An ant colony optimisation-based approach for clustering in a data matrix
by Chun-Hung Cheng; Angappa Gunasekaran; Kwan-Ho Woo
International Journal of Operational Research (IJOR), Vol. 19, No. 4, 2014

Abstract: Clustering is a process of classifying similar objects into different groups, such that the data within the same groups share the common features. As a common technique in statistical data analysis, it has been addressed in different contexts and by researchers in different disciplines. In this paper, we study the problem of clustering data into a diagonal block structure in a data matrix. This kind of clustering is very useful for analysing the interaction between the objects and their associated attributes in a dataset. In this work, we explore the use of ant colony optimisation-based approach to perform data clustering. Our approach offers several advantages. First, the objects and their attributes are re-arranged in the matrix such that a diagonal block structure is formed. This is useful for visual analysis. Second, our approach can deal with the case when the objects and attributes have weighting associated with them. Third, our approach is a non-parametric clustering method, (i.e., no explicit clustering criterion is required). Our computational study demonstrates the performance of our approach in data clustering.

Online publication date: Tue, 17-Jun-2014

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 Operational Research (IJOR):
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