Search

Abstract: In this paper, a model is considered to describe the dynamics of a class of non-autonomous neural networks with time-varying delays. By applying the properties of M-matrix, the techniques of inequality analysis and the Banach fixed point theorem, we obtain a series of new criteria on the dissipativity and existence of periodic attractor. Our results can extend and improve earlier ones. [Copyright &y& Elsevier]

A new load forecasting (LF) approach using bacterial foraging technique (BFT) trained wavelet neural network (WNN) is proposed in this paper. Artificial neural network (ANN) is combined with wavelet transform called wavelet neural network is applied for LF. The parameters of translation and dilation in the wavelet nodes and the weighting factors in the weighting nodes are tuned using BFT optimization. With the advantages of global search abilities of BFT as well as the multiresolution and localizing natures of wavelets, the networks are constructed which identifies the inherent non-linear characteristics of power system loads. The proposed approach is validated with Tamil Nadu Electricity Board (TNEB) system, India. The comparison of Delta Rule and BFT-based LF for different periods are depicted with their mean absolute percentage errors (MAPE). [Copyright &y& Elsevier]

Line flow or real-power contingency selection and ranking is performed to choose the contingencies that cause the worst overloading problems. In this paper, a cascade neural network-based approach is proposed for fast line flow contingency selection and ranking. The developed cascade neural network is a combination of a filter module and a ranking module. All the contingency cases are applied to the filter module, which is trained to classify them either in critical contingency class or in non-critical contingency class using a modified BP algorithm. The screened critical contingencies are passed to the ranking module (four-layered feed-forward artificial neural network (ANN)) for their further ranking. Effectiveness of the proposed ANN-based method is demonstrated by applying it for contingency screening and ranking at different loading conditions for IEEE 14-bus system. Once trained, the cascade neural network gives fast and accurate screening and ranking for unknown patterns and is found to be suitable for on-line applications at energy management centre. [Copyright &y& Elsevier]

Trenching is an economical and effective method to reduce surface vibrations and isolate structures from shaking. Previous reports on vibration screening concentrated on either experimental work or analytical study. Due to the construction of more complex structures in the last two decades, presenting more complicated boundary conditions, a variety of numerical methods have been used. Complexity of formulation, the large number of parameters involved, and the difficulty and time required to analyze an effective vibration screening makes the direct numerical approach impractical. The purpose of this paper is to explore the use of an artificial neural network to estimate the effectiveness of a vibration screening trench. Three artificial neural networks, BPN, GRNN, and RBF, are used to evaluate the performance of a chosen physical model. The results show that all three models can be used to evaluate effectiveness of screening trenches with varying accuracy, with GRNN having the highest accuracy. There is much stronger agreement with data of numerically calculated results for neural networks than for empirical multi-variate regression methods. [Copyright &y& Elsevier]

Abstract: One of the phenomena that can be observed when using neural networks for time series prediction is that the quality of the forecasts obtained is correlated with the dimensionality of the data. Higher data dimensionality leads, in most cases, to higher prediction errors. This phenomenon is connected by some authors to the decrease in variance of the distances between the data points, which occurs when the lengths of the predicted vectors increase. In this paper, a proof is given that the variance of the distances between data points also decreases with the so-called correlation dimension of the data. Therefore, a drop in forecast quality might be expected not only when the lengths of the data vectors are increased, but also when using vectors of the same length to represent data of increasing dimensionality. We also present some experimental results that illustrate the dependence between data dimensionality and the variance of the distances between the data points, and the forecast error obtained when using a multilayer perceptron to predict future values of some time series. [Copyright &y& Elsevier]

