基于证据距离和矛盾因子的加权证据合成法  

Combination of weighted belief functions based on evidence distance and conflicting belief

作　　者：刘准钆[1] 程咏梅[1] 潘泉[1] 苗壮[1] 

机构地区：[1]西北工业大学自动化学院,陕西西安710072

出　　处：《控制理论与应用》2009年第12期1439-1442,共4页Control Theory & Applications

基　　金：国家自然科学基金重点资助项目(60634030);航空科学基金资助项目(2007ZC53037);高等学校博士学科专项科研基金资助项目(20060699032)

摘　　要：针对Dempster-Shafer(DS)理论直接对高冲突证据合成时会有融合结果不合理的问题,本文提出了一种加权证据合成法.在多个证据融合时,该方法综合利用证据距离和矛盾因子表示证据冲突,并根据各证据与其它证据的冲突程度确定其权重系数,基于此又分别采用两种适用于不同情况的方法对证据基本置信指派函数修正,然后用DS规则合成.算例实验表明了本文方法对高冲突证据融合的有效性,并且其融合结果还具有良好的收敛性.Dempster-Shafer（DS） theory involves counter-intuitive behaviors when evidence highly conflicts. A new approach of combination of weighted belief functions is proposed to solve the problem. If many pieces of evidence are to be combined, the amount of conflict between evidences is at first evaluated by both evidence distance and conflicting belief, and every piece of evidence is given a weight coefficient according to its amount of conflict with the others. Two different methods are separately used to modify the belief function of each piece of evidence based on its weight coefficient. Finally, the modified functions are combined by DS rule. In the last part of this paper, numerical examples are given to illustrate the effectiveness and the good performance of convergence of the proposed approach in case of high conflict between evidences.

关 键 词：证据理论 权重系数 证据距离 矛盾因子 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]