An Attempt to Define Graphical Models in Dempster-Shafer Theory of Evidence

  • Radim Jiroušek
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 77)

Abstract

The goal of this paper is to introduce graphical models in Dempster-Shafer theory of evidence. The way the models are defined is a natural and straightforward generalization of the approach from probability theory. The models possess the same “Global Markov Properties”, which holds for probabilistic graphical models. Nevertheless, the last statement is true only under the assumption that one accepts a new definition of conditional independence in Dempster-Shafer theory, which was introduced in Jiroušek and Vejnarová (2010). Therefore, one can consider this paper as an additional reason supporting this new type of definition.

Keywords

Graphical Markov models Conditional independence Factorization Multidimensional basic assignment 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ben Yaghlane, B., Smets, P., Mellouli, K.: Belief Function Independence: I. The Marginal Case. Internat. J. Approx. Reason. 29, 47–70 (2002)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Ben Yaghlane, B., Smets, P., Mellouli, K.: Belief Function Independence: II. The Conditional Case. Internat. J. Approx. Reason. 31, 31–75 (2002)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Couso, I., Moral, S., Walley, P.: Examples of independence for imprecise probabilities. In: Proceedings of the First International Symposium on Imprecise Probabilities and Their Applications, ISIPTA 1999, Ghent, Belgium, pp. 121–130 (1999)Google Scholar
  4. 4.
    Dempster, A.: Upper and lower probabilities induced by a multi-valued mapping. Ann. Math. Statist. 38, 325–339 (1967)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Jiroušek, R.: Factorization and Decomposable Models in Dempster-Shafer Theory of Evidence. In: Workshop on the Theory of Belief Functions, Brest, France (2010)Google Scholar
  6. 6.
    Jiroušek, R., Vejnarová, J.: Compositional models and conditional independence in evidence theory. Internat. J. Approx. Reason (2010), doi:10.1016/j.ijar.2010.02.005Google Scholar
  7. 7.
    Klir, G.J.: Uncertainty and Information. In: Foundations of Generalized Information Theory. Wiley, Hoboken (2006)Google Scholar
  8. 8.
    Lauritzen, S.L.: Graphical models. Oxford University Press, Oxford (1996)Google Scholar
  9. 9.
    Shafer, G.: A Mathematical Theory of Evidence. Princeton University Press, New Jersey (1976)MATHGoogle Scholar
  10. 10.
    Shenoy, P.P.: Conditional independence in valuation-based systems. Internat. J. Approx. Reason. 10, 203–234 (1994)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Studený, M.: Formal properties of conditional independence in different calculi of AI. In: Moral, S., Kruse, R., Clarke, E. (eds.) ECSQARU 1993. LNCS, vol. 747, pp. 341–351. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  12. 12.
    Studený, M.: On stochastic conditional independence: the problems of characterization and description. Ann. Math. Artif. Intell. 35, 323–341 (2002)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Vejnarová, J.: On conditional independence in evidence theory. In: Proceedings of the Sixth International Symposium on Imprecise Probability: Theories and Applications, ISIPTA 2009, Durham, UK, pp. 431–440 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Radim Jiroušek
    • 1
    • 2
  1. 1.Faculty of ManagementUniversity of EconomicsHradec
  2. 2.Institute of Information Theory and AutomationAcademy of SciencesPrageCzech Republic

Personalised recommendations