Search

Abstract: Software reliability is an important factor for quantitatively characterizing software quality and estimating the duration of software testing period. Traditional parametric software reliability growth models (SRGMs) such as nonhomogeneous Poisson process (NHPP) models have been successfully utilized in practical software reliability engineering. However, no single such parametric model can obtain accurate prediction for all cases. In addition to the parametric models, non-parametric models like neural network have shown to be effective alternative techniques for software reliability prediction. In this paper, we propose a non-parametric software reliability prediction system based on neural network ensembles. The effects of system architecture on the performance are investigated. The comparative studies between the proposed system with the single neural network based system and three parametric NHPP models are carried out. The experimental results demonstrate that the system predictability can be significantly improved by combing multiple neural networks. [Copyright &y& Elsevier]

Abstract: This paper is a study of the application of artificial neural networks to the problem of calculating error compensation values for axis positioning on a machine tool. The primary focus is on the development of a neural network-based system that could be implemented and integrated into the open architecture control system of an actual machine. A number of neural network architectures were examined for applicability to the problem and one was selected and implemented on the actual machine. Positioning error compensation capabilities were evaluated using industry standard equipment and procedures, and the results obtained were compared with the capabilities of standard error compensation routines in machine tool controls. [Copyright &y& Elsevier]

Abstract: In this paper, we address the problem of neural networks (NNs) stabilization and disturbance rejection for a class of nonlinear switched impulsive systems. An adaptive NN feedback control scheme and an impulsive controller for output tracking error disturbance attenuation of nonlinear switched impulsive systems are given under all admissible switched strategy based on NN. The NN is used to compensate for the nonlinear uncertainties of switched impulsive systems, and the approximation error of NN is introduced to the adaptive law in order to improve the tracking attenuation quality of the switched impulsive systems. Impulsive controller is designed to attenuate effect of switching impulse. Under all admissible switching law, impulsive controller and adaptive NN feedback controller can guarantee asymptotic stability of tracking error and improve disturbance attenuation level of tracking error for the overall nonlinear switched impulsive system. Finally, a numerical example is given to demonstrate the effectiveness of the proposed control and stabilization methods. [Copyright &y& Elsevier]

Abstract: This paper presents a novel quadratic error-counting network for pattern classification. Two computational issues namely, the network learning issue and the classification error-counting issue have been addressed. Essentially, a linear series functional approximation to network structure and a smooth quadratic error-counting cost function were proposed to resolve these two computational issues within a single framework. Our analysis shows that the quadratic error-counting objective can be related to the least-squares-error objective by adjusting the class-specific normalization factors. The binary classification network is subsequently extended to cater for multicategory problems. An extensive empirical evaluation validates the usefulness of proposed method. [Copyright &y& Elsevier]

Abstract: Synchronization is an important phenomenon which occurs in the dynamics of complex systems. Synchronized states emerge both from an adjustment of the system parameters and from an application of a proper external stimulus. In the present paper we study synchronized activity in a neural network model whose dynamics is driven by an external activation. In this context we are interested in its synchronizability, i.e. the existence of inputs causing the model system to synchronize. Furthermore, we investigate global synchronizability properties of stochastic network structure ensembles (instead of single realizations of a network architecture). We study the small world network, a model of preferential linking structure, and the classical Erdős–Renyi random graph as particular examples of network topologies. Their synchronizability properties are investigated by analytical arguments and numerical simulations. Our analysis shows the emergence of synchronizable states of network ensembles for a wide range of the parameter values. In addition we observe and study the transition behaviour from synchronizability to nonsynchronizability. [Copyright &y& Elsevier]

Abstract: During the last 10 years, the application of neural networks to solve oilfield problems has advanced. More recently, fuzzy logic proved beneficial when selecting variables to serve as neural network inputs. This paper presents a background to establish that neural networks are more than a “black box” and summarizes three applications of artificial intelligence technology to predict the secondary-to-primary ratio of a waterflood candidate using public domain information, the potential gas-producing rate of a behind pipe interval given only gamma ray and density logs, and the performance of single-well chemical imbibition treatments. Artificial intelligence used in this manner is essentially a statistical analysis, and as such the size of the dataset and the extent of the domain are important. Ignoring these important factors could result in overtraining of the neural network. Special care should be taken to avoid the pitfalls associated with overtraining. The neural network architectures were designed using a trial-and-error technique. Initially, a constructive design was employed by adding complexity to the architecture in terms of increasing the number of input variables as well as the number of hidden layers and nodes. A technique based on conventional statistical parameters was developed to numerically describe the patterns observed in log crossplots. These numerical descriptions were then prioritized and used as neural network inputs to be correlated with known production response. [Copyright &y& Elsevier]

Abstract: The aim of this paper is the definition of a new model of neural network, called generalized cellular nonlinear network, that covers architectures and dynamics of the well known and widely used classes of feedforward neural networks and cellular neural networks. We show how cellular neural networks and feedforward neural networks can be derived from the general model: moreover we prove a theorem of existence and uniqueness for the solution of the system that describes the generalized cellular nonlinear network dynamics. These results are obtained using the method of Lyapunov’s finite majorizing equations that also represents a new approach in studying the stability of cellular neural networks. [Copyright &y& Elsevier]

Abstract: Principal component analysis (PCA) has been generalized to complex principal component analysis (CPCA), which has been widely applied to complex-valued data, two-dimensional vector fields, and complexified real data through the Hilbert transform. Nonlinear PCA (NLPCA) can also be performed using auto-associative feed-forward neural network (NN) models, which allows the extraction of nonlinear features in the data set. This paper introduces a nonlinear complex PCA (NLCPCA) method, which allows nonlinear feature extraction and dimension reduction in complex-valued data sets. The NLCPCA uses the architecture of the NLPCA network, but with complex variables (including complex weight and bias parameters). The application of NLCPCA on test problems confirms its ability to extract nonlinear features missed by the CPCA. For similar number of model parameters, the NLCPCA captures more variance of a data set than the alternative real approach (i.e. replacing each complex variable by two real variables and applying NLPCA). The NLCPCA is also used to perform nonlinear Hilbert PCA (NLHPCA) on complexified real data. The NLHPCA applied to the tropical Pacific sea surface temperatures extracts the El Niño-Southern Oscillation signal better than the linear Hilbert PCA. [Copyright &y& Elsevier]