Premium
Modeling resonant frequency of microstrip antenna based on neural network ensemble
Author(s) -
YuBo Tian,
SuLing Zhang,
JingYi Li
Publication year - 2010
Publication title -
international journal of numerical modelling: electronic networks, devices and fields
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.249
H-Index - 30
eISSN - 1099-1204
pISSN - 0894-3370
DOI - 10.1002/jnm.761
Subject(s) - particle swarm optimization , artificial neural network , genetic algorithm , algorithm , computer science , generalization , collinearity , binary number , antenna (radio) , chaos (operating system) , mathematics , artificial intelligence , telecommunications , machine learning , mathematical analysis , geometry , arithmetic , computer security
Resonant frequency is an important parameter in designing microstrip antenna (MSA). Selective neural network ensemble (NNE) methods based on decimal particle swarm optimization (PSO) algorithm and binary PSO algorithm are proposed in this study. The basic idea of the methods is to optimally select neural networks (NNs) to construct NNE with the aid of PSO algorithm. This may maintain the diversity of NNs and decrease the effects of collinearity and noise of sample. Simultaneously, chaos mutation is adopted to increase the diversity of particles of PSO. Experimental results show that the chaos PSO algorithm can improve the generalization ability of NNE. Moreover, by using this algorithm, model of resonant frequency of MSA is established. Computing results indicate that the model is better than the available ones. Copyright © 2010 John Wiley & Sons, Ltd.