Search results for: Neural Models

Authors: A. Muthuramalingam, S. Himavathi, E. Srinivasan

Abstract:

.Hardware realization of a Neural Network (NN), to a large extent depends on the efficient implementation of a single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. This paper discusses the issues involved in implementation of a multi-input neuron with linear/nonlinear excitation functions using FPGA. Implementation method with resource/speed tradeoff is proposed to handle signed decimal numbers. The VHDL coding developed is tested using Xilinx XC V50hq240 Chip. To improve the speed of operation a lookup table method is used. The problems involved in using a lookup table (LUT) for a nonlinear function is discussed. The percentage saving in resource and the improvement in speed with an LUT for a neuron is reported. An attempt is also made to derive a generalized formula for a multi-input neuron that facilitates to estimate approximately the total resource requirement and speed achievable for a given multilayer neural network. This facilitates the designer to choose the FPGA capacity for a given application. Using the proposed method of implementation a neural network based application, namely, a Space vector modulator for a vector-controlled drive is presented

Keywords: FPGA implementation, multi-input neuron, neural network, nn based space vector modulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4369

Authors: A. Jabbari, R. Jedermann, W. Lang

Abstract:

The new idea of this research is application of a new fault detection and isolation (FDI) technique for supervision of sensor networks in transportation system. In measurement systems, it is necessary to detect all types of faults and failures, based on predefined algorithm. Last improvements in artificial neural network studies (ANN) led to using them for some FDI purposes. In this paper, application of new probabilistic neural network features for data approximation and data classification are considered for plausibility check in temperature measurement. For this purpose, two-phase FDI mechanism was considered for residual generation and evaluation.

Keywords: Fault detection and Isolation, Neural network, Temperature measurement, measurement approximation and classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2037

Authors: Mohamed A. Khlifi, Badr M. Alshammari

Abstract:

This paper discusses the general methods to saturation in the steady-state, two axis (d & q) frame models of synchronous machines. In particular, the important role of the magnetic coupling between the d-q axes (cross-magnetizing phenomenon), is demonstrated. For that purpose, distinct methods of saturation modeling of dumper synchronous machine with cross-saturation are identified, and detailed models synthesis in d-q axes. A number of models are given in the final developed form. The procedure and the novel models are verified by a critical application to prove the validity of the method and the equivalence between all developed models is reported. Advantages of some of the models over the existing ones and their applicability are discussed.

Keywords: Cross-magnetizing, models synthesis, synchronous machine, saturated modeling, state-space vectors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2197

Authors: S. Mousavian, D. Ashouri, F. Mousavian, V. Nikkhah Rashidabad, N. Ghazinia

Abstract:

PH, temperature and time of extraction of each stage,  agitation speed and delay time between stages effect on efficiency of  zinc extraction from concentrate. In this research, efficiency of zinc  extraction was predicted as a function of mentioned variable by  artificial neural networks (ANN). ANN with different layer was  employed and the result show that the networks with 8 neurons in  hidden layer has good agreement with experimental data.

 

Keywords: Zinc extraction, Efficiency, Neural networks, Operating condition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1551

Authors: Zohreh Sheikh Khozani, Wan Hanna Melini Wan Mohtar, Mojtaba Porhemmat

Abstract:

Prediction of wall shear stress in a rectangular channel, with non-homogeneous roughness distribution, was studied. Estimation of shear stress is an important subject in hydraulic engineering, since it affects the flow structure directly. In this study, the Genetic Algorithm Artificial (GAA) neural network is introduced as a hybrid methodology of the Artificial Neural Network (ANN) and modified Genetic Algorithm (GA) combination. This GAA method was employed to predict the wall shear stress. Various input combinations and transfer functions were considered to find the most appropriate GAA model. The results show that the proposed GAA method could predict the wall shear stress of open channels with high accuracy, by Root Mean Square Error (RMSE) of 0.064 in the test dataset. Thus, using GAA provides an accurate and practical simple-to-use equation.

