A new correlation belief transfer method in the evidence theory

Abstract

Dempster-Shafer evidence theory (D-S evidence theory) is an effective method in dealing with uncertain information. However, it may get counterintuitive results when using traditional Dempste’s combination rule directly to fuse highly conflicting data. How to manage conflict in data fusion is still an open issue in D-S evidence theory. In this paper, a new correlation belief function is proposed to modify the basic belief assignment before combination in closed-world. The method transfers the belief from a certain proposition to another related proposition to avoid the loss of information when data are fused, which effectively solves the problem of conflict management in D-S evidence theory. The advantage of the proposed method is that it does not lose belief value in main propositions related to decision-making and also expresses the conflict information effectively. Several numerical examples and experiments with real data sets from the University of California Irvine Machine Learning Repository are adopted to verify the rationality and validity of the proposed method.