 |
    |
Generating Compact Rough Cluster Descriptions Using an Evolutionary Algorithm
Kevin Vogts1 and Nigel Pope2
1School of Management, University of Canterbury, Christchurch, New Zealand
Kevin.Voges@canterbury.ac.nz
2School of Marketing, Griffith University, Nathan Campus, Brisbane, Australia
N.Pope@griffith.edu.au
Abstract. Cluster analysis is a technique used to group objects into clusters such that similar objects are grouped together in the same cluster. Early methods were derived from multivariate statistics. Some newer methods are based on rough sets, introduced by Pawlak [3], [4]. An extension of rough sets to rough clusters was introduced in [5]. The lower approximation (LA) of a rough cluster contains objects that only belong to that cluster, and the upper approximation (UA) contains objects that may belong to more than one cluster. An EA can be used to find a set of lower approximations of rough clusters that provide the most comprehensive coverage of the data set with the minimum number of clusters.
LNCS 3103, p. 1332 f.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004