monsoon rainfall (AISMR) characteristics play a vital role for the policy planning and national economy of the country. In view of the significant impact of monsoon system on regional as well as global climate systems, accurate prediction of summer monsoon rainfall has become a challenge. The objective of this study is to develop an adaptive neuro-fuzzy inference system (ANFIS) for long range forecast of AISMR. The NCEP/NCAR reanalysis data of temperature, zonal and meridional wind at different pressure levels have been taken to construct the input matrix of ANFIS. The membership of the input parameters for AISMR as high, medium or low is estimated with trapezoidal membership function. The fuzzified standardized input parameters and the de-fuzzified target output are trained with artificial neural network models. The forecast of AISMR with ANFIS is compared with non-hybrid multi-layer perceptron model (MLP), radial basis functions network (RBFN) and multiple linear regression (MLR) models. The forecast error analyses of the models reveal that ANFIS provides the best forecast of AISMR with minimum prediction error of 0.076, whereas the errors with MLP, RBFN and MLR models are 0.22, 0.18 and 0.73 respectively. During validation with observations, ANFIS shows its potency over the said comparative models. Performance of the ANFIS model is verified through different statistical skill scores, which also confirms the aptitude of ANFIS in forecasting AISMR. The forecast skill of ANFIS is also observed to be better than Climate Forecast System version 2. The real-time forecast with ANFIS shows possibility of deficit (65-75 cm) AISMR in the year 2015.

Discrimination of acidic and alkaline enzyme using Chou's pseudo amino acid composition in conjunction with probabilistic neural network model.

PubMed

Khan, Zaheer Ullah; Hayat, Maqsood; Khan, Muazzam Ali

2015-01-21

Enzyme catalysis is one of the most essential and striking processes among of all the complex processes that have evolved in living organisms. Enzymes are biological catalysts, which play a significant role in industrial applications as well as in medical areas, due to profound specificity, selectivity and catalytic efficiency. Refining catalytic efficiency of enzymes has become the most challenging job of enzyme engineering, into acidic and alkaline. Discrimination of acidic and alkaline enzymes through experimental approaches is difficult, sometimes impossible due to lack of established structures. Therefore, it is highly desirable to develop a computational model for discriminating acidic and alkaline enzymes from primary sequences. In this study, we have developed a robust, accurate and high throughput computational model using two discrete sample representation methods Pseudo amino acid composition (PseAAC) and split amino acid composition. Various classification algorithms including probabilistic neural network (PNN), K-nearest neighbor, decision tree, multi-layer perceptron and support vector machine are applied to predict acidic and alkaline with high accuracy. 10-fold cross validation test and several statistical measures namely, accuracy, F-measure, and area under ROC are used to evaluate the performance of the proposed model. The performance of the model is examined using two benchmark datasets to demonstrate the effectiveness of the model. The empirical results show that the performance of PNN in conjunction with PseAAC is quite promising compared to existing approaches in the literature so for. It has achieved 96.3% accuracy on dataset1 and 99.2% on dataset2. It is ascertained that the proposed model might be useful for basic research and drug related application areas. Copyright © 2014 Elsevier Ltd. All rights reserved.

Ground-based telescope pointing and tracking optimization using a neural controller.

PubMed

Mancini, D; Brescia, M; Schipani, P

2003-01-01

Neural network models (NN) have emerged as important components for applications of adaptive control theories. Their basic generalization capability, based on acquired knowledge, together with execution rapidity and correlation ability between input stimula, are basic attributes to consider NN as an extremely powerful tool for on-line control of complex systems. By a control system point of view, not only accuracy and speed, but also, in some cases, a high level of adaptation capability is required in order to match all working phases of the whole system during its lifetime. This is particularly remarkable for a new generation ground-based telescope control system. Infact, strong changes in terms of system speed and instantaneous position error tolerance are necessary, especially in case of trajectory disturb induced by wind shake. The classical control scheme adopted in such a system is based on the proportional integral (PI) filter, already applied and implemented on a large amount of new generation telescopes, considered as a standard in this technological environment. In this paper we introduce the concept of a new approach, the neural variable structure proportional integral, (NVSPI), related to the implementation of a standard multi layer perceptron network in new generation ground-based Alt-Az telescope control systems. Its main purpose is to improve adaptive capability of the Variable structure proportional integral model, an already innovative control scheme recently introduced by authors [Proc SPIE (1997)], based on a modified version of classical PI control model, in terms of flexibility and accuracy of the dynamic response range also in presence of wind noise effects. The realization of a powerful well tested and validated telescope model simulation system allowed the possibility to directly compare performances of the two control schemes on simulated tracking trajectories, revealing extremely encouraging results in terms of NVSPI control robustness and reliability.

A multi-scale hybrid neural network retrieval model for dust storm detection, a study in Asia

NASA Astrophysics Data System (ADS)

Wong, Man Sing; Xiao, Fei; Nichol, Janet; Fung, Jimmy; Kim, Jhoon; Campbell, James; Chan, P. W.

2015-05-01

Dust storms are known to have adverse effects on human health and significant impact on weather, air quality, hydrological cycle, and ecosystem. Atmospheric dust loading is also one of the large uncertainties in global climate modeling, due to its significant impact on the radiation budget and atmospheric stability. Observations of dust storms in humid tropical south China (e.g. Hong Kong), are challenging due to high industrial pollution from the nearby Pearl River Delta region. This study develops a method for dust storm detection by combining ground station observations (PM10 concentration, AERONET data), geostationary satellite images (MTSAT), and numerical weather and climatic forecasting products (WRF/Chem). The method is based on a hybrid neural network (NN) retrieval model for two scales: (i) a NN model for near real-time detection of dust storms at broader regional scale; (ii) a NN model for detailed dust storm mapping for Hong Kong and Taiwan. A feed-forward multilayer perceptron (MLP) NN, trained using back propagation (BP) algorithm, was developed and validated by the k-fold cross validation approach. The accuracy of the near real-time detection MLP-BP network is 96.6%, and the accuracies for the detailed MLP-BP neural network for Hong Kong and Taiwan is 74.8%. This newly automated multi-scale hybrid method can be used to give advance near real-time mapping of dust storms for environmental authorities and the public. It is also beneficial for identifying spatial locations of adverse air quality conditions, and estimates of low visibility associated with dust events for port and airport authorities.

A deep auto-encoder model for gene expression prediction.

PubMed

Xie, Rui; Wen, Jia; Quitadamo, Andrew; Cheng, Jianlin; Shi, Xinghua

2017-11-17

Gene expression is a key intermediate level that genotypes lead to a particular trait. Gene expression is affected by various factors including genotypes of genetic variants. With an aim of delineating the genetic impact on gene expression, we build a deep auto-encoder model to assess how good genetic variants will contribute to gene expression changes. This new deep learning model is a regression-based predictive model based on the MultiLayer Perceptron and Stacked Denoising Auto-encoder (MLP-SAE). The model is trained using a stacked denoising auto-encoder for feature selection and a multilayer perceptron framework for backpropagation. We further improve the model by introducing dropout to prevent overfitting and improve performance. To demonstrate the usage of this model, we apply MLP-SAE to a real genomic datasets with genotypes and gene expression profiles measured in yeast. Our results show that the MLP-SAE model with dropout outperforms other models including Lasso, Random Forests and the MLP-SAE model without dropout. Using the MLP-SAE model with dropout, we show that gene expression quantifications predicted by the model solely based on genotypes, align well with true gene expression patterns. We provide a deep auto-encoder model for predicting gene expression from SNP genotypes. This study demonstrates that deep learning is appropriate for tackling another genomic problem, i.e., building predictive models to understand genotypes' contribution to gene expression. With the emerging availability of richer genomic data, we anticipate that deep learning models play a bigger role in modeling and interpreting genomics.

Centralized Routing and Scheduling Using Multi-Channel System Single Transceiver in 802.16d

NASA Astrophysics Data System (ADS)

Al-Hemyari, A.; Noordin, N. K.; Ng, Chee Kyun; Ismail, A.; Khatun, S.

This paper proposes a cross-layer optimized strategy that reduces the effect of interferences from neighboring nodes within a mesh networks. This cross-layer design relies on the routing information in network layer and the scheduling table in medium access control (MAC) layer. A proposed routing algorithm in network layer is exploited to find the best route for all subscriber stations (SS). Also, a proposed centralized scheduling algorithm in MAC layer is exploited to assign a time slot for each possible node transmission. The cross-layer optimized strategy is using multi-channel single transceiver and single channel single transceiver systems for WiMAX mesh networks (WMNs). Each node in WMN has a transceiver that can be tuned to any available channel for eliminating the secondary interference. Among the considered parameters in the performance analysis are interference from the neighboring nodes, hop count to the base station (BS), number of children per node, slot reuse, load balancing, quality of services (QoS), and node identifier (ID). Results show that the proposed algorithms significantly improve the system performance in terms of length of scheduling, channel utilization ratio (CUR), system throughput, and average end to end transmission delay.

Does EFL Readers' Lexical and Grammatical Knowledge Predict Their Reading Ability? Insights from a Perceptron Artificial Neural Network Study

ERIC Educational Resources Information Center

Aryadoust, Vahid; Baghaei, Purya

2016-01-01

This study aims to examine the relationship between reading comprehension and lexical and grammatical knowledge among English as a foreign language students by using an Artificial Neural Network (ANN). There were 825 test takers administered both a second-language reading test and a set of psychometrically validated grammar and vocabulary tests.…

Training trajectories by continuous recurrent multilayer networks.

PubMed

Leistritz, L; Galicki, M; Witte, H; Kochs, E

2002-01-01

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general nonlinear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

Dynamic Graph Analytic Framework (DYGRAF): greater situation awareness through layered multi-modal network analysis

NASA Astrophysics Data System (ADS)

Margitus, Michael R.; Tagliaferri, William A., Jr.; Sudit, Moises; LaMonica, Peter M.

2012-06-01

Understanding the structure and dynamics of networks are of vital importance to winning the global war on terror. To fully comprehend the network environment, analysts must be able to investigate interconnected relationships of many diverse network types simultaneously as they evolve both spatially and temporally. To remove the burden from the analyst of making mental correlations of observations and conclusions from multiple domains, we introduce the Dynamic Graph Analytic Framework (DYGRAF). DYGRAF provides the infrastructure which facilitates a layered multi-modal network analysis (LMMNA) approach that enables analysts to assemble previously disconnected, yet related, networks in a common battle space picture. In doing so, DYGRAF provides the analyst with timely situation awareness, understanding and anticipation of threats, and support for effective decision-making in diverse environments.

Function Prediction Using Recurrent Neural Networks

DTIC Science & Technology

1991-12-01

of Neurodynamics : Perceptrons and the Theory of Brain Mechanisms. Washington: Spartan Books, 1959. 16. Ruck, Dennis W. Characterization of Multilayer...Computing, 2(2) (Fall 1990). 18. Rumelhart, David E., et al. Parallel Distributed Processing: Explorations in the Microstructure of Cognition , Volume 1

Statistical physics of interacting neural networks

NASA Astrophysics Data System (ADS)

Kinzel, Wolfgang; Metzler, Richard; Kanter, Ido

2001-12-01

Recent results on the statistical physics of time series generation and prediction are presented. A neural network is trained on quasi-periodic and chaotic sequences and overlaps to the sequence generator as well as the prediction errors are calculated numerically. For each network there exists a sequence for which it completely fails to make predictions. Two interacting networks show a transition to perfect synchronization. A pool of interacting networks shows good coordination in the minority game-a model of competition in a closed market. Finally, as a demonstration, a perceptron predicts bit sequences produced by human beings.

Improved efficient routing strategy on two-layer complex networks

NASA Astrophysics Data System (ADS)

Ma, Jinlong; Han, Weizhan; Guo, Qing; Zhang, Shuai; Wang, Junfang; Wang, Zhihao

2016-10-01

The traffic dynamics of multi-layer networks has become a hot research topic since many networks are comprised of two or more layers of subnetworks. Due to its low traffic capacity, the traditional shortest path routing (SPR) protocol is susceptible to congestion on two-layer complex networks. In this paper, we propose an efficient routing strategy named improved global awareness routing (IGAR) strategy which is based on the betweenness centrality of nodes in the two layers. With the proposed strategy, the routing paths can bypass hub nodes of both layers to enhance the transport efficiency. Simulation results show that the IGAR strategy can bring much better traffic capacity than the SPR and the global awareness routing (GAR) strategies. Because of the significantly improved traffic performance, this study is helpful to alleviate congestion of the two-layer complex networks.

Seminal quality prediction using data mining methods.

PubMed

Sahoo, Anoop J; Kumar, Yugal

2014-01-01

Now-a-days, some new classes of diseases have come into existences which are known as lifestyle diseases. The main reasons behind these diseases are changes in the lifestyle of people such as alcohol drinking, smoking, food habits etc. After going through the various lifestyle diseases, it has been found that the fertility rates (sperm quantity) in men has considerably been decreasing in last two decades. Lifestyle factors as well as environmental factors are mainly responsible for the change in the semen quality. The objective of this paper is to identify the lifestyle and environmental features that affects the seminal quality and also fertility rate in man using data mining methods. The five artificial intelligence techniques such as Multilayer perceptron (MLP), Decision Tree (DT), Navie Bayes (Kernel), Support vector machine+Particle swarm optimization (SVM+PSO) and Support vector machine (SVM) have been applied on fertility dataset to evaluate the seminal quality and also to predict the person is either normal or having altered fertility rate. While the eight feature selection techniques such as support vector machine (SVM), neural network (NN), evolutionary logistic regression (LR), support vector machine plus particle swarm optimization (SVM+PSO), principle component analysis (PCA), chi-square test, correlation and T-test methods have been used to identify more relevant features which affect the seminal quality. These techniques are applied on fertility dataset which contains 100 instances with nine attribute with two classes. The experimental result shows that SVM+PSO provides higher accuracy and area under curve (AUC) rate (94% & 0.932) among multi-layer perceptron (MLP) (92% & 0.728), Support Vector Machines (91% & 0.758), Navie Bayes (Kernel) (89% & 0.850) and Decision Tree (89% & 0.735) for some of the seminal parameters. This paper also focuses on the feature selection process i.e. how to select the features which are more important for prediction of fertility rate. In this paper, eight feature selection methods are applied on fertility dataset to find out a set of good features. The investigational results shows that childish diseases (0.079) and high fever features (0.057) has less impact on fertility rate while age (0.8685), season (0.843), surgical intervention (0.7683), alcohol consumption (0.5992), smoking habit (0.575), number of hours spent on setting (0.4366) and accident (0.5973) features have more impact. It is also observed that feature selection methods increase the accuracy of above mentioned techniques (multilayer perceptron 92%, support vector machine 91%, SVM+PSO 94%, Navie Bayes (Kernel) 89% and decision tree 89%) as compared to without feature selection methods (multilayer perceptron 86%, support vector machine 86%, SVM+PSO 85%, Navie Bayes (Kernel) 83% and decision tree 84%) which shows the applicability of feature selection methods in prediction. This paper lightens the application of artificial techniques in medical domain. From this paper, it can be concluded that data mining methods can be used to predict a person with or without disease based on environmental and lifestyle parameters/features rather than undergoing various medical test. In this paper, five data mining techniques are used to predict the fertility rate and among which SVM+PSO provide more accurate results than support vector machine and decision tree.

A multi-layer MRI description of Parkinson's disease

NASA Astrophysics Data System (ADS)

La Rocca, M.; Amoroso, N.; Lella, E.; Bellotti, R.; Tangaro, S.

2017-09-01

Magnetic resonance imaging (MRI) along with complex network is currently one of the most widely adopted techniques for detection of structural changes in neurological diseases, such as Parkinson's Disease (PD). In this paper, we present a digital image processing study, within the multi-layer network framework, combining more classifiers to evaluate the informative power of the MRI features, for the discrimination of normal controls (NC) and PD subjects. We define a network for each MRI scan; the nodes are the sub-volumes (patches) the images are divided into and the links are defined using the Pearson's pairwise correlation between patches. We obtain a multi-layer network whose important network features, obtained with different feature selection methods, are used to feed a supervised multi-level random forest classifier which exploits this base of knowledge for accurate classification. Method evaluation has been carried out using T1 MRI scans of 354 individuals, including 177 PD subjects and 177 NC from the Parkinson's Progression Markers Initiative (PPMI) database. The experimental results demonstrate that the features obtained from multiplex networks are able to accurately describe PD patterns. Besides, also if a privileged scale for studying PD disease exists, exploring the informative content of more scales leads to a significant improvement of the performances in the discrimination between disease and healthy subjects. In particular, this method gives a comprehensive overview of brain regions statistically affected by the disease, an additional value to the presented study.

Modeling and Prediction of Monthly Total Ozone Concentrations by Use of an Artificial Neural Network Based on Principal Component Analysis

NASA Astrophysics Data System (ADS)

Chattopadhyay, Surajit; Chattopadhyay, Goutami

2012-10-01

In the work discussed in this paper we considered total ozone time series over Kolkata (22°34'10.92″N, 88°22'10.92″E), an urban area in eastern India. Using cloud cover, average temperature, and rainfall as the predictors, we developed an artificial neural network, in the form of a multilayer perceptron with sigmoid non-linearity, for prediction of monthly total ozone concentrations from values of the predictors in previous months. We also estimated total ozone from values of the predictors in the same month. Before development of the neural network model we removed multicollinearity by means of principal component analysis. On the basis of the variables extracted by principal component analysis, we developed three artificial neural network models. By rigorous statistical assessment it was found that cloud cover and rainfall can act as good predictors for monthly total ozone when they are considered as the set of input variables for the neural network model constructed in the form of a multilayer perceptron. In general, the artificial neural network has good potential for predicting and estimating monthly total ozone on the basis of the meteorological predictors. It was further observed that during pre-monsoon and winter seasons, the proposed models perform better than during and after the monsoon.

Method for automatic detection of wheezing in lung sounds.

PubMed

Riella, R J; Nohama, P; Maia, J M

2009-07-01

The present report describes the development of a technique for automatic wheezing recognition in digitally recorded lung sounds. This method is based on the extraction and processing of spectral information from the respiratory cycle and the use of these data for user feedback and automatic recognition. The respiratory cycle is first pre-processed, in order to normalize its spectral information, and its spectrogram is then computed. After this procedure, the spectrogram image is processed by a two-dimensional convolution filter and a half-threshold in order to increase the contrast and isolate its highest amplitude components, respectively. Thus, in order to generate more compressed data to automatic recognition, the spectral projection from the processed spectrogram is computed and stored as an array. The higher magnitude values of the array and its respective spectral values are then located and used as inputs to a multi-layer perceptron artificial neural network, which results an automatic indication about the presence of wheezes. For validation of the methodology, lung sounds recorded from three different repositories were used. The results show that the proposed technique achieves 84.82% accuracy in the detection of wheezing for an isolated respiratory cycle and 92.86% accuracy for the detection of wheezes when detection is carried out using groups of respiratory cycles obtained from the same person. Also, the system presents the original recorded sound and the post-processed spectrogram image for the user to draw his own conclusions from the data.

The Development of a Research Environment for Neural Networks: Instantiating Neocognitions

DTIC Science & Technology

1990-12-21

interactive activation to adaptive reso- nance. Cognitive Science, 11:23-63. Reprinted in (Grossberg, 1988). Grossberg, S., editor (1988). Neural...higher order correlation network. Physica 22D, pages 276-306. Rosenblatt, F. (1962). Principles of Neurodynamics : Perceptrons and the Theory of Brain...and the PDP Research Group (1986b). Parallel Dis- tributed Processing: Ezplorations in the Microstructures of Cognition , volume 1: Foun- dations

Clinical Outcome Prediction in Aneurysmal Subarachnoid Hemorrhage Using Bayesian Neural Networks with Fuzzy Logic Inferences

PubMed Central

Lo, Benjamin W. Y.; Macdonald, R. Loch; Baker, Andrew; Levine, Mitchell A. H.

2013-01-01

Objective. The novel clinical prediction approach of Bayesian neural networks with fuzzy logic inferences is created and applied to derive prognostic decision rules in cerebral aneurysmal subarachnoid hemorrhage (aSAH). Methods. The approach of Bayesian neural networks with fuzzy logic inferences was applied to data from five trials of Tirilazad for aneurysmal subarachnoid hemorrhage (3551 patients). Results. Bayesian meta-analyses of observational studies on aSAH prognostic factors gave generalizable posterior distributions of population mean log odd ratios (ORs). Similar trends were noted in Bayesian and linear regression ORs. Significant outcome predictors include normal motor response, cerebral infarction, history of myocardial infarction, cerebral edema, history of diabetes mellitus, fever on day 8, prior subarachnoid hemorrhage, admission angiographic vasospasm, neurological grade, intraventricular hemorrhage, ruptured aneurysm size, history of hypertension, vasospasm day, age and mean arterial pressure. Heteroscedasticity was present in the nontransformed dataset. Artificial neural networks found nonlinear relationships with 11 hidden variables in 1 layer, using the multilayer perceptron model. Fuzzy logic decision rules (centroid defuzzification technique) denoted cut-off points for poor prognosis at greater than 2.5 clusters. Discussion. This aSAH prognostic system makes use of existing knowledge, recognizes unknown areas, incorporates one's clinical reasoning, and compensates for uncertainty in prognostication. PMID:23690884

Multi-Layered Feedforward Neural Networks for Image Segmentation

DTIC Science & Technology

1991-12-01

the Gram-Schmidt Network ...................... 80 xi Preface WILLIAM SHAKESPEARE 1564-1616 Is this a dagger which I see before me, The handle toward...any input-output mapping with a single hidden layer of non-linear nodes, the result may be like proving that a monkey could write Hamlet . Certainly it

Drug release control and system understanding of sucrose esters matrix tablets by artificial neural networks.

PubMed

Chansanroj, Krisanin; Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele

2011-10-09

Artificial neural networks (ANNs) were applied for system understanding and prediction of drug release properties from direct compacted matrix tablets using sucrose esters (SEs) as matrix-forming agents for controlled release of a highly water soluble drug, metoprolol tartrate. Complexity of the system was presented through the effects of SE concentration and tablet porosity at various hydrophilic-lipophilic balance (HLB) values of SEs ranging from 0 to 16. Both effects contributed to release behaviors especially in the system containing hydrophilic SEs where swelling phenomena occurred. A self-organizing map neural network (SOM) was applied for visualizing interrelation among the variables and multilayer perceptron neural networks (MLPs) were employed to generalize the system and predict the drug release properties based on HLB value and concentration of SEs and tablet properties, i.e., tablet porosity, volume and tensile strength. Accurate prediction was obtained after systematically optimizing network performance based on learning algorithm of MLP. Drug release was mainly attributed to the effects of SEs, tablet volume and tensile strength in multi-dimensional interrelation whereas tablet porosity gave a small impact. Ability of system generalization and accurate prediction of the drug release properties proves the validity of SOM and MLPs for the formulation modeling of direct compacted matrix tablets containing controlled release agents of different material properties. Copyright © 2011 Elsevier B.V. All rights reserved.

Embedded feature ranking for ensemble MLP classifiers.

PubMed

Windeatt, Terry; Duangsoithong, Rakkrit; Smith, Raymond

2011-06-01

A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features.

An artificial neural network to predict resting energy expenditure in obesity.

PubMed

Disse, Emmanuel; Ledoux, Séverine; Bétry, Cécile; Caussy, Cyrielle; Maitrepierre, Christine; Coupaye, Muriel; Laville, Martine; Simon, Chantal

2017-09-01

The resting energy expenditure (REE) determination is important in nutrition for adequate dietary prescription. The gold standard i.e. indirect calorimetry is not available in clinical settings. Thus, several predictive equations have been developed, but they lack of accuracy in subjects with extreme weight including obese populations. Artificial neural networks (ANN) are useful predictive tools in the area of artificial intelligence, used in numerous clinical fields. The aim of this study was to determine the relevance of ANN in predicting REE in obesity. A Multi-Layer Perceptron (MLP) feed-forward neural network with a back propagation algorithm was created and cross-validated in a cohort of 565 obese subjects (BMI within 30-50 kg m -2 ) with weight, height, sex and age as clinical inputs and REE measured by indirect calorimetry as output. The predictive performances of ANN were compared to those of 23 predictive REE equations in the training set and in two independent sets of 100 and 237 obese subjects for external validation. Among the 23 established prediction equations for REE evaluated, the Harris & Benedict equations recalculated by Roza were the most accurate for the obese population, followed by the USA DRI, Müller and the original Harris & Benedict equations. The final 5-fold cross-validated three-layer 4-3-1 feed-forward back propagation ANN model developed in that study improved precision and accuracy of REE prediction over linear equations (precision = 68.1%, MAPE = 8.6% and RMSPE = 210 kcal/d), independently from BMI subgroups within 30-50 kg m -2 . External validation confirmed the better predictive performances of ANN model (precision = 73% and 65%, MAPE = 7.7% and 8.6%, RMSPE = 187 kcal/d and 200 kcal/d in the 2 independent datasets) for the prediction of REE in obese subjects. We developed and validated an ANN model for the prediction of REE in obese subjects that is more precise and accurate than established REE predictive equations independent from BMI subgroups. For convenient use in clinical settings, we provide a simple ANN-REE calculator available at: https://www.crnh-rhone-alpes.fr/fr/ANN-REE-Calculator. Copyright © 2017 Elsevier Ltd and European Society for Clinical Nutrition and Metabolism. All rights reserved.

Algorithm to Identify Frequent Coupled Modules from Two-Layered Network Series: Application to Study Transcription and Splicing Coupling

PubMed Central

Li, Wenyuan; Dai, Chao; Liu, Chun-Chi

2012-01-01

Abstract Current network analysis methods all focus on one or multiple networks of the same type. However, cells are organized by multi-layer networks (e.g., transcriptional regulatory networks, splicing regulatory networks, protein-protein interaction networks), which interact and influence each other. Elucidating the coupling mechanisms among those different types of networks is essential in understanding the functions and mechanisms of cellular activities. In this article, we developed the first computational method for pattern mining across many two-layered graphs, with the two layers representing different types yet coupled biological networks. We formulated the problem of identifying frequent coupled clusters between the two layers of networks into a tensor-based computation problem, and proposed an efficient solution to solve the problem. We applied the method to 38 two-layered co-transcription and co-splicing networks, derived from 38 RNA-seq datasets. With the identified atlas of coupled transcription-splicing modules, we explored to what extent, for which cellular functions, and by what mechanisms transcription-splicing coupling takes place. PMID:22697243

Multi-temporal Land Use Mapping of Coastal Wetlands Area using Machine Learning in Google Earth Engine

NASA Astrophysics Data System (ADS)

Farda, N. M.

2017-12-01

Coastal wetlands provide ecosystem services essential to people and the environment. Changes in coastal wetlands, especially on land use, are important to monitor by utilizing multi-temporal imagery. The Google Earth Engine (GEE) provides many machine learning algorithms (10 algorithms) that are very useful for extracting land use from imagery. The research objective is to explore machine learning in Google Earth Engine and its accuracy for multi-temporal land use mapping of coastal wetland area. Landsat 3 MSS (1978), Landsat 5 TM (1991), Landsat 7 ETM+ (2001), and Landsat 8 OLI (2014) images located in Segara Anakan lagoon are selected to represent multi temporal images. The input for machine learning are visible and near infrared bands, PCA band, invers PCA bands, bare soil index, vegetation index, wetness index, elevation from ASTER GDEM, and GLCM (Harralick) texture, and also polygon samples in 140 locations. There are 10 machine learning algorithms applied to extract coastal wetlands land use from Landsat imagery. The algorithms are Fast Naive Bayes, CART (Classification and Regression Tree), Random Forests, GMO Max Entropy, Perceptron (Multi Class Perceptron), Winnow, Voting SVM, Margin SVM, Pegasos (Primal Estimated sub-GrAdient SOlver for Svm), IKPamir (Intersection Kernel Passive Aggressive Method for Information Retrieval, SVM). Machine learning in Google Earth Engine are very helpful in multi-temporal land use mapping, the highest accuracy for land use mapping of coastal wetland is CART with 96.98 % Overall Accuracy using K-Fold Cross Validation (K = 10). GEE is particularly useful for multi-temporal land use mapping with ready used image and classification algorithms, and also very challenging for other applications.

Artificial neural networks using complex numbers and phase encoded weights.

PubMed

Michel, Howard E; Awwal, Abdul Ahad S

2010-04-01

The model of a simple perceptron using phase-encoded inputs and complex-valued weights is proposed. The aggregation function, activation function, and learning rule for the proposed neuron are derived and applied to Boolean logic functions and simple computer vision tasks. The complex-valued neuron (CVN) is shown to be superior to traditional perceptrons. An improvement of 135% over the theoretical maximum of 104 linearly separable problems (of three variables) solvable by conventional perceptrons is achieved without additional logic, neuron stages, or higher order terms such as those required in polynomial logic gates. The application of CVN in distortion invariant character recognition and image segmentation is demonstrated. Implementation details are discussed, and the CVN is shown to be very attractive for optical implementation since optical computations are naturally complex. The cost of the CVN is less in all cases than the traditional neuron when implemented optically. Therefore, all the benefits of the CVN can be obtained without additional cost. However, on those implementations dependent on standard serial computers, CVN will be more cost effective only in those applications where its increased power can offset the requirement for additional neurons.

Deep multi-scale convolutional neural network for hyperspectral image classification

NASA Astrophysics Data System (ADS)

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.

Robust hepatic vessel segmentation using multi deep convolution network

NASA Astrophysics Data System (ADS)

Kitrungrotsakul, Titinunt; Han, Xian-Hua; Iwamoto, Yutaro; Foruzan, Amir Hossein; Lin, Lanfen; Chen, Yen-Wei

2017-03-01

Extraction of blood vessels of the organ is a challenging task in the area of medical image processing. It is really difficult to get accurate vessel segmentation results even with manually labeling by human being. The difficulty of vessels segmentation is the complicated structure of blood vessels and its large variations that make them hard to recognize. In this paper, we present deep artificial neural network architecture to automatically segment the hepatic vessels from computed tomography (CT) image. We proposed novel deep neural network (DNN) architecture for vessel segmentation from a medical CT volume, which consists of three deep convolution neural networks to extract features from difference planes of CT data. The three networks have share features at the first convolution layer but will separately learn their own features in the second layer. All three networks will join again at the top layer. To validate effectiveness and efficiency of our proposed method, we conduct experiments on 12 CT volumes which training data are randomly generate from 5 CT volumes and 7 using for test. Our network can yield an average dice coefficient 0.830, while 3D deep convolution neural network can yield around 0.7 and multi-scale can yield only 0.6.

Artificial neural network in cosmic landscape

NASA Astrophysics Data System (ADS)

Liu, Junyu

2017-12-01

In this paper we propose that artificial neural network, the basis of machine learning, is useful to generate the inflationary landscape from a cosmological point of view. Traditional numerical simulations of a global cosmic landscape typically need an exponential complexity when the number of fields is large. However, a basic application of artificial neural network could solve the problem based on the universal approximation theorem of the multilayer perceptron. A toy model in inflation with multiple light fields is investigated numerically as an example of such an application.

Prediction of heart abnormality using MLP network

NASA Astrophysics Data System (ADS)

Hashim, Fakroul Ridzuan; Januar, Yulni; Mat, Muhammad Hadzren; Rizman, Zairi Ismael; Awang, Mat Kamil

2018-02-01

Heart abnormality does not choose gender, age and races when it strikes. With no warning signs or symptoms, it can result to a sudden death of the patient. Generally, heart's irregular electrical activity is defined as heart abnormality. Via implementation of Multilayer Perceptron (MLP) network, this paper tries to develop a program that allows the detection of heart abnormality activity. Utilizing several training algorithms with Purelin activation function, an amount of heartbeat signals received through the electrocardiogram (ECG) will be employed to condition the MLP network.

Controllability of multiplex, multi-time-scale networks

NASA Astrophysics Data System (ADS)

Pósfai, Márton; Gao, Jianxi; Cornelius, Sean P.; Barabási, Albert-László; D'Souza, Raissa M.

2016-09-01

The paradigm of layered networks is used to describe many real-world systems, from biological networks to social organizations and transportation systems. While recently there has been much progress in understanding the general properties of multilayer networks, our understanding of how to control such systems remains limited. One fundamental aspect that makes this endeavor challenging is that each layer can operate at a different time scale; thus, we cannot directly apply standard ideas from structural control theory of individual networks. Here we address the problem of controlling multilayer and multi-time-scale networks focusing on two-layer multiplex networks with one-to-one interlayer coupling. We investigate the practically relevant case when the control signal is applied to the nodes of one layer. We develop a theory based on disjoint path covers to determine the minimum number of inputs (Ni) necessary for full control. We show that if both layers operate on the same time scale, then the network structure of both layers equally affect controllability. In the presence of time-scale separation, controllability is enhanced if the controller interacts with the faster layer: Ni decreases as the time-scale difference increases up to a critical time-scale difference, above which Ni remains constant and is completely determined by the faster layer. We show that the critical time-scale difference is large if layer I is easy and layer II is hard to control in isolation. In contrast, control becomes increasingly difficult if the controller interacts with the layer operating on the slower time scale and increasing time-scale separation leads to increased Ni, again up to a critical value, above which Ni still depends on the structure of both layers. This critical value is largely determined by the longest path in the faster layer that does not involve cycles. By identifying the underlying mechanisms that connect time-scale difference and controllability for a simplified model, we provide crucial insight into disentangling how our ability to control real interacting complex systems is affected by a variety of sources of complexity.

Comparison of Logistic Regression and Artificial Neural Network in Low Back Pain Prediction: Second National Health Survey

PubMed Central

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

Background: The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Methods: Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. Results: The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Conclusions: Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant. PMID:23113198

Comparison of logistic regression and artificial neural network in low back pain prediction: second national health survey.

PubMed

Parsaeian, M; Mohammad, K; Mahmoudi, M; Zeraati, H

2012-01-01

The purpose of this investigation was to compare empirically predictive ability of an artificial neural network with a logistic regression in prediction of low back pain. Data from the second national health survey were considered in this investigation. This data includes the information of low back pain and its associated risk factors among Iranian people aged 15 years and older. Artificial neural network and logistic regression models were developed using a set of 17294 data and they were validated in a test set of 17295 data. Hosmer and Lemeshow recommendation for model selection was used in fitting the logistic regression. A three-layer perceptron with 9 inputs, 3 hidden and 1 output neurons was employed. The efficiency of two models was compared by receiver operating characteristic analysis, root mean square and -2 Loglikelihood criteria. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the logistic regression was 0.752 (0.004), 0.3832 and 14769.2, respectively. The area under the ROC curve (SE), root mean square and -2Loglikelihood of the artificial neural network was 0.754 (0.004), 0.3770 and 14757.6, respectively. Based on these three criteria, artificial neural network would give better performance than logistic regression. Although, the difference is statistically significant, it does not seem to be clinically significant.

