An evidence fusion method based on weight optimization

There are two ways to improve the D-S evidence theory, the methods based on modification for Dempster rule, and the methods based on modification for original evidence sources. For modification of evidence sources, there are mainly two methods: discounting factor method and weighted average method. Although the weighted average method has better focusing degree, it ignores conflicting degree of combination results. If the conflicting degree is not reduced effectively, it will bring risks to the decision process. This paper proposes an evidences combination method based on weight optimization. The grey correlation degree is used to describe different evidences' credibility. Although it can increase the focusing ability of the combination results, high conflict degree still exists; then the ambiguity measure (AM) is used to measure evidence's uncertainty; and then both of them are used to calculate the evidence's weight. The minimum conflict degree is regarded as the optimized target and particle swarm optimization (PSO) algorithm is used to select reasonable parameters rho, alpha and beta. Two examples show that the proposed method in this paper has better focusing effects and lower conflict degree.