ECMdd: Evidential c-medoids clustering with multiple prototypes

Kuang Zhou, Arnaud Martin, Quan Pan, Zhun-ga Liu

Abstract: Highlights•Extend medoid-based clustering algorithm on the framework of belief functions.•Introduce imprecise clusters which enable us to make soft decisions for uncertain data.•Use multiple weighted prototypes to capture various types of class structure.•Experimental results confirm the superiority of the proposed clustering algorithms.