Optical Network Virtualisation Using Multitechnology Monitoring and SDN-Enabled Optical Transceiver

NASA Astrophysics Data System (ADS)

Ou, Yanni; Davis, Matthew; Aguado, Alejandro; Meng, Fanchao; Nejabati, Reza; Simeonidou, Dimitra

2018-05-01

We introduce the real-time multi-technology transport layer monitoring to facilitate the coordinated virtualisation of optical and Ethernet networks supported by optical virtualise-able transceivers (V-BVT). A monitoring and network resource configuration scheme is proposed to include the hardware monitoring in both Ethernet and Optical layers. The scheme depicts the data and control interactions among multiple network layers under the software defined network (SDN) background, as well as the application that analyses the monitored data obtained from the database. We also present a re-configuration algorithm to adaptively modify the composition of virtual optical networks based on two criteria. The proposed monitoring scheme is experimentally demonstrated with OpenFlow (OF) extensions for a holistic (re-)configuration across both layers in Ethernet switches and V-BVTs.

Models of Innate Neural Attractors and Their Applications for Neural Information Processing

PubMed Central

Solovyeva, Ksenia P.; Karandashev, Iakov M.; Zhavoronkov, Alex; Dunin-Barkowski, Witali L.

2016-01-01

In this work we reveal and explore a new class of attractor neural networks, based on inborn connections provided by model molecular markers, the molecular marker based attractor neural networks (MMBANN). Each set of markers has a metric, which is used to make connections between neurons containing the markers. We have explored conditions for the existence of attractor states, critical relations between their parameters and the spectrum of single neuron models, which can implement the MMBANN. Besides, we describe functional models (perceptron and SOM), which obtain significant advantages over the traditional implementation of these models, while using MMBANN. In particular, a perceptron, based on MMBANN, gets specificity gain in orders of error probabilities values, MMBANN SOM obtains real neurophysiological meaning, the number of possible grandma cells increases 1000-fold with MMBANN. MMBANN have sets of attractor states, which can serve as finite grids for representation of variables in computations. These grids may show dimensions of d = 0, 1, 2,…. We work with static and dynamic attractor neural networks of the dimensions d = 0 and 1. We also argue that the number of dimensions which can be represented by attractors of activities of neural networks with the number of elements N = 104 does not exceed 8. PMID:26778977

Stabilizing bidirectional associative memory with Principles in Independent Component Analysis and Null Space (PICANS)

NASA Astrophysics Data System (ADS)

LaRue, James P.; Luzanov, Yuriy

2013-05-01

A new extension to the way in which the Bidirectional Associative Memory (BAM) algorithms are implemented is presented here. We will show that by utilizing the singular value decomposition (SVD) and integrating principles of independent component analysis (ICA) into the nullspace (NS) we have created a novel approach to mitigating spurious attractors. We demonstrate this with two applications. The first application utilizes a one-layer association while the second application is modeled after the several hierarchal associations of ventral pathways. The first application will detail the way in which we manage the associations in terms of matrices. The second application will take what we have learned from the first example and apply it to a cascade of a convolutional neural network (CNN) and perceptron this being our signal processing model of the ventral pathways, i.e., visual systems.

A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network

PubMed Central

Liu, Zengkai; Liu, Yonghong; Shan, Hongkai; Cai, Baoping; Huang, Qing

2015-01-01

This paper proposes a fault diagnosis methodology for a gear pump based on the ensemble empirical mode decomposition (EEMD) method and the Bayesian network. Essentially, the presented scheme is a multi-source information fusion based methodology. Compared with the conventional fault diagnosis with only EEMD, the proposed method is able to take advantage of all useful information besides sensor signals. The presented diagnostic Bayesian network consists of a fault layer, a fault feature layer and a multi-source information layer. Vibration signals from sensor measurement are decomposed by the EEMD method and the energy of intrinsic mode functions (IMFs) are calculated as fault features. These features are added into the fault feature layer in the Bayesian network. The other sources of useful information are added to the information layer. The generalized three-layer Bayesian network can be developed by fully incorporating faults and fault symptoms as well as other useful information such as naked eye inspection and maintenance records. Therefore, diagnostic accuracy and capacity can be improved. The proposed methodology is applied to the fault diagnosis of a gear pump and the structure and parameters of the Bayesian network is established. Compared with artificial neural network and support vector machine classification algorithms, the proposed model has the best diagnostic performance when sensor data is used only. A case study has demonstrated that some information from human observation or system repair records is very helpful to the fault diagnosis. It is effective and efficient in diagnosing faults based on uncertain, incomplete information. PMID:25938760

A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network.

PubMed

Liu, Zengkai; Liu, Yonghong; Shan, Hongkai; Cai, Baoping; Huang, Qing

2015-01-01

This paper proposes a fault diagnosis methodology for a gear pump based on the ensemble empirical mode decomposition (EEMD) method and the Bayesian network. Essentially, the presented scheme is a multi-source information fusion based methodology. Compared with the conventional fault diagnosis with only EEMD, the proposed method is able to take advantage of all useful information besides sensor signals. The presented diagnostic Bayesian network consists of a fault layer, a fault feature layer and a multi-source information layer. Vibration signals from sensor measurement are decomposed by the EEMD method and the energy of intrinsic mode functions (IMFs) are calculated as fault features. These features are added into the fault feature layer in the Bayesian network. The other sources of useful information are added to the information layer. The generalized three-layer Bayesian network can be developed by fully incorporating faults and fault symptoms as well as other useful information such as naked eye inspection and maintenance records. Therefore, diagnostic accuracy and capacity can be improved. The proposed methodology is applied to the fault diagnosis of a gear pump and the structure and parameters of the Bayesian network is established. Compared with artificial neural network and support vector machine classification algorithms, the proposed model has the best diagnostic performance when sensor data is used only. A case study has demonstrated that some information from human observation or system repair records is very helpful to the fault diagnosis. It is effective and efficient in diagnosing faults based on uncertain, incomplete information.

Application of Classification Models to Pharyngeal High-Resolution Manometry

ERIC Educational Resources Information Center

Mielens, Jason D.; Hoffman, Matthew R.; Ciucci, Michelle R.; McCulloch, Timothy M.; Jiang, Jack J.

2012-01-01

Purpose: The authors present 3 methods of performing pattern recognition on spatiotemporal plots produced by pharyngeal high-resolution manometry (HRM). Method: Classification models, including the artificial neural networks (ANNs) multilayer perceptron (MLP) and learning vector quantization (LVQ), as well as support vector machines (SVM), were…

Neural Networks Applied to Signal Processing

DTIC Science & Technology

1989-09-01

Distributed Processing, The MIT Press, Cambridge, MA, 1988. 3. Marvin Minsky and Seymour Papert, Perceptrons, The MIT Press, Cambridge, MA, 1969. 4...signum function, the linear function, and the sigmoid function. Initial research conducted in the 1950’s and 1960’s by Rosenblat, Minsky and others used

MLP based models to predict PM10, O3 concentrations, in Sines industrial area

NASA Astrophysics Data System (ADS)

Durao, R.; Pereira, M. J.

2012-04-01

Sines is an important Portuguese industrial area located southwest cost of Portugal with important nearby protected natural areas. The main economical activities are related with this industrial area, the deep-water port, petrochemical and thermo-electric industry. Nevertheless, tourism is also an important economic activity especially in summer time with potential to grow. The aim of this study is to develop prediction models of pollutant concentration categories (e.g. low concentration and high concentration) in order to provide early warnings to the competent authorities who are responsible for the air quality management. The knowledge in advanced of pollutant high concentrations occurrence will allow the implementation of mitigation actions and the release of precautionary alerts to population. The regional air quality monitoring network consists in three monitoring stations where a set of pollutants' concentrations are registered on a continuous basis. From this set stands out the tropospheric ozone (O3) and particulate matter (PM10) due to the high concentrations occurring in the region and their adverse effects on human health. Moreover, the major industrial plants of the region monitor SO2, NO2 and particles emitted flows at the principal chimneys (point sources), also on a continuous basis,. Therefore Artificial neuronal networks (ANN) were the applied methodology to predict next day pollutant concentrations; due to the ANNs structure they have the ability to capture the non-linear relationships between predictor variables. Hence the first step of this study was to apply multivariate exploratory techniques to select the best predictor variables. The classification trees methodology (CART) was revealed to be the most appropriate in this case.. Results shown that pollutants atmospheric concentrations are mainly dependent on industrial emissions and a complex combination of meteorological factors and the time of the year. In the second step, the Multi-layer perceptron (MLP) have shown to be able to learn the existent complex relationships using different combination of meteorological and emissions variables. Furthermore, MLP models identified what are the meteorological conditions that most affect O3 and PM10 concentrations in the region, namely wind speed and direction, boundary layer height, temperature, sunshine duration, relative humidity and the weather type. The developed MLP models showed good predictive success with model performances between 0.66 and 0.87, indicating a reasonable accuracy for models development and generalization capability. These performance values are obtained using cross entropy error functions. This error functions are only available for classification problems and ensure that the network outputs are true class membership probabilities, which is known to enhance the performance of classification neural networks.

Multicategory nets of single-layer perceptrons: complexity and sample-size issues.

PubMed

Raudys, Sarunas; Kybartas, Rimantas; Zavadskas, Edmundas Kazimieras

2010-05-01

The standard cost function of multicategory single-layer perceptrons (SLPs) does not minimize the classification error rate. In order to reduce classification error, it is necessary to: 1) refuse the traditional cost function, 2) obtain near to optimal pairwise linear classifiers by specially organized SLP training and optimal stopping, and 3) fuse their decisions properly. To obtain better classification in unbalanced training set situations, we introduce the unbalance correcting term. It was found that fusion based on the Kulback-Leibler (K-L) distance and the Wu-Lin-Weng (WLW) method result in approximately the same performance in situations where sample sizes are relatively small. The explanation for this observation is by theoretically known verity that an excessive minimization of inexact criteria becomes harmful at times. Comprehensive comparative investigations of six real-world pattern recognition (PR) problems demonstrated that employment of SLP-based pairwise classifiers is comparable and as often as not outperforming the linear support vector (SV) classifiers in moderate dimensional situations. The colored noise injection used to design pseudovalidation sets proves to be a powerful tool for facilitating finite sample problems in moderate-dimensional PR tasks.

Study on Data Clustering and Intelligent Decision Algorithm of Indoor Localization

NASA Astrophysics Data System (ADS)

Liu, Zexi

2018-01-01

Indoor positioning technology enables the human beings to have the ability of positional perception in architectural space, and there is a shortage of single network coverage and the problem of location data redundancy. So this article puts forward the indoor positioning data clustering algorithm and intelligent decision-making research, design the basic ideas of multi-source indoor positioning technology, analyzes the fingerprint localization algorithm based on distance measurement, position and orientation of inertial device integration. By optimizing the clustering processing of massive indoor location data, the data normalization pretreatment, multi-dimensional controllable clustering center and multi-factor clustering are realized, and the redundancy of locating data is reduced. In addition, the path is proposed based on neural network inference and decision, design the sparse data input layer, the dynamic feedback hidden layer and output layer, low dimensional results improve the intelligent navigation path planning.

Multi-channels coupling-induced pattern transition in a tri-layer neuronal network

NASA Astrophysics Data System (ADS)

Wu, Fuqiang; Wang, Ya; Ma, Jun; Jin, Wuyin; Hobiny, Aatef

2018-03-01

Neurons in nerve system show complex electrical behaviors due to complex connection types and diversity in excitability. A tri-layer network is constructed to investigate the signal propagation and pattern formation by selecting different coupling channels between layers. Each layer is set as different states, and the local kinetics is described by Hindmarsh-Rose neuron model. By changing the number of coupling channels between layers and the state of the first layer, the collective behaviors of each layer and synchronization pattern of network are investigated. A statistical factor of synchronization on each layer is calculated. It is found that quiescent state in the second layer can be excited and disordered state in the third layer is suppressed when the first layer is controlled by a pacemaker, and the developed state is dependent on the number of coupling channels. Furthermore, the collapse in the first layer can cause breakdown of other layers in the network, and the mechanism is that disordered state in the third layer is enhanced when sampled signals from the collapsed layer can impose continuous disturbance on the next layer.

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

Sampling Approaches for Multi-Domain Internet Performance Measurement Infrastructures

DOE Office of Scientific and Technical Information (OSTI.GOV)

Calyam, Prasad

2014-09-15

The next-generation of high-performance networks being developed in DOE communities are critical for supporting current and emerging data-intensive science applications. The goal of this project is to investigate multi-domain network status sampling techniques and tools to measure/analyze performance, and thereby provide “network awareness” to end-users and network operators in DOE communities. We leverage the infrastructure and datasets available through perfSONAR, which is a multi-domain measurement framework that has been widely deployed in high-performance computing and networking communities; the DOE community is a core developer and the largest adopter of perfSONAR. Our investigations include development of semantic scheduling algorithms, measurement federationmore » policies, and tools to sample multi-domain and multi-layer network status within perfSONAR deployments. We validate our algorithms and policies with end-to-end measurement analysis tools for various monitoring objectives such as network weather forecasting, anomaly detection, and fault-diagnosis. In addition, we develop a multi-domain architecture for an enterprise-specific perfSONAR deployment that can implement monitoring-objective based sampling and that adheres to any domain-specific measurement policies.« less

A neural network based computational model to predict the output power of different types of photovoltaic cells.

PubMed

Xiao, WenBo; Nazario, Gina; Wu, HuaMing; Zhang, HuaMing; Cheng, Feng

2017-01-01

In this article, we introduced an artificial neural network (ANN) based computational model to predict the output power of three types of photovoltaic cells, mono-crystalline (mono-), multi-crystalline (multi-), and amorphous (amor-) crystalline. The prediction results are very close to the experimental data, and were also influenced by numbers of hidden neurons. The order of the solar generation power output influenced by the external conditions from smallest to biggest is: multi-, mono-, and amor- crystalline silicon cells. In addition, the dependences of power prediction on the number of hidden neurons were studied. For multi- and amorphous crystalline cell, three or four hidden layer units resulted in the high correlation coefficient and low MSEs. For mono-crystalline cell, the best results were achieved at the hidden layer unit of 8.

Optical Processing.

DTIC Science & Technology

1985-12-31

34 Optics Letters, 2 (1), 1-3 (1978). 7. Grossberg, S., "Adaptive Resonance in Development, Perception and Cognition ," SIAM-AMS Proc., 13, 107-156...Illusions," Biol. Cybernetics, 23, 187-202, (1976b). 11. Grossberg, S., "How Does A Brain Build a Cognitive Code?", Psychol. Review, 87 (1), 1-51 (1980...34perceptron" (F. Rosenblatt, Principles of Neurodynamics ), workers in the neural network field have been seeking to understand how neural networks can perform

SINET3: advanced optical and IP hybrid network

NASA Astrophysics Data System (ADS)

Urushidani, Shigeo

2007-11-01

This paper introduces the new Japanese academic backbone network called SINET3, which has been in full-scale operation since June 2007. SINET3 provides a wide variety of network services, such as multi-layer transfer, enriched VPN, enhanced QoS, and layer-1 bandwidth on demand (BoD) services to create an innovative and prolific science infrastructure for more than 700 universities and research institutions. The network applies an advanced hybrid network architecture composed of 75 layer-1 switches and 12 high-performance IP routers to accommodate such diversified services in a single network platform, and provides sufficient bandwidth using Japan's first STM256 (40 Gbps) lines. The network adopts lots of the latest networking technologies, such as next-generation SDH (VCAT/GFP/LCAS), GMPLS, advanced MPLS, and logical-router technologies, for high network convergence, flexible resource assignment, and high service availability. This paper covers the network services, network design, and networking technologies of SINET3.

Uncoordinated MAC for Adaptive Multi-Beam Directional Networks: Analysis and Evaluation

DTIC Science & Technology

2016-04-10

transmission times, hence traditional CSMA approaches are not appropriate. We first present our model of these multi-beamforming capa- bilities and the...resulting wireless interference. We then derive an upper bound on multi-access performance for an idealized version of this physical layer. We then present... transmissions and receptions in a mobile ad-hoc network has in practice led to very constrained topologies. As mentioned, one approach for system design is to de

Patterns recognition of electric brain activity using artificial neural networks

NASA Astrophysics Data System (ADS)

Musatov, V. Yu.; Pchelintseva, S. V.; Runnova, A. E.; Hramov, A. E.

2017-04-01

An approach for the recognition of various cognitive processes in the brain activity in the perception of ambiguous images. On the basis of developed theoretical background and the experimental data, we propose a new classification of oscillating patterns in the human EEG by using an artificial neural network approach. After learning of the artificial neural network reliably identified cube recognition processes, for example, left-handed or right-oriented Necker cube with different intensity of their edges, construct an artificial neural network based on Perceptron architecture and demonstrate its effectiveness in the pattern recognition of the EEG in the experimental.

The importance of structural softening for the evolution and architecture of passive margins

PubMed Central

Duretz, T.; Petri, B.; Mohn, G.; Schmalholz, S. M.; Schenker, F. L.; Müntener, O.

2016-01-01

Lithospheric extension can generate passive margins that bound oceans worldwide. Detailed geological and geophysical studies in present and fossil passive margins have highlighted the complexity of their architecture and their multi-stage deformation history. Previous modeling studies have shown the significant impact of coarse mechanical layering of the lithosphere (2 to 4 layer crust and mantle) on passive margin formation. We built upon these studies and design high-resolution (~100–300 m) thermo-mechanical numerical models that incorporate finer mechanical layering (kilometer scale) mimicking tectonically inherited heterogeneities. During lithospheric extension a variety of extensional structures arises naturally due to (1) structural softening caused by necking of mechanically strong layers and (2) the establishment of a network of weak layers across the deforming multi-layered lithosphere. We argue that structural softening in a multi-layered lithosphere is the main cause for the observed multi-stage evolution and architecture of magma-poor passive margins. PMID:27929057

SENSITIVITY ANALYSIS OF THE MULTI-LAYER MODEL USED IN THE CLEAN AIR STATUS AND TRENDS NETWORK (CASTNET)

EPA Science Inventory

The U.S. Environmental Protection Agency (EPA) established the Clean Air Status and Trends Network (CASTNET) and its predecessor, the National Dry Deposition Network (NDDN), as national air quality and meteorological monitoring networks. The purpose of CASTNET is to track the pr...

Evaluation of multilayer perceptron algorithms for an analysis of network flow data

NASA Astrophysics Data System (ADS)

Bieniasz, Jedrzej; Rawski, Mariusz; Skowron, Krzysztof; Trzepiński, Mateusz

2016-09-01

The volume of exchanged information through IP networks is larger than ever and still growing. It creates a space for both benign and malicious activities. The second one raises awareness on security network devices, as well as network infrastructure and a system as a whole. One of the basic tools to prevent cyber attacks is Network Instrusion Detection System (NIDS). NIDS could be realized as a signature-based detector or an anomaly-based one. In the last few years the emphasis has been placed on the latter type, because of the possibility of applying smart and intelligent solutions. An ideal NIDS of next generation should be composed of self-learning algorithms that could react on known and unknown malicious network activities respectively. In this paper we evaluated a machine learning approach for detection of anomalies in IP network data represented as NetFlow records. We considered Multilayer Perceptron (MLP) as the classifier and we used two types of learning algorithms - Backpropagation (BP) and Particle Swarm Optimization (PSO). This paper includes a comprehensive survey on determining the most optimal MLP learning algorithm for the classification problem in application to network flow data. The performance, training time and convergence of BP and PSO methods were compared. The results show that PSO algorithm implemented by the authors outperformed other solutions if accuracy of classifications is considered. The major disadvantage of PSO is training time, which could be not acceptable for larger data sets or in real network applications. At the end we compared some key findings with the results from the other papers to show that in all cases results from this study outperformed them.

Gamma Spectroscopy by Artificial Neural Network Coupled with MCNP

NASA Astrophysics Data System (ADS)

Sahiner, Huseyin

While neutron activation analysis is widely used in many areas, sensitivity of the analysis depends on how the analysis is conducted. Even though the sensitivity of the techniques carries error, compared to chemical analysis, its range is in parts per million or sometimes billion. Due to this sensitivity, the use of neutron activation analysis becomes important when analyzing bio-samples. Artificial neural network is an attractive technique for complex systems. Although there are neural network applications on spectral analysis, training by simulated data to analyze experimental data has not been made. This study offers an improvement on spectral analysis and optimization on neural network for the purpose. The work considers five elements that are considered as trace elements for bio-samples. However, the system is not limited to five elements. The only limitation of the study comes from data library availability on MCNP. A perceptron network was employed to identify five elements from gamma spectra. In quantitative analysis, better results were obtained when the neural fitting tool in MATLAB was used. As a training function, Levenberg-Marquardt algorithm was used with 23 neurons in the hidden layer with 259 gamma spectra in the input. Because the interest of the study deals with five elements, five neurons representing peak counts of five isotopes in the input layer were used. Five output neurons revealed mass information of these elements from irradiated kidney stones. Results showing max error of 17.9% in APA, 24.9% in UA, 28.2% in COM, 27.9% in STRU type showed the success of neural network approach in analyzing gamma spectra. This high error was attributed to Zn that has a very long decay half-life compared to the other elements. The simulation and experiments were made under certain experimental setup (3 hours irradiation, 96 hours decay time, 8 hours counting time). Nevertheless, the approach is subject to be generalized for different setups.

ON AERODYNAMIC AND BOUNDARY LAYER RESISTANCES WITHIN DRY DEPOSITION MODELS

EPA Science Inventory

There have been many empirical parameterizations for the aerodynamic and boundary layer resistances proposed in the literature, e.g. those of the Meyers Multi-Layer Deposition Model (MLM) used with the nation-wide dry deposition network. Many include arbitrary constants or par...

Tansig activation function (of MLP network) for cardiac abnormality detection

NASA Astrophysics Data System (ADS)

Adnan, Ja'afar; Daud, Nik Ghazali Nik; Ishak, Mohd Taufiq; Rizman, Zairi Ismael; Rahman, Muhammad Izzuddin Abd

2018-02-01

Heart abnormality often occurs regardless of gender, age and races. This problem sometimes does not show any symptoms and it can cause a sudden death to the patient. In general, heart abnormality is the irregular electrical activity of the heart. This paper attempts to develop a program that can detect heart abnormality activity through implementation of Multilayer Perceptron (MLP) network. A certain amount of data of the heartbeat signals from the electrocardiogram (ECG) will be used in this project to train the MLP network by using several training algorithms with Tansig activation function.

Adaptation technology between IP layer and optical layer in optical Internet

NASA Astrophysics Data System (ADS)

Ji, Yuefeng; Li, Hua; Sun, Yongmei

2001-10-01

Wavelength division multiplexing (WDM) optical network provides a platform with high bandwidth capacity and is supposed to be the backbone infrastructure supporting the next-generation high-speed multi-service networks (ATM, IP, etc.). In the foreseeable future, IP will be the predominant data traffic, to make fully use of the bandwidth of the WDM optical network, many attentions have been focused on IP over WDM, which has been proposed as the most promising technology for new kind of network, so-called Optical Internet. According to OSI model, IP is in the 3rd layer (network layer) and optical network is in the 1st layer (physical layer), so the key issue is what adaptation technology should be used in the 2nd layer (data link layer). In this paper, firstly, we analyze and compare the current adaptation technologies used in backbone network nowadays. Secondly, aiming at the drawbacks of above technologies, we present a novel adaptation protocol (DONA) between IP layer and optical layer in Optical Internet and describe it in details. Thirdly, the gigabit transmission adapter (GTA) we accomplished based on the novel protocol is described. Finally, we set up an experiment platform to apply and verify the DONA and GTA, the results and conclusions of the experiment are given.

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose

PubMed Central

Rahman, Mohammad Mizanur; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-01-01

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k-nearest neighbor (k-NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms. PMID:28895910

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose.

PubMed

Rahman, Mohammad Mizanur; Charoenlarpnopparut, Chalie; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-09-12

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k -nearest neighbor ( k -NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms.

Designing an artificial neural network using radial basis function to model exergetic efficiency of nanofluids in mini double pipe heat exchanger

NASA Astrophysics Data System (ADS)

Ghasemi, Nahid; Aghayari, Reza; Maddah, Heydar

2018-06-01

The present study aims at predicting and optimizing exergetic efficiency of TiO2-Al2O3/water nanofluid at different Reynolds numbers, volume fractions and twisted ratios using Artificial Neural Networks (ANN) and experimental data. Central Composite Design (CCD) and cascade Radial Basis Function (RBF) were used to display the significant levels of the analyzed factors on the exergetic efficiency. The size of TiO2-Al2O3/water nanocomposite was 20-70 nm. The parameters of ANN model were adapted by a training algorithm of radial basis function (RBF) with a wide range of experimental data set. Total mean square error and correlation coefficient were used to evaluate the results which the best result was obtained from double layer perceptron neural network with 30 neurons in which total Mean Square Error(MSE) and correlation coefficient (R2) were equal to 0.002 and 0.999, respectively. This indicated successful prediction of the network. Moreover, the proposed equation for predicting exergetic efficiency was extremely successful. According to the optimal curves, the optimum designing parameters of double pipe heat exchanger with inner twisted tape and nanofluid under the constrains of exergetic efficiency 0.937 are found to be Reynolds number 2500, twisted ratio 2.5 and volume fraction( v/v%) 0.05.

Monthly prediction of air temperature in Australia and New Zealand with machine learning algorithms

NASA Astrophysics Data System (ADS)

Salcedo-Sanz, S.; Deo, R. C.; Carro-Calvo, L.; Saavedra-Moreno, B.

2016-07-01

Long-term air temperature prediction is of major importance in a large number of applications, including climate-related studies, energy, agricultural, or medical. This paper examines the performance of two Machine Learning algorithms (Support Vector Regression (SVR) and Multi-layer Perceptron (MLP)) in a problem of monthly mean air temperature prediction, from the previous measured values in observational stations of Australia and New Zealand, and climate indices of importance in the region. The performance of the two considered algorithms is discussed in the paper and compared to alternative approaches. The results indicate that the SVR algorithm is able to obtain the best prediction performance among all the algorithms compared in the paper. Moreover, the results obtained have shown that the mean absolute error made by the two algorithms considered is significantly larger for the last 20 years than in the previous decades, in what can be interpreted as a change in the relationship among the prediction variables involved in the training of the algorithms.

Activity recognition with smartphone support.

PubMed

Guiry, John J; van de Ven, Pepijn; Nelson, John; Warmerdam, Lisanne; Riper, Heleen

2014-06-01

In this paper, the authors describe a method of accurately detecting human activity using a smartphone accelerometer paired with a dedicated chest sensor. The design, implementation, testing and validation of a custom mobility classifier are also presented. Offline analysis was carried out to compare this custom classifier to de-facto machine learning algorithms, including C4.5, CART, SVM, Multi-Layer Perceptrons, and Naïve Bayes. A series of trials were carried out in Ireland, initially involving N=6 individuals to test the feasibility of the system, before a final trial with N=24 subjects took place in the Netherlands. The protocol used and analysis of 1165min of recorded activities from these trials are described in detail in this paper. Analysis of collected data indicate that accelerometers placed in these locations, are capable of recognizing activities including sitting, standing, lying, walking, running and cycling with accuracies as high as 98%. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

Comparison of genetic algorithm and imperialist competitive algorithms in predicting bed load transport in clean pipe.

PubMed

Ebtehaj, Isa; Bonakdari, Hossein

2014-01-01

The existence of sediments in wastewater greatly affects the performance of the sewer and wastewater transmission systems. Increased sedimentation in wastewater collection systems causes problems such as reduced transmission capacity and early combined sewer overflow. The article reviews the performance of the genetic algorithm (GA) and imperialist competitive algorithm (ICA) in minimizing the target function (mean square error of observed and predicted Froude number). To study the impact of bed load transport parameters, using four non-dimensional groups, six different models have been presented. Moreover, the roulette wheel selection method is used to select the parents. The ICA with root mean square error (RMSE) = 0.007, mean absolute percentage error (MAPE) = 3.5% show better results than GA (RMSE = 0.007, MAPE = 5.6%) for the selected model. All six models return better results than the GA. Also, the results of these two algorithms were compared with multi-layer perceptron and existing equations.

The Effect of Normalization in Violence Video Classification Performance

NASA Astrophysics Data System (ADS)

Ali, Ashikin; Senan, Norhalina

2017-08-01

Basically, data pre-processing is an important part of data mining. Normalization is a pre-processing stage for any type of problem statement, especially in video classification. Challenging problems that arises in video classification is because of the heterogeneous content, large variations in video quality and complex semantic meanings of the concepts involved. Therefore, to regularize this problem, it is thoughtful to ensure normalization or basically involvement of thorough pre-processing stage aids the robustness of classification performance. This process is to scale all the numeric variables into certain range to make it more meaningful for further phases in available data mining techniques. Thus, this paper attempts to examine the effect of 2 normalization techniques namely Min-max normalization and Z-score in violence video classifications towards the performance of classification rate using Multi-layer perceptron (MLP) classifier. Using Min-Max Normalization range of [0,1] the result shows almost 98% of accuracy, meanwhile Min-Max Normalization range of [-1,1] accuracy is 59% and for Z-score the accuracy is 50%.

When mental fatigue maybe characterized by Event Related Potential (P300) during virtual wheelchair navigation.

PubMed

Lamti, Hachem A; Gorce, Philippe; Ben Khelifa, Mohamed Moncef; Alimi, Adel M

2016-12-01

The goal of this study is to investigate the influence of mental fatigue on the event related potential P300 features (maximum pick, minimum amplitude, latency and period) during virtual wheelchair navigation. For this purpose, an experimental environment was set up based on customizable environmental parameters (luminosity, number of obstacles and obstacles velocities). A correlation study between P300 and fatigue ratings was conducted. Finally, the best correlated features supplied three classification algorithms which are MLP (Multi Layer Perceptron), Linear Discriminate Analysis and Support Vector Machine. The results showed that the maximum feature over visual and temporal regions as well as period feature over frontal, fronto-central and visual regions were correlated with mental fatigue levels. In the other hand, minimum amplitude and latency features didn't show any correlation. Among classification techniques, MLP showed the best performance although the differences between classification techniques are minimal. Those findings can help us in order to design suitable mental fatigue based wheelchair control.

Inter-layer synchronization in non-identical multi-layer networks

NASA Astrophysics Data System (ADS)

Leyva, I.; Sevilla-Escoboza, R.; Sendiña-Nadal, I.; Gutiérrez, R.; Buldú, J. M.; Boccaletti, S.

2017-04-01

Inter-layer synchronization is a dynamical process occurring in multi-layer networks composed of identical nodes. This process emerges when all layers are synchronized, while nodes in each layer do not necessarily evolve in unison. So far, the study of such inter-layer synchronization has been restricted to the case in which all layers have an identical connectivity structure. When layers are not identical, the inter-layer synchronous state is no longer a stable solution of the system. Nevertheless, when layers differ in just a few links, an approximate treatment is still feasible, and allows one to gather information on whether and how the system may wander around an inter-layer synchronous configuration. We report the details of an approximate analytical treatment for a two-layer multiplex, which results in the introduction of an extra inertial term accounting for structural differences. Numerical validation of the predictions highlights the usefulness of our approach, especially for small or moderate topological differences in the intra-layer coupling. Moreover, we identify a non-trivial relationship connecting the betweenness centrality of the missing links and the intra-layer coupling strength. Finally, by the use of multiplexed layers of electronic circuits, we study the inter-layer synchronization as a function of the removed links.

AMS 4.0: consensus prediction of post-translational modifications in protein sequences.

PubMed

Plewczynski, Dariusz; Basu, Subhadip; Saha, Indrajit

2012-08-01

We present here the 2011 update of the AutoMotif Service (AMS 4.0) that predicts the wide selection of 88 different types of the single amino acid post-translational modifications (PTM) in protein sequences. The selection of experimentally confirmed modifications is acquired from the latest UniProt and Phospho.ELM databases for training. The sequence vicinity of each modified residue is represented using amino acids physico-chemical features encoded using high quality indices (HQI) obtaining by automatic clustering of known indices extracted from AAindex database. For each type of the numerical representation, the method builds the ensemble of Multi-Layer Perceptron (MLP) pattern classifiers, each optimising different objectives during the training (for example the recall, precision or area under the ROC curve (AUC)). The consensus is built using brainstorming technology, which combines multi-objective instances of machine learning algorithm, and the data fusion of different training objects representations, in order to boost the overall prediction accuracy of conserved short sequence motifs. The performance of AMS 4.0 is compared with the accuracy of previous versions, which were constructed using single machine learning methods (artificial neural networks, support vector machine). Our software improves the average AUC score of the earlier version by close to 7 % as calculated on the test datasets of all 88 PTM types. Moreover, for the selected most-difficult sequence motifs types it is able to improve the prediction performance by almost 32 %, when compared with previously used single machine learning methods. Summarising, the brainstorming consensus meta-learning methodology on the average boosts the AUC score up to around 89 %, averaged over all 88 PTM types. Detailed results for single machine learning methods and the consensus methodology are also provided, together with the comparison to previously published methods and state-of-the-art software tools. The source code and precompiled binaries of brainstorming tool are available at http://code.google.com/p/automotifserver/ under Apache 2.0 licensing.

Can human experts predict solubility better than computers?

