Neural network construction via back-propagation
International Nuclear Information System (INIS)
A method is presented that combines back-propagation with multi-layer neural network construction. Back-propagation is used not only to adjust the weights but also the signal functions. Going from one network to an equivalent one that has additional linear units, the non-linearity of these units and thus their effective presence is then introduced via back-propagation (weight-splitting). The back-propagated error causes the network to include new units in order to minimize the error function. We also show how this formalism allows to escape local minima
Fuzzy neural network with fast backpropagation learning
Wang, Zhiling; De Sario, Marco; Guerriero, Andrea; Mugnuolo, Raffaele
1995-03-01
Neural filters with multilayer backpropagation network have been proved to be able to define mostly all linear or non-linear filters. Because of the slowness of the networks' convergency, however, the applicable fields have been limited. In this paper, fuzzy logic is introduced to adjust learning rate and momentum parameter depending upon output errors and training times. This makes the convergency of the network greatly improved. Test curves are shown to prove the fast filters' performance.
Privacy-preserving backpropagation neural network learning.
Chen, Tingting; Zhong, Sheng
2009-10-01
With the development of distributed computing environment , many learning problems now have to deal with distributed input data. To enhance cooperations in learning, it is important to address the privacy concern of each data holder by extending the privacy preservation notion to original learning algorithms. In this paper, we focus on preserving the privacy in an important learning model, multilayer neural networks. We present a privacy-preserving two-party distributed algorithm of backpropagation which allows a neural network to be trained without requiring either party to reveal her data to the other. We provide complete correctness and security analysis of our algorithms. The effectiveness of our algorithms is verified by experiments on various real world data sets. PMID:19709975
Prediction of tides using back-propagation neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.
Prediction of tides is very much essential for human activities and to reduce the construction cost in marine environment. This paper presents an application of the artificial neural network with back-propagation procedures for accurate prediction...
Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
Hernández-Lobato, José Miguel; Adams, Ryan P.
2015-01-01
Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic predictions, and a tendency to overfit the training data. In principle, the Bayesian approach to learning neural networks does not have these problems. However, existing Bayesian ...
Impact of Mutation Weights on Training Backpropagation Neural Networks
Directory of Open Access Journals (Sweden)
Lamia Abed Noor Muhammed
2014-07-01
Full Text Available Neural network is a computational approach, which based on the simulation of biology neural network. This approach is conducted by several parameters; learning rate, initialized weights, network architecture, and so on. However, this paper would be focused on one of these parameters that is weights. The aim is to shed lights on the mutation weights through training network and its effects on the results. The experiment was done using backpropagation neural network with one hidden layer. The results reveal the role of mutation in escape from the local minima and making the change
Tumor Diagnosis Using Backpropagation Neural Network Method
Ma, Lixing; Looney, Carl; Sukuta, Sydney; Bruch, Reinhard; Afanasyeva, Natalia
1998-05-01
For characterization of skin cancer, an artificial neural network (ANN) method has been developed to diagnose normal tissue, benign tumor and melanoma. The pattern recognition is based on a three-layer neural network fuzzy learning system. In this study, the input neuron data set is the Fourier Transform infrared (FT-IR)spectrum obtained by a new Fiberoptic Evanescent Wave Fourier Transform Infrared (FEW-FTIR) spectroscopy method in the range of 1480 to 1850 cm-1. Ten input features are extracted from the absorbency values in this region. A single hidden layer of neural nodes with sigmoids activation functions clusters the feature space into small subclasses and the output nodes are separated in different nonconvex classes to permit nonlinear discrimination of disease states. The output is classified as three classes: normal tissue, benign tumor and melanoma. The results obtained from the neural network pattern recognition are shown to be consistent with traditional medical diagnosis. Input features have also been extracted from the absorbency spectra using chemical factor analysis. These abstract features or factors are also used in the classification.
Conjugate descent formulation of backpropagation error in feedforward neural networks
Sharma NK; Kumar, S; Singh MP
2009-01-01
The feedforward neural network architecture uses backpropagation learning to determine optimal weights between different interconnected layers. This learning procedure uses a gradient descent technique applied to a sum-of-squares error function for the given input-output pattern. It employs an iterative procedure to minimise the error function for a given set of patterns, by adjusting the weights of the network. The first derivates of the error with respect to the weights identify the local e...
LVQ and backpropagation neural networks applied to NASA SSME data
Doniere, Timothy F.; Dhawan, Atam P.
1993-01-01
Feedfoward neural networks with backpropagation learning have been used as function approximators for modeling the space shuttle main engine (SSME) sensor signals. The modeling of these sensor signals is aimed at the development of a sensor fault detection system that can be used during ground test firings. The generalization capability of a neural network based function approximator depends on the training vectors which in this application may be derived from a number of SSME ground test-firings. This yields a large number of training vectors. Large training sets can cause the time required to train the network to be very large. Also, the network may not be able to generalize for large training sets. To reduce the size of the training sets, the SSME test-firing data is reduced using the learning vector quantization (LVQ) based technique. Different compression ratios were used to obtain compressed data in training the neural network model. The performance of the neural model trained using reduced sets of training patterns is presented and compared with the performance of the model trained using complete data. The LVQ can also be used as a function approximator. The performance of the LVQ as a function approximator using reduced training sets is presented and compared with the performance of the backpropagation network.
The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks
Thimm, Georg; Moerland, Perry,; Fiesler, Emile
1996-01-01
The backpropagation algorithm is widely used for training multilayer neural networks. In this publication the gain of its activation function(s) is investigated. In specific, it is proven that changing the gain of the activation function is equivalent to changing the learning rate and the weights. This simplifies the backpropagation learning rule by eliminating one of its parameters. The theorem can be extended to hold for some well-known variations on the backpropagation algorithm, such as u...
Reinforcement and backpropagation training for an optical neural network using self-lensing effects.
Cruz-Cabrera, A A; Yang, M; Cui, G; Behrman, E C; Steck, J E; Skinner, S R
2000-01-01
The optical bench training of an optical feedforward neural network, developed by the authors, is presented. The network uses an optical nonlinear material for neuron processing and a trainable applied optical pattern as the network weights. The nonlinear material, with the applied weight pattern, modulates the phase front of a forward propagating information beam by dynamically altering the index of refraction profile of the material. To verify that the network can be trained in real time, six logic gates were trained using a reinforcement training paradigm. More importantly, to demonstrate optical backpropagation, three gates were trained via optical error backpropagation. The output error is optically backpropagated, detected with a CCD camera, and the weight pattern is updated and stored on a computer. The obtained results lay the ground work for the implementation of multilayer neural networks that are trained using optical error backpropagation and are able to solve more complex problems. PMID:18249868
Cheng, Zhiyong; Soudry, Daniel; Mao, Zexi; Lan, Zhenzhong
2015-01-01
Compared to Multilayer Neural Networks with real weights, Binary Multilayer Neural Networks (BMNNs) can be implemented more efficiently on dedicated hardware. BMNNs have been demonstrated to be effective on binary classification tasks with Expectation BackPropagation (EBP) algorithm on high dimensional text datasets. In this paper, we investigate the capability of BMNNs using the EBP algorithm on multiclass image classification tasks. The performances of binary neural networks with multiple h...
Ocean wave parameters estimation using backpropagation neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; SubbaRao; Raju, D.H.
In the present study, various ocean wave parameters are estimated from theoretical Pierson-Moskowitz spectra as well as measured ocean wave spectra using back propagation neural networks (BNN). Ocean wave parameters estimation by BNN shows...
Directory of Open Access Journals (Sweden)
J. B. Habarulema
2012-05-01
Full Text Available In this work, results obtained by investigating the application of different neural network backpropagation training algorithms are presented. This was done to assess the performance accuracy of each training algorithm in total electron content (TEC estimations using identical datasets in models development and verification processes. Investigated training algorithms are standard backpropagation (SBP, backpropagation with weight delay (BPWD, backpropagation with momentum (BPM term, backpropagation with chunkwise weight update (BPC and backpropagation for batch (BPB training. These five algorithms are inbuilt functions within the Stuttgart Neural Network Simulator (SNNS and the main objective was to find out the training algorithm that generates the minimum error between the TEC derived from Global Positioning System (GPS observations and the modelled TEC data. Another investigated algorithm is the MatLab based Levenberg-Marquardt backpropagation (L-MBP, which achieves convergence after the least number of iterations during training. In this paper, neural network (NN models were developed using hourly TEC data (for 8 years: 2000–2007 derived from GPS observations over a receiver station located at Sutherland (SUTH (32.38° S, 20.81° E, South Africa. Verification of the NN models for all algorithms considered was performed on both "seen" and "unseen" data. Hourly TEC values over SUTH for 2003 formed the "seen" dataset. The "unseen" dataset consisted of hourly TEC data for 2002 and 2008 over Cape Town (CPTN (33.95° S, 18.47° E and SUTH, respectively. The models' verification showed that all algorithms investigated provide comparable results statistically, but differ significantly in terms of time required to achieve convergence during input-output data training/learning. This paper therefore provides a guide to neural network users for choosing appropriate algorithms based on the availability of computation capabilities used for research.
Training a Feed-Forward Neural Network with Artificial Bee Colony based Backpropagation Method
Directory of Open Access Journals (Sweden)
Sudarshan Nandy
2012-09-01
Full Text Available Back-propagation algorithm is one of the most widely used and popular techniques to optimize the feedforward neural network training. Nature inspired meta-heuristic algorithms also provide derivative-freesolution to optimize complex problem. Artificial bee colony algorithm is a nature inspired meta-heuristicalgorithm, mimicking the foraging or food source searching behaviour of bees in a bee colony and thisalgorithm is implemented in several applications for an improved optimized outcome. The proposedmethod in this paper includes an improved artificial bee colony algorithm based back-propagation neuralnetwork training method for fast and improved convergence rate of the hybrid neural network learningmethod. The result is analysed with the genetic algorithm based back-propagation method, and it isanother hybridized procedure of its kind. Analysis is performed over standard data sets, reflecting the lightof efficiency of proposed method in terms of convergence speed and rate.
On the capacity of multilayer neural networks trained with backpropagation.
Miranda, E N
2000-08-01
The capacity of a layered neural network for learning hetero-associations is studied numerically as a function of the number M of hidden neurons. We find that there is a sharp change in the learning ability of the network as the number of hetero-associations increases. This fact allows us to define a maximum capacity C for a given architecture. It is found that C grows logarithmically with M. PMID:11052415
Analog hardware for delta-backpropagation neural networks
Eberhardt, Silvio P. (Inventor)
1992-01-01
This is a fully parallel analog backpropagation learning processor which comprises a plurality of programmable resistive memory elements serving as synapse connections whose values can be weighted during learning with buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in a plurality of neuron layers in accordance with delta-backpropagation algorithms modified so as to control weight changes due to circuit drift.
Application of backpropagation neural networks to phonetic element classification
Energy Technology Data Exchange (ETDEWEB)
Bryan, S.R.
1990-01-01
A need was established in conjunction with an USAF-sponsored project to develop a speech element classifier. This classifier had to be capable of placing continuous speech into a number of phoneme-like categories, and also had to be independent of speaker identity and individual voice characteristics. The feasibility of using a neural network to perform this classification task was explored. The results of this exploration are discussed here.
Diagnosing coronary artery disease with a backpropagation neural network: Lessons learned
Energy Technology Data Exchange (ETDEWEB)
Turner, D.D. [Pacific Northwest Lab., Richland, WA (United States); Holmes, E.R. [Sacred Heart Medical Center, Spokane, WA (United States)
1995-12-31
The SPECT (single photon emitted computed tomography) procedure, while widely used for diagnosing coronary artery disease, is not a perfect technology. We have investigated using a backpropagation neural network to diagnose patients suffering from coronary artery disease that is independent from the SPECT procedure. The raw thallium-201 scintigrams produced before the SPECT tomographic reconstruction were used as input patterns for the backpropagation neural network, and the diagnoses resulting mainly from cardiac catheterization as the desired outputs for each pattern. Several preprocessing techniques were applied to the scintigrams, in an attempt to improve the information to noise ratio. After using the a procedure that extracted a subimage containing the heart from each scintigram, we used a data reduction technique, thereby encoding the scintigram in 12 values, which were the inputs to the backpropagation neural network. The network was then trained. This network per-formed superbly for patients suffering from inferolateral disease (classifying 10 out of 10 correctly), but performance was less than optimal for cases involving other coronary zones. While the scope of this project was limited to diagnosing coronary artery disease, this initial work can be extended to other medical imaging procedures, such as diagnosing breast cancer from a mammogram and evaluating lung perfusion studies.
Directory of Open Access Journals (Sweden)
Ikhthison Mekongga
2014-02-01
Full Text Available The need for bandwidth has been increasing recently. This is because the development of internet infrastructure is also increasing so that we need an economic and efficient provider system. This can be achieved through good planning and a proper system. The prediction of the bandwidth consumption is one of the factors that support the planning for an efficient internet service provider system. Bandwidth consumption is predicted using ANN. ANN is an information processing system which has similar characteristics as the biologic al neural network. ANN is chosen to predict the consumption of the bandwidth because ANN has good approachability to non-linearity. The variable used in ANN is the historical load data. A bandwidth consumption information system was built using neural networks with a backpropagation algorithm to make the use of bandwidth more efficient in the future both in the rental rate of the bandwidth and in the usage of the bandwidth.Keywords: Forecasting, Bandwidth, Backpropagation
Energy Technology Data Exchange (ETDEWEB)
Kerr, J.P.; Bartlett, E.B. [Iowa State Univ., Ames, IA (United States). Biomedical Engineering Program
1992-12-31
In this paper, the feasibility of reconstructing a single photon emission computed tomography (SPECT) image via the parallel implementation of a backpropagation neural network is shown. The MasPar, MP-1 is a single instruction multiple data (SIMD) massively parallel machine. It is composed of a 128 x 128 array of 4-bit processors. The neural network is distributed on the array by dedicating a processor to each node and each interconnection of the network. An 8 x 8 SPECT image slice section is projected into eight planes. It is shown that based on the projections, the neural network can produce the original SPECT slice image exactly. Likewise, when trained on two parallel slices, separated by one slice, the neural network is able to reproduce the center, untrained image to an RMS error of 0.001928.
Directory of Open Access Journals (Sweden)
Asif Ullah Khan
2011-03-01
Full Text Available Investment in stock market is one of the most popular type of investment. There are many conventional techniques being used and these include technical and fundamental analysis. The main aim of every investor is to earn maximum possible return on investments. The main issue with any approach is the proper weighting of criteria to obtain a list of stocks that are suitable for investments. This paper proposes an improved method for stock picking using self-organizing maps and genetic algorithm based backpropagation neural networks. The stock selected using self-organizing maps and genetic algorithm based backpropagation neural networks outperformed the BSE-30 Index by about 30.17% based on one and half month of stock data.
Attariuas Hicham; Bouhorma Mohammed; Sofi Anas
2012-01-01
ales forecasting is one of the most crucial issues addressed in business. Control and evaluation of future sales still seem concerned both researchers and policy makers and managers of companies. this research propose an intelligent hybrid sales forecasting system Delphi-FCBPN sales forecast based on Delphi Method, fuzzy clustering and Back-propagation (BP) Neural Networks with adaptive learning rate. The proposed model is constructed to integrate expert judgments, using Delphi method, in enh...
Energy Technology Data Exchange (ETDEWEB)
Kerr, J.P.
1992-12-31
The objective of this study was to determine the feasibility of using an Artificial Neural Network (ANN), in particular a backpropagation ANN, to improve the speed and quality of the reconstruction of three-dimensional SPECT (single photon emission computed tomography) images. In addition, since the processing elements (PE)s in each layer of an ANN are independent of each other, the speed and efficiency of the neural network architecture could be better optimized by implementing the ANN on a massively parallel computer. The specific goals of this research were: to implement a fully interconnected backpropagation neural network on a serial computer and a SIMD parallel computer, to identify any reduction in the time required to train these networks on the parallel machine versus the serial machine, to determine if these neural networks can learn to recognize SPECT data by training them on a section of an actual SPECT image, and to determine from the knowledge obtained in this research if full SPECT image reconstruction by an ANN implemented on a parallel computer is feasible both in time required to train the network, and in quality of the images reconstructed.
Directory of Open Access Journals (Sweden)
Sheela Tiwari
2013-08-01
Full Text Available This paperexplores theapplicationof artificial neural networksfor online identification of a multimachinepower system.Arecurrent neural networkhas been proposedas the identifier of the two area, four machinesystemwhich is a benchmark system for studying electromechanical oscillations in multimachine powersystems. This neural identifier is trained using the static Backpropagation algorithm. The emphasis of thepaper is on investigating the performance of the variants of the Backpropagation algorithm in training theneural identifier. The paper also compares the performances of the neural identifiers trained usingvariantsof the Backpropagation algorithmover a wide range of operating conditions.The simulation resultsestablish a satisfactory performance of the trained neural identifiers in identification of the test powersystem
Application of back-propagation neural networks to identification of seismic arrival types
Dai, Heng; MacBeth, Colin
1997-01-01
A back-propagation neural network (BPNN) approach is developed to identify P- and S-arrivals from three-component recordings of local earthquake data. The BPNN is trained by selecting trace segments of P- and S-waves and noise bursts converted into an attribute space based on the degree of polarization (DOP). After training, the network can automatically identify the type of arrival on earthquake recordings. Compared with manual analysis, a BPNN trained with nine groups of DOP segments can co...
Directory of Open Access Journals (Sweden)
Omaima N. A.
2010-01-01
Full Text Available Problem statement: The problem inherent to any digital image is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop algorithms that compress images to lower data rates with better quality. Artificial neural networks are becoming attractive in image processing where high computational performance and parallel architectures are required. Approach: In this research, a three layered Backpropagation Neural Network (BPNN was designed for building image compression/decompression system. The Backpropagation neural network algorithm (BP was used for training the designed BPNN. Many techniques were used to speed up and improve this algorithm by using different BPNN architecture and different values of learning rate and momentum variables. Results: Experiments had been achieved, the results obtained, such as Compression Ratio (CR and peak signal to noise ratio (PSNR are compared with the performance of BP with different BPNN architecture and different learning parameters. The efficiency of the designed BPNN comes from reducing the chance of error occurring during the compressed image transmission through analog or digital channel. Conclusion: The performance of the designed BPNN image compression system can be increased by modifying the network itself, learning parameters and weights. Practically, we can note that the BPNN has the ability to compress untrained images but not in the same performance of the trained images.
A modified backpropagation algorithm for training neural networks on data with error bars
International Nuclear Information System (INIS)
A method is proposed for training multilayer feedforward neural networks on data contaminated with noise. Specifically, we consider the case that the artificial neural system is required to learn a physical mapping when the available values of the target variable are subject to experimental uncertainties, but are characterized by error bars. The proposed method, based on maximum likelihood criterion for parameter estimation, involves simple modifications of the on-line backpropagation learning algorithm. These include incorporation of the error-bar assignments in a pattern-specific learning rate, together with epochal updating of a new measure of model accuracy that replaces the usual mean-square error. The extended backpropagation algorithm is successfully tested on two problems relevant to the modelling of atomic-mass systematics by neural networks. Provided the underlying mapping is reasonably smooth, neural nets trained with the new procedure are able to learn the true function to a good approximation even in the presence of high levels of Gaussian noise. (author). 26 refs, 2 figs, 5 tabs
A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.
Oohori, Takahumi; Naganuma, Hidenori; Watanabe, Kazuhisa
2007-05-01
We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance. PMID:17381272
The backpropagation algorithm in J, a fast prototyping tool for researching neural networks.
Brouwer, R K
1999-08-01
This paper illustrates the use of a powerful language, called J, that is ideal for simulating neural networks. The use of J is demonstrated by its application to a gradient descent method for training a multilayer perceptron. It is also shown how the back-propagation algorithm can be easily generalized to multilayer networks without any increase in complexity and that the algorithm can be completely expressed in an array notation which is directly executable through J. J is a general purpose language, which means that its user is given a flexibility not available in neural network simulators or in software packages such as MATLAB. Yet, because of its numerous operators, J allows a very succinct code to be used, leading to a tremendous decrease in development time. PMID:10586987
Neural network for processing both spatial and temporal data with time based back-propagation
Villarreal, James A. (Inventor); Shelton, Robert O. (Inventor)
1993-01-01
Neural networks are computing systems modeled after the paradigm of the biological brain. For years, researchers using various forms of neural networks have attempted to model the brain's information processing and decision-making capabilities. Neural network algorithms have impressively demonstrated the capability of modeling spatial information. On the other hand, the application of parallel distributed models to the processing of temporal data has been severely restricted. The invention introduces a novel technique which adds the dimension of time to the well known back-propagation neural network algorithm. In the space-time neural network disclosed herein, the synaptic weights between two artificial neurons (processing elements) are replaced with an adaptable-adjustable filter. Instead of a single synaptic weight, the invention provides a plurality of weights representing not only association, but also temporal dependencies. In this case, the synaptic weights are the coefficients to the adaptable digital filters. Novelty is believed to lie in the disclosure of a processing element and a network of the processing elements which are capable of processing temporal as well as spacial data.
Scanner color management model based on improved back-propagation neural network
Institute of Scientific and Technical Information of China (English)
Xinwu Li
2008-01-01
Scanner color management is one of the key techniques for color reproduction in information optics.A new scanner color management model is presented based on analyzing rendering principle of scanning objects.In this model,a standard color target is taken as experimental sample.Color blocks in color shade area are used to substitute complete color space to solve the difficulties in selecting experimental color blocks.Immune genetic algorithm is used to correct back-propagation neural network(BPNN)to speed up the convergence of the model.Experimental results show that the model can improve the accuracy of scanner color management.
Back-Propagation Artificial Neural Networks for Water Supply Pipeline Model
Institute of Scientific and Technical Information of China (English)
朱东海; 张土乔; 毛根海
2002-01-01
Water supply pipelines are the lifelines of a city. When pipelines burst, the burst site is difficult to locate by traditional methods such as manual tools or only by watching. In this paper, the burst site was identified using back-propagation (BP) artificial neural networks (ANN). The study is based on an indoor urban water supply model experiment. The key to appling BP ANN is to optimize the ANN's topological structure and learning parameters. This paper presents the optimizing method for a 3-layer BP neural network's topological structure and its learning parameters-learning ratio and the momentum factor. The indoor water supply pipeline model experimental results show that BP ANNs can be used to locate the burst point in urban water supply systems. The topological structure and learning parameters were optimized using the experimental results.
Ueda, Michihito; Nishitani, Yu; Kaneko, Yukihiro; Omote, Atsushi
2014-01-01
To realize an analog artificial neural network hardware, the circuit element for synapse function is important because the number of synapse elements is much larger than that of neuron elements. One of the candidates for this synapse element is a ferroelectric memristor. This device functions as a voltage controllable variable resistor, which can be applied to a synapse weight. However, its conductance shows hysteresis characteristics and dispersion to the input voltage. Therefore, the conductance values vary according to the history of the height and the width of the applied pulse voltage. Due to the difficulty of controlling the accurate conductance, it is not easy to apply the back-propagation learning algorithm to the neural network hardware having memristor synapses. To solve this problem, we proposed and simulated a learning operation procedure as follows. Employing a weight perturbation technique, we derived the error change. When the error reduced, the next pulse voltage was updated according to the back-propagation learning algorithm. If the error increased the amplitude of the next voltage pulse was set in such way as to cause similar memristor conductance but in the opposite voltage scanning direction. By this operation, we could eliminate the hysteresis and confirmed that the simulation of the learning operation converged. We also adopted conductance dispersion numerically in the simulation. We examined the probability that the error decreased to a designated value within a predetermined loop number. The ferroelectric has the characteristics that the magnitude of polarization does not become smaller when voltages having the same polarity are applied. These characteristics greatly improved the probability even if the learning rate was small, if the magnitude of the dispersion is adequate. Because the dispersion of analog circuit elements is inevitable, this learning operation procedure is useful for analog neural network hardware. PMID:25393715
Directory of Open Access Journals (Sweden)
Michihito Ueda
Full Text Available To realize an analog artificial neural network hardware, the circuit element for synapse function is important because the number of synapse elements is much larger than that of neuron elements. One of the candidates for this synapse element is a ferroelectric memristor. This device functions as a voltage controllable variable resistor, which can be applied to a synapse weight. However, its conductance shows hysteresis characteristics and dispersion to the input voltage. Therefore, the conductance values vary according to the history of the height and the width of the applied pulse voltage. Due to the difficulty of controlling the accurate conductance, it is not easy to apply the back-propagation learning algorithm to the neural network hardware having memristor synapses. To solve this problem, we proposed and simulated a learning operation procedure as follows. Employing a weight perturbation technique, we derived the error change. When the error reduced, the next pulse voltage was updated according to the back-propagation learning algorithm. If the error increased the amplitude of the next voltage pulse was set in such way as to cause similar memristor conductance but in the opposite voltage scanning direction. By this operation, we could eliminate the hysteresis and confirmed that the simulation of the learning operation converged. We also adopted conductance dispersion numerically in the simulation. We examined the probability that the error decreased to a designated value within a predetermined loop number. The ferroelectric has the characteristics that the magnitude of polarization does not become smaller when voltages having the same polarity are applied. These characteristics greatly improved the probability even if the learning rate was small, if the magnitude of the dispersion is adequate. Because the dispersion of analog circuit elements is inevitable, this learning operation procedure is useful for analog neural network hardware.
Olawoyin, Richard
2016-10-01
The backpropagation (BP) artificial neural network (ANN) is a renowned and extensively functional mathematical tool used for time-series predictions and approximations; which also define results for non-linear functions. ANNs are vital tools in the predictions of toxicant levels, such as polycyclic aromatic hydrocarbons (PAH) potentially derived from anthropogenic activities in the microenvironment. In the present work, BP ANN was used as a prediction tool to study the potential toxicity of PAH carcinogens (PAHcarc) in soils. Soil samples (16 × 4 = 64) were collected from locations in South-southern Nigeria. The concentration of PAHcarc in laboratory cultivated white melilot, Melilotus alba roots grown on treated soils was predicted using ANN model training. Results indicated the Levenberg-Marquardt back-propagation training algorithm converged in 2.5E+04 epochs at an average RMSE value of 1.06E-06. The averagedR(2) comparison between the measured and predicted outputs was 0.9994. It may be deduced from this study that, analytical processes involving environmental risk assessment as used in this study can successfully provide prompt prediction and source identification of major soil toxicants. PMID:27424056
International Nuclear Information System (INIS)
In this work it was analyzed the residual performance of Portland cement concretes, when cold after heat-treated up to 600 deg C. Granite-gneiss was used in the three concrete mix proportions as the coarse aggregate, and river sand with finesses modulus of 2.7 as the fine aggregate. Ultrasonic pulse tests were performed on all the specimens and ultrasonic dynamic modulus were obtained. An artificial neural network of the backpropagation type was trained to evaluate and apply models in predicting residual properties of Portland cement concretes. The input layer for both models consists of an external layer input vector of the temperature. The hidden layer has two processing units with hyperbolic tangent sigmoid transfer functions (tansig for short), and the output layer contains one processing unit that represents the network's output (ultrasonic pulse velocity or modulus of elasticity) for each input vector. The training phase of the network converged for reasonable results after 5.000 epochs approximately, resulting in mean squared errors less than 0.02 for the normalized data. The neural network developed for modeling residual properties of Portland cement concretes was shown to be efficient in both the training phase and the test. From the results reasonable predictions could be made for the ultrasonic pulse velocity or dynamic modulus of elasticity by using temperature. (author)
Khuriati, Ainie; Setiabudi, Wahyu; Nur, Muhammad; Istadi, Istadi
2015-12-01
Backpropgation neural network was trained to predict of combustible fraction heating value of MSW from the physical composition. Waste-to-Energy (WtE) is a viable option for municipal solid waste (MSW) management. The influence of the heating value of municipal solid waste (MSW) is very important on the implementation of WtE systems. As MSW is heterogeneous material, direct heating value measurements are often not feasible. In this study an empirical model was developed to describe the heating value of the combustible fraction of municipal solid waste as a function of its physical composition of MSW using backpropagation neural network. Sampling process was carried out at Jatibarang landfill. The weight of each sorting sample taken from each discharged MSW vehicle load is 100 kg. The MSW physical components were grouped into paper wastes, absorbent hygiene product waste, styrofoam waste, HD plastic waste, plastic waste, rubber waste, textile waste, wood waste, yard wastes, kitchen waste, coco waste, and miscellaneous combustible waste. Network was trained by 24 datasets with 1200, 769, and 210 epochs. The results of this analysis showed that the correlation from the physical composition is better than multiple regression method .
Automatic volcanic ash detection from MODIS observations using a back-propagation neural network
Directory of Open Access Journals (Sweden)
T. M. Gray
2015-12-01
Full Text Available Due to the climate effects and aviation threats of volcanic eruptions, it is important to accurately locate ash in the atmosphere. This study aims to explore the accuracy and reliability of training a neural network to identify cases of ash using observations from the Moderate Resolution Imaging Spectroradiometer (MODIS. Satellite images were obtained for the following eruptions: Kasatochi, Aleutian Islands, 2008; Okmok, Aleutian Islands, 2008; Grímsvötn, northeastern Iceland, 2011; Chaitén, southern Chile, 2008; Puyehue-Cordón Caulle, central Chile, 2011; Sangeang Api, Indonesia, 2014; and Kelut, Indonesia, 2014. The Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT model was used to obtain ash concentrations for the same archived eruptions. Two back-propagation neural networks were then trained using brightness temperature differences as inputs obtained via the following band combinations: 12–11, 11–8.6, 11–7.3, and 11 μm. Using the ash concentrations determined via HYSPLIT, flags were created to differentiate between ash (1 and no ash (0 and SO2-rich ash (1 and no SO2-rich ash (0 and used as output. When neural network output was compared to the test data set, 93 % of pixels containing ash were correctly identified and 7 % were missed. Nearly 100 % of pixels containing SO2-rich ash were correctly identified. The optimal thresholds, determined using Heidke skill scores, for ash retrieval and SO2-rich ash retrieval were 0.48 and 0.47, respectively. The networks show significantly less accuracy in the presence of high water vapor, liquid water, ice, or dust concentrations. Significant errors are also observed at the edge of the MODIS swath.
Application of back-propagation neural networks to identification of seismic arrival types
Dai, Hengchang; MacBeth, Colin
1997-05-01
A back-propagation neural network (BPNN) approach is developed to identify P- and S-arrivals from three-component recordings of local earthquake data. The BPNN is trained by selecting trace segments of P- and S-waves and noise bursts converted into an attribute space based on the degree of polarization (DOP). After training, the network can automatically identify the type of arrival on earthquake recordings. Compared with manual analysis, a BPNN trained with nine groups of DOP segments can correctly identify 82.3% of the P-arrivals and 62.6% of the S-arrivals from one seismic station, and when trained with five groups from a training dataset selected from another seismic station, it can correctly identify 76.6% of the P-arrivals and 60.5% of S-arrivals. This approach is adaptive and needs only the onset time of arrivals as input, although its performance cannot be improved by simply adding more training datasets due to the complexity of DOP patterns. Our experience suggests that other information or another network may be necessary to improve its performance.
Institute of Scientific and Technical Information of China (English)
WU Shun-chuan(吴顺川); ZHANG You-pa(张友葩); GAO Yong-tao(高永涛)
2003-01-01
Taking the practical reinforced engineering of a reinforced soil retaining wall as an example, which located in Shandong Province and set on 104 national highway, the stress-spread behaviors of the anchor bars in the preforced proceeding were tested. According to the test data, and by use of the update backpropagation (BP) algorithm neural network(NN), the test method and it's mechanism were studied by the network, then the learning results show the mean square error(MSE) only at the 2.55% level, and the proof-testing results show the MSE at 4.38% level (the main aim is to build a NN directly from the in-situ test results (the learning phase)). Ipso-facto, the learning and adjustment abilities of the NN permit us to develop the test data, subsequently, 36 test data were acquired from the NN. By use of the provide data, as well as the failure situation and carried loading capacity of the retaining wall, finally, the choice the reasonable range interval distance of prestress cement grouting anchor bars were carried out, and the result was 2 m×2 m.
Amit Kumar Ray; Navin Kumar Agrawal; Rakesh Kumar Sinha
2003-01-01
Three layered feed-forward backpropagation artificial neural network architecture is designed to classify sleep-wake stages in rats. Continuous three channel polygraphic signals such as electroencephalogram, electrooculogram and electromyogram were recorded from conscious rats for eight hours during day time. Signals were also stored in computer hard disk with the help of analog to digital converter and its compatible data acquisition software. The power spectra (in dB scale) of the digitized...
Salim Lahmiri
2014-01-01
This paper presents a forecasting model that integrates the discrete wavelet transform (DWT) and backpropagation neural networks (BPNN) for predicting financial time series. The presented model first uses the DWT to decompose the financial time series data. Then, the obtained approximation (low-frequency) and detail (high-frequency) components after decomposition of the original time series are used as input variables to forecast future stock prices. Indeed, while high-frequency components ca...
A back-propagation neural network for mineralogical mapping from AVIRIS data
International Nuclear Information System (INIS)
Imaging spectrometers have the potential to identify surface mineralogy based on the unique absorption features in pixel spectra. A back-propagation neural network (BPN) is introduced to classify Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) of the Cuprite mining district (Nevada) data into mineral maps. The results are compared with the traditional acquired surface mineralogy maps from spectral angle mapping (SAM). There is no misclassification for the training set in the case of BPN; however 17 percent misclassification occurs in SAM. The validation accuracy of the SAM is 69 percent, whereas BPN results in 86 percent accuracy. The calibration accuracy of the BPN is higher than that of the SAM, suggesting that the training process of BPN is better than that of the SAM. The high classification accuracy obtained withthe BPN can beexplained by: (1) its ability to deal with complex relationships (e.g., 40 dimensions) and (2) the nature of the dataset, the minerals are highly concentrated and they are mostly represented by pure pixels. This paper demonstrates that BPN has superior classification ability when applied to imaging spectrometer data. (author)
Institute of Scientific and Technical Information of China (English)
QIN Zhong; SU Gao-li; YU Qiang; HU Bing-min; LI Jun
2005-01-01
In this work, datasets of water and carbon fluxes measured with eddy covariance technique above a summer maize field in the North China Plain were simulated with artificial neural networks (ANNs) to explore the fluxes responses to local environmental variables. The results showed that photosynthetically active radiation (PAR), vapor pressure deficit (VPD), air temperature (T) and leaf area index (LAI) were primary factors regulating both water vapor and carbon dioxide fluxes. Three-layer back-propagation neural networks (BP) could be applied to model fluxes exchange between cropland surface and atmosphere without using detailed physiological information or specific parameters of the plant.
Qin, Zhong; Su, Gao-Li; Yu, Qiang; Hu, Bing-Min; Li, Jun
2005-05-01
In this work, datasets of water and carbon fluxes measured with eddy covariance technique above a summer maize field in the North China Plain were simulated with artificial neural networks (ANNs) to explore the fluxes responses to local environmental variables. The results showed that photosynthetically active radiation (PAR), vapor pressure deficit (VPD), air temperature (T) and leaf area index (LAI) were primary factors regulating both water vapor and carbon dioxide fluxes. Three-layer back-propagation neural networks (BP) could be applied to model fluxes exchange between cropland surface and atmosphere without using detailed physiological information or specific parameters of the plant. PMID:15822158
Directory of Open Access Journals (Sweden)
Bahman O. Taha
2015-06-01
Full Text Available The reinforced concrete with fiber reinforced polymer (FRP bars (carbon, aramid, basalt and glass is used in places where a high ratio of strength to weight is required and corrosion is not acceptable. Behavior of structural members using (FRP bars is hard to be modeled using traditional methods because of the high non-linearity relationship among factors influencing the strength of structural members. Back-propagation neural network is a very effective method for modeling such complicated relationships. In this paper, back-propagation neural network is used for modeling the flexural behavior of beams reinforced with (FRP bars. 101 samples of beams reinforced with fiber bars were collected from literatures. Five important factors are taken in consideration for predicting the strength of beams. Two models of Multilayer Perceptron (MLP are created, first with single-hidden layer and the second with two-hidden layers. The two-hidden layer model showed better accuracy ratio than the single-hidden layer model. Parametric study has been done for two-hidden layer model only. Equations are derived to be used instead of the model and the importance of input factors is determined. Results showed that the neural network is successful in modeling the behavior of concrete beams reinforced with different types of (FRP bars.
Lin, Bin; Lin, Gaotong; Liu, Xianyun; Ma, Jianshe; Wang, Xianchuan; Lin, Feiyan; Hu, Lufeng
2015-01-01
In order to develop pharmacokinetic model, a well-known multilayer feed-forward algorithm back-propagation artificial neural networks (BP-ANN) was applied to the pharmacokinetics of losartan in rabbit. The plasma concentrations of losartan in twelve rabbits, which were divided into two groups and given losartan 2 mg/kg by intravenous (Iv) and intragastrical (Ig) administration, were determined by LC-MS. The BP-ANN model included one input layer, hidden layers, and one output layer was constru...
Predicting carbonate permeabilities from wireline logs using a back-propagation neural network
International Nuclear Information System (INIS)
This paper explores the applicability of using Neural Networks to aid in the determination of carbonate permeability from wireline logs. Resistivity, interval transit time, neutron porosity, and bulk density logs form Texaco's Stockyard Creek Oil field were used as input to a specially designed neural network to predict core permeabilities in this carbonate reservoir. Also of interest was the comparison of the neural network's results to those of standard statistical techniques. The process of developing the neural network for this problem has shown that a good understanding of the data is required when creating the training set from which the network learns. This network was trained to learn core permeabilities from raw and transformed log data using a hyperbolic tangent transfer function and a sum of squares global error function. Also, it required two hidden layers to solve this particular problem
Directory of Open Access Journals (Sweden)
Attariuas Hicham
2012-11-01
Full Text Available In recent years, there has been a strong tendency by companies to use centralized management systems like Enterprise resource planning (ERP. ERP systems offer a comprehensive and simplified process managements and extensive functional coverage. Sales management module is an important element business management of ERP. This paper describes an intelligent hybrid sales forecasting system ERP-FCBPN sales forecast based on architecture of ERP through Delphi, fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN. The proposed approach is composed of three stages: (1 Stage of data collection: Data collection will be implemented from the fields (attributes existing at the interfaces (Tables the database of the ERP. Collection of Key factors that influence sales be made using the Delphi method; (2 Stage of Data preprocessing: Winter Exponential Smoothing method will be utilized to take the trend effect into consideration. (3 Stage of learning by FCBPN: We use hybrid sales forecasting system based on Delphi, fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN. The data for this study come from an industrial company that manufactures packaging. Experimental results show that the proposed model outperforms the previous and traditional approaches. Therefore, it is a very promising solution for industrial forecasting.
International Nuclear Information System (INIS)
Research highlights: → An ANN was built to predict the formation enthalpies of Al2X-type intermetallics. → The values predicted by the ANN agree with experiments well to typically within 10%. → The method comparison suggests that our ANN method is superior to Miedema's model. → Some trends of formation enthalpies for Al2X-type intermetallics were observed. - Abstract: A back-propagation artificial neural network (ANN) was established to predict the formation enthalpies of Al2X-type intermetallics as a function of some physical parameters. These physical parameters include the electronegativity difference, the electron density difference, the atomic size difference, and the electron-atom ratio (e/a). The values calculated by the ANN method agree with experiments well to typically within 10%, indicating that the well-trained back-propagation (BP) neural network is feasible, and can precisely predict the formation enthalpies of Al2X-type intermetallics. The method comparison based on the predicted formation enthalpies suggests that our ANN method is superior to Miedema's model. Some trends of formation enthalpies for Al2X-type intermetallics were also observed from the ANN.
Directory of Open Access Journals (Sweden)
Satyanarayana D
2006-01-01
Full Text Available A chemometric model for the simultaneous estimation of phenobarbitone and phenytoin sodium anticonvulsant tablets using the back-propagation neural network calibration has been presented. The use of calibration datasets constructed from the spectral data of pure components is proposed. The calibration sets were designed such that the concentrations were orthogonal and span the possible mixture space fairly evenly. Spectra of phenobarbitone and phenytoin sodium were recorded at several concentrations within their linear range and used to compute the calibration mixture between wavelengths 220 and 260 nm at an interval of 1 nm. The back-propagation neural network model was optimized using three different sets of calibration and monitoring data for the number of hidden sigmoid neurons. The calibration model was thoroughly evaluated at several concentration levels using spectra obtained for 95 synthetic binary mixtures prepared using orthogonal designs. The optimized model showed sufficient robustness even when the calibration sets were constructed from different sets of pure spectra of components. Although the components showed complete spectral overlap, the model could accurately estimate the drugs, with satisfactory precision and accuracy, in tablet dosage with no interference from excipients, as indicated by the recovery study results.