Keywords: Artificial neural network, genetic algorithm, genetic programming, rectangular channel, shear stress.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 622

Authors: M. Khouil, N. Saber, M. Mestari

Abstract:

In this paper, a different architecture of a collision detection neural network (DCNN) is developed. This network, which has been particularly reviewed, has enabled us to solve with a new approach the problem of collision detection between two convex polyhedra in a fixed time (O (1) time). We used two types of neurons, linear and threshold logic, which simplified the actual implementation of all the networks proposed. The study of the collision detection is divided into two sections, the collision between a point and a polyhedron and then the collision between two convex polyhedra. The aim of this research is to determine through the AMAXNET network a mini maximum point in a fixed time, which allows us to detect the presence of a potential collision.

Keywords: Collision identification, fixed time, convex polyhedra, neural network, AMAXNET.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1784

Authors: Abhishek Bansal, G. N. Pillai

Abstract:

This paper presents a new method to detect high impedance faults in radial distribution systems. Magnitudes of third and fifth harmonic components of voltages and currents are used as a feature vector for fault discrimination. The proposed methodology uses a learning vector quantization (LVQ) neural network as a classifier for identifying high impedance arc-type faults. The network learns from the data obtained from simulation of a simple radial system under different fault and system conditions. Compared to a feed-forward neural network, a properly tuned LVQ network gives quicker response.

Keywords: Fault identification, distribution networks, high impedance arc-faults, feature vector, LVQ networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2169

Authors: S. A. Gawish, F. A. Khalifa, R. M. Mostafa

Abstract:

This paper presents Simulation and experimental study aimed at investigating the effectiveness of an adaptive artificial neural network stabilizer on enhancing the damping torque of a synchronous generator. For this purpose, a power system comprising a synchronous generator feeding a large power system through a short tie line is considered. The proposed adaptive neuro-control system consists of two multi-layered feed forward neural networks, which work as a plant model identifier and a controller. It generates supplementary control signals to be utilized by conventional controllers. The details of the interfacing circuits, sensors and transducers, which have been designed and built for use in tests, are presented. The synchronous generator is tested to investigate the effect of tuning a Power System Stabilizer (PSS) on its dynamic stability. The obtained simulation and experimental results verify the basic theoretical concepts.

Keywords: Adaptive artificial neural network, power system stabilizer, synchronous generator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1426

Authors: Young-Seok Choi

Abstract:

This work assesses the cortical and the sub-cortical neural activity recorded from rodents using entropy and mutual information based approaches to study how hypothermia affects neural activity. By applying the multi-scale entropy and Shannon entropy, we quantify the degree of the regularity embedded in the cortical and sub-cortical neurons and characterize the dependency of entropy of these regions on temperature. We study also the degree of the mutual information on thalamocortical pathway depending on temperature. The latter is most likely an indicator of coupling between these highly connected structures in response to temperature manipulation leading to arousal after global cerebral ischemia.

Keywords: Spiking activity, entropy, mutual information, temperature modulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1598

Authors: Zixin Liu, Jianjun Jiao Wanping Bai

Abstract:

In this paper, the issue of pth moment exponential stability of stochastic recurrent neural network with distributed time delays is investigated. By using the method of variation parameters, inequality techniques, and stochastic analysis, some sufficient conditions ensuring pth moment exponential stability are obtained. The method used in this paper does not resort to any Lyapunov function, and the results derived in this paper generalize some earlier criteria reported in the literature. One numerical example is given to illustrate the main results.

Keywords: Stochastic recurrent neural networks, pth moment exponential stability, distributed time delays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1220

Authors: Pawalai Kraipeerapun, Chun Che Fung, Kok Wai Wong

Abstract:

This paper proposes a novel approach to the question of lithofacies classification based on an assessment of the uncertainty in the classification results. The proposed approach has multiple neural networks (NN), and interval neutrosophic sets (INS) are used to classify the input well log data into outputs of multiple classes of lithofacies. A pair of n-class neural networks are used to predict n-degree of truth memberships and n-degree of false memberships. Indeterminacy memberships or uncertainties in the predictions are estimated using a multidimensional interpolation method. These three memberships form the INS used to support the confidence in results of multiclass classification. Based on the experimental data, our approach improves the classification performance as compared to an existing technique applied only to the truth membership. In addition, our approach has the capability to provide a measure of uncertainty in the problem of multiclass classification.

Keywords: Multiclass classification, feed-forward backpropagation neural network, interval neutrosophic sets, uncertainty.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1600

Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota

Abstract:

Understanding the causes of a road accident and predicting their occurrence is key to prevent deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network. 