PubMed

Boobier, Samuel; Osbourn, Anne; Mitchell, John B O

2017-12-13

In this study, we design and carry out a survey, asking human experts to predict the aqueous solubility of druglike organic compounds. We investigate whether these experts, drawn largely from the pharmaceutical industry and academia, can match or exceed the predictive power of algorithms. Alongside this, we implement 10 typical machine learning algorithms on the same dataset. The best algorithm, a variety of neural network known as a multi-layer perceptron, gave an RMSE of 0.985 log S units and an R 2 of 0.706. We would not have predicted the relative success of this particular algorithm in advance. We found that the best individual human predictor generated an almost identical prediction quality with an RMSE of 0.942 log S units and an R 2 of 0.723. The collection of algorithms contained a higher proportion of reasonably good predictors, nine out of ten compared with around half of the humans. We found that, for either humans or algorithms, combining individual predictions into a consensus predictor by taking their median generated excellent predictivity. While our consensus human predictor achieved very slightly better headline figures on various statistical measures, the difference between it and the consensus machine learning predictor was both small and statistically insignificant. We conclude that human experts can predict the aqueous solubility of druglike molecules essentially equally well as machine learning algorithms. We find that, for either humans or algorithms, combining individual predictions into a consensus predictor by taking their median is a powerful way of benefitting from the wisdom of crowds.

Multi-focus image fusion with the all convolutional neural network

NASA Astrophysics Data System (ADS)

Du, Chao-ben; Gao, She-sheng

2018-01-01

A decision map contains complete and clear information about the image to be fused, which is crucial to various image fusion issues, especially multi-focus image fusion. However, in order to get a satisfactory image fusion effect, getting a decision map is very necessary and usually difficult to finish. In this letter, we address this problem with convolutional neural network (CNN), aiming to get a state-of-the-art decision map. The main idea is that the max-pooling of CNN is replaced by a convolution layer, the residuals are propagated backwards by gradient descent, and the training parameters of the individual layers of the CNN are updated layer by layer. Based on this, we propose a new all CNN (ACNN)-based multi-focus image fusion method in spatial domain. We demonstrate that the decision map obtained from the ACNN is reliable and can lead to high-quality fusion results. Experimental results clearly validate that the proposed algorithm can obtain state-of-the-art fusion performance in terms of both qualitative and quantitative evaluations.

Optimum coagulant forecasting by modeling jar test experiments using ANNs

NASA Astrophysics Data System (ADS)

Haghiri, Sadaf; Daghighi, Amin; Moharramzadeh, Sina

2018-01-01

Currently, the proper utilization of water treatment plants and optimizing their use is of particular importance. Coagulation and flocculation in water treatment are the common ways through which the use of coagulants leads to instability of particles and the formation of larger and heavier particles, resulting in improvement of sedimentation and filtration processes. Determination of the optimum dose of such a coagulant is of particular significance. A high dose, in addition to adding costs, can cause the sediment to remain in the filtrate, a dangerous condition according to the standards, while a sub-adequate dose of coagulants can result in the reducing the required quality and acceptable performance of the coagulation process. Although jar tests are used for testing coagulants, such experiments face many constraints with respect to evaluating the results produced by sudden changes in input water because of their significant costs, long time requirements, and complex relationships among the many factors (turbidity, temperature, pH, alkalinity, etc.) that can influence the efficiency of coagulant and test results. Modeling can be used to overcome these limitations; in this research study, an artificial neural network (ANN) multi-layer perceptron (MLP) with one hidden layer has been used for modeling the jar test to determine the dosage level of used coagulant in water treatment processes. The data contained in this research have been obtained from the drinking water treatment plant located in Ardabil province in Iran. To evaluate the performance of the model, the mean squared error (MSE) and correlation coefficient (R2) parameters have been used. The obtained values are within an acceptable range that demonstrates the high accuracy of the models with respect to the estimation of water-quality characteristics and the optimal dosages of coagulants; so using these models will allow operators to not only reduce costs and time taken to perform experimental jar tests but also to predict a proper dosage for coagulant amounts and to project the quality of the output water under real conditions.

Theoretical Investigation of Optical Computing Based on Neural Network Models.

DTIC Science & Technology

1987-09-29

34 Cognitive and Psychological Computation with Neu- ral Models," IEEE Trans. Sys., Man, and cyber., SMC-13, p. 799, 1983. 20’ K. Nakano, "Association-A...7),482(1986). 211 F. Rosenblatt, Principles of Neurodynamics : Perceptron and the The- ory of Brain Mechanisms, Spartan Books, Washington,(1961). 22

Feature Extraction and Classification of FLIR Imagery Using Relative Locations of Non-Homogeneous Regions with Feedforward Neural Networks

DTIC Science & Technology

1992-04-01

Proceedings of Tri-Service Data Fusion Symposium, Johns Hopkins University, May 1989. 39. F. Rosenblatt. Principles of Neurodynamics : Perceptrons and the...104 47. David E. Rummelhart and James L. McClelland. Parallel Distributed Processing: Explorations in the Microstructure of Cognition , volume 1. The

Novel maximum-margin training algorithms for supervised neural networks.

PubMed

Ludwig, Oswaldo; Nunes, Urbano

2010-06-01

This paper proposes three novel training methods, two of them based on the backpropagation approach and a third one based on information theory for multilayer perceptron (MLP) binary classifiers. Both backpropagation methods are based on the maximal-margin (MM) principle. The first one, based on the gradient descent with adaptive learning rate algorithm (GDX) and named maximum-margin GDX (MMGDX), directly increases the margin of the MLP output-layer hyperplane. The proposed method jointly optimizes both MLP layers in a single process, backpropagating the gradient of an MM-based objective function, through the output and hidden layers, in order to create a hidden-layer space that enables a higher margin for the output-layer hyperplane, avoiding the testing of many arbitrary kernels, as occurs in case of support vector machine (SVM) training. The proposed MM-based objective function aims to stretch out the margin to its limit. An objective function based on Lp-norm is also proposed in order to take into account the idea of support vectors, however, overcoming the complexity involved in solving a constrained optimization problem, usually in SVM training. In fact, all the training methods proposed in this paper have time and space complexities O(N) while usual SVM training methods have time complexity O(N (3)) and space complexity O(N (2)) , where N is the training-data-set size. The second approach, named minimization of interclass interference (MICI), has an objective function inspired on the Fisher discriminant analysis. Such algorithm aims to create an MLP hidden output where the patterns have a desirable statistical distribution. In both training methods, the maximum area under ROC curve (AUC) is applied as stop criterion. The third approach offers a robust training framework able to take the best of each proposed training method. The main idea is to compose a neural model by using neurons extracted from three other neural networks, each one previously trained by MICI, MMGDX, and Levenberg-Marquard (LM), respectively. The resulting neural network was named assembled neural network (ASNN). Benchmark data sets of real-world problems have been used in experiments that enable a comparison with other state-of-the-art classifiers. The results provide evidence of the effectiveness of our methods regarding accuracy, AUC, and balanced error rate.

Time Shared Optical Network (TSON): a novel metro architecture for flexible multi-granular services.

PubMed

Zervas, Georgios S; Triay, Joan; Amaya, Norberto; Qin, Yixuan; Cervelló-Pastor, Cristina; Simeonidou, Dimitra

2011-12-12

This paper presents the Time Shared Optical Network (TSON) as metro mesh network architecture for guaranteed, statistically-multiplexed services. TSON proposes a flexible and tunable time-wavelength assignment along with one-way tree-based reservation and node architecture. It delivers guaranteed sub-wavelength and multi-granular network services without wavelength conversion, time-slice interchange and optical buffering. Simulation results demonstrate high network utilization, fast service delivery, and low end-to-end delay on a contention-free sub-wavelength optical transport network. In addition, implementation complexity in terms of Layer 2 aggregation, grooming and optical switching has been evaluated. © 2011 Optical Society of America

Research on networked manufacturing system for reciprocating pump industry

NASA Astrophysics Data System (ADS)

Wu, Yangdong; Qi, Guoning; Xie, Qingsheng; Lu, Yujun

2005-12-01

Networked manufacturing is a trend of reciprocating pump industry. According to the enterprises' requirement, the architecture of networked manufacturing system for reciprocating pump industry was proposed, which composed of infrastructure layer, system management layer, application service layer and user layer. Its main functions included product data management, ASP service, business management, and customer relationship management, its physics framework was a multi-tier internet-based model; the concept of ASP service integration was put forward and its process model was also established. As a result, a networked manufacturing system aimed at the characteristics of reciprocating pump industry was built. By implementing this system, reciprocating pump industry can obtain a new way to fully utilize their own resources and enhance the capabilities to respond to the global market quickly.

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG.

PubMed

Bai, Ou; Lin, Peter; Vorbach, Sherry; Li, Jiang; Furlani, Steve; Hallett, Mark

2007-12-01

To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG). Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis (ICA), common spatial patterns analysis (CSP), and surface Laplacian derivation (SLD); temporal filtering using power spectral density estimation (PSD) and discrete wavelet transform (DWT); pattern classification using linear Mahalanobis distance classifier (LMD), quadratic Mahalanobis distance classifier (QMD), Bayesian classifier (BSC), multi-layer perceptron neural network (MLP), probabilistic neural network (PNN), and support vector machine (SVM). A robust multivariate feature selection strategy using a genetic algorithm was employed. The combinations of spatial filtering using ICA and SLD, temporal filtering using PSD and DWT, and classification methods using LMD, QMD, BSC and SVM provided higher performance than those of other combinations. Utilizing one of the better combinations of ICA, PSD and SVM, the discrimination accuracy was as high as 75%. Further feature analysis showed that beta band EEG activity of the channels over right sensorimotor cortex was most appropriate for discrimination of right and left hand movement intention. Effective combinations of computational methods provide possible classification of human movement intention from single trial EEG. Such a method could be the basis for a potential brain-computer interface based on human natural movement, which might reduce the requirement of long-term training. Effective combinations of computational methods can classify human movement intention from single trial EEG with reasonable accuracy.

Hybrid analysis for indicating patients with breast cancer using temperature time series.

PubMed

Silva, Lincoln F; Santos, Alair Augusto S M D; Bravo, Renato S; Silva, Aristófanes C; Muchaluat-Saade, Débora C; Conci, Aura

2016-07-01

Breast cancer is the most common cancer among women worldwide. Diagnosis and treatment in early stages increase cure chances. The temperature of cancerous tissue is generally higher than that of healthy surrounding tissues, making thermography an option to be considered in screening strategies of this cancer type. This paper proposes a hybrid methodology for analyzing dynamic infrared thermography in order to indicate patients with risk of breast cancer, using unsupervised and supervised machine learning techniques, which characterizes the methodology as hybrid. The dynamic infrared thermography monitors or quantitatively measures temperature changes on the examined surface, after a thermal stress. In the dynamic infrared thermography execution, a sequence of breast thermograms is generated. In the proposed methodology, this sequence is processed and analyzed by several techniques. First, the region of the breasts is segmented and the thermograms of the sequence are registered. Then, temperature time series are built and the k-means algorithm is applied on these series using various values of k. Clustering formed by k-means algorithm, for each k value, is evaluated using clustering validation indices, generating values treated as features in the classification model construction step. A data mining tool was used to solve the combined algorithm selection and hyperparameter optimization (CASH) problem in classification tasks. Besides the classification algorithm recommended by the data mining tool, classifiers based on Bayesian networks, neural networks, decision rules and decision tree were executed on the data set used for evaluation. Test results support that the proposed analysis methodology is able to indicate patients with breast cancer. Among 39 tested classification algorithms, K-Star and Bayes Net presented 100% classification accuracy. Furthermore, among the Bayes Net, multi-layer perceptron, decision table and random forest classification algorithms, an average accuracy of 95.38% was obtained. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Determination of important topographic factors for landslide mapping analysis using MLP network.

PubMed

Alkhasawneh, Mutasem Sh; Ngah, Umi Kalthum; Tay, Lea Tien; Mat Isa, Nor Ashidi; Al-batah, Mohammad Subhi

2013-01-01

Landslide is one of the natural disasters that occur in Malaysia. Topographic factors such as elevation, slope angle, slope aspect, general curvature, plan curvature, and profile curvature are considered as the main causes of landslides. In order to determine the dominant topographic factors in landslide mapping analysis, a study was conducted and presented in this paper. There are three main stages involved in this study. The first stage is the extraction of extra topographic factors. Previous landslide studies had identified mainly six topographic factors. Seven new additional factors have been proposed in this study. They are longitude curvature, tangential curvature, cross section curvature, surface area, diagonal line length, surface roughness, and rugosity. The second stage is the specification of the weight of each factor using two methods. The methods are multilayer perceptron (MLP) network classification accuracy and Zhou's algorithm. At the third stage, the factors with higher weights were used to improve the MLP performance. Out of the thirteen factors, eight factors were considered as important factors, which are surface area, longitude curvature, diagonal length, slope angle, elevation, slope aspect, rugosity, and profile curvature. The classification accuracy of multilayer perceptron neural network has increased by 3% after the elimination of five less important factors.

Determination of Important Topographic Factors for Landslide Mapping Analysis Using MLP Network

PubMed Central

Alkhasawneh, Mutasem Sh.; Ngah, Umi Kalthum; Mat Isa, Nor Ashidi; Al-batah, Mohammad Subhi

2013-01-01

Landslide is one of the natural disasters that occur in Malaysia. Topographic factors such as elevation, slope angle, slope aspect, general curvature, plan curvature, and profile curvature are considered as the main causes of landslides. In order to determine the dominant topographic factors in landslide mapping analysis, a study was conducted and presented in this paper. There are three main stages involved in this study. The first stage is the extraction of extra topographic factors. Previous landslide studies had identified mainly six topographic factors. Seven new additional factors have been proposed in this study. They are longitude curvature, tangential curvature, cross section curvature, surface area, diagonal line length, surface roughness, and rugosity. The second stage is the specification of the weight of each factor using two methods. The methods are multilayer perceptron (MLP) network classification accuracy and Zhou's algorithm. At the third stage, the factors with higher weights were used to improve the MLP performance. Out of the thirteen factors, eight factors were considered as important factors, which are surface area, longitude curvature, diagonal length, slope angle, elevation, slope aspect, rugosity, and profile curvature. The classification accuracy of multilayer perceptron neural network has increased by 3% after the elimination of five less important factors. PMID:24453846

Combining neural networks and genetic algorithms for hydrological flow forecasting

NASA Astrophysics Data System (ADS)

Neruda, Roman; Srejber, Jan; Neruda, Martin; Pascenko, Petr

2010-05-01

We present a neural network approach to rainfall-runoff modeling for small size river basins based on several time series of hourly measured data. Different neural networks are considered for short time runoff predictions (from one to six hours lead time) based on runoff and rainfall data observed in previous time steps. Correlation analysis shows that runoff data, short time rainfall history, and aggregated API values are the most significant data for the prediction. Neural models of multilayer perceptron and radial basis function networks with different numbers of units are used and compared with more traditional linear time series predictors. Out of possible 48 hours of relevant history of all the input variables, the most important ones are selected by means of input filters created by a genetic algorithm. The genetic algorithm works with population of binary encoded vectors defining input selection patterns. Standard genetic operators of two-point crossover, random bit-flipping mutation, and tournament selection were used. The evaluation of objective function of each individual consists of several rounds of building and testing a particular neural network model. The whole procedure is rather computational exacting (taking hours to days on a desktop PC), thus a high-performance mainframe computer has been used for our experiments. Results based on two years worth data from the Ploucnice river in Northern Bohemia suggest that main problems connected with this approach to modeling are ovetraining that can lead to poor generalization, and relatively small number of extreme events which makes it difficult for a model to predict the amplitude of the event. Thus, experiments with both absolute and relative runoff predictions were carried out. In general it can be concluded that the neural models show about 5 per cent improvement in terms of efficiency coefficient over liner models. Multilayer perceptrons with one hidden layer trained by back propagation algorithm and predicting relative runoff show the best behavior so far. Utilizing the genetically evolved input filter improves the performance of yet another 5 per cent. In the future we would like to continue with experiments in on-line prediction using real-time data from Smeda River with 6 hours lead time forecast. Following the operational reality we will focus on classification of the runoffs into flood alert levels, and reformulation of the time series prediction task as a classification problem. The main goal of all this work is to improve flood warning system operated by the Czech Hydrometeorological Institute.

Results of research on development of an intellectual information system of bankruptcy risk assessment of the enterprise

NASA Astrophysics Data System (ADS)

Telipenko, E.; Chernysheva, T.; Zakharova, A.; Dumchev, A.

2015-10-01

The article represents research results about the knowledge base development for the intellectual information system for the bankruptcy risk assessment of the enterprise. It is described the process analysis of the knowledge base development; the main process stages, some problems and their solutions are given. The article introduces the connectionist model for the bankruptcy risk assessment based on the analysis of industrial enterprise financial accounting. The basis for this connectionist model is a three-layer perceptron with the back propagation of error algorithm. The knowledge base for the intellectual information system consists of processed information and the processing operation method represented as the connectionist model. The article represents the structure of the intellectual information system, the knowledge base, and the information processing algorithm for neural network training. The paper shows mean values of 10 indexes for industrial enterprises; with the help of them it is possible to carry out a financial analysis of industrial enterprises and identify correctly the current situation for well-timed managerial decisions. Results are given about neural network testing on the data of both bankrupt and financially strong enterprises, which were not included into training and test sets.

SpaceFibre: The Standard and the Multi-Lane Layer

NASA Astrophysics Data System (ADS)

Parkes, Steve; McClements, Chris; McLaren, David; Florit, Albert Ferrer; Gonzalez Villafranca, Alberto

2016-08-01

SpaceFibre is a new standard for spacecraft on-board data-handling networks, initially designed to deliver multi-Gbit/s data rates for synthetic aperture radar and high-resolution, multi-spectral imaging instruments, The addition of quality of service (QoS) and fault detection, isolation and recovery (FDIR) capabilities to SpaceFibre has resulted in a unified network technology. SpaceFibre provides high bandwidth, low latency, fault isolation and recovery suitable for space applications, and novel QoS that combines priority, bandwidth reservation and scheduling and which provides babbling node protection. SpaceFibre is backwards compatible with the widely used SpaceWire standard at the network level allowing simple interconnection of existing SpaceWire equipment to a SpaceFibre link or network.Developed by STAR-Dundee and the University of Dundee for the European Space Agency (ESA) SpaceFibre is able to operate over fibre-optic and electrical cable. A single lane of SpaceFibre comprises four signals (TX+/- and RX+/-) and supports data rates of 2 Gbits/s (2.5 Gbits/s data signalling rate) with data rates up to 5 Gbits/s already planned.Several lanes can operate together to provide a multi- lane link. Multi-laning increases the data-rate to well over 20 Gbits/s.This paper details the current state of SpaceFibre which is now in the process of formal standardisation by the European Cooperation for Space Standardization (ECSS). The multi-lane layer of SpaceFibre is then described.

Large Scale Crop Classification in Ukraine using Multi-temporal Landsat-8 Images with Missing Data

NASA Astrophysics Data System (ADS)

Kussul, N.; Skakun, S.; Shelestov, A.; Lavreniuk, M. S.

2014-12-01

At present, there are no globally available Earth observation (EO) derived products on crop maps. This issue is being addressed within the Sentinel-2 for Agriculture initiative where a number of test sites (including from JECAM) participate to provide coherent protocols and best practices for various global agriculture systems, and subsequently crop maps from Sentinel-2. One of the problems in dealing with optical images for large territories (more than 10,000 sq. km) is the presence of clouds and shadows that result in having missing values in data sets. In this abstract, a new approach to classification of multi-temporal optical satellite imagery with missing data due to clouds and shadows is proposed. First, self-organizing Kohonen maps (SOMs) are used to restore missing pixel values in a time series of satellite imagery. SOMs are trained for each spectral band separately using non-missing values. Missing values are restored through a special procedure that substitutes input sample's missing components with neuron's weight coefficients. After missing data restoration, a supervised classification is performed for multi-temporal satellite images. For this, an ensemble of neural networks, in particular multilayer perceptrons (MLPs), is proposed. Ensembling of neural networks is done by the technique of average committee, i.e. to calculate the average class probability over classifiers and select the class with the highest average posterior probability for the given input sample. The proposed approach is applied for large scale crop classification using multi temporal Landsat-8 images for the JECAM test site in Ukraine [1-2]. It is shown that ensemble of MLPs provides better performance than a single neural network in terms of overall classification accuracy and kappa coefficient. The obtained classification map is also validated through estimated crop and forest areas and comparison to official statistics. 1. A.Yu. Shelestov et al., "Geospatial information system for agricultural monitoring," Cybernetics Syst. Anal., vol. 49, no. 1, pp. 124-132, 2013. 2. J. Gallego et al., "Efficiency Assessment of Different Approaches to Crop Classification Based on Satellite and Ground Observations," J. Autom. Inform. Scie., vol. 44, no. 5, pp. 67-80, 2012.

MAC layer security issues in wireless mesh networks

NASA Astrophysics Data System (ADS)

Reddy, K. Ganesh; Thilagam, P. Santhi

2016-03-01

Wireless Mesh Networks (WMNs) have emerged as a promising technology for a broad range of applications due to their self-organizing, self-configuring and self-healing capability, in addition to their low cost and easy maintenance. Securing WMNs is more challenging and complex issue due to their inherent characteristics such as shared wireless medium, multi-hop and inter-network communication, highly dynamic network topology and decentralized architecture. These vulnerable features expose the WMNs to several types of attacks in MAC layer. The existing MAC layer standards and implementations are inadequate to secure these features and fail to provide comprehensive security solutions to protect both backbone and client mesh. Hence, there is a need for developing efficient, scalable and integrated security solutions for WMNs. In this paper, we classify the MAC layer attacks and analyze the existing countermeasures. Based on attacks classification and countermeasures analysis, we derive the research directions to enhance the MAC layer security for WMNs.

Constructing general partial differential equations using polynomial and neural networks.

PubMed

Zjavka, Ladislav; Pedrycz, Witold

2016-01-01

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

Healthcare Text Classification System and its Performance Evaluation: A Source of Better Intelligence by Characterizing Healthcare Text.

PubMed

Srivastava, Saurabh Kumar; Singh, Sandeep Kumar; Suri, Jasjit S

2018-04-13

A machine learning (ML)-based text classification system has several classifiers. The performance evaluation (PE) of the ML system is typically driven by the training data size and the partition protocols used. Such systems lead to low accuracy because the text classification systems lack the ability to model the input text data in terms of noise characteristics. This research study proposes a concept of misrepresentation ratio (MRR) on input healthcare text data and models the PE criteria for validating the hypothesis. Further, such a novel system provides a platform to amalgamate several attributes of the ML system such as: data size, classifier type, partitioning protocol and percentage MRR. Our comprehensive data analysis consisted of five types of text data sets (TwitterA, WebKB4, Disease, Reuters (R8), and SMS); five kinds of classifiers (support vector machine with linear kernel (SVM-L), MLP-based neural network, AdaBoost, stochastic gradient descent and decision tree); and five types of training protocols (K2, K4, K5, K10 and JK). Using the decreasing order of MRR, our ML system demonstrates the mean classification accuracies as: 70.13 ± 0.15%, 87.34 ± 0.06%, 93.73 ± 0.03%, 94.45 ± 0.03% and 97.83 ± 0.01%, respectively, using all the classifiers and protocols. The corresponding AUC is 0.98 for SMS data using Multi-Layer Perceptron (MLP) based neural network. All the classifiers, the best accuracy of 91.84 ± 0.04% is shown to be of MLP-based neural network and this is 6% better over previously published. Further we observed that as MRR decreases, the system robustness increases and validated by standard deviations. The overall text system accuracy using all data types, classifiers, protocols is 89%, thereby showing the entire ML system to be novel, robust and unique. The system is also tested for stability and reliability.

Modeling Uncertainties in EEG Microstates: Analysis of Real and Imagined Motor Movements Using Probabilistic Clustering-Driven Training of Probabilistic Neural Networks.

PubMed

Dinov, Martin; Leech, Robert

2017-01-01

Part of the process of EEG microstate estimation involves clustering EEG channel data at the global field power (GFP) maxima, very commonly using a modified K-means approach. Clustering has also been done deterministically, despite there being uncertainties in multiple stages of the microstate analysis, including the GFP peak definition, the clustering itself and in the post-clustering assignment of microstates back onto the EEG timecourse of interest. We perform a fully probabilistic microstate clustering and labeling, to account for these sources of uncertainty using the closest probabilistic analog to KM called Fuzzy C-means (FCM). We train softmax multi-layer perceptrons (MLPs) using the KM and FCM-inferred cluster assignments as target labels, to then allow for probabilistic labeling of the full EEG data instead of the usual correlation-based deterministic microstate label assignment typically used. We assess the merits of the probabilistic analysis vs. the deterministic approaches in EEG data recorded while participants perform real or imagined motor movements from a publicly available data set of 109 subjects. Though FCM group template maps that are almost topographically identical to KM were found, there is considerable uncertainty in the subsequent assignment of microstate labels. In general, imagined motor movements are less predictable on a time point-by-time point basis, possibly reflecting the more exploratory nature of the brain state during imagined, compared to during real motor movements. We find that some relationships may be more evident using FCM than using KM and propose that future microstate analysis should preferably be performed probabilistically rather than deterministically, especially in situations such as with brain computer interfaces, where both training and applying models of microstates need to account for uncertainty. Probabilistic neural network-driven microstate assignment has a number of advantages that we have discussed, which are likely to be further developed and exploited in future studies. In conclusion, probabilistic clustering and a probabilistic neural network-driven approach to microstate analysis is likely to better model and reveal details and the variability hidden in current deterministic and binarized microstate assignment and analyses.

Modeling Uncertainties in EEG Microstates: Analysis of Real and Imagined Motor Movements Using Probabilistic Clustering-Driven Training of Probabilistic Neural Networks

PubMed Central

Dinov, Martin; Leech, Robert

2017-01-01

Part of the process of EEG microstate estimation involves clustering EEG channel data at the global field power (GFP) maxima, very commonly using a modified K-means approach. Clustering has also been done deterministically, despite there being uncertainties in multiple stages of the microstate analysis, including the GFP peak definition, the clustering itself and in the post-clustering assignment of microstates back onto the EEG timecourse of interest. We perform a fully probabilistic microstate clustering and labeling, to account for these sources of uncertainty using the closest probabilistic analog to KM called Fuzzy C-means (FCM). We train softmax multi-layer perceptrons (MLPs) using the KM and FCM-inferred cluster assignments as target labels, to then allow for probabilistic labeling of the full EEG data instead of the usual correlation-based deterministic microstate label assignment typically used. We assess the merits of the probabilistic analysis vs. the deterministic approaches in EEG data recorded while participants perform real or imagined motor movements from a publicly available data set of 109 subjects. Though FCM group template maps that are almost topographically identical to KM were found, there is considerable uncertainty in the subsequent assignment of microstate labels. In general, imagined motor movements are less predictable on a time point-by-time point basis, possibly reflecting the more exploratory nature of the brain state during imagined, compared to during real motor movements. We find that some relationships may be more evident using FCM than using KM and propose that future microstate analysis should preferably be performed probabilistically rather than deterministically, especially in situations such as with brain computer interfaces, where both training and applying models of microstates need to account for uncertainty. Probabilistic neural network-driven microstate assignment has a number of advantages that we have discussed, which are likely to be further developed and exploited in future studies. In conclusion, probabilistic clustering and a probabilistic neural network-driven approach to microstate analysis is likely to better model and reveal details and the variability hidden in current deterministic and binarized microstate assignment and analyses. PMID:29163110

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

PubMed

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.

Anomalous Signal Detection in ELF Band Electromagnetic Wave using Multi-layer Neural Network with Wavelet Decomposition

NASA Astrophysics Data System (ADS)

Itai, Akitoshi; Yasukawa, Hiroshi; Takumi, Ichi; Hata, Masayasu

It is well known that electromagnetic waves radiated from the earth's crust are useful for predicting earthquakes. We analyze the electromagnetic waves received at the extremely low frequency band of 223Hz. These observed signals contain the seismic radiation from the earth's crust, but also include several undesired signals. Our research focuses on the signal detection technique to identify an anomalous signal corresponding to the seismic radiation in the observed signal. Conventional anomalous signal detections lack a wide applicability due to their assumptions, e.g. the digital data have to be observed at the same time or the same sensor. In order to overcome the limitation related to the observed signal, we proposed the anomalous signals detection based on a multi-layer neural network which is trained by digital data observed during a span of a day. In the neural network approach, training data do not need to be recorded at the same place or the same time. However, some noises, which have a large amplitude, are detected as the anomalous signal. This paper develops a multi-layer neural network to decrease the false detection of the anomalous signal from the electromagnetic wave. The training data for the proposed network is the decomposed signal of the observed signal during several days, since the seismic radiations are often recorded from several days to a couple of weeks. Results show that the proposed neural network is useful to achieve the accurate detection of the anomalous signal that indicates seismic activity.

Competitive dynamics of lexical innovations in multi-layer networks

NASA Astrophysics Data System (ADS)

Javarone, Marco Alberto

2014-04-01

We study the introduction of lexical innovations into a community of language users. Lexical innovations, i.e. new term added to people's vocabulary, plays an important role in the process of language evolution. Nowadays, information is spread through a variety of networks, including, among others, online and offline social networks and the World Wide Web. The entire system, comprising networks of different nature, can be represented as a multi-layer network. In this context, lexical innovations diffusion occurs in a peculiar fashion. In particular, a lexical innovation can undergo three different processes: its original meaning is accepted; its meaning can be changed or misunderstood (e.g. when not properly explained), hence more than one meaning can emerge in the population. Lastly, in the case of a loan word, it can be translated into the population language (i.e. defining a new lexical innovation or using a synonym) or into a dialect spoken by part of the population. Therefore, lexical innovations cannot be considered simply as information. We develop a model for analyzing this scenario using a multi-layer network comprising a social network and a media network. The latter represents the set of all information systems of a society, e.g. television, the World Wide Web and radio. Furthermore, we identify temporal directed edges between the nodes of these two networks. In particular, at each time-step, nodes of the media network can be connected to randomly chosen nodes of the social network and vice versa. In doing so, information spreads through the whole system and people can share a lexical innovation with their neighbors or, in the event they work as reporters, by using media nodes. Lastly, we use the concept of "linguistic sign" to model lexical innovations, showing its fundamental role in the study of these dynamics. Many numerical simulations have been performed to analyze the proposed model and its outcomes.

Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer images.

PubMed

Fu, Min; Wu, Wenming; Hong, Xiafei; Liu, Qiuhua; Jiang, Jialin; Ou, Yaobin; Zhao, Yupei; Gong, Xinqi

2018-04-24

Efficient computational recognition and segmentation of target organ from medical images are foundational in diagnosis and treatment, especially about pancreas cancer. In practice, the diversity in appearance of pancreas and organs in abdomen, makes detailed texture information of objects important in segmentation algorithm. According to our observations, however, the structures of previous networks, such as the Richer Feature Convolutional Network (RCF), are too coarse to segment the object (pancreas) accurately, especially the edge. In this paper, we extend the RCF, proposed to the field of edge detection, for the challenging pancreas segmentation, and put forward a novel pancreas segmentation network. By employing multi-layer up-sampling structure replacing the simple up-sampling operation in all stages, the proposed network fully considers the multi-scale detailed contexture information of object (pancreas) to perform per-pixel segmentation. Additionally, using the CT scans, we supply and train our network, thus get an effective pipeline. Working with our pipeline with multi-layer up-sampling model, we achieve better performance than RCF in the task of single object (pancreas) segmentation. Besides, combining with multi scale input, we achieve the 76.36% DSC (Dice Similarity Coefficient) value in testing data. The results of our experiments show that our advanced model works better than previous networks in our dataset. On the other words, it has better ability in catching detailed contexture information. Therefore, our new single object segmentation model has practical meaning in computational automatic diagnosis.

Space-Time Processing for Tactical Mobile Ad Hoc Networks

DTIC Science & Technology

2007-08-01

rates in mobile ad hoc networks. In addition, he has considered the design of a cross-layer multi-user resource allocation framework using a... framework for many-to-one communication. In this context, multiple nodes cooperate to transmit their packets simultaneously to a single node using multi...spatially multiplexed signals transmitted from multiple nodes. Our goal is to form a framework that activates different sets of communication links

Artificial vision by multi-layered neural networks: neocognitron and its advances.

PubMed

Fukushima, Kunihiko

2013-01-01

The neocognitron is a neural network model proposed by Fukushima (1980). Its architecture was suggested by neurophysiological findings on the visual systems of mammals. It is a hierarchical multi-layered network. It acquires the ability to robustly recognize visual patterns through learning. Although the neocognitron has a long history, modifications of the network to improve its performance are still going on. For example, a recent neocognitron uses a new learning rule, named add-if-silent, which makes the learning process much simpler and more stable. Nevertheless, a high recognition rate can be kept with a smaller scale of the network. Referring to the history of the neocognitron, this paper discusses recent advances in the neocognitron. We also show that various new functions can be realized by, for example, introducing top-down connections to the neocognitron: mechanism of selective attention, recognition and completion of partly occluded patterns, restoring occluded contours, and so on. Copyright © 2012 Elsevier Ltd. All rights reserved.

Using Hybrid Algorithm to Improve Intrusion Detection in Multi Layer Feed Forward Neural Networks

ERIC Educational Resources Information Center

Ray, Loye Lynn

2014-01-01

The need for detecting malicious behavior on a computer networks continued to be important to maintaining a safe and secure environment. The purpose of this study was to determine the relationship of multilayer feed forward neural network architecture to the ability of detecting abnormal behavior in networks. This involved building, training, and…

The potential of computer vision, optical backscattering parameters and artificial neural network modelling in monitoring the shrinkage of sweet potato (Ipomoea batatas L.) during drying.

PubMed

Onwude, Daniel I; Hashim, Norhashila; Abdan, Khalina; Janius, Rimfiel; Chen, Guangnan

2018-03-01

Drying is a method used to preserve agricultural crops. During the drying of products with high moisture content, structural changes in shape, volume, area, density and porosity occur. These changes could affect the final quality of dried product and also the effective design of drying equipment. Therefore, this study investigated a novel approach in monitoring and predicting the shrinkage of sweet potato during drying. Drying experiments were conducted at temperatures of 50-70 °C and samples thicknesses of 2-6 mm. The volume and surface area obtained from camera vision, and the perimeter and illuminated area from backscattered optical images were analysed and used to evaluate the shrinkage of sweet potato during drying. The relationship between dimensionless moisture content and shrinkage of sweet potato in terms of volume, surface area, perimeter and illuminated area was found to be linearly correlated. The results also demonstrated that the shrinkage of sweet potato based on computer vision and backscattered optical parameters is affected by the product thickness, drying temperature and drying time. A multilayer perceptron (MLP) artificial neural network with input layer containing three cells, two hidden layers (18 neurons), and five cells for output layer, was used to develop a model that can monitor, control and predict the shrinkage parameters and moisture content of sweet potato slices under different drying conditions. The developed ANN model satisfactorily predicted the shrinkage and dimensionless moisture content of sweet potato with correlation coefficient greater than 0.95. Combined computer vision, laser light backscattering imaging and artificial neural network can be used as a non-destructive, rapid and easily adaptable technique for in-line monitoring, predicting and controlling the shrinkage and moisture changes of food and agricultural crops during drying. © 2017 Society of Chemical Industry. © 2017 Society of Chemical Industry.

