Self-Tuning of the Fuzzy Inference Rule by Integrated Method

  • Authors:
  • Mal-Rey Lee;Huinam Rhee;Kyungdal Cho;Beon-Joon Cho

  • Affiliations:
  • Department of Multimedia Information &/ System, School of Multimedia, Yosu National University, San 96-1, Dunduckdong, Yosu, JunNam, 550-749, Korea/ e-mail: mrlee@info.yosu.ac.kr

  • Venue:
  • Journal of Intelligent and Robotic Systems
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the fuzzy reasoning model, the fuzzy relation matrix, determined by a human expert according to experience, plays an important role, but may be difficult to extract optimally from an expert, particularly as the system increases in complexity. Moreover, a change in the fuzzy membership function may alter the performance of the fuzzy system significantly. Therefore, in this paper, the genetic algorithm is to be incorporated in the context fuzzy reasoning model in the loop whose function is to search for optimal fuzzy relation matrix and fuzzy membership functions simultaneously. In addition, the genetic algorithm used in this paper is supplemented by a local fine-tuning mechanism with executing the gradient descent genetic operator.