A new fusion algorithm for fuzzy clustering

In this paper, the authors have considered the merging problem of two ellipsoidal clusters in order to construct a new fusion algorithm for fuzzy clustering. They have proposed a criterion for merging two ellipsoidal clusters π^sub 1^, π^sub 2^ with associated main Mahalanobis circles E^sub j^(c^sub...

Full description

Saved in:
Bibliographic Details
Published in:Croatian Operational Research Review 2014-01, Vol.5 (2), p.149-159
Main Authors: Vidović, Ivan, Bajer, Dražen, Scitovski, Rudolf
Format: Article
Language:English
Subjects:
Algorithms
cluster merging
Clustering
Davies-Bouldin index
fusion algorithm
fuzzy clustering
Mahalanobis clustering
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, the authors have considered the merging problem of two ellipsoidal clusters in order to construct a new fusion algorithm for fuzzy clustering. They have proposed a criterion for merging two ellipsoidal clusters π^sub 1^, π^sub 2^ with associated main Mahalanobis circles E^sub j^(c^sub j^, σ^sub j^), where c^sub j^ is the centroid and ... is the Mahalanobis variance of cluster π^sub j^. Based on the well-known Davies-Bouldin index, they have constructed a new fusion algorithm. The criterion has been tested on several data sets, and the performance of the fusion algorithm has been demonstrated on an illustrative example. (ProQuest: ... denotes formulae/symbols omitted.)
ISSN:1848-0225
1848-9931
DOI:10.17535/crorr.2014.0004