Local Modelling in Classification on Different Feature Subspaces

  • Gero Szepannek
  • Claus Weihs
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4065)


Sometimes one may be confronted with classification problems where classes are constituted of several subclasses that possess different distributions and therefore destroy accurate models of the entire classes as one similar group. An issue is modelling via local models of several subclasses.

In this paper, a method is presented of how to handle such classification problems where the subclasses are furthermore characterized by different subsets of the variables. Situations are outlined and tested where such local models in different variable subspaces dramatically improve the classification error.


Variable Selection Linear Discriminant Analysis Local Modelling Average Error Rate Local Posterior 
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. 1.
    Bishop, Y., Fienberg, S., Holland, P.: Discrete multivariate analysis. MIT Press, Cambridge (1975)MATHGoogle Scholar
  2. 2.
    Bradley, R., Terry, M.: The rank analysis of incomplete block designs, i. the method of paired comparisons. Biometrics, 324–345 (1952)Google Scholar
  3. 3.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and regression trees. Wadsworth Publishing Co. Inc. (1984)Google Scholar
  4. 4.
    Dietterich, T., Bakiri, G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. Journal of Artificial Intelligence Research 2, 263–286 (1995)MATHGoogle Scholar
  5. 5.
    Hajek, J.: A course in nonparametric statistics. Holden Day, San Francisco (1969)MATHGoogle Scholar
  6. 6.
    Hastie, T., Tibshirani, R.: Classification by Pairwise Coupling. Annals of Statistics 26(1), 451–471 (1998)MATHMathSciNetGoogle Scholar
  7. 7.
    Szepannek, G., Ligges, U., Luebke, K., Raabe, N., Weihs, C.: Local Models in Register Classification by Timbre. Technical Report 47/2005, SFB 475, Fachbereich Statistik, Universität DortmundGoogle Scholar
  8. 8.
    Szepannek, G., Weihs, C.: Variable Selection for Discrimination of more than two Classes where Data are Sparse. In: Spiliopoulou, M., Kruse, R., Nürnberger, A., Borgelt, C., Gaul, W. (eds.) From Data and Information Analysis to Knowledge Engineering, pp. 700–707. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  9. 9.
    Weihs, C., Ligges, U.: Voice Prints as a Tool for Automatic Classification of Vocal Performance. In: Kopiez, R., Lehmann, A., Wolther, I., Wolf, C. (eds.) Proceedings of the 5th Triennial ESCOM Conference. Hannover University of Music and Drama, Germany, September 8-13, pp. 332–335 (2003)Google Scholar
  10. 10.
    Weihs, C., Ligges, U., Luebke, K., Raabe, N.: klaR Analyzing German Business Cycles. In: Baier, D., Becker, R., Schmidt-Thieme, L. (eds.) Data Analysis and Decision Support, pp. 335–343. Springer, Berlin (2005)CrossRefGoogle Scholar
  11. 11.
    Wu, T.-F., Lin, C.-J., Weng, R.: Probability Estimates for Multi-class Classification by Pairwise Coupling. Journal of Machine Learning Research 5, 975–1005 (2004)MathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gero Szepannek
    • 1
  • Claus Weihs
    • 1
  1. 1.Department of StatisticsUniversity of DortmundDortmund

Personalised recommendations