Search

A theoretical investigation of neutral-type of delayed inertial neural networks using the Lyapunov stability theory and Linear Matrix Inequality (LMI) approach is presented. Based on a suitable variable transformation, an inertial neural network consisting of second-order differential equations can be converted into a first-order differential model. The sufficient conditions of the delayed inertial neural network are derived by constructing suitable Lyapunov functional candidates, introducing new free weighting matrices, and utilizing the Writinger integral inequality. Through the LMI solution, we analyse the global asymptotic stability condition of the resulting delayed inertial neural network. Simulation examples are presented to demonstrate the effectiveness of the derived analytical results. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, the circle segments (CS) technique is proposed as a data visualization tool for selecting and analysing the effects of the input features towards the target outputs in constructing neural network models. Specifically, the multi-layer perceptron (MLP) network is employed to tackle function approximation and pattern classification tasks, and CS is used to provide visualization of the correlations between the input features and the target outputs in these tasks. The effectiveness of the proposed approach is evaluated using two benchmark data sets, one for function approximation and another for pattern classification. Performance comparison with the response surface methodology (in function approximation) and with principal component analysis (in pattern classification) is conducted. The results indicate the usefulness of CS in examining the correlations between the input–output data samples, with improved performances. In addition, a real medical diagnosis task is used to evaluate the applicability of the approach. The outcomes, again, demonstrate improvements in accuracy, sensitivity, and specificity with the use of CS for feature selection, even with more than 50% of the input features eliminated. [Copyright &y& Elsevier]

Abstract: In this paper, a hybrid neural network model, based on the integration of fuzzy ARTMAP (FAM) and the rectangular basis function network (RecBFN), which is capable of learning and revealing fuzzy rules is proposed. The hybrid network is able to classify data samples incrementally and, at the same time, to extract rules directly from the network weights for justifying its predictions. With regards to process systems engineering, the proposed network is applied to a fault detection and diagnosis task in a power generation station. Specifically, the efficiency of the network in monitoring the operating conditions of a circulating water (CW) system is evaluated by using a set of real sensor measurements collected from the power station. The rules extracted are analyzed, discussed, and compared with those from a rule extraction method of FAM. From the comparison results, it is observed that the proposed network is able to extract more meaningful rules with a lower degree of rule redundancy and higher interpretability within the neural network framework. The extracted rules are also in agreement with experts’ opinions for maintaining the CW system in the power generation plant. [Copyright &y& Elsevier]

This paper proposes an intelligent decision-support system for managing manufacturing technology investments. The intelligent system is a hybrid integration of two information processing modules: case-based reasoning and fuzzy ARTMAP – a supervised adaptive resonance theory (ART) neural network with a multi-dimensional map. The developed system captures a company's strategic information, provides facilities to quantify qualitative attributes and analyses them alongside the quantitative attributes in an evaluation framework. Through the system, similar cases can be retrieved to enable managers to make effective use of their knowledge and experience of previously delivered technologies and projects as an input to the prioritization of future projects. Other salient features of the system include its ability to adapt and absorb new knowledge and responses pertaining to significant events in the business environment, as well as to extract and elucidate information from the knowledge database for explaining and justifying its analysis. The applicability of the developed system is evaluated using a real case study in collaboration with a pharmaceutical manufacturing firm. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a hybrid Artificial Neural Network (ANN) model that is developed for noisy data classification. The model, named GRNNFA, is a fusion of the Fuzzy Adaptive Resonance Theory (FA) model and the General Regression Neural Network (GRNN) model. The GRNNFA model not only retains the important features of the parent models, which include stable learning, fast training, and an incremental growth network structure, but also facilitates the removal of noise that is embedded in training samples. The robustness of the GRNNFA model is demonstrated by the Noisy Two Intertwined Spirals problem and other benchmarking problems. The model is then applied to Fisher''s Iris Data, which is a real-world classification problem. The results show that the percentage of correct predictions is statistically higher than in variant models of the adaptive resonance theory. The GRNNFA is further employed in a new application area of soft computing—fire dynamics, which is highly non-linear in nature. Flashover is the most dangerous scenrio in the development of a compartment fire, during which, any unburned combustible material, including the unburned soot particles inside the compartment, is ignited spontaneously and all combustible material is then simultaneously involved in the burning process. The GRNNFA model is applied to predict the occurrence of the flashover in compartment fires based on the fire size and the geometry of the fire compartment. The performance of the GRNNFA is compared with other published results, and it is shown to be statistically superior to other ANN models. [Copyright &y& Elsevier]

This article, we explore the asymptotic stability and asymptotic synchronization analysis of fractional order delayed Cohen–Grossberg neural networks with discontinuous neuron activation functions (FCGNNDDs). First, under the framework of Filippov theory and differential inclusion theoretical analysis, the global existence of Filippov solution for FCGNNDDs is studied by means of the given growth condition. Second, by virtue of suitable Lyapunov functional, Young inequality and comparison theorem for fractional order delayed linear system, some global asymptotic stability conditions for such system is derived by limiting discontinuous neuron activations. Third, the global asymptotic synchronization condition for FCGNNDDs is obtained based on the pinning control. At last, two numerical simulations are given to verify the theoretical findings. [ABSTRACT FROM AUTHOR]

• this is the first study, on the global asymptotic stability of Clifford valued NNs with impulsive effects. • the results of our study are more general and newer as compared with those in the literature, even when our considered model degenerates into real-valued, complex-valued, or quaternion-valued systems. • Compared with the related literature, the conditions we need are easy to satisfy and the method used in this study can be easily applied for analyzing other dynamic properties of different delayed Clifford-valued NN models. In this paper, we focus on the global asymptotic stability problem for Clifford-valued neural network models with time-varying delays as well as impulsive effects. By considering impulsive effects, a general class of network model is considered, which encompasses real-valued, complex-valued, and quaternion-valued neural network models as special cases. Firstly, the n -dimensional Clifford-valued model is decomposed into 2 m n -dimensional real-valued model, which avoids non-commutativity of multiplication of Clifford numbers. Based on the Lyapunov stability theory, contraction mapping principle, and some mathematical concepts, we derive the existence, uniqueness of the equilibrium point with respect to the model. New sufficient conditions are also derived, in order to ensure the global asymptotic stability of the considered model. To illustrate the usefulness of the obtained results, a simulation example is presented. [ABSTRACT FROM AUTHOR]