WorldWideScience

Sample records for backpropagation

  1. Back-propagation of accuracy

    OpenAIRE

    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...

  2. 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

  3. Digital Backpropagation in the Nonlinear Fourier Domain

    CERN Document Server

    Wahls, Sander; Prilepsky, Jaroslaw E; Poor, H Vincent; Turitsyn, Sergei K

    2015-01-01

    Nonlinear and dispersive transmission impairments in coherent fiber-optic communication systems are often compensated by reverting the nonlinear Schr\\"odinger equation, which describes the evolution of the signal in the link, numerically. This technique is known as digital backpropagation. Typical digital backpropagation algorithms are based on split-step Fourier methods in which the signal has to be discretized in time and space. The need to discretize in both time and space however makes the real-time implementation of digital backpropagation a challenging problem. In this paper, a new fast algorithm for digital backpropagation based on nonlinear Fourier transforms is presented. Aiming at a proof of concept, the main emphasis will be put on fibers with normal dispersion in order to avoid the issue of solitonic components in the signal. However, it is demonstrated that the algorithm also works for anomalous dispersion if the signal power is low enough. Since the spatial evolution of a signal governed by the ...

  4. Circular backpropagation networks for classification.

    Science.gov (United States)

    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

  5. Fuzzy neural network with fast backpropagation learning

    Science.gov (United States)

    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.

  6. Memory-Efficient Backpropagation Through Time

    OpenAIRE

    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...

  7. Tunneling Ionization Time Resolved by Backpropagation

    Science.gov (United States)

    Ni, Hongcheng; Saalmann, Ulf; Rost, Jan-Michael

    2016-07-01

    We determine the ionization time in tunneling ionization by an elliptically polarized light pulse relative to its maximum. This is achieved by a full quantum propagation of the electron wave function forward in time, followed by a classical backpropagation to identify tunneling parameters, in particular, the fraction of electrons that has tunneled out. We find that the ionization time is close to zero for single active electrons in helium and in hydrogen if the fraction of tunneled electrons is large. We expect our analysis to be essential to quantify ionization times for correlated electron motion.

  8. The annealing robust backpropagation (ARBP) learning algorithm.

    Science.gov (United States)

    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

  9. TAO-robust backpropagation learning algorithm.

    Science.gov (United States)

    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

  10. Generalized Backpropagation Algorithms for Diffraction Tomography

    CERN Document Server

    Paladhi, Pavel Roy; Tayebi, Amin; Udpa, Lalita

    2016-01-01

    Filtered backpropagation (FBPP) is a well-known technique used for Diffraction Tomography (DT). For accurate reconstruction of a complex image using FBPP, full $360^{\\circ}$ angular coverage is necessary. However, it has been shown that using some inherent redundancies in projection data in a tomographic setup, accurate reconstruction is still possible with $270^{\\circ}$ coverage which is called the minimal-scan angle range. This can be done by applying weighing functions (or filters) on projection data of the object to eliminate the redundancies and accurately reconstruct the image from this lower angular coverage. This paper demonstrates procedures to generate many general classes of these weighing filters. These are all equivalent at $270^{\\circ}$ coverage but would perform differently at lower angular coverages and under presence of noise. This paper does a comparative analysis of different filters when angular coverage is lower than minimal-scan angle of $270^{\\circ}$. Simulation studies have been done t...

  11. Privacy-preserving backpropagation neural network learning.

    Science.gov (United States)

    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

  12. Optoelectronic Systems Trained With Backpropagation Through Time.

    Science.gov (United States)

    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

  13. 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...

  14. Analog hardware for delta-backpropagation neural networks

    Science.gov (United States)

    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.

  15. Pengenalan Pola Pin Barcode Menggunakan Metode Backpropagation dan Metode Perceptron

    OpenAIRE

    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 ...

  16. Error-backpropagation in temporally encoded networks of spiking neurons

    NARCIS (Netherlands)

    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

  17. Impairment mitigation in superchannels with digital backpropagation and MLSD

    DEFF Research Database (Denmark)

    Porto da Silva, Edson; Larsen, Knud J.; Zibar, Darko

    2015-01-01

    We assess numerically the performance of single-carrier digital backpropagation (SC-DBP) and maximum-likelihood sequence detection (MLSD) for DP-QPSK and DP-16QAM superchannel transmission over dispersion uncompensated links for three different cases of spectral shaping: optical pre-filtering of ...

  18. Backpropagation and ordered derivatives in the time scales calculus.

    Science.gov (United States)

    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

  19. Error-backpropagation in temporally encoded networks of spiking neurons

    OpenAIRE

    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...

  20. Conjugate descent formulation of backpropagation error in feedforward neural networks

    OpenAIRE

    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...

  1. Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

    OpenAIRE

    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 ...

  2. Newton's Method Backpropagation for Complex-Valued Holomorphic Multilayer Perceptrons

    OpenAIRE

    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...

  3. 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.

  4. The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks

    OpenAIRE

    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...

  5. Learning Sensor Multiplexing Design through Back-propagation

    OpenAIRE

    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...

  6. Single-step digital backpropagation for nonlinearity mitigation

    DEFF Research Database (Denmark)

    Secondini, Marco; Rommel, Simon; Meloni, Gianluca;

    2015-01-01

    Nonlinearity mitigation based on the enhanced split-step Fourier method (ESSFM) for the implementation of low-complexity digital backpropagation (DBP) is investigated and experimentally demonstrated. After reviewing the main computational aspects of DBP and of the conventional split-step Fourier...... method (SSFM), the ESSFM for dual-polarization signals is introduced. Computational complexity, latency, and power consumption of DBP based on the SSFM and ESSFM algorithms are estimated and compared. Effective low-complexity nonlinearity mitigation in a 112 Gb/s polarization-multiplexed QPSK system is...

  7. 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

  8. LVQ and backpropagation neural networks applied to NASA SSME data

    Science.gov (United States)

    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.

  9. 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

  10. Comparative Study of Backpropagation Algorithms in Neural Network Based Identification of Power System

    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

  11. Reinforcement and backpropagation training for an optical neural network using self-lensing effects.

    Science.gov (United States)

    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

  12. Equivalence of backpropagation and contrastive Hebbian learning in a layered network.

    Science.gov (United States)

    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

  13. Efficient Implementation of the Backpropagation Algorithm in FPGAs and Microcontrollers.

    Science.gov (United States)

    Ortega-Zamorano, Francisco; Jerez, Jose M; Urda Munoz, Daniel; Luque-Baena, Rafael M; Franco, Leonardo

    2016-09-01

    The well-known backpropagation learning algorithm is implemented in a field-programmable gate array (FPGA) board and a microcontroller, focusing in obtaining efficient implementations in terms of a resource usage and computational speed. The algorithm was implemented in both cases using a training/validation/testing scheme in order to avoid overfitting problems. For the case of the FPGA implementation, a new neuron representation that reduces drastically the resource usage was introduced by combining the input and first hidden layer units in a single module. Further, a time-division multiplexing scheme was implemented for carrying out product computations taking advantage of the built-in digital signal processor cores. In both implementations, the floating-point data type representation normally used in a personal computer (PC) has been changed to a more efficient one based on a fixed-point scheme, reducing system memory variable usage and leading to an increase in computation speed. The results show that the modifications proposed produced a clear increase in computation speed in comparison with the standard PC-based implementation, demonstrating the usefulness of the intrinsic parallelism of FPGAs in neurocomputational tasks and the suitability of both implementations of the algorithm for its application to the real world problems. PMID:26277004

  14. Maximum likelihood training of connectionist models: comparison with least squares back-propagation and logistic regression.

    OpenAIRE

    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...

  15. Investigating the performance of neural network backpropagation algorithms for TEC estimations using South African GPS data

    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.

  16. 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.

  17. Stocks selected using SOM and Genetic Algorithm based Backpropagation Neural Network gives better returns

    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.

  18. A simplification of the backpropagation-through-time algorithm for optimal neurocontrol.

    Science.gov (United States)

    Bersini, H; Gorrini, V

    1997-01-01

    Backpropagation-through-time (BPTT) is the temporal extension of backpropagation which allows a multilayer neural network to approximate an optimal state-feedback control law provided some prior knowledge (Jacobian matrices) of the process is available. In this paper, a simplified version of the BPTT algorithm is proposed which more closely respects the principle of optimality of dynamic programming. Besides being simpler, the new algorithm is less time-consuming and allows in some cases the discovery of better control laws. A formal justification of this simplification is attempted by mixing the Lagrangian calculus underlying BPTT with Bellman-Hamilton-Jacobi equations. The improvements due to this simplification are illustrated by two optimal control problems: the rendezvous and the bioreactor. PMID:18255645

  19. Maximum likelihood training of connectionist models: comparison with least squares back-propagation and logistic regression.

    Science.gov (United States)

    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

  20. Hybrid intelligent system for Sale Forecasting using Delphi and adaptive Fuzzy Back-Propagation Neural Networks

    OpenAIRE

    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...

  1. Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation

    OpenAIRE

    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...

  2. A low communication overhead parallel implementation of the back-propagation algorithm

    OpenAIRE

    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...

  3. 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.

  4. Application of back-propagation neural networks to identification of seismic arrival types

    OpenAIRE

    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...

  5. 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.

  6. The parallel implementation of a backpropagation neural network and its applicability to SPECT image reconstruction

    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.

  7. 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

  8. Application of backpropagation artificial neural network prediction model for the PAH bioremediation of polluted soil.

    Science.gov (United States)

    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

  9. The Prediction of Bandwidth On Need Computer Network Through Artificial Neural Network Method of Backpropagation

    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

  10. Improving the Performance of Backpropagation Neural Network Algorithm for Image Compression/Decompression System

    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.

  11. On nonlinearly-induced noise in single-channel optical links with digital backpropagation.

    Science.gov (United States)

    Beygi, Lotfollah; Irukulapati, Naga V; Agrell, Erik; Johannisson, Pontus; Karlsson, Magnus; Wymeersch, Henk; Serena, Paolo; Bononi, Alberto

    2013-11-01

    In this paper, we investigate the performance limits of electronic chromatic dispersion compensation (EDC) and digital backpropagation (DBP) for a single-channel non-dispersion-managed fiber-optical link. A known analytical method to derive the performance of the system with EDC is extended to derive a first-order approximation for the performance of the system with DBP. In contrast to the cubic growth of the variance of the nonlinear noise-like interference, often called nonlinear noise, with input power for EDC, a quadratic growth is observed with DBP using this approximation. Finally, we provide numerical results to verify the accuracy of the proposed approach and compare it with existing analytical models. PMID:24216860

  12. SPECT reconstruction using a backpropagation neural network implemented on a massively parallel SIMD computer

    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.

  13. 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.

  14. A new backpropagation learning algorithm for layered neural networks with nondifferentiable units.

    Science.gov (United States)

    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

  15. Backpropagation architecture optimization and an application in nuclear power plant diagnostics

    International Nuclear Information System (INIS)

    This paper presents a Dynamic Node Architecture (DNA) scheme to optimize the architecture of backpropagation Artificial Neural Networks (ANNs). This network scheme is used to develop an ANN based diagnostic adviser capable of identifying the operating status of a nuclear power plant. Specifically, a ''root'' network is trained to diagnose if the plant is in a normal operating condition or not. In the event of an abnormal condition, and other ''classifier'' network is trained to recognize the particular transient taking place. these networks are trained using plant instrumentation data gathered during simulations of the various transients and normal operating conditions at the Iowa Electric Light and Power Company's Duane Arnold Energy Center (DAEC) operator training simulator

  16. Sistem Informasi Penyebaran Penyakit Demam Berdarah Menggunakan Metode Jaringan Syaraf Tiruan Backpropagation

    OpenAIRE

    Didi Supriyadi; Kusworo Adi; Eko Adi Sarwoko

    2014-01-01

    Dengue  disease  is  a  major  health  problem  and  endemic  in  several  countries  including  Indonesia.  Indonesia  is  included  in  the  category  "A"  in  the stratification of DHF by WHO in 2001 which indicates the high rate of treatment in hospital and deaths from dengue. The purpose of this study was to investigate the ability of artificial neural networks Backpropagation method for information of the spread of dengue fever in   a region. In this study uses six input variables which...

  17. An artificial neural net and error backpropagation to reconstruct single photon emission computerized tomography data.

    Science.gov (United States)

    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

  18. The backpropagation algorithm in J, a fast prototyping tool for researching neural networks.

    Science.gov (United States)

    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

  19. An equalized error backpropagation algorithm for the on-line training of multilayer perceptrons.

    Science.gov (United States)

    Martens, J P; Weymaere, N

    2002-01-01

    The error backpropagation (EBP) training of a multilayer perceptron (MLP) may require a very large number of training epochs. Although the training time can usually be reduced considerably by adopting an on-line training paradigm, it can still be excessive when large networks have to be trained on lots of data. In this paper, a new on-line training algorithm is presented. It is called equalized EBP (EEBP), and it offers improved accuracy, speed, and robustness against badly scaled inputs. A major characteristic of EEBP is its utilization of weight specific learning rates whose relative magnitudes are derived from a priori computable properties of the network and the training data. PMID:18244454

  20. Analysis of the initial values in split-complex backpropagation algorithm.

    Science.gov (United States)

    Yang, Sheng-Sung; Siu, Sammy; Ho, Chia-Lu

    2008-09-01

    When a multilayer perceptron (MLP) is trained with the split-complex backpropagation (SCBP) algorithm, one observes a relatively strong dependence of the performance on the initial values. For the effective adjustments of the weights and biases in SCBP, we propose that the range of the initial values should be greater than that of the adjustment quantities. This criterion can reduce the misadjustment of the weights and biases. Based on the this criterion, the suitable range of the initial values can be estimated. The results show that the suitable range of the initial values depends on the property of the used communication channel and the structure of the MLP (the number of layers and the number of nodes in each layer). The results are studied using the equalizer scenarios. The simulation results show that the estimated range of the initial values gives significantly improved performance. PMID:18779088

  1. Nonlinear inverse modeling of sensor based on back-propagation fuzzy logical system

    Institute of Scientific and Technical Information of China (English)

    Li Jun; Liu Junhua

    2007-01-01

    Objective To correct the nonlinear error of sensor output, a new approach to sensor inverse modeling based on Back-Propagation Fuzzy Logical System (BP FS) is presented. Methods The BP FS is a computationally efficient nonlinear universal approximator, which is capable of implementing complex nonlinear mapping from its input pattern space to the output with fast convergence speed. Results The neuro-fuzzy hybrid system, i.e. BP FS, is then applied to construct nonlinear inverse model of pressure sensor. The experimental results show that the proposed inverse modeling method automatically compensates the associated nonlinear error in pressure estimation, and thus the performance of pressure sensor is significantly improved. Conclusion The proposed method can be widely used in nonlinearity correction of various kinds of sensors to compensate the effects of nonlinearity and temperature on sensor output.

  2. Back-propagation operation for analog neural network hardware with synapse components having hysteresis characteristics.

    Science.gov (United States)

    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

  3. Back-propagation operation for analog neural network hardware with synapse components having hysteresis characteristics.

    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.

  4. Quantitative assessment of the distributions of membrane conductances involved in action potential backpropagation along basal dendrites.

    Science.gov (United States)

    Acker, Corey D; Antic, Srdjan D

    2009-03-01

    Basal dendrites of prefrontal cortical neurons receive strong synaptic drive from recurrent excitatory synaptic inputs. Synaptic integration within basal dendrites is therefore likely to play an important role in cortical information processing. Both synaptic integration and synaptic plasticity depend crucially on dendritic membrane excitability and the backpropagation of action potentials. We carried out multisite voltage-sensitive dye imaging of membrane potential transients from thin basal branches of prefrontal cortical pyramidal neurons before and after application of channel blockers. We found that backpropagating action potentials (bAPs) are predominantly controlled by voltage-gated sodium and A-type potassium channels. In contrast, pharmacologically blocking the delayed rectifier potassium, voltage-gated calcium, or I(h) conductance had little effect on dendritic AP propagation. Optically recorded bAP waveforms were quantified and multicompartmental modeling was used to link the observed behavior with the underlying biophysical properties. The best-fit model included a nonuniform sodium channel distribution with decreasing conductance with distance from the soma, together with a nonuniform (increasing) A-type potassium conductance. AP amplitudes decline with distance in this model, but to a lesser extent than previously thought. We used this model to explore the mechanisms underlying two sets of published data involving high-frequency trains of APs and the local generation of sodium spikelets. We also explored the conditions under which I(A) down-regulation would produce branch strength potentiation in the proposed model. Finally, we discuss the hypothesis that a fraction of basal branches may have different membrane properties compared with sister branches in the same dendritic tree. PMID:19118105

  5. Sistem Informasi Penyebaran Penyakit Demam Berdarah Menggunakan Metode Jaringan Syaraf Tiruan Backpropagation

    Directory of Open Access Journals (Sweden)

    Didi Supriyadi

    2014-01-01

    Full Text Available Dengue  disease  is  a  major  health  problem  and  endemic  in  several  countries  including  Indonesia.  Indonesia  is  included  in  the  category  "A"  in  the stratification of DHF by WHO in 2001 which indicates the high rate of treatment in hospital and deaths from dengue. The purpose of this study was to investigate the ability of artificial neural networks Backpropagation method for information of the spread of dengue fever in   a region. In this study uses six input variables which are environmental factors that influence the spread of dengue fever, include average temperature  -  average, rainfall, number of rainy days, the population density, sea surface height, and the percentage of larvae-free number for  which data is sourced from BMKG, BPS and the Public Health Service. Network architecture applied to a multilayer network that uses an input with 6 neurons, one hidden lay er and an output with the output neuron is one. From the results obtained by training  the best network architecture is the number one hidden layer with the number of neurons obtained a total of 110 neurons and also the system can recognize the entire training data. The best training algorithm using  a variable learning rate and momentum of 0.9 by 0.6 by the end of the training MSE 0.000999879. in the process of testing using test data obtained 17 tissue levels of  approximately 88.23% accuracy. Therefore we can conclude that the network is implemented in this study when subjected to the test  data other then the error rate of about 11.77%.Keywords : Artificial Neural Networks; Backpropagation; Dengue fever

  6. Analysis of back-propagation and RF pilot-tone based nonlinearity compensation for a 9x224Gb/s POLMUX-16QAM system

    OpenAIRE

    Díaz Souto, Alberto; Napoli, Antonio; Adhikari, Susmita; Maalej, Zied; Lobato Polo, Adriana P.; Kuschnerov, Maxim; Prat Gomà, Josep Joan

    2012-01-01

    We investigate the joint implementation of back-propagation and RF-pilot tone for fiber nonlinear compensation in POLMUX-16QAM and show that the nonlinear tolerance is drastically improved when compared to OFDM system Peer Reviewed

  7. A power spectrum based backpropagation artificial neural network model for classification of sleep-wake stages in rats

    OpenAIRE

    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...

  8. Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks

    OpenAIRE

    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...

  9. Peramalan Nilai Tukar Mata Uang Rupiah Terhadap Dolar Amerika Serikat Tahun 2014 dengan Menggunakan Jaringan Syaraf Tiruan Model Backpropagation

    OpenAIRE

    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.

  10. Application of back-propagation neural networks to identification of seismic arrival types

    Science.gov (United States)

    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.

  11. Study on range interval distance of prestressed anchor bars using update backpropagation neural network

    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.

  12. Low complexity digital backpropagation for high baud subcarrier-multiplexing systems.

    Science.gov (United States)

    Zhang, Fangyuan; Zhuge, Qunbi; Qiu, Meng; Plant, David V

    2016-07-25

    In this paper, we propose two modifications to reduce the complexity of the subcarrier-multiplexing (SCM) based digital backpropagation (DBP) for high symbol rate SCM systems. The first one is to reduce the number of interfering subcarriers (RS-SCM-DBP) when evaluating the cross-subcarrier nonlinearity (CSN). The second one is to replace the original frequency domain CSN filters with the infinite impulse response (IIR) filters (IIR-RS-SCM-DBP) in the CSN compensation. The performance of the proposed schemes are numerically evaluated in three-channel dual-polarization (DP) 16QAM wavelength-division multiplexing (WDM) transmissions. The aggregate symbol rate for each channel is 120 GBaud and the transmission distance is 1600 km. For the SCM system with 16 subcarriers, the IIR-RS-SCM-DBP with only 4 interfering subcarriers and 2 steps can achieve a 0.3 dB Q-factor improvement in the WDM transmission. Compared to the original SCM-DBP, the proposed IIR-RS-SCM-DBP reduces the complexity by 48% at a performance loss of only 0.07 dB. PMID:27464154

  13. Heating value prediction for combustible fraction of municipal solid waste in Semarang using backpropagation neural network

    Science.gov (United States)

    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 .

  14. 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)

  15. Application of backpropagation neural architectures to the realization of control transfer functions and compensators

    Science.gov (United States)

    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.

  16. Neural network for processing both spatial and temporal data with time based back-propagation

    Science.gov (United States)

    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.

  17. Application of backpropagation neural networks to evaluate residual properties of thermally damaged concrete

    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)

  18. Scene segmentation of natural images using texture measures and back-propagation

    Science.gov (United States)

    Sridhar, Banavar; Phatak, Anil; Chatterji, Gano

    1993-01-01

    Knowledge of the three-dimensional world is essential for many guidance and navigation applications. A sequence of images from an electro-optical sensor can be processed using optical flow algorithms to provide a sparse set of ranges as a function of azimuth and elevation. A natural way to enhance the range map is by interpolation. However, this should be undertaken with care since interpolation assumes continuity of range. The range is continuous in certain parts of the image and can jump at object boundaries. In such situations, the ability to detect homogeneous object regions by scene segmentation can be used to determine regions in the range map that can be enhanced by interpolation. The use of scalar features derived from the spatial gray-level dependence matrix for texture segmentation is explored. Thresholding of histograms of scalar texture features is done for several images to select scalar features which result in a meaningful segmentation of the images. Next, the selected scalar features are used with a neural net to automate the segmentation procedure. Back-propagation is used to train the feed forward neural network. The generalization of the network approach to subsequent images in the sequence is examined. It is shown that the use of multiple scalar features as input to the neural network result in a superior segmentation when compared with a single scalar feature. It is also shown that the scalar features, which are not useful individually, result in a good segmentation when used together. The methodology is applied to both indoor and outdoor images.

  19. 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.

  20. Camera characterization using back-propagation artificial neutral network based on Munsell system

    Science.gov (United States)

    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.

  1. Fish Classification Based on Robust Features Extraction From Color Signature Using Back-Propagation Classifier

    Directory of Open Access Journals (Sweden)

    Mutasem K. Alsmadi

    2011-01-01

    Full Text Available Problem statement: Image recognition was a challenging problem researchers had been research into this area for so long especially in the recent years, due to distortion, noise, segmentation errors, overlap and occlusion of objects in digital images. In our study, there are many fields concern with pattern recognition, for example, fingerprint verification, face recognition, iris discrimination, chromosome shape discrimination, optical character recognition, texture discrimination and speech recognition, the subject of pattern recognition appears. A system for recognizing isolated pattern of interest may be as an approach for dealing with such application. Scientists and engineers with interests in image processing and pattern recognition have developed various approaches to deal with digital image recognition problems such as, neural network, contour matching and statistics. Approach: In this study, our aim was to recognize an isolated pattern of interest (fish in the image based robust features extraction. Where depend on color signatures that are extracted by RGB color space, color histogram and gray level co-occurrence matrix. Results: We presented a system prototype for dealing with such problem. The system started by acquiring an image containing pattern of fish, then the image segmentation was performed relying on color signature. Our system has been applied on 20 different fish families, each family has a different number of fish types and our sample consists of distinct 610 of fish images. These images are divided into two datasets: 400 training images and 210 testing images. An overall accuracy was obtained using back-propagation classifier was 84% on the test dataset used. Conclusion: We developed a classifier for fish images recognition. We efficiently have chosen an image segmentation method to fit our demands. Our classifier successfully design and implement a decision which performed efficiently without any

  2. Application of back-propagation artificial neural network and curve estimation in pharmacokinetics of losartan in rabbit

    OpenAIRE

    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...

  3. Modeling water and carbon fluxes above summer maize field in North China Plain with back-propagation neural networks

    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.

  4. Modeling water and carbon fluxes above summer maize field in North China Plain with back-propagation neural networks.

    Science.gov (United States)

    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

  5. Sales Forecasting Based on ERP System through Delphi, fuzzy Clustering and Back-Propagation Neural Networks with adaptive learning rate

    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.

  6. Prediction of formation enthalpies for Al2X-type intermetallics using back-propagation neural network

    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.

  7. Optimizing the Flexural Strength of Beams Reinforced with Fiber Reinforced Polymer Bars Using Back-Propagation Neural Networks

    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.

  8. Chemometric model for simultaneous spectrophotometric estimation of phenobarbitone and phenytoin sodium in tablets using back-propagation neural network

    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.