Abstract: Modal logics are amongst the most successful applied logical systems. Neural networks were proved to be effective learning systems. In this paper, we propose to combine the strengths of modal logics and neural networks by introducing Connectionist Modal Logics (CML). CML belongs to the domain of neural-symbolic integration, which concerns the application of problem-specific symbolic knowledge within the neurocomputing paradigm. In CML, one may represent, reason or learn modal logics using a neural network. This is achieved by a Modalities Algorithm that translates modal logic programs into neural network ensembles. We show that the translation is sound, i.e. the network ensemble computes a fixed-point meaning of the original modal program, acting as a distributed computational model for modal logic. We also show that the fixed-point computation terminates whenever the modal program is well-behaved. Finally, we validate CML as a computational model for integrated knowledge representation and learning by applying it to a well-known testbed for distributed knowledge representation. This paves the way for a range of applications on integrated knowledge representation and learning, from practical reasoning to evolving multi-agent systems. [Copyright &y& Elsevier]

The application of artificial neural networks (ANNs) to solve wind engineering problems has received increasing interests in recent years. This paper is concerned with developing two ANN approaches (a backpropagation neural network [BPNN] and a fuzzy neural network [FNN]) for the prediction of mean, root-mean-square (rms) pressure coefficients and time series of wind-induced pressures on a large gymnasium roof. In this study, simultaneous pressure measurements are made on a large gymnasium roof model in a boundary layer wind tunnel and parts of the model test data are used as the training sets for developing two ANN models to recognize the input–output patterns. Comparisons of the prediction results by the two ANN approaches and those from the wind tunnel test are made to examine the performance of the two ANN models, which demonstrates that the two ANN approaches can successfully predict the pressures on the entire surfaces of the large roof on the basis of wind tunnel pressure measurements from a certain number of pressure taps. Moreover, the FNN approach is found to be superior to the BPNN approach. It is shown through this study that the developed ANN approaches can be served as an effective tool for the design and analysis of wind effects on large roof structures. [Copyright &y& Elsevier]

Abstract: This paper proposes a new algorithm for a class of binary images thinning by using two PCNNs (pulse coupled neural networks). Once the travelling pulses of the two PCNNs meet, the thinning result is obtained. The criterion of pulses meeting is given, and the parameters of the PCNNs are also specified, which make the implementation of the proposed thinning algorithm easier. The algorithm is used to thin such a class of binary images, which separate the original images into two regions, as circularity-like images and ribbon-like shapes. Experimental results show that the proposed algorithm is efficient in extracting the skeleton of images (such as circularity-like images, ribbon-like shapes, handwriting ‘0’, etc.). [Copyright &y& Elsevier]

Abstract: Although the role of lateral inhibition in edge (contrast) enhancement is well known, it has not been parametrized. This paper investigates the imbalance between the lateral inhibitory and excitatory stimuli and its effect on the edge enhancement and stability. It is shown that this imbalance can be expressed through , a ratio of inhibitory to excitatory weights in a neuron. Stability requires to be less than the critical ratio . As approaches , edge enhancement increases, the rise being the sharpest just before instability. The increase in edge enhancement is also accompanied by an increase in the lateral spread of perturbations across the neuron layer. [Copyright &y& Elsevier]

Abstract: The construction of computational models with provision for effective learning and added reasoning is a fundamental problem in computer science. In this paper, we present a new computational model for integrated reasoning and learning that combines intuitionistic reasoning and neural networks. We use ensembles of neural networks to represent intuitionistic theories, and show that for each intuitionistic theory and intuitionistic modal theory there exists a corresponding neural network ensemble that computes a fixed-point semantics of the theory. This provides a massively parallel model for intuitionistic reasoning. In our model, the neural networks can be trained from examples to adapt to new situations using standard neural learning algorithms, thus providing a unifying foundation for intuitionistic reasoning, knowledge representation, and learning. [Copyright &y& Elsevier]

Abstract: This paper proves that the typical neural network-based input/output model does not have a state-space realization and suggests the Additive Nonlinear Auto-Regressive with eXogenous input (ANARX) structure as an excellent choice for neural-network-based input–output models. The advantage of the ANARX model is that the time-steps in the argument are pair-wise decomposed, which allows the ANARX model to be realized in state space, and to be linearized via dynamic output feedback. Moreover, accessibility of the state-space realization has been proved. [Copyright &y& Elsevier]