Artificial neural network for suppression of banding artifacts in balanced steady-state free precession MRI.

PubMed

Kim, Ki Hwan; Park, Sung-Hong

2017-04-01

The balanced steady-state free precession (bSSFP) MR sequence is frequently used in clinics, but is sensitive to off-resonance effects, which can cause banding artifacts. Often multiple bSSFP datasets are acquired at different phase cycling (PC) angles and then combined in a special way for banding artifact suppression. Many strategies of combining the datasets have been suggested for banding artifact suppression, but there are still limitations in their performance, especially when the number of phase-cycled bSSFP datasets is small. The purpose of this study is to develop a learning-based model to combine the multiple phase-cycled bSSFP datasets for better banding artifact suppression. Multilayer perceptron (MLP) is a feedforward artificial neural network consisting of three layers of input, hidden, and output layers. MLP models were trained by input bSSFP datasets acquired from human brain and knee at 3T, which were separately performed for two and four PC angles. Banding-free bSSFP images were generated by maximum-intensity projection (MIP) of 8 or 12 phase-cycled datasets and were used as targets for training the output layer. The trained MLP models were applied to another brain and knee datasets acquired with different scan parameters and also to multiple phase-cycled bSSFP functional MRI datasets acquired on rat brain at 9.4T, in comparison with the conventional MIP method. Simulations were also performed to validate the MLP approach. Both the simulations and human experiments demonstrated that MLP suppressed banding artifacts significantly, superior to MIP in both banding artifact suppression and SNR efficiency. MLP demonstrated superior performance over MIP for the 9.4T fMRI data as well, which was not used for training the models, while visually preserving the fMRI maps very well. Artificial neural network is a promising technique for combining multiple phase-cycled bSSFP datasets for banding artifact suppression. Copyright © 2016 Elsevier Inc. All rights reserved.

Energy management and multi-layer control of networked microgrids

NASA Astrophysics Data System (ADS)

Zamora, Ramon

Networked microgrids is a group of neighboring microgrids that has ability to interchange power when required in order to increase reliability and resiliency. Networked microgrid can operate in different possible configurations including: islanded microgrid, a grid-connected microgrid without a tie-line converter, a grid-connected microgrid with a tie-line converter, and networked microgrids. These possible configurations and specific characteristics of renewable energy offer challenges in designing control and management algorithms for voltage, frequency and power in all possible operating scenarios. In this work, control algorithm is designed based on large-signal model that enables microgrid to operate in wide range of operating points. A combination between PI controller and feed-forward measured system responses will compensate for the changes in operating points. The control architecture developed in this work has multi-layers and the outer layer is slower than the inner layer in time response. The main responsibility of the designed controls are to regulate voltage magnitude and frequency, as well as output power of the DG(s). These local controls also integrate with a microgrid level energy management system or microgrid central controller (MGCC) for power and energy balance for. the entire microgrid in islanded, grid-connected, or networked microgid mode. The MGCC is responsible to coordinate the lower level controls to have reliable and resilient operation. In case of communication network failure, the decentralized energy management will operate locally and will activate droop control. Simulation results indicate the superiority of designed control algorithms compared to existing ones.

Multiplex lexical networks reveal patterns in early word acquisition in children

NASA Astrophysics Data System (ADS)

Stella, Massimo; Beckage, Nicole M.; Brede, Markus

2017-04-01

Network models of language have provided a way of linking cognitive processes to language structure. However, current approaches focus only on one linguistic relationship at a time, missing the complex multi-relational nature of language. In this work, we overcome this limitation by modelling the mental lexicon of English-speaking toddlers as a multiplex lexical network, i.e. a multi-layered network where N = 529 words/nodes are connected according to four relationship: (i) free association, (ii) feature sharing, (iii) co-occurrence, and (iv) phonological similarity. We investigate the topology of the resulting multiplex and then proceed to evaluate single layers and the full multiplex structure on their ability to predict empirically observed age of acquisition data of English speaking toddlers. We find that the multiplex topology is an important proxy of the cognitive processes of acquisition, capable of capturing emergent lexicon structure. In fact, we show that the multiplex structure is fundamentally more powerful than individual layers in predicting the ordering with which words are acquired. Furthermore, multiplex analysis allows for a quantification of distinct phases of lexical acquisition in early learners: while initially all the multiplex layers contribute to word learning, after about month 23 free associations take the lead in driving word acquisition.

Locating Groundwater Pollution Source using Breakthrough Curve Characteristics and Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Kumar, J.; Jain, A.; Srivastava, R.

2005-12-01

The identification of pollution sources in aquifers is an important area of research not only for the hydrologists but also for the local and Federal agencies and defense organizations. Once the data in terms of pollutant concentration measurements at observation wells become known, it is important to identify the polluting industry in order to implement punitive or remedial measures. Traditionally, hydrologists have relied on the conceptual methods for the identification of groundwater pollution sources. The problem of identification of groundwater pollution sources using the conceptual methods requires a thorough understanding of the groundwater flow and contaminant transport processes and inverse modeling procedures that are highly complex and difficult to implement. Recently, the soft computing techniques, such as artificial neural networks (ANNs) and genetic algorithms, have provided an attractive and easy to implement alternative to solve complex problems efficiently. Some researchers have used ANNs for the identification of pollution sources in aquifers. A major problem with most previous studies using ANNs has been the large size of the neural networks that are needed to model the inverse problem. The breakthrough curves at an observation well may consist of hundreds of concentration measurements, and presenting all of them to the input layer of an ANN not only results in humongous networks but also requires large amount of training and testing data sets to develop the ANN models. This paper presents the results of a study aimed at using certain characteristics of the breakthrough curves and ANNs for determining the distance of the pollution source from a given observation well. Two different neural network models are developed that differ in the manner of characterizing the breakthrough curves. The first ANN model uses five parameters, similar to the synthetic unit hydrograph parameters, to characterize the breakthrough curves. The five parameters employed are peak concentration, time to peak concentration, the widths of the breakthrough curves at 50% and 75% of the peak concentration, and the time base of the breakthrough curve. The second ANN model employs only the first four parameters leaving out the time base. The measurement of breakthrough curve at an observation well involves very high costs in sample collection at suitable time intervals and analysis for various contaminants. The receding portions of the breakthrough curves are normally very long and excluding the time base from modeling would result in considerable cost savings. The feed-forward multi-layer perceptron (MLP) type neural networks trained using the back-propagation algorithm, are employed in this study. The ANN models for the two approaches were developed using simulated data generated for conservative pollutant transport through a homogeneous aquifer. A new approach for ANN training using back-propagation is employed that considers two different error statistics to prevent over-training and under-training of the ANNs. The preliminary results indicate that the ANNs are able to identify the location of the pollution source very efficiently from both the methods of the breakthrough curves characterization.

Multi-responsive hydrogels for drug delivery and tissue engineering applications

PubMed Central

Knipe, Jennifer M.; Peppas, Nicholas A.

2014-01-01

Multi-responsive hydrogels, or ‘intelligent’ hydrogels that respond to more than one environmental stimulus, have demonstrated great utility as a regenerative biomaterial in recent years. They are structured biocompatible materials that provide specific and distinct responses to varied physiological or externally applied stimuli. As evidenced by a burgeoning number of investigators, multi-responsive hydrogels are endowed with tunable, controllable and even biomimetic behavior well-suited for drug delivery and tissue engineering or regenerative growth applications. This article encompasses recent developments and challenges regarding supramolecular, layer-by-layer assembled and covalently cross-linked multi-responsive hydrogel networks and their application to drug delivery and tissue engineering. PMID:26816625

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks

PubMed Central

Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo

2015-01-01

Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns. PMID:26291608

A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.

PubMed

Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo

2015-08-01

Understanding the theoretical foundations of how memories are encoded and retrieved in neural populations is a central challenge in neuroscience. A popular theoretical scenario for modeling memory function is the attractor neural network scenario, whose prototype is the Hopfield model. The model simplicity and the locality of the synaptic update rules come at the cost of a poor storage capacity, compared with the capacity achieved with perceptron learning algorithms. Here, by transforming the perceptron learning rule, we present an online learning rule for a recurrent neural network that achieves near-maximal storage capacity without an explicit supervisory error signal, relying only upon locally accessible information. The fully-connected network consists of excitatory binary neurons with plastic recurrent connections and non-plastic inhibitory feedback stabilizing the network dynamics; the memory patterns to be memorized are presented online as strong afferent currents, producing a bimodal distribution for the neuron synaptic inputs. Synapses corresponding to active inputs are modified as a function of the value of the local fields with respect to three thresholds. Above the highest threshold, and below the lowest threshold, no plasticity occurs. In between these two thresholds, potentiation/depression occurs when the local field is above/below an intermediate threshold. We simulated and analyzed a network of binary neurons implementing this rule and measured its storage capacity for different sizes of the basins of attraction. The storage capacity obtained through numerical simulations is shown to be close to the value predicted by analytical calculations. We also measured the dependence of capacity on the strength of external inputs. Finally, we quantified the statistics of the resulting synaptic connectivity matrix, and found that both the fraction of zero weight synapses and the degree of symmetry of the weight matrix increase with the number of stored patterns.

Research of future network with multi-layer IP address

NASA Astrophysics Data System (ADS)

Li, Guoling; Long, Zhaohua; Wei, Ziqiang

2018-04-01

The shortage of IP addresses and the scalability of routing systems [1] are challenges for the Internet. The idea of dividing existing IP addresses between identities and locations is one of the important research directions. This paper proposed a new decimal network architecture based on IPv9 [11], and decimal network IP address from E.164 principle of traditional telecommunication network, the IP address level, which helps to achieve separation and identification and location of IP address, IP address form a multilayer network structure, routing scalability problem in remission at the same time, to solve the problem of IPv4 address depletion. On the basis of IPv9, a new decimal network architecture is proposed, and the IP address of the decimal network draws on the E.164 principle of the traditional telecommunication network, and the IP addresses are hierarchically divided, which helps to realize the identification and location separation of IP addresses, the formation of multi-layer IP address network structure, while easing the scalability of the routing system to find a way out of IPv4 address exhausted. In addition to modifying DNS [10] simply and adding the function of digital domain, a DDNS [12] is formed. At the same time, a gateway device is added, that is, IPV9 gateway. The original backbone network and user network are unchanged.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Fung, A. K.; Manry, M. T.

1992-01-01

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

Hybrid monitoring scheme for end-to-end performance enhancement of multicast-based real-time media

NASA Astrophysics Data System (ADS)

Park, Ju-Won; Kim, JongWon

2004-10-01

As real-time media applications based on IP multicast networks spread widely, end-to-end QoS (quality of service) provisioning for these applications have become very important. To guarantee the end-to-end QoS of multi-party media applications, it is essential to monitor the time-varying status of both network metrics (i.e., delay, jitter and loss) and system metrics (i.e., CPU and memory utilization). In this paper, targeting the multicast-enabled AG (Access Grid) a next-generation group collaboration tool based on multi-party media services, the applicability of hybrid monitoring scheme that combines active and passive monitoring is investigated. The active monitoring measures network-layer metrics (i.e., network condition) with probe packets while the passive monitoring checks both application-layer metrics (i.e., user traffic condition by analyzing RTCP packets) and system metrics. By comparing these hybrid results, we attempt to pinpoint the causes of performance degradation and explore corresponding reactions to improve the end-to-end performance. The experimental results show that the proposed hybrid monitoring can provide useful information to coordinate the performance improvement of multi-party real-time media applications.

Recursive least-squares learning algorithms for neural networks

NASA Astrophysics Data System (ADS)

Lewis, Paul S.; Hwang, Jenq N.

1990-11-01

This paper presents the development of a pair of recursive least squares (ItLS) algorithms for online training of multilayer perceptrons which are a class of feedforward artificial neural networks. These algorithms incorporate second order information about the training error surface in order to achieve faster learning rates than are possible using first order gradient descent algorithms such as the generalized delta rule. A least squares formulation is derived from a linearization of the training error function. Individual training pattern errors are linearized about the network parameters that were in effect when the pattern was presented. This permits the recursive solution of the least squares approximation either via conventional RLS recursions or by recursive QR decomposition-based techniques. The computational complexity of the update is 0(N2) where N is the number of network parameters. This is due to the estimation of the N x N inverse Hessian matrix. Less computationally intensive approximations of the ilLS algorithms can be easily derived by using only block diagonal elements of this matrix thereby partitioning the learning into independent sets. A simulation example is presented in which a neural network is trained to approximate a two dimensional Gaussian bump. In this example RLS training required an order of magnitude fewer iterations on average (527) than did training with the generalized delta rule (6 1 BACKGROUND Artificial neural networks (ANNs) offer an interesting and potentially useful paradigm for signal processing and pattern recognition. The majority of ANN applications employ the feed-forward multilayer perceptron (MLP) network architecture in which network parameters are " trained" by a supervised learning algorithm employing the generalized delta rule (GDIt) [1 2]. The GDR algorithm approximates a fixed step steepest descent algorithm using derivatives computed by error backpropagatiori. The GDII algorithm is sometimes referred to as the backpropagation algorithm. However in this paper we will use the term backpropagation to refer only to the process of computing error derivatives. While multilayer perceptrons provide a very powerful nonlinear modeling capability GDR training can be very slow and inefficient. In linear adaptive filtering the analog of the GDR algorithm is the leastmean- squares (LMS) algorithm. Steepest descent-based algorithms such as GDR or LMS are first order because they use only first derivative or gradient information about the training error to be minimized. To speed up the training process second order algorithms may be employed that take advantage of second derivative or Hessian matrix information. Second order information can be incorporated into MLP training in different ways. In many applications especially in the area of pattern recognition the training set is finite. In these cases block learning can be applied using standard nonlinear optimization techniques [3 4 5].

Multi-Layer Coating of Ultrathin Polymer Films on Nanoparticles of Alumina by a Plasma Treatment

DTIC Science & Technology

2001-01-01

Proc. Vol. 635 © 2001 Materials Research Society Multi-Layer Coating of Ultrathin Polymer Films on Nanoparticles of Alumina by a Plasma Treatment Donglu...interconnected organic and inorganic networks results in coatings with a very low permeability for gases and liquids. Hybrid materials are very suitable for... materials consist of a clear alcoholic solution that can easily be processed by classical application techniques such as dipping, spraying, or spin coating

Fractal multi-level organisation of human groups in a virtual world.

PubMed

Fuchs, Benedikt; Sornette, Didier; Thurner, Stefan

2014-10-06

Humans are fundamentally social. They form societies which consist of hierarchically layered nested groups of various quality, size, and structure. The anthropologic literature has classified these groups as support cliques, sympathy groups, bands, cognitive groups, tribes, linguistic groups, and so on. Anthropologic data show that, on average, each group consists of approximately three subgroups. However, a general understanding of the structural dependence of groups at different layers is largely missing. We extend these early findings to a very large high-precision large-scale internet-based social network data. We analyse the organisational structure of a complete, multi-relational, large social multiplex network of a human society consisting of about 400,000 odd players of an open-ended massive multiplayer online game for which we know all about their various group memberships at different layers. Remarkably, the online players' society exhibits the same type of structured hierarchical layers as found in hunter-gatherer societies. Our findings suggest that the hierarchical organisation of human society is deeply nested in human psychology.

Fractal multi-level organisation of human groups in a virtual world

PubMed Central

Fuchs, Benedikt; Sornette, Didier; Thurner, Stefan

2014-01-01

Humans are fundamentally social. They form societies which consist of hierarchically layered nested groups of various quality, size, and structure. The anthropologic literature has classified these groups as support cliques, sympathy groups, bands, cognitive groups, tribes, linguistic groups, and so on. Anthropologic data show that, on average, each group consists of approximately three subgroups. However, a general understanding of the structural dependence of groups at different layers is largely missing. We extend these early findings to a very large high-precision large-scale internet-based social network data. We analyse the organisational structure of a complete, multi-relational, large social multiplex network of a human society consisting of about 400,000 odd players of an open-ended massive multiplayer online game for which we know all about their various group memberships at different layers. Remarkably, the online players' society exhibits the same type of structured hierarchical layers as found in hunter-gatherer societies. Our findings suggest that the hierarchical organisation of human society is deeply nested in human psychology. PMID:25283998

Fractal multi-level organisation of human groups in a virtual world

NASA Astrophysics Data System (ADS)

Fuchs, Benedikt; Sornette, Didier; Thurner, Stefan

2014-10-01

Humans are fundamentally social. They form societies which consist of hierarchically layered nested groups of various quality, size, and structure. The anthropologic literature has classified these groups as support cliques, sympathy groups, bands, cognitive groups, tribes, linguistic groups, and so on. Anthropologic data show that, on average, each group consists of approximately three subgroups. However, a general understanding of the structural dependence of groups at different layers is largely missing. We extend these early findings to a very large high-precision large-scale internet-based social network data. We analyse the organisational structure of a complete, multi-relational, large social multiplex network of a human society consisting of about 400,000 odd players of an open-ended massive multiplayer online game for which we know all about their various group memberships at different layers. Remarkably, the online players' society exhibits the same type of structured hierarchical layers as found in hunter-gatherer societies. Our findings suggest that the hierarchical organisation of human society is deeply nested in human psychology.

Neural network modeling and an uncertainty analysis in Bayesian framework: A case study from the KTB borehole site

NASA Astrophysics Data System (ADS)

Maiti, Saumen; Tiwari, Ram Krishna

2010-10-01

A new probabilistic approach based on the concept of Bayesian neural network (BNN) learning theory is proposed for decoding litho-facies boundaries from well-log data. We show that how a multi-layer-perceptron neural network model can be employed in Bayesian framework to classify changes in litho-log successions. The method is then applied to the German Continental Deep Drilling Program (KTB) well-log data for classification and uncertainty estimation in the litho-facies boundaries. In this framework, a posteriori distribution of network parameter is estimated via the principle of Bayesian probabilistic theory, and an objective function is minimized following the scaled conjugate gradient optimization scheme. For the model development, we inflict a suitable criterion, which provides probabilistic information by emulating different combinations of synthetic data. Uncertainty in the relationship between the data and the model space is appropriately taken care by assuming a Gaussian a priori distribution of networks parameters (e.g., synaptic weights and biases). Prior to applying the new method to the real KTB data, we tested the proposed method on synthetic examples to examine the sensitivity of neural network hyperparameters in prediction. Within this framework, we examine stability and efficiency of this new probabilistic approach using different kinds of synthetic data assorted with different level of correlated noise. Our data analysis suggests that the designed network topology based on the Bayesian paradigm is steady up to nearly 40% correlated noise; however, adding more noise (˜50% or more) degrades the results. We perform uncertainty analyses on training, validation, and test data sets with and devoid of intrinsic noise by making the Gaussian approximation of the a posteriori distribution about the peak model. We present a standard deviation error-map at the network output corresponding to the three types of the litho-facies present over the entire litho-section of the KTB. The comparisons of maximum a posteriori geological sections constructed here, based on the maximum a posteriori probability distribution, with the available geological information and the existing geophysical findings suggest that the BNN results reveal some additional finer details in the KTB borehole data at certain depths, which appears to be of some geological significance. We also demonstrate that the proposed BNN approach is superior to the conventional artificial neural network in terms of both avoiding "over-fitting" and aiding uncertainty estimation, which are vital for meaningful interpretation of geophysical records. Our analyses demonstrate that the BNN-based approach renders a robust means for the classification of complex changes in the litho-facies successions and thus could provide a useful guide for understanding the crustal inhomogeneity and the structural discontinuity in many other tectonically complex regions.

Multilayer perceptron neural network-based approach for modeling phycocyanin pigment concentrations: case study from lower Charles River buoy, USA.

PubMed

Heddam, Salim

2016-09-01

This paper proposes multilayer perceptron neural network (MLPNN) to predict phycocyanin (PC) pigment using water quality variables as predictor. In the proposed model, four water quality variables that are water temperature, dissolved oxygen, pH, and specific conductance were selected as the inputs for the MLPNN model, and the PC as the output. To demonstrate the capability and the usefulness of the MLPNN model, a total of 15,849 data measured at 15-min (15 min) intervals of time are used for the development of the model. The data are collected at the lower Charles River buoy, and available from the US Environmental Protection Agency (USEPA). For comparison purposes, a multiple linear regression (MLR) model that was frequently used for predicting water quality variables in previous studies is also built. The performances of the models are evaluated using a set of widely used statistical indices. The performance of the MLPNN and MLR models is compared with the measured data. The obtained results show that (i) the all proposed MLPNN models are more accurate than the MLR models and (ii) the results obtained are very promising and encouraging for the development of phycocyanin-predictive models.

Cardiac abnormality prediction using HMLP network

NASA Astrophysics Data System (ADS)

Adnan, Ja'afar; Ahmad, K. A.; Mat, Muhamad Hadzren; Rizman, Zairi Ismael; Ahmad, Shahril

2018-02-01

Cardiac abnormality often occurs regardless of gender, age and races but depends on the lifestyle. This problem sometimes does not show any symptoms and usually detected once it already critical which lead to a sudden death to the patient. Basically, cardiac abnormality is the irregular electrical signal that generate by the pacemaker of the heart. This paper attempts to develop a program that can detect cardiac abnormality activity through implementation of Hybrid Multilayer Perceptron (HMLP) network. A certain amount of data of the heartbeat signals from the electrocardiogram (ECG) will be used in this project to train the MLP and HMLP network by using Modified Recursive Prediction Error (MRPE) algorithm and to test the network performance.

Simple artificial neural networks that match probability and exploit and explore when confronting a multiarmed bandit.

PubMed

Dawson, Michael R W; Dupuis, Brian; Spetch, Marcia L; Kelly, Debbie M

2009-08-01

The matching law (Herrnstein 1961) states that response rates become proportional to reinforcement rates; this is related to the empirical phenomenon called probability matching (Vulkan 2000). Here, we show that a simple artificial neural network generates responses consistent with probability matching. This behavior was then used to create an operant procedure for network learning. We use the multiarmed bandit (Gittins 1989), a classic problem of choice behavior, to illustrate that operant training balances exploiting the bandit arm expected to pay off most frequently with exploring other arms. Perceptrons provide a medium for relating results from neural networks, genetic algorithms, animal learning, contingency theory, reinforcement learning, and theories of choice.

A hybrid linear/nonlinear training algorithm for feedforward neural networks.

PubMed

McLoone, S; Brown, M D; Irwin, G; Lightbody, A

1998-01-01

This paper presents a new hybrid optimization strategy for training feedforward neural networks. The algorithm combines gradient-based optimization of nonlinear weights with singular value decomposition (SVD) computation of linear weights in one integrated routine. It is described for the multilayer perceptron (MLP) and radial basis function (RBF) networks and then extended to the local model network (LMN), a new feedforward structure in which a global nonlinear model is constructed from a set of locally valid submodels. Simulation results are presented demonstrating the superiority of the new hybrid training scheme compared to second-order gradient methods. It is particularly effective for the LMN architecture where the linear to nonlinear parameter ratio is large.

Artificial and Bayesian Neural Networks

PubMed

Korhani Kangi, Azam; Bahrampour, Abbas

2018-02-26

Introduction and purpose: In recent years the use of neural networks without any premises for investigation of prognosis in analyzing survival data has increased. Artificial neural networks (ANN) use small processors with a continuous network to solve problems inspired by the human brain. Bayesian neural networks (BNN) constitute a neural-based approach to modeling and non-linearization of complex issues using special algorithms and statistical methods. Gastric cancer incidence is the first and third ranking for men and women in Iran, respectively. The aim of the present study was to assess the value of an artificial neural network and a Bayesian neural network for modeling and predicting of probability of gastric cancer patient death. Materials and Methods: In this study, we used information on 339 patients aged from 20 to 90 years old with positive gastric cancer, referred to Afzalipoor and Shahid Bahonar Hospitals in Kerman City from 2001 to 2015. The three layers perceptron neural network (ANN) and the Bayesian neural network (BNN) were used for predicting the probability of mortality using the available data. To investigate differences between the models, sensitivity, specificity, accuracy and the area under receiver operating characteristic curves (AUROCs) were generated. Results: In this study, the sensitivity and specificity of the artificial neural network and Bayesian neural network models were 0.882, 0.903 and 0.954, 0.909, respectively. Prediction accuracy and the area under curve ROC for the two models were 0.891, 0.944 and 0.935, 0.961. The age at diagnosis of gastric cancer was most important for predicting survival, followed by tumor grade, morphology, gender, smoking history, opium consumption, receiving chemotherapy, presence of metastasis, tumor stage, receiving radiotherapy, and being resident in a village. Conclusion: The findings of the present study indicated that the Bayesian neural network is preferable to an artificial neural network for predicting survival of gastric cancer patients in Iran. Creative Commons Attribution License

Video Super-Resolution via Bidirectional Recurrent Convolutional Networks.

PubMed

Huang, Yan; Wang, Wei; Wang, Liang

2018-04-01

Super resolving a low-resolution video, namely video super-resolution (SR), is usually handled by either single-image SR or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video SR. Multi-Frame SR generally extracts motion information, e.g., optical flow, to model the temporal dependency, but often shows high computational cost. Considering that recurrent neural networks (RNNs) can model long-term temporal dependency of video sequences well, we propose a fully convolutional RNN named bidirectional recurrent convolutional network for efficient multi-frame SR. Different from vanilla RNNs, 1) the commonly-used full feedforward and recurrent connections are replaced with weight-sharing convolutional connections. So they can greatly reduce the large number of network parameters and well model the temporal dependency in a finer level, i.e., patch-based rather than frame-based, and 2) connections from input layers at previous timesteps to the current hidden layer are added by 3D feedforward convolutions, which aim to capture discriminate spatio-temporal patterns for short-term fast-varying motions in local adjacent frames. Due to the cheap convolutional operations, our model has a low computational complexity and runs orders of magnitude faster than other multi-frame SR methods. With the powerful temporal dependency modeling, our model can super resolve videos with complex motions and achieve well performance.

Phonological Constraint Induction in a Connectionist Network: Learning OCP-Place Constraints from Data

ERIC Educational Resources Information Center

Alderete, John; Tupper, Paul; Frisch, Stefan A.

2013-01-01

A significant problem in computational language learning is that of inferring the content of well-formedness constraints from input data. In this article, we approach the constraint induction problem as the gradual adjustment of subsymbolic constraints in a connectionist network. In particular, we develop a multi-layer feed-forward network that…

New consensus multivariate models based on PLS and ANN studies of sigma-1 receptor antagonists.

PubMed

Oliveira, Aline A; Lipinski, Célio F; Pereira, Estevão B; Honorio, Kathia M; Oliveira, Patrícia R; Weber, Karen C; Romero, Roseli A F; de Sousa, Alexsandro G; da Silva, Albérico B F

2017-10-02

The treatment of neuropathic pain is very complex and there are few drugs approved for this purpose. Among the studied compounds in the literature, sigma-1 receptor antagonists have shown to be promising. In order to develop QSAR studies applied to the compounds of 1-arylpyrazole derivatives, multivariate analyses have been performed in this work using partial least square (PLS) and artificial neural network (ANN) methods. A PLS model has been obtained and validated with 45 compounds in the training set and 13 compounds in the test set (r 2 training = 0.761, q 2 = 0.656, r 2 test = 0.746, MSE test = 0.132 and MAE test = 0.258). Additionally, multi-layer perceptron ANNs (MLP-ANNs) were employed in order to propose non-linear models trained by gradient descent with momentum backpropagation function. Based on MSE test values, the best MLP-ANN models were combined in a MLP-ANN consensus model (MLP-ANN-CM; r 2 test = 0.824, MSE test = 0.088 and MAE test = 0.197). In the end, a general consensus model (GCM) has been obtained using PLS and MLP-ANN-CM models (r 2 test = 0.811, MSE test = 0.100 and MAE test = 0.218). Besides, the selected descriptors (GGI6, Mor23m, SRW06, H7m, MLOGP, and μ) revealed important features that should be considered when one is planning new compounds of the 1-arylpyrazole class. The multivariate models proposed in this work are definitely a powerful tool for the rational drug design of new compounds for neuropathic pain treatment. Graphical abstract Main scaffold of the 1-arylpyrazole derivatives and the selected descriptors.

Hybrid artificial intelligence approach based on neural fuzzy inference model and metaheuristic optimization for flood susceptibilitgy modeling in a high-frequency tropical cyclone area using GIS

NASA Astrophysics Data System (ADS)

Tien Bui, Dieu; Pradhan, Biswajeet; Nampak, Haleh; Bui, Quang-Thanh; Tran, Quynh-An; Nguyen, Quoc-Phi

2016-09-01

This paper proposes a new artificial intelligence approach based on neural fuzzy inference system and metaheuristic optimization for flood susceptibility modeling, namely MONF. In the new approach, the neural fuzzy inference system was used to create an initial flood susceptibility model and then the model was optimized using two metaheuristic algorithms, Evolutionary Genetic and Particle Swarm Optimization. A high-frequency tropical cyclone area of the Tuong Duong district in Central Vietnam was used as a case study. First, a GIS database for the study area was constructed. The database that includes 76 historical flood inundated areas and ten flood influencing factors was used to develop and validate the proposed model. Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Receiver Operating Characteristic (ROC) curve, and area under the ROC curve (AUC) were used to assess the model performance and its prediction capability. Experimental results showed that the proposed model has high performance on both the training (RMSE = 0.306, MAE = 0.094, AUC = 0.962) and validation dataset (RMSE = 0.362, MAE = 0.130, AUC = 0.911). The usability of the proposed model was evaluated by comparing with those obtained from state-of-the art benchmark soft computing techniques such as J48 Decision Tree, Random Forest, Multi-layer Perceptron Neural Network, Support Vector Machine, and Adaptive Neuro Fuzzy Inference System. The results show that the proposed MONF model outperforms the above benchmark models; we conclude that the MONF model is a new alternative tool that should be used in flood susceptibility mapping. The result in this study is useful for planners and decision makers for sustainable management of flood-prone areas.

Pan evaporation modeling using six different heuristic computing methods in different climates of China

NASA Astrophysics Data System (ADS)

Wang, Lunche; Kisi, Ozgur; Zounemat-Kermani, Mohammad; Li, Hui

2017-01-01

Pan evaporation (Ep) plays important roles in agricultural water resources management. One of the basic challenges is modeling Ep using limited climatic parameters because there are a number of factors affecting the evaporation rate. This study investigated the abilities of six different soft computing methods, multi-layer perceptron (MLP), generalized regression neural network (GRNN), fuzzy genetic (FG), least square support vector machine (LSSVM), multivariate adaptive regression spline (MARS), adaptive neuro-fuzzy inference systems with grid partition (ANFIS-GP), and two regression methods, multiple linear regression (MLR) and Stephens and Stewart model (SS) in predicting monthly Ep. Long-term climatic data at various sites crossing a wide range of climates during 1961-2000 are used for model development and validation. The results showed that the models have different accuracies in different climates and the MLP model performed superior to the other models in predicting monthly Ep at most stations using local input combinations (for example, the MAE (mean absolute errors), RMSE (root mean square errors), and determination coefficient (R2) are 0.314 mm/day, 0.405 mm/day and 0.988, respectively for HEB station), while GRNN model performed better in Tibetan Plateau (MAE, RMSE and R2 are 0.459 mm/day, 0.592 mm/day and 0.932, respectively). The accuracies of above models ranked as: MLP, GRNN, LSSVM, FG, ANFIS-GP, MARS and MLR. The overall results indicated that the soft computing techniques generally performed better than the regression methods, but MLR and SS models can be more preferred at some climatic zones instead of complex nonlinear models, for example, the BJ (Beijing), CQ (Chongqing) and HK (Haikou) stations. Therefore, it can be concluded that Ep could be successfully predicted using above models in hydrological modeling studies.

Altmetric analysis of 2015 dental literature: a cross sectional survey.

PubMed

Kolahi, J; Iranmanesh, P; Khazaei, S

2017-05-12

Introduction To report and analyse Altmetric data of all dental articles and journals in 2015.Methods To identify all 2015 dental articles, PubMed was searched via Altmetric platform using the following query: ("2015/1/1"[PDAT]: "2015/12/31"[PDAT]) AND jsubsetd[text] NOT 2016[PDAT] on November 12, 2016. Altmetric data of all 2015 dental articles and journals were extracted and analysed by Microsoft Office Excel 2016 using descriptive statistics, graphs and trend-line analysis. To find the most important and influential Altmetric factors, multi-layered perceptron artificial neural network was employed using SPSS 22.Results A total of 14,884 dental articles published in 2015 using PubMed database were found, from which 5,153 (34.62%) articles had an Altmetric score. The mean Altmetric score was 2.94 ± 9.2 (95% C.I:2.703.22). Mendeley readers (73.19%), Twitter (21.48%), Facebook walls (3.67%), news outlets (0.69%) and bloggers (0.57%) were the most popular Altmetric data resources. At journal level, 147 dental journals with valid Altmetric data were included in the study. The British Dental Journal had the first rank, followed by Journal of Dental Research, Journal of Clinical Periodontology and Journal of the American Dental Association. Sensitivity analysis showed news outlets, tweeters and scientific bloggers were the most important and influential Altmetric data resources.Discussion In comparison with all science subjects and medical and health sciences, 2015 Altmetric scores in dentistry were very low. Uses of new and emerging scholarly tools such as social media, scientific blogs and post-publication peer-review were not common in the dental science. This negligence may be due to lack of knowledge and attitude. An Altmetric score is dynamic and may fluctuate over time.

Distributed Processing System for Restoration of Electric Power Distribution Network Using Two-Layered Contract Net Protocol

NASA Astrophysics Data System (ADS)

Kodama, Yu; Hamagami, Tomoki

Distributed processing system for restoration of electric power distribution network using two-layered CNP is proposed. The goal of this study is to develop the restoration system which adjusts to the future power network with distributed generators. The state of the art of this study is that the two-layered CNP is applied for the distributed computing environment in practical use. The two-layered CNP has two classes of agents, named field agent and operating agent in the network. In order to avoid conflicts of tasks, operating agent controls privilege for managers to send the task announcement messages in CNP. This technique realizes the coordination between agents which work asynchronously in parallel with others. Moreover, this study implements the distributed processing system using a de-fact standard multi-agent framework, JADE(Java Agent DEvelopment framework). This study conducts the simulation experiments of power distribution network restoration and compares the proposed system with the previous system. We confirmed the results show effectiveness of the proposed system.

