B-spline fuzzy systems faired by wavelet method and its applications

The B-spline fuzzy systems (B-FSs) are faired by using the quasi-uniform B-spline wavelet decomposition method to reduce adverse effects of the inaccurate data. First, the multi-resolution of B-FSs is transformed to the multiresolution of quasi-uniform B-splines; and then, the corresponding quasi-uniform B-splines are decomposed by using the quasi-uniform B-spline wavelet method to produce a series of fuzzy systems with gradually increasing fairness and gradually decreasing number of rules. Those fuzzy systems are called faired B-spline fuzzy systems by wavelet method. Simulation results show that fuzzy controllers constructed from faired B-FSs by wavelet method surpass in performances the fuzzy controllers by the original B-FSs, while consuming considerably less running time.