This paper presents architectures for comparator trees capable of finding the minimum value of a large number of inputs. Such circuits are of general applicability although the intended application for which the circuits were designed is the winner-take-all function of a digital implementation of a neural network based on the self organising map. Mechanisms for reducing delay based on look-ahead logic within individual comparators and mechanisms based on multiplexor architectures of a comparator are compared for both propagation delay and area. [Copyright &y& Elsevier]

This paper presents a technique based on artificial neural networks (ANN) to estimate pollutant rates of emission from industrial stacks, on the basis of pollutant concentrations measured on the ground. The ANN is trained on data generated by the ISCST3 model, widely accepted for evaluation of dispersion of primary pollutants as a part of an environmental impact study. Simulations using theoretical values and comparison with field data are done, obtaining good results in both cases at predicting emission rates.The application of this technique would allow the local environment authority to control emissions from industrial plants without need of performing direct measurements inside the plant. [Copyright &y& Elsevier]

Abstract: The Kohonen self-organization map is usually considered as a classification or clustering tool, with only a few applications in time series prediction. In this paper, a particular time series forecasting method based on Kohonen maps is described. This method has been specifically designed for the prediction of long-term trends. The proof of the stability of the method for long-term forecasting is given, as well as illustrations of the utilization of the method both in the scalar and vectorial cases. [Copyright &y& Elsevier]

Problem decomposition and divide-and-conquer strategies have been proposed to improve the performance and realization of neural network solutions for complex problems. This paper reports on an experimental evaluation of performance gains brought about by problem decomposition for abductive network classifiers that classify four noisy waveform patterns having two waveform types (sine/cosine) and two different frequencies. Two-stage problem decomposition improves overall classification accuracy from 87.2% to 99%. Problem decomposition classifiers were found to be much more tolerant to model simplification and reduction in the training set size compared to monolithic solutions. This allows trading-off some of the large gain in classification performance for some other advantages that may be quite desirable in some applications, such as simpler models that execute faster and are easier to implement, smaller training sets, and shorter training times. A problem decomposition classifier is more accurate than a monolithic classifier in spite of the former being five times simpler, executing over two times faster, requiring one-fifth of the training data, and synthesized in one-eleventh of the training time. Performance is comparable with a neural network solution using the same decomposition method and significantly superior to an abductive network committee approach. [Copyright &y& Elsevier]

This paper suggests a decision support system for tactical air combat environment where not much prior information is available about the decision regions. We proposed a combination of unsupervised learning for clustering the data (to develop decision regions) and a feed forward neural network to classify the decision regions accurately. The clustered data is used as the inputs to the multi-layered feed forward neural network, which is trained using several higher order learning paradigms. Experiment results reveal that the proposed method is efficient. [Copyright &y& Elsevier]

Principal component analysis (PCA) is an effective method of linear dimensional reduction. Because of its simplicity in theory and implementation, it is often used for analyses in various disciplines. However, because of its linearity, PCA is not always suitable, and has redundancy in expressing data. To overcome this problem, some nonlinear PCA methods have been proposed. However, most of these methods have drawbacks, such that the number of principal components must be predetermined, and also the order of the generated principal components is not explicitly given. In this paper, we propose a nonlinear PCA algorithm that nonlinearly transforms data into principal components, and at the same time, preserving the order of the principal components, and we also propose a hierarchical neural network model to perform the algorithm. Moreover, our method does not need to know the number of principal components in advance. The effectiveness of the proposed model will be shown through experiments. [Copyright &y& Elsevier]

