Advertisement

Concept Extensions and Weak Clusters Associated with Multiway Dissimilarity Measures

  • Jean Diatta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2961)

Abstract

We consider contexts with a finite set of entities described in a poset. When entity descriptions belong to a meet-semilattice, we show that nonempty extensions of concepts assigned to such a context coincide with weak clusters associated with pairwise or multiway dissimilarity measures satisfying some compatibility condition. Moreover, by duality principle, when entity descriptions belong to a join-semilattice, a similar result holds for so-called dual concepts of the given context.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Brito, P.: Order structure of symbolic assertion objects. IEEE Transactions on Knowledge and Data Engineering 6, 830–835 (1994)CrossRefGoogle Scholar
  2. 2.
    Polaillon, G.: Interpretation and reduction of Galois lattices of complex data. In: Rizzi, A., Vichi, M., Bock, H.H. (eds.) Advances in Data Science and Classification, Springer-Verlag, pp. 433–440. Springer, Heidelberg (1998)Google Scholar
  3. 3.
    Liquiere, M., Sallantin, J.: Structural machine learning with Galois lattice and graphs. In: Proc. 5th Int. Conf. Machine Learning ICML 1998, pp. 305–313. Morgan Kaufman, San Francisco (1998)Google Scholar
  4. 4.
    Ganter, B., Kuznetsov, S.O.: Pattern structures and their projections. In: Delugach, H.S., Stumme, G. (eds.) ICCS 2001. LNCS (LNAI), vol. 2120, pp. 129–142. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  5. 5.
    Diatta, J., Ralambondrainy, H.: The conceptual weak hierarchy associated with a dissimilarity measure. Mathematical Social Sciences 44, 301–319 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Bandelt, H.J., Dress, A.W.M.: Weak hierarchies associated with similarity mea¬sures: an additive clustering technique. Bull. Math. Biology 51, 113–166 (1989)MathSciNetGoogle Scholar
  7. 7.
    Bandelt, H.J., Dress, A.W.M.: An order theoretic framework for overlapping clus¬tering. Discrete Mathematics 136, 21–37 (1994)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Barbut, M., Monjardet, B.: Ordre et classification. Hachette, Paris (1970)zbMATHGoogle Scholar
  9. 9.
    Wille, R.: Restructuring lattice theory: an approach based on hierarchies of concepts. In: Rival, I. (ed.) Ordered sets, pp. 445–470. Ridel, Dordrecht (1982)Google Scholar
  10. 10.
    Birkhoff, G.: Lattice theory, 3rd edn. Coll. Publ., vol. XXV. American Mathematical Society, Providence (1967)zbMATHGoogle Scholar
  11. 11.
    Joly, S., Le Calve, G.: Three-way distances. J. Classification 12, 191–205 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Bennani, M., Heiser, W.J.: Triadic distance models: axiomatization and least squares representation. J. Math. Psychology 41, 189–206 (1997)zbMATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Diatta, J.: Dissimilarites multivoies et generalisations d’hypergraphes sans triangles. Math. Inf. Sci. hum. 138, 57–73 (1997)zbMATHMathSciNetGoogle Scholar
  14. 14.
    Stumme, G., Taouil, R., Bastide, Y., Pasquier, N., Lakhal, L.: Computing iceberg concept lattices with TITANIC. Data & Knowledge Engineering 42, 189–222 (2002)zbMATHCrossRefGoogle Scholar
  15. 15.
    van Deursen, A., Kuipers, T.: Identifying objects using cluster and concept analysis. Technical Report SEN-R981, CWI, Amsterdam, The Netherlands (1984)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Jean Diatta
    • 1
  1. 1.IREMIA, Université de la RéunionSaint-Denis messag cedex 9France

Personalised recommendations