Matching general type-2 fuzzy sets by comparing the vertical slices

In this paper, we propose a procedure for computing the dissimilarity measure of finite general type-2 fuzzy sets, represented as sequences of vertical slices. Through representing general type-2 fuzzy sets as a sequence of objects, we compute their overall dissimilarity value using suited matching algorithms for generalized sequences. The evaluation of the proposed matching algorithm is performed in the setting of classification, by defining datasets of general type-2 fuzzy sets conceived as labeled patterns. Experimental results show that the matching methodology is robust, accurate, and computationally acceptable.