A NEAR-OPTIMAL INITIAL SEED VALUE SELECTION IN K-MEANS ALGORITHM USING A GENETIC ALGORITHM

Authors
BABU GP MURTY MN
Citation
Gp. Babu et Mn. Murty, A NEAR-OPTIMAL INITIAL SEED VALUE SELECTION IN K-MEANS ALGORITHM USING A GENETIC ALGORITHM, Pattern recognition letters, 14(10), 1993, pp. 763-769
Citations number
8
Categorie Soggetti
Computer Sciences, Special Topics","Computer Applications & Cybernetics
Journal title
Pattern recognition letters → ACNP
ISSN journal
01678655
Volume
14
Issue
10
Year of publication
1993
Pages
763 - 769
Database
ISI
SICI code
0167-8655(1993)14:10<763:ANISVS>2.0.ZU;2-I
Abstract
The K-means algorithm for clustering is very much dependent on the ini tial seed values. We use a genetic al to find a near-optimal partition ing of the given data set by selecting proper initial seed values in t he K-means algorithm. Results obtained are very encouraging and in mos t of the cases, on data sets having well separated clusters, the propo sed scheme reached a global minimum.