Computational-Workload Based Binarization and Partition of Qualitative Markov Trees for Belief Combination

  • Weiru Liu
  • Xin Hong
  • Kenny Adamson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2711)


Binary join trees have been a popular structure to compute the impact of multiple belief functions initially assigned to nodes of trees or networks. Shenoy has proposed two alternative methods to transform a qualitative Markov tree into a binary tree. In this paper, we present an alternative algorithm of transforming a qualitative Markov tree into a binary tree based on the computational workload in nodes for an exact implementation of evidence combination. A binary tree is then partitioned into clusters with each cluster being assigned to a processor in a parallel environment. These three types of binary trees are examined to reveal the structural and computational differences.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barnett, J.A.: Computational methods for a mathematical theory of evidence. In: Proc. of IJCAI 1981, Vancouver, BC, pp. 868–875 (1981)Google Scholar
  2. 2.
    Cano, A., Moral, S., Salmeron, A.: Penniless propagation in join trees. International Journal of Intelligent Systems 15, 1027–1059 (2000)MATHCrossRefGoogle Scholar
  3. 3.
    Dubois, D., Prade, H.: Inference in possibilistic hypergraphs. In: Bouchon-Meunier, B., Zadeh, L.A., Yager, R.R. (eds.) IPMU 1990. LNCS, vol. 521, pp. 228–230. Springer, Heidelberg (1991)CrossRefGoogle Scholar
  4. 4.
    Gordon, J., Shortliffe, E.H.: A method for managing evidential reasoning in a hierarchical hypothesis space. Artificial Intelligence 26, 323–357 (1985)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Liu, W., Hong, X., Adamson, K.: Parallel implementation of evidence combination in qualitative Markov tress. Technical Report, University of UlsterGoogle Scholar
  6. 6.
    Madsen, A., Jensen, F.: LAZY propagation: A junction tree inference algorithm based on lazy propagation. Artificial Intelligence 113, 203–245 (1999)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Maheshwari, P., Shen, H.: An efficient clustering algorithm for partitioning parallel programs. Parallel Computing 24, 893–909 (1998)MATHCrossRefGoogle Scholar
  8. 8.
    Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, San Mateo (1988)Google Scholar
  9. 9.
    Shafer, G.: A mathematical theory of evidence. Princeton University Press, Princeton (1976)MATHGoogle Scholar
  10. 10.
    Shafer, G., Logan, R.: Implementing Dempster’s rule for hierarchical evidence. Artificial Intelligence 33, 271–298 (1987)MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Shafer, G., Shenoy, P., Mellouli, K.: Propagating belief functions in qualitative Markov trees. Int. J. of Approx. Reasoning. 1, 349–400 (1987)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Shenoy, P.: Binary join trees. In: Proc. of UAI 1996, pp. 492–499 (1996)Google Scholar
  13. 13.
    Shenoy, P.: Binary join trees for computing marginals in the Shenoy-Shafer architecture. Int. J. of Approx. Reasoning 17, 239–263 (1997)MATHCrossRefMathSciNetGoogle Scholar
  14. 14.
    Shenoy, P., Shafer, G.: Propagating belief functions with local computations. IEEE Expert 1, 43–52 (1986)CrossRefGoogle Scholar
  15. 15.
    Tessem, B.: Approximations for efficient computation in the theory of evidence. Artificial Intelligence 61, 315–329 (1993)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Voorbraak, F.: A computationally efficient approximation of Dempster-Shafer theory. International Journal of Man-Machine Studies 30, 525–536 (1989)MATHCrossRefGoogle Scholar
  17. 17.
    Wilson, N.: A Monte-Carlo algorithm for Dempster-Shafer belief. In: Proc. of UAI 1991, p. 414 (1991)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Weiru Liu
    • 1
  • Xin Hong
    • 1
  • Kenny Adamson
    • 1
  1. 1.School of Computing and MathematicsUniversity of Ulster at JordanstownUK

Personalised recommendations