Neural networks within multi-core optic fibers

PubMed Central

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-01-01

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks. PMID:27383911

Neural networks within multi-core optic fibers.

PubMed

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-07-07

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.

Recognition and classification of oscillatory patterns of electric brain activity using artificial neural network approach

NASA Astrophysics Data System (ADS)

Pchelintseva, Svetlana V.; Runnova, Anastasia E.; Musatov, Vyacheslav Yu.; Hramov, Alexander E.

2017-03-01

In the paper we study the problem of recognition type of the observed object, depending on the generated pattern and the registered EEG data. EEG recorded at the time of displaying cube Necker characterizes appropriate state of brain activity. As an image we use bistable image Necker cube. Subject selects the type of cube and interpret it either as aleft cube or as the right cube. To solve the problem of recognition, we use artificial neural networks. In our paper to create a classifier we have considered a multilayer perceptron. We examine the structure of the artificial neural network and define cubes recognition accuracy.

Daily Suspended Sediment Discharge Prediction Using Multiple Linear Regression and Artificial Neural Network

NASA Astrophysics Data System (ADS)

Uca; Toriman, Ekhwan; Jaafar, Othman; Maru, Rosmini; Arfan, Amal; Saleh Ahmar, Ansari

2018-01-01

Prediction of suspended sediment discharge in a catchments area is very important because it can be used to evaluation the erosion hazard, management of its water resources, water quality, hydrology project management (dams, reservoirs, and irrigation) and to determine the extent of the damage that occurred in the catchments. Multiple Linear Regression analysis and artificial neural network can be used to predict the amount of daily suspended sediment discharge. Regression analysis using the least square method, whereas artificial neural networks using Radial Basis Function (RBF) and feedforward multilayer perceptron with three learning algorithms namely Levenberg-Marquardt (LM), Scaled Conjugate Descent (SCD) and Broyden-Fletcher-Goldfarb-Shanno Quasi-Newton (BFGS). The number neuron of hidden layer is three to sixteen, while in output layer only one neuron because only one output target. The mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2 ) and coefficient of efficiency (CE) of the multiple linear regression (MLRg) value Model 2 (6 input variable independent) has the lowest the value of MAE and RMSE (0.0000002 and 13.6039) and highest R2 and CE (0.9971 and 0.9971). When compared between LM, SCG and RBF, the BFGS model structure 3-7-1 is the better and more accurate to prediction suspended sediment discharge in Jenderam catchment. The performance value in testing process, MAE and RMSE (13.5769 and 17.9011) is smallest, meanwhile R2 and CE (0.9999 and 0.9998) is the highest if it compared with the another BFGS Quasi-Newton model (6-3-1, 9-10-1 and 12-12-1). Based on the performance statistics value, MLRg, LM, SCG, BFGS and RBF suitable and accurately for prediction by modeling the non-linear complex behavior of suspended sediment responses to rainfall, water depth and discharge. The comparison between artificial neural network (ANN) and MLRg, the MLRg Model 2 accurately for to prediction suspended sediment discharge (kg/day) in Jenderan catchment area.

Robust, Multi-layered Plan Execution and Revision for Operation of a Network of Communication Antennas

NASA Technical Reports Server (NTRS)

Chien, S. A.; Hill, R. W., Jr.; Govindjee, A.; Wang, X.; Estlin, T.; Griesel, M. A.; Lam, R.; Fayyad, K. V.

1996-01-01

This paper describes a hierarchical scheduling, planning, control, and execution monitoring architecture for automating operations of a worldwide network of communications antennas. The purpose of this paper is to describe an architecture for automating the process of capturing spacecraft data.

Efficient evaluation of wireless real-time control networks.

PubMed

Horvath, Peter; Yampolskiy, Mark; Koutsoukos, Xenofon

2015-02-11

In this paper, we present a system simulation framework for the design and performance evaluation of complex wireless cyber-physical systems. We describe the simulator architecture and the specific developments that are required to simulate cyber-physical systems relying on multi-channel, multihop mesh networks. We introduce realistic and efficient physical layer models and a system simulation methodology, which provides statistically significant performance evaluation results with low computational complexity. The capabilities of the proposed framework are illustrated in the example of WirelessHART, a centralized, real-time, multi-hop mesh network designed for industrial control and monitor applications.

Angular relational signature-based chest radiograph image view classification.

PubMed

Santosh, K C; Wendling, Laurent

2018-01-22

In a computer-aided diagnosis (CAD) system, especially for chest radiograph or chest X-ray (CXR) screening, CXR image view information is required. Automatically separating CXR image view, frontal and lateral can ease subsequent CXR screening process, since the techniques may not equally work for both views. We present a novel technique to classify frontal and lateral CXR images, where we introduce angular relational signature through force histogram to extract features and apply three different state-of-the-art classifiers: multi-layer perceptron, random forest, and support vector machine to make a decision. We validated our fully automatic technique on a set of 8100 images hosted by the U.S. National Library of Medicine (NLM), National Institutes of Health (NIH), and achieved an accuracy close to 100%. Our method outperforms the state-of-the-art methods in terms of processing time (less than or close to 2 s for the whole test data) while the accuracies can be compared, and therefore, it justifies its practicality. Graphical Abstract Interpreting chest X-ray (CXR) through the angular relational signature.

Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task

PubMed Central

2017-01-01

Neural networks with a single plastic layer employing reward modulated spike time dependent plasticity (STDP) are capable of learning simple foraging tasks. Here we demonstrate advanced pattern discrimination and continuous learning in a network of spiking neurons with multiple plastic layers. The network utilized both reward modulated and non-reward modulated STDP and implemented multiple mechanisms for homeostatic regulation of synaptic efficacy, including heterosynaptic plasticity, gain control, output balancing, activity normalization of rewarded STDP and hard limits on synaptic strength. We found that addition of a hidden layer of neurons employing non-rewarded STDP created neurons that responded to the specific combinations of inputs and thus performed basic classification of the input patterns. When combined with a following layer of neurons implementing rewarded STDP, the network was able to learn, despite the absence of labeled training data, discrimination between rewarding patterns and the patterns designated as punishing. Synaptic noise allowed for trial-and-error learning that helped to identify the goal-oriented strategies which were effective in task solving. The study predicts a critical set of properties of the spiking neuronal network with STDP that was sufficient to solve a complex foraging task involving pattern classification and decision making. PMID:28961245

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

NASA Astrophysics Data System (ADS)

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.

3D MI-DRAGON: new model for the reconstruction of US FDA drug- target network and theoretical-experimental studies of inhibitors of rasagiline derivatives for AChE.

PubMed

Prado-Prado, Francisco; García-Mera, Xerardo; Escobar, Manuel; Alonso, Nerea; Caamaño, Olga; Yañez, Matilde; González-Díaz, Humberto

2012-01-01

The number of neurodegenerative diseases has been increasing in recent years. Many of the drug candidates to be used in the treatment of neurodegenerative diseases present specific 3D structural features. An important protein in this sense is the acetylcholinesterase (AChE), which is the target of many Alzheimer's dementia drugs. Consequently, the prediction of Drug-Protein Interactions (DPIs/nDPIs) between new drug candidates and specific 3D structure and targets is of major importance. To this end, we can use Quantitative Structure-Activity Relationships (QSAR) models to carry out a rational DPIs prediction. Unfortunately, many previous QSAR models developed to predict DPIs take into consideration only 2D structural information and codify the activity against only one target. To solve this problem we can develop some 3D multi-target QSAR (3D mt-QSAR) models. In this study, using the 3D MI-DRAGON technique, we have introduced a new predictor for DPIs based on two different well-known software. We have used the MARCH-INSIDE (MI) and DRAGON software to calculate 3D structural parameters for drugs and targets respectively. Both classes of 3D parameters were used as input to train Artificial Neuronal Network (ANN) algorithms using as benchmark dataset the complex network (CN) made up of all DPIs between US FDA approved drugs and their targets. The entire dataset was downloaded from the DrugBank database. The best 3D mt-QSAR predictor found was an ANN of Multi-Layer Perceptron-type (MLP) with profile MLP 37:37-24-1:1. This MLP classifies correctly 274 out of 321 DPIs (Sensitivity = 85.35%) and 1041 out of 1190 nDPIs (Specificity = 87.48%), corresponding to training Accuracy = 87.03%. We have validated the model with external predicting series with Sensitivity = 84.16% (542/644 DPIs; Specificity = 87.51% (2039/2330 nDPIs) and Accuracy = 86.78%. The new CNs of DPIs reconstructed from US FDA can be used to explore large DPI databases in order to discover both new drugs and/or targets. We have carried out some theoretical-experimental studies to illustrate the practical use of 3D MI-DRAGON. First, we have reported the prediction and pharmacological assay of 22 different rasagiline derivatives with possible AChE inhibitory activity. In this work, we have reviewed different computational studies on Drug- Protein models. First, we have reviewed 10 studies on DP computational models. Next, we have reviewed 2D QSAR, 3D QSAR, CoMFA, CoMSIA and Docking with different compounds to find Drug-Protein QSAR models. Last, we have developped a 3D multi-target QSAR (3D mt-QSAR) models for the prediction of the activity of new compounds against different targets or the discovery of new targets.

Distributed Multihoming Routing Method by Crossing Control MIPv6 with SCTP

NASA Astrophysics Data System (ADS)

Shi, Hongbo; Hamagami, Tomoki

There are various wireless communication technologies, such as 3G, WiFi, used widely in the world. Recently, not only the laptop but also the smart phones can be equipped with multiple wireless devices. The communication terminals which are implemented with multiple interfaces are usually called multi-homed nodes. Meanwhile, a multi-homed node with multiple interfaces can also be regarded as multiple single-homed nodes. For example, when a person who is using smart phone and laptop to connect to the Internet concurrently, we may regard the person as a multi-homed node in the Internet. This paper proposes a new routing method, Multi-homed Mobile Cross-layer Control to handle multi-homed mobile nodes. Our suggestion can provide a distributed end-to-end routing method for handling the communications among multi-homed nodes at the fundamental network layer.

Hazard Interactions and Interaction Networks (Cascades) within Multi-Hazard Methodologies

NASA Astrophysics Data System (ADS)

Gill, Joel; Malamud, Bruce D.

2016-04-01

Here we combine research and commentary to reinforce the importance of integrating hazard interactions and interaction networks (cascades) into multi-hazard methodologies. We present a synthesis of the differences between 'multi-layer single hazard' approaches and 'multi-hazard' approaches that integrate such interactions. This synthesis suggests that ignoring interactions could distort management priorities, increase vulnerability to other spatially relevant hazards or underestimate disaster risk. We proceed to present an enhanced multi-hazard framework, through the following steps: (i) describe and define three groups (natural hazards, anthropogenic processes and technological hazards/disasters) as relevant components of a multi-hazard environment; (ii) outline three types of interaction relationship (triggering, increased probability, and catalysis/impedance); and (iii) assess the importance of networks of interactions (cascades) through case-study examples (based on literature, field observations and semi-structured interviews). We further propose visualisation frameworks to represent these networks of interactions. Our approach reinforces the importance of integrating interactions between natural hazards, anthropogenic processes and technological hazards/disasters into enhanced multi-hazard methodologies. Multi-hazard approaches support the holistic assessment of hazard potential, and consequently disaster risk. We conclude by describing three ways by which understanding networks of interactions contributes to the theoretical and practical understanding of hazards, disaster risk reduction and Earth system management. Understanding interactions and interaction networks helps us to better (i) model the observed reality of disaster events, (ii) constrain potential changes in physical and social vulnerability between successive hazards, and (iii) prioritise resource allocation for mitigation and disaster risk reduction.

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease

PubMed Central

Yelshyna, Darya; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics. PMID:28074090

Application of Machine Learning in Postural Control Kinematics for the Diagnosis of Alzheimer's Disease.

PubMed

Costa, Luís; Gago, Miguel F; Yelshyna, Darya; Ferreira, Jaime; David Silva, Hélder; Rocha, Luís; Sousa, Nuno; Bicho, Estela

2016-01-01

The use of wearable devices to study gait and postural control is a growing field on neurodegenerative disorders such as Alzheimer's disease (AD). In this paper, we investigate if machine-learning classifiers offer the discriminative power for the diagnosis of AD based on postural control kinematics. We compared Support Vector Machines (SVMs), Multiple Layer Perceptrons (MLPs), Radial Basis Function Neural Networks (RBNs), and Deep Belief Networks (DBNs) on 72 participants (36 AD patients and 36 healthy subjects) exposed to seven increasingly difficult postural tasks. The decisional space was composed of 18 kinematic variables (adjusted for age, education, height, and weight), with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top ranked in an error incremental analysis. Classification results were based on threefold cross validation of 50 independent and randomized runs sets: training (50%), test (40%), and validation (10%). Having a decisional space relying solely on postural kinematics, accuracy of AD diagnosis ranged from 71.7 to 86.1%. Adding the MoCA variable, the accuracy ranged between 91 and 96.6%. MLP classifier achieved top performance in both decisional spaces. Having comprehended the interdynamic interaction between postural stability and cognitive performance, our results endorse machine-learning models as a useful tool for computer-aided diagnosis of AD based on postural control kinematics.

GenSo-EWS: a novel neural-fuzzy based early warning system for predicting bank failures.

PubMed

Tung, W L; Quek, C; Cheng, P

2004-05-01

Bank failure prediction is an important issue for the regulators of the banking industries. The collapse and failure of a bank could trigger an adverse financial repercussion and generate negative impacts such as a massive bail out cost for the failing bank and loss of confidence from the investors and depositors. Very often, bank failures are due to financial distress. Hence, it is desirable to have an early warning system (EWS) that identifies potential bank failure or high-risk banks through the traits of financial distress. Various traditional statistical models have been employed to study bank failures [J Finance 1 (1975) 21; J Banking Finance 1 (1977) 249; J Banking Finance 10 (1986) 511; J Banking Finance 19 (1995) 1073]. However, these models do not have the capability to identify the characteristics of financial distress and thus function as black boxes. This paper proposes the use of a new neural fuzzy system [Foundations of neuro-fuzzy systems, 1997], namely the Generic Self-organising Fuzzy Neural Network (GenSoFNN) [IEEE Trans Neural Networks 13 (2002c) 1075] based on the compositional rule of inference (CRI) [Commun ACM 37 (1975) 77], as an alternative to predict banking failure. The CRI based GenSoFNN neural fuzzy network, henceforth denoted as GenSoFNN-CRI(S), functions as an EWS and is able to identify the inherent traits of financial distress based on financial covariates (features) derived from publicly available financial statements. The interaction between the selected features is captured in the form of highly intuitive IF-THEN fuzzy rules. Such easily comprehensible rules provide insights into the possible characteristics of financial distress and form the knowledge base for a highly desired EWS that aids bank regulation. The performance of the GenSoFNN-CRI(S) network is subsequently benchmarked against that of the Cox's proportional hazards model [J Banking Finance 10 (1986) 511; J Banking Finance 19 (1995) 1073], the multi-layered perceptron (MLP) and the modified cerebellar model articulation controller (MCMAC) [IEEE Trans Syst Man Cybern: Part B 30 (2000) 491] in predicting bank failures based on a population of 3635 US banks observed over a 21 years period. Three sets of experiments are performed-bank failure classification based on the last available financial record and prediction using financial records one and two years prior to the last available financial statements. The performance of the GenSoFNN-CRI(S) network as a bank failure classification and EWS is encouraging.

Detection of different states of sleep in the rodents by the means of artificial neural networks

NASA Astrophysics Data System (ADS)

Musatov, Viacheslav; Dykin, Viacheslav; Pitsik, Elena; Pisarchik, Alexander

2018-04-01

This paper considers the possibility of classification of electroencephalogram (EEG) and electromyogram (EMG) signals corresponding to different phases of sleep and wakefulness of mice by the means of artificial neural networks. A feed-forward artificial neural network based on multilayer perceptron was created and trained on the data of one of the rodents. The trained network was used to read and classify the EEG and EMG data corresponding to different phases of sleep and wakefulness of the same mouse and other mouse. The results show a good recognition quality of all phases for the rodent on which the training was conducted (80-99%) and acceptable recognition quality for the data collected from the same mouse after a stroke.

Power plant fault detection using artificial neural network

NASA Astrophysics Data System (ADS)

Thanakodi, Suresh; Nazar, Nazatul Shiema Moh; Joini, Nur Fazriana; Hidzir, Hidzrin Dayana Mohd; Awira, Mohammad Zulfikar Khairul

2018-02-01

The fault that commonly occurs in power plants is due to various factors that affect the system outage. There are many types of faults in power plants such as single line to ground fault, double line to ground fault, and line to line fault. The primary aim of this paper is to diagnose the fault in 14 buses power plants by using an Artificial Neural Network (ANN). The Multilayered Perceptron Network (MLP) that detection trained utilized the offline training methods such as Gradient Descent Backpropagation (GDBP), Levenberg-Marquardt (LM), and Bayesian Regularization (BR). The best method is used to build the Graphical User Interface (GUI). The modelling of 14 buses power plant, network training, and GUI used the MATLAB software.

Inversion of parameters for semiarid regions by a neural network

NASA Technical Reports Server (NTRS)

Zurk, Lisa M.; Davis, Daniel; Njoku, Eni G.; Tsang, Leung; Hwang, Jenq-Neng

1992-01-01

Microwave brightness temperatures obtained from a passive radiative transfer model are inverted through use of a neural network. The model is applicable to semiarid regions and produces dual-polarized brightness temperatures for 6.6-, 10.7-, and 37-GHz frequencies. A range of temperatures is generated by varying three geophysical parameters over acceptable ranges: soil moisture, vegetation moisture, and soil temperature. A multilayered perceptron (MLP) neural network is trained with a subset of the generated temperatures, and the remaining temperatures are inverted using a backpropagation method. Several synthetic terrains are devised and inverted by the network under local constraints. All the inversions show good agreement with the original geophysical parameters, falling within 5 percent of the actual value of the parameter range.

Application of two neural network paradigms to the study of voluntary employee turnover.

PubMed

Somers, M J

1999-04-01

Two neural network paradigms--multilayer perceptron and learning vector quantization--were used to study voluntary employee turnover with a sample of 577 hospital employees. The objectives of the study were twofold. The 1st was to assess whether neural computing techniques offered greater predictive accuracy than did conventional turnover methodologies. The 2nd was to explore whether computer models of turnover based on neural network technologies offered new insights into turnover processes. When compared with logistic regression analysis, both neural network paradigms provided considerably more accurate predictions of turnover behavior, particularly with respect to the correct classification of leavers. In addition, these neural network paradigms captured nonlinear relationships that are relevant for theory development. Results are discussed in terms of their implications for future research.

Adaptive nonlinear polynomial neural networks for control of boundary layer/structural interaction

NASA Technical Reports Server (NTRS)

Parker, B. Eugene, Jr.; Cellucci, Richard L.; Abbott, Dean W.; Barron, Roger L.; Jordan, Paul R., III; Poor, H. Vincent

1993-01-01

The acoustic pressures developed in a boundary layer can interact with an aircraft panel to induce significant vibration in the panel. Such vibration is undesirable due to the aerodynamic drag and structure-borne cabin noises that result. The overall objective of this work is to develop effective and practical feedback control strategies for actively reducing this flow-induced structural vibration. This report describes the results of initial evaluations using polynomial, neural network-based, feedback control to reduce flow induced vibration in aircraft panels due to turbulent boundary layer/structural interaction. Computer simulations are used to develop and analyze feedback control strategies to reduce vibration in a beam as a first step. The key differences between this work and that going on elsewhere are as follows: that turbulent and transitional boundary layers represent broadband excitation and thus present a more complex stochastic control scenario than that of narrow band (e.g., laminar boundary layer) excitation; and secondly, that the proposed controller structures are adaptive nonlinear infinite impulse response (IIR) polynomial neural network, as opposed to the traditional adaptive linear finite impulse response (FIR) filters used in most studies to date. The controllers implemented in this study achieved vibration attenuation of 27 to 60 dB depending on the type of boundary layer established by laminar, turbulent, and intermittent laminar-to-turbulent transitional flows. Application of multi-input, multi-output, adaptive, nonlinear feedback control of vibration in aircraft panels based on polynomial neural networks appears to be feasible today. Plans are outlined for Phase 2 of this study, which will include extending the theoretical investigation conducted in Phase 2 and verifying the results in a series of laboratory experiments involving both bum and plate models.

A fiber optic tactical voice/data network based on FDDI

NASA Technical Reports Server (NTRS)

Bergman, L. A.; Hartmayer, R.; Marelid, S.; Wu, W. H.; Edgar, G.; Cassell, P.; Mancini, R.; Kiernicki, J.; Paul, L. J.; Jeng, J.

1988-01-01

An asynchronous high-speed fiber optic local area network is described that supports ordinary data packet traffic simultaneously with synchronous Tl voice traffic over a common FDDI token ring channel. A voice interface module was developed that parses, buffers, and resynchronizes the voice data to the packet network. The technique is general, however, and can be applied to any deterministic class of networks, including multi-tier backbones. A conventional single token access protocol was employed at the lowest layer, with fixed packet sizes for voice and variable for data. In addition, the higher layer packet data protocols are allowed to operate independently of those for the voice thereby permitting great flexibility in reconfiguring the network. Voice call setup and switching functions were performed external to the network with PABX equipment.

Reliability analysis of C-130 turboprop engine components using artificial neural network

NASA Astrophysics Data System (ADS)

Qattan, Nizar A.

In this study, we predict the failure rate of Lockheed C-130 Engine Turbine. More than thirty years of local operational field data were used for failure rate prediction and validation. The Weibull regression model and the Artificial Neural Network model including (feed-forward back-propagation, radial basis neural network, and multilayer perceptron neural network model); will be utilized to perform this study. For this purpose, the thesis will be divided into five major parts. First part deals with Weibull regression model to predict the turbine general failure rate, and the rate of failures that require overhaul maintenance. The second part will cover the Artificial Neural Network (ANN) model utilizing the feed-forward back-propagation algorithm as a learning rule. The MATLAB package will be used in order to build and design a code to simulate the given data, the inputs to the neural network are the independent variables, the output is the general failure rate of the turbine, and the failures which required overhaul maintenance. In the third part we predict the general failure rate of the turbine and the failures which require overhaul maintenance, using radial basis neural network model on MATLAB tool box. In the fourth part we compare the predictions of the feed-forward back-propagation model, with that of Weibull regression model, and radial basis neural network model. The results show that the failure rate predicted by the feed-forward back-propagation artificial neural network model is closer in agreement with radial basis neural network model compared with the actual field-data, than the failure rate predicted by the Weibull model. By the end of the study, we forecast the general failure rate of the Lockheed C-130 Engine Turbine, the failures which required overhaul maintenance and six categorical failures using multilayer perceptron neural network (MLP) model on DTREG commercial software. The results also give an insight into the reliability of the engine turbine under actual operating conditions, which can be used by aircraft operators for assessing system and component failures and customizing the maintenance programs recommended by the manufacturer.

Watchdog Sensor Network with Multi-Stage RF Signal Identification and Cooperative Intrusion Detection

DTIC Science & Technology

2012-03-01

detection and physical layer authentication in mobile Ad Hoc networks and wireless sensor networks (WSNs) have been investigated. Résume Le rapport...IEEE 802.16 d and e (WiMAX); (b) IEEE 802.11 (Wi-Fi) family of a, b, g, n, and s (c) Sensor networks based on IEEE 802.15.4: Wireless USB, Bluetooth... sensor network are investigated for standard compatible wireless signals. The proposed signal existence detection and identification process consists

A data-driven multi-model methodology with deep feature selection for short-term wind forecasting

DOE Office of Scientific and Technical Information (OSTI.GOV)

Feng, Cong; Cui, Mingjian; Hodge, Bri-Mathias

With the growing wind penetration into the power system worldwide, improving wind power forecasting accuracy is becoming increasingly important to ensure continued economic and reliable power system operations. In this paper, a data-driven multi-model wind forecasting methodology is developed with a two-layer ensemble machine learning technique. The first layer is composed of multiple machine learning models that generate individual forecasts. A deep feature selection framework is developed to determine the most suitable inputs to the first layer machine learning models. Then, a blending algorithm is applied in the second layer to create an ensemble of the forecasts produced by firstmore » layer models and generate both deterministic and probabilistic forecasts. This two-layer model seeks to utilize the statistically different characteristics of each machine learning algorithm. A number of machine learning algorithms are selected and compared in both layers. This developed multi-model wind forecasting methodology is compared to several benchmarks. The effectiveness of the proposed methodology is evaluated to provide 1-hour-ahead wind speed forecasting at seven locations of the Surface Radiation network. Numerical results show that comparing to the single-algorithm models, the developed multi-model framework with deep feature selection procedure has improved the forecasting accuracy by up to 30%.« less

Conic section function neural network circuitry for offline signature recognition.

PubMed

Erkmen, Burcu; Kahraman, Nihan; Vural, Revna A; Yildirim, Tulay

2010-04-01

In this brief, conic section function neural network (CSFNN) circuitry was designed for offline signature recognition. CSFNN is a unified framework for multilayer perceptron (MLP) and radial basis function (RBF) networks to make simultaneous use of advantages of both. The CSFNN circuitry architecture was developed using a mixed mode circuit implementation. The designed circuit system is problem independent. Hence, the general purpose neural network circuit system could be applied to various pattern recognition problems with different network sizes on condition with the maximum network size of 16-16-8. In this brief, CSFNN circuitry system has been applied to two different signature recognition problems. CSFNN circuitry was trained with chip-in-the-loop learning technique in order to compensate typical analog process variations. CSFNN hardware achieved highly comparable computational performances with CSFNN software for nonlinear signature recognition problems.

Network architecture in a converged optical + IP network

NASA Astrophysics Data System (ADS)

Wakim, Walid; Zottmann, Harald

2012-01-01

As demands on Provider Networks continue to grow at exponential rates, providers are forced to evaluate how to continue to grow the network while increasing service velocity, enhancing resiliency while decreasing the total cost of ownership (TCO). The bandwidth growth that networks are experiencing is in the form packet based multimedia services such as video, video conferencing, gaming, etc... mixed with Over the Top (OTT) content providers such as Netflix, and the customer's expectations that best effort is not enough you end up with a situation that forces the provider to analyze how to gain more out of the network with less cost. In this paper we will discuss changes in the network that are driving us to a tighter integration between packet and optical layers and how to improve on today's multi - layer inefficiencies to drive down network TCO and provide for a fully integrated and dynamic network that will decrease time to revenue.

Multi-Level and Multi-Scale Feature Aggregation Using Pretrained Convolutional Neural Networks for Music Auto-Tagging

NASA Astrophysics Data System (ADS)

Lee, Jongpil; Nam, Juhan

2017-08-01

Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pre-trained convolutional networks separately and aggregate them altogether given a long audio clip. Finally, we put them into fully-connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms previous state-of-the-arts on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Application-oriented programming model for sensor networks embedded in the human body.

PubMed

Barbosa, Talles M G de A; Sene, Iwens G; da Rocha, Adson F; Nascimento, Fransisco A de O; Carvalho, Hervaldo S; Camapum, Juliana F

2006-01-01

This work presents a new programming model for sensor networks embedded in the human body which is based on the concept of multi-programming application-oriented software. This model was conceived with a top-down approach of four layers and its main goal is to allow the healthcare professionals to program and to reconfigure the network locally or by the Internet. In order to evaluate this hypothesis, a benchmarking was executed in order to allow the assessment of the mean time spent in the programming of a multi-functional sensor node used for the measurement and transmission of the electrocardiogram.

Automated system for characterization and classification of malaria-infected stages using light microscopic images of thin blood smears.

PubMed

Das, D K; Maiti, A K; Chakraborty, C

2015-03-01

In this paper, we propose a comprehensive image characterization cum classification framework for malaria-infected stage detection using microscopic images of thin blood smears. The methodology mainly includes microscopic imaging of Leishman stained blood slides, noise reduction and illumination correction, erythrocyte segmentation, feature selection followed by machine classification. Amongst three-image segmentation algorithms (namely, rule-based, Chan-Vese-based and marker-controlled watershed methods), marker-controlled watershed technique provides better boundary detection of erythrocytes specially in overlapping situations. Microscopic features at intensity, texture and morphology levels are extracted to discriminate infected and noninfected erythrocytes. In order to achieve subgroup of potential features, feature selection techniques, namely, F-statistic and information gain criteria are considered here for ranking. Finally, five different classifiers, namely, Naive Bayes, multilayer perceptron neural network, logistic regression, classification and regression tree (CART), RBF neural network have been trained and tested by 888 erythrocytes (infected and noninfected) for each features' subset. Performance evaluation of the proposed methodology shows that multilayer perceptron network provides higher accuracy for malaria-infected erythrocytes recognition and infected stage classification. Results show that top 90 features ranked by F-statistic (specificity: 98.64%, sensitivity: 100%, PPV: 99.73% and overall accuracy: 96.84%) and top 60 features ranked by information gain provides better results (specificity: 97.29%, sensitivity: 100%, PPV: 99.46% and overall accuracy: 96.73%) for malaria-infected stage classification. © 2014 The Authors Journal of Microscopy © 2014 Royal Microscopical Society.

Effect of noise in intelligent cellular decision making.

PubMed

Bates, Russell; Blyuss, Oleg; Alsaedi, Ahmed; Zaikin, Alexey

2015-01-01

Similar to intelligent multicellular neural networks controlling human brains, even single cells, surprisingly, are able to make intelligent decisions to classify several external stimuli or to associate them. This happens because of the fact that gene regulatory networks can perform as perceptrons, simple intelligent schemes known from studies on Artificial Intelligence. We study the role of genetic noise in intelligent decision making at the genetic level and show that noise can play a constructive role helping cells to make a proper decision. We show this using the example of a simple genetic classifier able to classify two external stimuli.

Learning relevant features of data with multi-scale tensor networks

NASA Astrophysics Data System (ADS)

Miles Stoudenmire, E.

2018-07-01

Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorithm, then optimizing just the top layer for supervised classification of the MNIST and fashion MNIST data sets gives very good results. We also discuss mixing a prior guess for supervised weights together with an unsupervised representation of the data, yielding a smaller number of features nevertheless able to give good performance.

2D MI-DRAGON: a new predictor for protein-ligands interactions and theoretic-experimental studies of US FDA drug-target network, oxoisoaporphine inhibitors for MAO-A and human parasite proteins.

PubMed

Prado-Prado, Francisco; García-Mera, Xerardo; Escobar, Manuel; Sobarzo-Sánchez, Eduardo; Yañez, Matilde; Riera-Fernandez, Pablo; González-Díaz, Humberto

2011-12-01

There are many pairs of possible Drug-Proteins Interactions that may take place or not (DPIs/nDPIs) between drugs with high affinity/non-affinity for different proteins. This fact makes expensive in terms of time and resources, for instance, the determination of all possible ligands-protein interactions for a single drug. In this sense, we can use Quantitative Structure-Activity Relationships (QSAR) models to carry out rational DPIs prediction. Unfortunately, almost all QSAR models predict activity against only one target. To solve this problem we can develop multi-target QSAR (mt-QSAR) models. In this work, we introduce the technique 2D MI-DRAGON a new predictor for DPIs based on two different well-known software. We use the software MARCH-INSIDE (MI) to calculate 3D structural parameters for targets and the software DRAGON was used to calculated 2D molecular descriptors all drugs showing known DPIs present in the Drug Bank (US FDA benchmark dataset). Both classes of parameters were used as input of different Artificial Neural Network (ANN) algorithms to seek an accurate non-linear mt-QSAR predictor. The best ANN model found is a Multi-Layer Perceptron (MLP) with profile MLP 21:21-31-1:1. This MLP classifies correctly 303 out of 339 DPIs (Sensitivity = 89.38%) and 480 out of 510 nDPIs (Specificity = 94.12%), corresponding to training Accuracy = 92.23%. The validation of the model was carried out by means of external predicting series with Sensitivity = 92.18% (625/678 DPIs; Specificity = 90.12% (730/780 nDPIs) and Accuracy = 91.06%. 2D MI-DRAGON offers a good opportunity for fast-track calculation of all possible DPIs of one drug enabling us to re-construct large drug-target or DPIs Complex Networks (CNs). For instance, we reconstructed the CN of the US FDA benchmark dataset with 855 nodes 519 drugs+336 targets). We predicted CN with similar topology (observed and predicted values of average distance are equal to 6.7 vs. 6.6). These CNs can be used to explore large DPIs databases in order to discover both new drugs and/or targets. Finally, we illustrated in one theoretic-experimental study the practical use of 2D MI-DRAGON. We reported the prediction, synthesis, and pharmacological assay of 10 different oxoisoaporphines with MAO-A inhibitory activity. The more active compound OXO5 presented IC(50) = 0.00083 μM, notably better than the control drug Clorgyline. Copyright © 2011 Elsevier Masson SAS. All rights reserved.

Flexible and scalable wavelength multicast of coherent optical OFDM with tolerance against pump phase-noise using reconfigurable coherent multi-carrier pumping.

PubMed

Lu, Guo-Wei; Bo, Tianwai; Sakamoto, Takahide; Yamamoto, Naokatsu; Chan, Calvin Chun-Kit

2016-10-03

Recently the ever-growing demand for dynamic and high-capacity services in optical networks has resulted in new challenges that require improved network agility and flexibility in order for network resources to become more "consumable" and dynamic, or elastic, in response to requests from higher network layers. Flexible and scalable wavelength conversion or multicast is one of the most important technologies needed for developing agility in the physical layer. This paper will investigate how, using a reconfigurable coherent multi-carrier as a pump, the multicast scalability and the flexibility in wavelength allocation of the converted signals can be effectively improved. Moreover, the coherence in the multiple carriers prevents the phase noise transformation from the local pump to the converted signals, which is imperative for the phase-noise-sensitive multi-level single- or multi-carrier modulated signal. To verify the feasibility of the proposed scheme, we experimentally demonstrate the wavelength multicast of coherent optical orthogonal frequency division multiplexing (CO-OFDM) signals using a reconfigurable coherent multi-carrier pump, showing flexibility in wavelength allocation, scalability in multicast, and tolerance against pump phase noise. Less than 0.5 dB and 1.8 dB power penalties at a bit-error rate (BER) of 10^-3 are obtained for the converted CO-OFDM-quadrature phase-shift keying (QPSK) and CO-OFDM-16-ary quadrature amplitude modulation (16QAM) signals, respectively, even when using a distributed feedback laser (DFB) as a pump source. In contrast, with a free-running pumping scheme, the phase noise from DFB pumps severely deteriorates the CO-OFDM signals, resulting in a visible error-floor at a BER of 10^-2 in the converted CO-OFDM-16QAM signals.

