Clustering of interval-valued symbolic patterns based on mutual similarity value and the concept of k-mutual nearest neighborhood

In this paper, a novel similarity measure for estimating the degree of similarity between two symbolic patterns, the features of which are of interval type is proposed. A method for clustering data patterns based on the mutual similarity value (MSV) and the concept of k-mutual nearest neighbourhood is explored. The concept of mutual nearest neighbourhood exploits the mutual closeness possessed by the patterns for clustering thereby providing the naturalistic proximity characteristics of the patterns. Experiments on various datasets have been conducted in order to study the efficacy of the proposed methodology