一种基于改进证据相似度的D-S融合算法  

A D-S Fusion Algorithm Based on Improved Similarity of Evidence

作　　者：钱建波 王旭康[2] 董进 韩伟[3] 冯中存 QIAN Jianbo;WANG Xukang;DONG Jin;HAN Wei;FENG Zhongcun(Center of Modern Education Technology,Jiangsu Vocational College of Electronics and Information,Huai’an 223003,China;The 53rd Research Institute of CETC,Tianjin 300000,China;State Grid Huaian Power Supply Company,Huai’an 223001,China;Unit 32703,PLA,Shijiazhuang 050081,China)

机构地区：[1]江苏电子信息职业学院现代教育技术中心,江苏淮安223003 [2]中国电子科技集团公司第五十三研究所,天津300000 [3]国网淮安供电公司,江苏淮安223001 [4]中国人民解放军32703部队,河北石家庄050081

出　　处：《无线电工程》2021年第10期1157-1161,共5页Radio Engineering

基　　金：江苏省“333工程”科研项目(BRA2018315)。

摘　　要：通过改进证据相似度提出一种新颖的证据合成规则方法,有效解决了存在冲突证据时的证据理论(Dempster-Shafer,D-S)合成悖论问题。引入相容系数构造参考证据体,运用加权平均证据作为参考证据体;借助相似三角函数,判定异常证据体;运用D-S合成进行证据合成方法对各个证据进行融合。仿真结果表明,所提出的方法能够有效处理冲突证据,相对于其他几种典型改进算法具有更快的识别速度和精度。A novel evidence synthesis rule method is proposed by improving the similarity of evidence,which effectively solves the Dempster-Shafer(D-S)synthesis paradox in the presence of conflicting evidences.The reference body is constructed by using compatibility coefficient,and weighted average evidence is used as reference body.Abnormal evidence body is determined by using similar trigonometric function.The D-S synthesis method is used to integrate all the evidences.The simulation results show that the proposed method can effectively deal with conflicting evidences,and has faster recognition speed and better accuracy than other typical improved algorithms.

关 键 词：D-S证据理论 冲突证据 相容系数 参考证据体 三角函数 

分 类 号：TP14[自动化与计算机技术—控制理论与控制工程]