An extension to Rough c-means clustering based on decision-theoretic Rough Sets model

Abstract

Rough c-means algorithm has gained increasing attention in recent years. However, the assignment scheme of Rough c-means algorithm does not incorporate any information about the neighbors of the data point to be assigned and may cause undesirable solutions in practice. This paper proposes an extended Rough c-means clustering algorithm based on the concepts of decision-theoretic Rough Sets model. In the risk calculation, a new kind of loss function is utilized to capture the loss information of the neighbors. The assignment scheme of the present multi-category decision-theoretic Rough Sets model is also adjusted to deal with the potentially high computational cost. Experimental results are provided to validate the effectiveness of the proposed approach.