Continuous optimization schemes for fuzzy classification

Author

Blekas, K. ; Papageorgiou, G. ; Stafylopatis, A.

Author_Institution

Dept. of Electr. Eng., Nat. Tech. Univ. of Athens, Greece

Volume

1

fYear

1997

fDate

2-4 Jul 1997

Firstpage

265

Abstract

Two approaches are developed, which are suitable for the optimization of a fuzzy classification scheme through the formation of appropriate space-filling clusters. The first approach is based on the analog Hopfield (1985) neural network, while the second one uses real-encoded genetic optimization. Experimental results concerning difficult classification problems show that both proposed approaches are very successful in generating fuzzy partitions and outperform other known algorithms in terms of the correct placement of patterns into partitions

Keywords

Hopfield neural nets; fuzzy neural nets; genetic algorithms; pattern classification; algorithms; analog Hopfield neural network; classification problem; continuous optimization; experimental results; fuzzy classification; fuzzy partitions; pattern classification; pattern placement; real-encoded genetic optimization; space-filling clusters; Clustering algorithms; Fuzzy sets; Fuzzy systems; Genetic algorithms; Hopfield neural networks; Intelligent systems; Partitioning algorithms; Pattern classification; Pattern clustering; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on

Conference_Location

Santorini

Print_ISBN

0-7803-4137-6

Type

conf

DOI

10.1109/ICDSP.1997.628057

Filename

628057