证据推理规则的性质研究及方法修正  

Property Research and Approach Modification of Evidential Reasoning Rule

作　　者：柯小路[1] 马荔瑶[1] 李子懿 王永[1] 

机构地区：[1]中国科学技术大学信息科学技术学院,安徽合肥230027

出　　处：《信息与控制》2016年第2期165-170,共6页Information and Control

基　　金：中央高校基本科研业务费专项资金资助项目(WK2100100017)

摘　　要：证据推理规则能有效处理证据的重要性及可靠性,针对该方法中证据权重归一化对合成结果的影响进行研究,据此分析证据合成时是否应归一化权重;探究证据推理规则与证据折扣方法之间的联系,证明两者的合成结果呈比例关系;分析证据推理规则在证据的重要性与可靠性表示上的不合理之处,并提出一种改进方法,证明了修改后的方法仍然满足4条基本合成公理.The evidential reasoning rule effectively deals with the importance of evidence and reliability. In this study,we investigate the influence of weight normalization on evidence combinations and discuss whether evidence weights should be normalized in different cases. We survey the relation between the evidential reasoning rule and evidence discounting approach and prove that the beliefs of the former are proportional to those of the latter. Finally,we propose a modified approach that satisfies four synthesis axioms,following an analysis of the evidential reasoning rule problem in modeling the importance of evidence and reliability.

关 键 词：证据理论 证据推理规则 加权信度分配 证据折扣 证据可靠性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]