  9. Kerr Nonlinearity Mitigation: Mid-Link Spectral Inversion Versus Digital Backpropagation in 5×28-GBd PDM 16-QAM Signal Transmission

    DEFF Research Database (Denmark)

    Sackey, Isaac; Da Ros, Francesco; Karl Fischer, Johannes; Richter, Thomas; Jazayerifar, Mahmoud; Peucheret, Christophe; Petermann, Klaus; Schubert, Colja

    2015-01-01

    dual-pump polarization-independent fiber-optic parametric amplifier and compared to digital backpropagation (DBP) compensation over up to 800-km in a dispersion-managed link. In the single-channel case, the use of the DBP algorithm outperformed the OPC with a Q-factor improvement of 0.9 dB after 800-km...

  10. Resilient back-propagation algorithm, technical analysis and the predictability of time series in the financial industry

    Directory of Open Access Journals (Sweden)

    Salim Lahmiri

    2012-07-01

    Full Text Available In financial industry, the accurate forecasting of the stock market is a major challenge to optimize and update portfolios and also to evaluate several financial derivatives. Artificial neural networks and technical analysis are becoming widely used by industry experts to predict stock market moves. In this paper, different technical analysis measures and resilient back-propagation neural networks are used to predict the price level of five major developed international stock markets, namely the US S&P500, Japanese Nikkei, UK FTSE100, German DAX, and the French CAC40. Four categories of technical analysis measures are compared. They are indicators, oscillators, stochastics, and indexes. The out-of-sample simulation results show a strong evidence of the effectiveness of the indicators category over the oscillators, stochastics, and indexes. In addition, it is found that combining all these measures lead to an increase of the prediction error. In sum, technical analysis indicators provide valuable information to predict the S&P500, Nikkei, FTSE100, DAX, and the CAC40 price level.

  11. Forecasting foreign exchange rates with an improved back-propagation learning algorithm with adaptive smoothing momentum terms

    Institute of Scientific and Technical Information of China (English)

    Lean YU; Shouyang WANG; Kin Keung LAI

    2009-01-01

    The slow convergence of back-propagation neu-ral network (BPNN) has become a challenge in data-mining and knowledge discovery applications due to the drawbacks of the gradient descent (GD) optimization method, which is widely adopted in BPNN learning. To solve this problem,some standard Optimization techniques such as conjugate-gradient and Newton method have been proposed to improve the convergence rate of BP learning algorithm. This paper presents a heuristic method that adds an adaptive smooth-ing momentum term to original BP learning algorithm to speedup the convergence. In this improved BP learning al-gorithm, adaptive smoothing technique is used to adjust the momentums of weight updating formula automatically in terms of "3 σ limits theory." Using the adaptive smoothing momentum terms, the improved BP learning algorithm can make the network training and convergence process faster,and the network's generalization performance stronger than the standard BP learning algorithm can do. In order to ver-ify the effectiveness of the proposed BP learning algorithm,three typical foreign exchange rates, British pound (GBP),Euro (EUR), and Japanese yen (JPY), are chosen as the fore-casting targets for illustration purpose. Experimental results from homogeneous algorithm comparisons reveal that the proposed BP learning algorithm outperforms the other com-parable BP algorithms in performance and convergence rate.Furthermore, empirical results from heterogeneous model comparisons also show the effectiveness of the proposed BP learning algorithm.

  12. Analysis of phenol degradation in pulsed discharge plasma system based on Back-Propagation artificial neural network model

    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.

  13. Estimation of furnace exit gas temperature (FEGT) using optimized radial basis and back-propagation neural networks

    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

  14. Predictive accuracy of backpropagation neural network methodology in evapotranspiration forecasting in Dédougou region, western Burkina Faso

    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.

  15. Development of LC-MS determination method and back-propagation ANN pharmacokinetic model of corynoxeine in rat.

    Science.gov (United States)

    Ma, Jianshe; Cai, Jinzhang; Lin, Guanyang; Chen, Huilin; Wang, Xianqin; Wang, Xianchuan; Hu, Lufeng

    2014-05-15

    Corynoxeine(CX), isolated from the extract of Uncaria rhynchophylla, is a useful and prospective compound in the prevention and treatment for vascular diseases. A simple and selective liquid chromatography mass spectrometry (LC-MS) method was developed to determine the concentration of CX in rat plasma. The chromatographic separation was achieved on a Zorbax SB-C18 (2.1 mm × 150 mm, 5 μm) column with acetonitrile-0.1% formic acid in water as mobile phase. Selective ion monitoring (SIM) mode was used for quantification using target ions m/z 383 for CX and m/z 237 for the carbamazepine (IS). After the LC-MS method was validated, it was applied to a back-propagation artificial neural network (BP-ANN) pharmacokinetic model study of CX in rats. The results showed that after intravenous administration of CX, it was mainly distributed in blood and eliminated quickly, t1/2 was less than 1h. The predicted concentrations generated by BP-ANN model had a high correlation coefficient (R>0.99) with experimental values. The developed BP-ANN pharmacokinetic model can be used to predict the concentration of CX in rats. PMID:24732215

  16. Optimization of heat treatment technique of high-vanadium high-speed steel based on back-propagation neural networks

    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

  17. A power spectrum based backpropagation artificial neural network model for classification of sleep-wake stages in rats

    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.

  18. Wavelet low- and high-frequency components as features for predicting stock prices with backpropagation neural networks

    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.

  19. A novel hybrid classification model of genetic algorithms, modified k-Nearest Neighbor and developed backpropagation neural network.

    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

  20. Neural network design with combined backpropagation and creeping random search learning algorithms applied to the determination of retained austenite in TRIP steels

    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.

  1. Performance verification method on modification techniques of desired outputs for back-propagation neural networks; Back propagation neutral net eno kyoshi shingo shuseiho no seino kenshoho

    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.

  2. Application of Gaussian beam ray-equivalent model and back-propagation artificial neural network in laser diode fast axis collimator assembly.

    Science.gov (United States)

    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

  3. An improved approach based on fuzzy clustering and Back-Propagation Neural Networks with adaptive learning rate for sales forecasting: Case study of PCB industry

    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.

  4. Impact of learning rate and momentum factor in the performance of back-propagation neural network to identify internal dynamics of chaotic motion

    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.  

  5. Optimization of Operation Parameters for Helical Flow Cleanout with Supercritical CO2 in Horizontal Wells Using Back-Propagation Artificial Neural Network.

    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

  6. Optimization of Operation Parameters for Helical Flow Cleanout with Supercritical CO2 in Horizontal Wells Using Back-Propagation Artificial Neural Network.

    Science.gov (United States)

    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

  7. Learning Multiagent Communication with Backpropagation

    OpenAIRE

    Sukhbaatar, Sainbayar; Szlam, Arthur; Fergus, Rob

    2016-01-01

    Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNN, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to l...

  8. Modeling of stage-discharge relationship for Gharraf River, southern Iraq using backpropagation artificial neural networks, M5 decision trees, and Takagi-Sugeno inference system technique: a comparative study

    Science.gov (United States)

    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.

  9. Neural network design with combined backpropagation and creeping random search learning algorithms applied to the determination of retained austenite in TRIP steels; Diseno de redes neuronales con aprendizaje combinado de retropropagacion y busqueda aleatoria progresiva aplicado a la determinacion de austenita retenida en aceros TRIP

    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.

  10. Optimization of image quality assessment parameters based on back-propagation neural network%基于BP神经网络的图像质量评价参数优化

    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.

  11. Tumor Diagnosis Using Backpropagation Neural Network Method

    Science.gov (United States)

    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.

  12. Pengenalan Pola Citra Menggunakan Metode Corner Detection Dan Backpropagation

    OpenAIRE

    Tondang, Yenny Agustina

    2016-01-01

    Indonesia, a country that has many islands and culture, has a huge potential to develop tourism. Many tourism objects that can be used to increase the division of the country require a system to assist users in finding objects owned by the user. This study used corner detection methods and backpropgation (BP) to assist users in recognizing objects. Harris Corner Detection (HCD) will get the points contained in the image of the image. The results of the HCD will be studied using...

  13. Implementation of Back-Propagation Algorithm For Renal Datamining

    Directory of Open Access Journals (Sweden)

    P.Thrimurthy

    2008-04-01

    Full Text Available The present medical era data mining place a important role for quick access of appropriate information. To achieve this full automation is required which means less human interference. Therefore automatic renal data mining with decision making algorithm is necessary. Renal failure contributes to major health problem. In this research work a distributed neural network has been applied to a data mining problem for classification of renal data to have for proper diagnosis of patient. A multi layer perceptron with back propagation algorithm has been used. The network was trained offline using 500 patterns each of 17 inputs. Using the weight obtained during training, fresh patterns were tested for accuracy of diagnosis.

  14. 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...

  15. BACKPROPAGATION LEARNING ALGORITHM BASED ON LEVENBERG MARQUARDT ALGORITHM

    Directory of Open Access Journals (Sweden)

    S.Sapna

    2012-10-01

    Full Text Available Data Mining aims at discovering knowledge out of data and presenting it in a form that is easily compressible to humans. Data Mining represents a process developed to examine large amounts of data routinely collected. The term also refers to a collection of tools used to perform the process. One of the useful applications in the field of medicine is the incurable chronic disease diabetes. Data Mining algorithm is used for testing the accuracy in predicting diabetic status. Fuzzy Systems are been used for solving a wide range of problems in different application domain and Genetic Algorithm for designing. Fuzzy systems allows in introducing the learning and adaptation capabilities. Neural Networks are efficiently used for learning membership functions. Diabetes occurs throughout the world, but Type 2 is more common in the most developed countries. The greater increase in prevalence is however expected in Asia and Africa where most patients will likely be found by 2030. This paper is proposed on the Levenberg – Marquardt algorithm which is specifically designed to minimize sum-of-square error functions. Levernberg-Marquardt algorithm gives the best performance in the prediction of diabetes compared to any other backpropogation algorithm.

  16. Neural Network Back-Propagation Algorithm for Sensing Hypergols

    Science.gov (United States)

    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.

  17. Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation

    Science.gov (United States)

    Hinton, Geoffrey; Osindero, Simon; Welling, Max; Teh, Yee-Whye

    2006-01-01

    We describe a way of modeling high-dimensional data vectors by using an unsupervised, nonlinear, multilayer neural network in which the activity of each neuron-like unit makes an additive contribution to a global energy score that indicates how surprised the network is by the data vector. The connection weights that determine how the activity of…

  18. On the capacity of multilayer neural networks trained with backpropagation.

    Science.gov (United States)

    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

  19. Spike-timing error backpropagation in theta neuron networks.

    Science.gov (United States)

    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

  20. 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.

  1. Back-Propagation Operation for Analog Neural Network Hardware with Synapse Components Having Hysteresis Characteristics

    OpenAIRE

    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...

  2. 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

  3. Cortical Action Potential Backpropagation Explains Spike Threshold Variability and Rapid-Onset Kinetics

    OpenAIRE

    Yu, Yuguo; Shu, Yousheng; McCormick, David A.

    2008-01-01

    Neocortical action potential responses in vivo are characterized by considerable threshold variability, and thus timing and rate variability, even under seemingly identical conditions. This finding suggests that cortical ensembles are required for accurate sensorimotor integration and processing. Intracellularly, trial-to-trial variability results not only from variation in synaptic activities, but also in the transformation of these into patterns of action potentials. Through simultaneous ax...

  4. 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.

  5. Back-propagating the light of field stars to probe telescope mirrors aberrations

    CERN Document Server

    Soulez, Ferréol; Unser, Michael

    2016-01-01

    We propose a wavefront-based method to estimate the PSF over the whole field of view. This method estimate the aberrations of all the mirrors of the telescope using only field stars. In this proof of concept paper, we described the method and present some qualitative results.

  6. Back-propagating surface polaritons of a one-dimensional photonic crystal containing single negative metamaterials

    International Nuclear Information System (INIS)

    The existence of the surface polaritons at the interface separating a semi-infinite uniform left-handed metamaterial and a one-dimensional photonic crystal composed of alternating layers of two kinds of single-negative materials is theoretically investigated. The dispersion characteristics of the surface polaritons are analyzed and demonstrated that in the presence of metamaterial, the surface polaritons are sensitive to light polarization, so that there exist only backward TM-polarized (or TE-polarized) kind of the surface polaritons depending on the ratio of the thicknesses of the two periodic stacking layers. The existence regions of the surface polariton modes are determined for both TM-polarized and TE-polarized surface polariton modes.

  7. A Novel Classification Approach through Integration of Rough Sets and Back-Propagation Neural Network

    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.

  8. Automatic volcanic ash detection from MODIS observations using a back-propagation neural network

    OpenAIRE

    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...

  9. Forest Fire Smoke Detection Using Back-Propagation Neural Network Based on MODIS Data

    OpenAIRE

    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...

  10. Beyond Feedforward Models Trained by Backpropagation: a Practical Training Tool for a More Efficient Universal Approximator

    CERN Document Server

    Ilin, Roman; Werbos, Paul J

    2007-01-01

    Cellular Simultaneous Recurrent Neural Network (SRN) has been shown to be a function approximator more powerful than the MLP. This means that the complexity of MLP would be prohibitively large for some problems while SRN could realize the desired mapping with acceptable computational constraints. The speed of training of complex recurrent networks is crucial to their successful application. Present work improves the previous results by training the network with extended Kalman filter (EKF). We implemented a generic Cellular SRN and applied it for solving two challenging problems: 2D maze navigation and a subset of the connectedness problem. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results in the case of maze navigation, and superior generalization has been demonstrated in the case of connectedness. The implications of this improvements are discussed.

  11. RANCANG BANGUN SISTEM PENGENALAN EKSPRESI WAJAH MENGGUNAKAN FISHERFACE DAN JARINGAN SYARAF TIRUAN BACKPROPAGATION

    OpenAIRE

    Abidin, Z.

    2013-01-01

    Di dalam kehidupan sehari-hari, khususnya dalam komunikasi interpersonal, wajah sering digunakan untuk berekspresi. Melalui ekspresi wajah, maka dapat dipahami emosi yang sedang bergejolak pada diri individu. Ekspresi wajah merupakan salah satu karakteristik perilaku. Penggunaan sistem teknologi biometrika dengan karakteristik ekspresi wajah memungkinkan untuk mengenali mood atau emosi seseorang. Komponen dasar sistem analisis ekspresi wajah adalah deteksi wajah, ekstraksi data wajah, dan pen...

  12. RANCANG BANGUN SISTEM PENGENALAN EKSPRESI WAJAH MENGGUNAKAN FISHERFACE DAN JARINGAN SYARAF TIRUAN BACKPROPAGATION

    Directory of Open Access Journals (Sweden)

    Z Abidin

    2013-07-01

    Full Text Available Di dalam kehidupan sehari-hari, khususnya dalam komunikasi interpersonal, wajah sering digunakan untuk berekspresi. Melalui ekspresi wajah, maka dapat dipahami emosi yang sedang bergejolak pada diri individu. Ekspresi wajah merupakan salah satu karakteristik perilaku. Penggunaan sistem teknologi biometrika dengan karakteristik ekspresi wajah memungkinkan untuk mengenali mood atau emosi seseorang. Komponen dasar sistem analisis ekspresi wajah adalah deteksi wajah, ekstraksi data wajah, dan pengenalan ekspresi wajah. Sehingga untuk membangun sebuah sistem pengenal ekspersi wajah, maka perlu dirancang tiga buah sub sistem yaitu sistem deteksi wajah, sistem pembelajaran jaringan syaraf tiruan. Prinsipnya data wajah yang telah dideteksi, diolah menggunakan fisherface, yang selanjutnya hasilnya digunakan sebagai input untuk jaringan syaraf tiruan. Bobot yang dihasilkan pada saat proses pembelajaran jaringan syaraf tiruan inilah yang akan digunakan untuk pengenalan ekspresi wajah. In daily life, especially in interpersonal communication, face often used for express of emotions. Facial expressions are the facial changes in response to a person’s internal emotional states. A facial expression is one of the behavioral characteristics. The use of facial expression characteristics enables to recognize of person’s mood. Basic components of a facial expression analysis system are face detection, face data extraction, and facial expression recognition. So that, to build a facial expression recognition system, it should be designed three subsystems, namely face detection system, learning of neural network system, and facial expression recognition system itself. In principle, face data that has been successfully detected, then it will be constructed by fisherface, and the results of it will be used as an input of neural network. Afterwards, the weights of neural network learning will be used to recognize facial expression.

  13. Space-domain, filtered backpropagation algorithm for tomographic configuration with scanning of illumination

    Science.gov (United States)

    Kostencka, J.; Kozacki, T.

    2016-04-01

    Filtered back propagation (FBPP) is a well-established reconstruction technique that is used in diffractive holographic tomography. The great advantage of the algorithm is the space-domain implementation, which enables avoiding the error-prone interpolation in the spectral domain that is an inherent part of the main counterpart of FBPP - the direct inversion tomographic reconstruction method. However, the fundamental flaw of FBPP is lack of generality, i.e. the method can be applied solely for the classical tomographic systems, where alternation of the measurement views is achieved by rotating a sample. At the same time, majority of the nowadays tomographic setups apply an alternative measurement concept, which is based on scanning of an illumination beam. The aim of this paper is to remove the mentioned limitation of the FBPP and enable its application in the systems utilizing scanning of illumination. This is achieved by introducing a new method of accounting for uneven cover of the sampled object frequencies, which applies normalization of the object spectrum with coherent transfer function of a considered tomographic system. The feasibility of the proposed, modified filtered back propagation algorithm is demonstrated with numerical simulations, which mimic tomographic measurement of a complex sample, i.e. the Shepp-Logan phantom.

  14. Implementation of back-propagation neural networks with MatLab

    OpenAIRE

    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...

  15. The Prediction of Bankruptcy Using Backpropagation Algorithm for “IO” Model Analysis

    Directory of Open Access Journals (Sweden)

    Ciprian Dragota

    2007-01-01

    Full Text Available The basic question which every bank it putswhen a client or a future client whishes to take a bank loanis: “The future debtor it’s capable to refund the loan atmaturity? (Installments plus the interest“. To answer atthis question the bank makes an assessment in which assetsand liabilities are analyze. There is also assessed the creditrating, the cash flow, the securities and, very important,bankrupt risk analysis.For the last one, to calculate bankrupt risk analysis,banks use some models (knows as “Z” score. Few of themare financials methods (like Altman, Canon & Holder,Yves Colonques etc. Nevertheless, these models are beendevelop for a specific situation and for a western economywhich is functional and very articulated. For our economy,we propose a new model that is been build with the specificeconomic dates and inputs, the model we called “IO”model.Without pretending to be able to penetrate over thecomplexity of the phenomenon, this study is trying to do apractical and experimental analysis of bankruptcy usingback propagation algorithm applied to the ”IO” model.

  16. 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

  17. Axon-somatic back-propagation in detailed models of spinal alpha motoneurons

    Directory of Open Access Journals (Sweden)

    Pietro eBalbi

    2015-02-01

    Full Text Available Antidromic action potentials following distal stimulation of motor axons occasionally fail to invade the soma of alpha motoneurons in spinal cord, due to their passing through regions of high non-uniformity.Morphologically detailed conductance-based models of cat spinal alpha motoneurons have been developed, with the aim to reproduce and clarify some aspects of the electrophysiological behavior of the antidromic axon-somatic spike propagation. Fourteen 3D morphologically detailed somata and dendrites of cat spinal alpha motoneurons have been imported from an open-access web-based database of neuronal morphologies, NeuroMorpho.org, and instantiated in neurocomputational models. An axon hillock, an axonal initial segment and a myelinated axon are added to each model.By sweeping the diameter of the axonal initial segment (AIS and the axon hillock, as well as the maximal conductances of sodium channels at the AIS and at the soma, the developed models are able to show the relationships between different geometric and electrophysiological configurations and the voltage attenuation of the antidromically travelling wave.In particular, a greater than usually admitted sodium conductance at AIS is necessary and sufficient to overcome the dramatic voltage attenuation occurring during antidromic spike propagation both at the myelinated axon-AIS and at the AIS-soma transitions.

  18. The performance of the backpropagation algorithm with varying slope of the activation function

    International Nuclear Information System (INIS)

    Some adaptations are proposed to the basic BP algorithm in order to provide an efficient method to non-linear data learning and prediction. In this paper, an adopted BP algorithm with varying slope of activation function and different learning rates is put forward. The results of experiment indicated that this algorithm can get very good performance of training. We also test the prediction performance of our adopted BP algorithm on 16 instances. We compared the test results to the ones of the BP algorithm with gradient descent momentum and an adaptive learning rate. The results indicate this adopted BP algorithm gives best performance (100%) for test example, which conclude this adopted BP algorithm produces a smoothed reconstruction that learns better to new prediction function values than the BP algorithm improved with momentum.

  19. An efficient implementation of a backpropagation learning algorithm on quadrics parallel supercomputer

    International Nuclear Information System (INIS)

    A parallel implementation of a library to build and train Multi Layer Perceptrons via the Back Propagation algorithm is presented. The target machine is the SIMD massively parallel supercomputer Quadrics. Performance measures are provided on three different machines with different number of processors, for two network examples. A sample source code is given

  20. Training Deep Gaussian Processes using Stochastic Expectation Propagation and Probabilistic Backpropagation

    OpenAIRE

    Bui, Thang D.; Hernández-Lobato, José Miguel; Li, Yingzhen; Hernández-Lobato, Daniel; Turner, Richard E

    2015-01-01

    Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are probabilistic and non-parametric and as such are arguably more flexible, have a greater capacity to generalise, and provide better calibrated uncertainty estimates than alternative deep models. The focus of this paper is scalable approximate Bayesian learning of these networks. The paper de...

  1. Beyond feedforward models trained by backpropagation: a practical training tool for a more efficient universal approximator.

    Science.gov (United States)

    Ilin, Roman; Kozma, Robert; Werbos, Paul J

    2008-06-01

    Cellular simultaneous recurrent neural network (SRN) has been shown to be a function approximator more powerful than the multilayer perceptron (MLP). This means that the complexity of MLP would be prohibitively large for some problems while SRN could realize the desired mapping with acceptable computational constraints. The speed of training of complex recurrent networks is crucial to their successful application. This work improves the previous results by training the network with extended Kalman filter (EKF). We implemented a generic cellular SRN (CSRN) and applied it for solving two challenging problems: 2-D maze navigation and a subset of the connectedness problem. The speed of convergence has been improved by several orders of magnitude in comparison with the earlier results in the case of maze navigation, and superior generalization has been demonstrated in the case of connectedness. The implications of this improvements are discussed. PMID:18541494

  2. Mean Field Bayes Backpropagation: scalable training of multilayer neural networks with binary weights

    OpenAIRE

    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...

  3. 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

  4. New backpropagation algorithm with type-2 fuzzy weights for neural networks

    CERN Document Server

    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...

  5. The application of back-propagation neural network to automatic picking seismic arrivals from single-component recordings

    Science.gov (United States)

    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.

  6. Evaluation of Delamination Damages on Composite Plates using Techniques of Image Processing and Analysis and a Backpropagation Artificial Neural Network

    OpenAIRE

    de Albuquerque, Victor Hugo C.; João Manuel R. S. Tavares; Luís M. P. Durão

    2008-01-01

    Nowadays, drilling of carbon/epoxy laminates is extremely frequent in manufacturing and assembling processes and is normally carried through using standard drills, like twist or Brad drills. However, it is always necessary to have in mind the need to adapt properly the drilling operations and/or the drilling tools used as the risk of delamination occurrence in the laminates involved, or other kind of damages, is very high. Moreover, delamination can be critical because the mechanical properti...

  7. 3-D inversion of borehole-to-surface electrical data using a back-propagation neural network

    Science.gov (United States)

    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.

  8. Back-propagation of physiological action potential output in dendrites of slender-tufted L5A pyramidal neurons

    OpenAIRE

    Grewe, Benjamin F.; Audrey Bonnan; Andreas Frick

    2010-01-01

    Pyramidal neurons of layer 5A are a major neocortical output type and clearly distinguished from layer 5B pyramidal neurons with respect to morphology, in vivo firing patterns, and connectivity; yet knowledge of their dendritic properties is scant. We used a combination of whole-cell recordings and Ca2+ imaging techniques in vitro to explore the specific dendritic signalling role of physiological action potential patterns recorded in vivo in layer 5A pyramidal neurons of the whisker-related &...

  9. A forecasting model of productivity and efficiency for coal mining face based on reformatory back-propagation neural network

    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.

  10. Prediction of Prospective Mathematics Teachers' Academic Success in Entering Graduate Education by Using Back-Propagation Neural Network

    Science.gov (United States)

    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…

  11. A Study of Image Classification of Remote Sensing Based on Back-Propagation Neural Network with Extended Delta Bar Delta

    OpenAIRE

    2015-01-01

    This paper proposes a model to extract feature information quickly and accurately identifying what cannot be achieved through traditional methods of remote sensing image classification. First, process the selected Landsat-8 remote sensing data, including radiometric calibration, geometric correction, optimal band combination, and image cropping. Add the processed remote sensing image to the normalized geographic auxiliary information, digital elevation model (DEM), and normalized difference v...

