The modified Dempster-Shafer approach to classification

This paper describes “modified Dempster-Shafer” (MDS), an approach to object identification which incorporates Bayesian prior distributions into an altered Dempster-Shafer rule of combination. The MDS combination rule reduces, under strong independence assumptions, to a special case of Bayes´ rule. We show that MDS has rigorous probabilistic foundations in the theory of random sets. We also demonstrate close relationships between MDS and Smets´ “pignistic” probabilities (1990), which in the MDS framework become true posterior distributions. We describe the application of MDS to a practical classification algorithm which uses an information-theoretic technique to limit the combinatorial explosion of evidence. We also define a non-ad hoc, MDS-based classification “miss distance” metric used to measure the performance of this algorithm