A neurofuzzy system based on rough set theory and genetic algorithms

Author

Luo, Jian-xu ; Shao, Hui-he

Author_Institution

Inst. of Autom., Shanghai Jiao Tong Univ., China

Volume

2

fYear

2003

fDate

2-5 Nov. 2003

Firstpage

1147

Abstract

This paper presents a hybrid soft computing modeling approach, a neurofuzzy system based on rough set theory and genetic algorithms (NFRSGA). To solve the curse of dimensionality problem of neurofuzzy system, rough set is applied to obtain the reductive fuzzy rule set. The number of rules decreases, and each rule does not need all condition attributes values. Genetic algorithm is used to obtain the optimal discretization of continuous attributes. Then the fuzzy system is represented via an equivalent artificial neural network (ANN). The convergence of the ANN training is fast, and the structure size of the ANN becomes small.

Keywords

fuzzy neural nets; fuzzy set theory; fuzzy systems; genetic algorithms; rough set theory; ANN training; equivalent artificial neural network; genetic algorithms; neurofuzzy system; reductive fuzzy rule set; rough set theory; soft computing modeling approach; Artificial neural networks; Automation; Convergence; Data mining; Fuzzy logic; Fuzzy sets; Fuzzy systems; Genetic algorithms; Information systems; Set theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2003 International Conference on

Print_ISBN

0-7803-8131-9

Type

conf

DOI

10.1109/ICMLC.2003.1259658

Filename

1259658