Atlantis Press Paper Details: Reduct Driven Pattern Extraction from Clusters

Clustering algorithms give general description of clusters, listing number of clusters and member entities in those clusters. However, these algorithms lack in generating cluster description in the form of pattern. From data mining perspective, pattern learning from clusters is as important as cluster finding. In the proposed approach, reduct derived from rough set theory is employed for pattern formulation. Further, reduct are the set of attributes which distinguishes the entities in a homogenous cluster, hence these can be clear cut removed from the same. Remaining attributes are then ranked for their contribution in the cluster. Pattern is formulated with the conjunction of most contributing attributes such that pattern distinctively describes the cluster with minimum error.

		back to author index

title:		Reduct Driven Pattern Extraction from Clusters
publication:		IJCIS
volume-issue:		2 - 1
pages:		10 - 16
ISSN:		1875-6883
DOI:		doi:10.2991/jnmp.2009.2.1.2 (how to use a DOI)
author(s):		Shuchita Upadhyaya, Alka Arora, Rajni Jain
publication date:		March 2009
abstract:		Clustering algorithms give general description of clusters, listing number of clusters and member entities in those clusters. However, these algorithms lack in generating cluster description in the form of pattern. From data mining perspective, pattern learning from clusters is as important as cluster finding. In the proposed approach, reduct derived from rough set theory is employed for pattern formulation. Further, reduct are the set of attributes which distinguishes the entities in a homogenous cluster, hence these can be clear cut removed from the same. Remaining attributes are then ranked for their contribution in the cluster. Pattern is formulated with the conjunction of most contributing attributes such that pattern distinctively describes the cluster with minimum error.
copyright:		© Atlantis Press. This article is distributed under the terms of the Creative Commons Attribution License, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited.
full text:		ijcis-2_1art2.pdf (1160 K)