Practical Uses of Belief Functions

TL;DR

This paper demonstrates how belief functions can effectively address real-world problems involving incomplete or uncertain information across various domains.

Contribution

It provides practical examples showing the application of belief functions to solve complex, messy data problems in different fields.

Findings

Belief functions enable sound solutions to problems with missing data.

They facilitate data integration from overlapping sensor sources.

They help determine the number of sources by analyzing contradictions.

Abstract

We present examples where the use of belief functions provided sound and elegant solutions to real life problems. These are essentially characterized by ?missing' information. The examples deal with 1) discriminant analysis using a learning set where classes are only partially known; 2) an information retrieval systems handling inter-documents relationships; 3) the combination of data from sensors competent on partially overlapping frames; 4) the determination of the number of sources in a multi-sensor environment by studying the inter-sensors contradiction. The purpose of the paper is to report on such applications where the use of belief functions provides a convenient tool to handle ?messy' data problems.