SHADED: Shapley Value-Based Deceptive Evidence Detection in Belief Functions

Deceptive evidence detection is an important issue in the theory of belief functions, which can be used to solve the problem of conflicts among evidence and to assess the credibility of evidence sources. In this paper, we first define strong and weak deceptive evidence. Then, we propose a deceptive evidence detection approach that directly investigates the process of Dempster’s combination rule and decision-making based on the pignistic transformation. It can distinguish between strong and weak deceptive evidence and assess the importance of each piece of evidence. Several numerical examples are used to illustrate the effectiveness and efficiency of our proposed approach.