International Nuclear Information System (INIS)
The boiler is a very important component of a thermal power plant, and its efficient operation requires continuous online information of various relevant parameters. Furnace exit gas temperature (FEGT) is one such important design/operating parameter. Knowledge of FEGT is not only useful for design of convective heating surface but also helpful for operating actions and decision making. Its online information ensures improvement in economic benefit of the power plant. Non-availability of FEGT on the operator desk greatly limits efficient operation. In this study, a novel method of estimating FEGT using neural network is presented. The training data are first generated by calculating FEGT using heat balances through various heat exchangers. Prediction accuracy and fast response are major advantages in using neural network for estimating FEGT for operator information. Two types of feed forward neural modeling networks, radial basis function and back-propagation network, were applied and compared based on their network simplicity, model building and prediction accuracy. Results are verified on practical data obtained from a 210 MW boiler of a thermal power plant
Soudry, Daniel; Meir, Ron
2013-01-01
Significant success has been reported recently using deep neural networks for classification. Such large networks can be computationally intensive, even after training is over. Implementing these trained networks in hardware chips with a limited precision of synaptic weights may improve their speed and energy efficiency by several orders of magnitude, thus enabling their integration into small and low-power electronic devices. With this motivation, we develop a computationally efficient learn...
International Nuclear Information System (INIS)
Due to the advantages of Artificial Neural Network (ANN) for analyzing complex reaction system, the oxidation process of phenol in a pulsed discharge plasma system is simulated using an ANN model. Reaction factors including solution with pH values of 3.6, 5.4 and 9.8, and hydroxyl radicals (·OH) scavengers (Na2CO3 and n-butyl alcohol) are considered, and the changing trends of phenol degradation under various experimental conditions are simulated and predicted by the Back-Propagation (BP) neural network model. The obtained results show that the BP neural network model can effectively predict the degradation efficiency of phenol in the reaction system. According to the results, acidic solution is favourable for phenol oxidation and increase in the Na2CO3 and n-butyl alcohol addition will greatly restrain the phenol degradation. The restraining effect of scavengers on phenol degradation indicates that ·OH is one of most important active species for phenol oxidation in the pulsed discharge plasma system.
New backpropagation algorithm with type-2 fuzzy weights for neural networks
Gaxiola, Fernando; Valdez, Fevrier
2016-01-01
In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights. The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method. The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris bi...
International Nuclear Information System (INIS)
This paper is dedicated to the application of artificial neural networks in optimizing heat treatment technique of high-vanadium high-speed steel (HVHSS), including predictions of retained austenite content (A), hardness (H) and wear resistance (ε) according to quenching and tempering temperatures (T1, T2). Multilayer back-propagation (BP) networks are created and trained using comprehensive datasets tested by the authors. And very good performances of the neural networks are achieved. The prediction results show residual austenite content decreases with decreasing quenching temperature or increasing tempering temperature. The maximum value of relative wear resistance occurs at quenching of 1000-1050 deg. C and tempering of 530-560 deg. C, corresponding to the peak value of hardness and retained austenite content of about 20-40 vol%. The prediction values have sufficiently mined the basic domain knowledge of heat treatment process of HVHSS. A convenient and powerful method of optimizing heat treatment technique has been provided by the authors
Directory of Open Access Journals (Sweden)
Lei Si
2014-01-01
Full Text Available Classification is an important theme in data mining. Rough sets and neural networks are the most common techniques applied in data mining problems. In order to extract useful knowledge and classify ambiguous patterns effectively, this paper presented a hybrid algorithm based on the integration of rough sets and BP neural network to construct a novel classification system. The attribution values were discretized through PSO algorithm firstly to establish a decision table. The attribution reduction algorithm and rules extraction method based on rough sets were proposed, and the flowchart of proposed approach was designed. Finally, a prototype system was developed and some simulation examples were carried out. Simulation results indicated that the proposed approach was feasible and accurate and was outperforming others.
Ueda, Michihito; Nishitani, Yu; Kaneko, Yukihiro; Omote, Atsushi
2014-01-01
To realize an analog artificial neural network hardware, the circuit element for synapse function is important because the number of synapse elements is much larger than that of neuron elements. One of the candidates for this synapse element is a ferroelectric memristor. This device functions as a voltage controllable variable resistor, which can be applied to a synapse weight. However, its conductance shows hysteresis characteristics and dispersion to the input voltage. Therefore, the conduc...
Automatic volcanic ash detection from MODIS observations using a back-propagation neural network
T. M. Gray; Bennartz, R.
2015-01-01
Due to the climate effects and aviation threats of volcanic eruptions, it is important to accurately locate ash in the atmosphere. This study aims to explore the accuracy and reliability of training a neural network to identify cases of ash using observations from the Moderate Resolution Imaging Spectroradiometer (MODIS). Satellite images were obtained for the following eruptions: Kasatochi, Aleutian Islands, 2008; Okmok, Aleutian Islands, 2008; Grímsvötn, n...
Implementation of back-propagation neural networks with MatLab
Nazari, Jamshid; Ersoy, Okan K
1992-01-01
The artificial neural network back propagation algorithm is implemented in Matlab language. This implementation is compared with several other software packages. The effect of reducing the number of iterations in the performance of the algorithm iai studied. The speed of the back propagation program, mkckpmp, written in Matlab language is compared with the speed of several other back propagation programs which are written in the C language. The speed of the Matlab program mbackpmp is, also co...
Power prediction of nuclear power plant using backpropagation learning neural network
International Nuclear Information System (INIS)
A neural network paradigms, which is a data processing system with a number of simple highly interconnected processing elements in an architecture inspired by the structure of the brain, is proposed for the application to the prediction of thermal power in Nuclear Power Plant (NPP). The Back Propagation Network (BPN) algorithm is applied to develop the models of signal processing. A number of case studies were performed with emphasis on the applicability of network in a steady state high power level. It is revealed that the BPN algorithm can precisely predict the thermal power of NPP. It is also shown that the defected signals resulting from instrumentation problem, even when the signals comprising various patterns are noisy or incomplete, can be also properly handled in the case study
A Method of Movie Business Prediction Using Back-propagation Neural Network
Directory of Open Access Journals (Sweden)
Debaditya Barman
2012-10-01
Full Text Available Film industry is the most important component of Entertainment industry. Profit and Loss both are very high for this business. Before release of a particular movie, if the Production House or distributors gets any type of prediction that how the film will do business, then it can be helpful to reduce the risk. In this paper we have proposed, back propagation neural network for prediction about the business of a movie. Note that, this method is successfully applied in the field of Stock Market Prediction, Weather Prediction and Image Processing.
Indian Academy of Sciences (India)
S Traore; Y M Wang; W G Chung
2014-03-01
The present study evaluates the predictive accuracy of the feed forward backpropagation artificial neural network (BP) in evapotranspiration forecasting from temperature data basis in Dédougou region located in western Burkina Faso, sub-Saharan Africa. BP accuracy is compared to the conventional Blaney–Criddle (BCR) and Reference Model developed for Burkina Faso (RMBF) by referring to the FAO56 Penman–Monteith (PM) as the standard method. Statistically, the models accuracies were evaluated with the goodness-of-fit measures of root mean square error, mean absolute error and coefficient of determination between their estimated and PM observed values. From the statistical results, BP shows similar contour trends to PM, and performs better than the conventional methods in reference evapotranspiration (ET_ref) forecasting in the region. In poor data situation, BP based only on temperature data is much more preferred than the other alternative methods for ET_ref forecasting. Furthermore, it is noted that the BP network computing technique accuracy improves significantly with the addition of wind velocity into the network input set. Therefore, in the region, wind velocity is recommended to be incorporated into the BP model for high accuracy management purpose of irrigation water, which relies on accurate values of ET_ref.
Directory of Open Access Journals (Sweden)
Amit Kumar Ray
2003-05-01
Full Text Available Three layered feed-forward backpropagation artificial neural network architecture is designed to classify sleep-wake stages in rats. Continuous three channel polygraphic signals such as electroencephalogram, electrooculogram and electromyogram were recorded from conscious rats for eight hours during day time. Signals were also stored in computer hard disk with the help of analog to digital converter and its compatible data acquisition software. The power spectra (in dB scale of the digitized signals in three sleep-wake stages were calculated. Selected power spectrum data of all three simultaneously recorded polygraphic signals were used for training the network and to classify slow wave sleep, rapid eye movement sleep and awake stages. The ANN architecture used in present study shows a very good agreement with manual sleep stage scoring with an average of 94.83% for all the 1200 samples tested from SWS, REM and AWA stages. The high performance observed with the system based on ANN highlights the need of this computational tool into the field of sleep research.
Directory of Open Access Journals (Sweden)
Nader Salari
Full Text Available Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that
Directory of Open Access Journals (Sweden)
Salim Lahmiri
2014-07-01
Full Text Available This paper presents a forecasting model that integrates the discrete wavelet transform (DWT and backpropagation neural networks (BPNN for predicting financial time series. The presented model first uses the DWT to decompose the financial time series data. Then, the obtained approximation (low-frequency and detail (high-frequency components after decomposition of the original time series are used as input variables to forecast future stock prices. Indeed, while high-frequency components can capture discontinuities, ruptures and singularities in the original data, low-frequency components characterize the coarse structure of the data, to identify the long-term trends in the original data. As a result, high-frequency components act as a complementary part of low-frequency components. The model was applied to seven datasets. For all of the datasets, accuracy measures showed that the presented model outperforms a conventional model that uses only low-frequency components. In addition, the presented model outperforms both the well-known auto-regressive moving-average (ARMA model and the random walk (RW process.
International Nuclear Information System (INIS)
At the beginning of the decade of the nineties, the industrial interest for TRIP steels leads to a significant increase of the investigation and application in this field. In this work, the flexibility of neural networks for the modelling of complex properties is used to tackle the problem of determining the retained austenite content in TRIP-steel. Applying a combination of two learning algorithms (backpropagation and creeping-random-search) for the neural network, a model has been created that enables the prediction of retained austenite in low-Si / low-Al multiphase steels as a function of processing parameters. (Author). 34 refs.
Circular backpropagation networks for classification.
Ridella, S; Rovetta, S; Zunino, R
1997-01-01
The class of mapping networks is a general family of tools to perform a wide variety of tasks. This paper presents a standardized, uniform representation for this class of networks, and introduces a simple modification of the multilayer perceptron with interesting practical properties, especially well suited to cope with pattern classification tasks. The proposed model unifies the two main representation paradigms found in the class of mapping networks for classification, namely, the surface-based and the prototype-based schemes, while retaining the advantage of being trainable by backpropagation. The enhancement in the representation properties and the generalization performance are assessed through results about the worst-case requirement in terms of hidden units and about the Vapnik-Chervonenkis dimension and cover capacity. The theoretical properties of the network also suggest that the proposed modification to the multilayer perceptron is in many senses optimal. A number of experimental verifications also confirm theoretical results about the model's increased performances, as compared with the multilayer perceptron and the Gaussian radial basis functions network. PMID:18255613
Bahadir, Elif
2016-01-01
The purpose of this study is to examine a neural network based approach to predict achievement in graduate education for Elementary Mathematics prospective teachers. With the help of this study, it can be possible to make an effective prediction regarding the students' achievement in graduate education with Artificial Neural Networks (ANN). Two…
Energy Technology Data Exchange (ETDEWEB)
Yu, S.; Wang, X.; Shi, C.; Wang, H. [Shandong Mining Institute (China). Jinan Branch
1999-04-01
Four reformatory learning algorithms are applied to enhance the learning speed and the stability of neural network. The general principles of forecasting productivity and efficiency with artificial neural network and the specific operational steps are described in details. The processing of data before and after the learning procedure, the determination of the network structure, and the appropriate reiteration times for the learning procedure are the main points of discussion. 3 refs., 3 figs., 2 tabs.
Yu, Hao; Rossi, Giammarco; Braglia, Andrea; Perrone, Guido
2016-08-10
The paper presents the development of a tool based on a back-propagation artificial neural network to assist in the accurate positioning of the lenses used to collimate the beam from semiconductor laser diodes along the so-called fast axis. After training using a Gaussian beam ray-equivalent model, the network is capable of indicating the tilt, decenter, and defocus of such lenses from the measured field distribution, so the operator can determine the errors with respect to the actual lens position and optimize the diode assembly procedure. An experimental validation using a typical configuration exploited in multi-emitter diode module assembly and fast axis collimating lenses with different focal lengths and numerical apertures is reported. PMID:27534506
Energy Technology Data Exchange (ETDEWEB)
Kohara, K. [Nippon Telegraph and Telephone Corp., Tokyo (Japan)
1998-11-01
We proposed ways to improve pattern recognition ability by combining several small back-propagation neural networks (BPNNs) [1]. We found that modifying the desired outputs according to the similarity of the input patterns (i.e., increasing desired outputs to similar classes) increases the BPNN outputs for similar classes, thus improving the generalization ability of the modular-net architecture. We evaluated the learning technique using two subfeatures extracted from handwritten digits [1]. This paper proposes a performance-verification method and presents experimental results applying learning techniques to the proposed verification-problems: 4-class, 10-class, and 20-class classification problems using two-dimensional Gaussian distribution data. 7 refs., 7 figs., 6 tabs.
Qin, Zhong; Su, Gao-li; Yu, Qiang; Hu, Bing-min; Li, Jun
2005-01-01
In this work, datasets of water and carbon fluxes measured with eddy covariance technique above a summer maize field in the North China Plain were simulated with artificial neural networks (ANNs) to explore the fluxes responses to local environmental variables. The results showed that photosynthetically active radiation (PAR), vapor pressure deficit (VPD), air temperature (T) and leaf area index (LAI) were primary factors regulating both water vapor and carbon dioxide fluxes. Three-layer back...
3-D inversion of borehole-to-surface electrical data using a back-propagation neural network
Ho, Trong Long
2009-08-01
The "fluid-flow tomography", an advanced technique for geoelectrical survey based on the conventional mise-à-la-masse measurement, has been developed by Exploration Geophysics Laboratory at the Kyushu University. This technique is proposed to monitor fluid-flow behavior during water injection and production in a geothermal field. However data processing of this technique is very costly. In this light, this paper will discuss the solution to cost reduction by applying a neural network in the data processing. A case study in the Takigami geothermal field in Japan will be used to illustrate this. The achieved neural network in this case study is three-layered and feed-forward. The most successful learning algorithm in this network is the Resilient Propagation (RPROP). Consequently, the study advances the pragmatism of the "fluid-flow tomography" technique which can be widely used for geothermal fields. Accuracy of the solution is then verified by using root mean square (RMS) misfit error as an indicator.
Directory of Open Access Journals (Sweden)
Attariuas Hicham
2012-05-01
Full Text Available This paper describes new hybrid sales forecasting system based on fuzzy clustering and Back-propagation (BP Neural Networks with adaptive learning rate (FCBPN.The proposed approach is composed of three stages: (1 Winters Exponential Smoothing method will be utilized to take the trend effect into consideration; (2 utilizing Fuzzy C-Means clustering method (Used in an clusters memberships fuzzy system (CMFS, the clusters membership levels of each normalized data records will be extracted; (3 Each cluster will be fed into parallel BP networks with a learning rate adapted as the level of cluster membership of training data records. Compared to many researches which use Hard clustering, we employ fuzzy clustering which permits each data record to belong to each cluster to a certain degree, which allows the clusters to be larger which consequently increases the accuracy of the proposed forecasting system . Printed Circuit Board (PCB will be used as a case study to evaluate the precision of our proposed architecture. Experimental results show that the proposed model outperforms the previous and traditional approaches. Therefore, it is a very promising solution for industrial forecasting.
Directory of Open Access Journals (Sweden)
S. KARMAKAR
2014-04-01
Full Text Available The utilization of back-propagation neural network in identification of internal dynamics of chaotic motion is found appropriate. However, during its training through Rumelhart algorithm, it is found that, a high learning rate ( leads to rapid learning but the weights may oscillate, while a lower value of ` ' leads to slower learning process in weight updating formula Momentum factor ( is to accelerate the convergence of error during the training in the equation and while transfer function sigmoid . It is the most complicated and experimental task to identify optimum value of ` ' and ` ' during the training. To identify optimum value of ` ' and ` ' , firstly the network is trained with 103 epochs under different values of ` ' in the close interval and At the convergence of initial weights and minimization of error (i.e., mean square error process is found appropriate. Afterwards to find optimum value of , the network was trained again with = 0.3 (fixed and with different values of in the close interval for 103 epochs. It was observed that the convergence of initial weights and minimization of error was appropriate with = 0.3 and = 0.9. On this optimum value of and the network was trained successfully from local minima of error = 1.67029292416874E-03 at 103 epochs to global minima of error = 4.99180426869658E-04 at 15 105 epochs. At the global minima, the network has exhibited excellent performance in identification of internal dynamics of chaotic motion and in prediction of future values by past recorded data series. These essentials are presented through this research paper.
Dai, Hengchang; MacBeth, Colin
1997-07-01
An automatic approach is developed to pick P and S arrivals from single component (1-C) recordings of local earthquake data. In this approach a back propagation neural network (BPNN) accepts a normalized segment (window of 40 samples) of absolute amplitudes from the 1-C recordings as its input pattern, calculating two output values between 0 and 1. The outputs (0,1) or (1,0) correspond to the presence of an arrival or background noise within a moving window. The two outputs form a time series. The P and S arrivals are then retrieved from this series by using a threshold and a local maximum rule. The BPNN is trained by only 10 pairs of P arrivals and background noise segments from the vertical component (V-C) recordings. It can also successfully pick seismic arrivals from the horizontal components (E-W and N-S). Its performance is different for each of the three components due to strong effects of ray path and source position on the seismic waveforms. For the data from two stations of TDP3 seismic network, the success rates are 93%, 89%, and 83% for P arrivals and 75%, 91%, and 87% for S arrivals from the V-C, E-W, and N-S recordings, respectively. The accuracy of the onset times picked from each individual 1-C recording is similar. Adding a constraint on the error to be 10 ms (one sample increment), 66%, 59% and 63% of the P arrivals and 53%, 61%, and 58% of the S arrivals are picked from the V-C, E-W and N-S recordings respectively. Its performance is lower than a similar three-component picking approach but higher than other 1-C picking methods.
Directory of Open Access Journals (Sweden)
Xianzhi Song
Full Text Available Sand production and blockage are common during the drilling and production of horizontal oil and gas wells as a result of formation breakdown. The use of high-pressure rotating jets and annular helical flow is an effective way to enhance horizontal wellbore cleanout. In this paper, we propose the idea of using supercritical CO2 (SC-CO2 as washing fluid in water-sensitive formation. SC-CO2 is manifested to be effective in preventing formation damage and enhancing production rate as drilling fluid, which justifies tis potential in wellbore cleanout. In order to investigate the effectiveness of SC-CO2 helical flow cleanout, we perform the numerical study on the annular flow field, which significantly affects sand cleanout efficiency, of SC-CO2 jets in horizontal wellbore. Based on the field data, the geometry model and mathematical models were built. Then a numerical simulation of the annular helical flow field by SC-CO2 jets was accomplished. The influences of several key parameters were investigated, and SC-CO2 jets were compared to conventional water jets. The results show that flow rate, ambient temperature, jet temperature, and nozzle assemblies play the most important roles on wellbore flow field. Once the difference between ambient temperatures and jet temperatures is kept constant, the wellbore velocity distributions will not change. With increasing lateral nozzle size or decreasing rear/forward nozzle size, suspending ability of SC-CO2 flow improves obviously. A back-propagation artificial neural network (BP-ANN was successfully employed to match the operation parameters and SC-CO2 flow velocities. A comprehensive model was achieved to optimize the operation parameters according to two strategies: cost-saving strategy and local optimal strategy. This paper can help to understand the distinct characteristics of SC-CO2 flow. And it is the first time that the BP-ANN is introduced to analyze the flow field during wellbore cleanout in
Song, Xianzhi; Peng, Chi; Li, Gensheng; He, Zhenguo; Wang, Haizhu
2016-01-01
Sand production and blockage are common during the drilling and production of horizontal oil and gas wells as a result of formation breakdown. The use of high-pressure rotating jets and annular helical flow is an effective way to enhance horizontal wellbore cleanout. In this paper, we propose the idea of using supercritical CO2 (SC-CO2) as washing fluid in water-sensitive formation. SC-CO2 is manifested to be effective in preventing formation damage and enhancing production rate as drilling fluid, which justifies tis potential in wellbore cleanout. In order to investigate the effectiveness of SC-CO2 helical flow cleanout, we perform the numerical study on the annular flow field, which significantly affects sand cleanout efficiency, of SC-CO2 jets in horizontal wellbore. Based on the field data, the geometry model and mathematical models were built. Then a numerical simulation of the annular helical flow field by SC-CO2 jets was accomplished. The influences of several key parameters were investigated, and SC-CO2 jets were compared to conventional water jets. The results show that flow rate, ambient temperature, jet temperature, and nozzle assemblies play the most important roles on wellbore flow field. Once the difference between ambient temperatures and jet temperatures is kept constant, the wellbore velocity distributions will not change. With increasing lateral nozzle size or decreasing rear/forward nozzle size, suspending ability of SC-CO2 flow improves obviously. A back-propagation artificial neural network (BP-ANN) was successfully employed to match the operation parameters and SC-CO2 flow velocities. A comprehensive model was achieved to optimize the operation parameters according to two strategies: cost-saving strategy and local optimal strategy. This paper can help to understand the distinct characteristics of SC-CO2 flow. And it is the first time that the BP-ANN is introduced to analyze the flow field during wellbore cleanout in horizontal wells. PMID
Dynamic recurrent neural networks
Pearlmutter, Barak A
1990-01-01
We survey learning algorithms for recurrent neural networks with hidden units and attempt to put the various techniques into a common framework. We discuss fixpoint learning algorithms, namely recurrent backpropagation and deterministic Boltzmann Machines, and non-fixpoint algorithms, namely backpropagation through time, Elman's history cutoff nets, and Jordan's output feedback architecture. Forward propagation, an online technique that uses adjoint equations, is also discussed. In many cases...
Uršič, Aleš
2012-01-01
The goal of this work is construction of an artificial life model and simulation of organisms in an environment with food. Organisms survive if they find food successfuly. With evolution and learning organisms develop a neural network which enables that. First neural networks and their history are introduced with the basic concepts like a neuron model, a network, transfer functions, topologies and learning. I describe the backpropagation learning on multilayer feed forward network and dem...
Premature saturation in backpropagation networks: Mechanism and necessary conditions
International Nuclear Information System (INIS)
The mechanism that gives rise to the phenomenon of premature saturation of the output units of feedforward multilayer neural networks during training with the standard backpropagation algorithm is described. The entire process of premature saturation is characterized by three distinct stages and it is concluded that the momentum term plays the leading role in the occurrence of the phenomenon. The necessary conditions for the occurrence of premature saturation are presented and a new method is proposed, based on these conditions, that eliminates the occurrence of the phenomenon. Validity of the conditions and the proposed method are illustrated through simulation results. Three case studies are presented. The first two came from a training session for classification of three component failures in a nuclear power plant. The last case, comes from a training session for classification of welded fuel elements
Al-Abadi, Alaa M.
2014-12-01
The potential of using three different data-driven techniques namely, multilayer perceptron with backpropagation artificial neural network (MLP), M5 decision tree model, and Takagi-Sugeno (TS) inference system for mimic stage-discharge relationship at Gharraf River system, southern Iraq has been investigated and discussed in this study. The study used the available stage and discharge data for predicting discharge using different combinations of stage, antecedent stages, and antecedent discharge values. The models' results were compared using root mean squared error (RMSE) and coefficient of determination (R 2) error statistics. The results of the comparison in testing stage reveal that M5 and Takagi-Sugeno techniques have certain advantages for setting up stage-discharge than multilayer perceptron artificial neural network. Although the performance of TS inference system was very close to that for M5 model in terms of R 2, the M5 method has the lowest RMSE (8.10 m3/s). The study implies that both M5 and TS inference systems are promising tool for identifying stage-discharge relationship in the study area.
Error-backpropagation in temporally encoded networks of spiking neurons
Bohte, S.M.; La Poutré, J.A.; Kok, J.N.
2000-01-01
For a network of spiking neurons that encodes information in the timing of individual spike-times, we derive a supervised learning rule, emph{SpikeProp, akin to traditional error-backpropagation and show how to overcome the discontinuities introduced by thresholding. With this algorithm, we demonstr
Error-backpropagation in temporally encoded networks of spiking neurons
Bohte, Sander; La Poutré, Han; Kok, Joost
2000-01-01
For a network of spiking neurons that encodes information in the timing of individual spike-times, we derive a supervised learning rule, emph{SpikeProp, akin to traditional error-backpropagation and show how to overcome the discontinuities introduced by thresholding. With this algorithm, we demonstrate how networks of spiking neurons with biologically reasonable action potentials can perform complex non-linear classification in fast temporal coding just as well as rate-coded networks. We perf...
Diaz-Robainas, Regino R.; Pandya, Abhijit S.; Huang, Ming Z.
1994-03-01
A method is developed to design simulations of neural-network based transfer functions, applicable to both linear and nonlinear structures. The algorithm used to implement the trainable neural mechanism is backpropagation. Using the trained structures as building blocks, a neural architecture is constructed in order to drive systems from expected inputs to satisfactory transient and steady-state output performance, in effect, the scope of control compensation; this method results in the design of neural-net control compensators. The algorithms are coded in a PC-based prolog, traditionally used for rule-based logic and Artificial Intelligence, rather than for Neural or Fuzzy models. Given a sequence representing the time-sample of a desired control input trajectory that will drive the plant to a desired output response, such a control input will be modelled as the desired output layer of an antecedent network driven by an error vector consistent with the closed-loop system's commanded behavior. This Controller network is trained to provide such an output profile for all expected inputs, in accordance with arbitrary specifications of rise-time, permitted overshoot, settling time, etc. The control vectors are generated as a by-product of this training. Additionally, a correlation is investigated between classical control parameters and the characteristics of the weight matrices, threshold vectors, and representation traits of the converged neural nets.
Yang, Tsung-Ming; Fan, Shu-Kai; Fan, Chihhao; Hsu, Nien-Sheng
2014-08-01
The purpose of this study is to establish a turbidity forecasting model as well as an early-warning system for turbidity management using rainfall records as the input variables. The Taipei Water Source Domain was employed as the study area, and ANOVA analysis showed that the accumulative rainfall records of 1-day Ping-lin, 2-day Ping-lin, 2-day Fei-tsui, 2-day Shi-san-gu, 2-day Tai-pin and 2-day Tong-hou were the six most significant parameters for downstream turbidity development. The artificial neural network model was developed and proven capable of predicting the turbidity concentration in the investigated catchment downstream area. The observed and model-calculated turbidity data were applied to developing the turbidity early-warning system. Using a previously determined turbidity as the threshold, the rainfall criterion, above which the downstream turbidity would possibly exceed this respective threshold turbidity, for the investigated rain gauge stations was determined. An exemplary illustration demonstrated the effectiveness of the proposed turbidity early-warning system as a precautionary alarm of possible significant increase of downstream turbidity. This study is the first report of the establishment of the turbidity early-warning system. Hopefully, this system can be applied to source water turbidity forecasting during storm events and provide a useful reference for subsequent adjustment of drinking water treatment operation. PMID:24691737
Adamowski, J. F.
2008-12-01
Cyprus is in the middle of an unprecedented water crisis that has lasted several years. Four ideas that have been considered to aid in resolving the problem include imposing effective water use restrictions, implementing water demand reduction programs, optimizing water supply systems, and developing alternative water source strategies. A critical component of each of these initiatives is the accurate forecasting of short- term peak water demands. This study compared multiple linear regression and three types of artificial neural networks (ANNs) as methods for peak weekly water demand forecast modeling. Analysis was performed on six years of peak weekly water demand data and meteorological variables (maximum weekly temperature and total weekly rainfall) for two different regions (Athalassa and Public Garden) in the city of Nicosia, Cyprus. Twenty multiple linear regression models, twenty Levenberg-Marquardt ANN models, twenty Resilient Back- Propagation ANN models, and twenty Conjugate Gradient Powell-Beale ANN models were developed and their relative performance was compared. For both the Athalassa and Public Garden regions in Nicosia, the Levenberg-Marquardt ANN method was found to provide a more accurate forecast of peak weekly water demand than the other two types of ANNs and multiple linear regression. It was also found that the peak weekly water demand in Nicosia is better correlated with the rainfall occurrence rather than the amount of rainfall itself.
Energy Technology Data Exchange (ETDEWEB)
Toda-Caraballo, I.; Garcia-Mateo, C.; Capdevila, C.
2010-07-01
At the beginning of the decade of the nineties, the industrial interest for TRIP steels leads to a significant increase of the investigation and application in this field. In this work, the flexibility of neural networks for the modelling of complex properties is used to tackle the problem of determining the retained austenite content in TRIP-steel. Applying a combination of two learning algorithms (backpropagation and creeping-random-search) for the neural network, a model has been created that enables the prediction of retained austenite in low-Si / low-Al multiphase steels as a function of processing parameters. (Author). 34 refs.
Knoll, P; Mirzaei, S; Müllner, A; Leitha, T; Koriska, K; Köhn, H; Neumann, M
1999-02-01
At present, algorithms used in nuclear medicine to reconstruct single photon emission computerized tomography (SPECT) data are usually based on one of two principles: filtered backprojection and iterative methods. In this paper a different algorithm, applying an artificial neural network (multilayer perception) and error backpropagation as training method are used to reconstruct transaxial slices from SPECT data. The algorithm was implemented on an Elscint XPERT workstation (i486, 50 MHz), used as a routine digital image processing tool in our departments. Reconstruction time for a 64 x 64 matrix is approximately 45 s/transaxial slice. The algorithm has been validated by a mathematical model and tested on heart and Jaszczak phantoms. Phantom studies and very first clinical results ((111)In octreotide SPECT, 99mTc MDP bone SPECT) show in comparison with filtered backprojection an enhancement in image quality. PMID:10076982
Institute of Scientific and Technical Information of China (English)
范媛媛; 桑英军; 沈湘衡
2011-01-01
在基于噪声图像的无参考峰值信噪比质量评价方法中,为了得到最优的阈值参数,提出以图像块均方误差阈值threshold1、噪声检测阈值threshold2为输入因子,以Pearson相关系数和Spearman等级相关系数为输出因子,以实验值为样本建立[2 7 2]单隐层BP神经网络模型,应用BP神经网络的泛化能力实现对相关阈值参数的预测优化,为阈值参数的选择提供理论依据.实验结果表明,所建立的数学模型可靠,预测结果与试验值的偏差小,训练好的BP神经网络能够比较准确地预测不同阈值参数下的相关系数.优化后,选取threshold1=101,threshold2 =4,Pearson相关系数达到了-0.895 0,Spearman等级相关系数达到了-0.913 6,评价效果得到提高,且节省大量时间.%In no reference peak signal to noise ratio (PSNR) image quality assessment based on noisy images, in order to get optimal threshold parameters, it is proposed that taking experiment values as a sample, a [2 7 2] back-propagation (BP) neural network model is established with the mean square error (MSE) thresholdl of image block and the noise detection threshold2 as the input factors, and the Person and Spearman correlation coefficients as the output factors. The model realizes the prediction of relevant parameters by its generalization capability and offers a theoretical foundation for parameters selection. Experiments indicate that the model is reliable. The prediction results show little difference from the experimental data. The trained BP neural network can precisely predict the relevant parameters. After optimizing, thresholdl = 101 and threshold2 = 4 are selected, Pearson Correlation Coefficient and Spearman Rank Order Correlation Coefficient reaches -0. 895 0 and -0. 913 6 respectively. The assessment result improves a lot, and much time is saved.
USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS
Şeker, Murat; E. Selim YILDIRIM; BERKAY, Ahmet
2004-01-01
Examples of successful applications in Artificial Intelligence (AI) field; With financial applications, Control, Communication, Processing Radar signals, Pattern Recognition, general DSP application, Nonlinear Systems can be given. In the financial applications, generally back propagation (Feedforwared) algorithms of the Neural Network (NN) uses. In this application, backpropagation algorithms applied to Multi Layer Feedforward Neural Network for the future estimations of foreign currency exc...
Automatic Generation of Neural Networks
A. Fiszelew; P. Britos; G. Perichisky; R. García-Martínez
2003-01-01
This work deals with methods for finding optimal neural network architectures to learn particular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a performance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employ...
USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS
Directory of Open Access Journals (Sweden)
Murat ŞEKER
2004-04-01
Full Text Available Examples of successful applications in Artificial Intelligence (AI field; With financial applications, Control, Communication, Processing Radar signals, Pattern Recognition, general DSP application, Nonlinear Systems can be given. In the financial applications, generally back propagation (Feedforwared algorithms of the Neural Network (NN uses. In this application, backpropagation algorithms applied to Multi Layer Feedforward Neural Network for the future estimations of foreign currency exchange rates data. The calculation results which was founded by using past exchange rates data "estimations that produce by Neural Network Layers and parameters, which carry out by backpropagation algorithms for different values" was compared with the real data for measuring the productivity of the method.
Institute of Scientific and Technical Information of China (English)
舒雅琴; 曾锦光
2000-01-01
A GA-BP complex algorithm based on real number coding is proposed. The algorithm optimizes the original weights, structure and learning rules of BP network to search the optimal solution in the solution space. An example of oil/gas prediction is given.%提出了一种基于实数编码的GA－BP复合算法，该算法对BP网络初始权值、结构、学习规则进行优化，从而在解空间中搜索出最优解．文中还给出了应用该算法解决油气产能预测的实例．
Introduction to neural networks
International Nuclear Information System (INIS)
This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix
Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization.
Lee, Charles W.
1997-01-01
An algorithm is derived for supervised training in multilayer feedforward neural networks. Relative to the gradient descent backpropagation algorithm it appears to give both faster convergence and improved generalization, whilst preserving the system of backpropagating errors through the network. Copyright 1996 Elsevier Science Ltd. PMID:12662887
Information Theory for Analyzing Neural Networks
Sørngård, Bård
2014-01-01
The goal of this thesis was to investigate how information theory could be used to analyze artificial neural networks. For this purpose, two problems, a classification problem and a controller problem were considered. The classification problem was solved with a feedforward neural network trained with backpropagation, the controller problem was solved with a continuous-time recurrent neural network optimized with evolution.Results from the classification problem shows that mutual information ...
Artificial neural networks in NDT
International Nuclear Information System (INIS)
Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)
Context dependent learning in neural networks
Spreeuwers, L.J.; Zwaag, van der, Berend Jan; Heijden, van der, M.
1995-01-01
In this paper an extension to the standard error backpropagation learning rule for multi-layer feed forward neural networks is proposed, that enables them to be trained for context dependent information. The context dependent learning is realised by using a different error function (called Average Risk: AVR) in stead of the sum of squared errors (SQE) normally used in error backpropagation and by adapting the update rules. It is shown that for applications where this context dependent informa...
SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK
Institute of Scientific and Technical Information of China (English)
无
2003-01-01
For the redundant manipulators, neural network is used to tackle the velocity inverse kinematics of robot manipulators. The neural networks utilized are multi-layered perceptions with a back-propagation training algorithm. The weight table is used to save the weights solving the inverse kinematics based on the different optimization performance criteria. Simulations verify the effectiveness of using neural network.
A brief review of feed-forward neural networks
SAZLI, Murat Hüsnü
2006-01-01
Artificial neural networks, or shortly neural networks, find applications in a very wide spectrum. In this paper, following a brief presentation of the basic aspects of feed-forward neural networks, their mostly used learning/training algorithm, the so-called back-propagation algorithm, have been described.
Extrapolation limitations of multilayer feedforward neural networks
Haley, Pamela J.; Soloway, Donald
1992-01-01
The limitations of backpropagation used as a function extrapolator were investigated. Four common functions were used to investigate the network's extrapolation capability. The purpose of the experiment was to determine whether neural networks are capable of extrapolation and, if so, to determine the range for which networks can extrapolate. The authors show that neural networks cannot extrapolate and offer an explanation to support this result.
Medical diagnosis using neural network
Kamruzzaman, S M; Siddiquee, Abu Bakar; Mazumder, Md Ehsanul Hoque
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural networ...
Rule Extraction using Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Artificial neural networks have been successfully applied to a variety of business application problems involving classification and regression. Although backpropagation neural networks generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions are not as interpretable as those of decision trees. In many applications, it is desirable to extract knowledge from trained neural networks so that the users can gain a better understanding of the solution. This paper presents an efficient algorithm to extract rules from artificial neural networks. We use two-phase training algorithm for backpropagation learning. In the first phase, the number of hidden nodes of the network is determined automatically in a constructive fashion by adding nodes one after another based on the performance of the network on training data. In the second phase, the number of relevant input units of the network is determined using pruning algorithm. The ...
Learning Processes of Layered Neural Networks
Fujiki, Sumiyoshi; Fujiki, Nahomi M.
1995-01-01
A positive reinforcement type learning algorithm is formulated for a stochastic feed-forward neural network, and a learning equation similar to that of the Boltzmann machine algorithm is obtained. By applying a mean field approximation to the same stochastic feed-forward neural network, a deterministic analog feed-forward network is obtained and the back-propagation learning rule is re-derived.
Equivalence of backpropagation and contrastive Hebbian learning in a layered network.
Xie, Xiaohui; Seung, H Sebastian
2003-02-01
Backpropagation and contrastive Hebbian learning are two methods of training networks with hidden neurons. Backpropagation computes an error signal for the output neurons and spreads it over the hidden neurons. Contrastive Hebbian learning involves clamping the output neurons at desired values and letting the effect spread through feedback connections over the entire network. To investigate the relationship between these two forms of learning, we consider a special case in which they are identical: a multilayer perceptron with linear output units, to which weak feedback connections have been added. In this case, the change in network state caused by clamping the output neurons turns out to be the same as the error signal spread by backpropagation, except for a scalar prefactor. This suggests that the functionality of backpropagation can be realized alternatively by a Hebbian-type learning algorithm, which is suitable for implementation in biological networks. PMID:12590814
International Nuclear Information System (INIS)
Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing
Advances in Artificial Neural Networks – Methodological Development and Application
Yanbo Huang
2009-01-01
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 networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a back...
Advances in Artificial Neural Networks - Methodological Development and Application
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...
Dynamic Analysis of Structures Using Neural Networks
Directory of Open Access Journals (Sweden)
N. Ahmadi
2008-01-01
Full Text Available In the recent years, neural networks are considered as the best candidate for fast approximation with arbitrary accuracy in the time consuming problems. Dynamic analysis of structures against earthquake has the time consuming process. We employed two kinds of neural networks: Generalized Regression neural network (GR and Back-Propagation Wavenet neural network (BPW, for approximating of dynamic time history response of frame structures. GR is a traditional radial basis function neural network while BPW categorized as a wavelet neural network. In BPW, sigmoid activation functions of hidden layer neurons are substituted with wavelets and weights training are achieved using Scaled Conjugate Gradient (SCG algorithm. Comparison the results of BPW with those of GR in the dynamic analysis of eight story steel frame indicates that accuracy of the properly trained BPW was better than that of GR and therefore, BPW can be efficiently used for approximate dynamic analysis of structures.
Czech Academy of Sciences Publication Activity Database
Vajda, Igor; Grim, Jiří
Oxford : Eolss Publishers-UNESCO, 2008 - (Parra-Luna, F.), s. 224-248 ISBN 978-1-84826-654-4. - (Encyclopedia of Life Support Systems. Volume III) R&D Projects: GA ČR GA102/07/1594 Institutional research plan: CEZ:AV0Z10750506 Keywords : neural networks * probabilistic approach Subject RIV: BD - Theory of Information http://library.utia.cas.cz/separaty/2008/SI/vajda-systems science and cybernetics .pdf
Modular neural networks and reinforcement learning
Raicevic, Peter
2004-01-01
We investigate the effect of modular architecture in an artificial neural network for a reinforcement learning problem. Using the supervised backpropagation algorithm to solve a two-task problem, the network performance can be increased by using networks with modular structures. However, using a modular architecture to solve a two-task reinforcement learning problem will not increase the performance compared to a non-modular structure. We show that by combining a modular structure with a modu...
Institute of Scientific and Technical Information of China (English)
吕学志; 范保新; 尹建; 王宪文
2014-01-01
在任务执行期合理、科学地确定维修任务的优先级别对于有序、高效地组织维修保障活动具有重要意义。提出了一种基于BP神经网络的维修任务优先级分类方法。详细介绍了神经网络模型的建模过程，其中重点介绍了模型设计，包括输入数据准备、输出数据准备与神经网络结构。所建立的神经网络模型通过对输入与输出的训练，可以学习准则与维修任务优先级之间的复杂关系，获得并表示决策者的偏好，有效地辅助决策者对维修任务优先级进行分类。%During mission, determining priority categories of maintenance task rationally and scientifically is valuable to effectiveness and efficiency of maintenance support. A priority sorting approach of maintenance task during mission based on BP neural networks is proposed. Modeling process of neural networks model is discussed in detail, and it focuses on model design that includes input data preparation, output data preparation and neural networks structure. Through training of input and output, established neural networks can learn complex relationship between criteria and priority of mainte-nance tasks, obtain preference of decision makers, help decision maker sort maintenance tasks according to their priority.
