Uncertainty representation using fuzzy measures

  • Authors:
  • R. R. Yager

  • Affiliations:
  • Machine Intelligence Inst., Iona Coll., New Rochelle, NY

  • Venue:
  • IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

We introduce the fuzzy measure and discuss its use as a unifying structure for modeling knowledge about an uncertain variable. We show that a large class of well-established types of uncertainty representations can be modeled within this framework. A view of the Dempster-Shafer (D-S) belief structure as an uncertainty representation corresponding to a set of possible fuzzy measures is discussed. A methodology for generating this set of fuzzy measures from a belief structure is described. A measure of entropy associated with a fuzzy measure is introduced and its manifestation for different fuzzy measures is described. The problem of uncertain decision making for the case in which the uncertainty represented by a fuzzy measure is considered. The Choquet integral is introduced as providing a generalization of the expected value to this environment