一种基于最优权重分配的D-S改进算法  

An Improved D-S Algorithm based on the Optimization Weight Distribution

作　　者：王小艺[1] 刘载文[1] 侯朝桢[2] 原菊梅[2] 郭飞[2] 

机构地区：[1]北京工商大学信息工程学院,北京100037 [2]北京理工大学自动控制系,北京100081

出　　处：《系统工程理论与实践》2006年第11期103-107,共5页Systems Engineering-Theory & Practice

基　　金：国防基础研究基金(Z172004A001)

摘　　要：为解决高冲突证据下的D-S证据理论失效这一问题,在对已有一些代表性改进方法分析的基础上,提出了一种新的基于最优权重分配的D-S改进算法.在保证证据冲突整体最小情况下,建立证据最优权重分配模型,对原证据模型进行修正.通过实例分析,并与其它改进方法进行对比,验证了该算法在解决冲突证据方面更为有效.In order to solve the invalidation problem of D-S evidence theory with high conflict evidences, on the basis of analyzing some typical improved methods, a new improved D-S algorithm based on optimization weight distribution is proposed. In the condition of ensuring the minimum of whole evidence conflict, sots up the distribution model of evidence optimization weights, then modifies original evidence model. Through analyzing the number examples, and comparing with other improved methods, the results show that the algorithm is more efficient to solve conflict evidences.

关 键 词：最优权重分配 优化理论 冲突证据 组合规则 

分 类 号：O21[理学—概率论与数理统计] TP274[理学—数学]