Video Traffic Prediction Using Neural Networks
Directory of Open Access Journals (Sweden)
Miloš Oravec
2008-10-01
Full Text Available In this paper, we consider video stream prediction for application in services likevideo-on-demand, videoconferencing, video broadcasting, etc. The aim is to predict thevideo stream for an efficient bandwidth allocation of the video signal. Efficient predictionof traffic generated by multimedia sources is an important part of traffic and congestioncontrol procedures at the network edges. As a tool for the prediction, we use neuralnetworks – multilayer perceptron (MLP, radial basis function networks (RBF networksand backpropagation through time (BPTT neural networks. At first, we briefly introducetheoretical background of neural networks, the prediction methods and the differencebetween them. We propose also video time-series processing using moving averages.Simulation results for each type of neural network together with final comparisons arepresented. For comparison purposes, also conventional (non-neural prediction isincluded. The purpose of our work is to construct suitable neural networks for variable bitrate video prediction and evaluate them. We use video traces from [1].
Neural Networks Applied to Thermal Damage Classification in Grinding Process
Spadotto, Marcelo M.; Aguiar, Paulo Roberto de; Sousa, Carlos C. P.; Bianchi, Eduardo C.
2008-01-01
The utilization of neural network of type multi-layer perceptron using the back-propagation algorithm guaranteed very good results. Tests carried out in order to optimize the learning capacity of neural networks were of utmost importance in the training phase, where the optimum values for the number of neurons of the hidden layer, learning rate and momentum for each structure were determined. Once the architecture of the neural network was established with those optimum values, the mean squar...
Methods of Forecasting Based on Artificial Neural Networks
Stepčenko, A; Borisovs, A
2014-01-01
This article presents an overview of artificial neural network (ANN) applications in forecasting and possible forecasting accuracy improvements. Artificial neural networks are computational models and universal approximators, which can be applied to the time series forecasting with a high accuracy. A great rise in research activities was observed in using artificial neural networks for forecasting. This paper examines multi-layer perceptrons (MLPs) – back-propagation neur...
Local learning algorithm for optical neural networks
QIAO, YONG; Psaltis, Demetri
1992-01-01
An anti-Hebbian local learning algorithm for two-layer optical neural networks is introduced. With this learning rule, the weight update for a certain connection depends only on the input and output of that connection and a global, scalar error signal. Therefore the backpropagation of error signals through the network, as required by the commonly used back error propagation algorithm, is avoided. It still guarantees, however, that the synaptic weights are updated in the error descent directio...
Energy Technology Data Exchange (ETDEWEB)
Rosas Ortiz, German
2000-01-01
Fault detection and diagnosis on transmission systems is an interesting area of investigation to Artificial Intelligence (AI) based systems. Neurocomputing is one of fastest growing areas of research in the fields of AI and pattern recognition. This work explores the possible suitability of pattern recognition approach of neural networks for fault detection and classification on power systems. The conventional detection techniques in modern relays are based in digital processing of signals and it need some time (around 1 cycle) to send a tripping signal, also they are likely to make incorrect decisions if the signals are noisy. It's desirable to develop a fast, accurate and robust approach that perform accurately for changing system conditions (like load variations and fault resistance). The aim of this work is to develop a novel technique based on Artificial Neural Networks (ANN), which explores the suitability of a pattern classification approach for fault detection and diagnosis. The suggested approach is based in the fact that when a fault occurs, a change in the system impedance take place and, as a consequence changes in amplitude and phase of line voltage and current signals take place. The ANN-based fault discriminator is trained to detect this changes as indicators of the instant of fault inception. This detector uses instantaneous values of these signals to make decisions. Suitability of using neural network as pattern classifiers for transmission systems fault diagnosis is described in detail a neural network design and simulation environment for real-time is presented. Results showing the performance of this approach are presented and indicate that it is fast, secure and exact enough, and it can be used in high speed fault detection and classification schemes. [Spanish] El diagnostico y la deteccion de fallas en sistemas de transmision es una area de interes en investigacion para sistemas basados en Inteligencia Artificial (IA). El calculo neuronal
Pengenalan Pola Pin Barcode Menggunakan Metode Backpropagation dan Metode Perceptron
Hasiholan, Ardi
2015-01-01
Pattern recognition is one of the functions of the neural networks, where objects maybe identified by their patterns. This may assist in recognition of objects which patterns are damaged. Pattern recognition in neural networkcan make by using backpropagation and perceptron methods. In Backpropagation method, the network is trained with the pattern through three phases, namely forward propagation, backward propagation, and weights adjustment phases, repeated until the termination condition is ...
Neural network error correction for solving coupled ordinary differential equations
Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.
1992-01-01
A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.
Application of four-layer neural network on information extraction.
Han, Min; Cheng, Lei; Meng, Hua
2003-01-01
This paper applies neural network to extract marsh information. An adaptive back-propagation algorithm based on a robust error function is introduced to build a four-layer neural network, and it is used to classify Thematic Mapper (TM) image of Zhalong Wetland in China and then extract marsh information. Comparing marsh information extraction results of the four-layer neural network with three-layer neural network and the maximum likelihood classifier, conclusion can be drawn as follows: the structure of the four-layer neural network and the adaptive back-propagation algorithm based on the robust error function is effective to extract marsh information. The four-layer neural network adopted in this paper succeeded in building the complex model of TM image, and it avoided the problem of great storage of remotely sensed data, and the adaptive back-propagation algorithm speeded up the descending of error. Above all, the four-layer neural network is superior to the three-layer neural network and the maximum likelihood classifier in the accuracy of the total classification and marsh information extraction. PMID:12850006
Artificial Neural Networks, Symmetries and Differential Evolution
Urfalioglu, Onay; Arikan, Orhan
2010-01-01
Neuroevolution is an active and growing research field, especially in times of increasingly parallel computing architectures. Learning methods for Artificial Neural Networks (ANN) can be divided into two groups. Neuroevolution is mainly based on Monte-Carlo techniques and belongs to the group of global search methods, whereas other methods such as backpropagation belong to the group of local search methods. ANN's comprise important symmetry properties, which can influence Monte-Carlo methods....
Classification of coffee using artificial neural network
Yip, DHF; Yu, WWH
1996-01-01
The paper presents a method for classifying coffees according to their scents using artificial neural network (ANN). The proposed method of uses genetic algorithm (GA) to determine the optimal parameters and topology of ANN. It uses adaptive backpropagation to accelerate the training process so that the entire optimization process can be achieved in an accelerated time. The optimized ANN has successfully classified the coffees using a relatively small set of training data. The performance of ...
Tests of track segment and vertex finding with neural networks
International Nuclear Information System (INIS)
Feed forward neural networks have been trained, using back-propagation, to find the slopes of simulated track segments in a straw chamber and to find the vertex of tracks from both simulated and real events in a more conventional drift chamber geometry. Network architectures, training, and performance are presented. 12 refs., 7 figs
Neural network tomography: network replication from output surface geometry.
Minnett, Rupert C J; Smith, Andrew T; Lennon, William C; Hecht-Nielsen, Robert
2011-06-01
Multilayer perceptron networks whose outputs consist of affine combinations of hidden units using the tanh activation function are universal function approximators and are used for regression, typically by reducing the MSE with backpropagation. We present a neural network weight learning algorithm that directly positions the hidden units within input space by numerically analyzing the curvature of the output surface. Our results show that under some sampling requirements, this method can reliably recover the parameters of a neural network used to generate a data set. PMID:21377326
Optimal control learning with artificial neural networks
International Nuclear Information System (INIS)
This paper shows neural networks capabilities in optimal control applications of non linear dynamic systems. Our method is issued of a classical method concerning the direct research of the optimal control using gradient techniques. We show that neural approach and backpropagation paradigm are able to solve efficiently equations relative to necessary conditions for an optimizing solution. We have taken into account the known capabilities of multi layered networks in approximation functions. And for dynamic systems, we have generalized the indirect learning of inverse model adaptive architecture that is capable to define an optimal control in relation to a temporal criterion. (orig.)
Tracking and vertex finding with drift chambers and neural networks
International Nuclear Information System (INIS)
Finding tracks, track vertices and event vertices with neural networks from drift chamber signals is discussed. Simulated feed-forward neural networks have been trained with back-propagation to give track parameters using Monte Carlo simulated tracks in one case and actual experimental data in another. Effects on network performance of limited weight resolution, noise and drift chamber resolution are given. Possible implementations in hardware are discussed. 7 refs., 10 figs
A Global Algorithm for Training Multilayer Neural Networks
ZHAO, HONG; Jin, Tao
2006-01-01
We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples i...
Using Artificial Neural Networks for ECG Signals Denoising
Zoltán Germán-Salló; Katalin György
2010-01-01
The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG) signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1)th sample from n previous samples To train and adjust the network weights, the backpropagation (BP) algorithm was used. In this paper, prediction of ECG signals (as...
Artificial neural networks for plasma spectroscopy analysis
International Nuclear Information System (INIS)
Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics
Spike-timing error backpropagation in theta neuron networks.
McKennoch, Sam; Voegtlin, Thomas; Bushnell, Linda
2009-01-01
The main contribution of this letter is the derivation of a steepest gradient descent learning rule for a multilayer network of theta neurons, a one-dimensional nonlinear neuron model. Central to our model is the assumption that the intrinsic neuron dynamics are sufficient to achieve consistent time coding, with no need to involve the precise shape of postsynaptic currents; this assumption departs from other related models such as SpikeProp and Tempotron learning. Our results clearly show that it is possible to perform complex computations by applying supervised learning techniques to the spike times and time response properties of nonlinear integrate and fire neurons. Networks trained with our multilayer training rule are shown to have similar generalization abilities for spike latency pattern classification as Tempotron learning. The rule is also able to train networks to perform complex regression tasks that neither SpikeProp or Tempotron learning appears to be capable of. PMID:19431278
基于动态BP神经网络的财务危机预警算法研究%Efficient financial forecast based on dynamic back-propagation neural network
Institute of Scientific and Technical Information of China (English)
杨济亭
2013-01-01
Most of the classical methods in the investigations of financial forecast are generally based on a static pre-warning modeling by only exploring the single-period financial data, such as the signal-variable analysis, multiple-variables analysis, Logit regression analysis, which unfortunately ignores the potential influences from the historical data. In order to enhance the accuracy and stability of the financial forecasting, a promising dynamic back propagation ( BP) neural network relying on the Logit nonlinear mapping is proposed to perform financial forecasting. The historical panel data of financial companies is also fully taken into consideration in this new method, and different weights associated with different period data is used. The experimental results have demonstrated the effectiveness and the fair accuracy of the new forecasting model.%为进一步提升模型合理性和预测结果准确度,充分考虑公司财务情况历史值的影响,通过对不同时期的财务面板数据赋以不同权重,设计提出了一种基于Logit-动态BP神经网络的财务危机预警机制.实证结果显示,基于面板数据的新模型能更好地体现财务危机的发生机理,因而具备良好预警精度；在对财务危机公司及财务正常公司预警实验中,其预测性能均优于现有Logit回归分析模型和传统神经网络模型.
Advances in Artificial Neural Networks – Methodological Development and Application
Directory of Open Access Journals (Sweden)
Yanbo Huang
2009-08-01
Full Text Available 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 networks such as radial basis function, recurrent network, feedback network, and unsupervised Kohonen self-organizing network. These networks, especially the multilayer perceptron network with a backpropagation training algorithm, have gained recognition in research and applications in various scientific and engineering areas. In order to accelerate the training process and overcome data over-fitting, research has been conducted to improve the backpropagation algorithm. Further, artificial neural networks have been integrated with other advanced methods such as fuzzy logic and wavelet analysis, to enhance the ability of data interpretation and modeling and to avoid subjectivity in the operation of the training algorithm. In recent years, support vector machines have emerged as a set of high-performance supervised generalized linear classifiers in parallel with artificial neural networks. A review on development history of artificial neural networks is presented and the standard architectures and algorithms of artificial neural networks are described. Furthermore, advanced artificial neural networks will be introduced with support vector machines, and limitations of ANNs will be identified. The future of artificial neural network development in tandem with support vector machines will be discussed in conjunction with further applications to food science and engineering, soil and water relationship for crop management, and decision support for precision agriculture. Along with the network structures and training algorithms, the applications of artificial neural networks will be reviewed as well, especially in the fields of agricultural and biological
Neural network models for a resource allocation problem.
Walczak, S
1998-01-01
University admissions and business personnel offices use a limited number of resources to process an ever-increasing quantity of student and employment applications. Application systems are further constrained to identify and acquire, in a limited time period, those candidates who are most likely to accept an offer of enrolment or employment. Neural networks are a new methodology to this particular domain. Various neural network architectures and learning algorithms are analyzed comparatively to determine the applicability of supervised learning neural networks to the domain problem of personnel resource allocation and to identify optimal learning strategies in this domain. This paper focuses on multilayer perceptron backpropagation, radial basis function, counterpropagation, general regression, fuzzy ARTMAP, and linear vector quantization neural networks. Each neural network predicts the probability of enrolment and nonenrolment for individual student applicants. Backpropagation networks produced the best overall performance. Network performance results are measured by the reduction in counsellors student case load and corresponding increases in student enrolment. The backpropagation neural networks achieve a 56% reduction in counsellor case load. PMID:18255946
Manger, R
1998-01-01
Holographic neural networks are a new and promising type of artificial neural networks. This article gives an overview of the holographic neural technology and its possibilities. The theoretical principles of holographic networks are first reviewed. Then, some other papers are presented, where holographic networks have been applied or experimentally evaluated. A case study dealing with currency exchange rate prediction is described in more detail.
Incorporation of liquid-crystal light valve nonlinearities in optical multilayer neural networks.
Moerland, P D; Fiesler, E; Saxena, I
1996-09-10
Sigmoidlike activation functions, as available in analog hardware, differ in various ways from the standard sigmoidal function because they are usually asymmetric, truncated, and have a nonstandard gain. We present an adaptation of the backpropagation learning rule to compensate for these nonstandard sigmoids. This method is applied to multilayer neural networks with all-optical forward propagation and liquid-crystal light valves (LCLV) as optical thresholding devices. The results of simulations of a backpropagation neural network with five different LCLV response curves as activation functions are presented. Although LCLV's perform poorly with the standard backpropagation algorithm, it is shown that our adapted learning rule performs well with these LCLV curves. PMID:21127522
A Neural Network Based Collision Detection Engine for Multi-Arm Robotic Systems
Rana, A. S.; Zalzala, A.M.S.
1996-01-01
A neural ntwork is proposed for collision detection among multiple robotic arms sharing a common workspace. The structure of the neural network is a hybrid between Guassian Radial Basis Function (RBF) neural networks and Multi-layer perceptron back-propagation (BP) neural networks. This network is used to generate potential fields in the configuration space of the robotic arms. A path planning algorithm based on heuristics is presented. It is shown that this algorithm works better than the c...
Jet analysis by neural networks in high energy hadron-hadron collisions
De Felice, P; Pasquariello, G; De Felice, P; Nardulli, G; Pasquariello, G
1995-01-01
We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the k_\\bot algorithm. We consider both supervised multilayer feed-forward network trained by the backpropagation algorithm and unsupervised learning, where the neural network autonomously organizes the events in clusters.
JET ANALYSIS BY NEURAL NETWORKS IN HIGH ENERGY HADRON-HADRON COLLISIONS
De Felice, P.; Nardulli, G.; Pasquariello, G
1995-01-01
We study the possibility to employ neural networks to simulate jet clustering procedures in high energy hadron-hadron collisions. We concentrate our analysis on the Fermilab Tevatron energy and on the $k_\\bot$ algorithm. We consider both supervised multilayer feed-forward network trained by the backpropagation algorithm and unsupervised learning, where the neural network autonomously organizes the events in clusters.
Computationally Efficient Neural Network Intrusion Security Awareness
Energy Technology Data Exchange (ETDEWEB)
Todd Vollmer; Milos Manic
2009-08-01
An enhanced version of an algorithm to provide anomaly based intrusion detection alerts for cyber security state awareness is detailed. A unique aspect is the training of an error back-propagation neural network with intrusion detection rule features to provide a recognition basis. Network packet details are subsequently provided to the trained network to produce a classification. This leverages rule knowledge sets to produce classifications for anomaly based systems. Several test cases executed on ICMP protocol revealed a 60% identification rate of true positives. This rate matched the previous work, but 70% less memory was used and the run time was reduced to less than 1 second from 37 seconds.
AUTOMATED DEFECT CLASSIFICATION USING AN ARTIFICIAL NEURAL NETWORK
International Nuclear Information System (INIS)
The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.
Radar Target Classification Using Neural Network and Median Filter
J. Kurty; Z. Matousek
2001-01-01
The paper deals with Radar Target Classification based on the use of a neural network. A radar signal was acquired from the output of a J frequency band noncoherent radar. We applied the three layer feed forward neural network using the backpropagation learning algorithm. We defined classes of radar targets and designated each of them by its number. Our classification process resulted in the number of a radar target class, which the radar target belongs to.
Automated Defect Classification Using AN Artificial Neural Network
Chady, T.; Caryk, M.; Piekarczyk, B.
2009-03-01
The automated defect classification algorithm based on artificial neural network with multilayer backpropagation structure was utilized. The selected features of flaws were used as input data. In order to train the neural network it is necessary to prepare learning data which is representative database of defects. Database preparation requires the following steps: image acquisition and pre-processing, image enhancement, defect detection and feature extraction. The real digital radiographs of welded parts of a ship were used for this purpose.
Methodological Issues in Building, Training, and Testing Artificial Neural Networks
Ozesmi, Stacy L.; Ozesmi, Uygar; Tan, Can Ozan
2005-01-01
We review the use of artificial neural networks, particularly the feedforward multilayer perceptron with back-propagation for training (MLP), in ecological modelling. Overtraining on data or giving vague references to how it was avoided is the major problem. Various methods can be used to determine when to stop training in artificial neural networks: 1) early stopping based on cross-validation, 2) stopping after a analyst defined error is reached or after the error levels off, 3) use of a tes...
A Plausible Memristor Implementation of Deep Learning Neural Networks
Negrov, D. V.; Karandashev, I. M.; Shakirov, V. V.; Matveyev, Yu. A.; Dunin-Barkowski, W. L.; Zenkevich, A. V.
2015-01-01
A possible method for hardware implementation of multilayer neural networks with the back-propagation learning algorithm employing memristor cross-bar matrices for weight storage is modeled. The proposed approach offers an efficient way to perform both learning and recognition operations. The solution of several arising problems, such as the representation and multiplication of signals as well as error propagation is proposed.
Application of artificial neural networks in nonlinear analysis of trusses
Alam, J.; Berke, L.
1991-01-01
A method is developed to incorporate neural network model based upon the Backpropagation algorithm for material response into nonlinear elastic truss analysis using the initial stiffness method. Different network configurations are developed to assess the accuracy of neural network modeling of nonlinear material response. In addition to this, a scheme based upon linear interpolation for material data, is also implemented for comparison purposes. It is found that neural network approach can yield very accurate results if used with care. For the type of problems under consideration, it offers a viable alternative to other material modeling methods.
Web traffic prediction with artificial neural networks
Gluszek, Adam; Kekez, Michal; Rudzinski, Filip
2005-02-01
The main aim of the paper is to present application of the artificial neural network in the web traffic prediction. First, the general problem of time series modelling and forecasting is shortly described. Next, the details of building of dynamic processes models with the neural networks are discussed. At this point determination of the model structure in terms of its inputs and outputs is the most important question because this structure is a rough approximation of the dynamics of the modelled process. The following section of the paper presents the results obtained applying artificial neural network (classical multilayer perceptron trained with backpropagation algorithm) to the real-world web traffic prediction. Finally, we discuss the results, describe weak points of presented method and propose some alternative approaches.
Membership generation using multilayer neural network
Kim, Jaeseok
1992-01-01
There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.
Deep learning in neural networks: an overview.
Schmidhuber, Jürgen
2015-01-01
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links between actions and effects. I review deep supervised learning (also recapitulating the history of backpropagation), unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. PMID:25462637
Neural network method for characterizing video cameras
Zhou, Shuangquan; Zhao, Dazun
1998-08-01
This paper presents a neural network method for characterizing color video camera. A multilayer feedforward network with the error back-propagation learning rule for training, is used as a nonlinear transformer to model a camera, which realizes a mapping from the CIELAB color space to RGB color space. With SONY video camera, D65 illuminant, Pritchard Spectroradiometer, 410 JIS color charts as training data and 36 charts as testing data, results show that the mean error of training data is 2.9 and that of testing data is 4.0 in a 2563 RGB space.
Design of neural networks for classification of remotely sensed imagery
Chettri, Samir R.; Cromp, Robert F.; Birmingham, Mark
1992-01-01
Classification accuracies of a backpropagation neural network are discussed and compared with a maximum likelihood classifier (MLC) with multivariate normal class models. We have found that, because of its nonparametric nature, the neural network outperforms the MLC in this area. In addition, we discuss techniques for constructing optimal neural nets on parallel hardware like the MasPar MP-1 currently at GSFC. Other important discussions are centered around training and classification times of the two methods, and sensitivity to the training data. Finally, we discuss future work in the area of classification and neural nets.
Suppressing Halo-chaos for Intense Ion Beamby Neural Network Adaptation Control Strategy
Institute of Scientific and Technical Information of China (English)
FANGJin-qing; LUOXiao-shu; WENGJia-qiang; ZHULun-wu
2003-01-01
Neural network has some advantages of adaptation, learn-self, self-organization and suitable for high-dimension for various applications in many fields, especially among them the feed-forward back-propagating neural network self-adaptation method is suitable for control of nonlinear systems.
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Financial Time Series Prediction Using Elman Recurrent Random Neural Networks
Wang, Jie; Wang, Jun; Fang, Wen; Niu, Hongli
2016-01-01
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices. PMID:27293423
Institute of Scientific and Technical Information of China (English)
邓斌; 周志刚; 马泽粦; 易来龙; 张锡萍; 郭晃潮; 梅月志
2008-01-01
目的 应用BP人工神经网络模型探讨气象因素对肺结核病发病影响,同时建立肺结核病与气象因素关系的BP神经网络模型.方法 利用Matlab 6.5的Statistics Neural Network软件对气象因素与肺结核病关系的BP人工神经网络模型进行构建、训练与模拟.结果 经过数据训练得出理想网络模型,肺结核病发病回代误差均方、平均误差率和R2分别为0.00713、0.82和0.9081,说明所得人工神经网络模型效果理想.通过对自变量对输出量贡献量分析表明,平均蒸发量对肺结核发病影响最大,平均气压亦有一定影响.结论 肺结核与气象因素关系的BP人工神经网络模型效果良好,有助于进一步研究的价值.
The need for stochastic replication of ecological neural networks
Tosh, Colin R; Ruxton, Graeme D.
2007-01-01
Artificial neural networks are becoming increasingly popular as predictive statistical tools in ecosystem ecology and as models of signal processing in behavioural and evolutionary ecology. We demonstrate here that a commonly used network in ecology, the three-layer feed-forward network, trained with the backpropagation algorithm, can be extremely sensitive to the stochastic variation in training data that results from random sampling of the same underlying statistical distribution, with netw...
Chaotic diagonal recurrent neural network
Institute of Scientific and Technical Information of China (English)
Wang Xing-Yuan; Zhang Yi
2012-01-01
We propose a novel neural network based on a diagonal recurrent neural network and chaos,and its structure andlearning algorithm are designed.The multilayer feedforward neural network,diagonal recurrent neural network,and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map.The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks.
Chaotic diagonal recurrent neural network
International Nuclear Information System (INIS)
We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)
Applying artificial neural networks in nuclear power plant diagnostics
International Nuclear Information System (INIS)
Artificial neural networks are very effective tools in solving failure detection problems in complex plants such as nuclear power reactors and their subsidiary equipments, as they can perform parallel realizations of complicated classification processes. In the paper, after a brief historical and methodological introduction, a neural network based failure detection system is presented which has been developed for the use in the PWR units of the Nuclear Power Plant Paks (Hungary). A cellular processor array has been used to realize a back-propagation type neural network which can detect changes in the spectral features of the measured signals through off-line supervised learning processes. (authors)
Assessment of highway slope failure using neural networks
Institute of Scientific and Technical Information of China (English)
Tsung-lin LEE; Hung-ming LIN; Yuh-pin LU
2009-01-01
An artificial intelligence technique of back-propagation neural networks is used to assess the slope failure. On-site slope failure data from the South Cross-Island Highway in southern Taiwan are used to test the performance of the neural network model. The numerical results demonstrate the effectiveness of artificial neural networks in the evaluation of slope failure potential based on five major factors, such as the slope gradient angle, the slope height, the cumulative precipitation, daily rainfall and strength of materials.
Failure behavior identification for a space antenna via neural networks
Sartori, Michael A.; Antsaklis, Panos J.
1992-01-01
By using neural networks, a method for the failure behavior identification of a space antenna model is investigated. The proposed method uses three stages. If a fault is suspected by the first stage of fault detection, a diagnostic test is performed on the antenna. The diagnostic test results are used by the second and third stages to identify which fault occurred and to diagnose the extent of the fault, respectively. The first stage uses a multilayer perceptron, the second stage uses a multilayer perceptron and neural networks trained with the quadratic optimization algorithm, a novel training procedure, and the third stage uses backpropagation trained neural networks.
File access prediction using neural networks.
Patra, Prashanta Kumar; Sahu, Muktikanta; Mohapatra, Subasish; Samantray, Ronak Kumar
2010-06-01
One of the most vexing issues in design of a high-speed computer is the wide gap of access times between the memory and the disk. To solve this problem, static file access predictors have been used. In this paper, we propose dynamic file access predictors using neural networks to significantly improve upon the accuracy, success-per-reference, and effective-success-rate-per-reference by using neural-network-based file access predictor with proper tuning. In particular, we verified that the incorrect prediction has been reduced from 53.11% to 43.63% for the proposed neural network prediction method with a standard configuration than the recent popularity (RP) method. With manual tuning for each trace, we are able to improve upon the misprediction rate and effective-success-rate-per-reference using a standard configuration. Simulations on distributed file system (DFS) traces reveal that exact fit radial basis function (RBF) gives better prediction in high end system whereas multilayer perceptron (MLP) trained with Levenberg-Marquardt (LM) backpropagation outperforms in system having good computational capability. Probabilistic and competitive predictors are the most suitable for work stations having limited resources to deal with and the former predictor is more efficient than the latter for servers having maximum system calls. Finally, we conclude that MLP with LM backpropagation algorithm has better success rate of file prediction than those of simple perceptron, last successor, stable successor, and best k out of m predictors. PMID:20421183
Boundness of a Neural Network Weights Using the Notion of a Limit of a Sequence
Directory of Open Access Journals (Sweden)
Hazem Migdady
2014-05-01
Full Text Available feed forward neural network with backpropagation learning algorithm is considered as a black box learning classifier since there is no certain interpretation or anticipation of the behavior of a neural network weights. The weights of a neural network are considered as the learning tool of the classifier, and the learning task is performed by the repetition modification of those weights. This modification is performed using the delta rule which is mainly used in the gradient descent technique. In this article a proof is provided that helps to understand and explain the behavior of the weights in a feed forward neural network with backpropagation learning algorithm. Also, it illustrates why a feed forward neural network is not always guaranteed to converge in a global minimum. Moreover, the proof shows that the weights in the neural network are upper bounded (i.e. they do not approach infinity.
ÖRKÇÜ, H. Hasan; Mustafa İsa DOĞAN; Örkçü, Mediha
2015-01-01
Backpropagation algorithm is classical technique used in the training of the artificial neural networks. Since this algorithm has many disadvantages, the training of the neural networks has been implemented with various optimization methods. In this paper, a hybrid intelligent model, i.e., hybridGSA, is developed to training artificial neural networks (ANN) and undertaking data classification problems. The hybrid intelligent system aims to exploit the advantages of genetic and simulated annea...
Application of neural networks for sensor validation and plant monitoring
International Nuclear Information System (INIS)
Sensor and process monitoring in power plants requires the estimation of one or more process variables. Neural network paradigms are suitable for establishing general nonlinear relationships among a set of plant variables. Multiple-input/multiple-output autoassociative networks can follow changes in plantwide behavior. The backpropagation (BPN) algorithm has been applied for training multilayer feedforward networks. A new and enhanced BPN algorithm for training neural networks has been developed and implemented in a VAX workstation. Operational data from the Experimental Breeder Reactor II (EBR-II) have been used to study the performance of the BPN algorithm. In this paper several results of application to the EBR-II are presented
Neural networks for sensor validation and plant monitoring
International Nuclear Information System (INIS)
Sensor and process monitoring in power plants require the estimation of one or more process variables. Neural network paradigms are suitable for establishing general nonlinear relationships among a set of plant variables. Multiple-input multiple-output autoassociative networks can follow changes in plant-wide behavior. The backpropagation algorithm has been applied for training feedforward networks. A new and enhanced algorithm for training neural networks (BPN) has been developed and implemented in a VAX workstation. Operational data from the Experimental Breeder Reactor-II (EBR-II) have been used to study the performance of BPN. Several results of application to the EBR-II are presented
Neural network modeling in optimisation of continuous fermentation processes
Energy Technology Data Exchange (ETDEWEB)
Lednicky, P.; Meszaros, A. [Department of Process Control, Slovak University of Technology, Bratislava (Slovakia)
1998-06-01
The capability of self-recurrent neural networks in dynamic modeling of continuous fermentation is investigated in this simulation study. In the past, feedforward neural networks have been successfully used as one-step-ahead predictors. However, in steady-state optimisation of continuous fermentations the neural network model has to be iterated to predict many time steps ahead into the future in order to get steady-state values of the variables involved in objective cost function, and this iteration may result in increasing errors. Therefore, as an alternative to classical feedforward neural network trained by using backpropagation method, self-recurrent multilayer neural net trained by backpropagation through time method was chosen in order to improve accuracy of long-term predictions. Prediction capabilities of the resulting neural network model is tested by implementing this into the Integrated System Optimisation and Parameter Estimation (ISOPE) optimisation algorithm. Maximisation of cellular productivity of the baker`s yeast continuous fermentation was used as the goal of the proposed optimising control problem. The training and prediction results of proposed neural network and performances of resulting optimisation structure are demonstrated. (orig.) With 8 figs., 1 tab., 15 refs.
Neural Network Back-Propagation Algorithm for Sensing Hypergols
Perotti, Jose; Lewis, Mark; Medelius, Pedro; Bastin, Gary
2013-01-01
Fast, continuous detection of a wide range of hazardous substances simultaneously is needed to achieve improved safety for personnel working with hypergolic fuels and oxidizers, as well as other hazardous substances, with a requirement for such detection systems to warn personnel immediately upon the sudden advent of hazardous conditions, with a high probability of detection and a low false alarm rate. The primary purpose of this software is to read the voltage outputs from voltage dividers containing carbon nano - tube sensors as a variable resistance leg, and to recognize quickly when a leak has occurred through recognizing that a generalized pattern change in resistivity of a carbon nanotube sensor has occurred upon exposure to dangerous substances, and, further, to identify quickly just what substance is present through detailed pattern recognition of the shape of the response provided by the carbon nanotube sensor.
Time series prediction using artificial neural network for power stabilization
International Nuclear Information System (INIS)
Time series prediction has been applied to many business and scientific applications. Prominent among them are stock market prediction, weather forecasting, etc. Here, this technique has been applied to forecast plasma torch voltages to stabilize power using a backpropagation, a model of artificial neural network. The Extended-Delta-Bar-Delta algorithm is used to improve the convergence rate of the network and also to avoid local minima. Results from off-line data was quite promising to use in on-line
Handwritten Farsi Character Recognition using Artificial Neural Network
Reza Gharoie Ahangar; Mohammad Farajpoor Ahangar
2009-01-01
Neural Networks are being used for character recognition from last many years but most of the work was confined to English character recognition. Till date, a very little work has been reported for Handwritten Farsi Character recognition. In this paper, we have made an attempt to recognize handwritten Farsi characters by using a multilayer perceptron with one hidden layer. The error backpropagation algorithm has been used to train the MLP network. In addition, an analysis has been carried out...
Neural Networks: Implementations and Applications
Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.
1996-01-01
Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas
Senashova, M. Yu.; Gorban, A. N.; Wunsch II, D. C.
2003-01-01
In this paper we solve the problem: how to determine maximal allowable errors, possible for signals and parameters of each element of a network proceeding from the condition that the vector of output signals of the network should be calculated with given accuracy? "Back-propagation of accuracy" is developed to solve this problem. The calculation of allowable errors for each element of network by back-propagation of accuracy is surprisingly similar to a back-propagation of error, because it is...
Artificial neural network based approach to transmission lines protection
International Nuclear Information System (INIS)
The aim of this paper is to present and accurate fault detection technique for high speed distance protection using artificial neural networks. The feed-forward multi-layer neural network with the use of supervised learning and the common training rule of error back-propagation is chosen for this study. Information available locally at the relay point is passed to a neural network in order for an assessment of the fault location to be made. However in practice there is a large amount of information available, and a feature extraction process is required to reduce the dimensionality of the pattern vectors, whilst retaining important information that distinguishes the fault point. The choice of features is critical to the performance of the neural networks learning and operation. A significant feature in this paper is that an artificial neural network has been designed and tested to enhance the precision of the adaptive capabilities for distance protection
J.Maria Mont Lorenzo
2001-01-01
The aim of this research is the use of the artificial neural networks models, specifically Multilayer Perceptrons trained by the algorithm known as Backpropagation to estimate the free housing prices. This methodology allows, through the training of the backpropagated nets, to estimate the houses prices on the basis of some variables, related to the houses, which are considered relevant (location, age, surface, quality, ...), overcoming the linear restrictions characteristic of the traditiona...
Neural Networks For Electrohydrodynamic Effect Modelling
Directory of Open Access Journals (Sweden)
Wiesław Wajs
2004-01-01
Full Text Available This paper presents currently achieved results concerning methods of electrohydrodynamiceffect used in geophysics simulated with feedforward networks trained with backpropagation algorithm, radial basis function networks and generalized regression networks.
A Global Algorithm for Training Multilayer Neural Networks
Zhao, H; Zhao, Hong; Jin, Tao
2006-01-01
We present a global algorithm for training multilayer neural networks in this Letter. The algorithm is focused on controlling the local fields of neurons induced by the input of samples by random adaptations of the synaptic weights. Unlike the backpropagation algorithm, the networks may have discrete-state weights, and may apply either differentiable or nondifferentiable neural transfer functions. A two-layer network is trained as an example to separate a linearly inseparable set of samples into two categories, and its powerful generalization capacity is emphasized. The extension to more general cases is straightforward.
NEURAL NETWORK FOR THE QUANTUM CORRECTION OF NANOSCALE SOI MOSFETS
Institute of Scientific and Technical Information of China (English)
Li Zunchao; Jiang Yaolin; Zhang Lili
2006-01-01
The quantum effect of carrier distribution in nanoscale SOI MOSFETs is evident and must be taken into consideration in device modeling and simulation. In this paper, a backpropagation neural network was applied to predict the quantum density of carriers from the classical density, and the influence of the network structure on training speed and accuracy was studied. It was concluded that a carefully trained neural network with two hidden layers using the Levenberg-Marquardt learning algorithm could predict the carrier quantum density of SOI MOSFETs in very good agreement with Schrdinger Poisson equations.
Improving learning of neural networks for nuclear power plant transient classification
International Nuclear Information System (INIS)
The backpropagation learning algorithm has proven to be a robust method for training feedforward multilayer neural networks to map the relationships between input/output patterns. However, as with many gradient descent optimization methods, the rate of convergence of the backpropagation algorithm decreases the closer it gets to the solution, and it requires judicious selection of the learning and momentum constants to achieve reasonable convergence and avoid oscillations about the optimum solution. In this paper, the discussion focuses on how the method of conjugate gradients can be combined with the backpropagation algorithm to improve and accelerate learning in neural networks and eliminate the process of selecting parameters. The proposed method was used to train a neural network to classify nuclear power plant transients, and it significantly expedited the learning process. 5 refs., 1 fig
Directory of Open Access Journals (Sweden)
Yadana Thein
2010-11-01
Full Text Available This paper contributes an effective recognition approach for Myanmar Handwritten Characters. In this article, Hybrid approach use ICR and OCR recognition through MICR (Myanmar Intelligent Character Recognition and back-propagation neural network. MICR is one kind of ICR. It composed of statistical/semantic information and final decision is made by voting system. In Hybrid approach, the features of statistical and semantic information of MICR have been used in back-propagation neural network as input nodes. So it needs a few input nodes to use. The back-propagation algorithm has been used to train the feed-forward neural network and adjustment of weights to require the desired output. The purpose of Hybrid approach to achieve the high accuracy rates and very fast recognition rate compare with other recognition systems. The experiments were carried out on 1000 words samples of different writer. Using Hybrid approach, over-all recognition accuracy of 95% was obtained.
Handwritten Farsi Character Recognition using Artificial Neural Network
Ahangar, Reza Gharoie
2009-01-01
Neural Networks are being used for character recognition from last many years but most of the work was confined to English character recognition. Till date, a very little work has been reported for Handwritten Farsi Character recognition. In this paper, we have made an attempt to recognize handwritten Farsi characters by using a multilayer perceptron with one hidden layer. The error backpropagation algorithm has been used to train the MLP network. In addition, an analysis has been carried out to determine the number of hidden nodes to achieve high performance of backpropagation network in the recognition of handwritten Farsi characters. The system has been trained using several different forms of handwriting provided by both male and female participants of different age groups. Finally, this rigorous training results an automatic HCR system using MLP network. In this work, the experiments were carried out on two hundred fifty samples of five writers. The results showed that the MLP networks trained by the err...
NEURAL NETWORKS ARCHITECTURES FOR MODELING AND SIMULATION OF THE ECONOMY SYSTEM DYNAMICS
Nicolae Tudoroiu; Claudiu Chiru; Manuela Grigore
2009-01-01
This research work investigates the possibility to apply several neural network architectures for simulation and prediction of the dynamic behavior of the complex economic processes. Therefore we will explore different neural networks architectures to build several neural models of the complex dynamic economy system. In future work we will use these architectures to be trained by well-known training algorithms, such as Levenberg-Marquardt back-propagation error and Radial Basic Function (RBF)...
DEFF Research Database (Denmark)
Krogh, Anders Stærmose; Riis, Søren Kamaric
1999-01-01
A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...
Neural networks for aircraft control
Linse, Dennis
1990-01-01
Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.
Artificial neural networks in the nuclear engineering (Part 1)
International Nuclear Information System (INIS)
Artificial Neural Networks (ANN) can be defined as 'parallel systems composed of layers of simple processing units highly interconnected and inspired in the human brain.' ANN can be used to solve problems of difficult modeling, when the data are fail or incomplete and in problems of control of high complexity. Several problems related with network training and generalization are to be solved to a safe utilization in nuclear plants systems. This work, divided into two parts, intends to begin a discussion on three ANN concepts: feed-forward neural networks, Self-Organized Maps (SOM), and multi-synaptic neural networks. The discussion will cover control applications, approximation of functions and pattern recognition. A few set of samples are commented. This first part focus on feed-forward neural networks with the back-propagation algorithm. (author)
DEFF Research Database (Denmark)
Hansen, Lars Kai; Salamon, Peter
1990-01-01
We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....
Inversion of surface parameters using fast learning neural networks
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.
Critical Branching Neural Networks
Kello, Christopher T.
2013-01-01
It is now well-established that intrinsic variations in human neural and behavioral activity tend to exhibit scaling laws in their fluctuations and distributions. The meaning of these scaling laws is an ongoing matter of debate between isolable causes versus pervasive causes. A spiking neural network model is presented that self-tunes to critical…
Yorek, Nurettin; Ugulu, Ilker
2015-01-01
In this study, artificial neural networks are suggested as a model that can be "trained" to yield qualitative results out of a huge amount of categorical data. It can be said that this is a new approach applied in educational qualitative data analysis. In this direction, a cascade-forward back-propagation neural network (CFBPN) model was…
Neural Networks for Wordform Recognition
Eineborg, Martin; Gambäck, Björn
1994-01-01
The paper outlines a method for automatic lexical acquisition using three-layered back-propagation networks. Several experiments have been carried out where the performance of different network architectures have been compared to each other on two tasks: overall part-of-speech (noun, adjective or verb) classification and classification by a set of 13 possible output categories. The best results for the simple task were obtained by networks consisting of 204-212 input neurons...
