Applying the Kohonen Self-Organizing Map Networks to Select Variables

  • Kamila Migdał Najman
  • Krzysztof Najman
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


The problem of selection of variables seems to be the key issue in classification of multi-dimensional objects. An optimal set of features should be made of only those variables, which are essential for the differentiation of studied objects. This selection may be made easier if a graphic analysis of an U-matrix is carried out. It allows to easily identify variables, which do not differentiate the studied objects. A graphic analysis may, however, not suffice to analyse data when an object is described with hundreds of variables. The authors of the paper propose a procedure which allows to eliminate variables with the smallest discriminating potential based on the measurement of concentration of objects on the Kohonen self organising map networks.


Group Structure Graphic Analysis Concentration Index Select Variable Silhouette Index 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. DEBOECK G., KOHONEN T. (1998), Visual explorations in finance with Self-Organizing Maps, Springer-Verlag, London.zbMATHGoogle Scholar
  2. GNANADESIKAN R., KETTENRING J.R., TSAO S.L. (1995), Weighting and selection of variables for cluster analysis, Journal of Classification, vol. 12, p. 113-136.zbMATHCrossRefGoogle Scholar
  3. GORDON A.D. (1999), Classification , Chapman and Hall / CRC, London, p.3 KOHONEN T. (1997), Self-Organizing Maps, Springer Series in Information Sciences, Springer-Verlag, Berlin Heidelberg.Google Scholar
  4. MILLIGAN G.W., COOPER M.C. (1985), An examination of procedures for determining the number of clusters in data set. Psychometrika, 50(2), p. 159-179.CrossRefGoogle Scholar
  5. MILLIGAN G.W. (1994), Issues in Applied Classification: Selection of Variables to Cluster, Classification Society of North America News Letter, November Issue 37.Google Scholar
  6. MILLIGAN G.W. (1996), Clustering validation: Results and implications for applied analy-ses. In Phipps Arabie, Lawrence Hubert & G. DeSoete (Eds.), Clustering and classifica-tion, River Edge, NJ: World Scientific, p. 341-375.Google Scholar
  7. MIGDAĐ NAJMAN K., NAJMAN K. (2003), Zastosowanie sieci neuronowej typu SOM w badaniu przestrzennego zróŻnicowania powiatów, Wiadomosci Statystyczne, 4/2003, p. 72-85.Google Scholar
  8. ROUSSEEUW P.J. (1987), Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, p. 53-65.zbMATHCrossRefGoogle Scholar
  9. VESANTO J. (1997), Data Mining Techniques Based on the Self Organizing Map, Thesis for the degree of Master of Science in Engineering, Helsinki University of Technology.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Kamila Migdał Najman
    • 1
  • Krzysztof Najman
    • 1
  1. 1.University of GdańskPoland

Personalised recommendations