Optimization in Nonhierarchic Clustering

  • Edwin Diday


Algorithms which are operationally efficient and which give a good partition of a finite set produce solutions that are not necessarily optimum. The main aim of this paper is a synthetic study of properties of optimality in spaces formed by partitions of a finite set. We formalize and take for a model a family of particularly efficient technique of “cluster center” type. The proposed algorithm operates on groups of points or “kernels”; these kernels adapt and evolve into interesting clusters. After developing the notion of “strong” and “weak” patterns and the computer aspects we illustrate the different results by an artificial example and by two applications, one in mineral geology, the other in medicine to determine biological profiles.


Global Optimum Weak Form Strong Form Profile Type Good Partition 
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.
    G. H. Ball,Classification Analysis, Technical Note, Stanford Research Institute, Menlo Park, California (1970).Google Scholar
  2. 2.
    M. Barbu,Partitions d’un ensemble fini : leur treillis Mathématiques et Sciences Humaines, No. 22(1968).Google Scholar
  3. 3.
    J. P. Benzecri,Algorithmes rapides d’agrégation, Sup. Class. No. 9, Laboratoire de Statistique Mathématique, Université de Paris (1971).Google Scholar
  4. 4.
    J. P. Benzecri,Représentation Euclidienne d’un ensemble muni de masses et de distances, Université de Paris (1970).Google Scholar
  5. 5.
    C. Berge,Théorie des graphes et ses applications, Dunod, Paris (1967).Google Scholar
  6. 6.
    L. N. Bolshev, Cluster Analysis,ISIRSS(1969).Google Scholar
  7. 7.
    R. E. Bonner, On Some Clustering Techniques,IBM J. Res. Develop 8, 22 (1964).CrossRefGoogle Scholar
  8. 8.
    R. M. Cormack, A Review of Classification,J. Roy. Stat. Soc., Ser. A,134, Part 3, 321 (1971).CrossRefGoogle Scholar
  9. 9.
    E. Diday, M.Bergontm, and J. Barre, Différentes notes sur la programmation de la Méthode des nuées dynamiques, Note IRIA (Rocquencourt, France) (1970–72).Google Scholar
  10. 10.
    E. Diday,Le méthode des nuées dynamiques et la reconnaissance des formes Cahiers IRIA( Rocquencourt, France ) (1970).Google Scholar
  11. 11.
    E. Diday, Une nouvelle méthode en classification automatique et reconnaissance des formes,Revue de Statistique Appl,XIX(2), 19 (1971).Google Scholar
  12. 12.
    L. Fisher and J. W. Van Ness, Admissible Clustering Procedures,Biometrika 58(1), 91 (1971).CrossRefGoogle Scholar
  13. 13.
    N. Freeman, Experiments in Discrimination and Classification,Pattern Recognition J.1(3), 207 (1969).CrossRefGoogle Scholar
  14. 14.
    D. J. Hall and G. H. Hall, Isodata, a Novel Method of Data Analysis and Pattern Classification, Technical Report, 5 R I Project 5533, Stanford Research Institute, Menlo Park, California (1965).Google Scholar
  15. 15.
    D. R. Hill, Mechanized Information Storage, Retrieval and Dissemination, inProc. FID/ IF IP Joint Conf Rome(1967).Google Scholar
  16. 16.
    S. C. Johnson, Hierarchical Clustering Schemes,Psychometrica 32, 241–45 (1967).CrossRefGoogle Scholar
  17. 17.
    H. Lerman,Les Bases de la Classification Automatique, Gauthiers-Villars (1970).Google Scholar
  18. 18.
    J. Picard,Utilisation des méthodes d’analyse de données dans l’étude de courbes expérimentales, Thesis, Laboratoire de Statistique Mathématique, Université de Paris (1972).Google Scholar
  19. 19.
    J. M. Romeder, Méthodes de discrimination, Thesis Statistique Mathématique, Faculté des Sciences de Paris (1969).Google Scholar
  20. 20.
    M. Roux,Un algorithme pour construire une hiérarchie particulière, Thesis, Laboratoire de Statistique Mathématique, Université de Paris (1968).Google Scholar
  21. 21.
    H. R. Ruspini, Numerical Methods for Fuzzy Clustering,Inf. Sci 2, 319–350 (1970).CrossRefGoogle Scholar
  22. 22.
    G. Sandor, P. Lenoir, and M. Kerbaol, Une étude en ordinateur des corrélations entre les modifications des protéines sériques en pathologie humaine,Compt. Rend 272, 331–334 (1971).Google Scholar
  23. 23.
    G. Sandor, E. Diday, Y. Lechevallier, and J. Barre, Une étude informatique des corrélations entre les modifications des protéines sériques en pathologie humaine,Compt. Rend 274, 464–467 (1972).Google Scholar
  24. 24.
    G. S. Sebestien, Automatic Off-Line Multivariate Data Analysis, inProc. Fall Joint Computer Conf. (1966), pp. 685–694.Google Scholar
  25. 25.
    R. R. Sokal and P. H. R. Sneath,Numerical Taxonomy, W. H. Freeman and Co., San Francisco and London (1963).Google Scholar
  26. 26.
    M. S. Watanabe, A Unified View of Clustering Algorithms, inIFIP Congress71, Ijubiana, Booklet TA-2.Google Scholar
  27. 27.
    L. A. Zadeh, Fuzzy Sets,Information and Control 8, 338–353 ( 1965 ).Google Scholar
  28. 28.
    J. I. Zahn, Graph Theoretical Methods for Detecting and Describing Gestalt Clusters,IEEE Trans. on Computers,C-20(l) 281 (1971).Google Scholar
  29. 29.
    J. Mcqueen, Some Methods for Classification and Analysis of Multivariate Observations, in5th Berkeley Symp. on Mathematics, Statistics and Probability, Vol. 1, No. 1, (1967), pp. 281–297.Google Scholar
  30. 30.
    E. Diday, The dynamic clusters method in nonpiarchical clustering,Int. Journ. of JJJ. and Inf. Sc 2(1) (1973).Google Scholar

Copyright information

© Plenum Press, New York 1974

Authors and Affiliations

  • Edwin Diday
    • 1
  1. 1.Laboratoire de Recherche en Informatique et Automatique Domaine de VoluceauRocquencourtFrance

Personalised recommendations