Multiscale visual quality assessment for cluster analysis with self-organizing maps

Bernard, Jürgen; Landesberger, Tatiana von; Bremm, Sebastian; Schreck, Tobias

Multiscale visual quality assessment for cluster analysis with self-organizing maps

Dateien

Schreck_multiscale.pdfGröße: 10.56 MBDownloads: 724

Datum

2011

Autor:innen

Bernard, Jürgen

Landesberger, Tatiana von

Bremm, Sebastian

Schreck, Tobias

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

WONG, Pak Chung, ed. and others. Visualization and Data Analysis 2011. SPIE, 2011, pp. 78680N-78680N-12. SPIE Proceedings. 7868. Available under: doi: 10.1117/12.872545

Zusammenfassung

Cluster analysis is an important data mining technique for analyzing large amounts of data, reducing many objects to a limited number of clusters. Cluster visualization techniques aim at supporting the user in better understanding the characteristics and relationships among the found clusters. While promising approaches to visual cluster analysis already exist, these usually fall short of incorporating the quality of the obtained clustering results. However, due to the nature of the clustering process, quality plays an important aspect, as for most practical data sets, typically many di erent clusterings are possible. Being aware of clustering quality is important to judge the expressiveness of a given cluster visualization, or to adjust the clustering process with re ned parameters, among others. In this work, we present an encompassing suite of visual tools for quality assessment of an important visual
cluster algorithm, namely, the Self-Organizing Map (SOM) technique. We de ne, measure, and visualize the notion of SOM cluster quality along a hierarchy of cluster abstractions. The quality abstractions range from simple scalar-valued quality scores up to the structural comparison of a given SOM clustering with output of additional supportive clustering methods. The suite of methods allows the user to assess the SOM quality on the appropriate abstraction level, and arrive at improved clustering results. We implement our tools in an integrated system, apply it on experimental data sets, and show its applicability.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Visual Cluster Analysis, Self-Organizing Maps, Cluster Comparison, Quality Visualization and Assessment, Visual Analysis

Konferenz

IS&T/SPIE Electronic Imaging, San Francisco, California

Zitieren

ISO 690

BERNARD, Jürgen, Tatiana von LANDESBERGER, Sebastian BREMM, Tobias SCHRECK, 2011. Multiscale visual quality assessment for cluster analysis with self-organizing maps. IS&T/SPIE Electronic Imaging. San Francisco, California. In: WONG, Pak Chung, ed. and others. Visualization and Data Analysis 2011. SPIE, 2011, pp. 78680N-78680N-12. SPIE Proceedings. 7868. Available under: doi: 10.1117/12.872545

BibTex

@inproceedings{Bernard2011-01-24Multi-16618,
  year={2011},
  doi={10.1117/12.872545},
  title={Multiscale visual quality assessment for cluster analysis with self-organizing maps},
  number={7868},
  publisher={SPIE},
  series={SPIE Proceedings},
  booktitle={Visualization and Data Analysis 2011},
  pages={78680N--78680N-12},
  editor={Wong, Pak Chung},
  author={Bernard, Jürgen and Landesberger, Tatiana von and Bremm, Sebastian and Schreck, Tobias}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/16618">
    <dc:creator>Bremm, Sebastian</dc:creator>
    <dcterms:title>Multiscale visual quality assessment for cluster analysis with self-organizing maps</dcterms:title>
    <dc:rights>terms-of-use</dc:rights>
    <dc:language>eng</dc:language>
    <dc:contributor>Schreck, Tobias</dc:contributor>
    <dc:contributor>Bernard, Jürgen</dc:contributor>
    <dcterms:issued>2011-01-24</dcterms:issued>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dcterms:abstract xml:lang="eng">Cluster analysis is an important data mining technique for analyzing large amounts of data, reducing many objects to a limited number of clusters. Cluster visualization techniques aim at supporting the user in better understanding the characteristics and relationships among the found clusters. While promising approaches to visual cluster analysis already exist, these usually fall short of incorporating the quality of the obtained clustering results. However, due to the nature of the clustering process, quality plays an important aspect, as for most practical data sets, typically many di erent clusterings are possible. Being aware of clustering quality is important to judge the expressiveness of a given cluster visualization, or to adjust the clustering process with re ned parameters, among others. In this work, we present an encompassing suite of visual tools for quality assessment of an important visual&lt;br /&gt;cluster algorithm, namely, the Self-Organizing Map (SOM) technique. We de ne, measure, and visualize the notion of SOM cluster quality along a hierarchy of cluster abstractions. The quality abstractions range from simple scalar-valued quality scores up to the structural comparison of a given SOM clustering with output of additional supportive clustering methods. The suite of methods allows the user to assess the SOM quality on the appropriate abstraction level, and arrive at improved clustering results. We implement our tools in an integrated system, apply it on experimental data sets, and show its applicability.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Landesberger, Tatiana von</dc:contributor>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/16618"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2011-11-08T11:13:05Z</dc:date>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Schreck, Tobias</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2012-01-31T23:25:15Z</dcterms:available>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/16618/1/Schreck_multiscale.pdf"/>
    <dc:contributor>Bremm, Sebastian</dc:contributor>
    <dcterms:bibliographicCitation>First publ. in: Visualization and data analysis 2011 : 24 - 25 January 2011, California, United States ; [part of] IS&amp;T/SPIE electronic imaging, science and technology / sponsored and publ. by IS&amp;T - the Society for Imaging Science and Technology; SPIE. Pak Chung Wong ... (Eds.). - Bellingham, Wash. : SPIE [u.a.], 2011. - pp. 7868 0N. -  (Proceedings of SPIE ; 7868). - ISBN 978-0-8194-8405-5</dcterms:bibliographicCitation>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/16618/1/Schreck_multiscale.pdf"/>
    <dc:creator>Bernard, Jürgen</dc:creator>
    <dc:creator>Landesberger, Tatiana von</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja