New fuzzy inference system using a support vector machine

Author

Kim, Jongcheol ; Won, Sangchul

Author_Institution

Div. of Electr. & Comput. Eng., Pohang Univ. of Sci. & Technol., South Korea

Volume

2

fYear

2002

fDate

10-13 Dec. 2002

Firstpage

1349

Abstract

In this paper, we present a new support vector fuzzy inference system (SVFIS) for nonlinear system modeling. The proposed SVFIS is constructed using the support vector machine which does not have a bias term. The number of fuzzy rules is reduced by adjusting the parameter values of membership functions using the gradient descent method. Once a structure is selected, the parameter values in the consequent part of the Tagaki-Sugeno (TS) fuzzy model are determined by the least square method. The simulation result illustrates the effectiveness of the proposed SVFIS.

Keywords

fuzzy logic; gradient methods; inference mechanisms; learning automata; least squares approximations; nonlinear systems; SVFIS; TS fuzzy model; Tagaki-Sugeno fuzzy model; fuzzy rules; gradient descent method; least-square method; membership functions; nonlinear system modeling; parameter value adjustment; support vector fuzzy inference system; support vector machine; Clustering methods; Costs; Fuzzy neural networks; Fuzzy systems; Grid computing; Kernel; Least squares methods; Neural networks; Nonlinear systems; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 2002, Proceedings of the 41st IEEE Conference on

ISSN

0191-2216

Print_ISBN

0-7803-7516-5

Type

conf

DOI

10.1109/CDC.2002.1184703

Filename

1184703