Skip to main navigation Skip to search Skip to main content

An Indicator for the Number of Clusters: Using a Linear Map to Simplex Structure

  • Zuse Institute Berlin
  • Max Planck Institute for Molecular Genetics

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Citations (Scopus)

Abstract

The problem of clustering data can be formulated as a graph partitioning problem. In this setting, spectral methods for obtaining optimal solutions have received a lot of attention recently. We describe Perron Cluster Cluster Analysis (PCCA) and establish a connection to spectral graph partitioning. We show that in our approach a clustering can be efficiently computed by mapping the eigenvector data onto a simplex. To deal with the prevalent problem of noisy and possibly overlapping data we introduce the Min-chi indicator which helps in confirming the existence of a partition of the data and in selecting the number of clusters with quite favorable performance. Furthermore, if no hard partition exists in the data, the Min-chi can guide in selecting the number of modes in a mixture model. We close with showing results on simulated data generated by a mixture of Gaussians.

Original languageEnglish
Title of host publicationFrom Data and Information Analysis to Knowledge Engineering - Proceedings of the 29th Annual Conference of the Gesellschaft für Klassifikation
EditorsMyra Spiliopoulou, Rudolf Kruse, Christian Borgelt, Andreas Nürnberger, Wolfgang Gaul
PublisherSpringer Science and Business Media Deutschland GmbH
Pages103-110
Number of pages8
ISBN (Print)9783540313137
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event29th Annual Conference of the German Classification Society - Gesellschaft fur Klassifikation, GfKl 2005 - Magdeburg, Germany
Duration: 9 Mar 200511 Mar 2005

Publication series

NameStudies in Classification, Data Analysis, and Knowledge Organization
ISSN (Print)1431-8814
ISSN (Electronic)2198-3321

Conference

Conference29th Annual Conference of the German Classification Society - Gesellschaft fur Klassifikation, GfKl 2005
Country/TerritoryGermany
CityMagdeburg
Period9/03/0511/03/05

Fingerprint

Dive into the research topics of 'An Indicator for the Number of Clusters: Using a Linear Map to Simplex Structure'. Together they form a unique fingerprint.

Cite this