Title: A correlation based stochastic partitional algorithm for accurate cluster analysis

Authors: Satyasai Jagannath Nanda; Pyari Mohan Pradhan; Ganapati Panda; Lalu Mansinha; Kristy F. Tiampo

Addresses: School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar 751013, Orissa, India ' School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar 751013, Orissa, India ' School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Bhubaneswar 751013, Orissa, India ' Department of Earth Sciences, The University of Western Ontario, London N6A 5B7, Ontario, Canada ' Department of Earth Sciences, The University of Western Ontario, London N6A 5B7, Ontario, Canada

Abstract: Most partitional clustering algorithms such as K-means, K-nearest neighbour, evolutionary techniques use distance based similarity measures to group the patterns of a data set. However the distance based algorithms may converge to local optima when there are large variations in the attributes of the data set, leading to improper clustering. In this paper we propose a simple stochastic partitional clustering algorithm based on a Pearson correlation based similarity measure. Experiments on real-life data sets demonstrate that the proposed method provides superior performance compared to distance based K-means algorithm.

Keywords: K-means clustering; correlation clustering; clustering accuracy; clustering stability; cluster analysis; stochastic partitional clustering; Pearson correlation; similarity measures.

DOI: 10.1504/IJSISE.2013.051504

International Journal of Signal and Imaging Systems Engineering, 2013 Vol.6 No.1, pp.52 - 58

Received: 05 Feb 2011
Accepted: 11 Apr 2011

Published online: 20 Jan 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article