Conceptual K-Means Algorithm with Similarity Functions

  • I. O. Ayaquica-Martínez
  • J. F. Martínez-Trinidad
  • J. A. Carrasco-Ochoa
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3773)


The conceptual k-means algorithm consists of two steps. In the first step the clusters are obtained (aggregation step) and in the second one the concepts or properties for those clusters are generated (characterization step). We consider the conceptual k-means management of mixed, qualitative and quantitative, features is inappropriate. Therefore, in this paper, a new conceptual k-means algorithm using similarity functions is proposed. In the aggregation step we propose to use a different clustering strategy, which allows working in a more natural way with object descriptions in terms of quantitative and qualitative features. In addition, an improvement of the characterization step and a new quality measure for the generated concepts are presented. Some results obtained after applying both, the original and the modified algorithms on different databases are shown. Also, they are compared using the proposed quality measure.


Similarity Function Qualitative Feature Comparison Function Quantitative Feature Aggregation Step 
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.


  1. 1.
    Hanson, S.J.: Conceptual clustering and categorization: bridging the gap between induction and causal models. In: Kodratoff, Y., Michalski, R.S. (eds.) Machine Learning: an artificial intelligence approach, vol. 3, pp. 235–268. Morgan Kaufmann, Los Altos (1990)Google Scholar
  2. 2.
    Ralambondrainy, H.: A conceptual version of the K-means algorithm. Pattern Recognition Letters 16, 1147–1157 (1995)CrossRefGoogle Scholar
  3. 3.
    Ralambondrainy, H.: A clustering method for nominal data and mixture of numerical and nominal data. In: Proc. First Conf. Internat. Federation of Classification Societies, Aachen (1987)Google Scholar
  4. 4.
    García Serrano, J.R., Martínez-Trinidad, J.F.: Extension to k-means algorithm for the use of similarity functions. In: 3rd European Conference on Principles of Data Mining and Knowledge Discovery Proceedings, Prague, Czech. Republic, pp. 354–359 (1999)Google Scholar
  5. 5.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • I. O. Ayaquica-Martínez
    • 1
  • J. F. Martínez-Trinidad
    • 1
  • J. A. Carrasco-Ochoa
    • 1
  1. 1.Computer Science DepartmentNational Institute of Astrophysics, Optics and ElectronicsSanta María TonantzintlaMexico

Personalised recommendations