  12. Pengembangan Metode Backpropagation Dengan Menggunakan Adaptive Learning Rate Dan Parallel Training Dalam Pengenalan Huruf Atau Angka Pada Citra Digital

    OpenAIRE

    Khairani, Mufida

    2015-01-01

    Identification of characters in digital media to be one of the major concerns in the current era of technological development . Background of attempts to identify characters into digital form is not human activities release of documents or files manually in daily activities . Transformation process manually by way of input data and the information manually takes a long time , so it is considered a need for a mechanism to transform data and manual information into digital form automatically...

  13. Modeling water and carbon fluxes above summer maize field in North China Plain with back-propagation neural networks*

    OpenAIRE

    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...

  14. 2 x 344 Tb/s Propagation-direction Interleaved Transmission over 1500-km MCF Enhanced by Multicarrier Full Electric-field Digital Back-propagation

    DEFF Research Database (Denmark)

    Kobayashi, T.; Takara, H.; Sano, A.;

    2013-01-01

    We demonstrate 12-core fiber bidirectional long-haul transmission with sub-petabit-class capacity (2 × 344 Tb/s). Inter-core crosstalk management and multicarrier nonlinear compensation enabled the longest distance of 1500 km in SDM transmission with unidirectional capacity over 300 Tb/s....

  15. Back-propagation neural network in tidal-level forecasting by Ching-PiaoTsai and Tsong-Lin Lee - Discussion

    Digital Repository Service at National Institute of Oceanography (India)

    Mandal, S.

    satisfactory results. It may be worthwhile here to refer to ob- servations made by the authors on the study by Yen et al. (1996), where Kalman filtering method is employed to deter- mine the harmonic parameters. Yen et al. (1996), in their study, suggested.... Therefore, the identified input neurons almost completely explain the behavior of the process output. But the tidal levels, as rightfully explained by the authors, are deter- mined by a complete physical process involving the continu- ous changes...

  16. A Back-Propagation Neural Network Model Base on Genetic Algorithm and the Application%基于GA的BP网络模型及其应用

    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.

  17. Establishment of turbidity forecasting model and early-warning system for source water turbidity management using back-propagation artificial neural network algorithm and probability analysis.

    Science.gov (United States)

    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

  18. Development of Levenberg-Marquardt, Resilient Back-Propagation, and Conjugate Gradient Powell-Beale Artificial Neural Networks for Peak Urban Water Demand Forecasting in Nicosia, Cyprus

    Science.gov (United States)

    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.

  19. Comparison of Lavenberg-Marquardt, Scaled Conjugate Gradient and Bayesian Regularization Backpropagation Algorithms for Multistep Ahead Wind Speed Forecasting Using Multilayer Perceptron Feedforward Neural Network

    OpenAIRE

    Baghirli, Orkhan

    2015-01-01

    Wind speed forecasting is critical for wind energy conversion systems since it greatly influences the issues such as scheduling of the power systems, and dynamic control of the wind turbines. Also, it plays an essential role for siting, sizing and improving the efficiency of wind power generation systems. Due to volatile and non-stationary nature of wind speed time series, wind speed forecasting has been proven to be a challenging task that requires adamant care and caution. There are several...

  20. 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.

  1. Detecting and classifying faults on transmission systems using a backpropagation neural network; Deteccion y clasificacion de fallas en sistemas de transmision empleando una red neuronal con retropropagacion del error

    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 es una de las areas de investigacion de mas rapido crecimiento en el campo de la IA y el reconocimiento de patrones. Este trabajo explora la posible aplicabilidad de una tecnica de reconocimiento de patrones basada en redes neuronales para la deteccion y la clasificacion de fallas en un SEP. Las tecnicas convencionales de deteccion en los relevadores modernos se basan en un procesamiento digital de senales y requieren de cierto tiempo (alrededor de 1 ciclo) para enviar una senal de disparo, ademas de ser propensas a tomar decisiones incorrectas si las senales se encuentran contaminadas por ruido. Es deseable entonces desarrollar tecnicas que sean rapidas, exactas y robustas y que tengan un buen desempeno ante las condiciones cambiantes del sistema (como variaciones de carga y resistencia de falla, por ejemplo). El objetivo de este trabajo es desarrollar una tecnica novedosa basada en Redes Neuronales Atificales (RNA), la cual explora la aplicabilidad de la propuesta de reconocimiento de patrones para el diagnostico y deteccion de fallas. La tecnica sugerida se basa en el hecho de que cuando ocurre una falla, toma lugar un cambio de impedancia en el sistema y como consecuencia, cambios en la amplitud y fase de las senales de voltajes y corrientes de linea toman lugar. Se desarrolla un discriminador de fallas basado en redes neuronales que es entrenado para detectar estos cambios como indicadores del instante de ocurrencia de la falla. Este detector utiliza valores instantaneos de esas senales para tomar decisiones. Se describe a detalle la aplicabilidad de las redes neuronales como clasificadores de patrones para el diagnostico de fallas en sistemas de transmision y ademas, se presenta un diseno basado en redes neuronales y su ambiente de simulacion para la deteccion y clasificacion de fallas en tiempo real. Se presentan resultados del desempeno de esta tecnica que muestran que es rapida, segura y suficientemente exacta e indican su aplicabilidad dentro de esquemas de deteccion y clasificacion de fallas a muy alta velocidad.

  2. Priority sorting approach of maintenance task during mission based on Back-Propagation neural networks%基于BP神经网络的维修任务优先级分类方法

    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.

  3. 肺结核病与气象因素关系的BP神经网络模型研究%The Model of Back-propagation Neural Network about the Relationship between Meterological Factors and Pulmonary Tuberculosis

    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.

  4. Research on cloud and fog separation by a back-propagation (BP) network%遥感影像云雾分离的BP神经网络方法研究

    Institute of Scientific and Technical Information of China (English)

    陆衍

    2015-01-01

    The recognition and separation of cloud and heavy fog has been a particularly chalenging aspect of weather forecasting. Recently, on account of rapid socio-economic development, the harmful effects of fog have become increasingly serious, and some fog events have been classiifed as natural disasters. Thus, to prevent fog disasters, the monitoring of heavy fog and the development of early warning systems for heavy fog have become a focus of academic research. This study used an improved back propagation (BP) algorithm to build a BP neural network, using a train function to train the net and uses sim functions to simulate the net. In this way, areas of fog can be identiifed in remote sensing images. Experimental results show that the BP network can properly separate areas of fog from other meteorological features, thus producing good results in terms of prediction and early warning of conditions conducive to heavy fog.%使用改进算法构造BP神经网络,利用MATLAB中train函数训练,并用sim函数进行仿真,达到提取遥感影像中雾区的目的。图像处理结果表明,BP神经网络方法可以较好地分离影像中的雾区与其他地物。

  5. 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 network’s architecture and synapses’ 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.

  6. Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization.

    Science.gov (United States)

    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

  7. Incorporation of liquid-crystal light valve nonlinearities in optical multilayer neural networks.

    Science.gov (United States)

    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

  8. A study on the performance advancement of teat algorithm for defects in semiconductor packages

    International Nuclear Information System (INIS)

    In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, tile pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

  9. Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction

    OpenAIRE

    Jia, Hengjian

    2016-01-01

    The effectiveness of long short term memory networks trained by backpropagation through time for stock price prediction is explored in this paper. A range of different architecture LSTM networks are constructed trained and tested.

  10. Warping Similarity Space in Category Learning by Backprop Nets

    OpenAIRE

    Tijsseling, A.; Harnad, S.

    1997-01-01

    We report simulations with backpropagation networks trained to discriminate and then categorize a set of stimuli. The findings suggest a possible mechanism for categorical perception based on altering interstimulus similarity.

  11. 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...

  12. Optical phase conjugation for nonlinearity compensation in WDM PDM 16-QAM transmission over dispersion-compensated and dispersion-uncompensated links

    DEFF Research Database (Denmark)

    Da Ros, Francesco; Sackey, I.; Jazayerifar, M.;

    2015-01-01

    Kerr nonlinearity compensation by optical phase conjugation is demonstrated in a WDM PDM 16-QAM system. Improved received signal quality is reported for both dispersion-compensated and dispersion-uncompensated transmission and a comparison with digital backpropagation is provided....

  13. Mitigation of Linear and Nonlinear Impairments in Spectrally Efficient Superchannels

    DEFF Research Database (Denmark)

    Porto da Silva, Edson; Larsen, Knud J.; Zibar, Darko

    2015-01-01

    We assess numerically the performance of single-carrier digital backpropagation and maximum-likelihood sequence detection (MLSD) for DP-QPSK superchannel transmission. It is shown that MLSD is advantageous only against inter-carrier linear crosstalk....

  14. 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.

  15. A Novel Method for Shelf Life Detection of Processed Cheese Using Cascade Single and Multi Layer Artificial Neural Network Computing Models

    OpenAIRE

    Sumit Goyal; Gyanendra Kumar Goyal

    2012-01-01

    This paper presents the potential of Cascade Backpropagation algorithm based ANN models in detecting the shelf life of processed cheese stored at 30o C. Processed cheese is a dairy product made from ripened Cheddar cheese and sometimes a part of ripened cheese is replaced by fresh cheese; plus emulsifiers, extra salt, spices and food colorings. The cascade backpropagation algorithm (CBA) is the basis of a conceptual design for accelerating learning in ANNs. In this research input parameters w...

  16. Context dependent learning in neural networks

    OpenAIRE

    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...

  17. Dynamic recurrent neural networks

    OpenAIRE

    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...

  18. Load forecasting using different architectures of neural networks with the assistance of the MATLAB toolboxes; Previsao de cargas eletricas utilizando diferentes arquiteturas de redes neurais artificiais com o auxilio das toolboxes do MATLAB

    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)

  19. Macroeconomics modelling on UK GDP growth by neural computing

    OpenAIRE

    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...

  20. New Statistical Technologies applied to the estimation of the free Housing Prices: Artificial Neural Networks

    OpenAIRE

    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...

  1. Vibration Based Damage Assessment of a Cantilever using a Neural Network

    DEFF Research Database (Denmark)

    Kirkegaard, Poul Henning; Rytter, A.

    In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with with the Backpropagation Algorithm as a non-destructive damage assessment technique to locate and quantify a damage in structures is investigated.......In this paper the possibility of using a Multilayer Perceptron (MLP) network trained with with the Backpropagation Algorithm as a non-destructive damage assessment technique to locate and quantify a damage in structures is investigated....

  2. 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

  3. High Accuracy Myanmar Handwritten Character Recognition using Hybrid approach through MICR and Neural Network

    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.

  4. 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.

  5. Linear GPR inversion for lossy soil and a planar air-soil interface

    DEFF Research Database (Denmark)

    Meincke, Peter

    2001-01-01

    A three-dimensional inversion scheme for fixed-offset ground penetrating radar (GPR) is derived that takes into account the loss in the soil and the planar air-soil interface. The forward model of this inversion scheme is based upon the first Born approximation and the dyadic Green function for a...... two-layer medium. The forward model is inverted using the Tikhonov-regularized pseudo-inverse operator. This involves two steps: filtering and backpropagation. The filtering is carried out by numerically solving Fredholm integral equations of the first kind and the backpropagation is performed using...

  6. How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation

    OpenAIRE

    Bengio, Yoshua

    2014-01-01

    We propose to exploit {\\em reconstruction} as a layer-local training signal for deep learning. Reconstructions can be propagated in a form of target propagation playing a role similar to back-propagation but helping to reduce the reliance on derivatives in order to perform credit assignment across many levels of possibly strong non-linearities (which is difficult for back-propagation). A regularized auto-encoder tends produce a reconstruction that is a more likely version of its input, i.e., ...

  7. Neural Approach for Calculating Permeability of Porous Medium

    Institute of Scientific and Technical Information of China (English)

    ZHANG Ji-Cheng; LIU Li; SONG Kao-Ping

    2006-01-01

    @@ Permeability is one of the most important properties of porous media. It is considerably difficult to calculate reservoir permeability precisely by using single well-logging response and simple formula because reservoir is of serious heterogeneity, and well-logging response curves are badly affected by many complicated factors underground. We propose a neural network method to calculate permeability of porous media. By improving the algorithm of the back-propagation neural network, convergence speed is enhanced and better results can be achieved. A four-layer back-propagation network is constructed to effectively calculate permeability from well log data.

  8. Using Genetic Algorithms in Secured Business Intelligence Mobile Applications

    Directory of Open Access Journals (Sweden)

    Silvia TRIF

    2011-01-01

    Full Text Available The paper aims to assess the use of genetic algorithms for training neural networks used in secured Business Intelligence Mobile Applications. A comparison is made between classic back-propagation method and a genetic algorithm based training. The design of these algorithms is presented. A comparative study is realized for determining the better way of training neural networks, from the point of view of time and memory usage. The results show that genetic algorithms based training offer better performance and memory usage than back-propagation and they are fit to be implemented on mobile devices.

  9. Convolutional networks and learning invariant to homogeneous multiplicative scalings

    OpenAIRE

    Tygert, Mark; Szlam, Arthur; Chintala, Soumith; Ranzato, Marc'Aurelio; Tian, Yuandong; Zaremba, Wojciech

    2015-01-01

    The conventional classification schemes -- notably multinomial logistic regression -- used in conjunction with convolutional networks (convnets) are classical in statistics, designed without consideration for the usual coupling with convnets, stochastic gradient descent, and backpropagation. In the specific application to supervised learning for convnets, a simple scale-invariant classification stage turns out to be more robust than multinomial logistic regression, appears to result in slight...

  10. USING NEURAL NETWORK FOR FINANCIAL APPLICATIONS ESTIMATIONS

    OpenAIRE

    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...

  11. 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.

  12. Curriculum Assessment Using Artificial Neural Network and Support Vector Machine Modeling Approaches: A Case Study. IR Applications. Volume 29

    Science.gov (United States)

    Chen, Chau-Kuang

    2010-01-01

    Artificial Neural Network (ANN) and Support Vector Machine (SVM) approaches have been on the cutting edge of science and technology for pattern recognition and data classification. In the ANN model, classification accuracy can be achieved by using the feed-forward of inputs, back-propagation of errors, and the adjustment of connection weights. In…

  13. Second-Order Learning Methods for a Multilayer Perceptron

    International Nuclear Information System (INIS)

    First- and second-order learning methods for feed-forward multilayer neural networks are studied. Newton-type and quasi-Newton algorithms are considered and compared with commonly used back-propagation algorithm. It is shown that, although second-order algorithms require enhanced computer facilities, they provide better convergence and simplicity in usage. 13 refs., 2 figs., 2 tabs

  14. A CFBPN Artificial Neural Network Model for Educational Qualitative Data Analyses: Example of Students' Attitudes Based on Kellerts' Typologies

    Science.gov (United States)

    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…

  15. Multiobjective Tabu Search method used in chemistry

    Science.gov (United States)

    Rusu, T.; Bulacovschi, V.

    The use of a combined artificial intelligence method in macromolecular chemistry design is described. This method implies a Back-Propagation (BP) Neural Network, modified for two-dimensional input data and for a system composed of a genetic algorithm extended by a Tabu Search operator used to incorporate high-level chemical knowledge: thermodynamic polymer properties.

  16. Kv4 Potassium Channels Modulate Hippocampal EPSP-Spike Potentiation and Spatial Memory in Rats

    Science.gov (United States)

    Truchet, Bruno; Manrique, Christine; Sreng, Leam; Chaillan, Franck A.; Roman, Francois S.; Mourre, Christiane

    2012-01-01

    Kv4 channels regulate the backpropagation of action potentials (b-AP) and have been implicated in the modulation of long-term potentiation (LTP). Here we showed that blockade of Kv4 channels by the scorpion toxin AmmTX3 impaired reference memory in a radial maze task. In vivo, AmmTX3 intracerebroventricular (i.c.v.) infusion increased and…

  17. 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 ( ...

  18. Global Optimization Techniques for Fluid Flow and Propulsion Devices

    Science.gov (United States)

    Shyy, Wei; Papila, Nilay; Vaidyanathan, Raj; Tucker, Kevin; Griffin, Lisa; Dorney, Dan; Huber, Frank; Tran, Ken; Turner, James E. (Technical Monitor)

    2001-01-01

    This viewgraph presentation gives an overview of global optimization techniques for fluid flow and propulsion devices. Details are given on the need, characteristics, and techniques for global optimization. The techniques include response surface methodology (RSM), neural networks and back-propagation neural networks, design of experiments, face centered composite design (FCCD), orthogonal arrays, outlier analysis, and design optimization.

  19. A framework for predicting three-dimensional prostate deformation in real time

    NARCIS (Netherlands)

    Jahya, Alex; Herink, Mark; Misra, Sarthak

    2013-01-01

    Background Surgical simulation systems can be used to estimate soft tissue deformation during pre- and intra-operative planning. Such systems require a model that can accurately predict the deformation in real time. In this study, we present a back-propagation neural network for predicting three-dim

  20. 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

  1. Nonlinear Equalization in 40/112/224 Gbit/s Mixed Line Rate 15-Channel DP-QPSK and DP-16QAM Contiguous Spectrum Based Networks

    DEFF Research Database (Denmark)

    Asif, Rameez

    2014-01-01

    We evaluated that in-line non-linear compensation schemes decrease the com- plexity of digital back-propagation and enhance the perfor mance of 40/112/224Gbit/s mixed line rate network. Both grouped and un-grouped spectral all ocation schemes are investigated....

  2. Vehicle number plate recognition using multiple layer back propagation neural networks

    OpenAIRE

    tuti Asthana; Niresh Sharma, Rajdeep Singh

    2011-01-01

    Automatic Vehicle Number Plate Recognition is aspecial form of optical character recognition (OCR). Vehiclenumber plate recognition is a type of technology, mainlysoftware, which enables computer systems to read automaticallythe registration number of vehicles from digital pictures. Theproposed algorithm develops high quality recognition softwarefor the automatic recognition of vehicle license plates. In thisapproach Multilayer feed-forward back-propagation algorithmusing three hidden layers ...

  3. A Monte-Carlo-Based Network Method for Source Positioning in Bioluminescence Tomography

    OpenAIRE

    Zhun Xu; Xiaolei Song; Xiaomeng Zhang; Jing Bai

    2007-01-01

    We present an approach based on the improved Levenberg Marquardt (LM) algorithm of backpropagation (BP) neural network to estimate the light source position in bioluminescent imaging. For solving the forward problem, the table-based random sampling algorithm (TBRS), a fast Monte Carlo simulation method ...

  4. 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...

  5. Artificial neural network estimation of soil erosion and nutrient concentrations in runoff from land application areas

    Science.gov (United States)

    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...

  6. A Newton-type neural network learning algorithm

    International Nuclear Information System (INIS)

    First- and second-order learning methods for feed-forward multilayer networks are considered. A Newton-type algorithm is proposed and compared with the common back-propagation algorithm. It is shown that the proposed algorithm provides better learning quality. Some recommendations for their usage are given. 11 refs.; 1 fig.; 1 tab

  7. SOLVING INVERSE KINEMATICS OF REDUNDANT MANIPULATOR BASED ON NEURAL NETWORK

    Institute of Scientific and Technical Information of China (English)

    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.

  8. A brief review of feed-forward neural networks

    OpenAIRE

    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.

  9. Jet analysis by neural networks in high energy hadron-hadron collisions

    CERN Document Server

    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.

  10. JET ANALYSIS BY NEURAL NETWORKS IN HIGH ENERGY HADRON-HADRON COLLISIONS

    OpenAIRE

    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.

  11. A Plausible Memristor Implementation of Deep Learning Neural Networks

    OpenAIRE

    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.

  12. Use of a Neural Network for Damage Detection and Location in a Steel Member

    DEFF Research Database (Denmark)

    Kirkegaard, Poul Henning; Rytter, A.

    The paper explores the potential of using a Multilayer Perceptron (MLP) network trained with the Backpropagation algorithm for damage assessment of free-free cracked straight steel beam based on vibration measurements. The problem of damage assessment, i.e. detecting, locating and quantifying a...

  13. Advances in Artificial Neural Networks - Methodological Development and Application

    Science.gov (United States)

    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...

  14. On-line learning algorithms for locally recurrent neural networks.

    Science.gov (United States)

    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

  15. Initial Investigation of Software-Based Bone-Suppressed Imaging

    International Nuclear Information System (INIS)

    Chest radiography is the most widely used imaging modality in medicine. However, the diagnostic performance of chest radiography is deteriorated by the anatomical background of the patient. So, dual energy imaging (DEI) has recently been emerged and demonstrated an improved. However, the typical DEI requires more than two projections, hence causing additional patient dose. The motion artifact is another concern in the DEI. In this study, we investigate DEI-like bone-suppressed imaging based on the post processing of a single radiograph. To obtain bone-only images, we use the artificial neural network (ANN) method with the error backpropagation-based machine learning approach. The computational load of learning process of the ANN is too heavy for a practical implementation because we use the gradient descent method for the error backpropagation. We will use a more advanced error propagation method for the learning process

  16. Comparison of a neural network with multiple linear regression for quantitative analysis in ICP-atomic emission spectroscopy

    International Nuclear Information System (INIS)

    A two layer perceptron with backpropagation of error is used for quantitative analysis in ICP-AES. The network was trained by emission spectra of two interfering lines of Cd and As and the concentrations of both elements were subsequently estimated from mixture spectra. The spectra of the Cd and As lines were also used to perform multiple linear regression (MLR) via the calculation of the pseudoinverse S+ of the sensitivity matrix S. In the present paper it is shown that there exist close relations between the operation of the perceptron and the MLR procedure. These are most clearly apparent in the correlation between the weights of the backpropagation network and the elements of the pseudoinverse. Using MLR, the confidence intervals over the predictions are exploited to correct for the optical device of the wavelength shift. (orig.)

  17. FDI and Accommodation Using NN Based Techniques

    Science.gov (United States)

    Garcia, Ramon Ferreiro; de Miguel Catoira, Alberto; Sanz, Beatriz Ferreiro

    Massive application of dynamic backpropagation neural networks is used on closed loop control FDI (fault detection and isolation) tasks. The process dynamics is mapped by means of a trained backpropagation NN to be applied on residual generation. Process supervision is then applied to discriminate faults on process sensors, and process plant parameters. A rule based expert system is used to implement the decision making task and the corresponding solution in terms of faults accommodation and/or reconfiguration. Results show an efficient and robust FDI system which could be used as the core of an SCADA or alternatively as a complement supervision tool operating in parallel with the SCADA when applied on a heat exchanger.

  18. The development of intelligent expert system with SAT for semiconductor

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Jae Yeol; Shim, Jae Gi; Jeong, Hyun Jo; Cho, Young Tae; Kim, Chang Hyun; Ko, Myung Soo [Chosun University, Gwangju (Korea, Republic of)

    2001-05-15

    In this study, the researches classifying the artificial flaws in semiconductor packages are performed using pattern recognition technology. For this purposes image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtering, binary processing, edge detection and classifier selection is treated by BP(backpropagation). Specially, it is compared IP(image processing) and SOM(self-organizing map) as preprocessing method for dimensionality reduction for entrance into multi-layer perceptron(backpropagation). Also, the pattern recognition techniques is applied to the classification problem of semiconductor flaws as crack, delamination. According to this results, it is possible to acquire the recognition rate of 83.4% about delamination, 75.7% about crack for SOM, and to acquire the recognition rate of 100% for BP.

  19. 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.

  20. 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)

  1. Comparison of Back propagation neural network and Back propagation neural network Based Particle Swarm intelligence in Diagnostic Breast Cancer

    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.

  2. Extraction of Symbolic Rules from Artificial Neural Networks

    CERN Document Server

    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 ...

  3. Developing energy forecasting model using hybrid artificial intelligence method

    Institute of Scientific and Technical Information of China (English)

    Shahram Mollaiy-Berneti

    2015-01-01

    An important problem in demand planning for energy consumption is developing an accurate energy forecasting model. In fact, it is not possible to allocate the energy resources in an optimal manner without having accurate demand value. A new energy forecasting model was proposed based on the back-propagation (BP) type neural network and imperialist competitive algorithm. The proposed method offers the advantage of local search ability of BP technique and global search ability of imperialist competitive algorithm. Two types of empirical data regarding the energy demand (gross domestic product (GDP), population, import, export and energy demand) in Turkey from 1979 to 2005 and electricity demand (population, GDP, total revenue from exporting industrial products and electricity consumption) in Thailand from 1986 to 2010 were investigated to demonstrate the applicability and merits of the present method. The performance of the proposed model is found to be better than that of conventional back-propagation neural network with low mean absolute error.

