Fuzzy Clustering Based on Automated Feature Pattern-Driven Similarity Matrix Reduction

Abstract

Most of the medoid-based fuzzy clustering algorithms only use one similarity matrix to organize objects into groups. The similarity matrix is often constructed by equally employing all features which may ignore the contribution differences existing among the features. In this study, we also propose a medoid-based fuzzy clustering algorithm feature pattern-driven similarity matrices-reduction based fuzzy clustering (FP-SMR-FC) which is different from the existing ones in the following two aspects. First, multiple similarity matrices are constructed to represent the similarity between objects. Additionally, a feature pattern-driven Shannon entropy which combines nondeterminacy information contained in the similarity matrices and statistical information contained in the features together is used to learn the weight of each similarity matrix. Second, during the clustering processes of FP-SMR-FC, a new schema for eliminating some of the similarity matrices with very few contributions is developed for similarity matrices reduction. The comparison studies in terms of time complexity and clustering accuracy for FP-SMR-FC with various medoid-based clustering algorithms on real-life data sets are done. In addition, FP-SMR-FC is applied to head pose estimation of human behavior analysis. Comparisons, indeed, demonstrate the promising performance of FP-SMR-FC in practice.