Clustering belief functions based on attracting and conflicting metalevel evidence using Potts spin mean field theory

Abstract

In this paper we develop a Potts spin neural clustering method for clustering belief functions based on attracting and conflicting metalevel evidence. Such clustering is useful when the belief functions concern multiple events, and all belief functions are mixed up. The clustering process is used as the means for separating the belief functions into clusters that should be handled independently. A measure for the adequacy of a partitioning of all belief functions is derived and mapped onto the neural network in order to obtain fast clustering. A comparison of classification error rate between using conflicting metalevel evidence only and both conflicting and attracting metalevel evidence demonstrates a significant reduction in classification error rate when using both.