A new approach to semantic aspects of possibilistic reasoning
The purpose of this paper is to develop a formal environment that provides well-founded semantics of possibilistic reasoning in knowledge-based systems. Representing the universe of discourse as a product space Ω which consists of the domains of a finite number of characterizing attributes, expert knowledge and also evidential knowledge are expected to be given by possibility distributions on subspaces of Ω.
Our numerical approach clarifies the semantic background for the representation, interpretation, and operative handling of possibility distributions that are viewed as information-compressed specifications of so-called valuated imperfect characteristics. Furthermore the concepts of correctness- and sufficiency-preservation show how to operate on possibility distributions and how to find an appropriate inference mechanism as well as a justified interpretation of possibilistic implication rules, where, postulating weak preconditions, the well-known Gödel relation is justified to be the right choice.
An implementation of the presented concepts to solve data fusion problems has been developed in cooperation with German Aerospace.
KeywordsPossibility Distribution Inference Mechanism Possibility Theory Inference Mapping German Aerospace
Unable to display preview. Download preview PDF.
- [Buchanan, Shortliffle 1984]B.G.Buchanan, E.H.Shortliffle: Rule-Based Expert Systems. Addison Wesley, Reading, Massachusetts (1984)Google Scholar
- [Dubois, Prade 1988]D.Dubois, H.Prade: Possibility Theory, Plenum Press, New York (1988)Google Scholar
- [Dubois, Prade 1991]D.Dubois, H.Prade: Fuzzy Sets in Approximate Reasoning, Part 1: Inference with Possibility Distributions, Fuzzy Sets and Systems 40, No.1 (1991), 143–202Google Scholar
- [Dubois, Prade 1992]D.Dubois, H.Prade: Possibility Theory as a Basis for Preference Propagation in Automated Reasoning. Proc. FUZZIEEE'92, San Diego, 821–832 (1992)Google Scholar
- [Gebhardt et al. 1992]J.Gebhardt, R.Kruse, D.Nauck: Information Compression in the Context Model. Proc. NAFIPS'92, Puerto Vallarta, Mexico, 1992Google Scholar
- [Gebhardt, Kruse 1993]J.Gebhardt, R.Kruse: The Context Model — An Integrating View of Vagueness and Uncertainty, Int. Journal of Approximate Reasoning, (to appear)Google Scholar
- [Hestir et al. 1991]K.Hestir, H.T.Nguyen, G.S.Rogers: A Random Set Formalism for Evidential Reasoning. In: I.R.Goodman, M.M.Gupta, H.T.Nguyen, G.S.Rogers (eds.): Conditional Logic in Expert Systems, Elsevier, North-Holland, 309–344 (1991)Google Scholar
- [Klir, Folger 1988]G.J.Klir, T.A.Folger: Fuzzy Sets, Uncertainty, and Information, Prentice Hall, New York (1988)Google Scholar
- [Kruse, Siegel 1991]R.Kruse, P.Siegel (eds.): Symbolic and Quantitaive Approaches to Uncertainty. Lecture Notes in Computer Science, Springer, Berlin (1991)Google Scholar
- [Kruse et al. 1991a]R.Kruse, E.Schwecke, J.Heinsohn: Uncertainty and Vagueness in Knowledge Based Systems: Numerical Methods, Series Artificial Intelligence, Springer, Heidelberg (1991)Google Scholar
- [Kruse et al. 1991b]R.Kruse, E.Schwecke, F.Klawonn: On a Tool for Reasoning with Mass Distributions. Proc. IJCAI'91, Sydney, 1190–1195 (1991)Google Scholar
- [Lauritzen, Spiegelhalter 1988]S.L.Lauritzen, D.J.Spiegelhalter: Local Computation with Probabilities on Graphical Structures and their Application to Expert Systems. Journal of the Royal Statistical Society 50, 157–224 (1988)Google Scholar
- [Matheron 1975]G.Matheron: Random Sets and Integral Geometry, Wiley, New York (1975)Google Scholar
- [Pearl 1988]J.Pearl: Probabilistic Reasoning in Intelligent Systems, Networks of Plausible Inference, Morgan Kaufmann, New York (1988)Google Scholar
- [Shafer, Pearl 1990]G.Shafer, J.Pearl: Readings in Uncertain Reasoning. Morgan Kaufmann, San Mateo, CA (1990)Google Scholar