新不确定度量下的冲突证据融合

针对证据高度冲突的情况下,DS证据理论在实际应用中出现错误融合结果的问题,提出基于不确定度的冲突解决方法.首先分析现有的不确定度量方法的不足,研究基本概率赋值本身所包含的信息,提出一种新的对证据不确定性度量的方法;依据新的不确定度量,结合证据距离生成权重来修正待组合证据体,再利用Dempster规则完成证据组合,可有效解决证据高度冲突情况下的信息融合问题,最后通过算例验证了该方法的有效性.

Conflicting evidence combination based on a new measure method of uncertainty

In order to deal with the problem that Dempster-Shafer evidence theory will lead to fault results of information fusion under the situation of highly conflicting evidence, the solution procedure are proposed based on a new measure method of uncertainty. It analyzed the deficiencies of several existing uncertain measure methods, and studied the information contained in basic probability assignment, then proposed a new method to measure the uncertainty of evidence. According to the new approach of uncertainty measure, we could combine it with distance of evidence to generate weight, then we exploited the Dempster's rule to complete evidence combinations. In this way, we can deal with the problem of information fusion by Dempster's rule of combination effectively, when it comes to highly conflicting evidence combination. Finally, several examples illustrate the effectiveness of the proposed method.