Dynamic estimation of number of clusters in data sets

Authors
Boudraa, AO
Citation
Ao. Boudraa, Dynamic estimation of number of clusters in data sets, ELECTR LETT, 35(19), 1999, pp. 1606-1608
Citations number
12
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
ELECTRONICS LETTERS
ISSN journal
00135194 → ACNP
Volume
35
Issue
19
Year of publication
1999
Pages
1606 - 1608
Database
ISI
SICI code
0013-5194(19990916)35:19<1606:DEONOC>2.0.ZU;2-1
Abstract
A new method for estimating during clustering the number of clusters in dat a sets is proposed. The cluster validity index, B-crit, takes the homogenei ty in each cluster into account and is connected to the geometrical propert ies of the data set. B-crit represents the combination of two validity indi ces. Comparisons between B-crit and six cluster validity indices, conducted on real data sets, are presented.