Search

Abstract: This paper presents a procedure to add broader diversity at the beginning of the evolutionary process. It consists of creating two initial populations with different parameter settings, evolving them for a small number of generations, selecting the best individuals from each population in the same proportion and combining them to constitute a new initial population. At this point the main loop of an evolutionary algorithm is applied to the new population. The results show that our proposal considerably improves both the efficiency of previous methodologies and also, significantly, their efficacy in most of the data sets. We have carried out our experimentation on twelve data sets from the UCI repository and two complex real-world problems which differ in their number of instances, features and classes. [Copyright &y& Elsevier]

Abstract: In this paper, a Feature-Extraction Neuron-Fuzzy Classification Model (FENFCM) is proposed that enables the extraction of feature variables and provides the classification results. The proposed classification model synergistically integrates a standard fuzzy inference system and a neural network with supervised learning. The FENFCM automatically generates the fuzzy rules from the numerical data and triangular functions that are used as membership functions both in the feature extraction unit and in the inference unit. To adapt the proposed FENFCM, two modificatory algorithms are applied. First, we utilize Evolutionary Programming (EP) to determine the distribution of fuzzy sets for each feature variable of the feature extraction unit. Second, the Weight Revised Algorithm (WRA) is used to regulate the weight grade of the principal output node of the inference unit. Finally, the proposed FENFCM is validated using two benchmark data sets: the Wine database and the Iris database. Computer simulation results demonstrate that the proposed classification model can provide a sufficiently high classification rate in comparison with that of other models proposed in the literature. [Copyright &y& Elsevier]

In this paper, we focus on the experimental analysis on the performance in artificial neural networks with the use of statistical tests on the classification task. Particularly, we have studied whether the sample of results from multiple trials obtained by conventional artificial neural networks and support vector machines checks the necessary conditions for being analyzed through parametrical tests. The study is conducted by considering three possibilities on classification experiments: random variation in the selection of test data, the selection of training data and internal randomness in the learning algorithm. The results obtained state that the fulfillment of these conditions are problem-dependent and indefinite, which justifies the need of using non-parametric statistics in the experimental analysis. [Copyright &y& Elsevier]

Abstract: Minor component analysis (MCA) is an important statistical tool for signal processing and data analysis. Neural networks can be used to extract online minor component from input data. Compared with traditional algebraic approaches, a neural network method has a lower computational complexity. Stability of neural networks learning algorithms is crucial to practical applications. In this paper, we propose a stable MCA neural networks learning algorithm, which has a more satisfactory numerical stability than some existing MCA algorithms. Dynamical behaviors of the proposed algorithm are analyzed via deterministic discrete time (DDT) method and the conditions are obtained to guarantee convergence. Simulations are carried out to illustrate the theoretical results achieved. [Copyright &y& Elsevier]

Abstract: This paper proposes a new technique based on artificial neural network useful for the characterization of superplastic behaviour, in particular for PbSn60 alloy. A three-layer neural network with back propagation (BP) algorithm is employed to train the network. The network input parameters are: alloy grain size, strain and strain rate. Just one is the output: the flow stress. Experiments are performed to evaluate the behaviour of PbSn60 alloy, subject to uniaxial tensile test, when the cross speed is kept constant. The strain rate sensitivity value (m) has been estimated analyzing the slope of the curve. It is shown that BP artificial neural network can predict the flow stress and, consequently, the m index during superplastic deformation with considerable efficiency and accuracy. [Copyright &y& Elsevier]

Abstract: This paper presents a strength model of steel columns under elevated temperatures using the artificial neural network. The many influencing parameters make it difficult to build an analytical steel strength model. Being a flexible model building method, the artificial neural network is an ideal tool to construct the complex relationship between the input and the output parameters accurately. A hybrid neural network, which combines the sigmoid neurons and the radial basis function neurons at the hidden layer, is proposed to better map the input–output relationship both locally and globally. The use of the genetic algorithm approach in searching the best-hidden neurons makes the hybrid neural network less likely to be trapped in local minima than the traditional gradient-based search algorithms. The genetic algorithm based hybrid neural network is applied to model the strength of steel columns under fire. The neural network results are compared with the modified Rankine formula. [Copyright &y& Elsevier]

Abstract: Particle swarm optimization (PSO) is an optimization technique based on population, which has similarities to other evolutionary algorithms. It is initialized with a population of random solutions and searches for optima by updating generations. Particle swarm optimization has become the hotspot of evolutionary computation because of its excellent performance and simple implementation. After introducing the basic principle of the PSO, a particle swarm optimization algorithm embedded with constraint fitness priority-based ranking method is proposed in this paper to solve nonlinear programming problem. By designing the fitness function and constraints-handling method, the proposed PSO can evolve with a dynamic neighborhood and varied inertia weighted value to find the global optimum. The results from this preliminary investigation are quite promising and show that this algorithm is reliable and applicable to almost all of the problems in multiple-dimensional, nonlinear and complex constrained programming. It is proved to be efficient and robust by testing some example and benchmarks of the constrained nonlinear programming problems. [Copyright &y& Elsevier]

Mathematical essence and structures of the feedforward neural networks are investigated in this paper. The interpolation mechanisms of the feedforward neural networks are explored. For example, the well-known result, namely, that a neural network is an universal approximator, can be concluded naturally from the interpolative representations. Finally, the learning algorithms of the feedforward neural networks are discussed. [Copyright &y& Elsevier]