Vibration monitoring with artificial neural networks
International Nuclear Information System (INIS)
Vibration monitoring of components in nuclear power plants has been used for a number of years. This technique involves the analysis of vibration data coming from vital components of the plant to detect features which reflect the operational state of machinery. The analysis leads to the identification of potential failures and their causes, and makes it possible to perform efficient preventive maintenance. Earlydetection is important because it can decrease the probability of catastrophic failures, reduce forced outgage, maximize utilization of available assets, increase the life of the plant, and reduce maintenance costs. This paper documents our work on the design of a vibration monitoring methodology based on neural network technology. This technology provides an attractive complement to traditional vibration analysis because of the potential of neural network to operate in real-time mode and to handle data which may be distorted or noisy. Our efforts have been concentrated on the analysis and classification of vibration signatures collected from operating machinery. Two neural networks algorithms were used in our project: the Recirculation algorithm for data compression and the Backpropagation algorithm to perform the actual classification of the patterns. Although this project is in the early stages of development it indicates that neural networks may provide a viable methodology for monitoring and diagnostics of vibrating components. Our results to date are very encouraging
Neural network application to diesel generator diagnostics
International Nuclear Information System (INIS)
Diagnostic problems typically begin with the observation of some system behavior which is recognized as a deviation from the expected. The fundamental underlying process is one involving pattern matching cf observed symptoms to a set of compiled symptoms belonging to a fault-symptom mapping. Pattern recognition is often relied upon for initial fault detection and diagnosis. Parallel distributed processing (PDP) models employing neural network paradigms are known to be good pattern recognition devices. This paper describes the application of neural network processing techniques to the malfunction diagnosis of subsystems within a typical diesel generator configuration. Neural network models employing backpropagation learning were developed to correctly recognize fault conditions from the input diagnostic symptom patterns pertaining to various engine subsystems. The resulting network models proved to be excellent pattern recognizers for malfunction examples within the training set. The motivation for employing network models in lieu of a rule-based expert system, however, is related to the network's potential for generalizing malfunctions outside of the training set, as in the case of noisy or partial symptom patterns
Indian Stock Market Prediction Using Differential Evolutionary Neural Network Model
Puspanjali Mohapatra; Alok Raj; Tapas Kumar Patra
2012-01-01
This paper presents a scheme using Differential Evolution based Functional Link Artificial Neural Network(FLANN) to predict the Indian Stock Market Indices. The Model uses Back-Propagation (BP) algorithm and Differential Evolution (DE) algorithm respectively for predicting the Stock Price Indices or one day, one week, two weeks and one month in advance.The Indian stock prices i.e. BSE (Bombay Stock Exchange), NSE,INFY etc. with few technical indicators are considered as input for the experime...
Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents
Sher, Gene I.
2011-01-01
Though machine learning has been applied to the foreign exchange market for algorithmic trading for quiet some time now, and neural networks(NN) have been shown to yield positive results, in most modern approaches the NN systems are optimized through traditional methods like the backpropagation algorithm for example, and their input signals are price lists, and lists composed of other technical indicator elements. The aim of this paper is twofold: the presentation and testing of the applicati...
Directory of Open Access Journals (Sweden)
Farahnaz SADOUGHI
2014-03-01
Full Text Available Breast cancer is the most commonly diagnosed cancer and the most common cause of death in women all over the world. Use of computer technology supporting breast cancer diagnosing is now widespread and pervasive across a broad range of medical areas. Early diagnosis of this disease can greatly enhance the chances of long-term survival of breast cancer victims. Artificial Neural Networks (ANN as mainly method play important role in early diagnoses breast cancer. This paper studies Levenberg Marquardet Backpropagation (LMBP neural network and Levenberg Marquardet Backpropagation based Particle Swarm Optimization(LMBP-PSO for the diagnosis of breast cancer. The obtained results show that LMBP and LMBP based PSO system provides higher classification efficiency. But LMBP based PSO needs minimum training and testing time. It helps in developing Medical Decision System (MDS for breast cancer diagnosing. It can also be used as secondary observer in clinical decision making.
Recurrent Neural Network Regularization
Zaremba, Wojciech; Sutskever, Ilya; Vinyals, Oriol
2014-01-01
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks, does not work well with RNNs and LSTMs. In this paper, we show how to correctly apply dropout to LSTMs, and show that it substantially reduces overfitting on a variety of tasks. These tasks include language modeling, speech recognition, image caption generation, and machine translation.
Deep Sequential Neural Network
Denoyer, Ludovic; Gallinari, Patrick
2014-01-01
Neural Networks sequentially build high-level features through their successive layers. We propose here a new neural network model where each layer is associated with a set of candidate mappings. When an input is processed, at each layer, one mapping among these candidates is selected according to a sequential decision process. The resulting model is structured according to a DAG like architecture, so that a path from the root to a leaf node defines a sequence of transformations. Instead of c...
Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorith as a non-destructive damage assessment technique to locate and quantify a damage in Civil Engineering structures is investigated. Since artificial neural networks are proving to be...
Memory-Efficient Backpropagation Through Time
Gruslys, Audrūnas; Munos, Remi; Danihelka, Ivo; Lanctot, Marc; Graves, Alex
2016-01-01
We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of intermediate results and recomputation. The algorithm is capable of tightly fitting within almost any user-set memory budget while finding an optimal execution policy minimizing the computational cost. Computational devices have limited memory capacity and ma...
Lakra, Sachin; T. V. Prasad; G. Ramakrishna
2012-01-01
The paper describes some recent developments in neural networks and discusses the applicability of neural networks in the development of a machine that mimics the human brain. The paper mentions a new architecture, the pulsed neural network that is being considered as the next generation of neural networks. The paper also explores the use of memristors in the development of a brain-like computer called the MoNETA. A new model, multi/infinite dimensional neural networks, are a recent developme...
Neural Networks in Data Mining
Priyanka Gaur
2012-01-01
The application of neural networks in the data mining is very wide. Although neural networks may have complex structure, long training time, and uneasily understandable representation of results, neural networks have high acceptance ability for noisy data and high accuracy and are preferable in data mining. In this paper the data mining based on neural networks is researched in detail, and the key technology and ways to achieve the data mining based on neural networks are also researched.
Neural networks and graph theory
Institute of Scientific and Technical Information of China (English)
许进; 保铮
2002-01-01
The relationships between artificial neural networks and graph theory are considered in detail. The applications of artificial neural networks to many difficult problems of graph theory, especially NP-complete problems, and the applications of graph theory to artificial neural networks are discussed. For example graph theory is used to study the pattern classification problem on the discrete type feedforward neural networks, and the stability analysis of feedback artificial neural networks etc.
Using Neural Networks to Predict the Hardness of Aluminum Alloys
Directory of Open Access Journals (Sweden)
B. Zahran
2015-02-01
Full Text Available Aluminum alloys have gained significant industrial importance being involved in many of the light and heavy industries and especially in aerospace engineering. The mechanical properties of aluminum alloys are defined by a number of principal microstructural features. Conventional mathematical models of these properties are sometimes very complex to be analytically calculated. In this paper, a neural network model is used to predict the correlations between the hardness of aluminum alloys in relation to certain alloying elements. A backpropagation neural network is trained using a thorough dataset. The impact of certain elements is documented and an optimum structure is proposed.
Noise-enhanced convolutional neural networks.
Audhkhasi, Kartik; Osoba, Osonde; Kosko, Bart
2016-06-01
Injecting carefully chosen noise can speed convergence in the backpropagation training of a convolutional neural network (CNN). The Noisy CNN algorithm speeds training on average because the backpropagation algorithm is a special case of the generalized expectation-maximization (EM) algorithm and because such carefully chosen noise always speeds up the EM algorithm on average. The CNN framework gives a practical way to learn and recognize images because backpropagation scales with training data. It has only linear time complexity in the number of training samples. The Noisy CNN algorithm finds a special separating hyperplane in the network's noise space. The hyperplane arises from the likelihood-based positivity condition that noise-boosts the EM algorithm. The hyperplane cuts through a uniform-noise hypercube or Gaussian ball in the noise space depending on the type of noise used. Noise chosen from above the hyperplane speeds training on average. Noise chosen from below slows it on average. The algorithm can inject noise anywhere in the multilayered network. Adding noise to the output neurons reduced the average per-iteration training-set cross entropy by 39% on a standard MNIST image test set of handwritten digits. It also reduced the average per-iteration training-set classification error by 47%. Adding noise to the hidden layers can also reduce these performance measures. The noise benefit is most pronounced for smaller data sets because the largest EM hill-climbing gains tend to occur in the first few iterations. This noise effect can assist random sampling from large data sets because it allows a smaller random sample to give the same or better performance than a noiseless sample gives. PMID:26700535
Egg hatchability prediction by multiple linear regression and artificial neural networks
AC Bolzan; RAF Machado; JCZ Piaia
2008-01-01
An artificial neural network (ANN) was compared with a multiple linear regression statistical method to predict hatchability in an artificial incubation process. A feedforward neural network architecture was applied. Network trainings were made by the backpropagation algorithm based on data obtained from industrial incubations. The ANN model was chosen as it produced data that fit better the experimental data as compared to the multiple linear regression model, which used coefficients determi...
Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks
Kirkegaard, Poul Henning; Rytter, A.
1994-01-01
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorith as a non-destructive damage assessment technique to locate and quantify a damage in Civil Engineering structures is investigated. Since artificial neural networks are proving to be an effective tool for pattern recognition, the basic idea is to train a neural network with simulated values of modal parameters in order to recognize the behaviour of the damaged as well as the un...
Neural Network Course Changing and Track Keeping Controller for a Submarine
Dur Muhammad Pathan; Abdul Fatah Abbassi; Zeeshan Ali Memon
2012-01-01
This paper presents the performance of ANN (Artificial Neural Networks) technique for the development of controller for heading motions of submarine. A MLP (Multi-Layer Preceptron) FFNN (Feed-Forward Neural Network) is used for development of controller. Supervised type of learning is used for training of network by using back-propagation Algorithm. The training is performed by providing a nonlinear sliding mode controller as a supervisor. The development of controller is based on...
Learning behavior and temporary minima of two-layer neural networks
Annema, Anne-Johan; Hoen, Klaas; Wallinga, Hans
1994-01-01
This paper presents a mathematical analysis of the occurrence of temporary minima during training of a single-output, two-layer neural network, with learning according to the back-propagation algorithm. A new vector decomposition method is introduced, which simplifies the mathematical analysis of learning of neural networks considerably. The analysis shows that temporary minima are inherent to multilayer networks learning. A number of numerical results illustrate the analytical conclusions.
Control of a hybrid compensator in a power network by an artificial neural network
Directory of Open Access Journals (Sweden)
I. S. Shaw
1998-07-01
Full Text Available Increased interest in the elimination of distortion in electrical power networks has led to the development of various compensator topologies. The increasing cost of electrical energy necessitates the cost-effective operation of any of these topologies. This paper considers the development of an artificial neural network based controller, trained by means of the backpropagation method, that ensures the cost-effective operation of the hybrid compensator consisting of various converters and filters.
Nuclear fuel, pellet inspection using artificial neural networks
International Nuclear Information System (INIS)
Nuclear fuel must be of high quality before being placed into service in a reactor. Fuel vendors currently use manual inspection for quality control of fabricated nuclear fuel pellets. In order to reduce workers' exposure to radiation and increase the inspection accuracy and speed, the feasibility of automation of fuel pellet inspection using artificial neural networks (ANNs) is studied in this paper. Three kinds of neural network architectures are examined for evaluation of the ANN performance in proper classification of good versus bad pellets. Two supervised neural networks, backpropagation and fuzzy ARTMAP, and one unsupervised neural network called ART2-A are applied. The results indicate that a supervised ANN with adequate training can achieve a high success rate in classification of fuel pellets. (orig.)
Morphological Classification of Galaxies Using Artificial Neural Networks
Ball, N M
2001-01-01
The results of morphological galaxy classifications performed by humans and by automated methods are compared. In particular, a comparison is made between the eyeball classifications of 454 galaxies in the Sloan Digital Sky Survey (SDSS) commissioning data (Shimasaku et al. 2001) with those of supervised artificial neural network programs constructed using the MATLAB Neural Network Toolbox package. Networks in this package have not previously been used for galaxy classification. It is found that simple neural networks are able to improve on the results of linear classifiers, giving correlation coefficients of the order of 0.8 +/- 0.1, compared with those of around 0.7 +/- 0.1 for linear classifiers. The networks are trained using the resilient backpropagation algorithm, which, to the author's knowledge, has not been specifically used in the galaxy classification literature. The galaxy parameters used and the network architecture are both important, and in particular the galaxy concentration index, a measure o...
Sea ice classification using fast learning neural networks
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.
Blur identification by multilayer neural network based on multivalued neurons.
Aizenberg, Igor; Paliy, Dmitriy V; Zurada, Jacek M; Astola, Jaakko T
2008-05-01
A multilayer neural network based on multivalued neurons (MLMVN) is a neural network with a traditional feedforward architecture. At the same time, this network has a number of specific different features. Its backpropagation learning algorithm is derivative-free. The functionality of MLMVN is superior to that of the traditional feedforward neural networks and of a variety kernel-based networks. Its higher flexibility and faster adaptation to the target mapping enables to model complex problems using simpler networks. In this paper, the MLMVN is used to identify both type and parameters of the point spread function, whose precise identification is of crucial importance for the image deblurring. The simulation results show the high efficiency of the proposed approach. It is confirmed that the MLMVN is a powerful tool for solving classification problems, especially multiclass ones. PMID:18467216
On-line learning algorithms for locally recurrent neural networks.
Campolucci, P; Uncini, A; Piazza, F; Rao, B D
1999-01-01
This paper focuses on on-line learning procedures for locally recurrent neural networks with emphasis on multilayer perceptron (MLP) with infinite impulse response (IIR) synapses and its variations which include generalized output and activation feedback multilayer networks (MLN's). We propose a new gradient-based procedure called recursive backpropagation (RBP) whose on-line version, causal recursive backpropagation (CRBP), presents some advantages with respect to the other on-line training methods. The new CRBP algorithm includes as particular cases backpropagation (BP), temporal backpropagation (TBP), backpropagation for sequences (BPS), Back-Tsoi algorithm among others, thereby providing a unifying view on gradient calculation techniques for recurrent networks with local feedback. The only learning method that has been proposed for locally recurrent networks with no architectural restriction is the one by Back and Tsoi. The proposed algorithm has better stability and higher speed of convergence with respect to the Back-Tsoi algorithm, which is supported by the theoretical development and confirmed by simulations. The computational complexity of the CRBP is comparable with that of the Back-Tsoi algorithm, e.g., less that a factor of 1.5 for usual architectures and parameter settings. The superior performance of the new algorithm, however, easily justifies this small increase in computational burden. In addition, the general paradigms of truncated BPTT and RTRL are applied to networks with local feedback and compared with the new CRBP method. The simulations show that CRBP exhibits similar performances and the detailed analysis of complexity reveals that CRBP is much simpler and easier to implement, e.g., CRBP is local in space and in time while RTRL is not local in space. PMID:18252525
Hybrid Neural Network Architecture for On-Line Learning
Chen, Yuhua; Wang, Lei
2008-01-01
Approaches to machine intelligence based on brain models have stressed the use of neural networks for generalization. Here we propose the use of a hybrid neural network architecture that uses two kind of neural networks simultaneously: (i) a surface learning agent that quickly adapt to new modes of operation; and, (ii) a deep learning agent that is very accurate within a specific regime of operation. The two networks of the hybrid architecture perform complementary functions that improve the overall performance. The performance of the hybrid architecture has been compared with that of back-propagation perceptrons and the CC and FC networks for chaotic time-series prediction, the CATS benchmark test, and smooth function approximation. It has been shown that the hybrid architecture provides a superior performance based on the RMS error criterion.
Camera characterization using back-propagation artificial neutral network based on Munsell system
Liu, Ye; Yu, Hongfei; Shi, Junsheng
2008-02-01
The camera output RGB signals do not directly corresponded to the tristimulus values based on the CIE standard colorimetric observer, i.e., it is a device-independent color space. For achieving accurate color information, we need to do color characterization, which can be used to derive a transformation between camera RGB values and CIE XYZ values. In this paper we set up a Back-Propagation (BP) artificial neutral network to realize the mapping from camera RGB to CIE XYZ. We used the Munsell Book of Color with total number 1267 as color samples. Each patch of the Munsell Book of Color was recorded by camera, and the RGB values could be obtained. The Munsell Book of Color were taken in a light booth and the surround was kept dark. The viewing/illuminating geometry was 0/45 using D 65 illuminate. The lighting illuminating the reference target needs to be as uniform as possible. The BP network was a 5-layer one and (3-10-10-10-3), which was selected through our experiments. 1000 training samples were selected randomly from the 1267 samples, and the rest 267 samples were as the testing samples. Experimental results show that the mean color difference between the reproduced colors and target colors is 0.5 CIELAB color-difference unit, which was smaller than the biggest acceptable color difference 2 CIELAB color-difference unit. The results satisfy some applications for the more accurate color measurements, such as medical diagnostics, cosmetics production, the color reappearance of different media, etc.
Spackman, K. A.
1991-01-01
This paper presents maximum likelihood back-propagation (ML-BP), an approach to training neural networks. The widely reported original approach uses least squares back-propagation (LS-BP), minimizing the sum of squared errors (SSE). Unfortunately, least squares estimation does not give a maximum likelihood (ML) estimate of the weights in the network. Logistic regression, on the other hand, gives ML estimates for single layer linear models only. This report describes how to obtain ML estimates...
Hyperbolic Hopfield neural networks.
Kobayashi, M
2013-02-01
In recent years, several neural networks using Clifford algebra have been studied. Clifford algebra is also called geometric algebra. Complex-valued Hopfield neural networks (CHNNs) are the most popular neural networks using Clifford algebra. The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs. Hyperbolic algebra is a Clifford algebra based on Lorentzian geometry. In this brief, a hyperbolic neuron is defined in a manner analogous to a phasor neuron, which is a typical complex-valued neuron model. HHNNs share common concepts with CHNNs, such as the angle and energy. However, HHNNs and CHNNs are different in several aspects. The states of hyperbolic neurons do not form a circle, and, therefore, the start and end states are not identical. In the quantized version, unlike complex-valued neurons, hyperbolic neurons have an infinite number of states. PMID:24808287
GENETIC ALGORITHM AND NEURAL NETWORK FOR OPTICAL CHARACTER RECOGNITION
Directory of Open Access Journals (Sweden)
Hendy Yeremia
2013-01-01
Full Text Available Computer system has been able to recognize writing as human brain does. The method mostly used for character recognition is the backpropagation network. Backpropagation network has been known for its accuracy because it allows itself to learn and improving itself thus it can achieve higher accuracy. On the other hand, backpropagation was less to be used because of its time length needed to train the network to achieve the best result possible. In this study, backpropagation network algorithm is combined with genetic algorithm to achieve both accuracy and training swiftness for recognizing alphabets. Genetic algorithm is used to define the best initial values for the networkâs architecture and synapsesâ weight thus within a shorter period of time, the network could achieve the best accuracy. The optimized backpropagation network has better accuracy and less training time than the standard backpropagation network. The accuracy in recognizing character differ by 10, 77%, with a success rate of 90, 77% for the optimized backpropagation and 80% accuracy for the standard backpropagation network. The training time needed for backpropagation learning phase improved significantly from 03 h, 14 min and 40 sec, a standard backpropagation training time, to 02 h 18 min and 1 sec for the optimized backpropagation network.
The Effect of Network Parameters on Pi-Sigma Neural Network for Temperature Forecasting
Husaini, Noor Aida; Ghazali, Rozaida; Nawi, Nazri Mohd; Ismail, Lokman Hakim
In this paper, we present the effect of network parameters to forecast temperature of a suburban area in Batu Pahat, Johor. The common ways of predicting the temperature using Neural Network has been applied for most meteorological parameters. However, researchers frequently neglected the network parameters which might affect the Neural Network's performance. Therefore, this study tends to explore the effect of network parameters by using Pi Sigma Neural Network (PSNN) with backpropagation algorithm. The network's performance is evaluated using the historical dataset of temperature in Batu Pahat for one step-ahead and benchmarked against Multilayer Perceptron (MLP) for comparison. We found out that, network parameters have significantly affected the performance of PSNN for temperature forecasting. Towards the end of this paper, we concluded the best forecasting model to predict the temperature based on the comparison of our study.
Multi-agent reinforcement learning using modular neural network Q-learning algorithms
Institute of Scientific and Technical Information of China (English)
YANG Yin-xian; FANG Kai
2005-01-01
Reinforcement learning is an excellent approach which is used in artificial intelligence,automatic control, etc. However, ordinary reinforcement learning algorithm, such as Q-learning with lookup table cannot cope with extremely complex and dynamic environment due to the huge state space. To reduce the state space, modular neural network Q-learning algorithm is proposed, which combines Q-learning algorithm with neural network and module method. Forward feedback neural network, Elman neural network and radius-basis neural network are separately employed to construct such algorithm. It is revealed that Elman neural network Q-learning algorithm has the best performance under the condition that the same neural network training method, i.e. gradient descent error back-propagation algorithm is applied.
Rule Extraction:Using Neural Networks or for Neural Networks?
Institute of Scientific and Technical Information of China (English)
Zhi-Hua Zhou
2004-01-01
In the research of rule extraction from neural networks, fidelity describes how well the rules mimic the behavior of a neural network while accuracy describes how well the rules can be generalized. This paper identifies the fidelity-accuracy dilemma. It argues to distinguish rule extraction using neural networks and rule extraction for neural networks according to their different goals, where fidelity and accuracy should be excluded from the rule quality evaluation framework, respectively.
An optimization methodology for neural network weights and architectures.
Ludermir, Teresa B; Yamazaki, Akio; Zanchettin, Cleber
2006-11-01
This paper introduces a methodology for neural network global optimization. The aim is the simultaneous optimization of multilayer perceptron (MLP) network weights and architectures, in order to generate topologies with few connections and high classification performance for any data sets. The approach combines the advantages of simulated annealing, tabu search and the backpropagation training algorithm in order to generate an automatic process for producing networks with high classification performance and low complexity. Experimental results obtained with four classification problems and one prediction problem has shown to be better than those obtained by the most commonly used optimization techniques. PMID:17131660
A study of diagnosis of loose part monitoring system using neural network
International Nuclear Information System (INIS)
It is known that loose parts in the reactor coolant systems (RCS) cause serious damage into the systems. We applied the neural network algorithm to LPMS in order to estimate the mass of loose parts. We trained the impact test data of YGN3 using the backpropagation method. The input parameter for training is rising time, half period, maximum amplitude. The result showed that the neural network would be applied to LPMS
Artificial Neural Network Analysis for Prediction of Headache Prognosis in Elderly Patients
Taşdelen, Bahar; HELVACI, Sema; KALEAĞASI, Hakan; Özge, Aynur
2009-01-01
Aim: To investigate the ability of neural networks to detect and classify the complete improvement of headache in elderly patients during the follow- up period. Materials and Methods: The multilayer perceptron (MLP), which is the most common neural network, was used to predict prognosis of headache in elderly patients. The data set was divided into training and test sets, and back-propagation algorithm was used as the learning algorithm. The accuracies of the models to predict completely imp...
Indirect model for roughness in rough honing processes based on artificial neural networks
Sivatte Adroer, Mauricio; Llanas Parra, Francesc Xavier; Buj Corral, Irene; Vivancos Calvet, Joan
2016-01-01
In the present paper an indirect model based on neural networks is presented for modelling the rough honing process. It allows obtaining values to be set for different process variables (linear speed, tangential speed, pressure of abrasive stones, grain size of abrasive and density of abrasive) as a function of required average roughness Ra. A multilayer perceptron (feedforward) with a backpropagation (BP) training system was used for defining neural networks. Several configurations were test...
Spreeuwers, Luuk
1995-01-01
The least squares criterion, as used by the backpropagation learning rule in multi-layer feed forward neural networks, does not always yield a solution that is in accordance with the desired behaviour of the neural network. This is for example the case when differentiation between different types of errors is required and the costs of the error types must be taken into account. In this paper the application of other error measures, specifically matched to the application, is investigated. The...
The Buckling Analysis of Axially Loaded Columns with Artificial Neural Networks
Ülker, Mehmet; CİVALEK, Ömer
2002-01-01
The determination of effective design values in structural analysis is important.Axially loaded columns are designed according to the their buckling load capacity. In this study, a multi-layer artificial neural network is trained to give critical load for axially loaded columns and various support conditions. Back-propagation training algorithms are used considering the circular, square, rectangular, and I cross-sections. The artificial neural network, with is trained for circular and rec...
Artificial Neural Network Model for Predicting Compressive
Directory of Open Access Journals (Sweden)
Salim T. Yousif
2013-05-01
Full Text Available Compressive strength of concrete is a commonly used criterion in evaluating concrete. Although testing of the compressive strength of concrete specimens is done routinely, it is performed on the 28th day after concrete placement. Therefore, strength estimation of concrete at early time is highly desirable. This study presents the effort in applying neural network-based system identification techniques to predict the compressive strength of concrete based on concrete mix proportions, maximum aggregate size (MAS, and slump of fresh concrete. Back-propagation neural networks model is successively developed, trained, and tested using actual data sets of concrete mix proportions gathered from literature. The test of the model by un-used data within the range of input parameters shows that the maximum absolute error for model is about 20% and 88% of the output results has absolute errors less than 10%. The parametric study shows that water/cement ratio (w/c is the most significant factor affecting the output of the model. The results showed that neural networks has strong potential as a feasible tool for predicting compressive strength of concrete.
Fabric Quality Optimization by Using Desirability Function and Neural Networks
Directory of Open Access Journals (Sweden)
Hajer Souid
2012-01-01
Full Text Available The present paper presents a new method to estimate objective reflection of Denim fabric quality by using desirability function and neural networks. The global fabric quality was defined through one index belonging to the closed interval [0, 1]. For this reason, we have created a first algorithm that is modified when the definition of fabric quality is changed. This prediction would allow fabric producer to estimate customer’s quality satisfaction level. The present approach has conferred a good evaluation and prediction of the all-encompassing denim fabric quality. In the second stage of the study, we developed a model to predict global fabric quality from fiber, yarn, weaving parameters and finishing characteristics by using neural networks. The neural network model is accomplished by using a second algorithm based on back-propagation concept. The results have shown that the neuronal networks could predict global fabric quality of the untrained fabrics with better precision
Short Term Load Forecast Using Wavelet Neural Network
Institute of Scientific and Technical Information of China (English)
Gui Min; Rong Fei; Luo An
2005-01-01
This paper presents a wavelet neural network (WNN) model combining wavelet transform and artificial neural networks for short term load forecast (STLF). Both historical load and temperature data having important impacts on load level were used in the proposed forecasting model. The model used the three-layer feed forward network trained by the error back-propagation algorithm. To enhance the forecasting accuracy by neural networks, wavelet multi-resolution analysis method was introduced to pre-process these data and reconstruct the predicted output. The proposed model has been evaluated with actual data of electricity load and temperature of Hunan Province. The simulation results show that the model is capable of providing a reasonable forecasting accuracy in STLF.
Using Artificial Neural Networks for ECG Signals Denoising
Directory of Open Access Journals (Sweden)
Zoltán Germán-Salló
2010-12-01
Full Text Available The authors have investigated some potential applications of artificial neural networks in electrocardiografic (ECG signal prediction. For this, the authors used an adaptive multilayer perceptron structure to predict the signal. The proposed procedure uses an artificial neural network based learning structure to estimate the (n+1th sample from n previous samples To train and adjust the network weights, the backpropagation (BP algorithm was used. In this paper, prediction of ECG signals (as time series using multi-layer feedforward neural networks will be described. The results are evaluated through approximation error which is defined as the difference between the predicted and the original signal.The prediction procedure is carried out (simulated in MATLAB environment, using signals from MIT-BIH arrhythmia database. Preliminary results are encouraging enough to extend the proposed method for other types of data signals.
Extraction of Symbolic Rules from Artificial Neural Networks
Kamruzzaman, S M
2010-01-01
Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained ANNs for the users to gain a better understanding of how the networks solve the problems. A new rule extraction algorithm, called rule extraction from artificial neural networks (REANN) is proposed and implemented to extract symbolic rules from ANNs. A standard three-layer feedforward ANN is the basis of the algorithm. A four-phase training algorithm is proposed for backpropagation learning. Explicitness of the extracted rules is supported by comparing them to the symbolic rules generated by other methods. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and predictive accuracy. Extensive experimental studies on several benchmarks classification ...
Introduction to Artificial Neural Networks
DEFF Research Database (Denmark)
Larsen, Jan
1999-01-01
The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....
Artificial neural network modelling
Samarasinghe, Sandhya
2016-01-01
This book covers theoretical aspects as well as recent innovative applications of Artificial Neural networks (ANNs) in natural, environmental, biological, social, industrial and automated systems. It presents recent results of ANNs in modelling small, large and complex systems under three categories, namely, 1) Networks, Structure Optimisation, Robustness and Stochasticity 2) Advances in Modelling Biological and Environmental Systems and 3) Advances in Modelling Social and Economic Systems. The book aims at serving undergraduates, postgraduates and researchers in ANN computational modelling. .
Modeling Average Daily Traffic Volume using Neural Network-Wavelet Hybrid Method
Directory of Open Access Journals (Sweden)
Shahin Shabani
Full Text Available Forecasting traffic volume accurately and in a timely manner plays an important role to providing real-time traffic information, reducing congestion in pathways, and improving traffic safety. A combination of multi-layer back-propagation neural networks ( ...
The transport of sediment and nutrients from land application areas is an environmental concern. New methods are needed for estimating soil and nutrient concentrations of runoff from cropland areas on which manure is applied. Artificial Neural Networks (ANN) trained with a Backpropagation (BP) algor...
Neural Networks and Micromechanics
Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.
The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.
Generalized Adaptive Artificial Neural Networks
Tawel, Raoul
1993-01-01
Mathematical model of supervised learning by artificial neural network provides for simultaneous adjustments of both temperatures of neurons and synaptic weights, and includes feedback as well as feedforward synaptic connections. Extension of mathematical model described in "Adaptive Neurons For Artificial Neural Networks" (NPO-17803). Dynamics of neural network represented in new model by less-restrictive continuous formalism.
Energy Technology Data Exchange (ETDEWEB)
Nose Filho, Kenji; Araujo, Klayton A.M.; Maeda, Jorge L.Y.; Lotufo, Anna Diva P. [Universidade Estadual Paulista Julio de Mesquita Filho (UNESP), Ilha Solteira, SP (Brazil)], Emails: kenjinose@yahoo.com.br, klayton_ama@hotmail.com, jorge-maeda@hotmail.com, annadiva@dee.feis.unesp.br
2009-07-01
This paper presents a development and implementation of a program to electrical load forecasting with data from a Brazilian electrical company, using four different architectures of neural networks of the MATLAB toolboxes: multilayer backpropagation gradient descendent with momentum, multilayer backpropagation Levenberg-Marquardt, adaptive network based fuzzy inference system and general regression neural network. The program presented a satisfactory performance, guaranteeing very good results. (author)
Diagnosis method utilizing neural networks
International Nuclear Information System (INIS)
Studies have been made on the technique of neural networks, which will be used to identify a cause of a small anomalous state in the reactor coolant system of the ATR (Advance Thermal Reactor). Three phases of analyses were carried out in this study. First, simulation for 100 seconds was made to determine how the plant parameters respond after the occurence of a transient decrease in reactivity, flow rate and temperature of feed water and increase in the steam flow rate and steam pressure, which would produce a decrease of water level in a steam drum of the ATR. Next, the simulation data was analysed utilizing an autoregressive model. From this analysis, a total of 36 coherency functions up to 0.5 Hz in each transient were computed among nine important and detectable plant parameters: neutron flux, flow rate of coolant, steam or feed water, water level in the steam drum, pressure and opening area of control valve in a steam pipe, feed water temperature and electrical power. Last, learning of neural networks composed of 96 input, 4-9 hidden and 5 output layer units was done by use of the generalized delta rule, namely a back-propagation algorithm. These convergent computations were continued as far as the difference between the desired outputs, 1 for direct cause or 0 for four other ones and actual outputs reached less than 10%. (1) Coherency functions were not governed by decreasing rate of reactivity in the range of 0.41x10-2dollar/s to 1.62x10-2dollar /s or by decreasing depth of the feed water temperature in the range of 3 deg C to 10 deg C or by a change of 10% or less in the three other causes. Change in coherency functions only depended on the type of cause. (2) The direct cause from the other four ones could be discriminated with 0.94+-0.01 of output level. A maximum of 0.06 output height was found among the other four causes. (3) Calculation load which is represented as products of learning times and numbers of the hidden units did not depend on the numbers
Efficiently modeling neural networks on massively parallel computers
Farber, Robert M.
1993-01-01
Neural networks are a very useful tool for analyzing and modeling complex real world systems. Applying neural network simulations to real world problems generally involves large amounts of data and massive amounts of computation. To efficiently handle the computational requirements of large problems, we have implemented at Los Alamos a highly efficient neural network compiler for serial computers, vector computers, vector parallel computers, and fine grain SIMD computers such as the CM-2 connection machine. This paper describes the mapping used by the compiler to implement feed-forward backpropagation neural networks for a SIMD (Single Instruction Multiple Data) architecture parallel computer. Thinking Machines Corporation has benchmarked our code at 1.3 billion interconnects per second (approximately 3 gigaflops) on a 64,000 processor CM-2 connection machine (Singer 1990). This mapping is applicable to other SIMD computers and can be implemented on MIMD computers such as the CM-5 connection machine. Our mapping has virtually no communications overhead with the exception of the communications required for a global summation across the processors (which has a sub-linear runtime growth on the order of O(log(number of processors)). We can efficiently model very large neural networks which have many neurons and interconnects and our mapping can extend to arbitrarily large networks (within memory limitations) by merging the memory space of separate processors with fast adjacent processor interprocessor communications. This paper will consider the simulation of only feed forward neural network although this method is extendable to recurrent networks.
A classifier neural network for rotordynamic systems
Ganesan, R.; Jionghua, Jin; Sankar, T. S.
1995-07-01
A feedforward backpropagation neural network is formed to identify the stability characteristic of a high speed rotordynamic system. The principal focus resides in accounting for the instability due to the bearing clearance effects. The abnormal operating condition of 'normal-loose' Coulomb rub, that arises in units supported by hydrodynamic bearings or rolling element bearings, is analysed in detail. The multiple-parameter stability problem is formulated and converted to a set of three-parameter algebraic inequality equations. These three parameters map the wider range of physical parameters of commonly-used rotordynamic systems into a narrow closed region, that is used in the supervised learning of the neural network. A binary-type state of the system is expressed through these inequalities that are deduced from the analytical simulation of the rotor system. Both the hidden layer as well as functional-link networks are formed and the superiority of the functional-link network is established. Considering the real time interpretation and control of the rotordynamic system, the network reliability and the learning time are used as the evaluation criteria to assess the superiority of the functional-link network. This functional-link network is further trained using the parameter values of selected rotor systems, and the classifier network is formed. The success rate of stability status identification is obtained to assess the potentials of this classifier network. The classifier network is shown that it can also be used, for control purposes, as an 'advisory' system that suggests the optimum way of parameter adjustment.
Application of neural networks to seismic active control
International Nuclear Information System (INIS)
An exploratory study on seismic active control using an artificial neural network (ANN) is presented in which a singledegree-of-freedom (SDF) structural system is controlled by a trained neural network. A feed-forward neural network and the backpropagation training method are used in the study. In backpropagation training, the learning rate is determined by ensuring the decrease of the error function at each training cycle. The training patterns for the neural net are generated randomly. Then, the trained ANN is used to compute the control force according to the control algorithm. The control strategy proposed herein is to apply the control force at every time step to destroy the build-up of the system response. The ground motions considered in the simulations are the N21E and N69W components of the Lake Hughes No. 12 record that occurred in the San Fernando Valley in California on February 9, 1971. Significant reduction of the structural response by one order of magnitude is observed. Also, it is shown that the proposed control strategy has the ability to reduce the peak that occurs during the first few cycles of the time history. These promising results assert the potential of applying ANNs to active structural control under seismic loads
Artificial neural networks in the nuclear engineering (Part 2)
International Nuclear Information System (INIS)
The field of Artificial Neural Networks (ANN), one of the branches of Artificial Intelligence has been waking up a lot of interest in the Nuclear Engineering (NE). ANN can be used to solve problems of difficult modeling, when the data are fail or incomplete and in high complexity problems of control. The first part of this work began a discussion with feed-forward neural networks in back-propagation. In this part of the work, the Multi-synaptic neural networks is applied to control problems. Also, the self-organized maps is presented in a typical pattern classification problem: transients classification. The main purpose of the work is to show that ANN can be successfully used in NE if a carefully choice of its type is done: the application sets this choice. (author)
Structural Damage Detection Using Randomized Trained Neural Networks
Haryanto, Ismoyo; Budiyono, Agus
2008-01-01
A computationally method on damage detection problems in structures was conducted using neural networks. The problem that is considered in this works consists of estimating the existence, location and extent of stiffness reduction in structure which is indicated by the changes of the structural static parameters such as deflection and strain. The neural network was trained to recognize the behaviour of static parameter of the undamaged structure as well as of the structure with various possible damage extent and location which were modelled as random states. The proposed techniques were applied to detect damage in a simply supported beam. The structure was analyzed using finite-element-method (FEM) and the damage identification was conducted by a back-propagation neural network using the change of the structural strain and displacement. The results showed that using proposed method the strain is more efficient for identification of damage than the displacement.
The application of neural networks to the SSME startup transient
Meyer, Claudia M.; Maul, William A.
1991-01-01
Feedforward neural networks were used to model three parameters during the Space Shuttle Main Engine startup transient. The three parameters were the main combustion chamber pressure, a controlled parameter, the high pressure oxidizer turbine discharge temperature, a redlined parameter, and the high pressure fuel pump discharge pressure, a failure-indicating performance parameter. Network inputs consisted of time windows of data from engine measurements that correlated highly to the modeled parameter. A standard backpropagation algorithm was used to train the feedforward networks on two nominal firings. Each trained network was validated with four additional nominal firings. For all three parameters, the neural networks were able to accurately predict the data in the validation sets as well as the training set.
Synthesis of recurrent neural networks for dynamical system simulation.
Trischler, Adam P; D'Eleuterio, Gabriele M T
2016-08-01
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector-field representation of a given dynamical system using backpropagation, then recast it as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time. PMID:27182811
Intelligent Handwritten Digit Recognition using Artificial Neural Network
Directory of Open Access Journals (Sweden)
Saeed AL-Mansoori
2015-05-01
Full Text Available The aim of this paper is to implement a Multilayer Perceptron (MLP Neural Network to recognize and predict handwritten digits from 0 to 9. A dataset of 5000 samples were obtained from MNIST. The dataset was trained using gradient descent back-propagation algorithm and further tested using the feed-forward algorithm. The system performance is observed by varying the number of hidden units and the number of iterations. The performance was thereafter compared to obtain the network with the optimal parameters. The proposed system predicts the handwritten digits with an overall accuracy of 99.32%.
Backpropagation and ordered derivatives in the time scales calculus.
Seiffertt, John; Wunsch, Donald C
2010-08-01
Backpropagation is the most widely used neural network learning technique. It is based on the mathematical notion of an ordered derivative. In this paper, we present a formulation of ordered derivatives and the backpropagation training algorithm using the important emerging area of mathematics known as the time scales calculus. This calculus, with its potential for application to a wide variety of inter-disciplinary problems, is becoming a key area of mathematics. It is capable of unifying continuous and discrete analysis within one coherent theoretical framework. Using this calculus, we present here a generalization of backpropagation which is appropriate for cases beyond the specifically continuous or discrete. We develop a new multivariate chain rule of this calculus, define ordered derivatives on time scales, prove a key theorem about them, and derive the backpropagation weight update equations for a feedforward multilayer neural network architecture. By drawing together the time scales calculus and the area of neural network learning, we present the first connection of two major fields of research. PMID:20615808
Neural networks for control of nuclear reactors systems
International Nuclear Information System (INIS)
A new architecture of artificial neural networks was developed with the development of new control systems for nuclear facilities and robotics. The new concepts introduced with this architecture were based in the design of task dedicated networks, in the use of multiple synaptic contacts with new transfer functions, and in the use of synaptic plasticity processes similar to that of biological organisms. These concepts take advantage of the evolutionary aspects of biological systems in their architecture, signal transmission, and memory and learning processes, given rise to a generalization capacity not obtained with classical feed-forward (F-F) neural networks. The new concepts were applied to the control of a planar two-link robotic manipulator and to the control of a natural circulation water loop. Its efficiency and generalization capacity were compared with a classic neural network in F-F, trained with the back propagation algorithm. The excellent performance obtained, mainly in the manipulator's problem, that characterizes a system of dynamic more complex, demonstrated that the use of the new task specialized network, produces much better results than the results obtained with use of generic F-F networks. The training task in the new proposed neural network was 150 times faster than the F-F neural network training with back-propagation. The results showed that the positioning errors with the new model were up to 60 times smaller than the errors found with the F-F network. (author)
Directory of Open Access Journals (Sweden)
Kapil Nahar
2012-12-01
Full Text Available An artificial neural network is an information-processing paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons working in unison to solve specific problems. Ann’s, like people, learn by example.
Implementing Neural Networks Efficiently
Collobert, Ronan; Kavukcuoglu, Koray; Farabet, Clément; Montavon, Grégoire; Orr, Geneviève; Müller, K.-R.
2012-01-01
Neural networks and machine learning algorithms in general require a flexible environment where new algorithm prototypes and experiments can be set up as quickly as possible with best possible computational performance. To that end, we provide a new framework called Torch7, that is especially suited to achieve both of these competing goals. Torch7 is a versatile numeric computing framework and machine learning library that extends a very lightweight and powerful programming language Lua. Its ...
Neural networks for triggering
Energy Technology Data Exchange (ETDEWEB)
Denby, B. (Fermi National Accelerator Lab., Batavia, IL (USA)); Campbell, M. (Michigan Univ., Ann Arbor, MI (USA)); Bedeschi, F. (Istituto Nazionale di Fisica Nucleare, Pisa (Italy)); Chriss, N.; Bowers, C. (Chicago Univ., IL (USA)); Nesti, F. (Scuola Normale Superiore, Pisa (Italy))
1990-01-01
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab.
