Fast neuro-fuzzy classifier

Author

Gorshkov, Ye V. ; Kokshenev, I.V. ; Rudnyeva, O.O.

Author_Institution

Artificial Intelligence Dept., Kharkiv Nat. Univ. of Radioelectronics, Ukraine

fYear

2003

fDate

20-22 March 2003

Firstpage

549

Lastpage

552

Abstract

The problem of data classification with the help of neuro-fuzzy and clustering techniques is considered. The architecture of a neuro-fuzzy classifier is proposed. It is characterized by the incorporation of possibilistic information into the consequents of classification rules. Such information can be helpful in the interpretation of classification results. Comparison with some known neuro-fuzzy classification schemes is given. Special emphasis is placed on the learning speed, which can be critical when the learning dataset is large. Experimental results confirm the correctness of the theoretical assumptions.

Keywords

fuzzy neural nets; learning (artificial intelligence); pattern classification; pattern clustering; classification rules; clustering techniques; data classification; fast neuro-fuzzy classifier; learning dataset; learning speed; neuro-fuzzy techniques; possibilistic information; Artificial intelligence; Control systems; Distortion measurement; Fuzzy control; Fuzzy neural networks; Fuzzy sets; Fuzzy systems; Medical diagnosis; Multidimensional systems; Noise measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on

Print_ISBN

0-7803-7579-3

Type

conf

DOI

10.1109/CNE.2003.1196885

Filename

1196885