Automatic Fuzzy Rule Generation by Simulating Human Knowledge Gathering Process

사람의 지식 축정과정 모사를 통한 자동 퍼지규칙의 생성

  • 정성훈 (전기 및 전자공학과 한국과학기술원)
  • Published : 1995.12.01

Abstract

Fuzzy rules, developed by experts thus far, may be often inconsistent and incomplete. This paper proposes a new methodology for automatic generation of fuzzy rules which are nearly complete and not inconsistent. This is accomplished by simulating a knowledge gathering process of humans from control experiences. This method is simpler and more efficient than existing ones. It is shown through simulation that our method even generates better rules than those generated by experts, under fine tuned parameters.

지금까지 전문가들에 의해 만들어진 퍼지규칙들은 종종 모순되었고 불완전하였다. 본 논문에서 우리는 모순되지 않고 거의 완전한 퍼지규칙을 자동생성 하는 새로운 기법을 제안한다. 이러한 퍼지규칙의 자동생성은 제어경험으로 부터 퍼지규칙을 얻어내는 사람의 지식 축적과정을 모사한 방법이다. 이 방식은 기존의 방식들보다 보다간단하면서도 보다 효율적인 방법이다. 잘 조절된 파라메터상에서 우리의 방식이 전문가들보다 더욱 좋은 퍼지규칙을 생성함을 시뮬레이션을 통하여 보인다.

Keywords

References

  1. Fizzy Control and Fuzzy Systems Witold Pedrycz
  2. 5th IFSA World Congress v.2 Design of Fuzzy Logic Controller with Inconsistent Rule Base Wonseek Yu;Zeungnam Bien
  3. IEEE Transactions on Computers-Special Issue on Artificial Neural Netwokrs v.40 no.12 Neural-network-based fuzzy logic control and decision system Chin-Teng Lin;C.S.George Lee
  4. IEEE Trans.on Neural Netwokrs v.3 no.5 Self-Learning Fuzzy Controllers Based on Temporal Back Propagation Jyh Shing R.Jang
  5. Proceedings of the International Conference on Fuzzy Logic Intelligent Control Based on Fuzzy Logic and Neural Net Theory Chuem Chien Lee
  6. IEEE Trans.on Computers v.40 no.12 Neural-Network-Based Fuzzy Logic Control and Decision System Chin Teng Lin;C.S.George Lee
  7. IEEE Trans. on Neural Netwokrs v.3 no.5 Learning and Tuning Fuzzy Logic Controllers Through Reinforcements Hamid R.Berenji;Pratap Khedkar
  8. Electronics Letters v.30 no.9 Defuzzification Method for Multishaped Output Fuzzy Sets Sung Hoon Jung;Kwang Hyun CHo