Coevolution of a Fuzzy Rule Base for Classification Problems

  • Authors:
  • Barbara Fusińska;Marek Kisiel-Dorohinicki;Edward Nawarecki

  • Affiliations:
  • Department of Computer Science, AGH University of Science and Technology, Kraków, Poland;Department of Computer Science, AGH University of Science and Technology, Kraków, Poland;Department of Computer Science, AGH University of Science and Technology, Kraków, Poland

  • Venue:
  • RSEISP '07 Proceedings of the international conference on Rough Sets and Intelligent Systems Paradigms
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

In the paper a certain class of classification systems based on hybrid fuzzy-genetic approach is considered. The particular solution proposed allows for coevolution of two different populations, that search for a rule base structure and linguistic variables definitions respectively. The search is organised according to the principles of evolutionary multi-agent systems, which results in high generalisation capabilities of the system, as illustrated by the preliminary experimental results.