Neural networks for triggering
International Nuclear Information System (INIS)
Two types of neural network beauty trigger architectures, based on identification of electrons in jets and recognition of secondary vertices, have been simulated in the environment of the Fermilab CDF experiment. The efficiencies for B's and rejection of background obtained are encouraging. If hardware tests are successful, the electron identification architecture will be tested in the 1991 run of CDF. 10 refs., 5 figs., 1 tab
Prediction of the Electric Energy System State with the Help of Artificial Neural Networks
Czech Academy of Sciences Publication Activity Database
Vítková, G.; Jelínek, J.; Húsek, Dušan; Snášel, Václav
Anheim : ACTA press, 2006 - (Anderson, G.), s. 54-58 ISBN 0-88986-614-7. [IASTED International Conference on Power, Energy and Applications. Gaborone (BW), 11.09.2006-13.09.2006] R&D Projects: GA AV ČR 1ET100300414 Institutional research plan: CEZ:AV0Z10300504 Keywords : electricity distribution system * simulation * artificial intelligence * neural networks * backpropagation network * Kohonen network * ART2 Subject RIV: BB - Applied Statistics, Operational Research
Recurrent networks for wave forecasting
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Prabaharan, N.
, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper presents an application of the Artificial Neural Network, namely Backpropagation Recurrent Neural Network (BRNN) with rprop update algorithm for wave forecasting...
Umut Okkan
2011-01-01
Recently, Artificial Neural Networks (ANN), which is mathematical modelingtools inspired by the properties of the biological neural system, has been typically used inthe studies of hydrological time series modeling. These modeling studies generally includethe standart feed forward backpropagation (FFBP) algorithms such as gradient-descent,gradient-descent with momentum rate and, conjugate gradient etc. As the standart FFBPalgorithms have some disadvantages relating to the time requirement and...
Sensitivity analysis by neural networks applied to power systems transient stability
Energy Technology Data Exchange (ETDEWEB)
Lotufo, Anna Diva P.; Lopes, Mara Lucia M.; Minussi, Carlos R. [Departamento de Engenharia Eletrica, UNESP, Campus de Ilha Solteira, Av. Brasil, 56, 15385-000 Ilha Solteira, SP (Brazil)
2007-05-15
This work presents a procedure for transient stability analysis and preventive control of electric power systems, which is formulated by a multilayer feedforward neural network. The neural network training is realized by using the back-propagation algorithm with fuzzy controller and adaptation of the inclination and translation parameters of the nonlinear function. These procedures provide a faster convergence and more precise results, if compared to the traditional back-propagation algorithm. The adaptation of the training rate is effectuated by using the information of the global error and global error variation. After finishing the training, the neural network is capable of estimating the security margin and the sensitivity analysis. Considering this information, it is possible to develop a method for the realization of the security correction (preventive control) for levels considered appropriate to the system, based on generation reallocation and load shedding. An application for a multimachine power system is presented to illustrate the proposed methodology. (author)
Resource constrained design of artificial neural networks using comparator neural network
Wah, Benjamin W.; Karnik, Tanay S.
1992-01-01
We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.
International Nuclear Information System (INIS)
Cast austenitic stainless steel is used for several components, such as primary coolant piping, elbow, pump casing and valve bodies in light water reactors. These components are subject to thermal aging at the reactor operating temperature. Thermal aging results in spinodal decomposition of the delta-ferrite leading to increased strength and decreased toughness. This study shows that ferrite content can be predicted by use of the artificial neural network. The neural network has trained learning data of chemical components and ferrite contents using backpropagation learning process. The predicted results of the ferrite content using trained neural network are in good agreement with experimental ones
A Worsted Yarn Virtual Production System Based on BP Neural Network
Institute of Scientific and Technical Information of China (English)
董奎勇; 于伟东
2004-01-01
Back-Propagation (BP) neural network and its modified algorithm are introduced. Two series of BP neural network models have been established to predict yarn properties and to deduce wool fiber qualities. The results from these two series of models have been compared with the measured values respectively, proving that the accuracy in both the prediction model and the deduction model is high. The experimental results and the corresponding analysis show that the BP neural network is an efficient technique for the quality prediction and has wide prospect in the application of worsted yarn production system.
A SIMULATION OF THE PENICILLIN G PRODUCTION BIOPROCESS APPLYING NEURAL NETWORKS
Directory of Open Access Journals (Sweden)
A.J.G. da Cruz
1997-12-01
Full Text Available The production of penicillin G by Penicillium chrysogenum IFO 8644 was simulated employing a feedforward neural network with three layers. The neural network training procedure used an algorithm combining two procedures: random search and backpropagation. The results of this approach were very promising, and it was observed that the neural network was able to accurately describe the nonlinear behavior of the process. Besides, the results showed that this technique can be successfully applied to control process algorithms due to its long processing time and its flexibility in the incorporation of new data
Directory of Open Access Journals (Sweden)
Eric Sakk
2013-01-01
Full Text Available We revisit the protein secondary structure prediction problem using linear and backpropagation neural network architectures commonly applied in the literature. In this context, neural network mappings are constructed between protein training set sequences and their assigned structure classes in order to analyze the class membership of test data and associated measures of significance. We present numerical results demonstrating that classifier performance measures can vary significantly depending upon the classifier architecture and the structure class encoding technique. Furthermore, an analytic formulation is introduced in order to substantiate the observed numerical data. Finally, we analyze and discuss the ability of the neural network to accurately model fundamental attributes of protein secondary structure.
Parameter incremental learning algorithm for neural networks.
Wan, Sheng; Banta, Larry E
2006-11-01
In this paper, a novel stochastic (or online) training algorithm for neural networks, named parameter incremental learning (PIL) algorithm, is proposed and developed. The main idea of the PIL strategy is that the learning algorithm should not only adapt to the newly presented input-output training pattern by adjusting parameters, but also preserve the prior results. A general PIL algorithm for feedforward neural networks is accordingly presented as the first-order approximate solution to an optimization problem, where the performance index is the combination of proper measures of preservation and adaptation. The PIL algorithms for the multilayer perceptron (MLP) are subsequently derived. Numerical studies show that for all the three benchmark problems used in this paper the PIL algorithm for MLP is measurably superior to the standard online backpropagation (BP) algorithm and the stochastic diagonal Levenberg-Marquardt (SDLM) algorithm in terms of the convergence speed and accuracy. Other appealing features of the PIL algorithm are that it is computationally as simple as the BP algorithm, and as easy to use as the BP algorithm. It, therefore, can be applied, with better performance, to any situations where the standard online BP algorithm is applicable. PMID:17131658
F77NNS - A FORTRAN-77 NEURAL NETWORK SIMULATOR
Mitchell, P. H.
1994-01-01
F77NNS (A FORTRAN-77 Neural Network Simulator) simulates the popular back error propagation neural network. F77NNS is an ANSI-77 FORTRAN program designed to take advantage of vectorization when run on machines having this capability, but it will run on any computer with an ANSI-77 FORTRAN Compiler. Artificial neural networks are formed from hundreds or thousands of simulated neurons, connected to each other in a manner similar to biological nerve cells. Problems which involve pattern matching or system modeling readily fit the class of problems which F77NNS is designed to solve. The program's formulation trains a neural network using Rumelhart's back-propagation algorithm. Typically the nodes of a network are grouped together into clumps called layers. A network will generally have an input layer through which the various environmental stimuli are presented to the network, and an output layer for determining the network's response. The number of nodes in these two layers is usually tied to features of the problem being solved. Other layers, which form intermediate stops between the input and output layers, are called hidden layers. The back-propagation training algorithm can require massive computational resources to implement a large network such as a network capable of learning text-to-phoneme pronunciation rules as in the famous Sehnowski experiment. The Sehnowski neural network learns to pronounce 1000 common English words. The standard input data defines the specific inputs that control the type of run to be made, and input files define the NN in terms of the layers and nodes, as well as the input/output (I/O) pairs. The program has a restart capability so that a neural network can be solved in stages suitable to the user's resources and desires. F77NNS allows the user to customize the patterns of connections between layers of a network. The size of the neural network to be solved is limited only by the amount of random access memory (RAM) available to the
Metaplasticity Artificial Neural Networks Model Application to Radar Detection
Directory of Open Access Journals (Sweden)
Diego Andina
2007-12-01
Full Text Available Many Artificial Neural Networks design algorithms or learning methods imply the minimization of an error objective function. During learning, weight values are updated following a strategy that tends to minimize the final mean error in the Network performance. Weight values are classically seen as a representation of the synaptic weights in biological neurons and their ability to change its value could be interpreted as artificial plasticity inspired by this biological property of neurons. In such a way, metaplasticity is interpreted in this paper as the ability to change the efficiency of artificial plasticity giving more relevance to weight updating of less frequent activations and resting relevance to frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested in the Multilayer Perceptron with Backpropagation case. The results show a much more efficient training maintaining the Artificial Neural Network performance.
Estimation of scattered photons using a neural network in SPECT
International Nuclear Information System (INIS)
In single photon emission CT (SPECT), measured projection data involve scattered photons. This causes degradation of spatial resolution and contrast in reconstructed images. The purpose of this study is to estimate the scattered photons, and eliminate them from measured data. To estimate the scattered photons, we used an artificial neural network which consists of five input units, five hidden units, and two output units. The inputs of the network are the ratios of the counts acquired by five narrow energy windows and their sum. The outputs are the ratios of the count of scattered photons and that of primary photons to the total count. The neural network was trained with a back-propagation algorithm using count data obtained by a Monte Carlo simulation. The results of simulation showed improvement of contrast and spatial resolution in reconstructed images. (author)
An Artificial Neural Network for Data Forecasting Purposes
Directory of Open Access Journals (Sweden)
Catalina Lucia COCIANU
2015-01-01
Full Text Available Considering the fact that markets are generally influenced by different external factors, the stock market prediction is one of the most difficult tasks of time series analysis. The research reported in this paper aims to investigate the potential of artificial neural networks (ANN in solving the forecast task in the most general case, when the time series are non-stationary. We used a feed-forward neural architecture: the nonlinear autoregressive network with exogenous inputs. The network training function used to update the weight and bias parameters corresponds to gradient descent with adaptive learning rate variant of the backpropagation algorithm. The results obtained using this technique are compared with the ones resulted from some ARIMA models. We used the mean square error (MSE measure to evaluate the performances of these two models. The comparative analysis leads to the conclusion that the proposed model can be successfully applied to forecast the financial data.
International Nuclear Information System (INIS)
An artificial neural network has been applied for pattern recognition and used as a tool in an expert system. The purpose of this study is to examine the potential usefulness of the neural network approach in medical applications for image recognition and decision making. The authors designed multilayer feedforward neural networks with a back-propagation algorithm for our study. Using first-pass radionuclide ventriculograms, we attempted to identify the right and left ventricles of the heart and the lungs by training the neural network from patterns of time-activity curves. In a preliminary study, the neural network enabled identification of the lungs and heart chambers once the network was trained sufficiently by means of repeated entries of data from the same case
Intelligent Surveillance Robot with Obstacle Avoidance Capabilities Using Neural Network.
Budiharto, Widodo
2015-01-01
For specific purpose, vision-based surveillance robot that can be run autonomously and able to acquire images from its dynamic environment is very important, for example, in rescuing disaster victims in Indonesia. In this paper, we propose architecture for intelligent surveillance robot that is able to avoid obstacles using 3 ultrasonic distance sensors based on backpropagation neural network and a camera for face recognition. 2.4 GHz transmitter for transmitting video is used by the operator/user to direct the robot to the desired area. Results show the effectiveness of our method and we evaluate the performance of the system. PMID:26089863
Star pattern recognition method based on neural network
Institute of Scientific and Technical Information of China (English)
LI Chunyan; LI Ke; ZHANG Longyun; JIN Shengzhen; ZU Jifeng
2003-01-01
Star sensor is an avionics instrument used to provide the absolute 3-axis attitude of a spacecraft by utilizing star observations. The key function is to recognize the observed stars by comparing them with the reference catalogue. Autonomous star pattern recognition requires that similar patterns can be distinguished from each other with a small training set. Therefore, a new method based on neural network technology is proposed and a recognition system containing parallel backpropagation (BP) multi-subnets is designed. The simulation results show that the method performs much better than traditional algorithms and the proposed system can achieve both higher recognition accuracy and faster recognition speed.
Eukaryotic Promoter Recognition Using Back propagation Neural Network
Institute of Scientific and Technical Information of China (English)
XIONGQing; WANGYuan-Qiang; LIZhi-Liang
2004-01-01
A new system is developed to recognize promoter sequences from non-promoter sequences based on position weight matrix and backpropagation neural network in this paper. The system performs significantly better on the training set and the test set, the mean recognition rate is as high as 99% on the training set and 97% on the testing set. Experimental results demonstrate the effectiveness of the system to recognize the promoter sequences that have been trained and the promoter sequences that have not been seen previously.
Intelligent Surveillance Robot with Obstacle Avoidance Capabilities Using Neural Network
2015-01-01
For specific purpose, vision-based surveillance robot that can be run autonomously and able to acquire images from its dynamic environment is very important, for example, in rescuing disaster victims in Indonesia. In this paper, we propose architecture for intelligent surveillance robot that is able to avoid obstacles using 3 ultrasonic distance sensors based on backpropagation neural network and a camera for face recognition. 2.4 GHz transmitter for transmitting video is used by the operator/user to direct the robot to the desired area. Results show the effectiveness of our method and we evaluate the performance of the system. PMID:26089863
Pulse frequency classification based on BP neural network
Institute of Scientific and Technical Information of China (English)
WANG Rui; WANG Xu; YANG Dan; FU Rong
2006-01-01
In Traditional Chinese Medicine (TCM), it is an important parameter of the clinic disease diagnosis to analysis the pulse frequency. This article accords to pulse eight major essentials to identify pulse type of the pulse frequency classification based on back-propagation neural networks (BPNN). The pulse frequency classification includes slow pulse, moderate pulse, rapid pulse etc. By feature parameter of the pulse frequency analysis research and establish to identify system of pulse frequency features. The pulse signal from detecting system extracts period, frequency etc feature parameter to compare with standard feature value of pulse type. The result shows that identify-rate attains 92.5% above.
Fault Tolerant Neural Network for ECG Signal Classification Systems
Directory of Open Access Journals (Sweden)
MERAH, M.
2011-08-01
Full Text Available The aim of this paper is to apply a new robust hardware Artificial Neural Network (ANN for ECG classification systems. This ANN includes a penalization criterion which makes the performances in terms of robustness. Specifically, in this method, the ANN weights are normalized using the auto-prune method. Simulations performed on the MIT ? BIH ECG signals, have shown that significant robustness improvements are obtained regarding potential hardware artificial neuron failures. Moreover, we show that the proposed design achieves better generalization performances, compared to the standard back-propagation algorithm.
Neural logic networks a new class of neural networks
Heng, Teh Hoon
1995-01-01
This book is the first of a series of technical reports of a key research project of the Real-World Computing Program supported by the MITI of Japan.The main goal of the project is to model human intelligence by a special class of mathematical systems called neural logic networks.The book consists of three parts. Part 1 describes the general theory of neural logic networks and their potential applications. Part 2 discusses a new logic called Neural Logic which attempts to emulate more closely the logical thinking process of human. Part 3 studies the special features of neural logic networks wh
Nonlinear signal processing using neural networks: Prediction and system modelling
Energy Technology Data Exchange (ETDEWEB)
Lapedes, A.; Farber, R.
1987-06-01
The backpropagation learning algorithm for neural networks is developed into a formalism for nonlinear signal processing. We illustrate the method by selecting two common topics in signal processing, prediction and system modelling, and show that nonlinear applications can be handled extremely well by using neural networks. The formalism is a natural, nonlinear extension of the linear Least Mean Squares algorithm commonly used in adaptive signal processing. Simulations are presented that document the additional performance achieved by using nonlinear neural networks. First, we demonstrate that the formalism may be used to predict points in a highly chaotic time series with orders of magnitude increase in accuracy over conventional methods including the Linear Predictive Method and the Gabor-Volterra-Weiner Polynomial Method. Deterministic chaos is thought to be involved in many physical situations including the onset of turbulence in fluids, chemical reactions and plasma physics. Secondly, we demonstrate the use of the formalism in nonlinear system modelling by providing a graphic example in which it is clear that the neural network has accurately modelled the nonlinear transfer function. It is interesting to note that the formalism provides explicit, analytic, global, approximations to the nonlinear maps underlying the various time series. Furthermore, the neural net seems to be extremely parsimonious in its requirements for data points from the time series. We show that the neural net is able to perform well because it globally approximates the relevant maps by performing a kind of generalized mode decomposition of the maps. 24 refs., 13 figs.
Improved Marquardt Algorithm for Training Neural Networks for Chemical Process Modeling
Institute of Scientific and Technical Information of China (English)
吴建昱; 何小荣
2002-01-01
Back-propagation (BP) artificial neural networks have been widely used to model chemical processes. BP networks are often trained using the generalized delta-rule (GDR) algorithm but application of such networks is limited because of the low convergent speed of the algorithm. This paper presents a new algorithm incorporating the Marquardt algorithm into the BP algorithm for training feedforward BP neural networks. The new algorithm was tested with several case studies and used to model the Reid vapor pressure (RVP) of stabilizer gasoline. The new algorithm has faster convergence and is much more efficient than the GDR algorithm.
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. PMID:11088736
Highly Accurate Multi-layer Perceptron Neural Network for Air Data System
H. S. Krishna
2009-01-01
The error backpropagation multi-layer perceptron algorithm is revisited. This algorithm is used to train and validate two models of three-layer neural networks that can be used to calibrate a 5-hole pressure probe. This paper addresses Occam's Razor problem as it describes the adhoc training methodology applied to improve accuracy and sensitivity. The trained outputs from 5-4-3 feed-forward network architecture with jump connection are comparable to second decimal digit (~0.05) accuracy, hith...
International Nuclear Information System (INIS)
In this paper, a locally recurrent neural network (LRNN) is employed for approximating the temporal evolution of a nonlinear dynamic system model of a simplified nuclear reactor. To this aim, an infinite impulse response multi-layer perceptron (IIR-MLP) is trained according to a recursive back-propagation (RBP) algorithm. The network nodes contain internal feedback paths and their connections are realized by means of IIR synaptic filters, which provide the LRNN with the necessary system state memory
A low communication overhead parallel implementation of the back-propagation algorithm
Alfonso, Marcelo; Kavka, Carlos; Printista, Alicia Marcela
2000-01-01
The back-propagation algorithm is one of the most widely used training algorithms for neural networks. The training phase of a multilayer perceptron by using this algorithm can take very long time making neural networks difficult to accept. One approach to solve this problem consists in the parallelization of the training algorithm. There exists many different approaches, however most of them are well adapted to specialized hardware. The idea to use a network of workstations as a genera...
Jha, Ratneshwar; Rower, Jacob
2002-02-01
The use of neural networks for identification and control of smart structures is investigated experimentally. Piezoelectric actuators are employed to suppress the vibrations of a cantilevered plate subject to impulse, sine wave and band-limited white noise disturbances. The neural networks used are multilayer perceptrons trained with error backpropagation. Validation studies show that the identifier predicts the system dynamics accurately. The controller is trained adaptively with the help of the neural identifier. Experimental results demonstrate excellent closed-loop performance and robustness of the neurocontroller.
Heiden, Uwe
1980-01-01
The purpose of this work is a unified and general treatment of activity in neural networks from a mathematical pOint of view. Possible applications of the theory presented are indica ted throughout the text. However, they are not explored in de tail for two reasons : first, the universal character of n- ral activity in nearly all animals requires some type of a general approach~ secondly, the mathematical perspicuity would suffer if too many experimental details and empirical peculiarities were interspersed among the mathematical investigation. A guide to many applications is supplied by the references concerning a variety of specific issues. Of course the theory does not aim at covering all individual problems. Moreover there are other approaches to neural network theory (see e.g. Poggio-Torre, 1978) based on the different lev els at which the nervous system may be viewed. The theory is a deterministic one reflecting the average be havior of neurons or neuron pools. In this respect the essay is writt...
Total solar irradiance reconstruction using artificial neural networks
Tebabal Yirdaw, Ambelu; Damtie, Baylie; Nigussie, Melessew; Bires, Abiyot; Yizengaw, Endawoke
2015-08-01
A feed-forward neural network which can account for nonlinear relationships was used to reconstruct total solar irradiance (TSI). A single layer feed forward neural network with back-propagation algorithm have been implemented for reconstructing daily total solar irradiance from daily photometric sunspot index, and core to wing ratio of Mg II index data. The data year from 1978 to 2013 was used for the training, validation and testing purpose. In order to obtain the optimum neural network for TSI reconstruction, the root mean square error (RMSE), mean absolute error (MAE) and regression coefficient have been taken into account. We have carried out the analysis is made by comparing the reconstructed TSI from neural networks (NNs ) and TSI measurement from satellite. We have found out that the reconstructed TSI and the PMOD composite have the correlation coefficient of about R=0.9307 over the span of the recorded, 1978 to 2013. The NNs model output indicates that reconstructed TSI from solar proxies (photometric index and MgII ) can explain 86.6% of the variance of TSI. Neural network is able to recreate TSI observations on a time scale of a day. This reconstructed TSI using NNs further strengthens the view that surface magnetism indeed plays a dominant role in modulating solar irradiance.
A study of reactor diagnosis method with neural network using PWR plant simulator
International Nuclear Information System (INIS)
The purpose of this paper is to demonstrate the capability of the nuclear power plant monitoring system with a neural network, using a PWR plant training simulator by which many kinds of anomaly conditions can be easily simulated. The dynamics model of reactor plant was constructed by using a three layered auto-associative neural network with backpropagation learning algorithm. The basic idea of anomaly detection method is to monitor the deviation between process signals measured from an actual plant and corresponding output signals from the neural network plant model. Four kinds of simulated malfunctions caused by equipment failure during steady state operation were selected to evaluate the capability of the neural network monitoring system. The results show that this monitoring system can detect the symptoms of small anomalies earlier than the conventional alarm system. Furthermore, sensitivity analysis makes it clear that the modeling by the neural network is adequate. (author)
Neural network applications in telecommunications
Alspector, Joshua
1994-01-01
Neural network capabilities include automatic and organized handling of complex information, quick adaptation to continuously changing environments, nonlinear modeling, and parallel implementation. This viewgraph presentation presents Bellcore work on applications, learning chip computational function, learning system block diagram, neural network equalization, broadband access control, calling-card fraud detection, software reliability prediction, and conclusions.
Neural networks at the Tevatron
International Nuclear Information System (INIS)
This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF
Neural Networks for Optimal Control
DEFF Research Database (Denmark)
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
Neural Networks for the Beginner.
Snyder, Robin M.
Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…
The use of artificial neural networks for uranium metal production
International Nuclear Information System (INIS)
Production of uranium metal conducted by the fuel element production installation employs a standard and established procedure. Discrepancies between the uranium products and its theoretical yields could reach about 15%. This deviation is believed due to incomplete chemical reactions and inherent technical difficulties in uranium production procedure. Even though the causes may be identified, the deviation is unavoidable since raw materials characterization brings no benefit and procedure modification is impossible. An artificial neural network is proposed to estimate uranium produced and UF4 required. Three backpropagation neural networks have been built. Each of them consists of three neurons in input layer, seven neurons in hidden layer, and one neuron in output layer. The data used to train the network were generated from the equation of chemical reaction in uranium production. Thirty three data obtained from this equation were utilized to train and to evaluate the first network was tested. Its prediction raised error less than 0.99%. Meanwhile, there were only five data available from the uranium production activities. These data were employed to train and to test the second and third network. The second network predicts the resulted uranium and the third predicts the necessary UF4. During evaluation process, the second network responded with 3.86% error and the third network generated 1.34% error. Using relatively very few data, those networks are able to respond satisfactorily, as illustrated by these low levels of prediction error. This reflects that backpropagation networks are capable in handling pattern recognition-related problems of the uranium production. (author)
Evolution of an artificial neural network based autonomous land vehicle controller.
Baluja, S
1996-01-01
This paper presents an evolutionary method for creating an artificial neural network based autonomous land vehicle controller. The evolved controllers perform better in unseen situations than those trained with an error backpropagation learning algorithm designed for this task. In this paper, an overview of the previous connectionist based approaches to this task is given, and the evolutionary algorithms used in this study are described in detail. Methods for reducing the high computational costs of training artificial neural networks with evolutionary algorithms are explored. Error metrics specific to the task of autonomous vehicle control are introduced; the evolutionary algorithms guided by these error metrics reveal improved performance over those guided by the standard sum-squared error metric. Finally, techniques for integrating evolutionary search and error backpropagation are presented. The evolved networks are designed to control Carnegie Mellon University's NAVLAB vehicles in road following tasks. PMID:18263046
Neural Network Burst Pressure Prediction in Composite Overwrapped Pressure Vessels
Hill, Eric v. K.; Dion, Seth-Andrew T.; Karl, Justin O.; Spivey, Nicholas S.; Walker, James L., II
2007-01-01
Acoustic emission data were collected during the hydroburst testing of eleven 15 inch diameter filament wound composite overwrapped pressure vessels. A neural network burst pressure prediction was generated from the resulting AE amplitude data. The bottles shared commonality of graphite fiber, epoxy resin, and cure time. Individual bottles varied by cure mode (rotisserie versus static oven curing), types of inflicted damage, temperature of the pressurant, and pressurization scheme. Three categorical variables were selected to represent undamaged bottles, impact damaged bottles, and bottles with lacerated hoop fibers. This categorization along with the removal of the AE data from the disbonding noise between the aluminum liner and the composite overwrap allowed the prediction of burst pressures in all three sets of bottles using a single backpropagation neural network. Here the worst case error was 3.38 percent.
Mammographic mass detection using wavelets as input to neural networks.
Kilic, Niyazi; Gorgel, Pelin; Ucan, Osman N; Sertbas, Ahmet
2010-12-01
The objective of this paper is to demonstrate the utility of artificial neural networks, in combination with wavelet transforms for the detection of mammogram masses as malign or benign. A total of 45 patients who had breast masses in their mammography were enrolled in the study. The neural network was trained on the wavelet based feature vectors extracted from the mammogram masses for both benign and malign data. Therefore, in this study, Multilayer ANN was trained with the Backpropagation, Conjugate Gradient and Levenberg-Marquardt algorithms and ten-fold cross validation procedure was used. A satisfying sensitivity percentage of 89.2% was achieved with Levenberg-Marquardt algorithm. Since, this algorithm combines the best features of the Gauss-Newton technique and the other steepest-descent algorithms and thus it reaches desired results very fast. PMID:20703600
Empirical modeling of nuclear power plants using neural networks
International Nuclear Information System (INIS)
A summary of a procedure for nonlinear identification of process dynamics encountered in nuclear power plant components is presented in this paper using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the nonlinear structure for system identification. In the overall identification process, the feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of time-dependent system nonlinearities. The standard backpropagation learning algorithm is modified and is used to train the proposed hybrid network in a supervised manner. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The nonlinear response of a representative steam generator is predicted using a neural network and is compared to the response obtained from a sophisticated physical model during both high- and low-power operation. The transient responses compare well, though further research is warranted for training and testing of recurrent neural networks during more severe operational transients and accident scenarios
Chen, Chau-Kuang
2010-01-01
Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…
Trends in neural network technology. Neural network gijutsu no doko
Energy Technology Data Exchange (ETDEWEB)
Nishimura, K. (Toshiba Corp., Tokyo (Japan))
1991-12-01
The present and future of neural network technologies were reviewed. Neural networks simulate the neurons and synapses of human brain, thus permitting the utilization of heuristic knowledge difficult to describe in a logical manner. Such networks can therefore solve optimization problems, difficult to solve by conventional computers, more rapidly while sacrificing a permissible degree of rigor. In light of these advantages, many attempts have been made to apply neural networks to a variety of engineering fields including character recognition, phonetic recognition diagnosis, operation and so on. Now that these attempts have demonstrated the great potential of neural network technology, its application to practical problems will receive increasing attention. The necessity for fundamental studies on learning algorithms, modularization techniques, hardware technologies and so on will grow in conjunction with the above trends in application. 20 refs., 11 figs., 1 tab.
Newton's Method Backpropagation for Complex-Valued Holomorphic Multilayer Perceptrons
La Corte, Diana Thomson; Zou, Yi ming
2014-01-01
The study of Newton's method in complex-valued neural networks faces many difficulties. In this paper, we derive Newton's method backpropagation algorithms for complex-valued holomorphic multilayer perceptrons, and investigate the convergence of the one-step Newton steplength algorithm for the minimization of real-valued complex functions via Newton's method. To provide experimental support for the use of holomorphic activation functions, we perform a comparison of using sigmoidal functions v...
Neural Networks in Control Applications
DEFF Research Database (Denmark)
Sørensen, O.
The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all in a...... recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...
Groundwater Level Predictions Using Artificial Neural Networks
Institute of Scientific and Technical Information of China (English)
毛晓敏; 尚松浩; 刘翔
2002-01-01
The prediction of groundwater level is important for the use and management of groundwater resources. In this paper, the artificial neural networks (ANN) were used to predict groundwater level in the Dawu Aquifer of Zibo in Eastern China. The first step was an auto-correlation analysis of the groundwater level which showed that the monthly groundwater level was time dependent. An auto-regression type ANN (ARANN) model and a regression-auto-regression type ANN (RARANN) model using back-propagation algorithm were then used to predict the groundwater level. Monthly data from June 1988 to May 1998 was used for the network training and testing. The results show that the RARANN model is more reliable than the ARANN model, especially in the testing period, which indicates that the RARANN model can describe the relationship between the groundwater fluctuation and main factors that currently influence the groundwater level. The results suggest that the model is suitable for predicting groundwater level fluctuations in this area for similar conditions in the future.
Computer-assisted diagnosis of lung nodule detection using artificial convoultion neural network
Lo, Shih-Chung B.; Lin, Jyh-Shyan; Freedman, Matthew T.; Mun, Seong K.
1993-09-01
Several fuzzy assignment methods for the output association with convolution neural network are proposed for general medical image pattern recognition. A non-conventional method of using rotation and shift invariance is also proposed to enhance the neural net performance. These methods in conjunction with the convolution neural network technique are generally applicable to the recognition of medical disease patterns in gray scale imaging. The structure of the artificial neural network is a simplified network structure of neocognitron. Two- dimensional local connection as a group is the fundamental architecture for the signal propagation in the convolution (vision type) neural network. Weighting coefficients of convolution kernels are formed by neural network through backpropagated training for this artificial neural net. In addition, radiologists' reading procedure was modeled in order to instruct the artificial neural network to recognize the pre-defined image patterns and those of interest to experts. We have tested this method for lung nodule detection. The performance studies have shown the potential use of this technique in a clinical environment. Our computer program uses a sphere profile double-matching technique for initial nodule search. We set searching parameters in a highly sensitive level to identify all potential disease areas. The artificial convolution neural network acts as a final detection classifier to determine if a disease pattern is shown on the suspected image area. The total processing time for the automatic detection of lung nodules using both pre-scan and convolution neural network evaluation is about 10 seconds in a DEC Alpha workstation.
Neural Networks for Omni—View Road Image Understanding
Institute of Scientific and Technical Information of China (English)
朱志刚; 徐光You
1996-01-01
This paper presents a new approach to the outdoor roa scene understanding by using omni-view images and backpropagation networks.Both the road directions used for vehicle heading and th road categories used for vehicle localization are determined by the integrated system.There are three main features about the work.First,an omni-view image sensor is used to extract image samples,and the original image is preprocessed so that the inputs of the network is rotation-invariant and simple.Second,the problem of the network size,especially the number of the hidden units,is decided by the analysis of systematic experimental results.Finally,the internal representation,which reveals the properties of the neural network,is analyzed in the view point of visual signal processing.Experimental results with real scene images are encouraging.
Using neural networks for prediction of nuclear parameters
Energy Technology Data Exchange (ETDEWEB)
Pereira Filho, Leonidas; Souto, Kelling Cabral, E-mail: leonidasmilenium@hotmail.com, E-mail: kcsouto@bol.com.br [Instituto Federal de Educacao, Ciencia e Tecnologia do Rio de Janeiro (IFRJ), Rio de Janeiro, RJ (Brazil); Machado, Marcelo Dornellas, E-mail: dornemd@eletronuclear.gov.br [Eletrobras Termonuclear S.A. (GCN.T/ELETRONUCLEAR), Rio de Janeiro, RJ (Brazil). Gerencia de Combustivel Nuclear
2013-07-01
Dating from 1943, the earliest work on artificial neural networks (ANN), when Warren Mc Cullock and Walter Pitts developed a study on the behavior of the biological neuron, with the goal of creating a mathematical model. Some other work was done until after the 80 witnessed an explosion of interest in ANNs, mainly due to advances in technology, especially microelectronics. Because ANNs are able to solve many problems such as approximation, classification, categorization, prediction and others, they have numerous applications in various areas, including nuclear. Nodal method is adopted as a tool for analyzing core parameters such as boron concentration and pin power peaks for pressurized water reactors. However, this method is extremely slow when it is necessary to perform various core evaluations, for example core reloading optimization. To overcome this difficulty, in this paper a model of Multi-layer Perceptron (MLP) artificial neural network type backpropagation will be trained to predict these values. The main objective of this work is the development of Multi-layer Perceptron (MLP) artificial neural network capable to predict, in very short time, with good accuracy, two important parameters used in the core reloading problem - Boron Concentration and Power Peaking Factor. For the training of the neural networks are provided loading patterns and nuclear data used in cycle 19 of Angra 1 nuclear power plant. Three models of networks are constructed using the same input data and providing the following outputs: 1- Boron Concentration and Power Peaking Factor, 2 - Boron Concentration and 3 - Power Peaking Factor. (author)
Using neural networks for prediction of nuclear parameters
International Nuclear Information System (INIS)
Dating from 1943, the earliest work on artificial neural networks (ANN), when Warren Mc Cullock and Walter Pitts developed a study on the behavior of the biological neuron, with the goal of creating a mathematical model. Some other work was done until after the 80 witnessed an explosion of interest in ANNs, mainly due to advances in technology, especially microelectronics. Because ANNs are able to solve many problems such as approximation, classification, categorization, prediction and others, they have numerous applications in various areas, including nuclear. Nodal method is adopted as a tool for analyzing core parameters such as boron concentration and pin power peaks for pressurized water reactors. However, this method is extremely slow when it is necessary to perform various core evaluations, for example core reloading optimization. To overcome this difficulty, in this paper a model of Multi-layer Perceptron (MLP) artificial neural network type backpropagation will be trained to predict these values. The main objective of this work is the development of Multi-layer Perceptron (MLP) artificial neural network capable to predict, in very short time, with good accuracy, two important parameters used in the core reloading problem - Boron Concentration and Power Peaking Factor. For the training of the neural networks are provided loading patterns and nuclear data used in cycle 19 of Angra 1 nuclear power plant. Three models of networks are constructed using the same input data and providing the following outputs: 1- Boron Concentration and Power Peaking Factor, 2 - Boron Concentration and 3 - Power Peaking Factor. (author)
Artificial Neural Network applied to lightning flashes
Gin, R. B.; Guedes, D.; Bianchi, R.
2013-05-01
The development of video cameras enabled cientists to study lightning discharges comportment with more precision. The main goal of this project is to create a system able to detect images of lightning discharges stored in videos and classify them using an Artificial Neural Network (ANN)using C Language and OpenCV libraries. The developed system, can be split in two different modules: detection module and classification module. The detection module uses OpenCV`s computer vision libraries and image processing techniques to detect if there are significant differences between frames in a sequence, indicating that something, still not classified, occurred. Whenever there is a significant difference between two consecutive frames, two main algorithms are used to analyze the frame image: brightness and shape algorithms. These algorithms detect both shape and brightness of the event, removing irrelevant events like birds, as well as detecting the relevant events exact position, allowing the system to track it over time. The classification module uses a neural network to classify the relevant events as horizontal or vertical lightning, save the event`s images and calculates his number of discharges. The Neural Network was implemented using the backpropagation algorithm, and was trained with 42 training images , containing 57 lightning events (one image can have more than one lightning). TheANN was tested with one to five hidden layers, with up to 50 neurons each. The best configuration achieved a success rate of 95%, with one layer containing 20 neurons (33 test images with 42 events were used in this phase). This configuration was implemented in the developed system to analyze 20 video files, containing 63 lightning discharges previously manually detected. Results showed that all the lightning discharges were detected, many irrelevant events were unconsidered, and the event's number of discharges was correctly computed. The neural network used in this project achieved a
Neural Network Models for Free Radical Polymerization of Methyl Methacrylate
International Nuclear Information System (INIS)
In this paper, a neural network modeling of the batch bulk methyl methacrylate polymerization is performed. To obtain conversion, number and weight average molecular weights, three neural networks were built. Each was a multilayer perception with one or two hidden layers. The choice of network topology, i.e. the number of hidden layers and the number of neurons in these layers, was based on achieving a compromise between precision and complexity. Thus, it was intended to have an error as small as possible at the end of back-propagation training phases, while using a network with reduced complexity. The performances of the networks were evaluated by comparing network predictions with training data, validation data (which were not uses for training), and with the results of a mechanistic model. The accurate predictions of neural networks for monomer conversion, number average molecular weight and weight average molecular weight proves that this modeling methodology gives a good representation and generalization of the batch bulk methyl methacrylate polymerization. (author)
TAO-robust backpropagation learning algorithm.
Pernía-Espinoza, Alpha V; Ordieres-Meré, Joaquín B; Martínez-de-Pisón, Francisco J; González-Marcos, Ana
2005-03-01
In several fields, as industrial modelling, multilayer feedforward neural networks are often used as universal function approximations. These supervised neural networks are commonly trained by a traditional backpropagation learning format, which minimises the mean squared error (mse) of the training data. However, in the presence of corrupted data (outliers) this training scheme may produce wrong models. We combine the benefits of the non-linear regression model tau-estimates [introduced by Tabatabai, M. A. Argyros, I. K. Robust Estimation and testing for general nonlinear regression models. Applied Mathematics and Computation. 58 (1993) 85-101] with the backpropagation algorithm to produce the TAO-robust learning algorithm, in order to deal with the problems of modelling with outliers. The cost function of this approach has a bounded influence function given by the weighted average of two psi functions, one corresponding to a very robust estimate and the other to a highly efficient estimate. The advantages of the proposed algorithm are studied with an example. PMID:15795116
Principles of artificial neural networks
Graupe, Daniel
2013-01-01
Artificial neural networks are most suitable for solving problems that are complex, ill-defined, highly nonlinear, of many and different variables, and/or stochastic. Such problems are abundant in medicine, in finance, in security and beyond. This volume covers the basic theory and architecture of the major artificial neural networks. Uniquely, it presents 18 complete case studies of applications of neural networks in various fields, ranging from cell-shape classification to micro-trading in finance and to constellation recognition - all with their respective source codes. These case studies
Modular, Hierarchical Learning By Artificial Neural Networks
Baldi, Pierre F.; Toomarian, Nikzad
1996-01-01
Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.
Directory of Open Access Journals (Sweden)
Lukas Falat
2016-01-01
Full Text Available This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process.
Falat, Lukas; Marcek, Dusan; Durisova, Maria
2016-01-01
This paper deals with application of quantitative soft computing prediction models into financial area as reliable and accurate prediction models can be very helpful in management decision-making process. The authors suggest a new hybrid neural network which is a combination of the standard RBF neural network, a genetic algorithm, and a moving average. The moving average is supposed to enhance the outputs of the network using the error part of the original neural network. Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day. To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network. They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm. Finally, the authors find out that their suggested hybrid neural network is able to produce more accurate forecasts than the standard models and can be helpful in eliminating the risk of making the bad decision in decision-making process. PMID:26977450
High-speed reconstruction of spect images with a tailored piecewise neural network
Energy Technology Data Exchange (ETDEWEB)
Kerr, J.P.; Bartlett, E.B.
1993-12-31
Artificial neural networks (ANNs) have proven to be highly adept at mapping complex functional relationships. We have previously shown that a standard backpropagation neural network can be trained to reconstruct sections of single photon emission computed tomography (SPECT) images based on the planar image projections as inputs. In this study, we demonstrate that a neural network that utilizes a tailored three-phase piecewise activation function is able to perform high-speed reconstructions of SPECT images after learning the relationship between the planar images and the tomographic reconstructions. In addition, the tailored piecewise neural network produces reconstructions with significantly lower RMS error, and does so in far less training iterations, than a standard backpropagation ANN. The tailored piecewise function used in this research enables the network to train on a continuous range of outputs more efficiently than with a standard sigmoidal function. Based on the results obtained, we hypothesize that the optimal ANN transfer function or functions, are directly related to the statistical distribution of the training set data. As a preliminary demonstration, a neural network with statistically derived activation functions is shown to have better training and generalization characteristics for SPECT reconstruction than either the single sigmoidal or the three- phase sigmoidal activation functions.