Implementation of a spike-based perceptron learning rule using TiO2-x memristors.

PubMed

Mostafa, Hesham; Khiat, Ali; Serb, Alexander; Mayr, Christian G; Indiveri, Giacomo; Prodromakis, Themis

2015-01-01

Synaptic plasticity plays a crucial role in allowing neural networks to learn and adapt to various input environments. Neuromorphic systems need to implement plastic synapses to obtain basic "cognitive" capabilities such as learning. One promising and scalable approach for implementing neuromorphic synapses is to use nano-scale memristors as synaptic elements. In this paper we propose a hybrid CMOS-memristor system comprising CMOS neurons interconnected through TiO2-x memristors, and spike-based learning circuits that modulate the conductance of the memristive synapse elements according to a spike-based Perceptron plasticity rule. We highlight a number of advantages for using this spike-based plasticity rule as compared to other forms of spike timing dependent plasticity (STDP) rules. We provide experimental proof-of-concept results with two silicon neurons connected through a memristive synapse that show how the CMOS plasticity circuits can induce stable changes in memristor conductances, giving rise to increased synaptic strength after a potentiation episode and to decreased strength after a depression episode.

Multilayer Perceptron for Robust Nonlinear Interval Regression Analysis Using Genetic Algorithms

PubMed Central

2014-01-01

On the basis of fuzzy regression, computational models in intelligence such as neural networks have the capability to be applied to nonlinear interval regression analysis for dealing with uncertain and imprecise data. When training data are not contaminated by outliers, computational models perform well by including almost all given training data in the data interval. Nevertheless, since training data are often corrupted by outliers, robust learning algorithms employed to resist outliers for interval regression analysis have been an interesting area of research. Several approaches involving computational intelligence are effective for resisting outliers, but the required parameters for these approaches are related to whether the collected data contain outliers or not. Since it seems difficult to prespecify the degree of contamination beforehand, this paper uses multilayer perceptron to construct the robust nonlinear interval regression model using the genetic algorithm. Outliers beyond or beneath the data interval will impose slight effect on the determination of data interval. Simulation results demonstrate that the proposed method performs well for contaminated datasets. PMID:25110755

Multilayer perceptron for robust nonlinear interval regression analysis using genetic algorithms.

PubMed

Hu, Yi-Chung

2014-01-01

On the basis of fuzzy regression, computational models in intelligence such as neural networks have the capability to be applied to nonlinear interval regression analysis for dealing with uncertain and imprecise data. When training data are not contaminated by outliers, computational models perform well by including almost all given training data in the data interval. Nevertheless, since training data are often corrupted by outliers, robust learning algorithms employed to resist outliers for interval regression analysis have been an interesting area of research. Several approaches involving computational intelligence are effective for resisting outliers, but the required parameters for these approaches are related to whether the collected data contain outliers or not. Since it seems difficult to prespecify the degree of contamination beforehand, this paper uses multilayer perceptron to construct the robust nonlinear interval regression model using the genetic algorithm. Outliers beyond or beneath the data interval will impose slight effect on the determination of data interval. Simulation results demonstrate that the proposed method performs well for contaminated datasets.

Artificial Neural Network Models for Long Lead Streamflow Forecasts using Climate Information

NASA Astrophysics Data System (ADS)

Kumar, J.; Devineni, N.

2007-12-01

Information on season ahead stream flow forecasts is very beneficial for the operation and management of water supply systems. Daily streamflow conditions at any particular reservoir primarily depend on atmospheric and land surface conditions including the soil moisture and snow pack. On the other hand recent studies suggest that developing long lead streamflow forecasts (3 months ahead) typically depends on exogenous climatic conditions particularly Sea Surface Temperature conditions (SST) in the tropical oceans. Examples of some oceanic variables are El Nino Southern Oscillation (ENSO) and Pacific Decadal Oscillation (PDO). Identification of such conditions that influence the moisture transport into a given basin poses many challenges given the nonlinear dependency between the predictors (SST) and predictand (stream flows). In this study, we apply both linear and nonlinear dependency measures to identify the predictors that influence the winter flows into the Neuse basin. The predictor identification approach here adopted uses simple correlation coefficients to spearman rank correlation measures for detecting nonlinear dependency. All these dependency measures are employed with a lag 3 time series of the high flow season (January - February - March) using 75 years (1928-2002) of stream flows recorded in to the Falls Lake, Neuse River Basin. Developing streamflow forecasts contingent on these exogenous predictors will play an important role towards improved water supply planning and management. Recently, the soft computing techniques, such as artificial neural networks (ANNs) have provided an alternative method to solve complex problems efficiently. ANNs are data driven models which trains on the examples given to it. The ANNs functions as universal approximators and are non linear in nature. This paper presents a study aiming towards using climatic predictors for 3 month lead time streamflow forecast. ANN models representing the physical process of the system are developed between the identified predictors and the predictand. Predictors used are the scores of Principal Components Analysis (PCA). The models were tested and validated. The feed- forward multi-layer perceptron (MLP) type neural networks trained using the back-propagation algorithms are employed in the current study. The performance of the ANN-model forecasts are evaluated using various performance evaluation measures such as correlation coefficient, root mean square error (RMSE). The preliminary results shows that ANNs are efficient to forecast long lead time streamflows using climatic predictors.

Optimizing Airborne Networking Performance with Cross-Layer Design Approach

DTIC Science & Technology

2009-06-01

Schiavone , L.J.; “Airborne Networking –Approaches and Challenges,” Military Communications Conference IEEE, Oct 31 – Nov 3, 2004, Vol. 1, pp. 404...www.ccny.cuny.edu/cint/ [5] John Seguí and Esther Jennings,’’ Delay Tolerant Networking – Bundle Protocol Simulation’’ [6] DTNRG website...throughput route selection in multi-rate ad hoc wireless networks,” Technical report, Johns Hopkins CS Dept, March 2003. v 2. [15] R. Draves, J

Complexity of generic biochemical circuits: topology versus strength of interactions.

PubMed

Tikhonov, Mikhail; Bialek, William

2016-12-06

The historical focus on network topology as a determinant of biological function is still largely maintained today, illustrated by the rise of structure-only approaches to network analysis. However, biochemical circuits and genetic regulatory networks are defined both by their topology and by a multitude of continuously adjustable parameters, such as the strength of interactions between nodes, also recognized as important. Here we present a class of simple perceptron-based Boolean models within which comparing the relative importance of topology versus interaction strengths becomes a quantitatively well-posed problem. We quantify the intuition that for generic networks, optimization of interaction strengths is a crucial ingredient of achieving high complexity, defined here as the number of fixed points the network can accommodate. We propose a new methodology for characterizing the relative role of parameter optimization for topologies of a given class.

Zigbee networking technology and its application in Lamost optical fiber positioning and control system

NASA Astrophysics Data System (ADS)

Jin, Yi; Zhai, Chao; Gu, Yonggang; Zhou, Zengxiang; Gai, Xiaofeng

2010-07-01

4,000 fiber positioning units need to be positioned precisely in LAMOST(Large Sky Area Multi-object Optical Spectroscopic Telescope) optical fiber positioning & control system, and every fiber positioning unit needs two stepper motors for its driven, so 8,000 stepper motors need to be controlled in the entire system. Wireless communication mode is adopted to save the installing space on the back of the focal panel, and can save more than 95% external wires compared to the traditional cable control mode. This paper studies how to use the ZigBee technology to group these 8000 nodes, explores the pros and cons of star network and tree network in order to search the stars quickly and efficiently. ZigBee technology is a short distance, low-complexity, low power, low data rate, low-cost two-way wireless communication technology based on the IEEE 802.15.4 protocol. It based on standard Open Systems Interconnection (OSI): The 802.15.4 standard specifies the lower protocol layers-the physical layer (PHY), and the media access control (MAC). ZigBee Alliance defined on this basis, the rest layers such as the network layer and application layer, and is responsible for high-level applications, testing and marketing. The network layer used here, based on ad hoc network protocols, includes the following functions: construction and maintenance of the topological structure, nomenclature and associated businesses which involves addressing, routing and security and a self-organizing-self-maintenance functions which will minimize consumer spending and maintenance costs. In this paper, freescale's 802.15.4 protocol was used to configure the network layer. A star network and a tree network topology is realized, which can build network, maintenance network and create a routing function automatically. A concise tree network address allocate algorithm is present to assign the network ID automatically.

Network-level accident-mapping: Distance based pattern matching using artificial neural network.

PubMed

Deka, Lipika; Quddus, Mohammed

2014-04-01

The objective of an accident-mapping algorithm is to snap traffic accidents onto the correct road segments. Assigning accidents onto the correct segments facilitate to robustly carry out some key analyses in accident research including the identification of accident hot-spots, network-level risk mapping and segment-level accident risk modelling. Existing risk mapping algorithms have some severe limitations: (i) they are not easily 'transferable' as the algorithms are specific to given accident datasets; (ii) they do not perform well in all road-network environments such as in areas of dense road network; and (iii) the methods used do not perform well in addressing inaccuracies inherent in and type of road environment. The purpose of this paper is to develop a new accident mapping algorithm based on the common variables observed in most accident databases (e.g. road name and type, direction of vehicle movement before the accident and recorded accident location). The challenges here are to: (i) develop a method that takes into account uncertainties inherent to the recorded traffic accident data and the underlying digital road network data, (ii) accurately determine the type and proportion of inaccuracies, and (iii) develop a robust algorithm that can be adapted for any accident set and road network of varying complexity. In order to overcome these challenges, a distance based pattern-matching approach is used to identify the correct road segment. This is based on vectors containing feature values that are common in the accident data and the network data. Since each feature does not contribute equally towards the identification of the correct road segments, an ANN approach using the single-layer perceptron is used to assist in "learning" the relative importance of each feature in the distance calculation and hence the correct link identification. The performance of the developed algorithm was evaluated based on a reference accident dataset from the UK confirming that the accuracy is much better than other methods. Crown Copyright © 2014. Published by Elsevier Ltd. All rights reserved.

An Integrated Multi-layer Approach for Seamless Soft Handoff in Mobile Ad Hoc Networks

DTIC Science & Technology

2011-01-01

network to showcase how to leverage the IEEE 802.21 Media Independent Handover ( MIH ) framework [3] in our handoff solution. Moreover, to further...to the seamless handoff problem. The architecture leverages the IEEE 802.21 MIH standard to facilitate handover related decisions on multiple...provided by the MIH function (MIHF), the topology control manager dynamically activates/deactivates the wireless interfaces to ensure the network is

Automatic lithofacies segmentation from well-logs data. A comparative study between the Self-Organizing Map (SOM) and Walsh transform

NASA Astrophysics Data System (ADS)

Aliouane, Leila; Ouadfeul, Sid-Ali; Rabhi, Abdessalem; Rouina, Fouzi; Benaissa, Zahia; Boudella, Amar

2013-04-01

The main goal of this work is to realize a comparison between two lithofacies segmentation techniques of reservoir interval. The first one is based on the Kohonen's Self-Organizing Map neural network machine. The second technique is based on the Walsh transform decomposition. Application to real well-logs data of two boreholes located in the Algerian Sahara shows that the Self-organizing map is able to provide more lithological details that the obtained lithofacies model given by the Walsh decomposition. Keywords: Comparison, Lithofacies, SOM, Walsh References: 1)Aliouane, L., Ouadfeul, S., Boudella, A., 2011, Fractal analysis based on the continuous wavelet transform and lithofacies classification from well-logs data using the self-organizing map neural network, Arabian Journal of geosciences, doi: 10.1007/s12517-011-0459-4 2) Aliouane, L., Ouadfeul, S., Djarfour, N., Boudella, A., 2012, Petrophysical Parameters Estimation from Well-Logs Data Using Multilayer Perceptron and Radial Basis Function Neural Networks, Lecture Notes in Computer Science Volume 7667, 2012, pp 730-736, doi : 10.1007/978-3-642-34500-5_86 3)Ouadfeul, S. and Aliouane., L., 2011, Multifractal analysis revisited by the continuous wavelet transform applied in lithofacies segmentation from well-logs data, International journal of applied physics and mathematics, Vol01 N01. 4) Ouadfeul, S., Aliouane, L., 2012, Lithofacies Classification Using the Multilayer Perceptron and the Self-organizing Neural Networks, Lecture Notes in Computer Science Volume 7667, 2012, pp 737-744, doi : 10.1007/978-3-642-34500-5_87 5) Weisstein, Eric W. "Fast Walsh Transform." From MathWorld--A Wolfram Web Resource. http://mathworld.wolfram.com/FastWalshTransform.html

Use of artificial neural networks to identify the origin of green macroalgae

NASA Astrophysics Data System (ADS)

Żbikowski, Radosław

2011-08-01

This study demonstrates application of artificial neural networks (ANNs) for identifying the origin of green macroalgae ( Enteromorpha sp. and Cladophora sp.) according to their concentrations of Cd, Cu, Ni, Zn, Mn, Pb, Na, Ca, K and Mg. Earlier studies confirmed that algae can be used for biomonitoring surveys of metal contaminants in coastal areas of the Southern Baltic. The same data sets were classified with the use of different structures of radial basis function (RBF) and multilayer perceptron (MLP) networks. The selected networks were able to classify the samples according to their geographical origin, i.e. Southern Baltic, Gulf of Gdańsk and Vistula Lagoon. Additionally in the case of macroalgae from the Gulf of Gdańsk, the networks enabled the discrimination of samples according to areas of contrasting levels of pollution. Hence this study shows that artificial neural networks can be a valuable tool in biomonitoring studies.

Using deep recurrent neural network for direct beam solar irradiance cloud screening

NASA Astrophysics Data System (ADS)

Chen, Maosi; Davis, John M.; Liu, Chaoshun; Sun, Zhibin; Zempila, Melina Maria; Gao, Wei

2017-09-01

Cloud screening is an essential procedure for in-situ calibration and atmospheric properties retrieval on (UV-)MultiFilter Rotating Shadowband Radiometer [(UV-)MFRSR]. Previous study has explored a cloud screening algorithm for direct-beam (UV-)MFRSR voltage measurements based on the stability assumption on a long time period (typically a half day or a whole day). To design such an algorithm requires in-depth understanding of radiative transfer and delicate data manipulation. Recent rapid developments on deep neural network and computation hardware have opened a window for modeling complicated End-to-End systems with a standardized strategy. In this study, a multi-layer dynamic bidirectional recurrent neural network is built for determining the cloudiness on each time point with a 17-year training dataset and tested with another 1-year dataset. The dataset is the daily 3-minute cosine corrected voltages, airmasses, and the corresponding cloud/clear-sky labels at two stations of the USDA UV-B Monitoring and Research Program. The results show that the optimized neural network model (3-layer, 250 hidden units, and 80 epochs of training) has an overall test accuracy of 97.87% (97.56% for the Oklahoma site and 98.16% for the Hawaii site). Generally, the neural network model grasps the key concept of the original model to use data in the entire day rather than short nearby measurements to perform cloud screening. A scrutiny of the logits layer suggests that the neural network model automatically learns a way to calculate a quantity similar to total optical depth and finds an appropriate threshold for cloud screening.

Comprehensive optimization of friction stir weld parameters of lap joint AA1100 plates using artificial neural networks and modified NSGA-II

NASA Astrophysics Data System (ADS)

Khalkhali, Abolfazl; Ebrahimi-Nejad, Salman; Geran Malek, Nima

2018-06-01

Friction stir welding (FSW) process overcomes many difficulties arising in conventional fusion welding processes of aluminum alloys. The current paper presents a comprehensive investigation on the effects of rotational speed, traverse speed, tool tilt angle and tool pin profile on the longitudinal force, axial force, maximum temperature, tensile strength, percent elongation, grain size, micro-hardness of welded zone and welded zone thickness of AA1100 aluminum alloy sheets. Design of experiments (DOE) was applied using the Taguchi approach and subsequently, effects of the input parameter on process outputs were investigated using analysis of variance (ANOVA). A perceptron neural network model was developed to find a correlation between the inputs and outputs. Multi-objective optimization using modified NSGA-II was implemented followed by NIP and TOPSIS approaches to propose optimum points for each of the square, pentagon, hexagon, and circular pin profiles. Results indicate that the optimization process can reach horizontal and vertical forces as low as 1452 N and 2913 N, respectively and a grain size as low as 2 μm. This results in hardness values of up to 57.2 and tensile strength, elongation and joint thickness of 2126 N, 5.9% and 3.7 mm, respectively. The maximum operating temperature can also reach a sufficiently high value of 374 °C to provide adequate material flow.

Application of neural network to remote sensing of soil moisture using theoretical polarimetric backscattering coefficients

NASA Technical Reports Server (NTRS)

Wang, L.; Shin, R. T.; Kong, J. A.; Yueh, S. H.

1993-01-01

This paper investigates the potential application of neural network to inversion of soil moisture using polarimetric remote sensing data. The neural network used for the inversion of soil parameters is multi-layer perceptron trained with the back-propagation algorithm. The training data include the polarimetric backscattering coefficients obtained from theoretical surface scattering models together with an assumed nominal range of soil parameters which are comprised of the soil permittivity and surface roughness parameters. Soil permittivity is calculated from the soil moisture and the assumed soil texture based on an empirical formula at C-, L-, and P-bands. The rough surface parameters for the soil surface, which is described by the Gaussian random process, are the root-mean-square (rms) height and correlation length. For the rough surface scattering, small perturbation method is used for the L-band frequency, and Kirchhoff approximation is used for the C-band frequency to obtain the corresponding backscattering coefficients. During the training, the backscattering coefficients are the inputs to the neural net and the output from the net are compared with the desired soil parameters to adjust the interconnecting weights. The process is repeated for each input-output data entry and then for the entire training data until convergence is reached. After training, the backscattering coefficients are applied to the trained neural net to retrieve the soil parameters which are compared with the desired soil parameters to verify the effectiveness of this technique. Several cases are examined. First, for simplicity, the correlation length and rms height of the soil surface are fixed while soil moisture is varied. Soil moisture obtained using the neural networks with either L-band or C-band backscattering coefficients for the HH and VV polarizations as inputs is in good agreement with the desired soil moisture. The neural net output matches the desired output for the soil moisture range of 16 to 60 percent for the C-band case. The next case investigated is to vary both soil moisture and rms height while keeping the correlation length fixed. For this case, C-band backscattering coefficients are not sufficient for retrieving two parameters because the Kirchhoff approximation gives the same HH and VV backscattering coefficients. Therefore, the backscattering coefficients at two different frequency bands are necessary to find both the soil moisture and rms height. Finally, the neural nets are also applied to simultaneously invert soil moisture, rms height, and correlation length. Overall, the soil moisture retrieved from the neural network agrees very well with the desired soil moisture. This suggests that the neural network shows potential for retrieval of soil parameters from remote sensing data.

Networks for image acquisition, processing and display

NASA Technical Reports Server (NTRS)

Ahumada, Albert J., Jr.

1990-01-01

The human visual system comprises layers of networks which sample, process, and code images. Understanding these networks is a valuable means of understanding human vision and of designing autonomous vision systems based on network processing. Ames Research Center has an ongoing program to develop computational models of such networks. The models predict human performance in detection of targets and in discrimination of displayed information. In addition, the models are artificial vision systems sharing properties with biological vision that has been tuned by evolution for high performance. Properties include variable density sampling, noise immunity, multi-resolution coding, and fault-tolerance. The research stresses analysis of noise in visual networks, including sampling, photon, and processing unit noises. Specific accomplishments include: models of sampling array growth with variable density and irregularity comparable to that of the retinal cone mosaic; noise models of networks with signal-dependent and independent noise; models of network connection development for preserving spatial registration and interpolation; multi-resolution encoding models based on hexagonal arrays (HOP transform); and mathematical procedures for simplifying analysis of large networks.

Multi-layer holographic bifurcative neural network system for real-time adaptive EOS data analysis

NASA Technical Reports Server (NTRS)

Liu, Hua-Kuang; Huang, K. S.; Diep, J.

1993-01-01

Optical data processing techniques have the inherent advantage of high data throughout, low weight and low power requirements. These features are particularly desirable for onboard spacecraft in-situ real-time data analysis and data compression applications. the proposed multi-layer optical holographic neural net pattern recognition technique will utilize the nonlinear photorefractive devices for real-time adaptive learning to classify input data content and recognize unexpected features. Information can be stored either in analog or digital form in a nonlinear photofractive device. The recording can be accomplished in time scales ranging from milliseconds to microseconds. When a system consisting of these devices is organized in a multi-layer structure, a feedforward neural net with bifurcating data classification capability is formed. The interdisciplinary research will involve the collaboration with top digital computer architecture experts at the University of Southern California.

Effects of temporal correlations in social multiplex networks.

PubMed

Starnini, Michele; Baronchelli, Andrea; Pastor-Satorras, Romualdo

2017-08-17

Multi-layered networks represent a major advance in the description of natural complex systems, and their study has shed light on new physical phenomena. Despite its importance, however, the role of the temporal dimension in their structure and function has not been investigated in much detail so far. Here we study the temporal correlations between layers exhibited by real social multiplex networks. At a basic level, the presence of such correlations implies a certain degree of predictability in the contact pattern, as we quantify by an extension of the entropy and mutual information analyses proposed for the single-layer case. At a different level, we demonstrate that temporal correlations are a signature of a 'multitasking' behavior of network agents, characterized by a higher level of switching between different social activities than expected in a uncorrelated pattern. Moreover, temporal correlations significantly affect the dynamics of coupled epidemic processes unfolding on the network. Our work opens the way for the systematic study of temporal multiplex networks and we anticipate it will be of interest to researchers in a broad array of fields.

Genetic algorithm for neural networks optimization

NASA Astrophysics Data System (ADS)

Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta

2004-11-01

This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.

HOS network-based classification of power quality events via regression algorithms

NASA Astrophysics Data System (ADS)

Palomares Salas, José Carlos; González de la Rosa, Juan José; Sierra Fernández, José María; Pérez, Agustín Agüera

2015-12-01

This work compares seven regression algorithms implemented in artificial neural networks (ANNs) supported by 14 power-quality features, which are based in higher-order statistics. Combining time and frequency domain estimators to deal with non-stationary measurement sequences, the final goal of the system is the implementation in the future smart grid to guarantee compatibility between all equipment connected. The principal results are based in spectral kurtosis measurements, which easily adapt to the impulsive nature of the power quality events. These results verify that the proposed technique is capable of offering interesting results for power quality (PQ) disturbance classification. The best results are obtained using radial basis networks, generalized regression, and multilayer perceptron, mainly due to the non-linear nature of data.

Hazard interactions and interaction networks (cascades) within multi-hazard methodologies

NASA Astrophysics Data System (ADS)

Gill, Joel C.; Malamud, Bruce D.

2016-08-01

This paper combines research and commentary to reinforce the importance of integrating hazard interactions and interaction networks (cascades) into multi-hazard methodologies. We present a synthesis of the differences between multi-layer single-hazard approaches and multi-hazard approaches that integrate such interactions. This synthesis suggests that ignoring interactions between important environmental and anthropogenic processes could distort management priorities, increase vulnerability to other spatially relevant hazards or underestimate disaster risk. In this paper we proceed to present an enhanced multi-hazard framework through the following steps: (i) description and definition of three groups (natural hazards, anthropogenic processes and technological hazards/disasters) as relevant components of a multi-hazard environment, (ii) outlining of three types of interaction relationship (triggering, increased probability, and catalysis/impedance), and (iii) assessment of the importance of networks of interactions (cascades) through case study examples (based on the literature, field observations and semi-structured interviews). We further propose two visualisation frameworks to represent these networks of interactions: hazard interaction matrices and hazard/process flow diagrams. Our approach reinforces the importance of integrating interactions between different aspects of the Earth system, together with human activity, into enhanced multi-hazard methodologies. Multi-hazard approaches support the holistic assessment of hazard potential and consequently disaster risk. We conclude by describing three ways by which understanding networks of interactions contributes to the theoretical and practical understanding of hazards, disaster risk reduction and Earth system management. Understanding interactions and interaction networks helps us to better (i) model the observed reality of disaster events, (ii) constrain potential changes in physical and social vulnerability between successive hazards, and (iii) prioritise resource allocation for mitigation and disaster risk reduction.

Machine learning based sample extraction for automatic speech recognition using dialectal Assamese speech.

PubMed

Agarwalla, Swapna; Sarma, Kandarpa Kumar

2016-06-01

Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and Internet of Things (IoT) as extended elements of HCI, ASR techniques are found to be passing through a paradigm shift. Oflate, learning based techniques have started to receive greater attention from research communities related to ASR owing to the fact that former possess natural ability to mimic biological behavior and that way aids ASR modeling and processing. The current learning based ASR techniques are found to be evolving further with incorporation of big data, IoT like concepts. Here, in this paper, we report certain approaches based on machine learning (ML) used for extraction of relevant samples from big data space and apply them for ASR using certain soft computing techniques for Assamese speech with dialectal variations. A class of ML techniques comprising of the basic Artificial Neural Network (ANN) in feedforward (FF) and Deep Neural Network (DNN) forms using raw speech, extracted features and frequency domain forms are considered. The Multi Layer Perceptron (MLP) is configured with inputs in several forms to learn class information obtained using clustering and manual labeling. DNNs are also used to extract specific sentence types. Initially, from a large storage, relevant samples are selected and assimilated. Next, a few conventional methods are used for feature extraction of a few selected types. The features comprise of both spectral and prosodic types. These are applied to Recurrent Neural Network (RNN) and Fully Focused Time Delay Neural Network (FFTDNN) structures to evaluate their performance in recognizing mood, dialect, speaker and gender variations in dialectal Assamese speech. The system is tested under several background noise conditions by considering the recognition rates (obtained using confusion matrices and manually) and computation time. It is found that the proposed ML based sentence extraction techniques and the composite feature set used with RNN as classifier outperform all other approaches. By using ANN in FF form as feature extractor, the performance of the system is evaluated and a comparison is made. Experimental results show that the application of big data samples has enhanced the learning of the ASR system. Further, the ANN based sample and feature extraction techniques are found to be efficient enough to enable application of ML techniques in big data aspects as part of ASR systems. Copyright © 2015 Elsevier Ltd. All rights reserved.

Design and FPGA implementation for MAC layer of Ethernet PON

NASA Astrophysics Data System (ADS)

Zhu, Zengxi; Lin, Rujian; Chen, Jian; Ye, Jiajun; Chen, Xinqiao

2004-04-01

Ethernet passive optical network (EPON), which represents the convergence of low-cost, high-bandwidth and supporting multiple services, appears to be one of the best candidates for the next-generation access network. The work of standardizing EPON as a solution for access network is still underway in the IEEE802.3ah Ethernet in the first mile (EFM) task force. The final release is expected in 2004. Up to now, there has been no standard application specific integrated circuit (ASIC) chip available which fulfills the functions of media access control (MAC) layer of EPON. The MAC layer in EPON system has many functions, such as point-to-point emulation (P2PE), Ethernet MAC functionality, multi-point control protocol (MPCP), network operation, administration and maintenance (OAM) and link security. To implement those functions mentioned above, an embedded real-time operating system (RTOS) and a flexible programmable logic device (PLD) with an embedded processor are used. The software and hardware functions in MAC layer are realized through programming embedded microprocessor and field programmable gate array(FPGA). Finally, some experimental results are given in this paper. The method stated here can provide a valuable reference for developing EPON MAC layer ASIC.

Deferred discrimination algorithm (nibbling) for target filter management

NASA Astrophysics Data System (ADS)

Caulfield, H. John; Johnson, John L.

1999-07-01

A new method of classifying objects is presented. Rather than trying to form the classifier in one step or in one training algorithm, it is done in a series of small steps, or nibbles. This leads to an efficient and versatile system that is trained in series with single one-shot examples but applied in parallel, is implemented with single layer perceptrons, yet maintains its fully sequential hierarchical structure. Based on the nibbling algorithm, a basic new method of target reference filter management is described.

A Hierarchical multi-input and output Bi-GRU Model for Sentiment Analysis on Customer Reviews

NASA Astrophysics Data System (ADS)

Zhang, Liujie; Zhou, Yanquan; Duan, Xiuyu; Chen, Ruiqi

2018-03-01

Multi-label sentiment classification on customer reviews is a practical challenging task in Natural Language Processing. In this paper, we propose a hierarchical multi-input and output model based bi-directional recurrent neural network, which both considers the semantic and lexical information of emotional expression. Our model applies two independent Bi-GRU layer to generate part of speech and sentence representation. Then the lexical information is considered via attention over output of softmax activation on part of speech representation. In addition, we combine probability of auxiliary labels as feature with hidden layer to capturing crucial correlation between output labels. The experimental result shows that our model is computationally efficient and achieves breakthrough improvements on customer reviews dataset.

Comparing Different Approaches for Mapping Urban Vegetation Cover from Landsat ETM+ Data: A Case Study on Brussels

PubMed Central

Van de Voorde, Tim; Vlaeminck, Jeroen; Canters, Frank

2008-01-01

Urban growth and its related environmental problems call for sustainable urban management policies to safeguard the quality of urban environments. Vegetation plays an important part in this as it provides ecological, social, health and economic benefits to a city's inhabitants. Remotely sensed data are of great value to monitor urban green and despite the clear advantages of contemporary high resolution images, the benefits of medium resolution data should not be discarded. The objective of this research was to estimate fractional vegetation cover from a Landsat ETM+ image with sub-pixel classification, and to compare accuracies obtained with multiple stepwise regression analysis, linear spectral unmixing and multi-layer perceptrons (MLP) at the level of meaningful urban spatial entities. Despite the small, but nevertheless statistically significant differences at pixel level between the alternative approaches, the spatial pattern of vegetation cover and estimation errors is clearly distinctive at neighbourhood level. At this spatially aggregated level, a simple regression model appears to attain sufficient accuracy. For mapping at a spatially more detailed level, the MLP seems to be the most appropriate choice. Brightness normalisation only appeared to affect the linear models, especially the linear spectral unmixing. PMID:27879914

A Novel Fiber Optic Based Surveillance System for Prevention of Pipeline Integrity Threats.

PubMed

Tejedor, Javier; Macias-Guarasa, Javier; Martins, Hugo F; Piote, Daniel; Pastor-Graells, Juan; Martin-Lopez, Sonia; Corredera, Pedro; Gonzalez-Herraez, Miguel

2017-02-12

This paper presents a novel surveillance system aimed at the detection and classification of threats in the vicinity of a long gas pipeline. The sensing system is based on phase-sensitive optical time domain reflectometry ( ϕ -OTDR) technology for signal acquisition and pattern recognition strategies for threat identification. The proposal incorporates contextual information at the feature level and applies a system combination strategy for pattern classification. The contextual information at the feature level is based on the tandem approach (using feature representations produced by discriminatively-trained multi-layer perceptrons) by employing feature vectors that spread different temporal contexts. The system combination strategy is based on a posterior combination of likelihoods computed from different pattern classification processes. The system operates in two different modes: (1) machine + activity identification, which recognizes the activity being carried out by a certain machine, and (2) threat detection, aimed at detecting threats no matter what the real activity being conducted is. In comparison with a previous system based on the same rigorous experimental setup, the results show that the system combination from the contextual feature information improves the results for each individual class in both operational modes, as well as the overall classification accuracy, with statistically-significant improvements.

Biometric verification in dynamic writing

NASA Astrophysics Data System (ADS)

George, Susan E.

2002-03-01

Pen-tablet devices capable of capturing the dynamics of writing record temporal and pressure information as well as the spatial pattern. This paper explores biometric verification based upon the dynamics of writing where writers are distinguished not on the basis of what they write (ie the signature), but how they write. We have collected samples of dynamic writing from 38 Chinese writers. Each writer was asked to provide 10 copies of a paragraph of text and the same number of signature samples. From the data we have extracted stroke-based primitives from the sentence data utilizing pen-up/down information and heuristic rules about the shape of the character. The x, y and pressure values of each primitive were interpolated into an even temporal range based upon a 20 msec sampling rate. We applied the Daubechies 1 wavelet transform to the x signal, y signal and pressure signal using the coefficients as inputs to a multi-layer perceptron trained with back-propagation on the sentence data. We found a sensitivity of 0.977 and specificity of 0.990 recognizing writers based on test primitives extracted from sentence data and measures of 0.916 and 0.961 respectively, from test primitives extracted from signature data.

Designing a holistic end-to-end intelligent network analysis and security platform

NASA Astrophysics Data System (ADS)

Alzahrani, M.

2018-03-01

Firewall protects a network from outside attacks, however, once an attack entering a network, it is difficult to detect. Recent significance accidents happened. i.e.: millions of Yahoo email account were stolen and crucial data from institutions are held for ransom. Within two year Yahoo’s system administrators were not aware that there are intruder inside the network. This happened due to the lack of intelligent tools to monitor user behaviour in internal network. This paper discusses a design of an intelligent anomaly/malware detection system with proper proactive actions. The aim is to equip the system administrator with a proper tool to battle the insider attackers. The proposed system adopts machine learning to analyse user’s behaviour through the runtime behaviour of each node in the network. The machine learning techniques include: deep learning, evolving machine learning perceptron, hybrid of Neural Network and Fuzzy, as well as predictive memory techniques. The proposed system is expanded to deal with larger network using agent techniques.

Predicting changes of glass optical properties in polluted atmospheric environment by a neural network model

NASA Astrophysics Data System (ADS)

Verney-Carron, A.; Dutot, A. L.; Lombardo, T.; Chabas, A.

