Fuzzy clustering optimal k selection method based on multi-objective optimization

Because of the complexity data sets from real world, it is difficult to classify clearly and effectively, thus we prefer adopt fuzzy clustering approaches analyze sets. However, due variety algorithms, different number clusters will lead results. The closely related division, so how determine (k ) has become a problem. Until now, many researchers have proposed utilizing validity indexes deal with this kind effectiveness index can only be evaluated on basis algorithm FCM divide clusters. When range k value too large, FCM’s for values quite time-consuming. From perspective, paper proposes optimal selection method based multi-objective optimization (FMOEA-K). Different traditional methods, combines (MOEA), uses search appropriate cluster center concurrently. concurrency algorithm, calculation time shortened. experimental results show that compared method, FMOEA-K shorten improve accuracy calculating value.