A new fuzzy approach for pattern recognition with application to EMG classification

Author

Yong-Sheng Yuag ; Lam, F.K. ; Chan, Francis H Y ; Zhang, Yuan-ting ; Parker, Philip A.

Author_Institution

Dept. of Electr. & Electron. Eng., Hong Kong Univ., Hong Kong

Volume

2

fYear

1996

fDate

3-6 Jun 1996

Firstpage

1109

Abstract

A fuzzy logic system with center average defuzzifier, product-inference rule, nonsingleton fuzzifier and Gauss membership function is discussed. The fuzzy sets are initially defined by the cluster parameters from the Basic ISO-DATA algorithm on input space. The system is then trained via back error propagation algorithm so that the fuzzy sets are fine-tuned. The system is applied to functional EMG classification and compared with its ANN counterpart. It is superior to the latter in at least three points: higher recognition rate; insensitive to over-training; and more consistent outputs thus having higher reliability

Keywords

electromyography; fuzzy logic; fuzzy set theory; pattern classification; Basic ISO-DATA algorithm; EMG classification; Gauss membership function; back error propagation algorithm; center average defuzzifier; fuzzy logic system; fuzzy sets; nonsingleton fuzzifier; over-training insensitivity; pattern recognition; product-inference rule; recognition rate; Artificial neural networks; Clustering algorithms; Electromyography; Fuzzy logic; Fuzzy sets; Fuzzy systems; Gaussian processes; Neural networks; Pattern recognition; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.549053

Filename

549053