ABK-means: an algorithm for data clustering using ABC and K-means algorithm
by M. Krishnamoorthi; A.M. Natarajan
International Journal of Computational Science and Engineering (IJCSE), Vol. 8, No. 4, 2013

Abstract: Data clustering has become one of the promising areas in data mining field. The algorithms, such as K-means and FCM are traditionally used for clustering purpose. Recently, most of the research studies have concentrated on optimisation of clustering process using different optimisation methods. The commonly used optimising algorithms such as particle swarm optimisation and genetic algorithms have given some significant contributions for optimising the clustering results. In this paper, we have proposed an approach to optimise the clustering process using artificial bee colony (ABC) algorithm with K-means operator. Here, we modify the traditional ABC algorithm with K-means operator. From the experimental results, we conclude that our proposed approach has upper hand over other methods. The comparative analysis of our approach with other algorithms using datasets such as iris, thyroid and wine is satisfactory. The proposed approach has achieved the intra-cluster distance values of 68.2, 9,682.4 and 12,234.4 for iris, thyroid and wine datasets respectively for the best cases.

Online publication date: Fri, 27-Dec-2013

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Science and Engineering (IJCSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com