  4. Evolution of an artificial neural network based autonomous land vehicle controller.

    Science.gov (United States)

    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

  5. Rozpoznávání číslic pomocí neuronové sítě

    OpenAIRE

    Doupovec, Zdeněk

    2009-01-01

    Tato práce popisuje základními pojmy a principy v oboru neuronových sítí. Blíže se pak věnuje problematice vícevrstvých perceptronových sítí, konkrétně metodě back-propagation. Jsou zde rozebrány výhody a nevýhody zmíněné metody, návrh možného systému rozpoznávání číslic pomocí back-propagation. Cílem je získat konkrétní výsledky z programu schopného rozpoznávat čísla.

  6. A selective learning method to improve the generalization of multilayer feedforward neural networks.

    Science.gov (United States)

    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

  7. Learning multiple layers of representation.

    Science.gov (United States)

    Hinton, Geoffrey E

    2007-10-01

    To achieve its impressive performance in tasks such as speech perception or object recognition, the brain extracts multiple levels of representation from the sensory input. Backpropagation was the first computationally efficient model of how neural networks could learn multiple layers of representation, but it required labeled training data and it did not work well in deep networks. The limitations of backpropagation learning can now be overcome by using multilayer neural networks that contain top-down connections and training them to generate sensory data rather than to classify it. Learning multilayer generative models might seem difficult, but a recent discovery makes it easy to learn nonlinear distributed representations one layer at a time. PMID:17921042

  8. Polynomial harmonic GMDH learning networks for time series modeling.

    Science.gov (United States)

    Nikolaev, Nikolay Y; Iba, Hitoshi

    2003-12-01

    This paper presents a constructive approach to neural network modeling of polynomial harmonic functions. This is an approach to growing higher-order networks like these build by the multilayer GMDH algorithm using activation polynomials. Two contributions for enhancement of the neural network learning are offered: (1) extending the expressive power of the network representation with another compositional scheme for combining polynomial terms and harmonics obtained analytically from the data; (2) space improving the higher-order network performance with a backpropagation algorithm for further gradient descent learning of the weights, initialized by least squares fitting during the growing phase. Empirical results show that the polynomial harmonic version phGMDH outperforms the previous GMDH, a Neurofuzzy GMDH and traditional MLP neural networks on time series modeling tasks. Applying next backpropagation training helps to achieve superior polynomial network performances. PMID:14622880

  9. Rule Extraction using Artificial Neural Networks

    CERN Document Server

    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 ...

  10. Initial Investigation of Software-Based Bone-Suppressed Imaging

    Energy Technology Data Exchange (ETDEWEB)

    Park, Eunpyeong; Youn, Hanbean; Kim, Ho Kyung [Pusan National University, Busan (Korea, Republic of)

    2015-05-15

    Chest radiography is the most widely used imaging modality in medicine. However, the diagnostic performance of chest radiography is deteriorated by the anatomical background of the patient. So, dual energy imaging (DEI) has recently been emerged and demonstrated an improved. However, the typical DEI requires more than two projections, hence causing additional patient dose. The motion artifact is another concern in the DEI. In this study, we investigate DEI-like bone-suppressed imaging based on the post processing of a single radiograph. To obtain bone-only images, we use the artificial neural network (ANN) method with the error backpropagation-based machine learning approach. The computational load of learning process of the ANN is too heavy for a practical implementation because we use the gradient descent method for the error backpropagation. We will use a more advanced error propagation method for the learning process.

  11. The development of intelligent expert system with SAT for semiconductor

    International Nuclear Information System (INIS)

    In this study, the researches classifying the artificial flaws in semiconductor packages are performed using pattern recognition technology. For this purposes image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtering, binary processing, edge detection and classifier selection is treated by BP(backpropagation). Specially, it is compared IP(image processing) and SOM(self-organizing map) as preprocessing method for dimensionality reduction for entrance into multi-layer perceptron(backpropagation). Also, the pattern recognition techniques is applied to the classification problem of semiconductor flaws as crack, delamination. According to this results, it is possible to acquire the recognition rate of 83.4% about delamination, 75.7% about crack for SOM, and to acquire the recognition rate of 100% for BP.

  12. Tighter Lower Bounds on Mutual Information for Fiber-Optic Channels

    CERN Document Server

    Irukulapati, Naga V; Agrell, Erik; Johannisson, Pontus; Wymeersch, Henk

    2016-01-01

    In fiber-optic communications, evaluation of mutual information (MI) is still an open issue due to the unavailability of an exact and mathematically tractable channel model. Traditionally, lower bounds on MI are computed by approximating the (original) channel with an auxiliary forward channel. In this paper, lower bounds are computed using an auxiliary backward channel, which has not been previously considered in the context of fiber-optic communications. Distributions obtained through two variations of the stochastic digital backpropagation (SDBP) algorithm are used as auxiliary backward channels and these bounds are compared with bounds obtained through the conventional digital backpropagation (DBP). Through simulations, higher information rates were achieved with SDBP compared with DBP, which implies that tighter lower bound on MI can be achieved through SDBP.

  13. 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.

  14. Handwritten Farsi Character Recognition using Artificial Neural Network

    CERN Document Server

    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...

  15. MPPT control of wind generation systems based on FNN with PSO algorithm

    Directory of Open Access Journals (Sweden)

    Chih-Ming Hong, Whei-Min Lin, Chiung-Hsing Chen, Ting-Chia Ou

    2011-09-01

    Full Text Available This paper presents the design of an on-line training fuzzy neural network (FNN using back-propagation learning algorithm with particle swarm optimization (PSO regulating controller for the induction generator (IG. The PSO is adopted in this study to adapt the learning rates in the back-propagation process of the FNN to improve the learning capability. The proposed output maximization control is achieved without mechanical sensors such as the wind speed or position sensor, and the new control system will deliver maximum electric power with light weight, high efficiency, and high reliability. The estimation of the rotor speed is designed on the basis of the sliding mode control theory.

  16. Applying artificial intelligence technology to support decision-making in nursing: A case study in Taiwan.

    Science.gov (United States)

    Liao, Pei-Hung; Hsu, Pei-Ti; Chu, William; Chu, Woei-Chyn

    2015-06-01

    This study applied artificial intelligence to help nurses address problems and receive instructions through information technology. Nurses make diagnoses according to professional knowledge, clinical experience, and even instinct. Without comprehensive knowledge and thinking, diagnostic accuracy can be compromised and decisions may be delayed. We used a back-propagation neural network and other tools for data mining and statistical analysis. We further compared the prediction accuracy of the previous methods with an adaptive-network-based fuzzy inference system and the back-propagation neural network, identifying differences in the questions and in nurse satisfaction levels before and after using the nursing information system. This study investigated the use of artificial intelligence to generate nursing diagnoses. The percentage of agreement between diagnoses suggested by the information system and those made by nurses was as much as 87 percent. When patients are hospitalized, we can calculate the probability of various nursing diagnoses based on certain characteristics. PMID:26021669

  17. Indian Stock Market Prediction Using Differential Evolutionary Neural Network Model

    OpenAIRE

    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...

  18. Determination of Optical Properties of Turbid Media from Spatially Resolved Diffuse Reflectance by Neural Network

    Institute of Scientific and Technical Information of China (English)

    REN Hongwu; FANG Zujie

    2000-01-01

    A backpropagation (BP) network is applied to the inversion of spatially resolved diffuse reflectance from turbid media and then to determine its optical properties. A standard BP network may be trapped to the local minimum. A BP network with variable momentum and variable leaning rate can reduce this effect. After being trained, this network will produce reduced scattering coefficients and absorption coefficients when the spatially resolved diffuse reflectance are fed to its input.

  19. Automatic Generation of Neural Networks

    OpenAIRE

    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...

  20. Artificial Neural Networks, Symmetries and Differential Evolution

    OpenAIRE

    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....

  1. Classification of Human Emotions from EEG Signals using Statistical Features and Neural Network

    OpenAIRE

    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...

  2. Extreme Learning Machine for land cover classification

    OpenAIRE

    Pal, Mahesh

    2008-01-01

    This paper explores the potential of extreme learning machine based supervised classification algorithm for land cover classification. In comparison to a backpropagation neural network, which requires setting of several user-defined parameters and may produce local minima, extreme learning machine require setting of one parameter and produce a unique solution. ETM+ multispectral data set (England) was used to judge the suitability of extreme learning machine for remote sensing classifications...

  3. Power Transformer Differential Protection Based on Neural Network Principal Component Analysis, Harmonic Restraint and Park's Plots

    OpenAIRE

    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...

  4. Image Segmentation Based on Support Vector Machine

    Institute of Scientific and Technical Information of China (English)

    XU Hai-xiang; ZHU Guang-xi; TIAN Jin-wen; ZHANG Xiang; PENG Fu-yuan

    2005-01-01

    Image segmentation is a necessary step in image analysis. Support vector machine (SVM) approach is proposed to segment images and its segmentation performance is evaluated.Experimental results show that: the effects of kernel function and model parameters on the segmentation performance are significant; SVM approach is less sensitive to noise in image segmentation; The segmentation performance of SVM approach is better than that of back-propagation multi-layer perceptron (BP-MLP) approach and fuzzy c-means (FCM) approach.

  5. Reservoir computing for spatiotemporal signal classification without trained output weights

    OpenAIRE

    Prater, Ashley

    2016-01-01

    Reservoir computing is a recently introduced machine learning paradigm that has been shown to be well-suited for the processing of spatiotemporal data. Rather than training the network node connections and weights via backpropagation in traditional recurrent neural networks, reservoirs instead have fixed connections and weights among the `hidden layer' nodes, and traditionally only the weights to the output layer of neurons are trained using linear regression. We claim that for signal classif...

  6. Information Theory for Analyzing Neural Networks

    OpenAIRE

    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 ...

  7. Neural Networks for Wordform Recognition

    OpenAIRE

    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...

  8. Prediction by Artificial Neural Networks (ANN) of the diffusivity, mass, moisture, volume and solids on osmotically dehydrated yacon (Smallantus sonchifolius)

    OpenAIRE

    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...

  9. Egg hatchability prediction by multiple linear regression and artificial neural networks

    OpenAIRE

    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...

  10. 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

  11. Modular neural networks and reinforcement learning

    OpenAIRE

    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...

  12. Learning Processes of Layered Neural Networks

    OpenAIRE

    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.

  13. Local learning algorithm for optical neural networks

    OpenAIRE

    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...

  14. MEASUREMENT AND CORRELATION OF SOLUBILITY OF CAFFEINE IN WATER AND ETHANOL%咖啡因在水和乙醇中的溶解度及其关联

    Institute of Scientific and Technical Information of China (English)

    韩佳宾; 王静康

    2004-01-01

    The solubility of caffeine in water and ethanol at 0—50 ℃ was measured using the laser method. The results were regressed with an empirical equation and simplified EOS correlation. A 2 - 2 - 1 backpropagation (BP) artificial neural network (ANN) model was selected from many other models. The prediction of interpolation and extrapolation of the data was made with trained 2 - 2 - 1 BP ANN model. The result was satisfactory.

  15. Forecasting Models for Hydropower Unit Stability Using LS-SVM

    OpenAIRE

    Liangliang Qiao; Qijuan Chen

    2015-01-01

    This paper discusses a least square support vector machine (LS-SVM) approach for forecasting stability parameters of Francis turbine unit. To achieve training and testing data for the models, four field tests were presented, especially for the vibration in Y-direction of lower generator bearing (LGB) and pressure in draft tube (DT). A heuristic method such as a neural network using Backpropagation (NNBP) is introduced as a comparison model to examine the feasibility of forecasting performance...

  16. On learning by exchanging advice

    OpenAIRE

    Eugénio da Costa Oliveira; Luís Nunes

    2003-01-01

    One of the main questions concerning learning in Multi-Agent Systems is: (How) can agents benefit from mutual interaction during the learning process?. This paper describes the study of an interactive advice-exchange mechanism as a possible way to improve agents' learning performance. The advice-exchange technique, discussed here, uses supervised learning (backpropagation), where reinforcement is not directly coming from the environment but is based on advice given by peers with better perfor...

  17. Study of a New Neuron

    OpenAIRE

    Adler, S. L.; Bhanot, G. V.; Weckel, J. D.

    1994-01-01

    We study a modular neuron alternative to the McCulloch-Pitts neuron that arises naturally in analog devices in which the neuron inputs are represented as coherent oscillatory wave signals. Although the modular neuron can compute $XOR$ at the one neuron level, it is still characterized by the same Vapnik-Chervonenkis dimension as the standard neuron. We give the formulas needed for constructing networks using the new neuron and training them using back-propagation. A numerical study of the mod...

  18. 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

  19. Artificial Neural Network based Diagnostic Model For Causes of Success and Failures

    OpenAIRE

    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...

  20. 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.

  1. Radar Target Classification Using Neural Network and Median Filter

    OpenAIRE

    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.

  2. Classification of Ocean Acoustic Data Using AR Modeling and Wavelet Transforms

    OpenAIRE

    Fargues, Monique P.; Bennett, R., Harris, J.; Barsanti, R. J.

    1997-01-01

    This study investigates the application of orthogonal, non-orthogonal wavelet-based procedures, and AR modeling as feature extraction techniques to classify several classes of underwater signals consisting of sperm whale, killer whale, gray whale, pilot whale, humpback whale, and underwater earthquake data. A two-hidden-layer back-propagation neural network is used for the classification procedure. Performance obtained using the two wavelet-based schemes are compared with those obtained usin...

  3. Assessment of earthquake-triggered landslide susceptibility in El Salvador based on an Artificial Neural Network model

    OpenAIRE

    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 (M

  4. NEURAL NETWORKS ARCHITECTURES FOR MODELING AND SIMULATION OF THE ECONOMY SYSTEM DYNAMICS

    OpenAIRE

    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)...

  5. Assessment of earthquake-triggered landslide susceptibility in El Salvador based on an Artificial Neural Network model

    OpenAIRE

    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...

  6. Evolving Chart Pattern Sensitive Neural Network Based Forex Trading Agents

    OpenAIRE

    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...

  7. Neural Networks Applied to Thermal Damage Classification in Grinding Process

    OpenAIRE

    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...

  8. Lateral Connections in Denoising Autoencoders Support Supervised Learning

    OpenAIRE

    Rasmus, Antti; Valpola, Harri; Raiko, Tapani

    2015-01-01

    We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pretraining. It improves the state of the art significantly in the permutation-invariant MNIST classification task.

  9. One-Class Classification with Extreme Learning Machine

    OpenAIRE

    Qian Leng; Honggang Qi; Jun Miao; Wentao Zhu; Guiping Su

    2015-01-01

    One-class classification problem has been investigated thoroughly for past decades. Among one of the most effective neural network approaches for one-class classification, autoencoder has been successfully applied for many applications. However, this classifier relies on traditional learning algorithms such as backpropagation to train the network, which is quite time-consuming. To tackle the slow learning speed in autoencoder neural network, we propose a simple and efficient one-class classif...

  10. Alternating optimization method based on nonnegative matrix factorizations for deep neural networks

    OpenAIRE

    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...

  11. Unifying Adversarial Training Algorithms with Flexible Deep Data Gradient Regularization

    OpenAIRE

    Ororbia II, Alexander G.; Giles, C. Lee; Kifer, Daniel

    2016-01-01

    We present DataGrad, a general back-propagation style training procedure for deep neural architectures that uses regularization of a deep Jacobian-based penalty. It can be viewed as a deep extension of the layerwise contractive auto-encoder penalty. More importantly, it unifies previous proposals for adversarial training of deep neural nets -- this list includes directly modifying the gradient, training on a mix of original and adversarial examples, using contractive penalties, and approximat...

  12. Enhanced dynamic Performance of Matrix Converter Cage Drive with Neuro-fuzzy approach

    OpenAIRE

    R.R. Joshi; A.K. Wadhwani

    2007-01-01

    This paper proposes a new control algorithm for a matrix converter (MC) induction motor drive system. First, a new switching strategy, which applies a back-propagation neural network to adjust a pseudo dc bus voltage, is proposed to reduce the current harmonics of the induction motor. Next, a two-degree-of-freedom controller is proposed to improve the system performance. The controller design algorithm can be applied in an adjustable speed control system and a position control system to obtai...

  13. Akcelerované neuronové sítě

    OpenAIRE

    Flax, Michal

    2015-01-01

    Tato práce se zabývá simulací neuronových sítí a algoritmem Backpropagation. Simulace je akcelerována pomocí standardu OpenMP. Aplikace také umožňuje modifikovat strukturu neuronových sítí a simulovat tak nestandardní chování sítě.

  14. Detection of human colonic adenoma by laser-induced autofluorescence integrated with diffuse reflectance spectroscopy

    Science.gov (United States)

    Tang, Guilin; Lu, Haibao; Zhang, Yangde; Yan, Shuhua; Chen, Zhifeng

    2000-10-01

    A combined in vivo measurement system integrating laser- induced autofluorescence (LIAF) and diffuse reflectance spectroscopy (DRS) measurement was developed and investigated for detecting colonic adenoma. The system could work with regular endoscopy examination. A three- layer backpropagating neural network (BNN) was built to differentiate the two tissue classes. The preliminary results gave the mean predictive accuracy, sensitivity and specificity better than either of the two methods used alone.

  15. 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

  16. The need for stochastic replication of ecological neural networks

    OpenAIRE

    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...

  17. Parameter Sensitivity Analysis on Deformation of Composite Soil-Nailed Wall Using Artificial Neural Networks and Orthogonal Experiment

    OpenAIRE

    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...

  18. Predicting the supercritical carbon dioxide extraction of oregano bract essential oil

    OpenAIRE

    Abdolreza Moghadassi; Sayed Mohsen Hosseini; Fahime Parvizian; Ibrahim Al-Hajri; Mehdi Talebbeigi

    2011-01-01

    The extraction of essential oils using compressed carbon dioxide is a modern technique offering significant advantagesover more conventional methods, especially in particular applications. The prediction of extraction efficiency is a powerful toolfor designing and optimizing the process. The current work proposed a new method based on the artificial neural network(ANN) for the estimation of the extraction efficiency of the essential oil oregano bract. In addition, the work used the backpropag...

  19. Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

    OpenAIRE

    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...

  20. Layer-Specific Adaptive Learning Rates for Deep Networks

    OpenAIRE

    Singh, Bharat; De, Soham; Zhang, Yangmuzi; Goldstein, Thomas; Taylor, Gavin

    2015-01-01

    The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely large for weights connecting deep layers (layers near the output layer), and extremely small for shallow layers (near the input layer); this results in slow learning in the shallow layers. Additionally, it has also been shown that in highly non-convex proble...

  1. 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

  2. Reconocimiento de dígitos manuscritos usando la transformada wavelet continua en 2 dimensiones y redes neuronales

    OpenAIRE

    Romero, Diego J.; Seijas, Leticia; Ruedín, Ana M. C.

    2006-01-01

    En este trabajo presentamos un método de preprocesamiento para el reconocimiento de dígitos manuscritos, basado en la aplicación de la transformada wavelet continua en dos dimensiones. Los datos preprocesados son utilizados como entrada de una red neuronal del tipo feed forward multicapa, la cual es entrenada con el algoritmo de backpropagation. Nuestros resultados preliminares son alentadores

  3. Quaternionic Multilayer Perceptron with Local Analyticity

    OpenAIRE

    Nobuyuki Matsui; Haruhiko Nishimura; Teijiro Isokawa

    2012-01-01

    A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights...

  4. New computational solution to quantify synthetic material porosity from optical microscopic images

    OpenAIRE

    V.H.C. Albuquerque; P. P. Rebouças Filho; T. S. Cavalcante; Tavares, J.M.R.S.

    2010-01-01

    This paper presents a new computational solution to quantify the porosity of synthetic materials from optical microscopic images. The solution is based on an artificial neuronal network of the multilayer perceptron type and a backpropagation algorithm is used for training. To evaluate this new solution, 40 sample images of a synthetic material were analyzed and the quality of the results was confirmed by human visual analysis. Additionally, these results were compared with ones obtained with ...

  5. Learning Precise Spike Train to Spike Train Transformations in Multilayer Feedforward Neuronal Networks

    OpenAIRE

    Banerjee, Arunava

    2014-01-01

    We derive a synaptic weight update rule for learning temporally precise spike train to spike train transformations in multilayer feedforward networks of spiking neurons. The framework, aimed at seamlessly generalizing error backpropagation to the deterministic spiking neuron setting, is based strictly on spike timing and avoids invoking concepts pertaining to spike rates or probabilistic models of spiking. The derivation is founded on two innovations. First, an error functional is proposed th...

  6. Modelización de los procesos de conformado en caliente de los aceros microaleados de medio carbono mediante la aplicación de redes neuronales artificiales

    OpenAIRE

    Alcelay Larrión, José Ignacio

    2015-01-01

    In this thesis a study was performed to obtain a model of artificial neural network that is able to predict the flow behavior of steel under hot deformation conditions. The hot compression tests are performed on two types of steels: medium carbon micro alloyed steels, with different conditions austenitizing and molded duplex steel. or the neural network model the Multilayer Perceptron (MLP) with backpropagation learning algorithm was used. The inputs to the network are temperature, strain and...

  7. Performance comparison of neural network training algorithms in modeling of bimodal drug delivery.

    Science.gov (United States)

    Ghaffari, A; Abdollahi, H; Khoshayand, M R; Bozchalooi, I Soltani; Dadgar, A; Rafiee-Tehrani, M

    2006-12-11

    The major aim of this study was to model the effect of two causal factors, i.e. coating weight gain and amount of pectin-chitosan in the coating solution on the in vitro release profile of theophylline for bimodal drug delivery. Artificial neural network (ANN) as a multilayer perceptron feedforward network was incorporated for developing a predictive model of the formulations. Five different training algorithms belonging to three classes: gradient descent, quasi-Newton (Levenberg-Marquardt, LM) and genetic algorithm (GA) were used to train ANN containing a single hidden layer of four nodes. The next objective of the current study was to compare the performance of aforementioned algorithms with regard to predicting ability. The ANNs were trained with those algorithms using the available experimental data as the training set. The divergence of the RMSE between the output and target values of test set was monitored and used as a criterion to stop training. Two versions of gradient descent backpropagation algorithms, i.e. incremental backpropagation (IBP) and batch backpropagation (BBP) outperformed the others. No significant differences were found between the predictive abilities of IBP and BBP, although, the convergence speed of BBP is three- to four-fold higher than IBP. Although, both gradient descent backpropagation and LM methodologies gave comparable results for the data modeling, training of ANNs with genetic algorithm was erratic. The precision of predictive ability was measured for each training algorithm and their performances were in the order of: IBP, BBP>LM>QP (quick propagation)>GA. According to BBP-ANN implementation, an increase in coating levels and a decrease in the amount of pectin-chitosan generally retarded the drug release. Moreover, the latter causal factor namely the amount of pectin-chitosan played slightly more dominant role in determination of the dissolution profiles. PMID:16959449

  8. The Influence of Hidden Neurons Factor on Neural Nework Training Quality Assurance

    OpenAIRE

    Grabusts, Peter; Zorins, Aleksejs

    2015-01-01

    The work shows the role of hidden neurons in the multilayer feed-forward neural networks. The numeric expression of hidden neurons is usually determined in each case empirically. The methodology for determining the number of hidden neurons are described. The neural network based approach is analyzed using a multilayer feed-forward network with backpropagation learning algorithm. We have presented neural network implementation possibility in bankruptcy prediction (the experiments have been per...

  9. Highly Accurate Multi-layer Perceptron Neural Network for Air Data System

    OpenAIRE

    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...

  10. Numerical simulation of the alloying elements effect on steels’ properties

    OpenAIRE

    W. Sitek; J. Trzaska

    2011-01-01

    Purpose: The goal of the research carried out was evaluation of alloying elements effect on high-speed steels hardness and fracture toughness and austenite transformations during continuous cooling of structural steels.Design/methodology/approach: Multi-layer feedforward neural networks with learning rule based on the error backpropagation algorithm were employed for modelling the steels properties. Then the neural networks worked out were employed for the computer simulation of the effect of...

  11. FINANCIAL TIME SERIES FORECASTING BY NEURAL NETWORK USING CONJUGATE GRADIENT LEARNING ALGORITHM AND MULTIPLE LINEAR REGRESSION WEIGHT INITIALIZATION

    OpenAIRE

    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 ...

  12. Simulating the dynamics of the neutron flux in a nuclear reactor by locally recurrent neural networks

    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

  13. Evaluation of chemical composition effect on materials properties using AI methods

    OpenAIRE

    W. Sitek; J. Trzaska; L.A. Dobrzański

    2007-01-01

    Purpose: The paper presents the application of artificial neural network for evaluation of alloying elementseffect on selected materials properties and austenite transformations during continuous cooling.Design/methodology/approach: Multi-layer feedforward neural networks with learning rule based on theerror backpropagation algorithm were employed for modelling the steels properties. Then the neural networksworked out were employed for the computer simulation of the effect of particular alloy...

  14. A Neural Network Based Collision Detection Engine for Multi-Arm Robotic Systems

    OpenAIRE

    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...

  15. Automated Defect Classification Using AN Artificial Neural Network

    Science.gov (United States)

    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.

