General interval type-2 Mamdani fuzzy systems are universal approximators
Author:
- 1 May 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Fuzzy systems using type-2 fuzzy sets and fuzzy logic are important and are indeed gaining increasing attention in the literature (e.g., type-2 fuzzy controllers and fuzzy models). A fundamental question is whether a type-2 fuzzy system is a universal approximator in that it is capable of uniformly approximating any real continuous function on a compact domain to any degree of accuracy. Up to date, no work addressing this issue can be found in the literature. In this paper, we constructively prove that a general class of Mamdani interval type-2 fuzzy systems is universal approximator. This result lays a theoretical foundation for the fuzzy systems development.Keywords
This publication has 30 references indexed in Scilit:
- Sufficient and necessary conditions for Boolean fuzzy systems as universal approximatorsInformation Sciences, 2008
- Mamdani fuzzy system: universal approximator to a class of random processesIEEE Transactions on Fuzzy Systems, 2002
- Analysis of approximation of continuous fuzzy functions by multivariate fuzzy polynomialsFuzzy Sets and Systems, 2002
- Analyses for Lp(μ)-norm approximation capability of generalized Mamdani fuzzy systemsInformation Sciences, 2001
- A note on smooth approximation capabilities of fuzzy systemsIEEE Transactions on Fuzzy Systems, 2001
- Interval type-2 fuzzy logic systems: theory and designIEEE Transactions on Fuzzy Systems, 2000
- Comparison of necessary conditions for typical Takagi-Sugeno and Mamdani fuzzy systems as universal approximatorsIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 1999
- Sufficient conditions on uniform approximation of multivariate functions by general Takagi-Sugeno fuzzy systems with linear rule consequentIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 1998
- Approximation accuracy analysis of fuzzy systems as function approximatorsIEEE Transactions on Fuzzy Systems, 1996
- Sufficient conditions on general fuzzy systems as function approximatorsAutomatica, 1994