Chapter

Distributed Computing and Internet Technology

Volume 3816 of the series Lecture Notes in Computer Science pp 523-535

An Approach to Find Embedded Clusters Using Density Based Techniques

  • S. RoyAffiliated withDept of Computer Science & Information Technology, Tezpur University, Napaam 784 028, Assam
  • , D. K. BhattacharyyaAffiliated withDept of Computer Science & Information Technology, Tezpur University, Napaam 784 028, Assam

* Final gross prices may vary according to local VAT.

Get Access

Abstract

This paper presents an efficient clustering technique which can identify any embedded and nested cluster over any variable density space. The proposed algorithm is basically an enhanced version of DBSCAN [4] and OPTICS [7]. Experimental results are reported to establish that the proposed clustering technique outperforms both DBSCAN and OPTICS in terms of complex cluster detection.

Keywords: Variable density, embedded cluster, core-distance, cluster, core neighborhood, unsupervised.