  16. Advances in Artificial Neural Networks – Methodological Development and Application

    OpenAIRE

    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...

  17. A Hybrid Applied Optimization Algorithm for Training Multi-Layer Neural Networks in the Data Classification

    OpenAIRE

    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...

  18. A Global Algorithm for Training Multilayer Neural Networks

    OpenAIRE

    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...

  19. Beyond Hebb: exclusive-OR and biological learning.

    Science.gov (United States)

    Klemm, K; Bornholdt, S; Schuster, H G

    2000-03-27

    A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise. PMID:11018999

  20. Extrapolation limitations of multilayer feedforward neural networks

    Science.gov (United States)

    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.

  1. Artificial Neural Network Analysis for Prediction of Headache Prognosis in Elderly Patients

    OpenAIRE

    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...

  2. Using Artificial Neural Networks for ECG Signals Denoising

    OpenAIRE

    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...

  3. Handwritten Farsi Character Recognition using Artificial Neural Network

    OpenAIRE

    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...

  4. Neural-estimator for the surface emission rate of atmospheric gases

    OpenAIRE

    Paes, F. F.; Velho, H. F. Campos

    2009-01-01

    The emission rate of minority atmospheric gases is inferred by a new approach based on neural networks. The neural network applied is the multi-layer perceptron with backpropagation algorithm for learning. The identification of these surface fluxes is an inverse problem. A comparison between the new neural-inversion and regularized inverse solution id performed. The results obtained from the neural networks are significantly better. In addition, the inversion with the neural netwroks is fster...

  5. Incorporation of Liquid-Crystal Light Valve Non-Linearities in Optical Multilayer Neural Networks

    OpenAIRE

    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...

  6. Adapting Resilient Propagation for Deep Learning

    OpenAIRE

    Mosca, Alan; Magoulas, George D.

    2015-01-01

    The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In this paper, we propose a modification of the Rprop that combines standard Rprop steps with a special drop out technique. We apply the method for training Deep Neural Networks as s...

  7. Evaluating variable selection methods for diagnosis of myocardial infarction.

    OpenAIRE

    Dreiseitl, S.; Ohno-Machado, L.; Vinterbo, S.

    1999-01-01

    This paper evaluates the variable selection performed by several machine-learning techniques on a myocardial infarction data set. The focus of this work is to determine which of 43 input variables are considered relevant for prediction of myocardial infarction. The algorithms investigated were logistic regression (with stepwise, forward, and backward selection), backpropagation for multilayer perceptrons (input relevance determination), Bayesian neural networks (automatic relevance determinat...

  8. Comparative Analisys of Different Approaches Towards Multilayer Percentron Training

    OpenAIRE

    Vališevskis, A

    2001-01-01

    A comparative analysis of four multilayer perceptron learning algorithms is exposed in this work: the error backpropagation algorithm and three other algorithms with fundamentally different approaches towards the improvement of convergence time. Stock exchange share price prediction is at the basis of the comparison of the algorithms. The optimal neural network topology for the solution of the above-mentioned task is determined in this work. Furthermore the forecasts concerning fo...

  9. Vibration Based Damage Assessment of a Civil Engineering Structures using a Neural Networks

    OpenAIRE

    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...

  10. An Artificial Neural Network Modeling for Force Control System of a Robotic Pruning Machine

    OpenAIRE

    Ali Hashemi; Keyvan Asefpour Vakilian; Javad Khazaei; Jafar Massah

    2014-01-01

    Nowadays, there has been an increasing application of pruning robots for planted forests due to the growing concern on the efficiency and safety issues. Power consumption and working time of agricultural machines have become important issues due to the high value of energy in modern world. In this study, different multi-layer back-propagation networks were utilized for mapping the complex and highly interactive of pruning process parameters and to predict power consumption and cutting time of...

  11. Application of Levenberg-Marquardt Optimization Algorithm Based Multilayer Neural Networks for Hydrological Time Series Modeling

    OpenAIRE

    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...

  12. Evolution of neural networks

    OpenAIRE

    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...

  13. Methods of Forecasting Based on Artificial Neural Networks

    OpenAIRE

    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...

  14. Neural Network Course Changing and Track Keeping Controller for a Submarine

    OpenAIRE

    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...

  15. Automatic Modulation Recognition Using Wavelet Transform and Neural Networks in Wireless Systems

    OpenAIRE

    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...

  16. Indirect model for roughness in rough honing processes based on artificial neural networks

    OpenAIRE

    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...

  17. Beyond Hebb: Exclusive-OR and Biological Learning

    OpenAIRE

    Klemm, Konstantin; Bornholdt, Stefan; Schuster, Heinz Georg

    1999-01-01

    A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error back-propagation, as well as to increase robustness of learning in the presence of noise.

  18. Methodological Issues in Building, Training, and Testing Artificial Neural Networks

    OpenAIRE

    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...

  19. Analisis Dan Peracangan Aplikasi Sistem Pendeteksi Gangguan Jaringan Komputer Menggunakan Multilayer Dengan Pelatihan Feedforward

    OpenAIRE

    Melinwati, Siska

    2011-01-01

    Intrusion detection in computer networks may be achived by utilizing Artificial Neural Networks (ANN), which serves as a model the human brain with multilayer feedforward architecture and backpropagation training algorithm. This architecture consists of an input layer, one or more hidden layer, and output layer where each layer may consists of one or more neurons. Input signals are obtained from intrusion data which where normalized to yield values between 0 and 1. From the tes...

  20. A selective learning method to improve the generalization of multilayer feedforward neural networks.

    OpenAIRE

    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...

  1. Training Neural Networks for minimum average risk with a special application to context dependent learning

    OpenAIRE

    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...

  2. Learning behavior and temporary minima of two-layer neural networks

    OpenAIRE

    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.

  3. Neural networks for predicting flow discharge in the balarood river (Iran)

    OpenAIRE

    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. ...

  4. An Artificial Neural Network Approach for the Prediction of Absorption Measurements of an Evanescent Field Fiber Sensor

    Directory of Open Access Journals (Sweden)

    Ö. 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.

  5. Implementation of Back Propagation Algorithm in Verilog

    OpenAIRE

    Neelmani Chhedaiya; Prof. Vishal Moyal

    2012-01-01

    In this paper, a design method of neural networks based on Verilog HDL hardware description language, implementation is proposed. A design of a general neuron for topologies using back propagation algorithm is described. The sigmoid nonlinear activation function is also used. The neuron is then used in the design and implementation of a neural network using Xilinx Spartan-3e FPGA. The simulation results obtained with Xilinx ISE 9.2i software. The backpropagation algorithm is one of the most u...

  6. The Buckling Analysis of Axially Loaded Columns with Artificial Neural Networks

    OpenAIRE

    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...

  7. On-Line Condition Monitoring System for High Level Trip Water in Steam Boiler’s Drum

    OpenAIRE

    Ismail Alnaimi Firas B.; A Ali Marwan; Al-Kayiem Hussain H.; Mohamed Sahari Khairul Salleh bin

    2014-01-01

    This paper presents a monitoring technique using Artificial Neural Networks (ANN) with four different training algorithms for high level water in steam boiler’s drum. Four Back-Propagations neural networks multidimensional minimization algorithms have been utilized. Real time data were recorded from power plant located in Malaysia. The developed relevant variables were selected based on a combination of theory, experience and execution phases of the model. The Root Mean Square (RMS) Error has...

  8. Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference

    OpenAIRE

    Tran, Tung; Yang, Bo-Suk; Oh, Myung-Suck; Tan, Andy Chit Chiow

    2009-01-01

    This paper presents a fault diagnosis method based on adaptive neuro-fuzzy inference system (ANFIS) in combination with decision trees. Classification and regression tree (CART) which is one of the decision tree methods is used as a feature selection procedure to select pertinent features from data set. The crisp rules obtained from the decision tree are then converted to fuzzy if-then rules that are employed to identify the structure of ANFIS classifier. The hybrid of back-propagation and le...

  9. Quaternionic Multilayer Perceptron with Local Analyticity

    Directory of Open Access Journals (Sweden)

    Nobuyuki Matsui

    2012-11-01

    Full Text Available A multi-layered perceptron type neural network is presented and analyzed in this paper. All neuronal parameters such as input, output, action potential and connection weight are encoded by quaternions, which are a class of hypercomplex number system. Local analytic condition is imposed on the activation function in updating neurons’ states in order to construct learning algorithm for this network. An error back-propagation algorithm is introduced for modifying the connection weights of the network.

  10. Classification of coffee using artificial neural network

    OpenAIRE

    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 ...

  11. End-to-End Kernel Learning with Supervised Convolutional Kernel Networks

    OpenAIRE

    Mairal, Julien

    2016-01-01

    In this paper, we propose a new image representation based on a multilayer kernel machine that performs end-to-end learning. Unlike traditional kernel methods, where the kernel is handcrafted or adapted to data in an unsupervised manner, we learn how to shape the kernel for a supervised prediction problem. We proceed by generalizing convolutional kernel networks, which originally provide unsupervised image representations, and we derive backpropagation rules to optimize model parameters. As a...

  12. BPNN based MECG elimination from the abdominal signal to extract fetal signal for continuous fetal monitoring - doi: 10.4025/actascitechnol.v35i2.15361

    OpenAIRE

    Muhammad Asraful Hasan; Md. Mamun

    2013-01-01

    Fetal monitoring may help with possible recognition of problems in the fetus. This research work focuses on the design of the Back-propagation Neural Network (BPNN) and Adaptive Linear Neural Network (ADALINE) to extract the Fetal Electrocardiogram (FECG) from the Abdominal ECG (AECG). FECG is extracted to assess the fetus well-being during the pregnancy period of a mother to overcome some existing difficulties regarding the fetal heart rate (FHR) monitoring system. Different sets of ECG sign...

  13. Extended Mixture of MLP Experts by Hybrid of Conjugate Gradient Method and Modified Cuckoo Search

    OpenAIRE

    Hamid Salimi; Davar Giveki; Mohammad Ali Soltanshahi; Javad Hatami

    2012-01-01

    This paper investigates a new method for improving the learning algorithm of Mixture of Experts (ME) model using a hybrid of Modified Cuckoo Search (MCS) and Conjugate Gradient (CG) as a second order optimization technique. The CG technique is combined with Back-Propagation (BP) algorithm to yield a much more efficient learning algorithm for ME structure. In addition, the experts and gating networks in enhanced model are replaced by CG based Multi-Layer Perceptrons (MLPs) to provi...

  14. 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.

  15. Condition Parameter Modeling for Anomaly Detection in Wind Turbines

    OpenAIRE

    Yonglong Yan; Jian Li,; David Wenzhong Gao

    2014-01-01

    Data collected from the supervisory control and data acquisition (SCADA) system, used widely in wind farms to obtain operational and condition information about wind turbines (WTs), is of important significance for anomaly detection in wind turbines. The paper presents a novel model for wind turbine anomaly detection mainly based on SCADA data and a back-propagation neural network (BPNN) for automatic selection of the condition parameters. The SCADA data sets are determined through analysis o...

  16. Analysis of Height Affect on Average Wind Speed by Ann

    OpenAIRE

    Ata, Raşit; Çetin, Numan

    2011-01-01

    The power generated by wind turbines depends on several factors. Two of them are the wind speed and the tower height of wind turbine. In this study, the annual average wind speed based on the tower height is predicted using Artificial Neural Networks (ANN) and comparisons made with conventional model approach. The backpropagation multi layer ANNs were used to estimate annual average wind speed for three locations in Turkey. The Model has been developed with the help of neural network methodol...

  17. Analysis of Height Affect on Average Wind Speed by ANN

    OpenAIRE

    Ata, Raşit; Çetin, Numan

    2011-01-01

    The power generated by wind turbines depends on several factors. Two of them are the wind speed and the tower height of wind turbine. In this study, the annual average wind speed based on the tower height is predicted using Artificial Neural Networks (ANN) and comparisons made with conventional model approach. The backpropagation multi layer ANNs were used to estimate annual average wind speed for three locations in Turkey. The Model has been developed with the help of neural network methodol...

  18. Adaptive Control Using Fully Online Sequential-Extreme Learning Machine and a Case Study on Engine Air-Fuel Ratio Regulation

    OpenAIRE

    Pak Kin Wong; Chi Man Vong; Xiang Hui Gao; Ka In Wong

    2014-01-01

    Most adaptive neural control schemes are based on stochastic gradient-descent backpropagation (SGBP), which suffers from local minima problem. Although the recently proposed regularized online sequential-extreme learning machine (ReOS-ELM) can overcome this issue, it requires a batch of representative initial training data to construct a base model before online learning. The initial data is usually difficult to collect in adaptive control applications. Therefore, this paper proposes an impro...

  19. An ANN-based load model for fast transient stability calculations

    Energy Technology Data Exchange (ETDEWEB)

    Qian, Ai; Shrestha, G.B. [School of EEE, Nanyang Technological University (Singapore)

    2006-01-15

    Load models play an important role in the simulation and calculation of power system performance. This paper presents a new load model which is based on a particular form of artificial neural networks we call adaptive back-propagation (ABP) network. ABP has can overcome some of short-comings of common back-propagation (BP) and ABP load models offer many advantages over traditional load models as they are non-structural and can be derived quickly. The application of the method in modeling loads is illustrated using actual field test data. The load models so obtained are shown to replicate the test measurements more closely than that based on traditional load models. Further extension of the method for the identification of the parameters of the traditional load models is proposed. It is based on linear back-propagation (LBP) network. The proposed LBP load model is incorporated in a transient stability program to show that the computational time is significantly reduced. (author)

  20. Pengujian Model Jaringan Syaraf Tiruan Untuk Kualifikasi Calon Mahasiswa Baru Program Bidik Misi

    Directory of Open Access Journals (Sweden)

    Ilham Sayekti

    2014-02-01

    Full Text Available Testing of neural network models for qualified new students Bidik Misi program is a software program that is built by using backpropagation neural network (ANN-BP is used for the purpose of scholarship recipients qualify Bidik Misi of incoming freshmen at Semarang State Polytechnic . By using an 8 input variables such as parental occupation, parental income, parental education, number of dependents and academic values​​, with each variable consists of several different parameters, and 1 output variable result is rejected or accepted. Through a series of tests by combining the network parameters, in order to get the optimal results of neural networks, the best results are obtained logsig and purelin activation function. As research material used data from the 127 students who signed up as a potential recipient of a scholarship Bidik Misi. From some data, 50 data used as training data (learning, and 77 are used as test data, obtained results that a system built by the backpropagation neural network was able to qualify the scholarship recipients Bidik Misi success rate reached 99.21%. Keywords : Artificial neural network; Backpropagation; Bidik Misi; Kualifikasi

  1. Application of four-layer neural network on information extraction.

    Science.gov (United States)

    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

  2. Neural network models for a resource allocation problem.

    Science.gov (United States)

    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

  3. Hardware implementation of on -chip learning using re configurable FPGAS

    International Nuclear Information System (INIS)

    The multilayer perceptron (MLP) is a neural network model that is being widely applied in the solving of diverse problems. A supervised training is necessary before the use of the neural network.A highly popular learning algorithm called back-propagation is used to train this neural network model. Once trained, the MLP can be used to solve classification problems. An interesting method to increase the performance of the model is by using hardware implementations. The hardware can do the arithmetical operations much faster than software. In this paper, a design and implementation of the sequential mode (stochastic mode) of backpropagation algorithm with on-chip learning using field programmable gate arrays (FPGA) is presented, a pipelined adaptation of the on-line back propagation algorithm (BP) is shown.The hardware implementation of forward stage, backward stage and update weight of backpropagation algorithm is also presented. This implementation is based on a SIMD parallel architecture of the forward propagation the diagnosis of the multi-purpose research reactor of Egypt accidents is used to test the proposed system

  4. Noise-enhanced convolutional neural networks.

    Science.gov (United States)

    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

  5. PEMBUATAN PERANGKAT LUNAK PENGENALAN WAJAH MENGGUNAKAN PRINCIPAL COMPONENTS ANALYSIS

    Directory of Open Access Journals (Sweden)

    Kartika Gunadi

    2001-01-01

    Full Text Available Face recognition is one of many important researches, and today, many applications have implemented it. Through development of techniques like Principal Components Analysis (PCA, computers can now outperform human in many face recognition tasks, particularly those in which large database of faces must be searched. Principal Components Analysis was used to reduce facial image dimension into fewer variables, which are easier to observe and handle. Those variables then fed into artificial neural networks using backpropagation method to recognise the given facial image. The test results show that PCA can provide high face recognition accuracy. For the training faces, a correct identification of 100% could be obtained. From some of network combinations that have been tested, a best average correct identification of 91,11% could be obtained for the test faces while the worst average result is 46,67 % correct identification Abstract in Bahasa Indonesia : Pengenalan wajah manusia merupakan salah satu bidang penelitian yang penting, dan dewasa ini banyak aplikasi yang dapat menerapkannya. Melalui pengembangan suatu teknik seperti Principal Components Analysis (PCA, komputer sekarang dapat melebihi kemampuan otak manusia dalam berbagai tugas pengenalan wajah, terutama tugas-tugas yang membutuhkan pencarian pada database wajah yang besar. Principal Components Analysis digunakan untuk mereduksi dimensi gambar wajah sehingga menghasilkan variabel yang lebih sedikit yang lebih mudah untuk diobsevasi dan ditangani. Hasil yang diperoleh kemudian akan dimasukkan ke suatu jaringan saraf tiruan dengan metode Backpropagation untuk mengenali gambar wajah yang telah diinputkan ke dalam sistem. Hasil pengujian sistem menunjukkan bahwa penggunaan PCA untuk pengenalan wajah dapat memberikan tingkat akurasi yang cukup tinggi. Untuk gambar wajah yang diikutsertakankan dalam latihan, dapat diperoleh 100% identifikasi yang benar. Dari beberapa kombinasi jaringan yang

  6. 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

  7. Hybrid RGSA and Support Vector Machine Framework for Three-Dimensional Magnetic Resonance Brain Tumor Classification

    Directory of Open Access Journals (Sweden)

    R. Rajesh Sharma

    2015-01-01

    algorithm (RGSA. Support vector machines, over backpropagation network, and k-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002. The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods.

  8. 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.)

  9. Gradient Learning in Networks of Smoothly Spiking Neurons

    Czech Academy of Sciences Publication Activity Database

    Šíma, Jiří

    Berlin : Springer, 2009 - (Köppen, M.; Kasabov, N.; Coghill, G.), s. 179-186 ISBN 978-3-642-03039-0. - (Lecture Notes in Computer Science. 5507). [ICONIP 2008. International Conference on Neural Information Processing /15./. Auckland (NZ), 25.11.2008-28.11.2008] R&D Projects: GA AV ČR 1ET100300517; GA MŠk(CZ) 1M0545 Institutional research plan: CEZ:AV0Z10300504 Keywords : spiking neuron * back-propagation * SpikeProp * gradient learning Subject RIV: IN - Informatics, Computer Science

  10. Predictive models for determination of pitting corrosion versus inhibitor concentrations and temperature for radioactive sludge in carbon steel waste tanks

    International Nuclear Information System (INIS)

    Statistical models were developed to predict the occurrence of pitting corrosion in carbon steel (CS) waste storage tanks exposed to radioactive nuclear waste. Levels of nitrite (NO2-) concentrations necessary to inhibit pitting at various temperatures and nitrate (NO3-) concentrations were determined experimentally via electrochemical polarization and coupon immersion corrosion tests. Models for the pitting behavior were developed based upon various statistical analyses of the experimental data. Freed-forward, artificial neural network (ANN) models, trained using the back-propagation of error algorithm, more accurately predicted conditions at which pitting occurred than the logistic regression models development using the same data

  11. Predictive Models for the Determination of Pitting Corrosion Versus Inhibitor Concentrations and Temperature for Radioactive Sludge in Carbon Steel Waste Tanks

    International Nuclear Information System (INIS)

    Statistical models have been developed to predict the occurrence of pitting corrosion in carbon steel waste storage tanks exposed to radioactive nuclear waste. The levels of nitrite concentrations necessary to inhibit pitting at various temperatures and nitrate concentrations were experimentally determined via electrochemical polarization and coupon immersion corrosion tests. Models for the pitting behavior were developed based on various statistical analyses of the experimental data. Feed-forward Artificial Neural Network (ANN) models, trained using the Back-Propagation of Error Algorithm, more accurately predicted conditions at which pitting occurred than the logistic regression models developed using the same data

  12. 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)

  13. Application of artificial neural networks in nonlinear analysis of trusses

    Science.gov (United States)

    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.

  14. Design and analysis of a systolic array for neural computation

    OpenAIRE

    Viredaz, Marc; Nicoud, Jean-Daniel

    2009-01-01

    Research on artificial neural networks (ANNs) has been carried out for more than five decades. A renewed interest appeared in the 80's with the finding of powerful models like J. Hopfield's recurrent networks, T. Kohonen's self-organizing feature maps, and the back-propagation rule. At that time, there was no platform that was at the same time versatile enough for any ANN model to be implemented and fast enough to solve large problems. Super-computers were the sole exception to this rule, but...

  15. Design and analysis of a systolic array for neural computation

    OpenAIRE

    Viredaz, Marc

    1994-01-01

    Research on artificial neural networks (ANNs) has been carried out for more than five decades. A renewed interest appeared in the 80's with the finding of powerful models like J. Hopfield's recurrent networks, T. Kohonen's self-organizing feature maps, and the back-propagation rule. At that time, there was no platform that was at the same time versatile enough for any ANN model to be implemented and fast enough to solve large problems. Super-computers were the sole exception to this rule, but...

  16. Handwritten Digits Recognition Using Neural Computing

    OpenAIRE

    Călin Enăchescu; Cristian-Dumitru Miron

    2009-01-01

    In this paper we present a method for the recognition of handwritten digits and a practical implementation of this method for real-time recognition. A theoretical framework for the neural networks used to classify the handwritten digits is also presented.The classification task is performed using a Convolutional Neural Network (CNN). CNN is a special type of multy-layer neural network, being trained with an optimized version of the back-propagation learning algorithm.CNN is designed to recogni...

  17. Sequential Back—Propagation

    Institute of Scientific and Technical Information of China (English)

    王晖; 刘大有; 等

    1994-01-01

    In this paper we consider the problem of sequential processing and present a sequential model based on the back-propagation algorithm.This model is intended to deal with intrinsically sequential problems,such as word recognition,speech recognition,natural language understanding.This model can be used to train a network to learn the sequence of input patterns,in a fixed order or a random order.Besides,this model is open- and partial-associative,characterized as “resognizing while accumulating”, which, as we argue, is mental cognition process oriented.

  18. Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification

    Directory of Open Access Journals (Sweden)

    R. Sathya

    2013-02-01

    Full Text Available This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the present study.

  19. Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis

    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

  20. Forecasting Models for Hydropower Unit Stability Using LS-SVM

    Directory of Open Access Journals (Sweden)

    Liangliang Qiao

    2015-01-01

    Full Text Available This paper discusses a least square support vector machine (LS-SVM approach for forecasting stability parameters of Francis turbine unit. To achieve training and testing data for the models, four field tests were presented, especially for the vibration in Y-direction of lower generator bearing (LGB and pressure in draft tube (DT. A heuristic method such as a neural network using Backpropagation (NNBP is introduced as a comparison model to examine the feasibility of forecasting performance. In the experimental results, LS-SVM showed superior forecasting accuracies and performances to the NNBP, which is of significant importance to better monitor the unit safety and potential faults diagnosis.

  1. Deep learning in neural networks: an overview.

    Science.gov (United States)

    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

  2. Intelligent Surveillance Robot with Obstacle Avoidance Capabilities Using Neural Network.

    Science.gov (United States)

    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

  3. Freeze-drying modeling and monitoring using a new neuro-evolutive technique

    OpenAIRE

    Fissore, Davide

    2012-01-01

    This paper is focused on the design of a black-box model for the process of freeze-drying of pharmaceuticals. A new methodology based on a self-adaptive differential evolution scheme is combined with a back-propagation algorithm, as local search method, for the simultaneous structural and parametric optimization of the model represented by a neural network. Using the model of the freeze-drying process, both the temperature and the residual ice content in the product vs. time can be determine ...

  4. 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.

  5. 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.

  6. 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.

  7. 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.

  8. Comparative Study of Classification Techniques on Breast Cancer FNA Biopsy Data

    Directory of Open Access Journals (Sweden)

    George Rumbe

    2010-12-01

    Full Text Available Accurate diagnostic detection of the cancerous cells in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Bayesian classifier and other Artificial neural network classifiers (Backpropagation, linear programming, Learning vector quantization, and K nearest neighborhood on the Wisconsin breast cancer classification problem.

