Postprocessing the Hybrid Method for Addressing Uncertainty in Risk Assessments |
| |
Authors: | Cédric Baudrit Dominique Guyonnet Didier Dubois |
| |
Affiliation: | 1Math Specialist, Univ. Paul Sabatier, 31063 Toulouse, France. 2Environment Specialist, BRGM, BP 6009, 45060 Orléans Cédex 2, France (corresponding author). E-mail: d.guyonnet@brgm.fr
|
| |
Abstract: | In a previous paper in this Journal, a “hybrid method” was proposed for the joint propagation of probability distributions (expressing variability) and possibility distributions (i.e., fuzzy numbers, expressing imprecision or partial ignorance) in the computation of risk. In order to compare the results of the hybrid computation (a random fuzzy set) to a tolerance threshold (a tolerable level of risk), a postprocessing method was proposed. Recent work has highlighted a shortcoming of this postprocessing step which yields overly conservative results. A postprocessing method based on Shafer’s theory of evidence provides a rigorous answer to the problem of comparing a random fuzzy set with a threshold. The principles behind the new postprocessing scheme are presented and illustrated with a synthetic example. |
| |
Keywords: | Risk management Uncertainty principles Monte Carlo method Fuzzy sets Hybrid methods |
|
|