A Hybrid Method Based on Combining Artificial Neural Network and Fuzzy Inference System for Simultaneous Computation of Resonant Frequencies of Rectangular, Circular, and Triangular Microstrip Antennas

Author

Guney, Kerim ; Sarikaya, Nurcan

Author_Institution

Dept. of Electron. Eng., Erciyes Univ., Kayseri

Volume

55

Issue

3

fYear

2007

fDate

3/1/2007 12:00:00 AM

Firstpage

659

Lastpage

668

Abstract

A hybrid method based on a combination of artificial neural network (ANN) and fuzzy inference system (FIS) is presented to calculate simultaneously the resonant frequencies of various microstrip antennas (MSAs) of regular geometries. The ANN is trained with the Bayesian regulation algorithm. An algorithm that integrates least square method and backpropagation algorithm is used to identify the parameters of FIS. The resonant frequency results of the proposed hybrid method for the rectangular, circular, and triangular MSAs are in very good agreement with the experimental results available in the literature

Keywords

Bayes methods; backpropagation; electrical engineering computing; geometry; least squares approximations; microstrip antennas; neural nets; ANN; Bayesian regulation algorithm; FIS; artificial neural network; backpropagation; fuzzy inference system; geometry; hybrid method; least square method; microstrip antenna; rectangular-circular-triangular MSA; Artificial neural networks; Backpropagation algorithms; Bayesian methods; Computer networks; Fuzzy neural networks; Fuzzy systems; Geometry; Inference algorithms; Microstrip antennas; Resonant frequency; Fuzzy inference system; microstrip antenna (MSA); neural network; resonant frequency;

fLanguage

English

Journal_Title

Antennas and Propagation, IEEE Transactions on

Publisher

ieee

ISSN

0018-926X

Type

jour

DOI

10.1109/TAP.2007.891566

Filename

4120262