基于证据相似性度量的冲突性区间证据融合方法

基于证据相似性度量,该文提出一种冲突性区间证据融合的新方法。首先,定义了扩展型Pignistic概率转换,将区间证据转换为区间型Pignistic概率。利用区间模糊集的归一化欧式距离,求取区间型Pignistic概率之间的相似性,以此确定两两证据间的相似度矩阵,从中获取区间证据的置信度。然后,基于该置信度对原始的区间证据进行加权平均得到新的区间证据,利用Demspter区间证据组合公式对其进行融合。该方法可以有效地减弱高冲突性区间证据在组合规则中的作用,从而减小融合后所得区间证据的宽度,最终可降低决策中的不确定性。最后通过多个典型算例验证了经冲突处理后再对区间证据进行融合,要比直接融合能够产生更为合理和可靠的结果。

A New Fusion Method of Conflicting Interval Evidence Based on the Similarity Measure of Evidence

Based on the similarity measure of evidence,a new method for combining conflicting interval evidence is proposed.Firstly,interval evidence can be transformed into interval-valued Pignistic probability by using the defined extended Pignistic probability function.Using the normalized Euclidean distance of interval-valued fuzzy sets,the similarity between Pignistic probabilities of interval evidence are obtained,and similarity measure matrix can be constructed,from which the credibility degrees(weights) of interval evidence can be got.Secondly,based on the credibility degrees,new interval evidence can be obtained by modified and weightedly averaging the original interval evidence.Using Demspter interval evidence combination rule,the fusion result can be obtained by combining the new interval evidence.The proposed method can effectively eliminate the effect of highly conflicting interval evidence in combination so as to reduce the width of combined interval evidence.Therefore the uncertainty of decision-making can be decreased.Finally,in classical numerical examples,compared with the fused results by directly using Demspter interval evidence combination rule,the combined results by using this proposed method are more rational and reliable.