Multi-variables singular value based rule interpolation
Péter Bárányi, Y. Yam, László Tamás Kóczy · 2002
Fuzzy interpolative techniques have emerged as a new topic of fuzzy theories. The main advantage of fuzzy rule interpolation is that, unlike classical methods, it can function with a sparse rule base, thereby increasing the applicability of fuzzy reasoning. A major difficulty of fuzzy reasoning is that the size of the rule base increases exponentially with the number of variables or the number of fuzzy terms, and hence also the inference/control time. Interpolative reasoning can help to reduce the number of rules using a sparse rule base, but does not eliminate the problem of exponentially growing. Singular value based rule base reduction (FuzzySVD) methods have been published to various conventional methods. The interpolation technique specialized for full rule base combines the advantageous of fuzzy rule interpolation and classical methods. This paper introduces the extension of the FuzzySVD method to the specialized fuzzy rule interpolation method to achieve more significant reduction. This method is an extension of the two variables method to multi variables.