基于多义度和三角模算子的加权冲突证据组合  

Based on a weighted conflict and ambiguity of the triangle mold operator evidence combination

作　　者：文如泉[1] 田华[1] 张兴娇[1] 辛锋[1] 

机构地区：[1]萍乡学院机械电子工程系,江西萍乡337055

出　　处：《自动化与仪器仪表》2014年第12期158-160,163,共4页Automation & Instrumentation

基　　金：国家自然基金(61263031);江西省科技计划项目(20133BBE50036)

摘　　要：为了有效融合高度冲突的证据,本文在多义度和三角模算子的基础上提出了一种新的证据理论融合规则。首先基于三角模算子定义了证据之间的相似度,然后基于相似度矩阵和多义度定义了改进的证据权重,基于加权原则对冲突证据进行合成得到修正的证据体,从而消除证据间的冲突,最后利用Dempster规则完成证据组合。算法分析表明所提方法是合理有效的。In order to combine highly conflicting evidence efficiently. A new evidence combination rule based on ambiguity measure and triangular norm is proposed. The similarity between conflicting evidence is defined using triangular norm, then the improved evidence weight is obtained based on similarity matrix and ambiguity measure, the modified evidence is obtained by verify the conflicting evidence according to the weighting rule in order to eliminate the conflict. Finally, according to the Dempster＇s rule,the modified evidence is combined. Numerical examples show the efficiency and rationality of the proposed approach.

关 键 词：证据理论 冲突 多义度 三角模算子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]