Vibration monitoring of EDF rotating machinery using artificial neural networks
International Nuclear Information System (INIS)
Vibration monitoring of components in nuclear power plants has been used for a number of years. This technique involves the analysis of vibration data coming from vital components of the plant to detect features which reflect the operational state of machinery. The analysis leads to the identification of potential failures and their causes, and makes it possible to perform efficient preventive maintenance. Earlydetection is important because it can decrease the probability of catastrophic failures, reduce forced outgage, maximize utilization of available assets, increase the life of the plant, and reduce maintenance costs. This paper documents our work on the design of a vibration monitoring methodology based on neural network technology. This technology provides an attractive complement to traditional vibration analysis because of the potential of neural networks to operate in real-time mode and to handle data which may be distorted or noisy. Our efforts have been concentrated on the analysis and classification of vibration signatures collected by Electricite de France (EDF). Two neural networks algorithms were used in our project: the Recirculation algorithm and the Backpropagation algorithm. Although this project is in the early stages of development it indicates that neural networks may provide a viable methodology for monitoring and diagnostics of vibrating components. Our results are very encouraging
Nonlinear identification of process dynamics using neural networks
International Nuclear Information System (INIS)
In this paper the nonlinear identification of process dynamics encountered in nuclear power plant components is addressed, in an input-output sense, using artificial neural systems. A hybrid feedforward/feedback neural network, namely, a recurrent multilayer perceptron, is used as the model structure to be identified. The feedforward portion of the network architecture provides its well-known interpolation property, while through recurrency and cross-talk, the local information feedback enables representation of temporal variations in the system nonlinearities. The standard backpropagation learning algorithm is modified, and it is used for the supervised training of the proposed hybrid network. The performance of recurrent multilayer perceptron networks in identifying process dynamics is investigated via the case study of a U-tube steam generator. The response of representative steam generator is predicted using a neural network, and it is compared to the response obtained from a sophisticated computer model based on first principles. The transient responses compare well, although further research is warranted to determine the predictive capabilities of these networks during more severe operational transients and accident scenarios
Neural networks and statistical learning
Du, Ke-Lin
2014-01-01
Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...
A Neural Network Approach for GMA Butt Joint Welding
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least......This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self...
A Neural Network Approach for GMA Butt Joint Welding
DEFF Research Database (Denmark)
Christensen, Kim Hardam; Sørensen, Torben
2003-01-01
This paper describes the application of the neural network technology for gas metal arc welding (GMAW) control. A system has been developed for modeling and online adjustment of welding parameters, appropriate to guarantee a certain degree of quality in the field of butt joint welding with full...... penetration, when the gap width is varying during the welding process. The process modeling to facilitate the mapping from joint geometry and reference weld quality to significant welding parameters has been based on a multi-layer feed-forward network. The Levenberg-Marquardt algorithm for non-linear least...... squares has been used with the back-propagation algorithm for training the network, while a Bayesian regularization technique has been successfully applied for minimizing the risk of inexpedient over-training. Finally, a predictive closed-loop control strategy based on a so-called single-neuron self...
Classification of Human Emotions from EEG Signals using Statistical Features and Neural Network
Chai Tong Yuen; Woo San San; Tan Ching Seong; Mohamed Rizon
2009-01-01
A statistical based system for human emotions classification by using electroencephalogram (EEG) is proposed in this paper. The data used in this study is acquired using EEG and the emotions are elicited from six human subjects under the effect of emotion stimuli. This paper also proposed an emotion stimulation experiment using visual stimuli. From the EEG data, a total of six statistical features are computed and back-propagation neural network is applied for the classification of human emot...
Manoj Tripathy
2012-01-01
This paper describes a new approach for power transformer differential protection which is based on the wave-shape recognition technique. An algorithm based on neural network principal component analysis (NNPCA) with back-propagation learning is proposed for digital differential protection of power transformer. The principal component analysis is used to preprocess the data from power system in order to eliminate redundant information and enhance hidden pattern of differential current to disc...
Artificial Neural Network based Diagnostic Model For Causes of Success and Failures
Kaur, Bikrampal; Aggarwal, Himanshu
2010-01-01
In this paper an attempt has been made to identify most important human resource factors and propose a diagnostic model based on the back-propagation and connectionist model approaches of artificial neural network (ANN). The focus of the study is on the mobile -communication industry of India. The ANN based approach is particularly important because conventional approaches (such as algorithmic) to the problem solving have their inherent disadvantages. The algorithmic approach is well-suited t...
Alternating optimization method based on nonnegative matrix factorizations for deep neural networks
Sakurai, Tetsuya; Imakura, Akira; Inoue, Yuto; Futamura, Yasunori
2016-01-01
The backpropagation algorithm for calculating gradients has been widely used in computation of weights for deep neural networks (DNNs). This method requires derivatives of objective functions and has some difficulties finding appropriate parameters such as learning rate. In this paper, we propose a novel approach for computing weight matrices of fully-connected DNNs by using two types of semi-nonnegative matrix factorizations (semi-NMFs). In this method, optimization processes are performed b...
HAŞİLOĞLU, Abdulsamet
2001-01-01
A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were proposed for texture features extraction. In this study, non-subsampled wavelet frame transform was used for feature extraction of 16 textures from a set of Brodatz' album by means of various wavelet families. Texture classification was accomplished by artificial neural network with a fast adaptive backpropagation algorithm. A new pyramidal-w...
Incorporation of Liquid-Crystal Light Valve Non-Linearities in Optical Multilayer Neural Networks
Moerland, Perry,; Fiesler, Emile; Saxena, Indu
1996-01-01
Sigmoidlike activation functions, as available in analog hardware, differ in various ways from the standard sigmoidal function because they are usually asymmetric, truncated, and have a non-standard gain. We present an adaptation of the backpropagation learning rule to compensate for these nonstandard sigmoids. This method is applied to multilayer neural networks with all-optical forward propagation and liquid-crystal light valves (LCLV) as optical thresholding devices. In this paper, the res...
Automatic Modulation Recognition Using Wavelet Transform and Neural Networks in Wireless Systems
Dayoub I; Hamouda W; Hassan K; Berbineau M
2010-01-01
Modulation type is one of the most important characteristics used in signal waveform identification. In this paper, an algorithm for automatic digital modulation recognition is proposed. The proposed algorithm is verified using higher-order statistical moments (HOM) of continuous wavelet transform (CWT) as a features set. A multilayer feed-forward neural network trained with resilient backpropagation learning algorithm is proposed as a classifier. The purpose is to discriminate among differe...
A selective learning method to improve the generalization of multilayer feedforward neural networks.
Inés M. Galván; Isasi, Pedro; Aler, Ricardo; José M. Valls
2001-01-01
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in many applications. However, the level of generalization is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of training patterns, better generalization performance may be obtained. Nevertheless, generalization is carried out independently of the novel patterns to b...
Neural networks for predicting flow discharge in the balarood river (Iran)
Emamgholizadeh, S.
2008-01-01
In this study an artificial neural networks (ANNs) model, multi-layer perception using back-propagation algorithm (MLP/BP) was used for predicting flow discharge in the Balarood River which located in Khozestan province, Iran. The rain and temperature data as monthly collected at the five meteorology stations near the Balarood basin, and corresponding them the measured discharge at the Dokohe hydrometric station on the Balarood river were used to train and validate the ANN model. ...
Neural Networks Of VLSI Components
Eberhardt, Silvio P.
1991-01-01
Concept for design of electronic neural network calls for assembly of very-large-scale integrated (VLSI) circuits of few standard types. Each VLSI chip, which contains both analog and digital circuitry, used in modular or "building-block" fashion by interconnecting it in any of variety of ways with other chips. Feedforward neural network in typical situation operates under control of host computer and receives inputs from, and sends outputs to, other equipment.
Neural Networks for Fingerprint Recognition
Baldi, Pierre; Chauvin, Yves
1993-01-01
After collecting a data base of fingerprint images, we design a neural network algorithm for fingerprint recognition. When presented with a pair of fingerprint images, the algorithm outputs an estimate of the probability that the two images originate from the same finger. In one experiment, the neural network is trained using a few hundred pairs of images and its performance is subsequently tested using several thousand pairs of images originated from a subset of the database corresponding to...
Neural Networks and Photometric Redshifts
Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo
2002-01-01
We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy...
What are artificial neural networks?
DEFF Research Database (Denmark)
Krogh, Anders
2008-01-01
Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb......Artificial neural networks have been applied to problems ranging from speech recognition to prediction of protein secondary structure, classification of cancers and gene prediction. How do they work and what might they be good for? Udgivelsesdato: 2008-Feb...
Artificial neural network models for image understanding
Kulkarni, Arun D.; Byars, P.
1991-06-01
In this paper we introduce a new class of artificial neural network (ANN) models based on transformed domain feature extraction. Many optical and/or digital recognition systems based on transformed domain feature extraction are available in practice. Optical systems are inherently parallel in nature and are preferred for real time applications, whereas digital systems are more suitable for nonlinear operations. In our ANN models we combine advantages of both digital and optical systems. Many transformed domain feature extraction techniques have been developed during the last three decades. They include: the Fourier transform (FT), the Walsh Hadamard transform (WHT), the discrete cosine transform (DCT), etc. As an example, we have developed ANN models using the FT and WHT domain features. The models consist of two stages, the feature extraction stage and the recognition stage. We have used back-propagation and competitive learning algorithms in the recognition stage. We have used these ANN models for invariant object recognition. The models have been used successfully to recognize various types of aircraft, and also have been tested with test patterns. ANN models based on other transforms can be developed in a similar fashion.
Correlational Neural Networks.
Chandar, Sarath; Khapra, Mitesh M; Larochelle, Hugo; Ravindran, Balaraman
2016-02-01
Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms here are canonical correlation analysis (CCA)-based approaches and autoencoder (AE)-based approaches. CCA-based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace. AE-based methods learn a common representation by minimizing the error of reconstructing the two views. Each of these approaches has its own advantages and disadvantages. For example, while CCA-based approaches outperform AE-based approaches for the task of transfer learning, they are not as scalable as the latter. In this work, we propose an AE-based approach, correlational neural network (CorrNet), that explicitly maximizes correlation among the views when projected to the common subspace. Through a series of experiments, we demonstrate that the proposed CorrNet is better than AE and CCA with respect to its ability to learn correlated common representations. We employ CorrNet for several cross-language tasks and show that the representations learned using it perform better than the ones learned using other state-of-the-art approaches. PMID:26654210
A System for Predicting Subcellular Localization of Yeast Genome Using Neural Network
Thampi, Sabu M
2007-01-01
The subcellular location of a protein can provide valuable information about its function. With the rapid increase of sequenced genomic data, the need for an automated and accurate tool to predict subcellular localization becomes increasingly important. Many efforts have been made to predict protein subcellular localization. This paper aims to merge the artificial neural networks and bioinformatics to predict the location of protein in yeast genome. We introduce a new subcellular prediction method based on a backpropagation neural network. The results show that the prediction within an error limit of 5 to 10 percentage can be achieved with the system.
Application of Artificial Neural Networks in Differential Thermal Analysis of Inorganic Compounds
Ilgun, Ozlem; Beken, Murat; Alekberov, Vilayet; Ozcanli, Yesim
2010-01-01
Thermal decomposition of inorganic compounds have been analyzed by simultaneous differential thermal analysis (DTA) method. Also phase transitions and critical points have been investigated. Additionally a computer model based on backpropagation multilayer feed-forward artificial neural networks (ANNs) have been used for the stimulation and prediction of critical points and phase transitions of inorganic compounds. Experimental data and output values of artificial neural networks have been compared and ANN predictions showed a considerably good result due to some unjustified data values and ANN predictions concurred with each other.
International Nuclear Information System (INIS)
A back-propagation neural network technique is used at JET to extract plasma parameters like ion temperature, rotation velocities or spectral line intensities from charge exchange (CX) spectra. It is shown that in the case of the C VI CX spectra, neural networks can give a good estimation (better than +-20% accuracy) for the main plasma parameters (Ti, Vrot). Since the neural network approach involves no iterations or initial guesses the speed with which a spectrum is processed is so high (0.2 ms/spectrum) that real time analysis will be achieved in the near future. 4 refs., 8 figs
Energy Technology Data Exchange (ETDEWEB)
Koenig, R.W.T.; Von Hellermann, M. [Commission of the European Communities, Abingdon (United Kingdom). JET Joint Undertaking; Svensson, J. [Royal Inst. of Tech., Stockholm (Sweden)
1994-07-01
A back-propagation neural network technique is used at JET to extract plasma parameters like ion temperature, rotation velocities or spectral line intensities from charge exchange (CX) spectra. It is shown that in the case of the C VI CX spectra, neural networks can give a good estimation (better than +-20% accuracy) for the main plasma parameters (Ti, V{sub rot}). Since the neural network approach involves no iterations or initial guesses the speed with which a spectrum is processed is so high (0.2 ms/spectrum) that real time analysis will be achieved in the near future. 4 refs., 8 figs.
A Constructive Algorithm for Feedforward Neural Networks for Medical Diagnostic Reasoning
Siddiquee, Abu Bakar; Kamruzzaman, S M
2010-01-01
This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. Our research describes a constructive neural network algorithm with backpropagation; offer an approach for the incremental construction of nearminimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. Our algorithm was tested on several benchmarking classification problems including Cancer1, Heart, and Diabetes with good generalization ability.
Usage of neural network for the prediction of surface roughness after the roller burnishing
Directory of Open Access Journals (Sweden)
I. Stanković
2012-04-01
Full Text Available In order to increase productivity, machining times and market competitiveness of machining production systems, it is important to continuously develop existing technological solutions. This article describes the usage of the neural network for the prediction of surface roughness after the roller burnishing. Since the observed problem is multidimensional with several input parameters and one output parameter and since nonlinearity and complexity of parameter correlation, there was used the backpropagation neural network algorithm. Empirical and experimental values of input and output parameters were used as initial values for the learning of the neural network. Developed neural network model with its results can be used for easier implementation of further roller burnishing process plans.
Neural Network Analysis of Acoustic Emission Signals for Drill Wear Monitoring
International Nuclear Information System (INIS)
The objective of the proposed study is to produce a tool-condition monitoring (TCM) strategy that will lead to a more efficient and economical drilling tool usage. Drill-wear monitoring is an important attribute in the automatic cutting processes as it can help preventing damages of the tools and workpieces and optimizing the tool usage. This study presents the architectures of a multi-layer feed-forward neural network with back-propagation training algorithm for the monitoring of drill wear. The input features to the neural networks were extracted from the AE signals using the wavelet transform analysis. Training and testing were performed under a moderate range of cutting conditions in the dry drilling of steel plates. The results indicated that the extracted input features from AE signals to the supervised neural networks were effective for drill wear monitoring and the output of the neural networks could be utilized for the tool life management planning.
Neural networks: genuine artifical intelligence. Neurale netwerken: echte kunstmatige intelligentie
Energy Technology Data Exchange (ETDEWEB)
Jongepier, A.G. (KEMA NV, Arnhem (Netherlands))
Artificial neural networks are a new form of artificial intelligence. At this moment KEMA NV is examining the possibilities of applying artificial neural networks to processes that are related to power systems. A number of applications already gives hopeful results. Artificial neural networks are suited to pattern recognition. If a problem can be formulated in terms of pattern recognition, an artificial neural network may give a valuable contribution to the solution of this problem. 8 figs., 15 refs.
Beam pattern evaluation for cyclotron operations based on neural networks
International Nuclear Information System (INIS)
A beam pattern evaluation method using neural network has been developed to assist non-expert cyclotron operators. While an expert operator can easily tell beam accelerating conditions by the beam pattern measured by a scanned beam probe, it is not easy for non-expert operators to evaluate the pattern. The followings are the summarized procedure of the proposed method. First, the features of the beam patterns, which correspond to the view points of the experts, are extracted using Gabor expansion. A neural network algorithm is applied to calculate the Gabor expansion. Next, the number of the extracted features is reduced by averaging the features of high frequency ranges in five partial zones. The idea of this process is based on the fact that the operators do not pay attention to the details of the high frequency components of the patterns. Finally, the pattern evaluation process by the expert operators is learned by the back-propagation algorithm on a multi-layered feed forward neural network. Parallel processing architecture of the feature extraction network, and the learning capability of the non-linear clustering network are very useful for the evaluation model of beam patterns. (author)
Complex-Valued Neural Networks
Hirose, Akira
2012-01-01
This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...
Novel maximum-margin training algorithms for supervised neural networks.
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
An improved neural networks for stereo-camera calibration
Directory of Open Access Journals (Sweden)
Y.J. Xing
2007-01-01
Full Text Available Purpose: Improve the generalization capability and speed of back-propagation neural network (BPNN.Design/methodology/approach: In this paper, CCD cameras are calibrated implicitly using BP neural networkby means of its ability to fit the complicated nonlinear mapping relation. Conventional BP algorithms easily fallinto part-infinitesimal, slowing speed of convergence and exorbitance training that will influence the trainingresult, delay convergence time and debase generalization capability. During our experiments, dense sample dataare acquired by using high precisely numerical control platform, and the variances error (PVE is adopted duringtraining the neural network.Findings: Experiments indicate that the neural network used PVE has great generalization. The error percentagesobtained from our set-up are limitedly better than those obtained through Mean Square Error (MSE. The systemis generalization enough for most machine-vision applications and the calibrated system can reach acceptableprecision of 3D measurement standard.Research limitations/implications: The value needs to be decided by experiments, and the reconstructionimages will be distorted if the value is more than 6.Originality/value: The variances error is be adopted in BPNN first.
Fuzzy neural networks for classification and detection of anomalies.
Meneganti, M; Saviello, F S; Tagliaferri, R
1998-01-01
In this paper, a new learning algorithm for the Simpson's fuzzy min-max neural network is presented. It overcomes some undesired properties of the Simpson's model: specifically, in it there are neither thresholds that bound the dimension of the hyperboxes nor sensitivity parameters. Our new algorithm improves the network performance: in fact, the classification result does not depend on the presentation order of the patterns in the training set, and at each step, the classification error in the training set cannot increase. The new neural model is particularly useful in classification problems as it is shown by comparison with some fuzzy neural nets cited in literature (Simpson's min-max model, fuzzy ARTMAP proposed by Carpenter, Grossberg et al. in 1992, adaptive fuzzy systems as introduced by Wang in his book) and the classical multilayer perceptron neural network with backpropagation learning algorithm. The tests were executed on three different classification problems: the first one with two-dimensional synthetic data, the second one with realistic data generated by a simulator to find anomalies in the cooling system of a blast furnace, and the third one with real data for industrial diagnosis. The experiments were made following some recent evaluation criteria known in literature and by using Microsoft Visual C++ development environment on personal computers. PMID:18255771
Learning Sensor Multiplexing Design through Back-propagation
Chakrabarti, Ayan
2016-01-01
Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step further---to learn camera sensor designs jointly with networks that carry out inference on the images they capture. In this paper, we specifically consider the design and inference...
Fuzzy Neural Networks for water level and discharge forecasting
Alvisi, Stefano; Franchini, Marco
2010-05-01
A new procedure for water level (or discharge) forecasting under uncertainty using artificial neural networks is proposed: uncertainty is expressed in the form of a fuzzy number. For this purpose, the parameters of the neural network, namely, the weights and biases, are represented by fuzzy numbers rather than crisp numbers. Through the application of the extension principle, the fuzzy number representative of the output variable (water level or discharge) is then calculated at each time step on the basis of a set of crisp inputs and fuzzy parameters of the neural network. The proposed neural network thus allows uncertainty to be taken into account at the forecasting stage not providing only deterministic or crisp predictions, but rather predictions in terms of 'the discharge (or level) will fall between two values, indicated according to the level of credibility considered, whereas it will take on a certain value when the level of credibility is maximum'. The fuzzy parameters of the neural network are estimated using a calibration procedure that imposes a constraint whereby for an assigned h-level the envelope of the corresponding intervals representing the outputs (forecasted levels or discharges, calculated at different points in time) must include a prefixed percentage of observed values. The proposed model is applied to two different case studies. Specifically, the data related to the first case study are used to develop and test a flood event-based water level forecasting model, whereas the data related to the latter are used for continuous discharge forecasting. The results obtained are compared with those provided by other data-driven models - Bayesian neural networks (Neal, R.M. 1992, Bayesian training of backpropagation networks by the hybrid Monte Carlo method. Tech. Rep. CRG-TR-92-1, Dep. of Comput. Sci., Univ. of Toronto, Toronto, Ont., Canada.) and the Local Uncertainty Estimation Model (Shrestha D.L. and Solomatine D.P. 2006, Machine learning
Phase Transitions of Neural Networks
Kinzel, Wolfgang
1997-01-01
The cooperative behaviour of interacting neurons and synapses is studied using models and methods from statistical physics. The competition between training error and entropy may lead to discontinuous properties of the neural network. This is demonstrated for a few examples: Perceptron, associative memory, learning from examples, generalization, multilayer networks, structure recognition, Bayesian estimate, on-line training, noise estimation and time series generation.
COCOMO Estimates Using Neural Networks
Directory of Open Access Journals (Sweden)
Anupama Kaushik
2012-08-01
Full Text Available Software cost estimation is an important phase in software development. It predicts the amount of effort and development time required to build a software system. It is one of the most critical tasks and an accurate estimate provides a strong base to the development procedure. In this paper, the most widely used software cost estimation model, the Constructive Cost Model (COCOMO is discussed. The model is implemented with the help of artificial neural networks and trained using the perceptron learning algorithm. The COCOMO dataset is used to train and to test the network. The test results from the trained neural network are compared with that of the COCOMO model. The aim of our research is to enhance the estimation accuracy of the COCOMO model by introducing the artificial neural networks to it.
Neural Networks and Database Systems
Schikuta, Erich
2008-01-01
Object-oriented database systems proved very valuable at handling and administrating complex objects. In the following guidelines for embedding neural networks into such systems are presented. It is our goal to treat networks as normal data in the database system. From the logical point of view, a neural network is a complex data value and can be stored as a normal data object. It is generally accepted that rule-based reasoning will play an important role in future database applications. The knowledge base consists of facts and rules, which are both stored and handled by the underlying database system. Neural networks can be seen as representation of intensional knowledge of intelligent database systems. So they are part of a rule based knowledge pool and can be used like conventional rules. The user has a unified view about his knowledge base regardless of the origin of the unique rules.
Transient stability analysis of electric energy systems via a fuzzy ART-ARTMAP neural network
Energy Technology Data Exchange (ETDEWEB)
Ferreira, Wagner Peron; Silveira, Maria do Carmo G.; Lotufo, AnnaDiva P.; Minussi, Carlos. R. [Department of Electrical Engineering, Sao Paulo State University (UNESP), P.O. Box 31, 15385-000, Ilha Solteira, SP (Brazil)
2006-04-15
This work presents a methodology to analyze transient stability (first oscillation) of electric energy systems, using a neural network based on ART architecture (adaptive resonance theory), named fuzzy ART-ARTMAP neural network for real time applications. The security margin is used as a stability analysis criterion, considering three-phase short circuit faults with a transmission line outage. The neural network operation consists of two fundamental phases: the training and the analysis. The training phase needs a great quantity of processing for the realization, while the analysis phase is effectuated almost without computation effort. This is, therefore the principal purpose to use neural networks for solving complex problems that need fast solutions, as the applications in real time. The ART neural networks have as primordial characteristics the plasticity and the stability, which are essential qualities to the training execution and to an efficient analysis. The fuzzy ART-ARTMAP neural network is proposed seeking a superior performance, in terms of precision and speed, when compared to conventional ARTMAP, and much more when compared to the neural networks that use the training by backpropagation algorithm, which is a benchmark in neural network area. (author)
Prediction of metal corrosion using feed-forward neural networks
International Nuclear Information System (INIS)
The reliable prediction of corrosion behavior for the effective control of corrosion is a fundamental requirement. Since real world corrosion never seems to involve quite the same conditions that have previously been tested, using corrosion literature does not provide the necessary answers. In order to provide a methodology for predicting corrosion in real and complex situations, artificial neural networks can be utilized. Feed-forward artificial neural network (FFANN) is an information-processing paradigm inspired by the way the densely interconnected, parallel structure of the human brain process information.The aim of the present work is to predict corrosion behavior in critical conditions, such as industrial applications, based on some laboratory experimental data. Electrochemical behavior of stainless steel in different conditions were studied, using polarization technique and Tafel curves. Back-propagation neural networks models were developed to predict the corrosion behavior. The trained networks result in predicted value in good comparison to the experimental data. They have generally been claimed to be successful in modeling the corrosion behavior. The results are presented in two tables. Table 1 gives corrosion behavior of stainless-steel as a function of pH and CuSO4 concentration and table 2 gives corrosion behavior of stainless - steel as a function of electrode surface area and CuSO4 concentration. (authors)
Optoelectronic Systems Trained With Backpropagation Through Time.
Hermans, Michiel; Dambre, Joni; Bienstman, Peter
2015-07-01
Delay-coupled optoelectronic systems form promising candidates to act as powerful information processing devices. In this brief, we consider such a system that has been studied before in the context of reservoir computing (RC). Instead of viewing the system as a random dynamical system, we see it as a true machine-learning model, which can be fully optimized. We use a recently introduced extension of backpropagation through time, an optimization algorithm originally designed for recurrent neural networks, and use it to let the network perform a difficult phoneme recognition task. We show that full optimization of all system parameters of delay-coupled optoelectronics systems yields a significant improvement over the previously applied RC approach. PMID:25137733
Macroeconomics modelling on UK GDP growth by neural computing
Li, Y.; Ng, K. C.; Häußler, A.; Chow, V; Muscatelli, A
1995-01-01
This paper presents multilayer neural networks used in UK gross domestic product estimation. These networks are trained by backpropagation and genetic algorithm based methods. Different from backpropagation guided by gradients of the performance, the genetic algorithm directly evaluates the performance of multiple sets of neural networks in parallel and then uses the analysed results to breed new networks that tend to be better suited to the problems in hand. It is shown that this guided evol...
International Nuclear Information System (INIS)
Highlights: ► We obtained models for estimation of cetane number of biodiesel. ► Twenty-four neural networks using two topologies were evaluated. ► The best neural network for predict the cetane number was selected. ► The best accuracy was obtained for the selected neural network. - Abstract: Models for estimation of cetane number of biodiesel from their fatty acid methyl ester composition using multiple linear regression and artificial neural networks were obtained in this work. For the obtaining of models to predict the cetane number, an experimental data from literature reports that covers 48 and 15 biodiesels in the modeling-training step and validation step respectively were taken. Twenty-four neural networks using two topologies and different algorithms for the second training step were evaluated. The model obtained using multiple regression was compared with two other models from literature and it was able to predict cetane number with 89% of accuracy, observing one outlier. A model to predict cetane number using artificial neural network was obtained with better accuracy than 92% except one outlier. The best neural network to predict the cetane number was a backpropagation network (11:5:1) using the Levenberg–Marquardt algorithm for the second step of the networks training and showing R = 0.9544 for the validation data.
Neural networks and wavelet analysis in the computer interpretation of pulse oximetry data
Energy Technology Data Exchange (ETDEWEB)
Dowla, F.U.; Skokowski, P.G.; Leach, R.R. Jr.
1996-03-01
Pulse oximeters determine the oxygen saturation level of blood by measuring the light absorption of arterial blood. The sensor consists of red and infrared light sources and photodetectors. A method based on neural networks and wavelet analysis is developed for improved saturation estimation in the presence of sensor motion. Spectral and correlation functions of the dual channel oximetry data are used by a backpropagation neural network to characterize the type of motion. Amplitude ratios of red to infrared signals as a function of time scale are obtained from the multiresolution wavelet decomposition of the two-channel data. Motion class and amplitude ratios are then combined to obtain a short-time estimate of the oxygen saturation level. A final estimate of oxygen saturation is obtained by applying a 15 s smoothing filter on the short-time measurements based on 3.5 s windows sampled every 1.75 s. The design employs two backpropagation neural networks. The first neural network determines the motion characteristics and the second network determines the saturation estimate. Our approach utilizes waveform analysis in contrast to the standard algorithms that are based on the successful detection of peaks and troughs in the signal. The proposed algorithm is numerically efficient and has stable characteristics with a reduced false alarm rate with a small loss in detection. The method can be rapidly developed on a digital signal processing platform.
Video Compression Using Neural Network
Directory of Open Access Journals (Sweden)
Sangeeta Mishra
2012-08-01
Full Text Available Apart from the existing technology on image compression represented by series of JPEG, MPEG and H.26x standards, new technology such as neural networks and genetic algorithms are being developed to explore the future of image coding. Successful applications of neural networks to basic propagation algorithm have now become well established and other aspects of neural network involvement in this technology. In this paper different algorithms were implemented like gradient descent back propagation, gradient descent with momentum back propagation, gradient descent with adaptive learning back propagation, gradient descent with momentum and adaptive learning back propagation and Levenberg-Marquardt algorithm. The size of original video clip is 25MB and after compression it becomes 21.3MB giving the compression ratio as 85.2% and compression factor of 1.174. It was observed that the size remains same after compression but the difference is in the clarity.
Neural networks in signal processing
International Nuclear Information System (INIS)
Nuclear Engineering has matured during the last decade. In research and design, control, supervision, maintenance and production, mathematical models and theories are used extensively. In all such applications signal processing is embedded in the process. Artificial Neural Networks (ANN), because of their nonlinear, adaptive nature are well suited to such applications where the classical assumptions of linearity and second order Gaussian noise statistics cannot be made. ANN's can be treated as nonparametric techniques, which can model an underlying process from example data. They can also adopt their model parameters to statistical change with time. Algorithms in the framework of Neural Networks in Signal processing have found new applications potentials in the field of Nuclear Engineering. This paper reviews the fundamentals of Neural Networks in signal processing and their applications in tasks such as recognition/identification and control. The topics covered include dynamic modeling, model based ANN's, statistical learning, eigen structure based processing and generalization structures. (orig.)
Chi-Cheong Chris Wong; Man-Chung Chan; Chi-Chung Lam
2000-01-01
Multilayer neural network has been successfully applied to the time series forecasting. Backpropagation, a popular learning algorithm, converges slowly and has the difficulty in determining the network parameters. In this paper, conjugate gradient learning algorithm with restart procedure is introduced to overcome these problems. Also, the commonly used random weight initialization does not guarantee to generate a set of initial connection weights close to the optimal weights leading to slow ...
Lure, Y. M. Fleming; Grody, Norman C.; Chiou, Y. S. Peter; Yeh, H. Y. Michael
1993-01-01
A data fusion system with artificial neural networks (ANN) is used for fast and accurate classification of five earth surface conditions and surface changes, based on seven SSMI multichannel microwave satellite measurements. The measurements include brightness temperatures at 19, 22, 37, and 85 GHz at both H and V polarizations (only V at 22 GHz). The seven channel measurements are processed through a convolution computation such that all measurements are located at same grid. Five surface classes including non-scattering surface, precipitation over land, over ocean, snow, and desert are identified from ground-truth observations. The system processes sensory data in three consecutive phases: (1) pre-processing to extract feature vectors and enhance separability among detected classes; (2) preliminary classification of Earth surface patterns using two separate and parallely acting classifiers: back-propagation neural network and binary decision tree classifiers; and (3) data fusion of results from preliminary classifiers to obtain the optimal performance in overall classification. Both the binary decision tree classifier and the fusion processing centers are implemented by neural network architectures. The fusion system configuration is a hierarchical neural network architecture, in which each functional neural net will handle different processing phases in a pipelined fashion. There is a total of around 13,500 samples for this analysis, of which 4 percent are used as the training set and 96 percent as the testing set. After training, this classification system is able to bring up the detection accuracy to 94 percent compared with 88 percent for back-propagation artificial neural networks and 80 percent for binary decision tree classifiers. The neural network data fusion classification is currently under progress to be integrated in an image processing system at NOAA and to be implemented in a prototype of a massively parallel and dynamically reconfigurable Modular
Relations Between Wavelet Network and Feedforward Neural Network
Institute of Scientific and Technical Information of China (English)
刘志刚; 何正友; 钱清泉
2002-01-01
A comparison of construction forms and base functions is made between feedforward neural network and wavelet network. The relations between them are studied from the constructions of wavelet functions or dilation functions in wavelet network by different activation functions in feedforward neural network. It is concluded that some wavelet function is equal to the linear combination of several neurons in feedforward neural network.
Applications of a new neural network to on-line voltage stability assessment
International Nuclear Information System (INIS)
Voltage stability problems have been one of the major concerns for electric utilities as a result of system heavy loading. This paper reports on an investigation on the application of a new neural network in on-line voltage stability assessment. The proposed neural network is a functional link net with an efficient functional expansion model for learning. This neural network is used for estimation of voltage stability margins. A comparison between the proposed neural network and a multi-layer percept ron with standard error back-propagation learning is presented, which indicates efficiency of this neural network. Based on the energy method, a direct mapping relation between system loading conditions and the voltage stability margins is set up via the designed neural network. A systematic method for selecting the neural networks input variables was developed using sensitivity analysis. The proposed method has been tested on the IEEE test systems and a portion of the Iran's power system network. Obtained results confirm the validity of the developed approach
Modeling of methane emissions using artificial neural network approach
Directory of Open Access Journals (Sweden)
Stamenković Lidija J.
2015-01-01
Full Text Available The aim of this study was to develop a model for forecasting CH4 emissions at the national level, using Artificial Neural Networks (ANN with broadly available sustainability, economical and industrial indicators as their inputs. ANN modeling was performed using two different types of architecture; a Backpropagation Neural Network (BPNN and a General Regression Neural Network (GRNN. A conventional multiple linear regression (MLR model was also developed in order to compare model performance and assess which model provides the best results. ANN and MLR models were developed and tested using the same annual data for 20 European countries. The ANN model demonstrated very good performance, significantly better than the MLR model. It was shown that a forecast of CH4 emissions at the national level using the ANN model can be made successfully and accurately for a future period of up to two years, thereby opening the possibility to apply such a modeling technique which can be used to support the implementation of sustainable development strategies and environmental management policies. [Projekat Ministarstva nauke Republike Srbije, br. 172007
Incremental communication for multilayer neural networks: error analysis.
Ghorbani, A A; Bhavsar, V C
1998-01-01
Artificial neural networks (ANNs) involve a large amount of internode communications. To reduce the communication cost as well as the time of learning process in ANNs, we earlier proposed (1995) an incremental internode communication method. In the incremental communication method, instead of communicating the full magnitude of the output value of a node, only the increment or decrement to its previous value is sent to a communication link. In this paper, the effects of the limited precision incremental communication method on the convergence behavior and performance of multilayer neural networks are investigated. The nonlinear aspects of representing the incremental values with reduced (limited) precision for the commonly used error backpropagation training algorithm are analyzed. It is shown that the nonlinear effect of small perturbations in the input(s)/output of a node does not cause instability. The analysis is supported by simulation studies of two problems. The simulation results demonstrate that the limited precision errors are bounded and do not seriously affect the convergence of multilayer neural networks. PMID:18252431
Directory of Open Access Journals (Sweden)
Ming Xue
2013-06-01
Full Text Available As the forefront of complex nonlinear science and artificial intelligence science, artificial neural network has began to be applied in the field of water quality control and planning step by step. According to the fuzzy feature of water quality information, this paper proposes a membership degree Back-Propagation network (MDBP for water quality assessment with combining fuzzy mathematics and artificial neural network. The proposed MDBP model combines the merits of artificial neural network method and fuzzy evaluation method, which overcomes effectively the shortcoming of other assessment methods. With improving the accuracy and reliability of the assessment method, the method has a higher flexibility than other conventional approach and its programs have a better adaptability and more convenient application. The assessment method is closer to the reality with considering the continuity of the changes of water quality environment.
Modeling and prediction of Turkey's electricity consumption using Artificial Neural Networks
International Nuclear Information System (INIS)
Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input-output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export-import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption.
Application of Neural Networks for unfolding neutron spectra measured by means of Bonner Spheres
International Nuclear Information System (INIS)
A Neural Network structure has been used for unfolding neutron spectra measured by means of a Bonner Sphere Spectrometer set. The present work used the 'Stuttgart Neural Network Simulator' as the interface for designing, training and validation of a MultiLayer Perceptron network. The back-propagation algorithm was applied. The Bonner Sphere set chosen has been calibrated at the National Physical Laboratory, United Kingdom, and uses gold activation foils as thermal neutron detectors. The neutron energy covered by the response functions goes from 0.0001 eV to 10 MeV. Two types of neutron spectra were numerically investigated: monoenergetic and continuous. Good results were obtained, indicating that the Neural Network can be considered an interesting alternative among the neutron spectrum unfolding methodologies
Modeling and prediction of Turkey's electricity consumption using Artificial Neural Networks
International Nuclear Information System (INIS)
Artificial Neural Networks are proposed to model and predict electricity consumption of Turkey. Multi layer perceptron with backpropagation training algorithm is used as the neural network topology. Tangent-sigmoid and pure-linear transfer functions are selected in the hidden and output layer processing elements, respectively. These input-output network models are a result of relationships that exist among electricity consumption and several other socioeconomic variables. Electricity consumption is modeled as a function of economic indicators such as population, gross national product, imports and exports. It is also modeled using export-import ratio and time input only. Performance comparison among different models is made based on absolute and percentage mean square error. Electricity consumption of Turkey is predicted until 2027 using data from 1975 to 2006 along with other economic indicators. The results show that electricity consumption can be modeled using Artificial Neural Networks, and the models can be used to predict future electricity consumption. (author)
Use of Neural Networks for Damage Assessment in a Steel Mast
DEFF Research Database (Denmark)
Kirkegaard, Poul Henning; Rytter, A.
In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with the Backpropagation Algorithm for detecting location and size of a damage in a civil engineering structure is investigated. The structure considered is a 20 m high steel lattice mast subjected to wind...... excitation. The basic idea is to train a neural network with simulated patterns of the relative changes in natural frequencies and corresponding sizes and locations of damages in order to recognize the behaviour of the damaged as well as the undamaged structure. Subjecting this trained neural network to...... bolted joint consists of 4 slice plates giving the possibilities of simulating a 1/4, 1/2, 3/4 and full reduction of the area of a diagonal. A damage is simulated by removing one or more splice plates in these bolted joints. The utility of the neural network approach is demonstrated by a simulation study...
Determining the confidence levels of sensor outputs using neural networks
International Nuclear Information System (INIS)
This paper describes an approach for determining the confidence level of a sensor output using multi-sensor arrays, sensor fusion and artificial neural networks. The authors have shown in previous work that sensor fusion and artificial neural networks can be used to learn the relationships between the outputs of an array of simulated partially selective sensors and the individual analyte concentrations in a mixture of analyses. Other researchers have shown that an array of partially selective sensors can be used to determine the individual gas concentrations in a gaseous mixture. The research reported in this paper shows that it is possible to extract confidence level information from an array of partially selective sensors using artificial neural networks. The confidence level of a sensor output is defined as a numeric value, ranging from 0% to 100%, that indicates the confidence associated with a output of a given sensor. A three layer back-propagation neural network was trained on a subset of the sensor confidence level space, and was tested for its ability to generalize, where the confidence level space is defined as all possible deviations from the correct sensor output. A learning rate of 0.1 was used and no momentum terms were used in the neural network. This research has shown that an artificial neural network can accurately estimate the confidence level of individual sensors in an array of partially selective sensors. This research has also shown that the neural network's ability to determine the confidence level is influenced by the complexity of the sensor's response and that the neural network is able to estimate the confidence levels even if more than one sensor is in error. The fundamentals behind this research could be applied to other configurations besides arrays of partially selective sensors, such as an array of sensors separated spatially. An example of such a configuration could be an array of temperature sensors in a tank that is not in
Application of neural networks in coastal engineering
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.
the neural network attractive. A neural network is an information processing system modeled on the structure of the dynamic process. It can solve the complex/nonlinear problems quickly once trained by operating on problems using an interconnected number...
Plant Growth Models Using Artificial Neural Networks
Bubenheim, David
1997-01-01
In this paper, we descrive our motivation and approach to devloping models and the neural network architecture. Initial use of the artificial neural network for modeling the single plant process of transpiration is presented.
Ocean wave forecasting using recurrent neural networks
Digital Repository Service at National Institute of Oceanography (India)
Mandal, S.; Prabaharan, N.
, merchant vessel routing, nearshore construction, etc. more efficiently and safely. This paper describes an artificial neural network, namely recurrent neural network with rprop update algorithm and is applied for wave forecasting. Measured ocean waves off...
Neural network exploitation in reliability assurance
International Nuclear Information System (INIS)
The contribution deals with neural network application for the diagnostic system of the three-phase asynchronous electro motor. The case study is done and can be used as a model for the next application of neural network methodology.
Neural Networks for Flight Control
Jorgensen, Charles C.
1996-01-01
Neural networks are being developed at NASA Ames Research Center to permit real-time adaptive control of time varying nonlinear systems, enhance the fault-tolerance of mission hardware, and permit online system reconfiguration. In general, the problem of controlling time varying nonlinear systems with unknown structures has not been solved. Adaptive neural control techniques show considerable promise and are being applied to technical challenges including automated docking of spacecraft, dynamic balancing of the space station centrifuge, online reconfiguration of damaged aircraft, and reducing cost of new air and spacecraft designs. Our experiences have shown that neural network algorithms solved certain problems that conventional control methods have been unable to effectively address. These include damage mitigation in nonlinear reconfiguration flight control, early performance estimation of new aircraft designs, compensation for damaged planetary mission hardware by using redundant manipulator capability, and space sensor platform stabilization. This presentation explored these developments in the context of neural network control theory. The discussion began with an overview of why neural control has proven attractive for NASA application domains. The more important issues in control system development were then discussed with references to significant technical advances in the literature. Examples of how these methods have been applied were given, followed by projections of emerging application needs and directions.
