On designing of flexible neuro-fuzzy systems for nonlinear modelling

Authors:
Krzysztof Cpałka;Olga Rebrova;Robert Nowicki;Leszek Rutkowski
Affiliations:
Czestochowa University of Technology, Department of Computer Engineering, Poland and Academy of Management, SWSPiZ, Institute of Information Technology, Poland;The Russian State Medical University, Institute of Pharmaeconomics, Russia;Czestochowa University of Technology, Department of Computer Engineering, Poland and Academy of Management, SWSPiZ, Institute of Information Technology, Poland;Czestochowa University of Technology, Department of Computer Engineering, Poland and Academy of Management, SWSPiZ, Institute of Information Technology, Poland
Venue:
RSFDGrC'11 Proceedings of the 13th international conference on Rough sets, fuzzy sets, data mining and granular computing
Year:
2011

Citing 7
Cited 1

Evolutionary Computation

Evolutionary Computation
Computational Intelligence: Methods and Techniques

Computational Intelligence: Methods and Techniques
Introduction to Genetic Algorithms

Introduction to Genetic Algorithms
A new method for design and reduction of neuro-fuzzy classification systems

IEEE Transactions on Neural Networks
Evolutionary learning of mamdani-type neuro-fuzzy systems

ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
A robust design criterion for interpretable fuzzy models with uncertain data

IEEE Transactions on Fuzzy Systems
Flexible neuro-fuzzy systems

IEEE Transactions on Neural Networks

Statistical analysis of parametric t-norms

Information Sciences: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the paper the evolutionary strategy is used for learning of neuro-fuzzy structures of a Mamdani type applied to modelling of nonlinear systems. In the process of evolution we determine parameters of fuzzy membership functions, specific t-norm in a fuzzy inference, specific t-norm for aggregation of antecedents in each rule, and specific t-conorm describing an aggregation operator. The method is tested using well known approximation benchmarks.