Advertisement

On the combination of information sources

  • R. Kruse
  • E. Schwecke
1. Mathematical Theory Of Evidence
Part of the Lecture Notes in Computer Science book series (LNCS, volume 521)

Abstract

Subject of this paper is a thorough modeling of uncertain knowledge based on the theory of belief functions. In this context it has to be taken into account, that some experts state of mind changes in the light of new information, thus we introduce the notion of an information source. Considering the integration of information sources it turns out that this approach leads to Dempster's well-known rule of combination.

Keywords

belief function information source combination theory of evidence 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

5-References

  1. [1]
    DUBOIS, D. and PRADE, H., 1986, A set theoretic view of belief functions, logical operations and approximations by fuzzy sets, Int. J. of General Systems 12, 193–226.Google Scholar
  2. [2]
    DUBOIS, D. and PRADE, H., to appear, Consonant approximations of belief functions, Int. J. of Approximate Reasoning.Google Scholar
  3. [3]
    GOODMAN, J.R. and NGUYEN, H.C., 1985, Uncertainty models for knowledge based systems, North Holland, Amsterdam.Google Scholar
  4. [4]
    KRUSE, R. SCHWECKE, E. and HEINSOHN, J., to appear, Uncertainty and vagueness in knowledge based systems: Numerical methods, Springer.Google Scholar
  5. [5]
    SHAFER, G., 1976, A mathematical theory of evidence, Princeton.Google Scholar
  6. [6]
    SMETS, P., 1989, personal communications, DRUMS-First workshop at Najac.Google Scholar
  7. [7]
    YAGER, R.R., 1986, The entailment principle for Dempster/Shafer granules, Int. J. of Intelligent Systems 1, 247–262.Google Scholar
  8. [8]
    KRUSE, R. and SCHWECKE, E., to appear, Specialization — A new concept for uncertainty handling with belief functions, Int. J. of General Systems.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • R. Kruse
    • 1
  • E. Schwecke
    • 1
  1. 1.Institut für Betriebssysteme und Rechnerverbund TU BraunschweigBraunschweigWest Germany

Personalised recommendations