
	Information Technology Journal
	Year: 2012 \| Volume: 11 \| Issue: 10 \| Page No.: 1409-1417 DOI: 10.3923/itj.2012.1409.1417

A Fast Evolutionary Algorithm for Automatic Evolution of Clusters

Singh Vijendra, K. Ashiwini and Sahoo Laxman

Abstract: This paper proposed an evolutionary clustering algorithm which can automatically determine the number of clusters present in a data set. The chromosomes are represented as strings of real numbers, encode the centers of a fixed number of clusters. The searching capability of evolutionary clustering is exploited in order to search for appropriate cluster centers in the feature space such that a similarity metric of the resulting clusters is optimized. The proposed clustering approach called Fast Automatic Clustering Evolution (FACE) in data set. To obtain a speedup over linear search in high dimensional data a randomized k-d trees based nearest neighbor search is used. The chromosomes are able to exchange their gene values according to nearest cluster centers and relation among genes in crossover operator. Mutation operator replaced the mutation gene value with respect to nearest neighbor cluster. Adaptive probabilities of crossover and mutation are employed to prevent the convergence of the GA (Genetic Algorithm) to a local optimum. The Adjusted-Rand Index is used as a measure of the validity of the clusters. Effectiveness of the proposed algorithm is demonstrated for both artificial and real-life data sets. The experimental result demonstrates that the proposed clustering algorithm (FACE) has high performance, effectiveness and flexibility. The proposed evolutionary algorithm is able for clustering low to high dimensional data set.

PDF Fulltext XML References Citation Report Citation

RELATED ARTICLES:

•	A Novel Custom Topology Generation for Application Specific Network-on-chip Using Genetic Algorithm Optimization Technique

•	Cluster Analysis of Rainfall-Runoff Training Patterns to Flow Modeling Using Hybrid RBF Networks

•	Integrated Approach of Reduct and Clustering for Mining Patterns from Clusters

•	Variations of k-mean Algorithm: A Study for High-Dimensional Large Data Sets

•	A Semaphore Based Multiprocessing k-Mean Algorithm for Massive Biological Data

How to cite this article:

Singh Vijendra, K. Ashiwini and Sahoo Laxman, 2012. A Fast Evolutionary Algorithm for Automatic Evolution of Clusters. Information Technology Journal, 11: 1409-1417.

DOI: 10.3923/itj.2012.1409.1417

URL: https://scialert.net/abstract/?doi=itj.2012.1409.1417

COMMENT ON THIS PAPER

Navigation


		Online First
		Current Issue
		Previous Issues
		Editorial Board
		Submit a Manuscript
		Guide to Authors
		Subscribe to E-alerts

Indexed In


		ASCI-Database
		Asian Digital Library
		Google Scholar

Science Alert