Fuzzy Measure and Probability Distributions: Distorted Probabilities

Abstract

This work studies fuzzy measures and their application to data modeling. We focus on the particular case when fuzzy measures are distorted probabilities. We analyze their properties and introduce a new family of measures (m-dimensional distorted probabilities). The work finishes with the application of two dimensional distorted probabilities to a modeling problem. Results of the application of such fuzzy measure to data modeling using Choquet integral are discussed