Building a Chaotic Proved Neural Network
Bahi, Jacques M; Salomon, Michel
2011-01-01
Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.
Neural Network Adaptations to Hardware Implementations
Moerland, Perry,; Fiesler,Emile
1997-01-01
In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential.However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and ...
Neural Network Adaptations to Hardware Implementations
Moerland, Perry,; Fiesler,Emile; Beale, R
1997-01-01
In order to take advantage of the massive parallelism offered by artificial neural networks, hardware implementations are essential. However, most standard neural network models are not very suitable for implementation in hardware and adaptations are needed. In this section an overview is given of the various issues that are encountered when mapping an ideal neural network model onto a compact and reliable neural network hardware implementation, like quantization, handling nonuniformities and...
Neural networks and applications tutorial
Guyon, I.
1991-09-01
The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.
Deep Gate Recurrent Neural Network
Gao, Yuan; Glowacka, Dorota
2016-01-01
This paper introduces two recurrent neural network structures called Simple Gated Unit (SGU) and Deep Simple Gated Unit (DSGU), which are general structures for learning long term dependencies. Compared to traditional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), both structures require fewer parameters and less computation time in sequence classification tasks. Unlike GRU and LSTM, which require more than one gates to control information flow in the network, SGU and DSGU only...
Network Firewall using Artificial Neural Networks
Kristián Valentín; Michal Malý
2014-01-01
Today's most common firewalls are mostly rule-based. Their knowledge consists of a set of rules upon which they process received packets. They cannot do anything they have not been explicitly configured to do. This makes the system more straightforward to set up, but less flexible and less adaptive to changing circumstances. We will investigate a network firewall whose rule-base we will try to model using an artificial neural network, more specifically using a multi-layer perceptron (MLP) tra...
Modeling Slump of Ready Mix Concrete Using Genetically Evolved Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Vinay Chandwani
2014-01-01
Full Text Available Artificial neural networks (ANNs have been the preferred choice for modeling the complex and nonlinear material behavior where conventional mathematical approaches do not yield the desired accuracy and predictability. Despite their popularity as a universal function approximator and wide range of applications, no specific rules for deciding the architecture of neural networks catering to a specific modeling task have been formulated. The research paper presents a methodology for automated design of neural network architecture, replacing the conventional trial and error technique of finding the optimal neural network. The genetic algorithms (GA stochastic search has been harnessed for evolving the optimum number of hidden layer neurons, transfer function, learning rate, and momentum coefficient for backpropagation ANN. The methodology has been applied for modeling slump of ready mix concrete based on its design mix constituents, namely, cement, fly ash, sand, coarse aggregates, admixture, and water-binder ratio. Six different statistical performance measures have been used for evaluating the performance of the trained neural networks. The study showed that, in comparison to conventional trial and error technique of deciding the neural network architecture and training parameters, the neural network architecture evolved through GA was of reduced complexity and provided better prediction performance.
Artificial neural networks in medicine
Energy Technology Data Exchange (ETDEWEB)
Keller, P.E.
1994-07-01
This Technology Brief provides an overview of artificial neural networks (ANN). A definition and explanation of an ANN is given and situations in which an ANN is used are described. ANN applications to medicine specifically are then explored and the areas in which it is currently being used are discussed. Included are medical diagnostic aides, biochemical analysis, medical image analysis and drug development.
Medical Imaging with Neural Networks
International Nuclear Information System (INIS)
The objective of this paper is to provide an overview of the recent developments in the use of artificial neural networks in medical imaging. The areas of medical imaging that are covered include : ultrasound, magnetic resonance, nuclear medicine and radiological (including computerized tomography). (authors)
Aphasia Classification Using Neural Networks
DEFF Research Database (Denmark)
Axer, H.; Jantzen, Jan; Berks, G.;
2000-01-01
A web-based software model (http://fuzzy.iau.dtu.dk/aphasia.nsf) was developed as an example for classification of aphasia using neural networks. Two multilayer perceptrons were used to classify the type of aphasia (Broca, Wernicke, anomic, global) according to the results in some subtests of the...
Model Of Neural Network With Creative Dynamics
Zak, Michail; Barhen, Jacob
1993-01-01
Paper presents analysis of mathematical model of one-neuron/one-synapse neural network featuring coupled activation and learning dynamics and parametrical periodic excitation. Demonstrates self-programming, partly random behavior of suitable designed neural network; believed to be related to spontaneity and creativity of biological neural networks.
Simplified LQG Control with Neural Networks
DEFF Research Database (Denmark)
Sørensen, O.
1997-01-01
A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce a...
Artificial neural networks for plasma x-ray spectroscopic analysis
International Nuclear Information System (INIS)
Modern diagnostic instrumentation produces a vast amount of data that often requires substantial analysis efforts. New methods are needed to improve the efficiency of the analysis process. Artificial neural networks have been applied to a variety of signal processing and image recognition problems. The feed-forward, back-propagation technique is well suited for the analysis of scientific laboratory data, which is viewed as a pattern-matching problem. We summarize the concepts and algorithms as implemented on a personal computer, and illustrate the method using a nonlocal thermodynamic equilibrium theoretical atomic physics model for k-shell x-ray spectroscopy of a high density, high temperature aluminum plasma. Extensions to other types of spectroscopy data analysis are discussed
fMRI Segmentation Using Echo State Neural Network
Directory of Open Access Journals (Sweden)
D.Suganthi
2008-02-01
Full Text Available This research work proposes a new intelligent segmentation technique forfunctional Magnetic Resonance Imaging (fMRI. It has been implemented usingan Echostate Neural Network (ESN. Segmentation is an important process thathelps in identifying objects of the image. Existing segmentation methods are notable to exactly segment the complicated profile of the fMRI accurately.Segmentation of every pixel in the fMRI correctly helps in proper location oftumor. The presence of noise and artifacts poses a challenging problem in propersegmentation. The proposed ESN is an estimation method with energyminimization. The estimation property helps in better segmentation of thecomplicated profile of the fMRI. The performance of the new segmentationmethod is found to be better with higher peak signal to noise ratio (PSNR of 61when compared to the PSNR of the existing back-propagation algorithm (BPAsegmentation method which is 57.
Optical infrared flame detection system with neural networks
Huseynov, Javid J.; Baliga, Shankar B.
2007-09-01
A model for an infrared (IR) flame detection system using artificial neural networks (ANN) is presented. The joint time-frequency analysis (JTFA) in the form of a Short-Time Fourier Transform (STFT) is used for extracting relevant input features for a set of ANNs. Each ANN is trained using the backpropagation conjugate-gradient (CG) method to distinguish all hydrocarbon flames from a particular type of environmental nuisance and background noise. Signal saturation caused by the increased intensity of IR sources at closer distances is resolved by an adjustable gain control. A classification scheme with trained ANN connection weights was implemented on a digital signal processor for use in an industrial hydrocarbon flame detector.
Optical proximity correction using a multilayer perceptron neural network
International Nuclear Information System (INIS)
Optical proximity correction (OPC) is one of the resolution enhancement techniques (RETs) in optical lithography, where the mask pattern is modified to improve the output pattern fidelity. Algorithms are needed to generate the modified mask pattern automatically and efficiently. In this paper, a multilayer perceptron (MLP) neural network (NN) is used to synthesize the mask pattern. We employ the pixel-based approach in this work. The MLP takes the pixel values of the desired output wafer pattern as input, and outputs the optimal mask pixel values. The MLP is trained with the backpropagation algorithm, with a training set retrieved from the desired output pattern, and the optimal mask pattern obtained by the model-based method. After training, the MLP is able to generate the optimal mask pattern non-iteratively with good pattern fidelity. (paper)
Robust local stability of multilayer recurrent neural networks.
Suykens, J K; De Moor, B; Vandewalle, J
2000-01-01
In this paper we derive a condition for robust local stability of multilayer recurrent neural networks with two hidden layers. The stability condition follows from linking theory about linearization, robustness analysis of linear systems under nonlinear perturbation and matrix inequalities. A characterization of the basin of attraction of the origin is given in terms of the level set of a quadratic Lyapunov function. In a similar way like for NL theory, local stability is imposed around the origin and the apparent basin of attraction is made large by applying the criterion, while the proven basin of attraction is relatively small due to conservatism of the criterion. Modifying dynamic backpropagation by the new stability condition is discussed and illustrated by simulation examples. PMID:18249754
Optical proximity correction using a multilayer perceptron neural network
Luo, Rui
2013-07-01
Optical proximity correction (OPC) is one of the resolution enhancement techniques (RETs) in optical lithography, where the mask pattern is modified to improve the output pattern fidelity. Algorithms are needed to generate the modified mask pattern automatically and efficiently. In this paper, a multilayer perceptron (MLP) neural network (NN) is used to synthesize the mask pattern. We employ the pixel-based approach in this work. The MLP takes the pixel values of the desired output wafer pattern as input, and outputs the optimal mask pixel values. The MLP is trained with the backpropagation algorithm, with a training set retrieved from the desired output pattern, and the optimal mask pattern obtained by the model-based method. After training, the MLP is able to generate the optimal mask pattern non-iteratively with good pattern fidelity.
Neural Network Aided Glitch-Burst Discrimination and Glitch Classification
Rampone, Salvatore; Troiano, Luigi; Pinto, Innocenzo M
2014-01-01
We investigate the potential of neural-network based classifiers for discriminating gravitational wave bursts (GWBs) of a given canonical family (e.g. core-collapse supernova waveforms) from typical transient instrumental artifacts (glitches), in the data of a single detector. The further classification of glitches into typical sets is explored.In order to provide a proof of concept,we use the core-collapse supernova waveform catalog produced by H. Dimmelmeier and co-Workers, and the data base of glitches observed in laser interferometer gravitational wave observatory (LIGO) data maintained by P. Saulson and co-Workers to construct datasets of (windowed) transient waveforms (glitches and bursts) in additive (Gaussian and compound-Gaussian) noise with different signal-tonoise ratios (SNR). Principal component analysis (PCA) is next implemented for reducing data dimensionality, yielding results consistent with, and extending those in the literature. Then, a multilayer perceptron is trained by a backpropagation ...
Prediction of the plasma distribution using an artificial neural network
International Nuclear Information System (INIS)
In this work, an artificial neural network (ANN) model is established using a back-propagation training algorithm in order to predict the plasma spatial distribution in an electron cyclotron resonance (ECR) — plasma-enhanced chemical vapor deposition (PECVD) plasma system. In our model, there are three layers: the input layer, the hidden layer and the output layer. The input layer is composed of five neurons: the radial position, the axial position, the gas pressure, the microwave power and the magnet coil current. The output layer is our target output neuron: the plasma density. The accuracy of our prediction is tested with the experimental data obtained by a Langmuir probe, and ANN results show a good agreement with the experimental data. It is concluded that ANN is a useful tool in dealing with some nonlinear problems of the plasma spatial distribution
The annealing robust backpropagation (ARBP) learning algorithm.
Chuang, C C; Su, S F; Hsiao, C C
2000-01-01
Multilayer feedforward neural networks are often referred to as universal approximators. Nevertheless, if the used training data are corrupted by large noise, such as outliers, traditional backpropagation learning schemes may not always come up with acceptable performance. Even though various robust learning algorithms have been proposed in the literature, those approaches still suffer from the initialization problem. In those robust learning algorithms, the so-called M-estimator is employed. For the M-estimation type of learning algorithms, the loss function is used to play the role in discriminating against outliers from the majority by degrading the effects of those outliers in learning. However, the loss function used in those algorithms may not correctly discriminate against those outliers. In this paper, the annealing robust backpropagation learning algorithm (ARBP) that adopts the annealing concept into the robust learning algorithms is proposed to deal with the problem of modeling under the existence of outliers. The proposed algorithm has been employed in various examples. Those results all demonstrated the superiority over other robust learning algorithms independent of outliers. In the paper, not only is the annealing concept adopted into the robust learning algorithms but also the annealing schedule k/t was found experimentally to achieve the best performance among other annealing schedules, where k is a constant and is the epoch number. PMID:18249835
Çebi, A.; Akdoğan, E.; Celen, A.; Dalkilic, A. S.
2016-06-01
An artificial neural network (ANN) model of friction factor in smooth and microfin tubes under heating, cooling and isothermal conditions was developed in this study. Data used in ANN was taken from a vertically positioned heat exchanger experimental setup. Multi-layered feed-forward neural network with backpropagation algorithm, radial basis function networks and hybrid PSO-neural network algorithm were applied to the database. Inputs were the ratio of cross sectional flow area to hydraulic diameter, experimental condition number depending on isothermal, heating, or cooling conditions and mass flow rate while the friction factor was the output of the constructed system. It was observed that such neural network based system could effectively predict the friction factor values of the flows regardless of their tube types. A dependency analysis to determine the strongest parameter that affected the network and database was also performed and tube geometry was found to be the strongest parameter of all as a result of analysis.
Taufikurrahman, Mohammad
2015-01-01
Neural networks is one of method which suitable for used to predict the time series data which include volatile. This research has been finished by using software Matlab 7.10.0 (R2010a). The research used the model neural network backpropagation. The aim to predict exchange rate Rupiah to Dollar U.S in 2014 from the research, discussion and the data process. To get exchange rate Rupiah for Dollar U.S in 2014 is 12.111,09.
A Software Package for Neural Network Applications Development
Baran, Robert H.
1993-01-01
Original Backprop (Version 1.2) is an MS-DOS package of four stand-alone C-language programs that enable users to develop neural network solutions to a variety of practical problems. Original Backprop generates three-layer, feed-forward (series-coupled) networks which map fixed-length input vectors into fixed length output vectors through an intermediate (hidden) layer of binary threshold units. Version 1.2 can handle up to 200 input vectors at a time, each having up to 128 real-valued components. The first subprogram, TSET, appends a number (up to 16) of classification bits to each input, thus creating a training set of input output pairs. The second subprogram, BACKPROP, creates a trilayer network to do the prescribed mapping and modifies the weights of its connections incrementally until the training set is leaned. The learning algorithm is the 'back-propagating error correction procedures first described by F. Rosenblatt in 1961. The third subprogram, VIEWNET, lets the trained network be examined, tested, and 'pruned' (by the deletion of unnecessary hidden units). The fourth subprogram, DONET, makes a TSR routine by which the finished product of the neural net design-and-training exercise can be consulted under other MS-DOS applications.
BACKPROPAGATION TRAINING ALGORITHM WITH ADAPTIVE PARAMETERS TO SOLVE DIGITAL PROBLEMS
Directory of Open Access Journals (Sweden)
R. Saraswathi
2011-01-01
Full Text Available An efficient technique namely Backpropagation training with adaptive parameters using Lyapunov Stability Theory for training single hidden layer feed forward network is proposed. A three-layered Feedforward neural network architecture is used to solve the selected problems. Sequential Training Mode is used to train the network. Lyapunov stability theory is employed to ensure the faster and steady state error convergence and to construct and energy surface with a single global minimum point through the adaptive adjustment of the weights and the adaptive parameter ß. To avoid local minima entrapment, an adaptive backpropagation algorithm based on Lyapunov stability theory is used. Lyapunov stability theory gives the algorithm, the efficiency of attaining a single global minimum point. The learning parameters used in this algorithm is responsible for the faster error convergence. The adaptive learning parameter used in this algorithm is chosen properly for faster error convergence. The error obtained has been asymptotically converged to zero according to Lyapunov Stability theory. The performance of the adaptive Backpropagation algorithm is measured by solving parity problem, half adder and full adder problems.
Data acquisition in modeling using neural networks and decision trees
Directory of Open Access Journals (Sweden)
R. Sika
2011-04-01
Full Text Available The paper presents a comparison of selected models from area of artificial neural networks and decision trees in relation with actualconditions of foundry processes. The work contains short descriptions of used algorithms, their destination and method of data preparation,which is a domain of work of Data Mining systems. First part concerns data acquisition realized in selected iron foundry, indicating problems to solve in aspect of casting process modeling. Second part is a comparison of selected algorithms: a decision tree and artificial neural network, that is CART (Classification And Regression Trees and BP (Backpropagation in MLP (Multilayer Perceptron networks algorithms.Aim of the paper is to show an aspect of selecting data for modeling, cleaning it and reducing, for example due to too strong correlationbetween some of recorded process parameters. Also, it has been shown what results can be obtained using two different approaches:first when modeling using available commercial software, for example Statistica, second when modeling step by step using Excel spreadsheetbasing on the same algorithm, like BP-MLP. Discrepancy of results obtained from these two approaches originates from a priorimade assumptions. Mentioned earlier Statistica universal software package, when used without awareness of relations of technologicalparameters, i.e. without user having experience in foundry and without scheduling ranks of particular parameters basing on acquisition, can not give credible basis to predict the quality of the castings. Also, a decisive influence of data acquisition method has been clearly indicated, the acquisition should be conducted according to repetitive measurement and control procedures. This paper is based on about 250 records of actual data, for one assortment for 6 month period, where only 12 data sets were complete (including two that were used for validation of neural network and useful for creating a model. It is definitely too
Directory of Open Access Journals (Sweden)
Vikas Kumar
2012-09-01
Full Text Available This paper comparator networks - a well-known modelof parallel computation. This model is used extensivelyfor keys arrangement tasks such as sorting and selection.This work investigates several aspects of comparatornetworks. It starts with presenting handy tools foranalysis of comparator networks in the form ofconclusive sets - non-binary vectors that verify a specificfunctionality. The 0-1 principle introduced by Knuthstates that a comparator network is a sorting network ifand only if it sorts all binary inputs. Hence, it points out acertain binary conclusive set. We compare these twomodels by considering several 0-1 -like principles andshow that the min-max model is the ‘strongest’ model ofcomputation which obeys our principles. That is, if afunction is computable in a model of computation inwhich any of these principles holds, a min-max networkcan compute this function.
A BP neural network model for sea state recognition using laser altimeter
Shi, Chun-bo; Jia, Xiao-dong; Li, Sheng; Wang, Zhen
2009-07-01
A BP neural network method for the recognition of sea state in laser altimeter is presented in this paper. Sea wave is the typical stochastic disturbance factor of laser altimeter effecting on low-altitude defense penetration of the intelligent antiship missiles, the recognition of sea state is studied in order to satisfy the practical needs of flying over the ocean. The BP neural network fed with the feature vector of laser range-measurement presents the analysis of features and outputs the estimation result of sea state. The two most distinguishing features are the mean and the variance of the sea echo, which are extracted from the distance characteristics of sea echo using general theory of statistics. The use of a feedforward network trained with the back-propagation algorithm is also investigated. The BP neural network is trained using sample data set to the neural network, and then the BP neural network trained is tested to recognize the sea state waiting for the classification. The network output shows the recognition accuracy of the model can up to 88%, and the results of tests show that the BP neural network model for the recognition of sea state is feasible and effective.
A NOVEL INTRUSION DETECTION MODE BASED ON UNDERSTANDABLE NEURAL NETWORK TREES
Institute of Scientific and Technical Information of China (English)
Xu Qinzhen; Yang Luxi; Zhao Qiangfu; He Zhenya
2006-01-01
Several data mining techniques such as Hidden Markov Model (HMM), artificial neural network,statistical techniques and expert systems are used to model network packets in the field of intrusion detection.In this paper a novel intrusion detection mode based on understandable Neural Network Tree (NNTree) is presented. NNTree is a modular neural network with the overall structure being a Decision Tree (DT), and each non-terminal node being an Expert Neural Network (ENN). One crucial advantage of using NNTrees is that they keep the non-symbolic model ENN's capability of learning in changing environments. Another potential advantage of using NNTrees is that they are actually "gray boxes" as they can be interpreted easily ifthe number of inputs for each ENN is limited. We showed through experiments that the trained NNTree achieved a simple ENN at each non-terminal node as well as a satisfying recognition rate of the network packets dataset.We also compared the performance with that of a three-layer backpropagation neural network. Experimental results indicated that the NNTree based intrusion detection model achieved better performance than the neural network based intrusion detection model.
Neural Networks and Photometric Redshifts
Tagliaferri, R; Andreon, S; Capozziello, S; Donalek, C; Giordano, G; Tagliaferri, Roberto; Longo, Giuseppe; Andreon, Stefano; Capozziello, Salvatore; Donalek, Ciro; Giordano, Gerardo
2002-01-01
We present a neural network based approach to the determination of photometric redshift. The method was tested on the Sloan Digital Sky Survey Early Data Release (SDSS-EDR) reaching an accuracy comparable and, in some cases, better than SED template fitting techniques. Different neural networks architecture have been tested and the combination of a Multi Layer Perceptron with 1 hidden layer (22 neurons) operated in a Bayesian framework, with a Self Organizing Map used to estimate the accuracy of the results, turned out to be the most effective. In the best experiment, the implemented network reached an accuracy of 0.020 (interquartile error) in the range 0
Evaluation of convolutional neural networks for visual recognition.
Nebauer, C
1998-01-01
Convolutional neural networks provide an efficient method to constrain the complexity of feedforward neural networks by weight sharing and restriction to local connections. This network topology has been applied in particular to image classification when sophisticated preprocessing is to be avoided and raw images are to be classified directly. In this paper two variations of convolutional networks--neocognitron and a modification of neocognitron--are compared with classifiers based on fully connected feedforward layers (i.e., multilayer perceptron, nearest neighbor classifier, auto-encoding network) with respect to their visual recognition performance. Beside the original neocognitron a modification of the neocognitron is proposed which combines neurons from perceptron with the localized network structure of neocognitron. Instead of training convolutional networks by time-consuming error backpropagation, in this work a modular procedure is applied whereby layers are trained sequentially from the input to the output layer in order to recognize features of increasing complexity. For a quantitative experimental comparison with standard classifiers two very different recognition tasks have been chosen: handwritten digit recognition and face recognition. In the first example on handwritten digit recognition the generalization of convolutional networks is compared to fully connected networks. In several experiments the influence of variations of position, size, and orientation of digits is determined and the relation between training sample size and validation error is observed. In the second example recognition of human faces is investigated under constrained and variable conditions with respect to face orientation and illumination and the limitations of convolutional networks are discussed. PMID:18252491
Butterfly Classification by HSI and RGB Color Models Using Neural Networks
Directory of Open Access Journals (Sweden)
Jorge E. Grajales-Múnera
2013-11-01
Full Text Available This study aims the classification of Butterfly species through the implementation of Neural Networks and Image Processing. A total of 9 species of Morpho genre which has blue as a characteristic color are processed. For Butterfly segmentation we used image processing tools such as: Binarization, edge processing and mathematical morphology. For data processing RGB values are obtained for every image which are converted to HSI color model to identify blue pixels and obtain the data to the proposed Neural Networks: Back-Propagation and Perceptron. For analysis and verification of results confusion matrix are built and analyzed with the results of neural networks with the lowest error levels. We obtain error levels close to 1% in classification of some Butterfly species.
Using Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort
Directory of Open Access Journals (Sweden)
G.E. Wittig
1994-05-01
Full Text Available Hie value of neural network modelling techniques in performing complicated pattern recognition and nonlinear estimation tasks has been demonstrated across an impressive spectrum of applications. Software development is a complex environment with many interrelated factors affecting development effort and productivity. Accurate forecasting has proved difficult since many of these interrelationships are not fully understood. An attempt to capture the significant attributes of the software development environment to enable improved accuracy in forecasting of development effort is made using backpropagation artificial neural networks. The data for this study was gathered from commercial 4GL software development projects, across a large range of sizes. As is typical of software developments, the range in productivity and other development factors in the data set is also large, accentuating the estimation problem. Despite these difficulties the neural network model predictions were reasonably accurate in comparison with other published results, indicating the potential of the use of this approach.
The fundamentals of fuzzy neural network and application in nuclear monitoring
International Nuclear Information System (INIS)
The authors presents a fuzzy modeling method using fuzzy neural network with the back-propagation algorithm. The new method can identify the fuzzy model of a nonlinear system automatically. Fuzzy neural network is used to generate fuzzy rules and membership functions. The feasibility and inferential statistic of the method is examined by using numerical data and XOR problem. The FNN improves accuracy and reliability, reduces design time and minimizes system cost of fuzzy design. The FNN can be used for estimation of human injury in nuclear explosions and can be simplified to a rule neural network (RNN), which is used for pole extraction of signal. Preliminary simulation show that FNN has vest vistas in nuclear monitoring
Adaptive learning with guaranteed stability for discrete-time recurrent neural networks
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
To avoid unstable learning, a stable adaptive learning algorithm was proposed for discrete-time recurrent neural networks. Unlike the dynamic gradient methods, such as the backpropagation through time and the real time recurrent learning, the weights of the recurrent neural networks were updated online in terms of Lyapunov stability theory in the proposed learning algorithm, so the learning stability was guaranteed. With the inversion of the activation function of the recurrent neural networks, the proposed learning algorithm can be easily implemented for solving varying nonlinear adaptive learning problems and fast convergence of the adaptive learning process can be achieved. Simulation experiments in pattern recognition show that only 5 iterations are needed for the storage of a 15X15 binary image pattern and only 9 iterations are needed for the perfect realization of an analog vector by an equilibrium state with the proposed learning algorithm.
Directory of Open Access Journals (Sweden)
Sen Tian
2014-01-01
Full Text Available With the development of mine industry, tailings storage facility (TSF, as the important facility of mining, has attracted increasing attention for its safety problems. However, the problems of low accuracy and slow operation rate often occur in current TSF safety evaluation models. This paper establishes a reasonable TSF safety evaluation index system and puts forward a new TSF safety evaluation model by combining the theories for the analytic hierarchy process (AHP and improved back-propagation (BP neural network algorithm. The varying proportions of cross validation were calculated, demonstrating that this method has better evaluation performance with higher learning efficiency and faster convergence speed and avoids the oscillation in the training process in traditional BP neural network method and other primary neural network methods. The entire analysis shows the combination of the two methods increases the accuracy and reliability of the safety evaluation, and it can be well applied in the TSF safety evaluation.
Dynamic properties of cellular neural networks
Directory of Open Access Journals (Sweden)
Angela Slavova
1993-01-01
Full Text Available Dynamic behavior of a new class of information-processing systems called Cellular Neural Networks is investigated. In this paper we introduce a small parameter in the state equation of a cellular neural network and we seek for periodic phenomena. New approach is used for proving stability of a cellular neural network by constructing Lyapunov's majorizing equations. This algorithm is helpful for finding a map from initial continuous state space of a cellular neural network into discrete output. A comparison between cellular neural networks and cellular automata is made.
Neural Network Prediction of Disruptions Caused by Locked Modes on J-TEXT Tokamak
International Nuclear Information System (INIS)
Prediction of disruptions caused by locked modes using the Back-Propagation (BP) neural network is completed on J-TEXT tokamak. The network, which is based on the BP neural network, uses Mirnov coils and locked mode coils signals as input data, and outputs a signal including information of prediction of locked mode. The rate of successful prediction of locked modes is more than 90%. For intrinsic locked mode disruptions, the network can give a prewarning signal about 1 ms ahead of the locking-time. For the disruption caused by resonant magnetic perturbation (RMPs) locked modes, the network can give a prewarning signal about 10 ms ahead of the locking-time
Circuit Design of On-Chip BP Learning Neural Network with Programmable Neuron Characteristics
Institute of Scientific and Technical Information of China (English)
卢纯; 石秉学; 陈卢
2000-01-01
A circuit system of on chip BP(Back-Propagation) learning neural network with pro grammable neurons has been designed,which comprises a feedforward network,an error backpropagation network and a weight updating circuit. It has the merits of simplicity,programmability, speedness,low power-consumption and high density. A novel neuron circuit with pro grammable parameters has been proposed. It generates not only the sigmoidal function but also its derivative. HSPICE simulations are done to a neuron circuit with level 47 transistor models as a standard 1.2tμm CMOS process. The results show that both functions are matched with their respec ive ideal functions very well. The non-linear partition problem is used to verify the operation of the network. The simulation result shows the superior performance of this BP neural network with on-chip learning.
International Nuclear Information System (INIS)
Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network
Static and Transient Performance Prediction for CFB Boilers Using a Bayesian—Gaussian Neural Network
Institute of Scientific and Technical Information of China (English)
HaiwenYe; WeidouNi
1997-01-01
A bayesian-Gaussian Neural Network(BGNN)is put forward in this paper to predict the static and transient performance of Circulating Fluidized Bed(CFB) boilers.The advantages of this network over Back-Propagation Neural Networks(BPNNs),easier determination of topology,simpler and time saving in training process as well as self-organizing bility,make this network more practical in on-line performance prediction for complicatied processes,Simulation shows that this network is comparable to the BPNNs in predicting the performance of CFB boilers.Good and practical on-line performance predictions are essential for operation guide and model predictive control of CFB boilers,which are under research by the authors.
Directory of Open Access Journals (Sweden)
R. Murugadoss
2014-10-01
Full Text Available Neural networks are modeled on the way the human brain. They are capable of learning and can automatically recognize by skillfully training and design complex relationships and hidden dependencies based on historical example patterns and use this information for forecasting. The main difference, and at the same time is biggest advantage of the model of neural networks over statistical techniques seen that the forecaster the exact functional structure between input and Output variables need not be specified, but this by the system with certain Learning algorithms is "learned" using a kind of threshold logic. Goal of the learning procedure is to define the training phase while those parameters of the network, with Help the network has one of those adequate for the problem behavior. Mathematically, the training phase is an iterative, converging towards a minimum error value process. They identify the processors of the network, minimize the "total error". The currently the most popular and most widely for business applications algorithm is the backpropagation algorithm. This paper opens the black box of Backpropagation networks and makes the optimization process in the network over time and locally comprehensible.
Comparison of the BP training algorithm and LVQ neural networks for e, μ, π identification
International Nuclear Information System (INIS)
Two different kinds of neural networks, feed-forward multi-layer mode with back-propagation training algorithm (BP) and Kohonen's learning vector quantization networks (LVQ), are adopted for the identification of e, μ, π particles in Beijing spectrometer (BES) experiment. The data samples for training and test consist of μ from cosmic ray, e and π from experimental data by strict selection. Although their momentum spectra are non-uniform, the identification efficiencies given by BP are quite uniform versus momentum, and LVQ is little worse. At least in this application BP is shown to be more powerful in pattern recognition than LVQ. (orig.)
Identification of Nonlinear Dynamic Systems Using Hammerstein-Type Neural Network
Directory of Open Access Journals (Sweden)
Hongshan Yu
2014-01-01
Full Text Available Hammerstein model has been popularly applied to identify the nonlinear systems. In this paper, a Hammerstein-type neural network (HTNN is derived to formulate the well-known Hammerstein model. The HTNN consists of a nonlinear static gain in cascade with a linear dynamic part. First, the Lipschitz criterion for order determination is derived. Second, the backpropagation algorithm for updating the network weights is presented, and the stability analysis is also drawn. Finally, simulation results show that HTNN identification approach demonstrated identification performances.
Application of artificial neural network for prediction of marine diesel engine performance
Mohd Noor, C. W.; Mamat, R.; Najafi, G.; Nik, W. B. Wan; Fadhil, M.
2015-12-01
This study deals with an artificial neural network (ANN) modelling of a marine diesel engine to predict the brake power, output torque, brake specific fuel consumption, brake thermal efficiency and volumetric efficiency. The input data for network training was gathered from engine laboratory testing running at various engine speed. The prediction model was developed based on standard back-propagation Levenberg-Marquardt training algorithm. The performance of the model was validated by comparing the prediction data sets with the measured experiment data. Results showed that the ANN model provided good agreement with the experimental data with high accuracy.
Photon spectrometry utilizing neural networks
International Nuclear Information System (INIS)
Having in mind the time spent on the uneventful work of characterization of the radiation beams used in a ionizing radiation metrology laboratory, the Metrology Service of the Centro Regional de Ciencias Nucleares do Nordeste - CRCN-NE verified the applicability of artificial intelligence (artificial neural networks) to perform the spectrometry in photon fields. For this, was developed a multilayer neural network, as an application for the classification of patterns in energy, associated with a thermoluminescent dosimetric system (TLD-700 and TLD-600). A set of dosimeters was initially exposed to various well known medium energies, between 40 keV and 1.2 MeV, coinciding with the beams determined by ISO 4037 standard, for the dose of 10 mSv in the quantity Hp(10), on a chest phantom (ISO slab phantom) with the purpose of generating a set of training data for the neural network. Subsequently, a new set of dosimeters irradiated in unknown energies was presented to the network with the purpose to test the method. The methodology used in this work was suitable for application in the classification of energy beams, having obtained 100% of the classification performed. (authors)
Energy Technology Data Exchange (ETDEWEB)
Cabrera, L.A.; Elbuluk, M.E. [Univ. of Akron, OH (United States). Dept. of Electrical Engineering; Zinger, D.S. [Northern Illinois Univ., Dekalb, IL (United States). Dept. of Electrical Engineering
1997-09-01
Neural networks are receiving attention as controllers for many industrial applications. Although these networks eliminate the need for mathematical models, they require a lot of training to understand the model of a plant or a process. Issues such as learning speed, stability, and weight convergence remain as areas of research and comparison of many training algorithms. This paper discusses the application of neural networks to control induction machines using direct torque control (DTC). A neural network is used to emulate the state selector of the DTC. The training algorithms used in this paper are the backpropagation, adaptive neuron model, extended Kalman filter, and the parallel recursive prediction error. Computer simulations of the motor and neural-network system using the four approaches are presented and compared. Discussions about the parallel recursive prediction error and the extended Kalman filter algorithms as the most promising training techniques is presented, giving their advantages and disadvantages.
Fuzzy logic systems are equivalent to feedforward neural networks
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i.e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.
Gap Filling of Daily Sea Levels by Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Lyubka Pashova
2013-06-01
Full Text Available In the recent years, intelligent methods as artificial neural networks are successfully applied for data analysis from different fields of the geosciences. One of the encountered practical problems is the availability of gaps in the time series that prevent their comprehensive usage for the scientific and practical purposes. The article briefly describes two types of the artificial neural network (ANN architectures - Feed-Forward Backpropagation (FFBP and recurrent Echo state network (ESN. In some cases, the ANN can be used as an alternative on the traditional methods, to fill in missing values in the time series. We have been conducted several experiments to fill the missing values of daily sea levels spanning a 5-years period using both ANN architectures. A multiple linear regression for the same purpose has been also applied. The sea level data are derived from the records of the tide gauge Burgas, which is located on the western Black Sea coast. The achieved results have shown that the performance of ANN models is better than that of the classical one and they are very promising for the real-time interpolation of missing data in the time series.
Diagnostic systems for ultrasonic examination utilizing neural networks
International Nuclear Information System (INIS)
In nuclear power plants, one has to confirm the integrity of pressure boundary such as piping welding joints by nondestructive examinations. This activity is called ISI (In Service-Inspection). Here, the authors have been trying to identify an IGSCC (Inter granular Stress Corrosion Cracking) from UT (Ultrasonic Testing) echo using a neural network for several years. At the first step of the study, the authors had developed an evaluation system, which consists of a preprocessing for input data and neural network. By using the system, IGSCC samples were identified with 81% reliability. In order to increase the reliability of the system, a series of UT echoes around a peak echo which contains the important information for human inspectors, is applied in the next step. To use the series of UT echoes, the previous system including preprocessing has been improved. The network consists of 3 layers. The modified backpropagation method is employed for a learning algorithm. The preprocessing arranges 5 echoes and makes an input pattern for the system. Through several examinations, the optimum reprocessing for an input pattern is settled. By the improved system, the probability of correct call in the evaluation have increased up to about 90%, although the system shows a little dependence on input data
Combinatorial evolution of regression nodes in feedforward neural networks.
Schmitz, Gregor P.J.; Aldrich, Chris
1999-01-01
A number of techniques exist with which neural network architectures such as multilayer perceptrons and radial basis function networks can be trained. These include backpropagation, k-means clustering and evolutionary algorithms. The latter method is particularly useful as it is able to avoid local optima in the search space and can optimise parameters for which no gradient information exists. Unfortunately, only moderately sized networks can be trained by this method, owing to the fact that evolutionary optimisation is very computationally intensive. In this paper a novel algorithm (CERN) is therefore proposed which uses a special form of combinatorial search to optimise groups of neural nodes. Oriented, ellipsoidal basis nodes optimised with CERN achieved significantly better accuracy with fewer nodes than spherical basis nodes optimised by k-means clustering. Multilayer perceptrons optimised by CERN were found to be as accurate as those trained by advanced gradient descent techniques. CERN was also found to be significantly more efficient than a conventional evolutionary algorithm that does not use a combinatorial search. PMID:12662726
Obtulowicz, Adam
2009-01-01
An idea of modularization of complex networks (from cortial neural net, Internet computer network, to market and social networks) is explained and some its topic motivations are presented. Then some known modularization algorithms and modular architectures (constructions) of complex networks are discussed in the context of possible applications of spiking neural P systems in order to improve these modularization algorithms and to analyze massively parallel processes in networks of mo...
Spackman, K A
1991-01-01
This paper presents maximum likelihood back-propagation (ML-BP), an approach to training neural networks. The widely reported original approach uses least squares back-propagation (LS-BP), minimizing the sum of squared errors (SSE). Unfortunately, least squares estimation does not give a maximum likelihood (ML) estimate of the weights in the network. Logistic regression, on the other hand, gives ML estimates for single layer linear models only. This report describes how to obtain ML estimates of the weights in a multi-layer model, and compares LS-BP to ML-BP using several examples. It shows that in many neural networks, least squares estimation gives inferior results and should be abandoned in favor of maximum likelihood estimation. Questions remain about the potential uses of multi-level connectionist models in such areas as diagnostic systems and risk-stratification in outcomes research. PMID:1807606
A selective learning method to improve the generalization of multilayer feedforward neural networks.
Galván, I M; Isasi, P; Aler, R; Valls, J M
2001-04-01
Multilayer feedforward neural networks with backpropagation algorithm have been used successfully in many applications. However, the level of generalization is heavily dependent on the quality of the training data. That is, some of the training patterns can be redundant or irrelevant. It has been shown that with careful dynamic selection of training patterns, better generalization performance may be obtained. Nevertheless, generalization is carried out independently of the novel patterns to be approximated. In this paper, we present a learning method that automatically selects the training patterns more appropriate to the new sample to be predicted. This training method follows a lazy learning strategy, in the sense that it builds approximations centered around the novel sample. The proposed method has been applied to three different domains: two artificial approximation problems and a real time series prediction problem. Results have been compared to standard backpropagation using the complete training data set and the new method shows better generalization abilities. PMID:14632169
Crop Classification by Forward Neural Network with Adaptive Chaotic Particle Swarm Optimization
Directory of Open Access Journals (Sweden)
Yudong Zhang
2011-05-01
Full Text Available This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM based texture features. Then, the features were reduced by principle component analysis (PCA. Finally, a two-hidden-layer forward neural network (NN was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO. K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP, adaptive BP (ABP, momentum BP (MBP, Particle Swarm Optimization (PSO, and Resilient back-propagation (RPROP methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.
Neural Networks Methodology and Applications
Dreyfus, Gérard
2005-01-01
Neural networks represent a powerful data processing technique that has reached maturity and broad application. When clearly understood and appropriately used, they are a mandatory component in the toolbox of any engineer who wants make the best use of the available data, in order to build models, make predictions, mine data, recognize shapes or signals, etc. Ranging from theoretical foundations to real-life applications, this book is intended to provide engineers and researchers with clear methodologies for taking advantage of neural networks in industrial, financial or banking applications, many instances of which are presented in the book. For the benefit of readers wishing to gain deeper knowledge of the topics, the book features appendices that provide theoretical details for greater insight, and algorithmic details for efficient programming and implementation. The chapters have been written by experts ands seemlessly edited to present a coherent and comprehensive, yet not redundant, practically-oriented...
LOAD BALANCING WITH NEURAL NETWORK
Directory of Open Access Journals (Sweden)
Nada M. Al Sallami
2013-11-01
Full Text Available This paper discusses a proposed load balance technique based on artificial neural network. It distributes workload equally across all the nodes by using back propagation learning algorithm to train feed forward Artificial Neural Network (ANN. The proposed technique is simple and it can work efficiently when effective training sets are used. ANN predicts the demand and thus allocates resources according to that demand. Thus, it always maintains the active servers according to current demand, which results in low energy consumption than the conservative approach of over-provisioning. Furthermore, high utilization of server results in more power consumption, server running at higher utilization can process more workload with similar power usage. Finally the existing load balancing techniques in cloud computing are discussed and compared with the proposed technique based on various parameters like performance, scalability, associated overhead... etc. In addition energy consumption and carbon emission perspective are also considered to satisfy green computing.
Color conversion using neural networks
Tominaga, Shoji
1998-01-01
Neural network methods are described for color coordinate conversion between color systems. We present solutions for two problems of (1) conversion between two color-specification systems and (2) conversion between a color-specification system and a device coordinate system. First we discuss the color-notation conversion between the Munsell and CIE color systems. The conversion algorithms are developed for both directions of Munsell-to-L*a*b* and L*a*b*-to-Munsell. Second we discuss a neural network method for color reproduction on a printer. The color reproduction problem on the printer using more than four inks is considered as the problem of controlling an unknown system. The practical algorithms are presented for realizing the mapping from the L*a*b* space to the CMYK space. Moreover the method is applied to the color control using CMYK plus light cyan and light magenta.
