A Novel Evidence Distance in Power Set Space

Abstract

Distance measure of evidence presented has been used to measure the similarity of two bodies of evidence. However, it is not considered that the probability distribution on a power set is able to assign to its subsets not only single elements. In this paper a novel approach is proposed to measure the distance of evidence. And some properties that the novel approach has, such as nonnegativity, symmetry, triangular inequality, downward compatibility and higher sensitivity, is proved. Numerical example and real application are used to strictly illustrate the effciency of the new distance.