INTERVAL TYPE-2 FUZZY KOHONEN CLUSTERING NETWORKS (KCN)

Abstract

In Fuzzy Kohonen Clustering Networks (FKCN) there is uncertainty associated with the fuzzifier parameter m that controls the amount of fuzziness. To design and manage uncertainty for fuzzifier m, an interval type-2 fuzzy approach to Fuzzy Kohonen Clustering Networks (FKCN) by using two fuzzifiers m1 and m2 is proposed, which create a foot of uncertainty (FOU) for the fuzzifier parameter m. Then, we incorporate this interval type-2 fuzzy set into FKCN to observe the effect of managing uncertainty from two fuzzifiers. Several experimental results are given to show the validity of proposed method and by doing so, the proposed algorithm also shows the ability to learn faster and obtain improved clustering results.