Keywords: Accident risks estimation, artificial neural network, deep learning, K-mean, road safety.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 878

Authors: Jiann-Ming Wu, Hsiao-Chang Chen, Chun-Chang Wu, Pei-Hsun Hsu

Abstract:

This work explores blind image deconvolution by recursive function approximation based on supervised learning of neural networks, under the assumption that a degraded image is linear convolution of an original source image through a linear shift-invariant (LSI) blurring matrix. Supervised learning of neural networks of radial basis functions (RBF) is employed to construct an embedded recursive function within a blurring image, try to extract non-deterministic component of an original source image, and use them to estimate hyper parameters of a linear image degradation model. Based on the estimated blurring matrix, reconstruction of an original source image from a blurred image is further resolved by an annealed Hopfield neural network. By numerical simulations, the proposed novel method is shown effective for faithful estimation of an unknown blurring matrix and restoration of an original source image.

Keywords: Blind image deconvolution, linear shift-invariant(LSI), linear image degradation model, radial basis functions (rbf), recursive function, annealed Hopfield neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2011

Authors: Truong Quang Dang Khoa, Masahiro Nakagawa

Abstract:

Chaos and fractals are novel fields of physics and mathematics showing up a new way of universe viewpoint and creating many ideas to solve several present problems. In this paper, a novel algorithm based on the chaotic sequence generator with the highest ability to adapt and reach the global optima is proposed. The adaptive ability of proposal algorithm is flexible in 2 steps. The first one is a breadth-first search and the second one is a depth-first search. The proposal algorithm is examined by 2 functions, the Camel function and the Schaffer function. Furthermore, the proposal algorithm is applied to optimize training Multilayer Neural Networks.

Keywords: learning and evolutionary computing, Chaos Optimization Algorithm, Artificial Neural Networks, nonlinear optimization, intelligent computational technologies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1746

Authors: Entisar A. Elgmati

Abstract:

Recurrent event data is a special type of multivariate survival data. Dynamic and frailty models are one of the approaches that dealt with this kind of data. A comparison between these two models is studied using the empirical standard deviation of the standardized martingale residual processes as a way of assessing the fit of the two models based on the Aalen additive regression model. Here we found both approaches took heterogeneity into account and produce residual standard deviations close to each other both in the simulation study and in the real data set.

Keywords: Dynamic, frailty, misspecification, recurrent events.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2322

Authors: S. Anna Durai, E. Anna Saro

Abstract:

In general the images used for compression are of different types like dark image, high intensity image etc. When these images are compressed using Counter Propagation Neural Network, it takes longer time to converge. The reason for this is that the given image may contain a number of distinct gray levels with narrow difference with their neighborhood pixels. If the gray levels of the pixels in an image and their neighbors are mapped in such a way that the difference in the gray levels of the neighbor with the pixel is minimum, then compression ratio as well as the convergence of the network can be improved. To achieve this, a Cumulative Distribution Function is estimated for the image and it is used to map the image pixels. When the mapped image pixels are used the Counter Propagation Neural Network yield high compression ratio as well as it converges quickly.

Keywords: Correlation, Counter Propagation Neural Networks, Cummulative Distribution Function, Image compression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1636

Authors: Govind Shay Sharma, Randhir Singh Baghel

Abstract:

The stock management of raw materials and finished goods is a significant issue for industries in fulfilling customer demand. Optimization of inventory strategies is crucial to enhancing customer service, reducing lead times and costs, and meeting market demand. This paper suggests finding an approach to predict the optimum stock level by utilizing past stocks and forecasting the required quantities. In this paper, we utilized Artificial Neural Network (ANN) to determine the optimal value. The objective of this paper is to discuss the optimized ANN that can find the best solution for the inventory model. In the context of the paper, we mentioned that the k-means algorithm is employed to create homogeneous groups of items. These groups likely exhibit similar characteristics or attributes that make them suitable for being managed using uniform inventory control policies. The paper proposes a method that uses the neural fit algorithm to control the cost of inventory.

Keywords: Artificial Neural Network, inventory management, optimization, distributor center.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 109

Authors: P. Sankar, P. James Daniel Paul, Siddhant Sahu

Abstract:

A brief review of the empirical studies on the methodology of the stock market decision support would indicate that they are at a threshold of validating the accuracy of the traditional and the fuzzy, artificial neural network and the decision trees. Many researchers have been attempting to compare these models using various data sets worldwide. However, the research community is on the way to the conclusive confidence in the emerged models. This paper attempts to use the automotive sector stock prices from National Stock Exchange (NSE), India and analyze them for the intra-sectorial support for stock market decisions. The study identifies the significant variables and their lags which affect the price of the stocks using OLS analysis and decision tree classifiers.

