Search

Abstract: The Gravitational Search Algorithm (GSA) is a novel heuristic optimization method based on the law of gravity and mass interactions. It has been proven that this algorithm has good ability to search for the global optimum, but it suffers from slow searching speed in the last iterations. This work proposes a hybrid of Particle Swarm Optimization (PSO) and GSA to resolve the aforementioned problem. In this paper, GSA and PSOGSA are employed as new training methods for Feedforward Neural Networks (FNNs) in order to investigate the efficiencies of these algorithms in reducing the problems of trapping in local minima and the slow convergence rate of current evolutionary learning algorithms. The results are compared with a standard PSO-based learning algorithm for FNNs. The resulting accuracy of FNNs trained with PSO, GSA, and PSOGSA is also investigated. The experimental results show that PSOGSA outperforms both PSO and GSA for training FNNs in terms of converging speed and avoiding local minima. It is also proven that an FNN trained with PSOGSA has better accuracy than one trained with GSA. [Copyright &y& Elsevier]

Abstract: The biggest problem that networked control systems face is the random time-varying delay, which often causes system instability and even collapse. Aiming at this problem, a new modeling scheme for the networked control systems, motivated from a variable-period sampling approach, is presented in this paper. Here, the time delay to occur at current sampling step is taken as the sampling period between current sampling step and next sampling step. To predict online the time delay induced in the networked control systems, a BP feedforward neural network is adopted and the training algorithm of the BP neural network is given. To make the BP neural network adapt to the changing environment of the networked control systems and improve its prediction accuracy, the BP neural network is designed to further update according to its prediction error after each prediction. At each sampling step, good approximation to actual time delay becomes available and different sampling period is obtained. Control simulations using the variable sampling period and fixed sampling period are compared. Simulation results show that this new approach can alleviate the influence of time delay to the greatest extent and improve the performance of the networked control systems. [Copyright &y& Elsevier]

Abstract: In this paper we equate the problem of predicting the loop 3D structure in the comparative modeling to a problem of finding the maximal clique with the best weight. Each possible conformation of a residue in a loop sequence is represented as a node in a graph. Edges are then drawn between pairs of nodes that are consistent with each other. Edge and nodes are weighted according to some fixed criteria. Once the entire graph is constructed, all the maximal sets of cliques are found using an algorithm of artificial neural network models. The cliques with the best weights represent the optimal conformation of the region of loop sequence. [Copyright &y& Elsevier]