In this paper we show how genetic algorithms and neural networks are combined to build a high-performance signal pattern classifier (GNSPC). Signal patterns are intrinsic to many sensor-based systems. The goal of GNSPC is to differentiate among large numbers of signal pattern classes with low classification cost and high classification performance. Classification performance is measured by the correct classification of noisy signal patterns despite using pure signal patterns for building the classifier. GNSPC is basically a decision tree classifier with similarity classification rules. The rules are used to test the similarity of signal patterns. A combination of a genetic algorithm and a neural network is used to find the best rules for the decision tree. This combination provides powerful classification capabilities with great tuning flexibility for either performance or cost-efficiency. Learning techniques are employed to set the genetic algorithm global parameters and to obtain training data for the neural network. [Copyright &y& Elsevier]

In this paper, we propose a new clustering algorithm for a mixture of Gaussian-based neural network and self-growing probabilistic decision-based neural networks (SPDNN). The proposed self-growing cluster learning (SGCL) algorithm is able to find the natural number of prototypes based on a self-growing validity measure, Bayesian information criterion (BIC). The learning process starts from a single prototype randomly initialized in the feature space and grows adaptively during the learning process until most appropriate number of prototypes are found. We have conducted numerical and real-world experiments to demonstrate the effectiveness of the SGCL algorithm. In the results of using SGCL to train the SPDNN for data clustering and speaker identification problems, we have observed a noticeable improvement among various model-based or vector quantization-based classification schemes. [Copyright &y& Elsevier]

This paper presents a new approach for integrating case-based reasoning (CBR) with an ART-Kohonen neural network (ART-KNN) to enhance fault diagnosis. When solving a new problem, the neural network is used to make hypotheses and to guide the CBR module in the search for a similar previous case that supports one of the hypotheses. The knowledge acquired by the network is interpreted and mapped into symbolic diagnosis descriptors, which are kept and used by the system to determine whether a final answer is credible, and to build explanations for the reasoning carried out. ART-KNN, synthesizing the theory of adaptive resonance theory and the learning strategy of Kohonen neural network, can solve the plasticity-stability dilemma of conventional neural networks. It can carry out ‘on-line’ training without forgetting previously trained patterns (stable training), and recode previously trained categories adaptive to changes in the environment and is self-organizing, which differs from most of networks that only can be carried out off-line. The proposed system has been used in the faults diagnosis of electric motor to verify the system performance. The result shows the proposed system performs better than self-organizing feature map (SOFM) based system with respect to classification rate. [Copyright &y& Elsevier]

One of the main tasks of chemometrics is to classify chemical objects to one of several distinct predefined categories. There are many classification methods in data mining, one of which is the boosting technique that can improve predicate performance of a given classifier and it is one of the most powerful methods in classification methodology. In this paper, we apply boosting neural network (NN) and boosting tree in classification for chemical data. Experimental results show that boosting can significantly improve the prediction performance of any single classification method. Two techniques to interpret the model are also introduced in order to help us better understand the experimental results. [Copyright &y& Elsevier]

In the presented work, we propose two approaches to study the similarity between proteomic maps. First, we introduced similarity index as a robust parameter to express the degree of similarity among proteomic maps. Second, we treated the proteomic maps with self-organizing map (SOM) technique taking the abundances of spots as input variables. The study was performed on a set of reported proteomic maps, which were experimentally derived from mouse liver after the animals were treated with peroxisome proliferators. (Entire study included five peroxisome proliferators, control, and a non-peroxisome proliferating compound.) In original paper, the authors analyzed the data with the principal component method. Later other authors reported the study on the same data set using different numerical representations of proteomic maps. The presented results are in agreement with reported conclusions. [Copyright &y& Elsevier]

In this work we present the cooperative coevolution of multi-layer generalized perceptrons. This model is based on the cooperation of different subpopulations of modules, each one being a generalized multi-layered perceptron.In some previous works we have developed a modular cooperative coevolutive model for evolving multi-layer perceptrons with two hidden layers. This model performs very well but tends to generate big networks. In the present paper we show the results of substituting these multi-layer perceptrons by generalized multi-layer perceptrons, which allow a more compact representation of networks.The use of generalized multi-layer perceptrons improved the performance of the evolutionary model with regard to the evolution of other kinds of networks. Another improvement was that the networks obtained were much smaller. The comparison proved statistically significant by means of a Student''s t-test. [Copyright &y& Elsevier]

