A kind of fuzzy genetic algorithm based on rule and its performance research

  • Authors:

  • Fachao Li;Shuxin Luo;Lianqing Su

  • Affiliations:

  • College of Economics and Management, Hebei University of Science and Technology, Shijiazhuang, P.R. China;College of Science, Hebei University of Science and Technology, Shijiazhuang, P.R. China;College of Science, Hebei University of Science and Technology, Shijiazhuang, P.R. China

  • Venue:
  • ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Ranking fuzzy information has been becoming the key issue in solving uncertainty optimization problems. Credibility being not embodied, it becomes powerless for both the order relation based on level cuts and the order relation determined by centralized quantification to play their key part in ranking fuzzy information under certain consciousness. In this paper, we introduce the concept of location values of fuzzy numbers with a rule pool and develop a new way to rank fuzzy numbers. We give the further descriptions of the location values by using coincidence degrees of fuzzy numbers with a rule pool. Composite quantifica-tion technique is used for processing fuzzy information. Moreover, we present a numerical model for computing location values and coincidence degrees. Furthermore, we propose a kind of fuzzy genetic algorithm based on rules, BR-FGA, by using the location values and coincidence degrees of fuzzy numbers with rules, and its performance is then considered with two illustrative examples.