An approach to measure the robustness of fuzzy reasoning: Research Articles

  • Authors:

  • Yongming Li;Dechao Li;Witold Pedrycz;Jingjie Wu

  • Affiliations:

  • Institute of Fuzzy Systems, College of Mathematics and Information Sciences, Shaanxi Normal University, Xi'an and Department of Computer Science and Technology, Tianjing University, Tianjing, 3000 ...;Institute of Fuzzy Systems, College of Mathematics and Information Sciences, Shaanxi Normal University, Xi'an, 710062, China;Department of Electrical and Computer Engineering, University of Alberta, Edmonton, T6G2V4, Canada and Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland;Institute of Fuzzy Systems, College of Mathematics and Information Sciences, Shaanxi Normal University, Xi'an, 710062, China

  • Venue:
  • International Journal of Intelligent Systems
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Fuzzy reasoning is intensively used in intelligent systems including fuzzy control, classification, expert systems, and networks to name a few dominant categories of such architectures. As being a fundamental construct permeating so many diverse areas, fuzzy reasoning was studied with respect to its fundamental properties such as robustness. The notion of robustness or sensitivity becomes of paramount importance by leading to a more comprehensive understanding of the way in which reasoning processes are developed. In this study, we introduce and study properties of some measures of robustness (or sensitivity) of fuzzy connectives and implication operators and discuss their relationships with perturbation properties of fuzzy sets. The results produced here are compared and contrasted with the previous findings available in the literature. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 393–413, 2005.