一种基于粗集的证据理论组合算法

A Algorithm on Rought sets-Based of Evidence Theory

Dempster合成规则为证据理论提供了一个有用的合成公式,但该公式在合成高度冲突的证据时,合成结果将有悖于常理.将粗集理论中属性重要度的思想引入到证据理论中,以此衡量证据的重要性,改善冲突证据的合成效果.该方法可把专家的主观判断和过去可用的知识与数据综合考虑,使群体决策得到更符合实际的结论.

Dempster has offered a useful algorithm of Evidence Combination,but the algorithm need independent evidence. If it is used in high conflict evidence,the result would be innormal. This paper present the algorithm of Evidence Theory which draw into the concept of Attribute importance of Rough Sets, utilize it to weigh the evidenc importance and improve the effect of high conflict evidence, the method stick together the experience of expert and the knowledge of historic data ,with it we would be obtain real conclusion in Group Decision.