Dynamic branch prediction in high-performance processors is a specific instance of a general time series prediction problem that occurs in many areas of science. Most branch prediction research focuses on two-level adaptive branch prediction techniques, a very specific solution to the branch prediction problem. An alternative approach is to look to other application areas and fields for novel solutions to the problem. In this paper, we examine the application of neural networks to dynamic branch prediction. We retain the first level history register of conventional two-level predictors and replace the second level PHT with a neural network. Two neural networks are considered: a learning vector quantisation network and a backpropagation network. We demonstrate that a neural predictor can achieve misprediction rates comparable to conventional two-level adaptive predictors and suggest that neural predictors merit further investigation. [Copyright &y& Elsevier]

Jet engines are nonlinear dynamical systems for which an exact mathematical model cannot be used for estimator design, because it is either not available or so complex that it does not fit the necessary assumptions. Thus, classical analytical tools for studying standard system properties like observability, which is very important in estimator design, cannot be directly applied. Generally, for practical jet engine applications, the designer faces two closely related problems: first, given a non-measurable parameter, find the minimal set of estimator inputs that facilitates achieving a satisfactory estimation performance (input selection); second, given a predetermined set of inputs, derive an “observability” measure that characterizes the estimation feasibility of a specific non-measurable parameter. In this paper, techniques for solving these two problems are developed and applied to estimator design for jet engine thrust, stall margins, and an unmeasurable state. [Copyright &y& Elsevier]

This paper investigates the asymmetric costs of false positive and negative errors to enhance the IDS performance. The proposed method utilizes the neural network model to consider the cost ratio of false negative errors to false positive errors. Compared with false positive errors, false negative errors incur a greater loss to organizations which are connected to the systems by networks. This method is designed to accomplish both security and system performance objectives. The results of our empirical experiment show that the neural network model provides high accuracy in intrusion detection. In addition, the simulation results show that the effectiveness of intrusion detection can be enhanced by considering the asymmetric costs of false negative and false positive errors. [Copyright &y& Elsevier]

The application of pattern recognition techniques, expert systems, artificial neural networks, fuzzy systems and nowadays hybrid artificial intelligence (AI) techniques in manufacturing can be regarded as consecutive elements of a process started two decades ago. The paper outlines the most important steps of this process and introduces some new results with special emphasis on hybrid AI and multistrategy machine learning approaches. Agent-based (holonic) systems are highlighted as promising tools for managing complexity, changes and disturbances in production systems. Further integration of approaches is predicted. [Copyright &y& Elsevier]

In this paper, we address the problem of stable tracking control of a flexible macro–micro manipulator (M3) system. A two-layer neural network is utilized to approximate the nonlinear robot dynamic behavior of the M3 system, and the controllers for the macro and micro arms are developed without any need for prior knowledge of the dynamic model of the controlled M3 system. A learning algorithm for the neural network using Lyapunov stability theory is derived. It is shown that both the tracking error and the weight-tuning error are uniformly ultimately bounded under this new control scheme. Simulation results are presented and compared to those obtained using a PD controller. [Copyright &y& Elsevier]

A neural network model called lateral interaction in accumulative computation for detection of non-rigid objects from motion of any of their parts in indefinite sequences of images is presented. Some biological evidences inspire the model. After introducing the model, the complete multi-layer neural architecture is offered in this paper. The architecture consists of four layers that perform segmentation by gray level bands, accumulative charge computation, charge redistribution by gray level bands and moving object fusion. The lateral interaction in accumulative computation associated learning algorithm is also introduced. Some examples that explain the usefulness of the system we propose are shown at the end of this article. [Copyright &y& Elsevier]