• Jan 21, 2020 News! Vol.11, No.1- Vol.11, No.3 has been indexed by EI(Inspec)!   [Click]
  • Nov 12, 2020 News!Vol.12, No. 4 has been published with online version.   [Click]
  • Feb 08, 2017 News!Welcome Assoc. Prof. Lei Chen from China to join the Editorial board of IJET.   [Click]
General Information
    • ISSN: 1793-8236 (Online)
    • Abbreviated Title Int. J. Eng. Technol.
    • Frequency:  Quarterly 
    • DOI: 10.7763/IJET
    • Executive Editor: Ms.Yoyo Y. Zhou
    • Abstracting/ Indexing: Chemical Abstracts Services (CAS) EBSCO, Google Scholar, Ulrich Periodicals Directory, Crossref, ProQuest, Index CopernicusEI (INSPEC, IET).
    • E-mail: ijet@vip.163.com
Prof. T. Hikmet Karakoc
Anadolu University, Faculty of Aeronautics and Astronautics, Turkey

IJET 2011 Vol.3(3): 297-303 ISSN: 1793-8236
DOI: 10.7763/IJET.2011.V3.241

DOFCM: A Robust Clustering Technique Based upon Density

Kaur Prabhjot, Lamba I. M. S, and Gosain Anjana

Abstract—Robust clustering methods reduce the impact of outliers on cluster centroids. Definition of outlier depends on the data structure and applied detection methods. Noise Clustering (NC) is a robust technique, which defines outlier in terms of a distance, called noise distance. NC identifies outliers during clustering process and modifies various parameters, required for creating clusters, thus effecting clustering output. Its main motive is to reduce the influence of outliers on cluster centroids rather than identifying it hence could not result into original clusters. However, in many applications, identification of outliers is important, as they may contain important information. Density Oriented Fuzzy C - Means (DOFCM) is a robust technique, which identifies outlier before clustering, on the basis of density of data-set. According to DOFCM, outliers are defined as the points that are not in the dense part of the data-set. In this paper, we have compared both the techniques for outlier identification and clustering. The results obtained through comparison, by implementing various tests, concluded that DOFCM based upon density approach identifies outliers very well and gives efficient clustering results than NC technique which identify outliers based upon distance.

Index Terms—Data mining, Density-Oriented approach, Fuzzy clustering, Outlier identification, Robust clustering.

Prabhjot Kaur is with the Department of Information Technology at Maharaja Surajmal Institute of Technology , C-4, Janakpuri, New Delhi,110058, India (Phone: +919810665064, +919810165064; E-mail:thisisprabhjot@gmail.com). IEEE member ID- 90526150
Anjana Gosain is with the Department of Information Technology, University School of Information Technology, Guru Gobind SinghIndraprastha University, New Delhi, India (Phone: +919811055716, Email: anjana_gosain@hotmail.com).
I. M. S. Lamba is with the Department of Computer Science, Shardha University, Greater Noida, U. P., India (Phone: +919810326870, Email: ims.lamba@sharda.ac.in ).


Cite: Kaur Prabhjot, Lamba I. M. S, and Gosain Anjana, "DOFCM: A Robust Clustering Technique Based upon Density," International Journal of Engineering and Technology vol. 3, no. 3, pp. 297-303, 2011.

Copyright © 2008-2021. International Journal of Engineering and Technology. All rights reserved. 
E-mail: ijet@vip.163.com