FuzzyProbSim: Fuzzy probability as similarity measure

Abstract

This study investigates a unified robust measures of similarity applicable in many domains and across many dimensions of data. Given a distance or discrepancy measure on a domain, the similarity of two values in this domain is defined as the probability that any pair of values from that domain are more different (at a larger distance) than these two values are. Fuzzy sets are introduced to make this definition more sensitive to quantitative difference. Combination across domains is also discussed.