RBF-fuzzy system with GA based unsupervised/supervised learning method
Koji Shimojima, Toshio Fukuda, Yasuhisa Hasegawa · 2002
Fuzzy systems are used in many fields and places so far. In order to apply the fuzzy systems to the various fields and places, the tuning and optimizing method of the fuzzy system is the key issue. And the optimization of structure of fuzzy system (the number of membership function, the number of rules) is also very important to simplify the fuzzy systems. Some self-tuning methods have been proposed so far. However these conventional self-tuning methods do not have sufficient capability of learning. In this paper, we propose new unsupervised/supervised self-tuning fuzzy system, which consists of some membership functions expressed by the radial basis function with insensitive region. Learning are based on the genetic algorithms. The descent method is also utilized for tuning the shapes of membership function and consequent parts in case of supervised learning. The effectiveness of the proposed methods is shown by some numerical examples and simulations.>