International joint conference on neural networks
Energy Technology Data Exchange (ETDEWEB)
1989-01-01
This book contains papers on neural networks. Included are the following topics: A self-training visual inspection system with a neural network classifier; A bifurcation theory approach to vector field programming for periodic attractors; and construction of neural nets using the radon transform.
Julio Rojas Naccha; Víctor Vásquez Villalobos
2012-01-01
The predictive ability of Artificial Neural Network (ANN) on the effect of the concentration (30, 40, 50 y 60 % w/w) and temperature (30, 40 y 50°C) of fructooligosaccharides solution, in the mass, moisture, volume and solids of osmodehydrated yacon cubes, and in the coefficients of the water means effective diffusivity with and without shrinkage was evaluated. The Feedforward type ANN with the Backpropagation training algorithms and the Levenberg-Marquardt weight adjustment was applied, usin...
García-Rodríguez, M. J.; J. A. Malpica
2010-01-01
This paper presents an approach for assessing earthquake-triggered landslide susceptibility using artificial neural networks (ANNs). The computational method used for the training process is a back-propagation learning algorithm. It is applied to El Salvador, one of the most seismically active regions in Central America, where the last severe destructive earthquakes occurred on 13 January 2001 (M_{w} 7.7) and 13 February 2001 (M
García-Rodríguez, M. J.; J. A. Malpica
2010-01-01
This paper presents an approach for assessing earthquake-triggered landslide susceptibility using artificial neural networks (ANNs). The computational method used for the training process is a back-propagation learning algorithm. It is applied to El Salvador, one of the most seismically active regions in Central America, where the last severe destructive earthquakes occurred on 13 January 2001 (Mw 7.7) and 13 February 2001 (Mw 6.6). The first one triggered more than 600 landsli...
Jianbin Hao; Banqiao Wang
2014-01-01
Based on the back-propagation algorithm of artificial neural networks (ANNs), this paper establishes an intelligent model, which is used to predict the maximum lateral displacement of composite soil-nailed wall. Some parameters, such as soil cohesive strength, soil friction angle, prestress of anchor cable, soil-nail spacing, soil-nail diameter, soil-nail length, and other factors, are considered in the model. Combined with the in situ test data of composite soil-nail wall reinforcement engi...
Directory of Open Access Journals (Sweden)
ÃƒÂ–. Galip Saracoglu
2008-03-01
Full Text Available This paper describes artificial neural network (ANN based prediction of theresponse of a fiber optic sensor using evanescent field absorption (EFA. The sensingprobe of the sensor is made up a bundle of five PCS fibers to maximize the interaction ofevanescent field with the absorbing medium. Different backpropagation algorithms areused to train the multilayer perceptron ANN. The Levenberg-Marquardt algorithm, aswell as the other algorithms used in this work successfully predicts the sensor responses.
Learning Compact Recurrent Neural Networks
Lu, Zhiyun; Sindhwani, Vikas; Sainath, Tara N.
2016-01-01
Recurrent neural networks (RNNs), including long short-term memory (LSTM) RNNs, have produced state-of-the-art results on a variety of speech recognition tasks. However, these models are often too large in size for deployment on mobile devices with memory and latency constraints. In this work, we study mechanisms for learning compact RNNs and LSTMs via low-rank factorizations and parameter sharing schemes. Our goal is to investigate redundancies in recurrent architectures where compression ca...
Learning with heterogeneous neural networks
Belanche Muñoz, Luis Antonio
2011-01-01
This chapter studies a class of neuron models that computes a user-defined similarity function between inputs and weights. The neuron transfer function is formed by composition of an adapted logistic function with the quasi-linear mean of the partial input-weight similarities. The neuron model is capable of dealing directly with mixtures of continuous as well as discrete quantities, among other data types and there is provision for missing values. An artificial neural network using these n...
Process Neural Networks Theory and Applications
He, Xingui
2010-01-01
"Process Neural Networks - Theory and Applications" proposes the concept and model of a process neural network for the first time, showing how it expands the mapping relationship between the input and output of traditional neural networks, and enhancing the expression capability for practical problems, with broad applicability to solving problems relating to process in practice. Some theoretical problems such as continuity, functional approximation capability, and computing capability, are strictly proved. The application methods, network construction principles, and optimization alg
using artificial neural network
Directory of Open Access Journals (Sweden)
Rafael do Espírito Santo
2007-01-01
Full Text Available In this work, a Multilayer Perceptron implementation MLP using functional Magnetic Resonance Imaging (fMRI is used to infer stimuli performed. Sets of images of brain activation were generated by visual, auditory and finger tapping paradigms in 54 healthy volunteers. These images were used for training the MLP network in a leave-one-out manner in order to predict the paradigm that a subject performed by using other images, so far unseen by the MLP network. The aim in this paper is the exploring of the influence of the number of the Principal Component (PC on the performance of the MLP in classifying fMRI paradigms. The classifier´s performance was evaluated in terms of the Sensitivity and Specificity, Prediction Accuracy and the area Az under the receiver operating characteristics (ROC curve. From the ROC analysis, values of Az up to 1 were obtained with 60 PCs in discriminating the visual paradigm from the auditory paradigm.
The LILARTI neural network system
Energy Technology Data Exchange (ETDEWEB)
Allen, J.D. Jr.; Schell, F.M.; Dodd, C.V.
1992-10-01
The material of this Technical Memorandum is intended to provide the reader with conceptual and technical background information on the LILARTI neural network system of detail sufficient to confer an understanding of the LILARTI method as it is presently allied and to facilitate application of the method to problems beyond the scope of this document. Of particular importance in this regard are the descriptive sections and the Appendices which include operating instructions, partial listings of program output and data files, and network construction information.
Peng, Jinzhu; Dubay, Rickey
2011-10-01
In this paper, an adaptive control approach based on the neural networks is presented to control a DC motor system with dead-zone characteristics (DZC), where two neural networks are proposed to formulate the traditional identification and control approaches. First, a Wiener-type neural network (WNN) is proposed to identify the motor DZC, which formulates the Wiener model with a linear dynamic block in cascade with a nonlinear static gain. Second, a feedforward neural network is proposed to formulate the traditional PID controller, termed as PID-type neural network (PIDNN), which is then used to control and compensate for the DZC. In this way, the DC motor system with DZC is identified by the WNN identifier, which provides model information to the PIDNN controller in order to make it adaptive. Back-propagation algorithms are used to train both neural networks. Also, stability and convergence analysis are conducted using the Lyapunov theorem. Finally, experiments on the DC motor system demonstrated accurate identification and good compensation for dead-zone with improved control performance over the conventional PID control. PMID:21788017
Application of BP neural networks in non-linearity correction of optical tweezers
Institute of Scientific and Technical Information of China (English)
Ziqiang WANG; Yinmei LI; Liren LOU; Henghua WEI; Zhong WANG
2008-01-01
The back-propagation (BP) neural network is proposed to correct nonlinearity and optimize the force measurement and calibration of an optical tweezer sys-tem. Considering the low convergence rate of the BP algo-rithm, the Levenberg-Marquardt (LM) algorithm is used to improve the BP network. The proposed method is experimentally studied for force calibration in a typical optical tweezer system using hydromechanics. The result shows that with the nonlinear correction using BP net-works, the range of force measurement of an optical tweezer system is enlarged by 30% and the precision is also improved compared with the polynomial fitting method. It is demonstrated that nonlinear correction by the neural network method effectively improves the per-formance of optical tweezers without adding or changing the measuring system.
SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
Graff, Philip; Hobson, Michael P; Lasenby, Anthony N
2013-01-01
We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine-learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a powerful 'pre-training' method, to obtain a set of network parameters close to the true global maximum of the training objective function, followed by further optimisation using an automatically-regularised variant of Newton's method; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimise using standard backpropagation techniques....
Nonlinear dynamic system identification using Chebyshev functional link artificial neural networks.
Patra, J C; Kot, A C
2002-01-01
A computationally efficient artificial neural network (ANN) for the purpose of dynamic nonlinear system identification is proposed. The major drawback of feedforward neural networks, such as multilayer perceptrons (MLPs) trained with the backpropagation (BP) algorithm, is that they require a large amount of computation for learning. We propose a single-layer functional-link ANN (FLANN) in which the need for a hidden layer is eliminated by expanding the input pattern by Chebyshev polynomials. The novelty of this network is that it requires much less computation than that of a MLP. We have shown its effectiveness in the problem of nonlinear dynamic system identification. In the presence of additive Gaussian noise, the performance of the proposed network is found to be similar or superior to that of a MLP. A performance comparison in terms of computational complexity has also been carried out. PMID:18238146
Identifying three-phase induction motor faults using artificial neural networks
Kolla; Varatharasa
2000-01-01
This paper presents an artificial neural network (ANN) based technique to identify faults in a three-phase induction motor. The main types of faults considered are overload, single phasing, unbalanced supply voltage, locked rotor, ground fault, over-voltage and under-voltage. Three-phase currents and voltages from the induction motor are used in the proposed approach. A feedforward layered neural network structure is used. The network is trained using the backpropagation algorithm. The trained network is tested with simulated fault current and voltage data. Fault detection is attempted in the no fault to fault transition period. Off-line testing results on a 3 HP induction motor model show that the proposed ANN based method is effective in identifying various types of faults. PMID:11106295
Classification of brain compartments and head injury lesions by neural networks applied to MRI
International Nuclear Information System (INIS)
An automatic, neural network-based approach was applied to segment normal brain compartments and lesions on MR images. Two supervised networks, backpropagation (BPN) and counterpropagation, and two unsupervised networks, Kohonen learning vector quantizer and analog adaptive resonance theory, were trained on registered T2-weighted and proton density images. The classes of interest were background, gray matter, white matter, cerebrospinal fluid, macrocystic encephalomalacia, gliosis, and 'unknown'. A comprehensive feature vector was chosen to discriminate these classes. The BPN combined with feature conditioning, multiple discriminant analysis followed by Hotelling transform, produced the most accurate and consistent classification results. Classifications of normal brain compartments were generally in agreement with expert interpretation of the images. Macrocystic encephalomalacia and gliosis were recognized and, except around the periphery, classified in agreement with the clinician's report used to train the neural network. (orig.)
Neural networks for feedback feedforward nonlinear control systems.
Parisini, T; Zoppoli, R
1994-01-01
This paper deals with the problem of designing feedback feedforward control strategies to drive the state of a dynamic system (in general, nonlinear) so as to track any desired trajectory joining the points of given compact sets, while minimizing a certain cost function (in general, nonquadratic). Due to the generality of the problem, conventional methods are difficult to apply. Thus, an approximate solution is sought by constraining control strategies to take on the structure of multilayer feedforward neural networks. After discussing the approximation properties of neural control strategies, a particular neural architecture is presented, which is based on what has been called the "linear-structure preserving principle". The original functional problem is then reduced to a nonlinear programming one, and backpropagation is applied to derive the optimal values of the synaptic weights. Recursive equations to compute the gradient components are presented, which generalize the classical adjoint system equations of N-stage optimal control theory. Simulation results related to nonlinear nonquadratic problems show the effectiveness of the proposed method. PMID:18267810
Artificial neural network Radon inversion for image reconstruction
International Nuclear Information System (INIS)
Image reconstruction techniques are essential to computer tomography. Algorithms such as filtered backprojection (FBP) or algebraic techniques are most frequently used. This paper presents an attempt to apply a feed-forward back-propagation supervised artificial neural network (BPN) to tomographic image reconstruction, specifically to positron emission tomography (PET). The main result is that the network trained with Gaussian test images proved to be successful at reconstructing images from projection sets derived from arbitrary objects. Additional results relate to the design of the network and the full width at half maximum (FWHM) of the Gaussians in the training sets. First, the optimal number of nodes in the middle layer is about an order of magnitude less than the number of input or output nodes. Second, the number of iterations required to achieve a required training set tolerance appeared to decrease exponentially with the number of nodes in the middle layer. Finally, for training sets containing Gaussians of a single width, the optimal accuracy of reconstructing the control set is obtained with a FWHM of three pixels. Intended to explore feasibility, the BPN presented in the following does not provide reconstruction accuracy adequate for immediate application to PET. However, the trained network does reconstruct general images independent of the data with which it was trained. Proposed in the concluding section are several possible refinements that should permit the development of a network capable of fast reconstruction of three-dimensional images from the discrete, noisy projection data characteristic of PET
Sea level forecasts using neural networks
Röske, Frank
1997-03-01
In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the
Ghosh, Arka
2011-01-01
Financial forecasting is an example of a signal processing problem which is challenging due to Small sample sizes, high noise, non-stationarity, and non-linearity,but fast forecasting of stock market price is very important for strategic business planning.Present study is aimed to develop a comparative predictive model with Feedforward Multilayer Artificial Neural Network & Recurrent Time Delay Neural Network for the Financial Timeseries Prediction.This study is developed with the help of historical stockprice dataset made available by GoogleFinance.To develop this prediction model Backpropagation method with Gradient Descent learning has been implemented.Finally the Neural Net, learned with said algorithm is found to be skillful predictor for non-stationary noisy Financial Timeseries.
Practical neural network recipies in C++
Masters
2014-01-01
This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum
MEMBRAIN NEURAL NETWORK FOR VISUAL PATTERN RECOGNITION
Directory of Open Access Journals (Sweden)
Artur Popko
2013-06-01
Full Text Available Recognition of visual patterns is one of significant applications of Artificial Neural Networks, which partially emulate human thinking in the domain of artificial intelligence. In the paper, a simplified neural approach to recognition of visual patterns is portrayed and discussed. This paper is dedicated for investigators in visual patterns recognition, Artificial Neural Networking and related disciplines. The document describes also MemBrain application environment as a powerful and easy to use neural networks’ editor and simulator supporting ANN.
Laidi, Maamar; Hanini, Salah; Rezrazi, Ahmed; Yaiche, Mohamed Redha; El Hadj, Abdallah Abdallah; Chellali, Farouk
2016-01-01
In this study, a backpropagation artificial neural network (BP-ANN) model is used as an alternative approach to predict solar radiation on tilted surfaces (SRT) using a number of variables involved in physical process. These variables are namely the latitude of the site, mean temperature and relative humidity, Linke turbidity factor and Angstrom coefficient, extraterrestrial solar radiation, solar radiation data measured on horizontal surfaces (SRH), and solar zenith angle. Experimental solar radiation data from 13 stations spread all over Algeria around the year (2004) were used for training/validation and testing the artificial neural networks (ANNs), and one station was used to make the interpolation of the designed ANN. The ANN model was trained, validated, and tested using 60, 20, and 20 % of all data, respectively. The configuration 8-35-1 (8 inputs, 35 hidden, and 1 output neurons) presented an excellent agreement between the prediction and the experimental data during the test stage with determination coefficient of 0.99 and root meat squared error of 5.75 Wh/m2, considering a three-layer feedforward backpropagation neural network with Levenberg-Marquardt training algorithm, a hyperbolic tangent sigmoid and linear transfer function at the hidden and the output layer, respectively. This novel model could be used by researchers or scientists to design high-efficiency solar devices that are usually tilted at an optimum angle to increase the solar incident on the surface.
Optimizing the De-Noise Neural Network Model for GPS Time-Series Monitoring of Structures
Directory of Open Access Journals (Sweden)
Mosbeh R. Kaloop
2015-09-01
Full Text Available The Global Positioning System (GPS is recently used widely in structures and other applications. Notwithstanding, the GPS accuracy still suffers from the errors afflicting the measurements, particularly the short-period displacement of structural components. Previously, the multi filter method is utilized to remove the displacement errors. This paper aims at using a novel application for the neural network prediction models to improve the GPS monitoring time series data. Four prediction models for the learning algorithms are applied and used with neural network solutions: back-propagation, Cascade-forward back-propagation, adaptive filter and extended Kalman filter, to estimate which model can be recommended. The noise simulation and bridge’s short-period GPS of the monitoring displacement component of one Hz sampling frequency are used to validate the four models and the previous method. The results show that the Adaptive neural networks filter is suggested for de-noising the observations, specifically for the GPS displacement components of structures. Also, this model is expected to have significant influence on the design of structures in the low frequency responses and measurements’ contents.
Neural network modeling of emotion
Levine, Daniel S.
2007-03-01
This article reviews the history and development of computational neural network modeling of cognitive and behavioral processes that involve emotion. The exposition starts with models of classical conditioning dating from the early 1970s. Then it proceeds toward models of interactions between emotion and attention. Then models of emotional influences on decision making are reviewed, including some speculative (not and not yet simulated) models of the evolution of decision rules. Through the late 1980s, the neural networks developed to model emotional processes were mainly embodiments of significant functional principles motivated by psychological data. In the last two decades, network models of these processes have become much more detailed in their incorporation of known physiological properties of specific brain regions, while preserving many of the psychological principles from the earlier models. Most network models of emotional processes so far have dealt with positive and negative emotion in general, rather than specific emotions such as fear, joy, sadness, and anger. But a later section of this article reviews a few models relevant to specific emotions: one family of models of auditory fear conditioning in rats, and one model of induced pleasure enhancing creativity in humans. Then models of emotional disorders are reviewed. The article concludes with philosophical statements about the essential contributions of emotion to intelligent behavior and the importance of quantitative theories and models to the interdisciplinary enterprise of understanding the interactions of emotion, cognition, and behavior.
Directory of Open Access Journals (Sweden)
Golmohammadi Hassan
2013-01-01
Full Text Available A quantitative structure-property relationship (QSPR study based on partial least squares (PLS and artificial neural network (ANN was developed for the prediction of ferric iron precipitation in bioleaching process. The leaching temperature, initial pH, oxidation/reduction potential (ORP, ferrous concentration and particle size of ore were used as inputs to the network. The output of the model was ferric iron precipitation. The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. After optimization and training of the network according to back-propagation algorithm, a 5-5-1 neural network was generated for prediction of ferric iron precipitation. The root mean square error for the neural network calculated ferric iron precipitation for training, prediction and validation set are 32.860, 40.739 and 35.890, respectively, which are smaller than those obtained by PLS model (180.972, 165.047 and 149.950, respectively. Results obtained reveal the reliability and good predictivity of neural network model for the prediction of ferric iron precipitation in bioleaching process.
Hybrid digital signal processing and neural networks for automated diagnostics using NDE methods
International Nuclear Information System (INIS)
The primary purpose of the current research was to develop an integrated approach by combining information compression methods and artificial neural networks for the monitoring of plant components using nondestructive examination data. Specifically, data from eddy current inspection of heat exchanger tubing were utilized to evaluate this technology. The focus of the research was to develop and test various data compression methods (for eddy current data) and the performance of different neural network paradigms for defect classification and defect parameter estimation. Feedforward, fully-connected neural networks, that use the back-propagation algorithm for network training, were implemented for defect classification and defect parameter estimation using a modular network architecture. A large eddy current tube inspection database was acquired from the Metals and Ceramics Division of ORNL. These data were used to study the performance of artificial neural networks for defect type classification and for estimating defect parameters. A PC-based data preprocessing and display program was also developed as part of an expert system for data management and decision making. The results of the analysis showed that for effective (low-error) defect classification and estimation of parameters, it is necessary to identify proper feature vectors using different data representation methods. The integration of data compression and artificial neural networks for information processing was established as an effective technique for automation of diagnostics using nondestructive examination methods
Neural-Network Computer Transforms Coordinates
Josin, Gary M.
1990-01-01
Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.
Fast Algorithms for Convolutional Neural Networks
Lavin, Andrew; Gray, Scott
2015-01-01
Deep convolutional neural networks take GPU days of compute time to train on large data sets. Pedestrian detection for self driving cars requires very low latency. Image recognition for mobile phones is constrained by limited processing resources. The success of convolutional neural networks in these situations is limited by how fast we can compute them. Conventional FFT based convolution is fast for large filters, but state of the art convolutional neural networks use small, 3x3 filters. We ...
Adaptive optimization and control using neural networks
Energy Technology Data Exchange (ETDEWEB)
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
Modelling Microwave Devices Using Artificial Neural Networks
Directory of Open Access Journals (Sweden)
Andrius Katkevičius
2012-04-01
Full Text Available Artificial neural networks (ANN have recently gained attention as fast and flexible equipment for modelling and designing microwave devices. The paper reviews the opportunities to use them for undertaking the tasks on the analysis and synthesis. The article focuses on what tasks might be solved using neural networks, what challenges might rise when using artificial neural networks for carrying out tasks on microwave devices and discusses problem-solving techniques for microwave devices with intermittent characteristics.Article in Lithuanian
Adaptive Control Based On Neural Network
Wei, Sun; Lujin, Zhang; Jinhai, Zou; Siyi, Miao
2009-01-01
In this paper, the adaptive control based on neural network is studied. Firstly, a neural network based adaptive robust tracking control design is proposed for robotic systems under the existence of uncertainties. In this proposed control strategy, the NN is used to identify the modeling uncertainties, and then the disadvantageous effects caused by neural network approximating error and external disturbances in robotic system are counteracted by robust controller. Especially the proposed cont...
Sequential optimizing investing strategy with neural networks
Ryo Adachi; Akimichi Takemura
2010-01-01
In this paper we propose an investing strategy based on neural network models combined with ideas from game-theoretic probability of Shafer and Vovk. Our proposed strategy uses parameter values of a neural network with the best performance until the previous round (trading day) for deciding the investment in the current round. We compare performance of our proposed strategy with various strategies including a strategy based on supervised neural network models and show that our procedure is co...
Boolean Factor Analysis by Attractor Neural Network
Czech Academy of Sciences Publication Activity Database
Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.
2007-01-01
Roč. 18, č. 3 (2007), s. 698-707. ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007
Artificial neural networks in nuclear medicine
International Nuclear Information System (INIS)
An analysis of the accessible literature on the diagnostic applicability of artificial neural networks in coronary artery disease and pulmonary embolism appears to be comparative to the diagnosis of experienced doctors dealing with nuclear medicine. Differences in the employed models of artificial neural networks indicate a constant search for the most optimal parameters, which could guarantee the ultimate accuracy in neural network activity. The diagnostic potential within systems containing artificial neural networks proves this calculation tool to be an independent or/and an additional device for supporting a doctor's diagnosis of artery disease and pulmonary embolism. (author)
Fuzzy neural network theory and application
Liu, Puyin
2004-01-01
This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he
Artificial neural networks in prediction of mechanical behavior of concrete at high temperature
International Nuclear Information System (INIS)
The behavior of concrete structures that are exposed to extreme thermo-mechanical loading is an issue of great importance in nuclear engineering. The mechanical behavior of concrete at high temperature is non-linear. The properties that regulate its response are highly temperature dependent and extremely complex. In addition, the constituent materials, e.g. aggregates, influence the response significantly. Attempts have been made to trace the stress-strain curve through mathematical models and rheological models. However, it has been difficult to include all the contributing factors in the mathematical model. This paper examines a new programming paradigm, artificial neural networks, for the problem. Implementing a feedforward network and backpropagation algorithm the stress-strain relationship of the material is captured. The neural networks for the prediction of uniaxial behavior of concrete at high temperature has been presented here. The results of the present investigation are very encouraging. (orig.)
Neural Network Based on Quantum Chemistry for Predicting Melting Point of Organic Compounds
Institute of Scientific and Technical Information of China (English)
Juan A. Lazzús
2009-01-01
The melting points of organic compounds were estimated using a combined method that includes a backpropagation neural network and quantitative structure property relationship (QSPR) parameters in quantum chemistry. Eleven descriptors that reflect the intermolec-ular forces and molecular symmetry were used as input variables. QSPR parameters were calculated using molecular modeling and PM3 semi-empirical molecular orbital theories. A total of 260 compounds were used to train the network, which was developed using MatLab. Then, the melting points of 73 other compounds were predicted and results were compared to experimental data from the literature. The study shows that the chosen artificial neural network and the quantitative structure property relationships method present an excellent alternative for the estimation of the melting point of an organic compound, with average absolute deviation of 5%.
Damage assessment in structure from changes in static parameter using neural networks
Indian Academy of Sciences (India)
Damodar Maity; Asish Saha
2004-06-01
Damage to structures may occur as a result of normal operations, accidents, deterioration or severe natural events such as earthquakes and storms. Most often the extent and location of damage may be determined through visual inspection. However, in some cases this may not be feasible. The basic strategy applied in this study is to train a neural network to recognize the behaviour of the undamaged structure as well as of the structure with various possible damaged states. When this trained network is subjected to the measured response, it should be able to detect any existing damage. This idea is applied on a simple cantilever beam. Strain and displacement are used as possible candidates for damage identiﬁcation by a back-propagation neural network. The superiority of strain over displacement for identiﬁcation of damage has been observed in this study.
Feed-forward neural networks for shower recognition: construction and generalization
International Nuclear Information System (INIS)
Strictly layered feed-forward neural networks are explored as recognition tools for energy deposition patterns in a calorimeter. This study is motivated by possible applications for on-line event selection. Networks consisting of linear threshold units are generated by a constructive learning algorithm, the Patch algorithm. As a non-constructive counterpart the back-propagation algorithm is applied. This algorithm makes use of analogue neurons. The generalization capabilities of the neural networks resulting from both methods are compared to those of nearest-neighbour classifiers and of Probabilistic Neural Networks implementing Parzen-windows. The latter non-parametric statistical method is applied to estimate the optimal Bayesian classifier. For all methods the generalization capabilities are determined for different ways of pre-processing of the input data. The complexity of the feed-forward neural networks studied does not grow with the training set size. This favours a hardwired implementation of these neural networks as any implementation of the other two methods grows linearly with the training set size. ((orig.))
Neural networks for nuclear spectroscopy
Energy Technology Data Exchange (ETDEWEB)
Keller, P.E.; Kangas, L.J.; Hashem, S.; Kouzes, R.T. [Pacific Northwest Lab., Richland, WA (United States)] [and others
1995-12-31
In this paper two applications of artificial neural networks (ANNs) in nuclear spectroscopy analysis are discussed. In the first application, an ANN assigns quality coefficients to alpha particle energy spectra. These spectra are used to detect plutonium contamination in the work environment. The quality coefficients represent the levels of spectral degradation caused by miscalibration and foreign matter affecting the instruments. A set of spectra was labeled with quality coefficients by an expert and used to train the ANN expert system. Our investigation shows that the expert knowledge of spectral quality can be transferred to an ANN system. The second application combines a portable gamma-ray spectrometer with an ANN. In this system the ANN is used to automatically identify, radioactive isotopes in real-time from their gamma-ray spectra. Two neural network paradigms are examined: the linear perception and the optimal linear associative memory (OLAM). A comparison of the two paradigms shows that OLAM is superior to linear perception for this application. Both networks have a linear response and are useful in determining the composition of an unknown sample when the spectrum of the unknown is a linear superposition of known spectra. One feature of this technique is that it uses the whole spectrum in the identification process instead of only the individual photo-peaks. For this reason, it is potentially more useful for processing data from lower resolution gamma-ray spectrometers. This approach has been tested with data generated by Monte Carlo simulations and with field data from sodium iodide and Germanium detectors. With the ANN approach, the intense computation takes place during the training process. Once the network is trained, normal operation consists of propagating the data through the network, which results in rapid identification of samples. This approach is useful in situations that require fast response where precise quantification is less important.
A Neural Network Based Recognition and Classification of Commonly Used Indian Non Leafy Vegetables
Directory of Open Access Journals (Sweden)
Ajit Danti
2014-09-01
Full Text Available A methodology to characterize the commonly used Indian non-leafy vegetables’ images is developed. From the captured images of Indian non-leafy vegetables, color components, namely, RGB and HSV features are extracted, analyzed and classified. A feed forward backpropagation artificial neural network (BPNN is used for the classification. The results show that it has good robustness and a very high success rate in the range of 96-100% for eight types of vegetables. The work finds usefulness in developing recognition system for super market, automatic vending, packing and grading of vegetables, food preparation and Agriculture Produce Market Committee (APMC.
Directory of Open Access Journals (Sweden)
Oliveira-Esquerre K.P.
2002-01-01
Full Text Available This work presents a way to predict the biochemical oxygen demand (BOD of the output stream of the biological wastewater treatment plant at RIPASA S/A Celulose e Papel, one of the major pulp and paper plants in Brazil. The best prediction performance is achieved when the data are preprocessed using principal components analysis (PCA before they are fed to a backpropagated neural network. The influence of input variables is analyzed and satisfactory prediction results are obtained for an optimized situation.
A BOD-DO coupling model for water quality simulation by artificial neural network
Institute of Scientific and Technical Information of China (English)
郭劲松; LONG; Tengrui; 等
2002-01-01
A one-dimensional BOD-DO coupling model for water quality simulation is presented,which adopts Streeter-Phelps equations and the theory of back-propagation artificial neural network.The water quality data of Yangtze River in the Chongqing region in the year of 1989 are divided into 5 groups and used in the learning and testing courses of this model.The result shows that such model is feasible for water quality simulation and is more accurate than traditional models.
Pattern recognition in high energy physics with artificial neural networks - JETNET 2.0
International Nuclear Information System (INIS)
A F77 package of adaptive artificial neural network algorithms, JETNET 2.0, is presented. Its primary target is the high energy physics community, but it is general enough to be used in any pattern-recognition application area. The basic ingredients are the multilayer perceptron back-propagation algorithm and the topological self-organizing map. The package consists of a set of subroutines, which can either be used with standard options or be easily modified to host alternative architectures and procedures. (orig.)
Alireza Taravat; Simon Proud; Simone Peronaci; Fabio Del Frate; Natascha Oppelt
2014-01-01
A multilayer perceptron neural network cloud mask for Meteosat Second Generation SEVIRI (Spinning Enhanced Visible and Infrared Imager) images is introduced and evaluated. The model is trained for cloud detection on MSG SEVIRI daytime data. It consists of a multi-layer perceptron with one hidden sigmoid layer, trained with the error back-propagation algorithm. The model is fed by six bands of MSG data (0.6, 0.8, 1.6, 3.9, 6.2 and 10.8 μm) with 10 hidden nodes. The multiple-layer perceptrons l...
Utilization of artificial neural networks in the diagnosis of optic nerve diseases.
Kara, Sadik; Güven, Ayşegül; Oner, Ayşe Oztürk
2006-04-01
This research is concentrated on the diagnosis of optic nerve disease through the analysis of pattern electroretinography (PERG) signals with the help of artificial neural network (ANN). Multilayer feed forward ANN trained with a Levenberg Marquart (LM) backpropagation algorithm was implemented. The designed classification structure has about 96.4% sensitivity, 90.4% specifity and positive prediction is calculated to be 94.2%. The end results are classified as healthy and diseased. Testing results were found to be compliant with the expected results that are derived from the physician's direct diagnosis. The end benefit would be to assist the physician to make the final decision without hesitation. PMID:16488775
International Nuclear Information System (INIS)
The artificial neural network technique was used to identify drugs and plastic explosives, from a tomography composed by a set of six neutrongraphic projections obtained in real time. Bidimensional tomographic images of samples of drugs, explosives and other materials, when digitally processed, yield the characteristic spectra of each type of material. The information contained in those spectra was then used for ANN training, the best images being obtained when the multilayer perceptron model, the back-propagation training algorithm and the Cross-validation interruption criterion were used. ANN showed to be useful in forecasting presence of drugs and explosives hitting a rate of success above 97 %. (author)
Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry
Lee, Wooram; Heo, Gunhaeng; You, Kwanho
The heterodyne laser interferometer acts as an ultra-precise measurement apparatus in semiconductor manufacture. However the periodical nonlinearity property caused from frequency cross-talk is an obstacle to improve the high measurement accuracy in nanometer scale. In order to minimize the nonlinearity error of the heterodyne interferometer, we propose a frequency cross-talk compensation algorithm using an artificial intelligence method. The feedforward neural network trained by back-propagation compensates the nonlinearity error and regulates to minimize the difference with the reference signal. With some experimental results, the improved accuracy is proved through comparison with the position value from a capacitive displacement sensor.
Chess Endgames and Neural Networks
Haworth, Guy McCrossan; Velliste, Meel
1998-01-01
The existence of endgame databases challenges us to extract higher-grade information and knowledge from their basic data content. Chess players, for example, would like simple and usable endgame theories if such holy grail exists: endgame experts would like to provide such insights and be inspired by computers to do so. Here, we investigate the use of artificial neural networks (NNs) to mine these databases and we report on a first use of NNs on KPK. The results encourage us to suggest furthe...
Neural Network based Consumption Forecasting
DEFF Research Database (Denmark)
Madsen, Per Printz
2016-01-01
active participation in the future smart grid environment. One of the main obstacles for making optimal energy consumption is to have good predictions of the future energy consumption. This study is based on real consumption data from eight houses in Denmark. There are designed two different prediction...... models. It is shown that both of the predictions model produce a better consumption prediction then a naïve model. Seen in this perspective is it concluded that it is possible to use Artificial Neural Networks for predicting the energy consumption in ordinary family houses....
Artificial Neural Networks An Introduction
Priddy, Kevin L
2005-01-01
This tutorial text provides the reader with an understanding of artificial neural networks (ANNs) and their application, beginning with the biological systems which inspired them, through the learning methods that have been developed and the data collection processes, to the many ways ANNs are being used today. The material is presented with a minimum of math (although the mathematical details are included in the appendices for interested readers), and with a maximum of hands-on experience. All specialized terms are included in a glossary. The result is a highly readable text that will teach t
Prediction of geomagnetic storms from solar wind data with the use of a neural network
Directory of Open Access Journals (Sweden)
H. Lundstedt
Full Text Available An artificial feed-forward neural network with one hidden layer and error back-propagation learning is used to predict the geomagnetic activity index (D_{st} one hour in advance. The B_{z}-component and Σ_{Bz}, the density, and the velocity of the solar wind are used as input to the network. The network is trained on data covering a total of 8700 h, extracted from the 25-year period from 1963 to 1987, taken from the NSSDC data base. The performance of the network is examined with test data, not included in the training set, which covers 386 h and includes four different storms. Whilst the network predicts the initial and main phase well, the recovery phase is not modelled correctly, implying that a single hidden layer error back-propagation network is not enough, if the measured D_{st} is not available instantaneously. The performance of the network is independent of whether the raw parameters are used, or the electric field and square root of the dynamical pressure.
Three dimensional living neural networks
Linnenberger, Anna; McLeod, Robert R.; Basta, Tamara; Stowell, Michael H. B.
2015-08-01
We investigate holographic optical tweezing combined with step-and-repeat maskless projection micro-stereolithography for fine control of 3D positioning of living cells within a 3D microstructured hydrogel grid. Samples were fabricated using three different cell lines; PC12, NT2/D1 and iPSC. PC12 cells are a rat cell line capable of differentiation into neuron-like cells NT2/D1 cells are a human cell line that exhibit biochemical and developmental properties similar to that of an early embryo and when exposed to retinoic acid the cells differentiate into human neurons useful for studies of human neurological disease. Finally induced pluripotent stem cells (iPSC) were utilized with the goal of future studies of neural networks fabricated from human iPSC derived neurons. Cells are positioned in the monomer solution with holographic optical tweezers at 1064 nm and then are encapsulated by photopolymerization of polyethylene glycol (PEG) hydrogels formed by thiol-ene photo-click chemistry via projection of a 512x512 spatial light modulator (SLM) illuminated at 405 nm. Fabricated samples are incubated in differentiation media such that cells cease to divide and begin to form axons or axon-like structures. By controlling the position of the cells within the encapsulating hydrogel structure the formation of the neural circuits is controlled. The samples fabricated with this system are a useful model for future studies of neural circuit formation, neurological disease, cellular communication, plasticity, and repair mechanisms.
Neural Network Controlled Visual Saccades
Johnson, Jeffrey D.; Grogan, Timothy A.
1989-03-01
The paper to be presented will discuss research on a computer vision system controlled by a neural network capable of learning through classical (Pavlovian) conditioning. Through the use of unconditional stimuli (reward and punishment) the system will develop scan patterns of eye saccades necessary to differentiate and recognize members of an input set. By foveating only those portions of the input image that the system has found to be necessary for recognition the drawback of computational explosion as the size of the input image grows is avoided. The model incorporates many features found in animal vision systems, and is governed by understandable and modifiable behavior patterns similar to those reported by Pavlov in his classic study. These behavioral patterns are a result of a neuronal model, used in the network, explicitly designed to reproduce this behavior.
Comparison of Evolution Strategy and Back-Propagation for Estimating Parameters of Neural Networks
Czech Academy of Sciences Publication Activity Database
Malczyk, Roman; Gottvald, Aleš
Brno: Institute of Scientific Instruments of the Academy of Sciences of the Czech Republic, 1996. s. 48. [Optimization and Inverse Problems in Electromagnetism /4./. 19.06.1996-21.06.1996, Brno] R&D Projects: GA ČR GA102/95/0282
Forest Fire Smoke Detection Using Back-Propagation Neural Network Based on MODIS Data
Xiaolian Li; Weiguo Song; Liping Lian; Xiaoge Wei
2015-01-01
Satellite remote sensing provides global observations of the Earth’s surface and provides useful information for monitoring smoke plumes emitted from forest fires. The aim of this study is to automatically separate smoke plumes from the background by analyzing the MODIS data. An identification algorithm was improved based on the spectral analysis among the smoke, cloud and underlying surface. In order to get satisfactory results, a multi-threshold method is used for extracting training sampl...
Neural Networks for Emotion Classification
Sun, Yafei
2011-01-01
It is argued that for the computer to be able to interact with humans, it needs to have the communication skills of humans. One of these skills is the ability to understand the emotional state of the person. This thesis describes a neural network-based approach for emotion classification. We learn a classifier that can recognize six basic emotions with an average accuracy of 77% over the Cohn-Kanade database. The novelty of this work is that instead of empirically selecting the parameters of the neural network, i.e. the learning rate, activation function parameter, momentum number, the number of nodes in one layer, etc. we developed a strategy that can automatically select comparatively better combination of these parameters. We also introduce another way to perform back propagation. Instead of using the partial differential of the error function, we use optimal algorithm; namely Powell's direction set to minimize the error function. We were also interested in construction an authentic emotion databases. This...
The Laplacian spectrum of neural networks
Directory of Open Access Journals (Sweden)
Siemon ede Lange
2014-01-01
Full Text Available The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these ‘conventional’ graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network’s structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks.
Differentiating Agar wood Oil Quality Using Artificial Neural Network
International Nuclear Information System (INIS)
Agar wood oil is well known as expensive oil extracted from the resinous of fragrant heartwood. The oil is getting high demand in the market especially from the Middle East countries, China and Japan because of its unique odor. As part of an on-going research in grading the agar wood oil quality, the application of Artificial Neural Network (ANN) is proposed in this study to analyze agar wood oil quality using its chemical profiles. The work involves of selected agar wood oil from low and high quality, the extraction of chemical compounds using GC-MS and Z-score to identify of the significant compounds as input to the network. The ANN programming algorithm was developed and computed automatically via Matlab software version R2010a. Back-propagation training algorithm and sigmoid transfer function were used to optimize the parameters in the training network. The result obtained showed the capability of ANN in analyzing the agar wood oil quality hence beneficial for the further application such as grading and classification for agar wood oil. (author)
Institute of Scientific and Technical Information of China (English)
LONG Jiangqi; LAN Fengchong; CHEN Jiqing; YU Ping
2009-01-01
For optimal design of mechanical clinching steel-aluminum joints, the back propagation (BP) neural network is used to research the mapping relationship between joining technique parameters including sheet thickness, sheet hardness, joint bottom diameter etc., and mechanical properties of shearing and peeling in order to investigate joining technology between various material plates in the steel-aluminum hybrid structure car body. Genetic algorithm (GA) is adopted to optimize the back-propagation neural network connection weights. The training and validating samples are made by the BTM(R) Tog-L-Loc system with different technologic parameters. The training samples' parameters and the corresponding joints' mechanical properties are supplied to the artificial neural network (ANN) for training. The validating samples' experimental data is used for checking up the prediction outputs. The calculation results show that GA can improve the model's prediction precision and generalization ability of BP neural network. The comparative analysis between the experimental data and the prediction outputs shows that ANN prediction models after training can effectively predict the mechanical properties of mechanical clinching joints and prove the feasibility and reliability of the intelligent neural networks system when used in the mechanical properties prediction of mechanical clinching joints. The prediction results can be used for a reference in the design of mechanical clinching steel-aluminum joints.
Drift chamber tracking with neural networks
Energy Technology Data Exchange (ETDEWEB)
Lindsey, C.S.; Denby, B.; Haggerty, H.
1992-10-01
We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed.
Drift chamber tracking with neural networks
International Nuclear Information System (INIS)
We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed
Coherence resonance in bursting neural networks
Kim, June Hoan; Lee, Ho Jun; Min, Cheol Hong; Lee, Kyoung J.
2015-10-01
Synchronized neural bursts are one of the most noticeable dynamic features of neural networks, being essential for various phenomena in neuroscience, yet their complex dynamics are not well understood. With extrinsic electrical and optical manipulations on cultured neural networks, we demonstrate that the regularity (or randomness) of burst sequences is in many cases determined by a (few) low-dimensional attractor(s) working under strong neural noise. Moreover, there is an optimal level of noise strength at which the regularity of the interburst interval sequence becomes maximal—a phenomenon of coherence resonance. The experimental observations are successfully reproduced through computer simulations on a well-established neural network model, suggesting that the same phenomena may occur in many in vivo as well as in vitro neural networks.