An Enhanced ART2 Neural Network for Clustering Analysis

Author

Luo, Jianhong ; Chen, Dezhao

Author_Institution

Zhejiang Univ., Hangzhou

fYear

2008

fDate

23-24 Jan. 2008

Firstpage

81

Lastpage

85

Abstract

The adaptive resonance theory 2 (ART2) neural network exhibits several properties which can be useful in the data mining and which are lacking in most other neural networks. But ART2 has deficiencies that the categories clustered by ART2 are very mutable to slight changes in training conditions. An improved ART2 with enhanced triplex matching mechanism, named as ETM-ART2, is presented to redress the deficiencies. Several tests results show that ETM-ART2 performs better than classic ART2 when applied to clustering tasks. It is an effective improved algorithm and can be applied to a wide variety of problems.

Keywords

ART neural nets; data mining; pattern clustering; pattern matching; ETM-ART2; adaptive resonance theory; clustering analysis; data mining; enhanced ART2 neural network; enhanced triplex matching mechanism; Artificial neural networks; Clustering algorithms; Data mining; Information analysis; Neural networks; Pattern matching; Pattern recognition; Performance evaluation; Resonance; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge Discovery and Data Mining, 2008. WKDD 2008. First International Workshop on

Conference_Location

Adelaide, SA

Print_ISBN

978-0-7695-3090-1

Type

conf

DOI

10.1109/WKDD.2008.117

Filename

4470354