An efficient centroid type-reduction strategy for general type-2 fuzzy logic system

In this paper, an efficient centroid type-reduction strategy for general type-2 fuzzy set is introduced. This strategy makes use of the result of α-plane representation, and performs the centroid type-reduction on each α-plane. Simulations show that it usually needs only several resolution of α value such that the defuzzified value converges to a real value. Consequently, comparing with the exhaustive computation approach, this approach can tremendously decrease the computation complexity from exponential into linear.