Modified SDSA clustering algorithm

An effective clustering algorithm, named SDSA algorithm, is developed recently by Wei Li, Haohao Li and Jianye Chen. The algorithm based on the concept of the short distance of the consecutive points and the small angle between the consecutive vectors formed by three adjacent points. In this paper, we present a modification of the newly developed SDSA algorithm (MSDS). The MSDS algorithm is suitable for almost all test data sets used by Chung and Liu for point symmetry based K-means (PSK) algorithm and SDSA algorithm. Also, its much more effective than SDSA algorithm, since the computational effort per iteration required by MSDS algorithm is a lot less than that required by SDSA algorithm. Experimental results demonstrate that our proposed MSDS algorithm is rather encouraging.