  9. Coherent detection and digital signal processing for fiber optic communications

    Science.gov (United States)

    Ip, Ezra

    to cycle slips. In systems where nonlinear effects are concentrated mostly at fiber locations with small accumulated dispersion, nonlinear phase de-rotation is a low-complexity algorithm that can partially mitigate nonlinear effects. For systems with arbitrary dispersion maps, however, backpropagation is the only universal technique that can jointly compensate dispersion and fiber nonlinearity. Backpropagation requires solving the nonlinear Schrodinger equation at the receiver, and has high computational cost. Backpropagation is most effective when dispersion compensation fibers are removed, and when signal processing is performed at three times oversampling. Backpropagation can improve system performance and increase transmission distance. With anticipated advances in analog-to-digital converters and integrated circuit technology, DSP-based coherent receivers at bit rates up to 100 Gb/s should become practical in the near future.

  10. 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%.

  11. A Recursive Born Approach to Nonlinear Inverse Scattering

    CERN Document Server

    Kamilov, Ulugbek S; Mansour, Hassan; Boufounos, Petros T

    2016-01-01

    The Iterative Born Approximation (IBA) is a well-known method for describing waves scattered by semi-transparent objects. In this paper, we present a novel nonlinear inverse scattering method that combines IBA with an edge-preserving total variation (TV) regularizer. The proposed method is obtained by relating iterations of IBA to layers of a feedforward neural network and developing a corresponding error backpropagation algorithm for efficiently estimating the permittivity of the object. Simulations illustrate that, by accounting for multiple scattering, the method successfully recovers the permittivity distribution where the traditional linear inverse scattering fails.

  12. Reconocimiento de caracteres por medio de una red neuronal artificial

    Directory of Open Access Journals (Sweden)

    Cesar Rivera-Ordoñez

    2009-01-01

    Full Text Available In this project we develop a characters recognition system implemented in a general purpose FPGA card. First, The characters classification is executed by a neural network model called feed-forward backpropagation. The Matlab toobox, NNTool used for neural networks is used to create, training and simulate this kind of Artificial Neural Network (ANN with five different patterns of training. For the implementation the ANN computer model is realizes as hardware system, which is described in a block diagram using both Matlab/ Simulink and Xilinx System Generator (XSG. Subsequently, the bitstream configuration file -necessary for the FPGA programming- is generated by XSG for implementing with Xilinx ISE foundation.

  13. Simulation of an industrial wastewater treatment plant using artificial neural networks and principal components analysis

    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.

  14. Intelligent temperature control system of quench furnace

    Institute of Scientific and Technical Information of China (English)

    胡燕瑜; 桂卫华; 唐朝晖; 唐玲

    2004-01-01

    A fuzzy-neural networks intelligent temperature control system of quench furnace was presented. Combined genetic algorithm with back-propagation algorithm, the weight values of neural networks, parameters of fuzzy membership functions and inference rules can be adjusted automatically, which realizes the optimal control of temperature. The results show that this control system can run effectively with satisfied temperature precision: in temperature uprising stage, overshot of temperature is under 4 ℃; in stable stage, the scope of temperature change is controlled within ±2 ℃, which meets the need of control veracity of temperature.

  15. Vehicle License Plate Recognition Syst

    Directory of Open Access Journals (Sweden)

    Meenakshi,R. B. Dubey

    2012-12-01

    Full Text Available The vehicle license plate recognition system has greater efficiency for vehicle monitoring in automatic zone access control. This Plate recognition system will avoid special tags, since all vehicles possess a unique registration number plate. A number of techniques have been used for car plate characters recognition. This system uses neural network character recognition and pattern matching of characters as two character recognition techniques. In this approach multilayer feed-forward back-propagation algorithm is used. The performance of the proposed algorithm has been tested on several car plates and provides very satisfactory results.

  16. Design of neural networks for classification of remotely sensed imagery

    Science.gov (United States)

    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.

  17. Multilayered perceptron neural networks to compute energy losses in magnetic cores

    International Nuclear Information System (INIS)

    This paper presents a new approach based on multilayered perceptrons (MLPs) to compute the specific energy losses of toroidal wound cores built from 3% SiFe 0.27 mm thick M4, 0.1 and 0.08 mm thin gauge electrical steel strips. The MLP has been trained by a back-propagation and extended delta-bar-delta learning algorithm. The results obtained by using the MLP model were compared with a commonly used conventional method. The comparison has shown that the proposed model improved loss estimation with respect to the conventional method

  18. A System for Predicting Subcellular Localization of Yeast Genome Using Neural Network

    CERN Document Server

    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.

  19. Vehicle License Plate Recognition System

    Directory of Open Access Journals (Sweden)

    Meenakshi

    2012-12-01

    Full Text Available The vehicle license plate recognition system has greater efficiency for vehicle monitoring in automatic zone access control. This Plate recognition system will avoid special tags, since all vehicles possess a unique registration number plate. A number of techniques have been used for car plate characters recognition. This system uses neural network character recognition and pattern matching of characters as two character recognition techniques. In this approach multilayer feed-forward back-propagation algorithm is used. The performance of the proposed algorithm has been tested on several car plates and provides very satisfactory results.

  20. Intelligent Surveillance Robot with Obstacle Avoidance Capabilities Using Neural Network

    Science.gov (United States)

    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

  1. Robust Bioinformatics Recognition with VLSI Biochip Microsystem

    Science.gov (United States)

    Lue, Jaw-Chyng L.; Fang, Wai-Chi

    2006-01-01

    A microsystem architecture for real-time, on-site, robust bioinformatic patterns recognition and analysis has been proposed. This system is compatible with on-chip DNA analysis means such as polymerase chain reaction (PCR)amplification. A corresponding novel artificial neural network (ANN) learning algorithm using new sigmoid-logarithmic transfer function based on error backpropagation (EBP) algorithm is invented. Our results show the trained new ANN can recognize low fluorescence patterns better than the conventional sigmoidal ANN does. A differential logarithmic imaging chip is designed for calculating logarithm of relative intensities of fluorescence signals. The single-rail logarithmic circuit and a prototype ANN chip are designed, fabricated and characterized.

  2. Model identification with BPNN on restrictive ecological factors of SRB for sulfate-reduction

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    The model of back-propagation neural network(BPNN)was presented to demonstrate the effect of restrictive ecological factors,COD/SO42-ratio,pH value,alkalinity(ALK)and SO42-loading rate(Ns),on sulfate-reduction of Sulfate Reducing Bacteria(SRB)in an acidogenic sulfate-reducing reactor supplied with molasses as sole organic carbon source and sodium sulfate as electron acceptor.The compare of experimental results and computer simulation was also discussed.It was shown that the method of BPNN had a powerful ability to analyze the ecological characteristic of acidogenic sulfate-reducing ecosystem quantitatively.

  3. Prospects of real-time ion temperature and rotation profiles based on neural-network charge exchange analysis

    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.

  4. Learning Optimal Nonlinearities for Iterative Thresholding Algorithms

    Science.gov (United States)

    Kamilov, Ulugbek S.; Mansour, Hassan

    2016-05-01

    Iterative shrinkage/thresholding algorithm (ISTA) is a well-studied method for finding sparse solutions to ill-posed inverse problems. In this letter, we present a data-driven scheme for learning optimal thresholding functions for ISTA. The proposed scheme is obtained by relating iterations of ISTA to layers of a simple deep neural network (DNN) and developing a corresponding error backpropagation algorithm that allows to fine-tune the thresholding functions. Simulations on sparse statistical signals illustrate potential gains in estimation quality due to the proposed data adaptive ISTA.

  5. Neural network error correction for solving coupled ordinary differential equations

    Science.gov (United States)

    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.

  6. Neural network method for characterizing video cameras

    Science.gov (United States)

    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.

  7. 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.

  8. Evaluation of thermal embrittlement susceptibility in cast austenitic stainless steel using artificial neural network

    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

  9. Training neural networks using sequential extended Kalman filtering

    Energy Technology Data Exchange (ETDEWEB)

    Plumer, E.S.

    1995-03-01

    Recent work has demonstrated the use of the extended Kalman filter (EKF) as an alternative to gradient-descent backpropagation when training multi-layer perceptrons. The EKF approach significantly improves convergence properties but at the cost of greater storage and computational complexity. Feldkamp et al. have described a decoupled version of the EKF which preserves the training advantages of the general EKF but which reduces the storage and computational requirements. This paper reviews the general and decoupled EKF approaches and presents sequentialized versions which provide further computational savings over the batch forms. The usefulness of the sequentialized EKF algorithms is demonstrated on a pattern classification problem.

  10. Un modelo neuronal basado en la metaplasticidad para la clasificación de objetos en señales 1-d y 2-d

    OpenAIRE

    Marcano Cedeño, Alexis Enrique

    2010-01-01

    El Algoritmo de Retropropagación (Algoritmo Backpropagation, ABP), es uno de los algoritmos más conocidos y utilizados para el entrenamiento de las Redes Neuronales Artificiales, RNAs. El ABP ha sido empleado con éxito en problemas de clasificación de patrones en áreas como: Medicina, Bioinformática, Telecomunicaciones, Banca, Predicciones Climatológicas, etc. Sin embargo el ABP tiene algunas limitaciones que le impiden alcanzar un nivel óptimo de eficiencia (problemas de lentitud, convergenc...

  11. 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.

  12. 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.

  13. Classifying LEP Data with Support Vector Algorithms

    CERN Document Server

    Vannerem, P; Schölkopf, B; Smola, A J; Söldner-Rembold, S

    1999-01-01

    We have studied the application of different classification algorithms in the analysis of simulated high energy physics data. Whereas Neural Network algorithms have become a standard tool for data analysis, the performance of other classifiers such as Support Vector Machines has not yet been tested in this environment. We chose two different problems to compare the performance of a Support Vector Machine and a Neural Net trained with back-propagation: tagging events of the type e+e- -> ccbar and the identification of muons produced in multihadronic e+e- annihilation events.

  14. Machine Learning ANN Models for Predicting Sensory Quality of Roasted Coffee Flavoured Sterilized Drink

    Directory of Open Access Journals (Sweden)

    Sumit GOYAL

    2013-11-01

    Full Text Available This paper highlights the significance of feedforward artificial neural network models for predicting shelf life of roasted coffee falvoured sterilized drink. Coffee is one of the most important products for trade in international market. Single as well as multilayer models were explored and different backpropagation algorithms were investigated, Root mean square error and coefficient of determination R2 were used to compare the prediction performance of single and multilayer feedforward ANN models. Experimental results suggested that multilayer models take less time and give better results as compared to single layer ANN models for prediction of sensory quality of roasted coffee falvoured sterilized drink..

  15. 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.

  16. Normalized RBF networks: application to a system of integral equations

    International Nuclear Information System (INIS)

    Linear integral and integro-differential equations of Fredholm and Volterra types have been successfully treated using radial basis function (RBF) networks in previous works. This paper deals with the case of a system of integral equations of Fredholm and Volterra types with a normalized radial basis function (NRBF) network. A novel learning algorithm is developed for the training of NRBF networks in which the BFGS backpropagation (BFGS-BP) least-squares optimization method as a recursive model is used. In the approach presented here, a trial solution is given by an NRBF network of incremental architecture with a set of unknown parameters. Detailed learning algorithms and concrete examples are also included

  17. Application of the fuzzy Kohonen clustering network to remote-sensed data processing

    Science.gov (United States)

    Blonda, Palma N.; Bennardo, A.; Pasquariello, Guido; Satalino, Giuseppe; la Forgia, Vincenza

    1996-06-01

    In this work the effectiveness of the fuzzy Kohonen clustering network (FKCN) has been explored in two classification experiments of remote sensed data. The FKCN has been introduced in a multi-modular neural classification system for feature extraction before labeling. The unsupervised module is connected in cascade with the next supervised module, based on the backpropagation learning rule. The performance of the FKCN has been evaluated in comparison with those of a conventional Kohonen self organizing map (SOM) neural network. Experimental results have proved that the fuzzy clustering network can be used for complex data pre-processing.

  18. 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.)

  19. 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.)

  20. A Global Algorithm for Training Multilayer Neural Networks

    CERN Document Server

    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.

  1. 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

  2. Learning in compressed space.

    Science.gov (United States)

    Fabisch, Alexander; Kassahun, Yohannes; Wöhrle, Hendrik; Kirchner, Frank

    2013-06-01

    We examine two methods which are used to deal with complex machine learning problems: compressed sensing and model compression. We discuss both methods in the context of feed-forward artificial neural networks and develop the backpropagation method in compressed parameter space. We further show that compressing the weights of a layer of a multilayer perceptron is equivalent to compressing the input of the layer. Based on this theoretical framework, we will use orthogonal functions and especially random projections for compression and perform experiments in supervised and reinforcement learning to demonstrate that the presented methods reduce training time significantly. PMID:23501172

  3. Multilayer Perceptron Neural Networks Model for Meteosat Second Generation SEVIRI Daytime Cloud Masking

    OpenAIRE

    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...

  4. Experimental investigation of active vibration control using neural networks and piezoelectric actuators

    Science.gov (United States)

    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.

  5. Visualization of learning in multilayer perceptron networks using principal component analysis.

    Science.gov (United States)

    Gallagher, M; Downs, T

    2003-01-01

    This paper is concerned with the use of scientific visualization methods for the analysis of feedforward neural networks (NNs). Inevitably, the kinds of data associated with the design and implementation of neural networks are of very high dimensionality, presenting a major challenge for visualization. A method is described using the well-known statistical technique of principal component analysis (PCA). This is found to be an effective and useful method of visualizing the learning trajectories of many learning algorithms such as backpropagation and can also be used to provide insight into the learning process and the nature of the error surface. PMID:18238154

  6. 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

  7. Neural network tomography: network replication from output surface geometry.

    Science.gov (United States)

    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

  8. Application of Artificial Neural Networks in Differential Thermal Analysis of Inorganic Compounds

    Science.gov (United States)

    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.

  9. An optimization methodology for neural network weights and architectures.

    Science.gov (United States)

    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

  10. Failure behavior identification for a space antenna via neural networks

    Science.gov (United States)

    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.

  11. Utilization of artificial neural networks and autoregressive modeling in diagnosing mitral valve stenosis.

    Science.gov (United States)

    Kara, Sadik; Güven, Ayşegül; Okandan, Mustafa; Dirgenali, Fatma

    2006-05-01

    This research is concentrated on the diagnosis of mitral heart valve stenosis through the analysis of Doppler Signals' AR power spectral density graphic with the help of ANN. Multilayer feedforward ANN trained with a Levenberg Marquart backpropagation algorithm was implemented in the MATLAB environment. Correct classification of 94% was achieved, whereas 4 false classifications have been observed for the test group of 68 subjects in total. The designed classification structure has about 97.3% sensitivity, 90.3% specifity and positive prediction is calculated to be 92.3%. The stated results show that the proposed method can make an effective interpretation. PMID:15890326

  12. Modeling of dimensional changes during sintering

    Directory of Open Access Journals (Sweden)

    Drndarević D.

    2005-01-01

    Full Text Available An approach to modeling the behavior of dimensions of PM parts during the sintering process for the prediction of dimensional changes is given. The model is developed on the basis of significant process factors by applying a multilayer neural network architecture with the backpropagation learning algorithm. Results of the simulation in the form of diagrams and tables are presented. The presented model gives better results than the one based on statistical analysis of experimental data, i.e. less total mean approximation errors of the part dimensions for 11.4%. A practical result of the model is the determination of compact dimensions to compensate for dimensional changes during sintering. .

  13. Identification of nonlinear dynamic systems using functional link artificial neural networks.

    Science.gov (United States)

    Patra, J C; Pal, R N; Chatterji, B N; Panda, G

    1999-01-01

    We have presented an alternate ANN structure called functional link ANN (FLANN) for nonlinear dynamic system identification using the popular backpropagation algorithm. In contrast to a feedforward ANN structure, i.e., a multilayer perceptron (MLP), the FLANN is basically a single layer structure in which nonlinearity is introduced by enhancing the input pattern with nonlinear functional expansion. With proper choice of functional expansion in a FLANN, this network performs as good as and in some cases even better than the MLP structure for the problem of nonlinear system identification. PMID:18252296

  14. Evaluating variable selection methods for diagnosis of myocardial infarction.

    Science.gov (United States)

    Dreiseitl, S; Ohno-Machado, L; Vinterbo, S

    1999-01-01

    This paper evaluates the variable selection performed by several machine-learning techniques on a myocardial infarction data set. The focus of this work is to determine which of 43 input variables are considered relevant for prediction of myocardial infarction. The algorithms investigated were logistic regression (with stepwise, forward, and backward selection), backpropagation for multilayer perceptrons (input relevance determination), Bayesian neural networks (automatic relevance determination), and rough sets. An independent method (self-organizing maps) was then used to evaluate and visualize the different subsets of predictor variables. Results show good agreement on some predictors, but also variability among different methods; only one variable was selected by all models. PMID:10566358

  15. Utilization of artificial neural networks in the diagnosis of optic nerve diseases.

    Science.gov (United States)

    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

  16. 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.

  17. Design and evaluation of a robust dynamic neurocontroller for a multivariable aircraft control problem

    Science.gov (United States)

    Troudet, T.; Garg, S.; Merrill, W.

    1992-01-01

    The design of a dynamic neurocontroller with good robustness properties is presented for a multivariable aircraft control problem. The internal dynamics of the neurocontroller are synthesized by a state estimator feedback loop. The neurocontrol is generated by a multilayer feedforward neural network which is trained through backpropagation to minimize an objective function that is a weighted sum of tracking errors, and control input commands and rates. The neurocontroller exhibits good robustness through stability margins in phase and vehicle output gains. By maintaining performance and stability in the presence of sensor failures in the error loops, the structure of the neurocontroller is also consistent with the classical approach of flight control design.

  18. Use of artificial neural networks in drug and explosive detection through tomographic images with thermal neutrons

    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)

  19. Minimizing the Quadratic Training Error of a Sigmoid Neuron is Hard

    Czech Academy of Sciences Publication Activity Database

    Šíma, Jiří

    Berlin : Springer, 2001 - (Abe, N.; Khardon, R.; Zeugmann, T.), s. 92-105 ISBN 3-540-42875-5. - (Lecture Notes in Computer Science. 2225). [ALT'2001. International Conference /12./. Washington (US), 25.11.2001-28.11.2001] R&D Projects: GA AV ČR IAB2030007; GA ČR GA201/00/1489 Institutional research plan: AV0Z1030915 Keywords : loading problem * learning complexity * NP-hardness * sigmoid neuron * back-propagation * constructive learning Subject RIV: BA - General Mathematics

  20. 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.

  1. Fine tuning of cascaded d-q axis controller for AC-DC-AC converter without DC link capacitor using artificial neural network

    OpenAIRE

    Padmanaban Sanjeevikumar; Balakrishnan GeethaLakshmi; Perumal Danajayan

    2008-01-01

    This paper presents an artificial neural network (ANN) based approach to tune the parameters of the cascaded d-q axis controller for an AC-DC-AC converter without dc link capacitor. The proposed converter uses the cascaded d-q axis controller on the rectifier side and space vector pulse width modulation on the inverter side. The feed-forward ANN with the error back-propagation training is employed to tune the parameters of the cascaded d-q axis controller. The converter topology provides simp...

  2. 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

  3. 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.

  4. On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem

    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.

  5. 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.

  6. On-Line Condition Monitoring System for High Level Trip Water in Steam Boiler’s Drum

    Directory of Open Access Journals (Sweden)

    Ismail Alnaimi Firas B.

    2014-07-01

    Full Text Available This paper presents a monitoring technique using Artificial Neural Networks (ANN with four different training algorithms for high level water in steam boiler’s drum. Four Back-Propagations neural networks multidimensional minimization algorithms have been utilized. Real time data were recorded from power plant located in Malaysia. The developed relevant variables were selected based on a combination of theory, experience and execution phases of the model. The Root Mean Square (RMS Error has been used to compare the results of one and two hidden layer (1HL, (2HL ANN structures

  7. 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 Schrdinger Poisson equations.

  8. Application of artificial neural network for prediction of marine diesel engine performance

    Science.gov (United States)

    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.

  9. Neural Network Compensation for Frequency Cross-Talk in Laser Interferometry

    Science.gov (United States)

    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.

  10. Method and system for training dynamic nonlinear adaptive filters which have embedded memory

    Science.gov (United States)

    Rabinowitz, Matthew (Inventor)

    2002-01-01

    Described herein is a method and system for training nonlinear adaptive filters (or neural networks) which have embedded memory. Such memory can arise in a multi-layer finite impulse response (FIR) architecture, or an infinite impulse response (IIR) architecture. We focus on filter architectures with separate linear dynamic components and static nonlinear components. Such filters can be structured so as to restrict their degrees of computational freedom based on a priori knowledge about the dynamic operation to be emulated. The method is detailed for an FIR architecture which consists of linear FIR filters together with nonlinear generalized single layer subnets. For the IIR case, we extend the methodology to a general nonlinear architecture which uses feedback. For these dynamic architectures, we describe how one can apply optimization techniques which make updates closer to the Newton direction than those of a steepest descent method, such as backpropagation. We detail a novel adaptive modified Gauss-Newton optimization technique, which uses an adaptive learning rate to determine both the magnitude and direction of update steps. For a wide range of adaptive filtering applications, the new training algorithm converges faster and to a smaller value of cost than both steepest-descent methods such as backpropagation-through-time, and standard quasi-Newton methods. We apply the algorithm to modeling the inverse of a nonlinear dynamic tracking system 5, as well as a nonlinear amplifier 6.

  11. Supervised artificial neural network-based method for conversion of solar radiation data (case study: Algeria)

    Science.gov (United States)

    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.

  12. Classification of multispectral image data by the Binary Diamond neural network and by nonparametric, pixel-by-pixel methods

    Science.gov (United States)

    Salu, Yehuda; Tilton, James

    1993-01-01

    The classification of multispectral image data obtained from satellites has become an important tool for generating ground cover maps. This study deals with the application of nonparametric pixel-by-pixel classification methods in the classification of pixels, based on their multispectral data. A new neural network, the Binary Diamond, is introduced, and its performance is compared with a nearest neighbor algorithm and a back-propagation network. The Binary Diamond is a multilayer, feed-forward neural network, which learns from examples in unsupervised, 'one-shot' mode. It recruits its neurons according to the actual training set, as it learns. The comparisons of the algorithms were done by using a realistic data base, consisting of approximately 90,000 Landsat 4 Thematic Mapper pixels. The Binary Diamond and the nearest neighbor performances were close, with some advantages to the Binary Diamond. The performance of the back-propagation network lagged behind. An efficient nearest neighbor algorithm, the binned nearest neighbor, is described. Ways for improving the performances, such as merging categories, and analyzing nonboundary pixels, are addressed and evaluated.

  13. Maximum power point tracking-based control algorithm for PMSG wind generation system without mechanical sensors

    International Nuclear Information System (INIS)

    Highlights: ► This paper presents MPPT based control for optimal wind energy capture using RBFN. ► MPSO is adopted to adjust the learning rates to improve the learning capability. ► This technique can maintain the system stability and reach the desired performance. ► The EMF in the rotating reference frame is utilized in order to estimate speed. - Abstract: This paper presents maximum-power-point-tracking (MPPT) based control algorithms for optimal wind energy capture using radial basis function network (RBFN) and a proposed torque observer MPPT algorithm. The design of a high-performance on-line training RBFN using back-propagation learning algorithm with modified particle swarm optimization (MPSO) regulating controller for the sensorless control of a permanent magnet synchronous generator (PMSG). The MPSO is adopted in this study to adapt the learning rates in the back-propagation process of the RBFN to improve the learning capability. The PMSG is controlled by the loss-minimization control with MPPT below the base speed, which corresponds to low and high wind speed, and the maximum energy can be captured from the wind. Then the observed disturbance torque is feed-forward to increase the robustness of the PMSG system

  14. UNIVERSAL APPROXIMATION WITH NON-SIGMOID HIDDEN LAYER ACTIVATION FUNCTIONS BY USING ARTIFICIAL NEURAL NETWORK MODELING

    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.

  15. 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.

  16. Earthquake-induced landslide-susceptibility mapping using an artificial neural network

    Directory of Open Access Journals (Sweden)

    S. Lee

    2006-01-01

    Full Text Available The purpose of this study was to apply and verify landslide-susceptibility analysis techniques using an artificial neural network and a Geographic Information System (GIS applied to Baguio City, Philippines. The 16 July 1990 earthquake-induced landslides were studied. Landslide locations were identified from interpretation of aerial photographs and field survey, and a spatial database was constructed from topographic maps, geology, land cover and terrain mapping units. Factors that influence landslide occurrence, such as slope, aspect, curvature and distance from drainage were calculated from the topographic database. Lithology and distance from faults were derived from the geology database. Land cover was identified from the topographic database. Terrain map units were interpreted from aerial photographs. These factors were used with an artificial neural network to analyze landslide susceptibility. Each factor weight was determined by a back-propagation exercise. Landslide-susceptibility indices were calculated using the back-propagation weights, and susceptibility maps were constructed from GIS data. The susceptibility map was compared with known landslide locations and verified. The demonstrated prediction accuracy was 93.20%.