2012-07-01

Soiling results from the deposition of pollutants on materials. On glass, it leads to an alteration of its intrinsic optical properties. The nature and intensity of this phenomenon mirrors the pollution of an environment. This paper proposes a new statistical model in order to predict the evolution of haze (H) (i.e. diffuse/direct transmitted light ratio) as a function of time and major pollutant concentrations in the atmosphere (SO2, NO2, and PM10 (Particulate Matter < 10 μm)). The model was parameterized by using a large set of data collected in European cities (especially, Paris and its suburbs, Athens, Krakow, Prague, and Rome) during field exposure campaigns (French, European, and international programs). This statistical model, called NEUROPT-Glass, comes from an artificial neural network with two hidden layers and uses a non-linear parametric regression named Multilayer Perceptron (MLP). The results display a high determination coefficient (R2 = 0.88) between the measured and the predicted hazes and minimizes the dispersion of data compared to existing multilinear dose-response functions. Therefore, this model can be used with a great confidence in order to predict the soiling of glass as a function of time in world cities with different levels of pollution or to assess the effect of pollution reduction policies on glass soiling problems in urban environments.

Grounding the Meanings in Sensorimotor Behavior using Reinforcement Learning

PubMed Central

Farkaš, Igor; Malík, Tomáš; Rebrová, Kristína

2012-01-01

The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behavior. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch, and push) oriented toward objects in robot’s peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalizes well in case of novel action-target combinations with randomized initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution. PMID:22393319

Generalized information fusion and visualization using spatial voting and data modeling

NASA Astrophysics Data System (ADS)

Jaenisch, Holger M.; Handley, James W.

2013-05-01

We present a novel and innovative information fusion and visualization framework for multi-source intelligence (multiINT) data using Spatial Voting (SV) and Data Modeling. We describe how different sources of information can be converted into numerical form for further processing downstream, followed by a short description of how this information can be fused using the SV grid. As an illustrative example, we show the modeling of cyberspace as cyber layers for the purpose of tracking cyber personas. Finally we describe a path ahead for creating interactive agile networks through defender customized Cyber-cubes for network configuration and attack visualization.

A Cross-Layer Approach to Multi-Hop Networking with Cognitive Radios

DTIC Science & Technology

2008-11-01

recent investigations. In [2], Behzad and Rubin studied the special case that the same power level are used at each node and found that the maximum...Sep. 2, 2005. [2] A. Behzad and I. Rubin, “Impact of power control on the performance of ad hoc wireless networks,” in Proc. IEEE Infocom, pp. 102–113

Three layers multi-granularity OCDM switching system based on learning-stateful PCE

NASA Astrophysics Data System (ADS)

Wang, Yubao; Liu, Yanfei; Sun, Hao

2017-10-01

In the existing three layers multi-granularity OCDM switching system (TLMG-OCDMSS), F-LSP, L-LSP and OC-LSP can be bundled as switching granularity. For CPU-intensive network, the node not only needs to compute the path but also needs to bundle the switching granularity so that the load of single node is heavy. The node will paralyze when the traffic of the node is too heavy, which will impact the performance of the whole network seriously. The introduction of stateful PCE(S-PCE) will effectively solve these problems. PCE is composed of two parts, namely, the path computation element and the database (TED and LSPDB), and returns the result of path computation to PCC (path computation clients) after PCC sends the path computation request to it. In this way, the pressure of the distributed path computation in each node is reduced. In this paper, we propose the concept of Learning PCE (L-PCE), which uses the existing LSPDB as the data source of PCE's learning. By this means, we can simplify the path computation and reduce the network delay, as a result, improving the performance of network.

A Theory of How Columns in the Neocortex Enable Learning the Structure of the World

PubMed Central

Hawkins, Jeff; Ahmad, Subutai; Cui, Yuwei

2017-01-01

Neocortical regions are organized into columns and layers. Connections between layers run mostly perpendicular to the surface suggesting a columnar functional organization. Some layers have long-range excitatory lateral connections suggesting interactions between columns. Similar patterns of connectivity exist in all regions but their exact role remain a mystery. In this paper, we propose a network model composed of columns and layers that performs robust object learning and recognition. Each column integrates its changing input over time to learn complete predictive models of observed objects. Excitatory lateral connections across columns allow the network to more rapidly infer objects based on the partial knowledge of adjacent columns. Because columns integrate input over time and space, the network learns models of complex objects that extend well beyond the receptive field of individual cells. Our network model introduces a new feature to cortical columns. We propose that a representation of location relative to the object being sensed is calculated within the sub-granular layers of each column. The location signal is provided as an input to the network, where it is combined with sensory data. Our model contains two layers and one or more columns. Simulations show that using Hebbian-like learning rules small single-column networks can learn to recognize hundreds of objects, with each object containing tens of features. Multi-column networks recognize objects with significantly fewer movements of the sensory receptors. Given the ubiquity of columnar and laminar connectivity patterns throughout the neocortex, we propose that columns and regions have more powerful recognition and modeling capabilities than previously assumed. PMID:29118696

The Age in Swimming of Champions in World Championships (1994–2013) and Olympic Games (1992–2012): A Cross-Sectional Data Analysis

PubMed Central

Knechtle, Beat; Bragazzi, Nicola Luigi; König, Stefan; Nikolaidis, Pantelis Theodoros; Wild, Stefanie; Rosemann, Thomas; Rüst, Christoph Alexander

2016-01-01

(1) Background: We investigated the age of swimming champions in all strokes and race distances in World Championships (1994–2013) and Olympic Games (1992–2012); (2) Methods: Changes in age and swimming performance across calendar years for 412 Olympic and world champions were analysed using linear, non-linear, multi-level regression analyses and MultiLayer Perceptron (MLP); (3) Results: The age of peak swimming performance remained stable in most of all race distances for world champions and in all race distances for Olympic champions. Longer (i.e., 200 m and more) race distances were completed by younger (~20 years old for women and ~22 years old for men) champions than shorter (i.e., 50 m and 100 m) race distances (~22 years old for women and ~24 years old for men). There was a sex difference in the age of champions of ~2 years with a mean age of ~21 and ~23 years for women and men, respectively. Swimming performance improved in most race distances for world and Olympic champions with a larger trend of increase in Olympic champions; (4) Conclusion: Swimmers at younger ages (<20 years) may benefit from training and competing in longer race distances (i.e., 200 m and longer) before they change to shorter distances (i.e., 50 m and 100 m) when they become older (>22 years). PMID:29910265

Comparing multilayer brain networks between groups: Introducing graph metrics and recommendations.

PubMed

Mandke, Kanad; Meier, Jil; Brookes, Matthew J; O'Dea, Reuben D; Van Mieghem, Piet; Stam, Cornelis J; Hillebrand, Arjan; Tewarie, Prejaas

2018-02-01

There is an increasing awareness of the advantages of multi-modal neuroimaging. Networks obtained from different modalities are usually treated in isolation, which is however contradictory to accumulating evidence that these networks show non-trivial interdependencies. Even networks obtained from a single modality, such as frequency-band specific functional networks measured from magnetoencephalography (MEG) are often treated independently. Here, we discuss how a multilayer network framework allows for integration of multiple networks into a single network description and how graph metrics can be applied to quantify multilayer network organisation for group comparison. We analyse how well-known biases for single layer networks, such as effects of group differences in link density and/or average connectivity, influence multilayer networks, and we compare four schemes that aim to correct for such biases: the minimum spanning tree (MST), effective graph resistance cost minimisation, efficiency cost optimisation (ECO) and a normalisation scheme based on singular value decomposition (SVD). These schemes can be applied to the layers independently or to the multilayer network as a whole. For correction applied to whole multilayer networks, only the SVD showed sufficient bias correction. For correction applied to individual layers, three schemes (ECO, MST, SVD) could correct for biases. By using generative models as well as empirical MEG and functional magnetic resonance imaging (fMRI) data, we further demonstrated that all schemes were sensitive to identify network topology when the original networks were perturbed. In conclusion, uncorrected multilayer network analysis leads to biases. These biases may differ between centres and studies and could consequently lead to unreproducible results in a similar manner as for single layer networks. We therefore recommend using correction schemes prior to multilayer network analysis for group comparisons. Copyright © 2017 Elsevier Inc. All rights reserved.

Weighted complex network analysis of the Beijing subway system: Train and passenger flows

NASA Astrophysics Data System (ADS)

Feng, Jia; Li, Xiamiao; Mao, Baohua; Xu, Qi; Bai, Yun

2017-05-01

In recent years, complex network theory has become an important approach to the study of the structure and dynamics of traffic networks. However, because traffic data is difficult to collect, previous studies have usually focused on the physical topology of subway systems, whereas few studies have considered the characteristics of traffic flows through the network. Therefore, in this paper, we present a multi-layer model to analyze traffic flow patterns in subway networks, based on trip data and an operation timetable obtained from the Beijing Subway System. We characterize the patterns in terms of the spatiotemporal flow size distributions of both the train flow network and the passenger flow network. In addition, we describe the essential interactions between these two networks based on statistical analyses. The results of this study suggest that layered models of transportation systems can elucidate fundamental differences between the coexisting traffic flows and can also clarify the mechanism that causes these differences.

Memory Efficient Evaluations of Nonlinear Stochastic Equations and C3 Applications.

DTIC Science & Technology

1987-12-01

time. In the 1960’s, when Massachusetts Institute of Technology’s Marvin Minsky [16] and others criticized the concept on the grounds of .nsufficient...recognize letters of the alphabet [231. Minsky and Papert [16] criticized the perceptron, asserting that too little is known of the human brain to...1987). [15] Kinoshita, J. and Palevsky, N. G., "Computing with neural networks," High Technology (May 1987). . [16] Minsky , M. and Papert, S

Multiplex congruence network of natural numbers.

PubMed

Yan, Xiao-Yong; Wang, Wen-Xu; Chen, Guan-Rong; Shi, Ding-Hua

2016-03-31

Congruence theory has many applications in physical, social, biological and technological systems. Congruence arithmetic has been a fundamental tool for data security and computer algebra. However, much less attention was devoted to the topological features of congruence relations among natural numbers. Here, we explore the congruence relations in the setting of a multiplex network and unveil some unique and outstanding properties of the multiplex congruence network. Analytical results show that every layer therein is a sparse and heterogeneous subnetwork with a scale-free topology. Counterintuitively, every layer has an extremely strong controllability in spite of its scale-free structure that is usually difficult to control. Another amazing feature is that the controllability is robust against targeted attacks to critical nodes but vulnerable to random failures, which also differs from ordinary scale-free networks. The multi-chain structure with a small number of chain roots arising from each layer accounts for the strong controllability and the abnormal feature. The multiplex congruence network offers a graphical solution to the simultaneous congruences problem, which may have implication in cryptography based on simultaneous congruences. Our work also gains insight into the design of networks integrating advantages of both heterogeneous and homogeneous networks without inheriting their limitations.

Multiplex congruence network of natural numbers

NASA Astrophysics Data System (ADS)

Yan, Xiao-Yong; Wang, Wen-Xu; Chen, Guan-Rong; Shi, Ding-Hua

2016-03-01

Congruence theory has many applications in physical, social, biological and technological systems. Congruence arithmetic has been a fundamental tool for data security and computer algebra. However, much less attention was devoted to the topological features of congruence relations among natural numbers. Here, we explore the congruence relations in the setting of a multiplex network and unveil some unique and outstanding properties of the multiplex congruence network. Analytical results show that every layer therein is a sparse and heterogeneous subnetwork with a scale-free topology. Counterintuitively, every layer has an extremely strong controllability in spite of its scale-free structure that is usually difficult to control. Another amazing feature is that the controllability is robust against targeted attacks to critical nodes but vulnerable to random failures, which also differs from ordinary scale-free networks. The multi-chain structure with a small number of chain roots arising from each layer accounts for the strong controllability and the abnormal feature. The multiplex congruence network offers a graphical solution to the simultaneous congruences problem, which may have implication in cryptography based on simultaneous congruences. Our work also gains insight into the design of networks integrating advantages of both heterogeneous and homogeneous networks without inheriting their limitations.

Nonlinear Deep Kernel Learning for Image Annotation.

PubMed

Jiu, Mingyuan; Sahbi, Hichem

2017-02-08

Multiple kernel learning (MKL) is a widely used technique for kernel design. Its principle consists in learning, for a given support vector classifier, the most suitable convex (or sparse) linear combination of standard elementary kernels. However, these combinations are shallow and often powerless to capture the actual similarity between highly semantic data, especially for challenging classification tasks such as image annotation. In this paper, we redefine multiple kernels using deep multi-layer networks. In this new contribution, a deep multiple kernel is recursively defined as a multi-layered combination of nonlinear activation functions, each one involves a combination of several elementary or intermediate kernels, and results into a positive semi-definite deep kernel. We propose four different frameworks in order to learn the weights of these networks: supervised, unsupervised, kernel-based semisupervised and Laplacian-based semi-supervised. When plugged into support vector machines (SVMs), the resulting deep kernel networks show clear gain, compared to several shallow kernels for the task of image annotation. Extensive experiments and analysis on the challenging ImageCLEF photo annotation benchmark, the COREL5k database and the Banana dataset validate the effectiveness of the proposed method.

Optimal exponential synchronization of general chaotic delayed neural networks: an LMI approach.

PubMed

Liu, Meiqin

2009-09-01

This paper investigates the optimal exponential synchronization problem of general chaotic neural networks with or without time delays by virtue of Lyapunov-Krasovskii stability theory and the linear matrix inequality (LMI) technique. This general model, which is the interconnection of a linear delayed dynamic system and a bounded static nonlinear operator, covers several well-known neural networks, such as Hopfield neural networks, cellular neural networks (CNNs), bidirectional associative memory (BAM) networks, and recurrent multilayer perceptrons (RMLPs) with or without delays. Using the drive-response concept, time-delay feedback controllers are designed to synchronize two identical chaotic neural networks as quickly as possible. The control design equations are shown to be a generalized eigenvalue problem (GEVP) which can be easily solved by various convex optimization algorithms to determine the optimal control law and the optimal exponential synchronization rate. Detailed comparisons with existing results are made and numerical simulations are carried out to demonstrate the effectiveness of the established synchronization laws.

Cross-domain and multi-task transfer learning of deep convolutional neural network for breast cancer diagnosis in digital breast tomosynthesis

NASA Astrophysics Data System (ADS)

Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A.; Richter, Caleb; Cha, Kenny

2018-02-01

We propose a cross-domain, multi-task transfer learning framework to transfer knowledge learned from non-medical images by a deep convolutional neural network (DCNN) to medical image recognition task while improving the generalization by multi-task learning of auxiliary tasks. A first stage cross-domain transfer learning was initiated from ImageNet trained DCNN to mammography trained DCNN. 19,632 regions-of-interest (ROI) from 2,454 mass lesions were collected from two imaging modalities: digitized-screen film mammography (SFM) and full-field digital mammography (DM), and split into training and test sets. In the multi-task transfer learning, the DCNN learned the mass classification task simultaneously from the training set of SFM and DM. The best transfer network for mammography was selected from three transfer networks with different number of convolutional layers frozen. The performance of single-task and multitask transfer learning on an independent SFM test set in terms of the area under the receiver operating characteristic curve (AUC) was 0.78+/-0.02 and 0.82+/-0.02, respectively. In the second stage cross-domain transfer learning, a set of 12,680 ROIs from 317 mass lesions on DBT were split into validation and independent test sets. We first studied the data requirements for the first stage mammography trained DCNN by varying the mammography training data from 1% to 100% and evaluated its learning on the DBT validation set in inference mode. We found that the entire available mammography set provided the best generalization. The DBT validation set was then used to train only the last four fully connected layers, resulting in an AUC of 0.90+/-0.04 on the independent DBT test set.

A novel multi-model neuro-fuzzy-based MPPT for three-phase grid-connected photovoltaic system

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chaouachi, Aymen; Kamel, Rashad M.; Nagasaka, Ken

This paper presents a novel methodology for Maximum Power Point Tracking (MPPT) of a grid-connected 20 kW photovoltaic (PV) system using neuro-fuzzy network. The proposed method predicts the reference PV voltage guarantying optimal power transfer between the PV generator and the main utility grid. The neuro-fuzzy network is composed of a fuzzy rule-based classifier and three multi-layered feed forwarded Artificial Neural Networks (ANN). Inputs of the network (irradiance and temperature) are classified before they are fed into the appropriated ANN for either training or estimation process while the output is the reference voltage. The main advantage of the proposed methodology,more » comparing to a conventional single neural network-based approach, is the distinct generalization ability regarding to the nonlinear and dynamic behavior of a PV generator. In fact, the neuro-fuzzy network is a neural network based multi-model machine learning that defines a set of local models emulating the complex and nonlinear behavior of a PV generator under a wide range of operating conditions. Simulation results under several rapid irradiance variations proved that the proposed MPPT method fulfilled the highest efficiency comparing to a conventional single neural network and the Perturb and Observe (P and O) algorithm dispositive. (author)« less

Spin switches for compact implementation of neuron and synapse

NASA Astrophysics Data System (ADS)

Quang Diep, Vinh; Sutton, Brian; Behin-Aein, Behtash; Datta, Supriyo

2014-06-01

Nanomagnets driven by spin currents provide a natural implementation for a neuron and a synapse: currents allow convenient summation of multiple inputs, while the magnet provides the threshold function. The objective of this paper is to explore the possibility of a hardware neural network implementation using a spin switch (SS) as its basic building block. SS is a recently proposed device based on established technology with a transistor-like gain and input-output isolation. This allows neural networks to be constructed with purely passive interconnections without intervening clocks or amplifiers. The weights for the neural network are conveniently adjusted through analog voltages that can be stored in a non-volatile manner in an underlying CMOS layer using a floating gate low dropout voltage regulator. The operation of a multi-layer SS neural network designed for character recognition is demonstrated using a standard simulation model based on coupled Landau-Lifshitz-Gilbert equations, one for each magnet in the network.

Software-Defined Architectures for Spectrally Efficient Cognitive Networking in Extreme Environments

NASA Astrophysics Data System (ADS)

Sklivanitis, Georgios

The objective of this dissertation is the design, development, and experimental evaluation of novel algorithms and reconfigurable radio architectures for spectrally efficient cognitive networking in terrestrial, airborne, and underwater environments. Next-generation wireless communication architectures and networking protocols that maximize spectrum utilization efficiency in congested/contested or low-spectral availability (extreme) communication environments can enable a rich body of applications with unprecedented societal impact. In recent years, underwater wireless networks have attracted significant attention for military and commercial applications including oceanographic data collection, disaster prevention, tactical surveillance, offshore exploration, and pollution monitoring. Unmanned aerial systems that are autonomously networked and fully mobile can assist humans in extreme or difficult-to-reach environments and provide cost-effective wireless connectivity for devices without infrastructure coverage. Cognitive radio (CR) has emerged as a promising technology to maximize spectral efficiency in dynamically changing communication environments by adaptively reconfiguring radio communication parameters. At the same time, the fast developing technology of software-defined radio (SDR) platforms has enabled hardware realization of cognitive radio algorithms for opportunistic spectrum access. However, existing algorithmic designs and protocols for shared spectrum access do not effectively capture the interdependencies between radio parameters at the physical (PHY), medium-access control (MAC), and network (NET) layers of the network protocol stack. In addition, existing off-the-shelf radio platforms and SDR programmable architectures are far from fulfilling runtime adaptation and reconfiguration across PHY, MAC, and NET layers. Spectrum allocation in cognitive networks with multi-hop communication requirements depends on the location, network traffic load, and interference profile at each network node. As a result, the development and implementation of algorithms and cross-layer reconfigurable radio platforms that can jointly treat space, time, and frequency as a unified resource to be dynamically optimized according to inter- and intra-network interference constraints is of fundamental importance. In the next chapters, we present novel algorithmic and software/hardware implementation developments toward the deployment of spectrally efficient terrestrial, airborne, and underwater wireless networks. In Chapter 1 we review the state-of-art in commercially available SDR platforms, describe their software and hardware capabilities, and classify them based on their ability to enable rapid prototyping and advance experimental research in wireless networks. Chapter 2 discusses system design and implementation details toward real-time evaluation of a software-radio platform for all-spectrum cognitive channelization in the presence of narrowband or wideband primary stations. All-spectrum channelization is achieved by designing maximum signal-to-interference-plus-noise ratio (SINR) waveforms that span the whole continuum of the device-accessible spectrum, while satisfying peak power and interference temperature (IT) constraints for the secondary and primary users, respectively. In Chapter 3, we introduce the concept of all-spectrum channelization based on max-SINR optimized sparse-binary waveforms, we propose optimal and suboptimal waveform design algorithms, and evaluate their SINR and bit-error-rate (BER) performance in an SDR testbed. Chapter 4 considers the problem of channel estimation with minimal pilot signaling in multi-cell multi-user multi-input multi-output (MIMO) systems with very large antenna arrays at the base station, and proposes a least-squares (LS)-type algorithm that iteratively extracts channel and data estimates from a short record of data measurements. Our algorithmic developments toward spectrally-efficient cognitive networking through joint optimization of channel access code-waveforms and routes in a multi-hop network are described in Chapter 5. Algorithmic designs are software optimized on heterogeneous multi-core general-purpose processor (GPP)-based SDR architectures by leveraging a novel software-radio framework that offers self-optimization and real-time adaptation capabilities at the PHY, MAC, and NET layers of the network protocol stack. Our system design approach is experimentally validated under realistic conditions in a large-scale hybrid ground-air testbed deployment. Chapter 6 reviews the state-of-art in software and hardware platforms for underwater wireless networking and proposes a software-defined acoustic modem prototype that enables (i) cognitive reconfiguration of PHY/MAC parameters, and (ii) cross-technology communication adaptation. The proposed modem design is evaluated in terms of effective communication data rate in both water tank and lake testbed setups. In Chapter 7, we present a novel receiver configuration for code-waveform-based multiple-access underwater communications. The proposed receiver is fully reconfigurable and executes (i) all-spectrum cognitive channelization, and (ii) combined synchronization, channel estimation, and demodulation. Experimental evaluation in terms of SINR and BER show that all-spectrum channelization is a powerful proposition for underwater communications. At the same time, the proposed receiver design can significantly enhance bandwidth utilization. Finally, in Chapter 8, we focus on challenging practical issues that arise in underwater acoustic sensor network setups where co-located multi-antenna sensor deployment is not feasible due to power, computation, and hardware limitations, and design, implement, and evaluate an underwater receiver structure that accounts for multiple carrier frequency and timing offsets in virtual (distributed) MIMO underwater systems.

Ortho Image and DTM Generation with Intelligent Methods

NASA Astrophysics Data System (ADS)

Bagheri, H.; Sadeghian, S.

2013-10-01

Nowadays the artificial intelligent algorithms has considered in GIS and remote sensing. Genetic algorithm and artificial neural network are two intelligent methods that are used for optimizing of image processing programs such as edge extraction and etc. these algorithms are very useful for solving of complex program. In this paper, the ability and application of genetic algorithm and artificial neural network in geospatial production process like geometric modelling of satellite images for ortho photo generation and height interpolation in raster Digital Terrain Model production process is discussed. In first, the geometric potential of Ikonos-2 and Worldview-2 with rational functions, 2D & 3D polynomials were tested. Also comprehensive experiments have been carried out to evaluate the viability of the genetic algorithm for optimization of rational function, 2D & 3D polynomials. Considering the quality of Ground Control Points, the accuracy (RMSE) with genetic algorithm and 3D polynomials method for Ikonos-2 Geo image was 0.508 pixel sizes and the accuracy (RMSE) with GA algorithm and rational function method for Worldview-2 image was 0.930 pixel sizes. For more another optimization artificial intelligent methods, neural networks were used. With the use of perceptron network in Worldview-2 image, a result of 0.84 pixel sizes with 4 neurons in middle layer was gained. The final conclusion was that with artificial intelligent algorithms it is possible to optimize the existing models and have better results than usual ones. Finally the artificial intelligence methods, like genetic algorithms as well as neural networks, were examined on sample data for optimizing interpolation and for generating Digital Terrain Models. The results then were compared with existing conventional methods and it appeared that these methods have a high capacity in heights interpolation and that using these networks for interpolating and optimizing the weighting methods based on inverse distance leads to a high accurate estimation of heights.

Characterization of cementitiously stabilized subgrades for mechanistic-empirical pavement design

NASA Astrophysics Data System (ADS)

Solanki, Pranshoo

Pavements are vulnerable to subgrade layer performance because it acts as a foundation. Due to increase in the truck traffic, pavement engineers are challenged to build more strong and long-lasting pavements. To increase the load-bearing capacity of pavements, subgrade layer is often stabilized with cementitious additives. Thus, an overall characterization of stabilized subgrade layer is important for enhanced short- and long-term pavement performance. In this study, the effect of type and amount of additive on the short-term performance in terms of material properties recommended by the new Mechanistic-Empirical Pavement Design Guide (MEPDG) is examined. A total of four soils commonly encountered as subgrades in Oklahoma are utilized. Results show that the changes in the Mr, ME and UCS values stabilized specimens depend on the soil type and properties of additives. The long-term performance (or durability) of stabilized soil specimens is investigated by conducting freeze-thaw (F-T) cycling, vacuum saturation and tube suction tests on 7-day cured P-, K- and C-soil specimens stabilized with 6% lime, 10% CFA and 10% CKD. This study is motivated by the fact that during the service life of pavement stabilized layers are subjected to F-T cycles and moisture variations. It is found that that UCS value of all the stabilized specimens decreased with increase in the number of F-T cycles. A strong correlation was observed between UCS values retained after vacuum saturation and F-T cycles indicating that vacuum saturation could be used as a time-efficient and inexpensive method for evaluating durability of stabilized soils. In this study, short- and long-term observations from stabilization of sulfate bearing soil with locally available low (CFA), moderate (CKD) and high (lime) calcium-based stabilizers are determined to evaluate and compare the effect of additive type on the phenomenon of sulfate-induced heave. The impact of different factors on the development of the ettringite, responsible for sulfate-induced heaving, is also discussed. For Level 2 design of pavements, a total of four stress-based statistical models and two feed-forward-type artificial neural network (ANN) models, are evaluated for predicting resilient modulus of 28-day cured stabilized specimens. Specifically, one semi-log stress-based, three log-log stress-based, one Multi-Layer Perceptrons Network (MLPN), and one Radial Basis Function Network (RBFN) are developed. Overall, semi-log stress-based and MLPN neural network are found to show best acceptable performance for the present evaluation and validation datasets. Further, correlations are presented for stress-based models to correlate Mr with compacted specimen characteristics and soil/additive properties. Additionally, the effect of type of additive on indirect tensile and fatigue characteristics of selected stabilized P- and V-soil is evaluated. This study is based on the fact that stabilized layer is subjected to tensile stresses under wheel loading. Thus, the resilient modulus in tension (M rt), fatigue life and strength in tension (sigmat) or flexure (represented by modulus of rupture, MOR) becomes another important design parameter within the mechanistic framework. Cylindrical specimens are prepared, cured for 28 days and subjected to different stress sequences in indirect tension to study the Mrt. On the other hand, stabilized beam specimens are compacted using a Linear Kneading Compactor and subjected to repeated cycles of reloading-unloading after 28 days of curing in a four-point beam fatigue apparatus for evaluating fatigue life and flexural stiffness. It is found that all three additives improved the Mrt, sigmat and MOR values; however, degree of improvement varied with the type of additive and soil. This study encompasses the differences in the design of semi-rigid pavements developed using AASHTO 1993 and AASHTO 2002 MEPDG methodologies. Further, the design curves for fatigue performance prediction of stabilized layers are developed for different stabilized pavement sections. Knowledge gained from the parametric analysis of different sections using AASHTO 1993 and MEPDG is expected to be useful to pavement designers and others in implementation of the new MEPDG for future pavement design. (Abstract shortened by UMI.)

Nonparametric Representations for Integrated Inference, Control, and Sensing

DTIC Science & Technology

2015-10-01

Learning (ICML), 2013. [20] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. DeCAF: A deep ...unlimited. Multi-layer feature learning “SuperVision” Convolutional Neural Network (CNN) ImageNet Classification with Deep Convolutional Neural Networks...to develop a new framework for autonomous operations that will extend the state of the art in distributed learning and modeling from data, and

Rochester Connectionist Papers. 1979-1985

DTIC Science & Technology

1985-12-01

updated and improved version of the thesis account of recent neurolinguistic data. Fanty, M., "Context-free parsing in connectionist networks." TR 174...April 1982. Our first large program in the connectionist paradigm. It simulates a multi- layer network for recognizing line drawings of Origami figures...The program successfully deals with noise and simple occlusion and the thesis incorporates many key ideas on designing and running large models. Small

On structure-exploiting trust-region regularized nonlinear least squares algorithms for neural-network learning.

PubMed

Mizutani, Eiji; Demmel, James W

2003-01-01

This paper briefly introduces our numerical linear algebra approaches for solving structured nonlinear least squares problems arising from 'multiple-output' neural-network (NN) models. Our algorithms feature trust-region regularization, and exploit sparsity of either the 'block-angular' residual Jacobian matrix or the 'block-arrow' Gauss-Newton Hessian (or Fisher information matrix in statistical sense) depending on problem scale so as to render a large class of NN-learning algorithms 'efficient' in both memory and operation costs. Using a relatively large real-world nonlinear regression application, we shall explain algorithmic strengths and weaknesses, analyzing simulation results obtained by both direct and iterative trust-region algorithms with two distinct NN models: 'multilayer perceptrons' (MLP) and 'complementary mixtures of MLP-experts' (or neuro-fuzzy modular networks).

Using recorded sound spectra profile as input data for real-time short-term urban road-traffic-flow estimation.

PubMed

Torija, Antonio J; Ruiz, Diego P

2012-10-01

Road traffic has a heavy impact on the urban sound environment, constituting the main source of noise and widely dominating its spectral composition. In this context, our research investigates the use of recorded sound spectra as input data for the development of real-time short-term road traffic flow estimation models. For this, a series of models based on the use of Multilayer Perceptron Neural Networks, multiple linear regression, and the Fisher linear discriminant were implemented to estimate road traffic flow as well as to classify it according to the composition of heavy vehicles and motorcycles/mopeds. In view of the results, the use of the 50-400 Hz and 1-2.5 kHz frequency ranges as input variables in multilayer perceptron-based models successfully estimated urban road traffic flow with an average percentage of explained variance equal to 86%, while the classification of the urban road traffic flow gave an average success rate of 96.1%. Copyright © 2012 Elsevier B.V. All rights reserved.

River flow simulation using a multilayer perceptron-firefly algorithm model

NASA Astrophysics Data System (ADS)

Darbandi, Sabereh; Pourhosseini, Fatemeh Akhoni

2018-06-01

River flow estimation using records of past time series is importance in water resources engineering and management and is required in hydrologic studies. In the past two decades, the approaches based on the artificial neural networks (ANN) were developed. River flow modeling is a non-linear process and highly affected by the inputs to the modeling. In this study, the best input combination of the models was identified using the Gamma test then MLP-ANN and hybrid multilayer perceptron (MLP-FFA) is used to forecast monthly river flow for a set of time intervals using observed data. The measurements from three gauge at Ajichay watershed, East Azerbaijani, were used to train and test the models approach for the period from January 2004 to July 2016. Calibration and validation were performed within the same period for MLP-ANN and MLP-FFA models after the preparation of the required data. Statistics, the root mean square error and determination coefficient, are used to verify outputs from MLP-ANN to MLP-FFA models. The results show that MLP-FFA model is satisfactory for monthly river flow simulation in study area.

Ultra-high aggregate bandwidth two-dimensional multiple-wavelength diode laser arrays

NASA Astrophysics Data System (ADS)

Chang-Hasnain, Connie

1994-04-01

Two-dimensional (2D) multi-wavelength vertical cavity surface emitting laser (VCSEL) arrays is promising for ultrahigh aggregate capacity optical networks. A 2D VCSEL array emitting 140 distinct wavelengths was reported by implementing a spatially graded layer in the VCSEL structure, which in turn creates a wavelength spread. In this program, we concentrated on novel epitaxial growth techniques to make reproducible and repeatable multi-wavelength VCSEL arrays.

Self-Organized Information Processing in Neuronal Networks: Replacing Layers in Deep Networks by Dynamics

NASA Astrophysics Data System (ADS)

Kirst, Christoph

It is astonishing how the sub-parts of a brain co-act to produce coherent behavior. What are mechanism that coordinate information processing and communication and how can those be changed flexibly in order to cope with variable contexts? Here we show that when information is encoded in the deviations around a collective dynamical reference state of a recurrent network the propagation of these fluctuations is strongly dependent on precisely this underlying reference. Information here 'surfs' on top of the collective dynamics and switching between states enables fast and flexible rerouting of information. This in turn affects local processing and consequently changes in the global reference dynamics that re-regulate the distribution of information. This provides a generic mechanism for self-organized information processing as we demonstrate with an oscillatory Hopfield network that performs contextual pattern recognition. Deep neural networks have proven to be very successful recently. Here we show that generating information channels via collective reference dynamics can effectively compress a deep multi-layer architecture into a single layer making this mechanism a promising candidate for the organization of information processing in biological neuronal networks.

Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor.

PubMed

Pandey, Daya Shankar; Das, Saptarshi; Pan, Indranil; Leahy, James J; Kwapinski, Witold

2016-12-01

In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHV p ) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier. Copyright © 2016 Elsevier Ltd. All rights reserved.

Optimal Path Analyzer (Version 1.0)

DTIC Science & Technology

1989-10-01

now be easier for Y to stimulate X to produce an output in the future. In 1951, Dean Edmonds and Marvin Minsky built a learning machine. In 1958...J., "Profiles: AI, Marvin Minsky ," The New Yorker, pp. 50-126. Eliot, Lance B., "Neural Networks, Part 1: What are they and why is everybody so...34 Bulletin of Mathematical Biophysics, 1943, Vol. 5, pg. 115-133. Minsky , Marvin , and Seymour Papert, "Perceptrons," The MIT Press, 1969, pg. 10

CNNH_PSS: protein 8-class secondary structure prediction by convolutional neural network with highway.

