Partition based Clustering Algorithms: A Brief Study on the K-Means Algorithm & its Variants

Home
Copyright
Preface
Organizing Committee
International Advisory Board
About the Editor-in-Chief
Reviewers
Technical Papers
Author Index
Search
Help

doi:10.3850/978-981-08-7300-4_0816

Partition based Clustering Algorithms: A Brief Study on the K-Means Algorithm & its Variants

Mrinal Kanti Ghose and Samarjeet Borah

Department of Computer Science & Engineering, Sikkim Manipal Institute of Technology, Majitar, Rangpo, East Sikkim-737136.

ABSTRACT

Among all the categories of clustering algorithms partition based clustering algorithms more popularity among the researchers. K-means is a popular and well known partition based clustering method. It generally shows impressive results even in considerably large data sets. Its computational complexity does not suffer from the size of the data set. K-means has a number of variants on various application areas and efficiency improvement of the algorithm. In this paper a brief study has been conducted on the k-means algorithm and some of its widely used variants.

Keywords: Partition based, K-means, Clustering, Distance measure, Hierarchical, Complexity.

Back to TOC

FULL TEXT(PDF)