By Topic

A hybrid algorithm for k-medoid clustering of large data sets

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Weiguo Sheng ; Dept. of Inf. Syst. & Comput., Brunel Univ., London, UK ; Xiaohui Liu

In this paper, we propose a novel local search heuristic and then hybridize it with a genetic algorithm for k-medoid clustering of large data sets, which is an NP-hard optimization problem. The local search heuristic selects k-medoids from the data set and tries to efficiently minimize the total dissimilarity within each cluster. In order to deal with the local optimality, the local search heuristic is hybridized with a genetic algorithm and then the Hybrid K-medoid Algorithm (HKA) is proposed. Our experiments show that, compared with previous genetic algorithm based k-medoid clustering approaches - GCA and RARwGA, HKA can provide better clustering solutions and do so more efficiently. Experiments use two gene expression data sets, which may involve large noise components.

Published in:

Evolutionary Computation, 2004. CEC2004. Congress on  (Volume:1 )

Date of Conference:

19-23 June 2004