PubMed

Zhou, Jiyun; Wang, Hongpeng; Zhao, Zhishan; Xu, Ruifeng; Lu, Qin

2018-05-08

Protein secondary structure is the three dimensional form of local segments of proteins and its prediction is an important problem in protein tertiary structure prediction. Developing computational approaches for protein secondary structure prediction is becoming increasingly urgent. We present a novel deep learning based model, referred to as CNNH_PSS, by using multi-scale CNN with highway. In CNNH_PSS, any two neighbor convolutional layers have a highway to deliver information from current layer to the output of the next one to keep local contexts. As lower layers extract local context while higher layers extract long-range interdependencies, the highways between neighbor layers allow CNNH_PSS to have ability to extract both local contexts and long-range interdependencies. We evaluate CNNH_PSS on two commonly used datasets: CB6133 and CB513. CNNH_PSS outperforms the multi-scale CNN without highway by at least 0.010 Q8 accuracy and also performs better than CNF, DeepCNF and SSpro8, which cannot extract long-range interdependencies, by at least 0.020 Q8 accuracy, demonstrating that both local contexts and long-range interdependencies are indeed useful for prediction. Furthermore, CNNH_PSS also performs better than GSM and DCRNN which need extra complex model to extract long-range interdependencies. It demonstrates that CNNH_PSS not only cost less computer resource, but also achieves better predicting performance. CNNH_PSS have ability to extracts both local contexts and long-range interdependencies by combing multi-scale CNN and highway network. The evaluations on common datasets and comparisons with state-of-the-art methods indicate that CNNH_PSS is an useful and efficient tool for protein secondary structure prediction.

Artificial neural networks applied to forecasting time series.

PubMed

Montaño Moreno, Juan J; Palmer Pol, Alfonso; Muñoz Gracia, Pilar

2011-04-01

This study offers a description and comparison of the main models of Artificial Neural Networks (ANN) which have proved to be useful in time series forecasting, and also a standard procedure for the practical application of ANN in this type of task. The Multilayer Perceptron (MLP), Radial Base Function (RBF), Generalized Regression Neural Network (GRNN), and Recurrent Neural Network (RNN) models are analyzed. With this aim in mind, we use a time series made up of 244 time points. A comparative study establishes that the error made by the four neural network models analyzed is less than 10%. In accordance with the interpretation criteria of this performance, it can be concluded that the neural network models show a close fit regarding their forecasting capacity. The model with the best performance is the RBF, followed by the RNN and MLP. The GRNN model is the one with the worst performance. Finally, we analyze the advantages and limitations of ANN, the possible solutions to these limitations, and provide an orientation towards future research.

Comparison of different artificial neural network architectures in modeling of Chlorella sp. flocculation.

PubMed

Zenooz, Alireza Moosavi; Ashtiani, Farzin Zokaee; Ranjbar, Reza; Nikbakht, Fatemeh; Bolouri, Oberon

2017-07-03

Biodiesel production from microalgae feedstock should be performed after growth and harvesting of the cells, and the most feasible method for harvesting and dewatering of microalgae is flocculation. Flocculation modeling can be used for evaluation and prediction of its performance under different affective parameters. However, the modeling of flocculation in microalgae is not simple and has not performed yet, under all experimental conditions, mostly due to different behaviors of microalgae cells during the process under different flocculation conditions. In the current study, the modeling of microalgae flocculation is studied with different neural network architectures. Microalgae species, Chlorella sp., was flocculated with ferric chloride under different conditions and then the experimental data modeled using artificial neural network. Neural network architectures of multilayer perceptron (MLP) and radial basis function architectures, failed to predict the targets successfully, though, modeling was effective with ensemble architecture of MLP networks. Comparison between the performances of the ensemble and each individual network explains the ability of the ensemble architecture in microalgae flocculation modeling.

Inter-allotropic transformations in the heterogeneous carbon nanotube networks.

PubMed

Jung, Hyun Young; Jung, Sung Mi; Kim, Dong Won; Jung, Yung Joon

2017-01-19

The allotropic transformations of carbon provide an immense technological interest for tailoring the desired molecular structures in the scalable nanoelectronic devices. Herein, we explore the effects of morphology and geometric alignment of the nanotubes for the re-engineering of carbon bonds in the heterogeneous carbon nanotube (CNT) networks. By applying alternating voltage pulses and electrical forces, the single-walled CNTs in networks were predominantly transformed into other predetermined sp 2 carbon structures (multi-walled CNTs and multi-layered graphitic nanoribbons), showing a larger intensity in a coalescence-induced mode of Raman spectra with the increasing channel width. Moreover, the transformed networks have a newly discovered sp 2 -sp 3 hybrid nanostructures in accordance with the alignment. The sp 3 carbon structures at the small channel are controlled, such that they contain up to about 29.4% networks. This study provides a controllable method for specific types of inter-allotropic transformations/hybridizations, which opens up the further possibility for the engineering of nanocarbon allotropes in the robust large-scale network-based devices.

Biochemical component identification by plasmonic improved whispering gallery mode optical resonance based sensor

NASA Astrophysics Data System (ADS)

Saetchnikov, Vladimir A.; Tcherniavskaia, Elina A.; Saetchnikov, Anton V.; Schweiger, Gustav; Ostendorf, Andreas

2014-05-01

Experimental data on detection and identification of variety of biochemical agents, such as proteins, microelements, antibiotic of different generation etc. in both single and multi component solutions under varied in wide range concentration analyzed on the light scattering parameters of whispering gallery mode optical resonance based sensor are represented. Multiplexing on parameters and components has been realized using developed fluidic sensor cell with fixed in adhesive layer dielectric microspheres and data processing. Biochemical component identification has been performed by developed network analysis techniques. Developed approach is demonstrated to be applicable both for single agent and for multi component biochemical analysis. Novel technique based on optical resonance on microring structures, plasmon resonance and identification tools has been developed. To improve a sensitivity of microring structures microspheres fixed by adhesive had been treated previously by gold nanoparticle solution. Another technique used thin film gold layers deposited on the substrate below adhesive. Both biomolecule and nanoparticle injections caused considerable changes of optical resonance spectra. Plasmonic gold layers under optimized thickness also improve parameters of optical resonance spectra. Biochemical component identification has been also performed by developed network analysis techniques both for single and for multi component solution. So advantages of plasmon enhancing optical microcavity resonance with multiparameter identification tools is used for development of a new platform for ultra sensitive label-free biomedical sensor.

Supervised Machine Learning for Regionalization of Environmental Data: Distribution of Uranium in Groundwater in Ukraine

NASA Astrophysics Data System (ADS)

Govorov, Michael; Gienko, Gennady; Putrenko, Viktor

2018-05-01

In this paper, several supervised machine learning algorithms were explored to define homogeneous regions of con-centration of uranium in surface waters in Ukraine using multiple environmental parameters. The previous study was focused on finding the primary environmental parameters related to uranium in ground waters using several methods of spatial statistics and unsupervised classification. At this step, we refined the regionalization using Artifi-cial Neural Networks (ANN) techniques including Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Convolutional Neural Network (CNN). The study is focused on building local ANN models which may significantly improve the prediction results of machine learning algorithms by taking into considerations non-stationarity and autocorrelation in spatial data.

Agent-based modeling of porous scaffold degradation and vascularization: Optimal scaffold design based on architecture and degradation dynamics.

PubMed

Mehdizadeh, Hamidreza; Bayrak, Elif S; Lu, Chenlin; Somo, Sami I; Akar, Banu; Brey, Eric M; Cinar, Ali

2015-11-01

A multi-layer agent-based model (ABM) of biomaterial scaffold vascularization is extended to consider the effects of scaffold degradation kinetics on blood vessel formation. A degradation model describing the bulk disintegration of porous hydrogels is incorporated into the ABM. The combined degradation-angiogenesis model is used to investigate growing blood vessel networks in the presence of a degradable scaffold structure. Simulation results indicate that higher porosity, larger mean pore size, and rapid degradation allow faster vascularization when not considering the structural support of the scaffold. However, premature loss of structural support results in failure for the material. A strategy using multi-layer scaffold with different degradation rates in each layer was investigated as a way to address this issue. Vascularization was improved with the multi-layered scaffold model compared to the single-layer model. The ABM developed provides insight into the characteristics that influence the selection of optimal geometric parameters and degradation behavior of scaffolds, and enables easy refinement of the model as new knowledge about the underlying biological phenomena becomes available. This paper proposes a multi-layer agent-based model (ABM) of biomaterial scaffold vascularization integrated with a structural-kinetic model describing bulk degradation of porous hydrogels to consider the effects of scaffold degradation kinetics on blood vessel formation. This enables the assessment of scaffold characteristics and in particular the disintegration characteristics of the scaffold on angiogenesis. Simulation results indicate that higher porosity, larger mean pore size, and rapid degradation allow faster vascularization when not considering the structural support of the scaffold. However, premature loss of structural support by scaffold disintegration results in failure of the material and disruption of angiogenesis. A strategy using multi-layer scaffold with different degradation rates in each layer was investigated as away to address this issue. Vascularization was improved with the multi-layered scaffold model compared to the single-layer model. The ABM developed provides insight into the characteristics that influence the selection of optimal geometric and degradation characteristics of tissue engineering scaffolds. Copyright © 2015 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Identifying individuality and variability in team tactics by means of statistical shape analysis and multilayer perceptrons.

PubMed

Jäger, Jörg M; Schöllhorn, Wolfgang I

2012-04-01

Offensive and defensive systems of play represent important aspects of team sports. They include the players' positions at certain situations during a match, i.e., when players have to be on specific positions on the court. Patterns of play emerge based on the formations of the players on the court. Recognition of these patterns is important to react adequately and to adjust own strategies to the opponent. Furthermore, the ability to apply variable patterns of play seems to be promising since they make it harder for the opponent to adjust. The purpose of this study is to identify different team tactical patterns in volleyball and to analyze differences in variability. Overall 120 standard situations of six national teams in women's volleyball are analyzed during a world championship tournament. Twenty situations from each national team are chosen, including the base defence position (start configuration) and the two players block with middle back deep (end configuration). The shapes of the defence formations at the start and end configurations during the defence of each national team as well as the variability of these defence formations are statistically analyzed. Furthermore these shapes data are used to train multilayer perceptrons in order to test whether artificial neural networks can recognize the teams by their tactical patterns. Results show significant differences between the national teams in both the base defence position at the start and the two players block with middle back deep at the end of the standard defence situation. Furthermore, the national teams show significant differences in variability of the defence systems and start-positions are more variable than the end-positions. Multilayer perceptrons are able to recognize the teams at an average of 98.5%. It is concluded that defence systems in team sports are highly individual at a competitive level and variable even in standard situations. Artificial neural networks can be used to recognize teams by the shapes of the players' configurations. These findings support the concept that tactics and strategy have to be adapted for the team and need to be flexible in order to be successful. Copyright © 2010 Elsevier B.V. All rights reserved.

Dense deconvolution net: Multi path fusion and dense deconvolution for high resolution skin lesion segmentation.

PubMed

He, Xinzi; Yu, Zhen; Wang, Tianfu; Lei, Baiying; Shi, Yiyan

2018-01-01

Dermoscopy imaging has been a routine examination approach for skin lesion diagnosis. Accurate segmentation is the first step for automatic dermoscopy image assessment. The main challenges for skin lesion segmentation are numerous variations in viewpoint and scale of skin lesion region. To handle these challenges, we propose a novel skin lesion segmentation network via a very deep dense deconvolution network based on dermoscopic images. Specifically, the deep dense layer and generic multi-path Deep RefineNet are combined to improve the segmentation performance. The deep representation of all available layers is aggregated to form the global feature maps using skip connection. Also, the dense deconvolution layer is leveraged to capture diverse appearance features via the contextual information. Finally, we apply the dense deconvolution layer to smooth segmentation maps and obtain final high-resolution output. Our proposed method shows the superiority over the state-of-the-art approaches based on the public available 2016 and 2017 skin lesion challenge dataset and achieves the accuracy of 96.0% and 93.9%, which obtained a 6.0% and 1.2% increase over the traditional method, respectively. By utilizing Dense Deconvolution Net, the average time for processing one testing images with our proposed framework was 0.253 s.

Trade-off analysis of discharge-desiltation-turbidity and ANN analysis on sedimentation of a combined reservoir-reach system under multi-phase and multi-layer conjunctive releasing operation

NASA Astrophysics Data System (ADS)

Huang, Chien-Lin; Hsu, Nien-Sheng; Wei, Chih-Chiang; Yao, Chun-Hao

2017-10-01

Multi-objective reservoir operation considering the trade-off of discharge-desiltation-turbidity during typhoons and sediment concentration (SC) simulation modeling are the vital components for sustainable reservoir management. The purposes of this study were (1) to analyze the multi-layer release trade-offs between reservoir desiltation and intake turbidity of downstream purification plants and thus propose a superior conjunctive operation strategy and (2) to develop ANFIS-based (adaptive network-based fuzzy inference system) and RTRLNN-based (real-time recurrent learning neural networks) substitute SC simulation models. To this end, this study proposed a methodology to develop (1) a series of multi-phase and multi-layer sediment-flood conjunctive release modes and (2) a specialized SC numerical model for a combined reservoir-reach system. The conjunctive release modes involve (1) an optimization model where the decision variables are multi-phase reduction/scaling ratios and the timings to generate a superior total release hydrograph for flood control (Phase I: phase prior to flood arrival, Phase II/III: phase prior to/subsequent to peak flow) and (2) a combination method with physical limitations regarding separation of the singular hydrograph into multi-layer release hydrographs for sediment control. This study employed the featured signals obtained from statistical quartiles/sediment duration curve in mesh segmentation, and an iterative optimization model with a sediment unit response matrix and corresponding geophysical-based acceleration factors, for efficient parameter calibration. This research applied the developed methodology to the Shihmen Reservoir basin in Taiwan. The trade-off analytical results using Typhoons Sinlaku and Jangmi as case examples revealed that owing to gravity current and re-suspension effects, Phase I + II can de-silt safely without violating the intake's turbidity limitation before reservoir discharge reaches 2238 m3/s; however, Phase III can only de-silt after the release at spillway reaches 827 m3/s, and before reservoir discharge reaches 1924 m3/s, with corresponding maximum desiltation ratio being 0.221 and 0.323, respectively. Moreover, the model construction results demonstrated that the self-adaption/fuzzy inference of ANFIS can effectively simulate the SC hydrograph in an unsteady state for suspended load-dominated water bodies, and that the real-time recurrent deterministic routing of RTRLNN can accurately simulate that of a bedload-dominated flow regime.

Dynamical origins of the community structure of an online multi-layer society

NASA Astrophysics Data System (ADS)

Klimek, Peter; Diakonova, Marina; Eguíluz, Víctor M.; San Miguel, Maxi; Thurner, Stefan

2016-08-01

Social structures emerge as a result of individuals managing a variety of different social relationships. Societies can be represented as highly structured dynamic multiplex networks. Here we study the dynamical origins of the specific community structures of a large-scale social multiplex network of a human society that interacts in a virtual world of a massive multiplayer online game. There we find substantial differences in the community structures of different social actions, represented by the various layers in the multiplex network. Community sizes distributions are either fat-tailed or appear to be centered around a size of 50 individuals. To understand these observations we propose a voter model that is built around the principle of triadic closure. It explicitly models the co-evolution of node- and link-dynamics across different layers of the multiplex network. Depending on link and node fluctuation probabilities, the model exhibits an anomalous shattered fragmentation transition, where one layer fragments from one large component into many small components. The observed community size distributions are in good agreement with the predicted fragmentation in the model. This suggests that several detailed features of the fragmentation in societies can be traced back to the triadic closure processes.

A comparison between HMLP and HRBF for attitude control.

PubMed

Fortuna, L; Muscato, G; Xibilia, M G

2001-01-01

In this paper the problem of controlling the attitude of a rigid body, such as a Spacecraft, in three-dimensional space is approached by introducing two new control strategies developed in hypercomplex algebra. The proposed approaches are based on two parallel controllers, both derived in quaternion algebra. The first is a feedback controller of the proportional derivative (PD) type, while the second is a feedforward controller, which is implemented either by means of a hypercomplex multilayer perceptron (HMLP) neural network or by means of a hypercomplex radial basis function (HRBF) neural network. Several simulations show the performance of the two approaches. The results are also compared with a classical PD controller and with an adaptive controller, showing the improvements obtained by using neural networks, especially when an external disturbance acts on the rigid body. In particular the HMLP network gave better results when considering trajectories not presented during the learning phase.

Lithofacies classification of the Barnett Shale gas reservoir using neural network

NASA Astrophysics Data System (ADS)

Aliouane, Leila; Ouadfeul, Sid-Ali

2017-04-01

Here, we show the contribution of the artificial intelligence such as neural network to predict the lithofacies in the lower Barnett shale gas reservoir. The Multilayer Perceptron (MLP) neural network with Hidden Weight Optimization Algorithm is used. The input is raw well-logs data recorded in a horizontal well drilled in the Lower Barnett shale formation, however the output is the concentration of the Clay and the Quartz calculated using the ELAN model and confirmed with the core rock measurement. After training of the MLP machine weights of connection are calculated, the raw well-logs data of two other horizontal wells drilled in the same reservoir are propagated though the neural machine and an output is calculated. Comparison between the predicted and measured clay and Quartz concentrations in these two horizontal wells shows the ability of neural network to improve shale gas reservoirs characterization.

Biophysical constraints on the computational capacity of biochemical signaling networks

NASA Astrophysics Data System (ADS)

Wang, Ching-Hao; Mehta, Pankaj

Biophysics fundamentally constrains the computations that cells can carry out. Here, we derive fundamental bounds on the computational capacity of biochemical signaling networks that utilize post-translational modifications (e.g. phosphorylation). To do so, we combine ideas from the statistical physics of disordered systems and the observation by Tony Pawson and others that the biochemistry underlying protein-protein interaction networks is combinatorial and modular. Our results indicate that the computational capacity of signaling networks is severely limited by the energetics of binding and the need to achieve specificity. We relate our results to one of the theoretical pillars of statistical learning theory, Cover's theorem, which places bounds on the computational capacity of perceptrons. PM and CHW were supported by a Simons Investigator in the Mathematical Modeling of Living Systems Grant, and NIH Grant No. 1R35GM119461 (both to PM).

Fixation of CO2 in bi-layered coordination networks of zinc tetra(4-carboxyphenyl)porphyrin with multi-component [Pr2Na3(NO3)(H2O)3] connectors.

PubMed

Nandi, Goutam; Goldberg, Israel

2014-11-14

CO2 is fixed in a rare μ2-η bridging mode by bi-layered coordination networks of ZnTCPP tessellated along the four equatorial directions by [Pr2Na3(NO3)(H2O)3](8+) connecting clusters in a 2 : 1 ratio (1), but not in the isomorphous free-base porphyrin analogue [(TCPPH2)2(Pr2Na3(NO3)(H2O)3)]n (2), revealing the crucial role of the zinc metal in this process.

The algorithm study for using the back propagation neural network in CT image segmentation

NASA Astrophysics Data System (ADS)

Zhang, Peng; Liu, Jie; Chen, Chen; Li, Ying Qi

2017-01-01

Back propagation neural network(BP neural network) is a type of multi-layer feed forward network which spread positively, while the error spread backwardly. Since BP network has advantages in learning and storing the mapping between a large number of input and output layers without complex mathematical equations to describe the mapping relationship, it is most widely used. BP can iteratively compute the weight coefficients and thresholds of the network based on the training and back propagation of samples, which can minimize the error sum of squares of the network. Since the boundary of the computed tomography (CT) heart images is usually discontinuous, and it exist large changes in the volume and boundary of heart images, The conventional segmentation such as region growing and watershed algorithm can't achieve satisfactory results. Meanwhile, there are large differences between the diastolic and systolic images. The conventional methods can't accurately classify the two cases. In this paper, we introduced BP to handle the segmentation of heart images. We segmented a large amount of CT images artificially to obtain the samples, and the BP network was trained based on these samples. To acquire the appropriate BP network for the segmentation of heart images, we normalized the heart images, and extract the gray-level information of the heart. Then the boundary of the images was input into the network to compare the differences between the theoretical output and the actual output, and we reinput the errors into the BP network to modify the weight coefficients of layers. Through a large amount of training, the BP network tend to be stable, and the weight coefficients of layers can be determined, which means the relationship between the CT images and the boundary of heart.

A Computer-Aided Type-II Fuzzy Image Processing for Diagnosis of Meniscus Tear.

PubMed

Zarandi, M H Fazel; Khadangi, A; Karimi, F; Turksen, I B

2016-12-01

Meniscal tear is one of the prevalent knee disorders among young athletes and the aging population, and requires correct diagnosis and surgical intervention, if necessary. Not only the errors followed by human intervention but also the obstacles of manual meniscal tear detection highlight the need for automatic detection techniques. This paper presents a type-2 fuzzy expert system for meniscal tear diagnosis using PD magnetic resonance images (MRI). The scheme of the proposed type-2 fuzzy image processing model is composed of three distinct modules: Pre-processing, Segmentation, and Classification. λ-nhancement algorithm is used to perform the pre-processing step. For the segmentation step, first, Interval Type-2 Fuzzy C-Means (IT2FCM) is applied to the images, outputs of which are then employed by Interval Type-2 Possibilistic C-Means (IT2PCM) to perform post-processes. Second stage concludes with re-estimation of "η" value to enhance IT2PCM. Finally, a Perceptron neural network with two hidden layers is used for Classification stage. The results of the proposed type-2 expert system have been compared with a well-known segmentation algorithm, approving the superiority of the proposed system in meniscal tear recognition.

Multifunctional substrate of Al alloy based on general hierarchical micro/nanostructures: superamphiphobicity and enhanced corrosion resistance.

PubMed

Li, Xuewu; Shi, Tian; Liu, Cong; Zhang, Qiaoxin; Huang, Xingjiu

2016-10-24

Aluminum alloys are vulnerable to penetrating and peeling failures in seawater and preparing a barrier coating to isolate the substrate from corrosive medium is an effective anticorrosion method. Inspired by the lotus leaves effect, a wetting alloy surface with enhanced anticorrosion behavior has been prepared via etch, deposition, and low-surface-energy modification. Results indicate that excellent superamphiphobicity has been achieved after the modification of the constructed hierarchical labyrinth-like microstructures and dendritic nanostructures. The as-prepared surface is also found with good chemical stability and mechanical durability. Furthermore, superior anticorrosion behaviors of the resultant samples in seawater are investigated by electrochemical measurements. Due to trapped air in micro/nanostructures, the newly presented solid-air-liquid contacting interface can help to resist the seawater penetration by greatly reducing the interface interaction between corrosive ions and the superamphiphobic surface. Finally, an optimized two-layer perceptron artificial neural network is set up to model and predict the cause-and-effect relationship between preparation conditions and the anticorrosion parameters. This work provides a great potential to extend the applications of aluminum alloys especially in marine engineering fields.

Multifunctional substrate of Al alloy based on general hierarchical micro/nanostructures: superamphiphobicity and enhanced corrosion resistance

PubMed Central

Li, Xuewu; Shi, Tian; Liu, Cong; Zhang, Qiaoxin; Huang, Xingjiu

2016-01-01

Aluminum alloys are vulnerable to penetrating and peeling failures in seawater and preparing a barrier coating to isolate the substrate from corrosive medium is an effective anticorrosion method. Inspired by the lotus leaves effect, a wetting alloy surface with enhanced anticorrosion behavior has been prepared via etch, deposition, and low-surface-energy modification. Results indicate that excellent superamphiphobicity has been achieved after the modification of the constructed hierarchical labyrinth-like microstructures and dendritic nanostructures. The as-prepared surface is also found with good chemical stability and mechanical durability. Furthermore, superior anticorrosion behaviors of the resultant samples in seawater are investigated by electrochemical measurements. Due to trapped air in micro/nanostructures, the newly presented solid-air-liquid contacting interface can help to resist the seawater penetration by greatly reducing the interface interaction between corrosive ions and the superamphiphobic surface. Finally, an optimized two-layer perceptron artificial neural network is set up to model and predict the cause-and-effect relationship between preparation conditions and the anticorrosion parameters. This work provides a great potential to extend the applications of aluminum alloys especially in marine engineering fields. PMID:27775053

Multifunctional substrate of Al alloy based on general hierarchical micro/nanostructures: superamphiphobicity and enhanced corrosion resistance

NASA Astrophysics Data System (ADS)

Li, Xuewu; Shi, Tian; Liu, Cong; Zhang, Qiaoxin; Huang, Xingjiu

2016-10-01

Aluminum alloys are vulnerable to penetrating and peeling failures in seawater and preparing a barrier coating to isolate the substrate from corrosive medium is an effective anticorrosion method. Inspired by the lotus leaves effect, a wetting alloy surface with enhanced anticorrosion behavior has been prepared via etch, deposition, and low-surface-energy modification. Results indicate that excellent superamphiphobicity has been achieved after the modification of the constructed hierarchical labyrinth-like microstructures and dendritic nanostructures. The as-prepared surface is also found with good chemical stability and mechanical durability. Furthermore, superior anticorrosion behaviors of the resultant samples in seawater are investigated by electrochemical measurements. Due to trapped air in micro/nanostructures, the newly presented solid-air-liquid contacting interface can help to resist the seawater penetration by greatly reducing the interface interaction between corrosive ions and the superamphiphobic surface. Finally, an optimized two-layer perceptron artificial neural network is set up to model and predict the cause-and-effect relationship between preparation conditions and the anticorrosion parameters. This work provides a great potential to extend the applications of aluminum alloys especially in marine engineering fields.

New Abstractions for Mobile Connectivity and Resource Management

DTIC Science & Technology

2016-05-01

networked systems, con- sisting of replicated backend services and mobile , multi-homed clients. We derive a state machine for ECCP supporting migration...makes ECCP useful not only for mobility of client devices, but also for backend services which are increasingly run in VMs or containers on platforms...layers of the network stack, instead of the traditional IP/port, improve mobility for clients and backend services and reduce unnecessary coupling of

Synchronized and mixed outbreaks of coupled recurrent epidemics.

PubMed

Zheng, Muhua; Zhao, Ming; Min, Byungjoon; Liu, Zonghua

2017-05-25

Epidemic spreading has been studied for a long time and most of them are focused on the growing aspect of a single epidemic outbreak. Recently, we extended the study to the case of recurrent epidemics (Sci. Rep. 5, 16010 (2015)) but limited only to a single network. We here report from the real data of coupled regions or cities that the recurrent epidemics in two coupled networks are closely related to each other and can show either synchronized outbreak pattern where outbreaks occur simultaneously in both networks or mixed outbreak pattern where outbreaks occur in one network but do not in another one. To reveal the underlying mechanism, we present a two-layered network model of coupled recurrent epidemics to reproduce the synchronized and mixed outbreak patterns. We show that the synchronized outbreak pattern is preferred to be triggered in two coupled networks with the same average degree while the mixed outbreak pattern is likely to show for the case with different average degrees. Further, we show that the coupling between the two layers tends to suppress the mixed outbreak pattern but enhance the synchronized outbreak pattern. A theoretical analysis based on microscopic Markov-chain approach is presented to explain the numerical results. This finding opens a new window for studying the recurrent epidemics in multi-layered networks.

The benefits of convergence.

PubMed

Chang, Gee-Kung; Cheng, Lin

2016-03-06

A multi-tier radio access network (RAN) combining the strength of fibre-optic and radio access technologies employing adaptive microwave photonics interfaces and radio-over-fibre (RoF) techniques is envisioned for future heterogeneous wireless communications. All-band radio spectrum from 0.1 to 100 GHz will be used to deliver wireless services with high capacity, high link speed and low latency. The multi-tier RAN will improve the cell-edge performance in an integrated heterogeneous environment enabled by fibre-wireless integration and networking for mobile fronthaul/backhaul, resource sharing and all-layer centralization of multiple standards with different frequency bands and modulation formats. In essence, this is a 'no-more-cells' architecture in which carrier aggregation among multiple frequency bands can be easily achieved with seamless handover between cells. In this way, current and future mobile network standards such as 4G and 5G can coexist with optimized and continuous cell coverage using multi-tier RoF regardless of the underlying network topology or protocol. In terms of users' experience, the future-proof approach achieves the goals of system capacity, link speed, latency and continuous heterogeneous cell coverage while overcoming the bandwidth crunch in next-generation communication networks. © 2016 The Author(s).

PaintOmics 3: a web resource for the pathway analysis and visualization of multi-omics data.

PubMed

Hernández-de-Diego, Rafael; Tarazona, Sonia; Martínez-Mira, Carlos; Balzano-Nogueira, Leandro; Furió-Tarí, Pedro; Pappas, Georgios J; Conesa, Ana

2018-05-25

The increasing availability of multi-omic platforms poses new challenges to data analysis. Joint visualization of multi-omics data is instrumental in better understanding interconnections across molecular layers and in fully utilizing the multi-omic resources available to make biological discoveries. We present here PaintOmics 3, a web-based resource for the integrated visualization of multiple omic data types onto KEGG pathway diagrams. PaintOmics 3 combines server-end capabilities for data analysis with the potential of modern web resources for data visualization, providing researchers with a powerful framework for interactive exploration of their multi-omics information. Unlike other visualization tools, PaintOmics 3 covers a comprehensive pathway analysis workflow, including automatic feature name/identifier conversion, multi-layered feature matching, pathway enrichment, network analysis, interactive heatmaps, trend charts, and more. It accepts a wide variety of omic types, including transcriptomics, proteomics and metabolomics, as well as region-based approaches such as ATAC-seq or ChIP-seq data. The tool is freely available at www.paintomics.org.

Multi-level deep supervised networks for retinal vessel segmentation.

PubMed

Mo, Juan; Zhang, Lei

2017-12-01

Changes in the appearance of retinal blood vessels are an important indicator for various ophthalmologic and cardiovascular diseases, including diabetes, hypertension, arteriosclerosis, and choroidal neovascularization. Vessel segmentation from retinal images is very challenging because of low blood vessel contrast, intricate vessel topology, and the presence of pathologies such as microaneurysms and hemorrhages. To overcome these challenges, we propose a neural network-based method for vessel segmentation. A deep supervised fully convolutional network is developed by leveraging multi-level hierarchical features of the deep networks. To improve the discriminative capability of features in lower layers of the deep network and guide the gradient back propagation to overcome gradient vanishing, deep supervision with auxiliary classifiers is incorporated in some intermediate layers of the network. Moreover, the transferred knowledge learned from other domains is used to alleviate the issue of insufficient medical training data. The proposed approach does not rely on hand-crafted features and needs no problem-specific preprocessing or postprocessing, which reduces the impact of subjective factors. We evaluate the proposed method on three publicly available databases, the DRIVE, STARE, and CHASE_DB1 databases. Extensive experiments demonstrate that our approach achieves better or comparable performance to state-of-the-art methods with a much faster processing speed, making it suitable for real-world clinical applications. The results of cross-training experiments demonstrate its robustness with respect to the training set. The proposed approach segments retinal vessels accurately with a much faster processing speed and can be easily applied to other biomedical segmentation tasks.

Exponential H(infinity) synchronization of general discrete-time chaotic neural networks with or without time delays.

PubMed

Qi, Donglian; Liu, Meiqin; Qiu, Meikang; Zhang, Senlin

2010-08-01

This brief studies exponential H(infinity) synchronization of a class of general discrete-time chaotic neural networks with external disturbance. On the basis of the drive-response concept and H(infinity) control theory, and using Lyapunov-Krasovskii (or Lyapunov) functional, state feedback controllers are established to not only guarantee exponential stable synchronization between two general chaotic neural networks with or without time delays, but also reduce the effect of external disturbance on the synchronization error to a minimal H(infinity) norm constraint. The proposed controllers can be obtained by solving the convex optimization problems represented by linear matrix inequalities. Most discrete-time chaotic systems with or without time delays, such as Hopfield neural networks, cellular neural networks, bidirectional associative memory networks, recurrent multilayer perceptrons, Cohen-Grossberg neural networks, Chua's circuits, etc., can be transformed into this general chaotic neural network to be H(infinity) synchronization controller designed in a unified way. Finally, some illustrated examples with their simulations have been utilized to demonstrate the effectiveness of the proposed methods.

Identifying Jets Using Artifical Neural Networks

NASA Astrophysics Data System (ADS)

Rosand, Benjamin; Caines, Helen; Checa, Sofia

2017-09-01

We investigate particle jet interactions with the Quark Gluon Plasma (QGP) using artificial neural networks modeled on those used in computer image recognition. We create jet images by binning jet particles into pixels and preprocessing every image. We analyzed the jets with a Multi-layered maxout network and a convolutional network. We demonstrate each network's effectiveness in differentiating simulated quenched jets from unquenched jets, and we investigate the method that the network uses to discriminate among different quenched jet simulations. Finally, we develop a greater understanding of the physics behind quenched jets by investigating what the network learnt as well as its effectiveness in differentiating samples. Yale College Freshman Summer Research Fellowship in the Sciences and Engineering.

Multi-time scale control of demand flexibility in smart distribution networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bhattarai, Bishnu; Myers, Kurt; Bak-Jensen, Birgitte

This study presents a multi-timescale control strategy to deploy demand flexibilities of electric vehicles (EV) for providing system balancing and local congestion management by simultaneously ensuring economic benefits to participating actors. First, the EV charging problem from consumer, aggregator, and grid operator’s perspective is investigated. A hierarchical control architecture (HCA) comprising scheduling, coordinative, and adaptive layers is then designed to realize their coordinative goal. This is realized by integrating a multi-time scale control, which works from a day-ahead scheduling up to real-time adaptive control. The performance of the developed method is investigated with high EV penetration in a typical distributionmore » network. The simulation results demonstrates that HCA exploit EV flexibility to solve grid unbalancing and congestions with simultaneous maximization of economic benefits by ensuring EV participation to day-ahead, balancing, and regulation markets. For the given network configuration and pricing structure, HCA ensures the EV owners to get paid up to 5 times the cost they were paying without control.« less

Multi-time scale control of demand flexibility in smart distribution networks

DOE PAGES

Bhattarai, Bishnu; Myers, Kurt; Bak-Jensen, Birgitte; ...

2017-01-01

This study presents a multi-timescale control strategy to deploy demand flexibilities of electric vehicles (EV) for providing system balancing and local congestion management by simultaneously ensuring economic benefits to participating actors. First, the EV charging problem from consumer, aggregator, and grid operator’s perspective is investigated. A hierarchical control architecture (HCA) comprising scheduling, coordinative, and adaptive layers is then designed to realize their coordinative goal. This is realized by integrating a multi-time scale control, which works from a day-ahead scheduling up to real-time adaptive control. The performance of the developed method is investigated with high EV penetration in a typical distributionmore » network. The simulation results demonstrates that HCA exploit EV flexibility to solve grid unbalancing and congestions with simultaneous maximization of economic benefits by ensuring EV participation to day-ahead, balancing, and regulation markets. For the given network configuration and pricing structure, HCA ensures the EV owners to get paid up to 5 times the cost they were paying without control.« less