퍼지 신경 회로망을 이용한 패턴 분류기의 설계

Design of the Pattern Classifier using Fuzzy Neural Network

  • 김문환 (연세대학교 전기전자공학과) ;
  • 이호재 (연세대학교 전기전자공학과) ;
  • 주영훈 (군산대학교 전자정보공학부) ;
  • 박진배 (연세대학교 전기전자공학과)
  • Kim, Moon-Hwan (Dept. of Electrical and Electronic Eng., Yonsei Univ.) ;
  • Lee, Ho-Jae (Dept. of Electrical and Electronic Eng., Yonsei Univ.) ;
  • Joo, Young-Hoon (School of Electronic and Information Eng., Kunsan National Univ.) ;
  • Park, Jin-Bae (Dept. of Electrical and Electronic Eng., Yonsei Univ.)
  • 발행 : 2003.07.21

초록

In this paper, we discuss a fuzzy neural network classifier with immune algorithm. The fuzzy neural network classifier is constructed with the fuzzy classifier and the neural network classifier based on fuzzy rules. To maximize performance of classifier, the immune algorithm and the back propagation algorithm are used. For the generalized classification ability, the simulation results from the iris data demonstrate superiority of the proposed classifier in comparison with other classifier.

키워드