  17. A Novel Method for Shelf Life Detection of Processed Cheese Using Cascade Single and Multi Layer Artificial Neural Network Computing Models

    Directory of Open Access Journals (Sweden)

    Sumit Goyal

    2012-02-01

    Full Text Available This paper presents the potential of Cascade Backpropagation algorithm based ANN models in detecting the shelf life of processed cheese stored at 30o C. Processed cheese is a dairy product made from ripened Cheddar cheese and sometimes a part of ripened cheese is replaced by fresh cheese; plus emulsifiers, extra salt, spices and food colorings. The cascade backpropagation algorithm (CBA is the basis of a conceptual design for accelerating learning in ANNs. In this research input parameters were texture, aroma and flavour, moisture, free fatty acids.Sensory score was taken as output parameter. Bayesian regularization algorithm was used for training the network. Neurons in each hidden layers varied from 1 to 50. The network was trained with 200 epochs with single and multiple hidden layers. Transfer function for hidden layers was tangent sigmoid and pure linear was output function. Mean Square Error, Root Mean Square Error, Coefficient of Determination and Nash - Sutcliffo Coefficient performance measures were used to test the prediction potential of the developed CBA model. CBA model detected 29.13 daysshelf life which is quite close to experimentally obtained shelf life of 30 days suggesting that the product is acceptable.

  18. Differentiation of mint (Mentha haplocalyx Briq.) from different regions in China using gas and liquid chromatography.

    Science.gov (United States)

    Dong, Wenjiang; Ni, Yongnian; Kokot, Serge

    2015-02-01

    In this study, complex substances such as Mint (Mentha haplocalyx Briq.) samples from different growing regions in China were analyzed for phenolic compounds by high-performance liquid chromatography with diode array detection and for the volatile aroma compounds by gas chromatography with mass spectrometry. Chemometrics methods, e.g. principal component analysis, back-propagation artificial neural networks, and partial least squares discriminant analysis, were applied to resolve complex chromatographic profiles of Mint samples. A total of 49 aroma components and 23 phenolic compounds were identified in 79 Mint samples. Principal component analysis score plots from gas chromatography with mass spectrometry and high-performance liquid chromatography with diode array detection data sets showed a clear distinction among Mint from three different regions in China. Classification results showed that satisfactory performance of prediction ability for back-propagation artificial neural networks and partial least squares discriminant analysis. The major compounds that contributed to the discrimination were chlorogenic acid, unknown 3, kaempherol 7-O-rutinoside, salvianolic acid L, hesperidin, diosmetin, unknown 6 and pebrellin in Mint according to regression coefficients of the partial least squares discriminant analysis model. This study indicated that the proposed strategy could provide a simple and rapid technique to distinguish clearly complex profiles from samples such as Mint. PMID:25431171

  19. Estimation of Possible Profit/ Loss of a New Movie Using “Natural Grouping” of Movie Genres

    Directory of Open Access Journals (Sweden)

    Debaditya Barman

    2013-10-01

    Full Text Available Film industry is the most important component of entertainment industry. A large amount of money is invested in this high risk industry. Both profit and loss are very high for this business. Thus if the production houses have an option to know the probable profit/loss of a completed movie to be released then it will be very helpful for them to reduce the said risk. We know that artificial neural networks have been successfully used to solve various problems in numerous fields of application. For instance backpropagation neural networks have successfully been applied for Stock Market Prediction, Weather Prediction etc. In this work we have used a backpropagation network that is being trained using a subset of data points. These subsets are nothing but the “natural grouping” of data points, being extracted by an MST based clustering methods. The proposed method presented in this paper is experimentally found to produce good result for the real life data sets considered for experimentation.

  20. Computing tunneling paths with the Hamilton-Jacobi equation and the fast marching method

    Science.gov (United States)

    Dey, Bijoy K.; Ayers, Paul W.

    We present a new method for computing the most probable tunneling paths based on the minimum imaginary action principle. Unlike many conventional methods, the paths are calculated without resorting to an optimization (minimization) scheme. Instead, a fast marching method coupled with a back-propagation scheme is used to efficiently compute the tunneling paths. The fast marching method solves a Hamilton-Jacobi equation for the imaginary action on a discrete grid where the action value at an initial point (usually the reactant state configuration) is known in the beginning. Subsequently, a back-propagation scheme uses a steepest descent method on the imaginary action surface to compute a path connecting an arbitrary point on the potential energy surface (usually a state in the product valley) to the initial state. The proposed method is demonstrated for the tunneling paths of two different systems: a model 2D potential surface and the collinear reaction. Unlike existing methods, where the tunneling path is based on a presumed reaction coordinate and a correction is made with respect to the reaction coordinate within an 'adiabatic' approximation, the proposed method is very general and makes no assumptions about the relationship between the reaction coordinate and tunneling path.

  1. Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network

    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.

  2. Intelligent Soft Computing on Forex: Exchange Rates Forecasting with Hybrid Radial Basis Neural Network.

    Science.gov (United States)

    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

  3. An Interval Type-2 Fuzzy System with a Species-Based Hybrid Algorithm for Nonlinear System Control Design

    Directory of Open Access Journals (Sweden)

    Chung-Ta Li

    2014-01-01

    Full Text Available We propose a species-based hybrid of the electromagnetism-like mechanism (EM and back-propagation algorithms (SEMBP for an interval type-2 fuzzy neural system with asymmetric membership functions (AIT2FNS design. The interval type-2 asymmetric fuzzy membership functions (IT2 AFMFs and the TSK-type consequent part are adopted to implement the network structure in AIT2FNS. In addition, the type reduction procedure is integrated into an adaptive network structure to reduce computational complexity. Hence, the AIT2FNS can enhance the approximation accuracy effectively by using less fuzzy rules. The AIT2FNS is trained by the SEMBP algorithm, which contains the steps of uniform initialization, species determination, local search, total force calculation, movement, and evaluation. It combines the advantages of EM and back-propagation (BP algorithms to attain a faster convergence and a lower computational complexity. The proposed SEMBP algorithm adopts the uniform method (which evenly scatters solution agents over the feasible solution region and the species technique to improve the algorithm’s ability to find the global optimum. Finally, two illustrative examples of nonlinear systems control are presented to demonstrate the performance and the effectiveness of the proposed AIT2FNS with the SEMBP algorithm.

  4. Artificial neural networks for neutron source localization within sealed tanks

    International Nuclear Information System (INIS)

    A modular back-propagation ANN has been implemented for the non-destructive localization of a source of Even Plutonium Isotopes (EPI) contained in sealed tanks. The ANN has been trained on data obtained from a simulation of a well counter (filtered and Fourier transformed signals of the neutron detectors surrounding the well counter) for known positions of the EPI. After training, the ANN can predict the position of EPI within sealed tanks from the corresponding detector signals. The introduction of median and majority ANNs has been found to significantly improve the accuracy of prediction. Furthermore, these ANNs perform in a satisfactory manner when noise is injected to the detector signals; prediction is corrupted in a manner which is directly related to the extent and amount of noise. The motivation for using back-propagation ANNs is twofold: on one hand (theoretical importance), they are capable of learning to approximate complex functions such as the strongly non-linear relation that exists between the neutron detector signals and the EPI position; on the other hand, they accomplish on-line localization which is of practical interest. (Author)

  5. Neuro-Knowledge-Based Expert System (NKBES)for Optimal Scheming of Die Casting Process

    Institute of Scientific and Technical Information of China (English)

    Qiaodan HU; Peng LUO; Yi YANG; Liliang CHEN

    2004-01-01

    We develop a neuro-knowledge-based expert system (NKBES) frame in this work. The system mainly concerns with decision of gating system and die casting machine based on a neuro-inference engine launched under the MATLAB software environment. For enhancement of reasoning agility, an error back-propagation neural network was applied.A rapidly convergent adaptive learning rate (ALR) and a momentum-based error back-propagation algorithm was used to conduct neuro-reasoning. The working effect of the system was compared to a conventional expert system that is based on a two-way (forward and backward) chaining inference mechanism. As the reference, the present paper provided the neural networks sum-squared error (SSE) and ALR vs iterative epoch curves of process planning case mentioned above. The study suggests that the neuro-modeling optimization application to die casting process design has good feasibility, and based on that a novel and effective intelligent expert system can be launched at low cost.

  6. 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.

  7. 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.

  8. Multimodal Deep Autoencoder for Human Pose Recovery.

    Science.gov (United States)

    Hong, Chaoqun; Yu, Jun; Wan, Jian; Tao, Dacheng; Wang, Meng

    2015-12-01

    Video-based human pose recovery is usually conducted by retrieving relevant poses using image features. In the retrieving process, the mapping between 2D images and 3D poses is assumed to be linear in most of the traditional methods. However, their relationships are inherently non-linear, which limits recovery performance of these methods. In this paper, we propose a novel pose recovery method using non-linear mapping with multi-layered deep neural network. It is based on feature extraction with multimodal fusion and back-propagation deep learning. In multimodal fusion, we construct hypergraph Laplacian with low-rank representation. In this way, we obtain a unified feature description by standard eigen-decomposition of the hypergraph Laplacian matrix. In back-propagation deep learning, we learn a non-linear mapping from 2D images to 3D poses with parameter fine-tuning. The experimental results on three data sets show that the recovery error has been reduced by 20%-25%, which demonstrates the effectiveness of the proposed method. PMID:26452284

  9. Implementation of a multi-layer perception for a non-linear control problem

    International Nuclear Information System (INIS)

    We present the practical application of a 1-hidden-layer multilayer perception (MLP) to provide a non-linear continuous multi-variable mapping with 42 inputs and 13 outputs. The problem resolved is one of extracting information from experimental signals with a bandwidth of many kilohertz. We have an exact model of the inverse mapping of this problem, but we have no explicit form of the required forward mapping. This is the typical situation in data interpretation. The MLP was trained to provide this mapping by learning on 500 input-output examples. The success of the off-line solution to this problem using an MLP led us to examine the robustness of the MLP to different noise sources. We found that the MLP is more robust than an approximate linear mapping of the same problem. 12 bits of resolution in the weights are necessary to avoid a significant loss of precision. The practical implementation of large analog weight matrices using DAS-multipliers and a simple segmented sigmoid is also presented. A General Adaptive Recipe (GAR) for improving the performance of conventional back-propagation was developed. The GAR uses an adaptive step length and both the bias terms and the initial weight seeding are determined by the network size. The GAR was found to be robust and much faster than conventional back-propagation. (author) 20 figs., 1 tab., 15 refs

  10. 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

  11. Programming an Artificial Neural Network Tool for Spatial Interpolation in GIS - A Case Study for Indoor Radio Wave Propagation of WLAN

    Directory of Open Access Journals (Sweden)

    Umut Bulucu

    2008-09-01

    Full Text Available Wireless communication networks offer subscribers the possibilities of free mobility and access to information anywhere at any time. Therefore, electromagnetic coverage calculations are important for wireless mobile communication systems, especially in Wireless Local Area Networks (WLANs. Before any propagation computation is performed, modeling of indoor radio wave propagation needs accurate geographical information in order to avoid the interruption of data transmissions. Geographic Information Systems (GIS and spatial interpolation techniques are very efficient for performing indoor radio wave propagation modeling. This paper describes the spatial interpolation of electromagnetic field measurements using a feed-forward back-propagation neural network programmed as a tool in GIS. The accuracy of Artificial Neural Networks (ANN and geostatistical Kriging were compared by adjusting procedures. The feedforward back-propagation ANN provides adequate accuracy for spatial interpolation, but the predictions of Kriging interpolation are more accurate than the selected ANN. The proposed GIS ensures indoor radio wave propagation model and electromagnetic coverage, the number, position and transmitter power of access points and electromagnetic radiation level. Pollution analysis in a given propagation environment was done and it was demonstrated that WLAN (2.4 GHz electromagnetic coverage does not lead to any electromagnetic pollution due to the low power levels used. Example interpolated electromagnetic field values for WLAN system in a building of Yildiz Technical University, Turkey, were generated using the selected network architectures to illustrate the results with an ANN.

  12. Prediction of thermal conductivity of rock through physico-mechanical properties

    Energy Technology Data Exchange (ETDEWEB)

    Singh, T.N. [Department of Earth Sciences, Indian Institute of Technology, Bombay 400 076 (India); Sinha, S.; Singh, V.K. [Institute of Technology, Banaras Hindu University, Varanasi 221 005 (India)

    2007-01-15

    The transfer of energy between two adjacent parts of rock mainly depends on its thermal conductivity. Present study supports the use of artificial neural network (ANN) and adaptive neuro fuzzy inference system (ANFIS) in the study of thermal conductivity along with other intrinsic properties of rock due to its increasing importance in many areas of rock engineering, agronomy and geo environmental engineering field. In recent years, considerable effort has been made to develop techniques to determine these properties. Comparative analysis is made to analyze the capabilities among six different models of ANN and ANFIS. ANN models are based on feedforward backpropagation network with training functions resilient backpropagation (RP), one step secant (OSS) and Powell-Beale restarts (CGB) and radial basis with training functions generalized regression neural network (GRNN) and more efficient design radial basis network (NEWRB). A data set of 136 has been used for training different models and 15 were used for testing purposes. A statistical analysis is made to show the consistency among them. ANFIS is proved to be the best among all the networks tried in this case with average absolute percentage error of 0.03% and regression coefficient of 1, whereas best performance shown by the FFBP (RP) with average absolute error of 2.26%. Thermal conductivity is predicted using P-wave velocity, porosity, bulk density, uniaxial compressive strength of rock as input parameters. (author)

  13. Reflection-artifact-free photoacoustic imaging using PAFUSion (photoacoustic-guided focused ultrasound)

    Science.gov (United States)

    Kuniyil Ajith Singh, Mithun; Jaeger, Michael; Frenz, Martin; Steenbergen, Wiendelt

    2016-03-01

    Reflection artifacts caused by acoustic inhomogeneities are a main challenge to deep-tissue photoacoustic imaging. Photoacoustic transients generated by the skin surface and superficial vasculature will propagate into the tissue and reflect back from echogenic structures to generate reflection artifacts. These artifacts can cause problems in image interpretation and limit imaging depth. In its basic version, PAFUSion mimics the inward travelling wave-field from blood vessel-like PA sources by applying focused ultrasound pulses, and thus provides a way to identify reflection artifacts. In this work, we demonstrate reflection artifact correction in addition to identification, towards obtaining an artifact-free photoacoustic image. In view of clinical applications, we implemented an improved version of PAFUSion in which photoacoustic data is backpropagated to imitate the inward travelling wave-field and thus the reflection artifacts of a more arbitrary distribution of PA sources that also includes the skin melanin layer. The backpropagation is performed in a synthetic way based on the pulse-echo acquisitions after transmission on each single element of the transducer array. We present a phantom experiment and initial in vivo measurements on human volunteers where we demonstrate significant reflection artifact reduction using our technique. The results provide a direct confirmation that reflection artifacts are prominent in clinical epi-photoacoustic imaging, and that PAFUSion can reduce these artifacts significantly to improve the deep-tissue photoacoustic imaging.

  14. A neurocomputational model of classical conditioning phenomena: a putative role for the hippocampal region in associative learning.

    Science.gov (United States)

    Moustafa, Ahmed A; Myers, Catherine E; Gluck, Mark A

    2009-06-18

    Some existing models of hippocampal function simulate performance in classical conditioning tasks using the error backpropagation algorithm to guide learning (Gluck, M.A., and Myers, C.E., (1993). Hippocampal mediation of stimulus representation: a computational theory. Hippocampus, 3(4), 491-516.). This algorithm is not biologically plausible because it requires information to be passed backward through layers of nodes and assumes that the environment provides information to the brain about what correct outputs should be. Here, we show that the same information-processing function proposed for the hippocampal region in the Gluck and Myers (1993) model can also be implemented in a network without using the backpropagation algorithm. Instead, our newer instantiation of the theory uses only (a) Hebbian learning methods which match more closely with synaptic and associative learning mechanisms ascribed to the hippocampal region and (b) a more plausible representation of input stimuli. We demonstrate here that this new more biologically plausible model is able to simulate various behavioral effects, including latent inhibition, acquired equivalence, sensory preconditioning, negative patterning, and context shift effects. In addition, the newer model is able to address some new phenomena including the effect of the number of training trials on blocking and overshadowing. PMID:19379717

  15. Hebbian learning in parallel and modular memories.

    Science.gov (United States)

    Poon, C S; Shah, J V

    1998-02-01

    Many cognitive and sensorimotor functions in the brain involve parallel and modular memory subsystems that are adapted by activity-dependent Hebbian synaptic plasticity. This is in contrast to the multilayer perceptron model of supervised learning where sensory information is presumed to be integrated by a common pool of hidden units through backpropagation learning. Here we show that Hebbian learning in parallel and modular memories is more advantageous than backpropagation learning in lumped memories in two respects: it is computationally much more efficient and structurally much simpler to implement with biological neurons. Accordingly, we propose a more biologically relevant neural network model, called a tree-like perceptron, which is a simple modification of the multilayer perceptron model to account for the general neural architecture, neuronal specificity, and synaptic learning rule in the brain. The model features a parallel and modular architecture in which adaptation of the input-to-hidden connection follows either a Hebbian or anti-Hebbian rule depending on whether the hidden units are excitatory or inhibitory, respectively. The proposed parallel and modular architecture and implicit interplay between the types of synaptic plasticity and neuronal specificity are exhibited by some neocortical and cerebellar systems. PMID:9525034

  16. Rychlost učení vícevrstvé sítě

    OpenAIRE

    Maceček, Aleš

    2011-01-01

    Teoretický rozbor umělých neuronových sítí, zvláště jejich typů topologií a učení sítí. Zvláštní zaměření je na vícevrstvou neuronovou síť s učením backpropagation. Uvedený algoritmus učení backpropagation jednoduché sítě společně s popisem parametrů ovlivňujících učení sítě a také metody zhodnocení kvality naučení sítě. Definice momentů invariantních na otočení, posun a změnu měřítka. Optimalizace parametrů neuronové sítě k nalezení nejrychleji učící se neuronové sítě, a také sítě s nejlepší...

  17. How dependencies between successive examples affect on-line learning.

    Science.gov (United States)

    Wiegerinck, W; Heskes, T

    1996-11-15

    We study the dynamics of on-line learning for a large class of neural networks and learning rules, including backpropagation for multilayer perceptrons. In this paper, we focus on the case where successive examples are dependent, and we analyze how these dependencies affect the learning process. We define the representation error and the prediction error. The representation error measures how well the environment is represented by the network after learning. The prediction error is the average error that a continually learning network makes on the next example. In the neighborhood of a local minimum of the error surface, we calculate these errors. We find that the more predictable the example presentation, the higher the representation error, i.e., the less accurate the asymptotic representation of the whole environment. Furthermore we study the learning process in the presence of a plateau. Plateaus are flat spots on the error surface, which can severely slow down the learning process. In particular, they are notorious in applications with multilayer perceptrons. Our results, which are confirmed by simulations of a multilayer perceptron learning a chaotic time series using backpropagation, explain how dependencies between examples can help the learning process to escape from a plateau. PMID:8888616

  18. File access prediction using neural networks.

    Science.gov (United States)

    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

  19. 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.

  20. A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks.

    Science.gov (United States)

    Cavalieri, Salvatore; Mirabella, Orazio

    1999-01-01

    The paper deals with the problem of fault tolerance in a multilayer perceptron network. Although it already possesses a reasonable fault tolerance capability, it may be insufficient in particularly critical applications. Studies carried out by the authors have shown that the traditional backpropagation learning algorithm may entail the presence of a certain number of weights with a much higher absolute value than the others. Further studies have shown that faults in these weights is the main cause of deterioration in the performance of the neural network. In other words, the main cause of incorrect network functioning on the occurrence of a fault is the non-uniform distribution of absolute values of weights in each layer. The paper proposes a learning algorithm which updates the weights, distributing their absolute values as uniformly as possible in each layer. Tests performed on benchmark test sets have shown the considerable increase in fault tolerance obtainable with the proposed approach as compared with the traditional backpropagation algorithm and with some of the most efficient fault tolerance approaches to be found in literature. PMID:12662719

  1. Using a binaural biomimetic array to identify bottom objects ensonified by echolocating dolphins

    Science.gov (United States)

    Heiweg, D.A.; Moore, P.W.; Martin, S.W.; Dankiewicz, L.A.

    2006-01-01

    The development of a unique dolphin biomimetic sonar produced data that were used to study signal processing methods for object identification. Echoes from four metallic objects proud on the bottom, and a substrate-only condition, were generated by bottlenose dolphins trained to ensonify the targets in very shallow water. Using the two-element ('binaural') receive array, object echo spectra were collected and submitted for identification to four neural network architectures. Identification accuracy was evaluated over two receive array configurations, and five signal processing schemes. The four neural networks included backpropagation, learning vector quantization, genetic learning and probabilistic network architectures. The processing schemes included four methods that capitalized on the binaural data, plus a monaural benchmark process. All the schemes resulted in above-chance identification accuracy when applied to learning vector quantization and backpropagation. Beam-forming or concatenation of spectra from both receive elements outperformed the monaural benchmark, with higher sensitivity and lower bias. Ultimately, best object identification performance was achieved by the learning vector quantization network supplied with beam-formed data. The advantages of multi-element signal processing for object identification are clearly demonstrated in this development of a first-ever dolphin biomimetic sonar. ?? 2006 IOP Publishing Ltd.

  2. Laser ultrasound and simulated time reversal on bulk waves for non destructive control

    International Nuclear Information System (INIS)

    Laser welding of aluminium generally creates embedded welding defects, such as porosities or cracks. Non Destructive Inspection (NDI) after processing may ensure an acceptable weld quality by defect detection. Nowadays, NDI techniques used to control the inside of a weld are mainly limited to X-Rays or ultrasonics. The current paper describes the use of a Laser Ultrasound (LU) technique to inspect porosities in 2 and 4-mm thick sheet lap welds. First experimentations resulted in the detection of 0.5-mm drilled holes in bulk aluminium sheets. The measurement of the depth of these defects is demonstrated too. Further experimentations shows the applicability of the LU technique to detect porosities in aluminium laser welds. However, as the interpretation of raw measures is limiting the detection capacity of this technique, we developed a signal processing using Time-Reversal capabilities to enhance detection capacities. Furthermore, the signal processing output is a geometrical image of the material's inner state, increasing the ease of interpretation. It is based on a mass-spring simulation which enables the back-propagation of the acquired ultrasound signal. The spring-mass simulation allows the natural generation of all the different sound waves and thus enables the back-propagation of a raw signal without any need of filtering or wave identification and extraction. Therefore the signal processing uses the information contained in the compression wave as well as in the shear wave

  3. State-dependent firing determines intrinsic dendritic Ca2+ signaling in thalamocortical neurons.

    Science.gov (United States)

    Errington, Adam C; Renger, John J; Uebele, Victor N; Crunelli, Vincenzo

    2010-11-01

    Activity-dependent dendritic Ca(2+) signals play a critical role in multiple forms of nonlinear cellular output and plasticity. In thalamocortical neurons, despite the well established spatial separation of sensory and cortical inputs onto proximal and distal dendrites, respectively, little is known about the spatiotemporal dynamics of intrinsic dendritic Ca(2+) signaling during the different state-dependent firing patterns that are characteristic of these neurons. Here we demonstrate that T-type Ca(2+) channels are expressed throughout the entire dendritic tree of rat thalamocortical neurons and that they mediate regenerative propagation of low threshold spikes, typical of, but not exclusive to, sleep states, resulting in global dendritic Ca(2+) influx. In contrast, actively backpropagating action potentials, typical of wakefulness, result in smaller Ca(2+) influxes that can temporally summate to produce dendritic Ca(2+) accumulations that are linearly related to firing frequency but spatially confined to proximal dendritic regions. Furthermore, dendritic Ca(2+) transients evoked by both action potentials and low-threshold spikes are shaped by Ca(2+) uptake by sarcoplasmic/endoplasmic reticulum Ca(2+) ATPases but do not rely on Ca(2+)-induced Ca(2+) release. Our data demonstrate that thalamocortical neurons are endowed with intrinsic dendritic Ca(2+) signaling properties that are spatially and temporally modified in a behavioral state-dependent manner and suggest that backpropagating action potentials faithfully inform proximal sensory but not distal corticothalamic synapses of neuronal output, whereas corticothalamic synapses only "detect" Ca(2+) signals associated with low-threshold spikes. PMID:21048143

  4. Membership generation using multilayer neural network

    Science.gov (United States)

    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.

