|
Organizers |
Analysis of data clustering algorithm by various distance measures
by
Ashok Kumar. D
Department of Computer Science, Government Arts College, Udumalpet, Tamilnadu, INDIA.
Coauthors: THANGAVEL . K, Department of Mathematics, Gandhigram Rural Institute , Deemed University, Gandhigram, Tamilnadu, INDIA
The clustering problem has been widely studied since it arises in many knowledge management oriented applications. It aims at identifying the distribution of patterns and intrinsic correlations in data sets by partitioning the data points into similarity clusters. Traditional clustering algorithm use distance functions to measure similarity. Hence in this paper, we analyse various distace measures used to find similarity for finding better cluster. And we propose a similarity measure Combined Standard Deviation (CSD). The performance of proposed measure CSD is tested on synthetic data sets and it compare favorably to widely used similarity measures for data clustering problems.
Date received: May 26, 2005
Copyright © 2005 by the author(s). The author(s) of this document and the organizers of the conference have granted their consent to include this abstract in Atlas Conferences Inc. Document # caqt-15.