Back to Search
Start Over
Reduct Driven Pattern Extraction from Clusters
- Source :
- International Journal of Computational Intelligence Systems; March 2009, Vol. 2 Issue: 1 p10-16, 7p
- Publication Year :
- 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.
Details
- Language :
- English
- ISSN :
- 18756891 and 18756883
- Volume :
- 2
- Issue :
- 1
- Database :
- Supplemental Index
- Journal :
- International Journal of Computational Intelligence Systems
- Publication Type :
- Periodical
- Accession number :
- ejs65126126
- Full Text :
- https://doi.org/10.2991/jnmp.2009.2.1.2