Multicriteria Relational Clustering: The Case of Binary Outranking Matrices

  • Yves De Smet
  • Stefan Eppe
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5467)

Abstract

In this paper we address the question of multicriteria relational clustering. We develop a method that builds clusters and relations between these clusters on the basis of a binary outranking matrix. An extension of the k-means algorithm is presented and tested on artificial data sets. Finally, an example about the clustering of journals from the field of “Operations Research and Management Science” is illustrated.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cailloux, O., Lamboray, C., Nemery, P.: A taxonomy of clustering procedures. In: Proceedings of the 66th Meeting of the EWG on MCDA, Marrakech, Maroc (2007)Google Scholar
  2. 2.
    De Smet, Y., Montano Guzmán, L.: Towards multicriteria clustering: An extension of the k-means algorithm. European Journal of Operational Research 158, 390–398 (2004)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Nemery, P., Lamboray, C.: FlowSort: a flow-based sorting method with limiting and central profiles. TOP (Journal of the Spanish Society of Statistics and Operations Research) (to appear)Google Scholar
  4. 4.
    Vincke, P.: Multicriteria Decision-aid. John Wiley & Sons Ltd., Chichester (1992)MATHGoogle Scholar
  5. 5.
    Yu, W.: Aide multicritère à la décision dans le cadre de la probl’ematique du tri: m’ethodes et applications, PhD thesis, LAMSADE, Universit’e Paris Dauphine, Paris (1992)Google Scholar
  6. 6.
    Zopounidis, C., Doumpos, M.: Multicriteria classification and sorting methods. A literature review. European Journal of Operational Research 138, 229–246 (2002)CrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Yves De Smet
    • 1
  • Stefan Eppe
    • 1
  1. 1.CoDE – SMGUniversité Libre de BruxellesBrusselsBelgium

Personalised recommendations