  5. Selective interferometric imaging of internal multiples

    KAUST Repository

    Zuberi, M. A H

    2013-01-01

    Internal multiples deteriorate the image when the imaging procedure assumes only single scattering, especially if the velocity model does not reproduce such scattering in the Green’s function. If properly imaged, internal multiples (and internally-scattered energy) can enhance the seismic image and illuminate areas otherwise neglected or poorly imaged by conventional single-scattering approaches. Conventionally, in order to image internal multiples, accurate, sharp contrasts in the velocity model are required to construct a Green’s function with all the scattered energy. As an alternative, we develop a three-step procedure, which images the first-order internal scattering using the background Green’s function (from the surface to each image point), constructed from a smooth velocity model: We first back-propagate the recorded surface data using the background Green’s function, then cross-correlate the back-propagated data with the recorded data and finally cross-correlate the result with the original background Green’s function. This procedure images the contribution of the recorded first-order internal multiples and is almost free of the single-scattering recorded energy. This image can be added to the conventional single-scattering image, obtained e.g. from Kirchhoff migration, to enhance the image. Application to synthetic data with reflectors illuminated by multiple scattering only demonstrates the effectiveness of the approach.

  6. Feasibility of using neural networks to unfold the response of multi-element TLD for mixed field dosimetry

    International Nuclear Information System (INIS)

    Significant advances have been made in recent years to improve calibration methodology and dose calculation algorithm in the fields of TL dosimetry. This process was accelerated in the past decade particularly in the Republic of Korea by the need to meet mandatory national accreditation requirements. The objective of this study is to develop a new algorithm to replace the simplistic decision tree algorithms by the more sophisticated neural networks in hopes of achieving a higher degree of accuracy and precision in personnel dosimetry system. The original hypothesis of this work is that the spectral information of an X and γ-ray fields may be obtained by the analysis of the response of a multi-element system. In this study, a feed forward neural network using the error back-propagation method with Bayesian optimization was designed for the response unfolding procedure. The response functions of the single element to photons were calculated by application of a computational Monte-Carlo model for an energy range from 10 keV to 2 MeV with different spectral proportions. The training of the artificial neural network was based on the computation of responses of a four-element system for the back-propagation method. The validation of the proposed algorithm was investigated by unfolding the 10 computed responses for arbitrary mixed gamma fields and the spectra resulting from the unfolding procedure agree well with the original spectra. (author)

  7. A Sequential Monte Carlo Approach for Streamflow Forecasting

    Science.gov (United States)

    Hsu, K.; Sorooshian, S.

    2008-12-01

    As alternatives to traditional physically-based models, Artificial Neural Network (ANN) models offer some advantages with respect to the flexibility of not requiring the precise quantitative mechanism of the process and the ability to train themselves from the data directly. In this study, an ANN model was used to generate one-day-ahead streamflow forecasts from the precipitation input over a catchment. Meanwhile, the ANN model parameters were trained using a Sequential Monte Carlo (SMC) approach, namely Regularized Particle Filter (RPF). The SMC approaches are known for their capabilities in tracking the states and parameters of a nonlinear dynamic process based on the Baye's rule and the proposed effective sampling and resampling strategies. In this study, five years of daily rainfall and streamflow measurement were used for model training. Variable sample sizes of RPF, from 200 to 2000, were tested. The results show that, after 1000 RPF samples, the simulation statistics, in terms of correlation coefficient, root mean square error, and bias, were stabilized. It is also shown that the forecasted daily flows fit the observations very well, with the correlation coefficient of higher than 0.95. The results of RPF simulations were also compared with those from the popular back-propagation ANN training approach. The pros and cons of using SMC approach and the traditional back-propagation approach will be discussed.

  8. 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 (Dst one hour in advance. The Bz-component and ΣBz, 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 Dst 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.

  9. An approach to unfold the response of a multi-element system using an artificial neural network

    International Nuclear Information System (INIS)

    An unfolding procedure is proposed which aims at obtaining spectral information of a neutron radiation field by the analysis of the response of a multi-element system consisting of converter type semiconductors. For the unfolding procedure an artificial neural network (feed forward network), trained by the back-propagation method, was used. The response functions of the single elements to neutron radiation were calculated by application of a computational model for an energy range from 10-2 eV to 10 MeV. The training of the artificial neural network was based on the computation of responses of a six-element system for a set of 300 neutron spectra and the application of the back-propagation method. The validation was performed by the unfolding of 100 computed responses. Two unfolding examples were pointed out for the determination of the neutron spectra. The spectra resulting from the unfolding procedure agree well with the original spectra used for the response computation

  10. Novel maximum-margin training algorithms for supervised neural networks.

    Science.gov (United States)

    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

  11. Structured Dendritic Inhibition Supports Branch-Selective Integration in CA1 Pyramidal Cells.

    Science.gov (United States)

    Bloss, Erik B; Cembrowski, Mark S; Karsh, Bill; Colonell, Jennifer; Fetter, Richard D; Spruston, Nelson

    2016-03-01

    Neuronal circuit function is governed by precise patterns of connectivity between specialized groups of neurons. The diversity of GABAergic interneurons is a hallmark of cortical circuits, yet little is known about their targeting to individual postsynaptic dendrites. We examined synaptic connectivity between molecularly defined inhibitory interneurons and CA1 pyramidal cell dendrites using correlative light-electron microscopy and large-volume array tomography. We show that interneurons can be highly selective in their connectivity to specific dendritic branch types and, furthermore, exhibit precisely targeted connectivity to the origin or end of individual branches. Computational simulations indicate that the observed subcellular targeting enables control over the nonlinear integration of synaptic input or the initiation and backpropagation of action potentials in a branch-selective manner. Our results demonstrate that connectivity between interneurons and pyramidal cell dendrites is more precise and spatially segregated than previously appreciated, which may be a critical determinant of how inhibition shapes dendritic computation. VIDEO ABSTRACT. PMID:26898780

  12. Learning techniques to train neural networks as a state selector for inverter-fed induction machines using direct torque control

    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.

  13. Artificial intelligence techniques to optimize the EDC/NHS-mediated immobilization of cellulase on Eudragit L-100.

    Science.gov (United States)

    Zhang, Yu; Xu, Jing-Liang; Yuan, Zhen-Hong; Qi, Wei; Liu, Yun-Yun; He, Min-Chao

    2012-01-01

    Two artificial intelligence techniques, namely artificial neural network (ANN) and genetic algorithm (GA) were combined to be used as a tool for optimizing the covalent immobilization of cellulase on a smart polymer, Eudragit L-100. 1-Ethyl-3-(3-dimethyllaminopropyl) carbodiimide (EDC) concentration, N-hydroxysuccinimide (NHS) concentration and coupling time were taken as independent variables, and immobilization efficiency was taken as the response. The data of the central composite design were used to train ANN by back-propagation algorithm, and the result showed that the trained ANN fitted the data accurately (correlation coefficient R(2) = 0.99). Then a maximum immobilization efficiency of 88.76% was searched by genetic algorithm at a EDC concentration of 0.44%, NHS concentration of 0.37% and a coupling time of 2.22 h, where the experimental value was 87.97 ± 6.45%. The application of ANN based optimization by GA is quite successful. PMID:22942683

  14. Application of Adaptive Neuro-Fuzzy Inference System for Prediction of Neutron Yield of IR-IECF Facility in High Voltages

    Science.gov (United States)

    Adineh-Vand, A.; Torabi, M.; Roshani, G. H.; Taghipour, M.; Feghhi, S. A. H.; Rezaei, M.; Sadati, S. M.

    2013-09-01

    This paper presents a soft computing based artificial intelligent technique, adaptive neuro-fuzzy inference system (ANFIS) to predict the neutron production rate (NPR) of IR-IECF device in wide discharge current and voltage ranges. A hybrid learning algorithm consists of back-propagation and least-squares estimation is used for training the ANFIS model. The performance of the proposed ANFIS model is tested using the experimental data using four performance measures: correlation coefficient, mean absolute error, mean relative error percentage (MRE%) and root mean square error. The obtained results show that the proposed ANFIS model has achieved good agreement with the experimental results. In comparison to the experimental data the proposed ANFIS model has MRE% <1.53 and 2.85 % for training and testing data respectively. Therefore, this model can be used as an efficient tool to predict the NPR in the IR-IECF device.

  15. Fault Diagnosis of Power System Based on Improved Genetic Optimized BP-NN

    Directory of Open Access Journals (Sweden)

    Yuan Pu

    2015-01-01

    Full Text Available BP neural network (Back-Propagation Neural Network, BP-NN is one of the most widely neural network models and is applied to fault diagnosis of power system currently. BP neural network has good self-learning and adaptive ability and generalization ability, but the operation process is easy to fall into local minima. Genetic algorithm has global optimization features, and crossover is the most important operation of the Genetic Algorithm. In this paper, we can modify the crossover of traditional Genetic Algorithm, using improved genetic algorithm optimized BP neural network training initial weights and thresholds, to avoid the problem of BP neural network fall into local minima. The results of analysis by an example, the method can efficiently diagnose network fault location, and improve fault-tolerance and grid fault diagnosis effect.

  16. 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

  17. Intelligent classification methods of grain kernels using computer vision analysis

    Science.gov (United States)

    Lee, Choon Young; Yan, Lei; Wang, Tianfeng; Lee, Sang Ryong; Park, Cheol Woo

    2011-06-01

    In this paper, a digital image analysis method was developed to classify seven kinds of individual grain kernels (common rice, glutinous rice, rough rice, brown rice, buckwheat, common barley and glutinous barley) widely planted in Korea. A total of 2800 color images of individual grain kernels were acquired as a data set. Seven color and ten morphological features were extracted and processed by linear discriminant analysis to improve the efficiency of the identification process. The output features from linear discriminant analysis were used as input to the four-layer back-propagation network to classify different grain kernel varieties. The data set was divided into three groups: 70% for training, 20% for validation, and 10% for testing the network. The classification experimental results show that the proposed method is able to classify the grain kernel varieties efficiently.

  18. Wavelet based approach for facial expression recognition

    Directory of Open Access Journals (Sweden)

    Zaenal Abidin

    2015-03-01

    Full Text Available Facial expression recognition is one of the most active fields of research. Many facial expression recognition methods have been developed and implemented. Neural networks (NNs have capability to undertake such pattern recognition tasks. The key factor of the use of NN is based on its characteristics. It is capable in conducting learning and generalizing, non-linear mapping, and parallel computation. Backpropagation neural networks (BPNNs are the approach methods that mostly used. In this study, BPNNs were used as classifier to categorize facial expression images into seven-class of expressions which are anger, disgust, fear, happiness, sadness, neutral and surprise. For the purpose of feature extraction tasks, three discrete wavelet transforms were used to decompose images, namely Haar wavelet, Daubechies (4 wavelet and Coiflet (1 wavelet. To analyze the proposed method, a facial expression recognition system was built. The proposed method was tested on static images from JAFFE database.

  19. FORECASTING NIKKEI 225 INDEX WITH SUPPORT VECTOR MACHINE

    Institute of Scientific and Technical Information of China (English)

    HUANG Wei; Yoshiteru Nakamori; WANG Shouyang; YU Lean

    2003-01-01

    Support Vector Machine (SVM) is a very specific type of learning algorithms characterized by the capacity control of the decision function, the use of the kernel functions and the sparsity of the solution. In this paper, we investigate the predictability of financial movement direction with SVM by forecasting the weekly movement direction of NIKKEI 225 index. To evaluate the forecasting ability of SVM, we compare the performance with those of Linear Discriminant Analysis, Quadratic Discriminant Analysis and Elman Backpropagation Neural Networks. The experiment results show that SVM outperforms other classification methods. Furthermore, we propose a combining model by integrating SVM with other classification methods. The combining model performs the best among the forecasting methods.

  20. Volatility Degree Forecasting of Stock Market by Stochastic Time Strength Neural Network

    Directory of Open Access Journals (Sweden)

    Haiyan Mo

    2013-01-01

    Full Text Available In view of the applications of artificial neural networks in economic and financial forecasting, a stochastic time strength function is introduced in the backpropagation neural network model to predict the fluctuations of stock price changes. In this model, stochastic time strength function gives a weight for each historical datum and makes the model have the effect of random movement, and then we investigate and forecast the behavior of volatility degrees of returns for the Chinese stock market indexes and some global market indexes. The empirical research is performed in testing the prediction effect of SSE, SZSE, HSI, DJIA, IXIC, and S&P 500 with different selected volatility degrees in the established model.

  1. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks.

    Science.gov (United States)

    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

  2. Detection of the electrocardiogram P-wave using wavelet analysis

    Energy Technology Data Exchange (ETDEWEB)

    Anant, K.S.; Rodrigue, G.H. [California Univ., Davis, CA (United States). Dept. of Applied Science]|[Lawrence Livermore National Lab., CA (United States); Dowla, F.U. [Lawrence Livermore National Lab., CA (United States)

    1994-01-01

    Since wavelet analysis is an effective tool for analyzing transient signals, we studied its feature extraction and representation properties for events in electrocardiogram (EKG) data. Significant features of the EKG include the P-wave, the QRS complex, and the T-wave. For this paper the feature that we chose to focus on was the P-wave. Wavelet analysis was used as a pre-processor for a backpropagation neural network with conjugate gradient learning. The inputs to the neural network were the wavelet transforms of EKGs at a particular scale. The desired output was the location of the P-wave. The results were compared to results obtained without using the wavelet transform as a pre-processor.

  3. Matching of the ECRH transmission line of W7-X

    Energy Technology Data Exchange (ETDEWEB)

    Michel, Georg, E-mail: michel@ipp.mpg.de [Max-Planck-Institut für Plasmaphysik, Teilinstitut Greifswald, EURATOM Association, Wendelsteinstr. 1, 17491 Greifswald (Germany); Erckmann, Volker; Hollmann, Frank; Jonitz, Lothar [Max-Planck-Institut für Plasmaphysik, Teilinstitut Greifswald, EURATOM Association, Wendelsteinstr. 1, 17491 Greifswald (Germany); Kasparek, Walter [Universität Stuttgart, Institut für Plasmaforschung, Pfaffenwaldring 31, 70569 Stuttgart (Germany); Laqua, Heinrich [Max-Planck-Institut für Plasmaphysik, Teilinstitut Greifswald, EURATOM Association, Wendelsteinstr. 1, 17491 Greifswald (Germany); Lechte, Carsten [Universität Stuttgart, Institut für Plasmaforschung, Pfaffenwaldring 31, 70569 Stuttgart (Germany); Marushchenko, Nikolai [Max-Planck-Institut für Plasmaphysik, Teilinstitut Greifswald, EURATOM Association, Wendelsteinstr. 1, 17491 Greifswald (Germany); Plaum, Burkhard [Universität Stuttgart, Institut für Plasmaforschung, Pfaffenwaldring 31, 70569 Stuttgart (Germany); Turkin, Yuriy [Max-Planck-Institut für Plasmaphysik, Teilinstitut Greifswald, EURATOM Association, Wendelsteinstr. 1, 17491 Greifswald (Germany); Weißgerber, Michael [Max-Planck-Institut für Plasmaphysik, EURATOM Association, Boltzmannstr. 2, 85748 Garching (Germany)

    2013-10-15

    The polarization of the directed ECRH power has to be matched to the plasma boundary with respect to the magnetic field at the density gradient region close to the last closed flux surface (LCFS). This is achieved by means of grooved mirrors, which provide the required polarization and which are part of the matching optics unit (MOU) of the gyrotrons. The RF radiation from the gyrotrons has to pass typically 16 mirrors in a complex three-dimensional arrangement in order to reach the plasma. The paper discusses the modeling of the ECRH transmission in order to find the required polarizer adjustment for each possible injection angle and plasma wave type (O- or X-mode). This includes the calculation of the polarization state on the plasma boundary, the back-propagation through the transmission line up to the MOU and finally the calculation of the corresponding angles of both polarizers.

  4. A method for predicting in-cylinder compound combustion emissions

    Institute of Scientific and Technical Information of China (English)

    苏石川; 严兆大; 元广杰; 曹韵华; 周重光

    2002-01-01

    This paper presents a method using a large steady-state engine operation data matrix to provide necessary information for successfully training a predictive network, while at the same time eliminating errors produced by the dispersive effects of the emissions measurement system. The steady-state training conditions of compound fuel allow for the correlation of time-averaged in-cylinder combustion variables to the engine-out NOx and HC emissions. The error back-propagation neural network (EBP) is then capable of learning the relationships between these variables and the measured gaseous emissions, and then interpolating between steady-state points in the matrix. This method for NOx and HC has been proved highly successful.

  5. Cutting force signal pattern recognition using hybrid neural network in end milling

    Institute of Scientific and Technical Information of China (English)

    Song-Tae SEONG; Ko-Tae JO; Young-Moon LEE

    2009-01-01

    Under certain cutting conditions in end milling, the signs of cutting forces change from positive to negative during a revolution of the tool. The change of force direction causes the cutting dynamics to be unstable which results in chatter vibration. Therefore, cutting force signal monitoring and classification are needed to determine the optimal cutting conditions and to improve the efficiency of cut. Artificial neural networks are powerful tools for solving highly complex and nonlinear problems. It can be divided into supervised and unsupervised learning machines based on the availability of a teacher. Hybrid neural network was introduced with both of functions of multilayer perceptron (MLP) trained with the back-propagation algorithm for monitoring and detecting abnormal state, and self organizing feature map (SOFM) for treating huge datum such as image processing and pattern recognition, for predicting and classifying cutting force signal patterns simultaneously. The validity of the results is verified with cutting experiments and simulation tests.

  6. Test system for defect detection in cementitious material with artificial neural network

    Directory of Open Access Journals (Sweden)

    Saowanee Saechai

    2013-04-01

    Full Text Available This paper introduces a newly developed test system for defect detection, classification of number of defects andidentification of defect materials in cement-based products. With the system, the pattern of ultrasonic waves for each case ofspecimen can be obtained from direct and indirect measurements. The machine learning algorithm called artificial neuralnetwork classifier with back-propagation model is employed for classification and verification of the wave patterns obtainedfrom different specimens. By applying the system, the presence or absence of a defect in mortar can be identified. Moreover,the system is applied to identify the number and materials of defects inside the mortar. The methodology is explained and theclassification results are discussed. The effectiveness of the developed test system is evaluated. Comparison of the classification results between different input features with different number of training sets is demonstrated. The results show that thistechnique based on pattern recognition has a potential for practical inspection of concrete structures.

  7. Development and evaluation of neural network models to estimate daily solar radiation at Córdoba, Argentina

    International Nuclear Information System (INIS)

    The objective of this work was to develop neural network models of backpropagation type to estimate solar radiation based on extraterrestrial radiation data, daily temperature range, precipitation, cloudiness and relative sunshine duration. Data from Córdoba, Argentina, were used for development and validation. The behaviour and adjustment between values observed and estimates obtained by neural networks for different combinations of input were assessed. These estimations showed root mean square error between 3.15 and 3.88 MJ m-2 d-1 . The latter corresponds to the model that calculates radiation using only precipitation and daily temperature range. In all models, results show good adjustment to seasonal solar radiation. These results allow inferring the adequate performance and pertinence of this methodology to estimate complex phenomena, such as solar radiation

  8. Bidding strategy based on artificial intelligence for a competitive electric market

    International Nuclear Information System (INIS)

    A bidding strategy using a fuzzy-c-mean (FCM) algorithm and the artificial neural network (ANN) was developed for competitive electric markets. The nodal price information was assumed to be released into the market. The FCM was used, first, to classify the daily load pattern into peak, medium-peak and off-peak levels and, secondly, to classify the competitive generation companies (gencos) into less-menacing, possible-menacing and menacing gencos. The back-propagation ANN was used for determining the bidding price for a genco. The FCM results aided in lessening the training data and reducing the ANN input nodes. The IEEE 30-busbar system was used for illustrating the applicability of the proposed method. (Author)

  9. A Prediction Model for Taiwan Tourism Industry Stock Index

    Directory of Open Access Journals (Sweden)

    Han-Chen Huang

    2013-12-01

    Full Text Available Investors and scholars pay continuous attention to the stock market, as each day, many investors attem pt to use different methods to predict stock price trends . However, as stock price is affected by economy, p olitics, domestic and foreign situations, emergency, human f actor, and other unknown factors, it is difficult t o establish an accurate prediction model. This study used a back-propagation neural network (BPN as the research approach, and input 29 variables, such as international exchange rate, indices of internation al stock markets, Taiwan stock market analysis indicat ors, and overall economic indicators, to predict Taiwan’s monthly tourism industry stock index. The empirical findings show that the BPN prediction mod el has better predictive accuracy, Absolute Relative E rror is 0.090058, and correlation coefficient is 0.944263. The model has low error and high correlat ion, and can serve as reference for investors and relevant industries.

  10. Learning and optimization with cascaded VLSI neural network building-block chips

    Science.gov (United States)

    Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

    1992-01-01

    To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

  11. Predicting Learners Performance Using Artificial Neural Networks in Linear Programming Intelligent Tutoring System

    Directory of Open Access Journals (Sweden)

    Samy S. Abu Naser

    2012-04-01

    Full Text Available In this paper we present a technique that employ Artificial Neural Networks and expert systems to obtain knowledge for the learner model in the Linear Programming Intelligent Tutoring System(LP-ITS to be able to determine the academic performance level of the learners in order to offer him/her the properdifficulty level of linear programming problems to solve. LP-ITS uses Feed forward Back-propagation algorithm to be trained with a group of learners data to predict their academic performance. Furthermore, LP-ITS uses an Expert System to decide the proper difficulty level that is suitable with the predicted academic performance of the learner. Several tests have been carried out to examine adherence to real time data. The accuracy of predicting the performance of the learners is very high and thus states that the Artificial Neural Network is skilled enough to make suitable predictions.

  12. Predicting Learners Performance Using Artificial Neural Networks in Linear Programming Intelligent Tutoring System

    Directory of Open Access Journals (Sweden)

    Samy S. Abu Naser

    2012-03-01

    Full Text Available In this paper we present a technique that employ Artificial Neural Networks and expert systems to obtain knowledge for the learner model in the Linear Programming Intelligent Tutoring System(LP-ITS to be able to determine the academic performance level of the learners in order to offer him/her the proper difficulty level of linear programming problems to solve. LP-ITS uses Feed forward Back-propagation algorithm to be trained with a group of learners data to predict their academic performance. Furthermore, LP-ITS uses an Expert System to decide the proper difficulty level that is suitable with the predicted academic performance of the learner. Several tests have been carried out to examine adherence to real time data. The accuracy of predicting the performance of the learners is very high and thus states that the Artificial Neural Network is skilled enough to make suitable predictions.

  13. 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.)

  14. 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

  15. 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.)

  16. 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)

  17. 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.

  18. Design of a Neuro-Fuzzy Controller for Speed Control Applied to DC Servo Motor

    Energy Technology Data Exchange (ETDEWEB)

    Kim, S.H.; Kang, Y.H.; Kim, L.K. [Konkuk University, Seoul (Korea); Ko, B.W. [Cheju College of Technology, Cheju (Korea)

    2002-02-01

    In this study, a neuro-fuzzy controller which has the characteristic of fuzzy control and artificial neural network is designed. A fuzzy rule to be applied is automatically selected by the allocated neurons. The neurons correspond to fuzzy rules are created by an expert. To adapt the more precise model is implemented by error back-propagation learning algorithm to adjust the link-weight of fuzzy membership function in the neuro-fuzzy controller. The more classified fuzzy rule is used to include the property of dual mode method. In order to verify the effectiveness of the proposed algorithm designed above, an operating characteristic of a DC servo motor with variable load is investigated. (author). 10 refs., 12 figs., 9 tabs.

  19. Condition Parameter Modeling for Anomaly Detection in Wind Turbines

    Directory of Open Access Journals (Sweden)

    Yonglong Yan

    2014-05-01

    Full Text Available Data collected from the supervisory control and data acquisition (SCADA system, used widely in wind farms to obtain operational and condition information about wind turbines (WTs, is of important significance for anomaly detection in wind turbines. The paper presents a novel model for wind turbine anomaly detection mainly based on SCADA data and a back-propagation neural network (BPNN for automatic selection of the condition parameters. The SCADA data sets are determined through analysis of the cumulative probability distribution of wind speed and the relationship between output power and wind speed. The automatic BPNN-based parameter selection is for reduction of redundant parameters for anomaly detection in wind turbines. Through investigation of cases of WT faults, the validity of the automatic parameter selection-based model for WT anomaly detection is verified.

  20. Automated Periodontal Diseases Classification System

    Directory of Open Access Journals (Sweden)

    Aliaa A. A. Youssif

    2012-01-01

    Full Text Available This paper presents an efficient and innovative system for automated classification of periodontal diseases, The strength of our technique lies in the fact that it incorporates knowledge from the patients' clinical data, along with the features automatically extracted from the Haematoxylin and Eosin (H&E stained microscopic images. Our system uses image processing techniques based on color deconvolution, morphological operations, and watershed transforms for epithelium & connective tissue segmentation, nuclear segmentation, and extraction of the microscopic immunohistochemical features for the nuclei, dilated blood vessels & collagen fibers. Also, Feedforward Backpropagation Artificial Neural Networks are used for the classification process. We report 100% classification accuracy in correctly identifying the different periodontal diseases observed in our 30 samples dataset.