Keywords: Indian Automotive Sector, Stock Market Decisions, Equity Portfolio Analysis, Decision Tree Classifiers, Statistical Data Analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2003

Authors: Z. Shaaban

Abstract:

This paper presents a new approach to tackle the problem of recognizing machine-printed Arabic texts. Because of the difficulty of recognizing cursive Arabic words, the text has to be normalized and segmented to be ready for the recognition stage. The new scheme for recognizing Arabic characters depends on multiple parallel neural networks classifier. The classifier has two phases. The first phase categories the input character into one of eight groups. The second phase classifies the character into one of the Arabic character classes in the group. The system achieved high recognition rate.

Keywords: Neural Networks, character recognition, feature extraction, multiple networks, Arabic text.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1444

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, capsule network, capacity optimization, character recognition, data augmentation; semantic segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 656

Authors: Yaping Ren, Yongkun Li

Abstract:

In this paper, by using the continuation theorem of coincidence degree theory, M-matrix theory and constructing some suitable Lyapunov functions, some sufficient conditions are obtained for the existence and global exponential stability of periodic solutions of recurrent neural networks with distributed delays and impulses on time scales. Without assuming the boundedness of the activation functions gj, hj , these results are less restrictive than those given in the earlier references.

Keywords: Recurrent neural networks, global exponential stability, periodic solutions, distributed delays, impulses, time scales.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1557

Authors: Amir Reza Saffari Azar Alamdari

Abstract:

In this paper, a model of self-organizing spiking neural networks is introduced and applied to mobile robot environment representation and path planning problem. A network of spike-response-model neurons with a recurrent architecture is used to create robot-s internal representation from surrounding environment. The overall activity of network simulates a self-organizing system with unsupervised learning. A modified A* algorithm is used to find the best path using this internal representation between starting and goal points. This method can be used with good performance for both known and unknown environments.

Keywords: Mobile Robot, Path Planning, Self-organization, Spiking Neural Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1458

Authors: Yongzhi Liao

Abstract:

By using the theory of exponential dichotomy and Banach fixed point theorem, this paper is concerned with the problem of the existence and uniqueness of positive almost periodic solution in a delayed Lotka-Volterra recurrent neural networks with harvesting terms. To a certain extent, our work in this paper corrects some result in recent years. Finally, an example is given to illustrate the feasibility and effectiveness of the main result.

Keywords: positive almost periodic solution, Lotka-Volterra, neural networks, Banach fixed point theorem, harvesting

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1584

Authors: Tao Peng, Jing Zhao, Yanqing Xu, Jing Cai

Abstract:

Due to missing/ambiguous boundaries between the prostate and neighboring structures, the presence of shadow artifacts, as well as the large variability in prostate shapes, ultrasound prostate segmentation is challenging. To handle these issues, this paper develops a hybrid method for ultrasound prostate segmentation by combining an optimized closed principal curve-based method and the evolutionary neural network; the former can fit curves with great curvature and generate a contour composed of line segments connected by sorted vertices, and the latter is used to express an appropriate map function (represented by parameters of evolutionary neural network) for generating the smooth prostate contour to match the ground truth contour. Both qualitative and quantitative experimental results showed that our proposed method obtains accurate and robust performances.

Keywords: Ultrasound prostate segmentation, optimized closed polygonal segment method, evolutionary neural network, smooth mathematical model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 387

Authors: S. Jadid, S. Jalilzadeh

Abstract:

In this paper, an improved technique for contingency ranking using artificial neural network (ANN) is presented. The proposed approach is based on multi-layer perceptrons trained by backpropagation to contingency analysis. Severity indices in dynamic stability assessment are presented. These indices are based on the concept of coherency and three dot products of the system variables. It is well known that some indices work better than others for a particular power system. This paper along with test results using several different systems, demonstrates that combination of indices with ANN provides better ranking than a single index. The presented results are obtained through the use of power system simulation (PSS/E) and MATLAB 6.5 software.

