Selection from Overlapping Classifications

  • F. Gebhardt
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


Semantic classification utilizes structural and semantical properties of data rather than purely their numerical values for constructing classes of objects. In the process of semantic interpretation of data sets, we arrive in our project EXPLORA at a collection of possible descriptions of a given goal set. We propose here a procedure for selecting certain classes from this collection. The procedure chooses them by means of their quality and of a kind of similarity, usually unsymmetric, which we call affinity. The idea is to suppress a class if it is sufficiently similar to, but also inferior to an other class that is itself retained. Some examples illustrate the method and its effect on the results.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Diday, Edwin (1989): atIntroduction à l’analyse des données symboliques. Le Chesnay: INRTA, 1989 (Rapports de Recherche 1074).-38 pp.Google Scholar
  2. Gebhardt, Friedrich (1988): On the usefulness of expert systems in exploratory data analysis. In: Data analysis and informatics, V: proc. of the 5th International Symposium (Versailles, Sept. 1987) /E. Diday (ed.). Amsterdam: North-Holland, 1988, 183–188.Google Scholar
  3. Gebhardt, Friedrich (1989): Choosing among competing generalizations. Sankt Augustin: GMD, 1989 (Arbeitspapiere der GMD, 421).-16 pp.-Preprint, to be published elsewhere.Google Scholar
  4. Gebhardt, Friedrich (1990): Explanatory data analysis using data semantics. In: DEXA 90: proc. (Wien, Aug. 1990) / A Min Tjoa (ed.). Wien: Springer, 1990.-In print.Google Scholar
  5. Hoschka, Peter; Klösgen, Willi (1990): A support system for interpreting statistical data. In: Knowledge discovery in databases / G. Piatetsky-Shapiro (ed.); W. Frawley (ed.). Cambridge, Mass.: MIT-Press, 1990.-In preparation.Google Scholar
  6. Stepp, Robert E. (1987): Concepts in conceptual clustering. In: Tenth International Joint Conference on Artificial Intelligence: proc. (Milano, Aug. 1987) / J. McDermott (ed.). Los Angeles: Morgan Kaufmann, 1987, 211–213.Google Scholar

Copyright information

© Springer-Verlag Berlin · Heidelberg 1991

Authors and Affiliations

  • F. Gebhardt
    • 1
  1. 1.Gesellschaft für Mathematik und Datenverarbeitung mbHInstitut für Angewandte Informationstechnik Schloß BirlinghovenSankt Augustin 1Germany

Personalised recommendations