Keywords: composite indices, transient stability, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2191

Authors: M.V Rajesh, Archana R, A Unnikrishnan, R Gopikakumari, Jeevamma Jacob

Abstract:

The System Identification problem looks for a suitably parameterized model, representing a given process. The parameters of the model are adjusted to optimize a performance function based on error between the given process output and identified process output. The linear system identification field is well established with many classical approaches whereas most of those methods cannot be applied for nonlinear systems. The problem becomes tougher if the system is completely unknown with only the output time series is available. It has been reported that the capability of Artificial Neural Network to approximate all linear and nonlinear input-output maps makes it predominantly suitable for the identification of nonlinear systems, where only the output time series is available. [1][2][4][5]. The work reported here is an attempt to implement few of the well known algorithms in the context of modeling of nonlinear systems, and to make a performance comparison to establish the relative merits and demerits.

Keywords: Multilayer neural networks, Radial Basis Functions, Clustering algorithm, Back Propagation training, Extended Kalmanfiltering, Mean Square Error, Nonlinear Modeling, Cramer RaoLower Bound.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1618

Authors: M. Sedighizadeh, M. Rezaei, V. Najmi

Abstract:

The Proton Exchange Membrane Fuel Cell (PEMFC) control system has an important effect on operation of cell. Traditional controllers couldn-t lead to acceptable responses because of time- change, long- hysteresis, uncertainty, strong- coupling and nonlinear characteristics of PEMFCs, so an intelligent or adaptive controller is needed. In this paper a neural network predictive controller have been designed to control the voltage of at the presence of fluctuations of temperature. The results of implementation of this designed NN Predictive controller on a dynamic electrochemical model of a small size 5 KW, PEM fuel cell have been simulated by MATLAB/SIMULINK.

Keywords: PEMFC, Neural Network, Predictive Control..

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2574

Authors: Asaad Moosa

Abstract:

In recent years with the rapid development of Internet and the Web, more and more web applications have been deployed in many fields and organizations such as finance, military, and government. Together with that, hackers have found more subtle ways to attack web applications. According to international statistics, SQL Injection is one of the most popular vulnerabilities of web applications. The consequences of this type of attacks are quite dangerous, such as sensitive information could be stolen or authentication systems might be by-passed. To mitigate the situation, several techniques have been adopted. In this research, a security solution is proposed using Artificial Neural Network to protect web applications against this type of attacks. The solution has been experimented on sample datasets and has given promising result. The solution has also been developed in a prototypic web application firewall called ANNbWAF.

Keywords: Artificial Neural Networks ANN, SQL Injection, Web Application Firewall WAF, Web Application Scanner WAS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5595

Authors: Venus Marza, Amin Seyyedi, Luiz Fernando Capretz

Abstract:

Software estimation accuracy is among the greatest challenges for software developers. This study aimed at building and evaluating a neuro-fuzzy model to estimate software projects development time. The forty-one modules developed from ten programs were used as dataset. Our proposed approach is compared with fuzzy logic and neural network model and Results show that the value of MMRE (Mean of Magnitude of Relative Error) applying neuro-fuzzy was substantially lower than MMRE applying fuzzy logic and neural network.

Keywords: Artificial Neural Network, Fuzzy Logic, Neuro-Fuzzy, Software Estimation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1624

Authors: Christian Endisch, Christoph Hackl, Dierk Schröder

Abstract:

This paper presents an exact pruning algorithm with adaptive pruning interval for general dynamic neural networks (GDNN). GDNNs are artificial neural networks with internal dynamics. All layers have feedback connections with time delays to the same and to all other layers. The structure of the plant is unknown, so the identification process is started with a larger network architecture than necessary. During parameter optimization with the Levenberg- Marquardt (LM) algorithm irrelevant weights of the dynamic neural network are deleted in order to find a model for the plant as simple as possible. The weights to be pruned are found by direct evaluation of the training data within a sliding time window. The influence of pruning on the identification system depends on the network architecture at pruning time and the selected weight to be deleted. As the architecture of the model is changed drastically during the identification and pruning process, it is suggested to adapt the pruning interval online. Two system identification examples show the architecture selection ability of the proposed pruning approach.

Keywords: System identification, dynamic neural network, recurrentneural network, GDNN, optimization, Levenberg Marquardt, realtime recurrent learning, network pruning, quasi-online learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1899