基于Einstein算子的证据冲突度量方法  

Measurement of evidence conflict based on Einstein operator

作　　者：李军伟[1] 刘先省[1] 胡振涛[1] LI junwei;LIU Xianxing;HU Zhentao(School of Computer and Information Engineering , Henan University , Kaifeng 475004 , Chin)

机构地区：[1]河南大学计算机与信息工程学院,河南开封475004

出　　处：《系统工程与电子技术》2017年第12期2659-2664,共6页Systems Engineering and Electronics

基　　金：国家自然科学基金(61300214);河南省高等学校重点科研项目(16A510001);河南省科技发展计划(162102210401);河南省博士后科研项目二等资助;河南省高校科技创新团队支持计划(13IRTSTHN021);河南大学科学研究基金(2015YBZR026)资助课题

摘　　要：为了有效度量融合证据之间的冲突,在分析冲突因子和典型证据冲突度量方法不足的基础上,提出了一种基于Einstein算子的证据冲突度量方法。首先,利用证据向量度量思想给出证据之间的差异度矩阵,并定义对数形式的差异因子;然后,引入模糊集相似关系定义证据之间的相关系数;最后,综合考虑证据之间的差异性和相关性,利用Einstein算子定义一种新的证据冲突度量因子。仿真实验结果表明:该方法不但可以有效度量证据之间的冲突程度,而且对冲突证据的融合具有良好的收敛性。In order to efficiently measure the conflict degree between the fusion evidences,an Evidence conflict measurement based on the Einstein operator is proposed based on the analysis of conflict coefficients and typical evidence conflict measure shortcomings.First,the evidences vector measure is used to give the difference matrix between the evidences and the logarithmic form of the difference coefficient is defined.Then,the similarity relation between the fuzzy sets is introduced to define the correlation coefficient between the evidence.Finally,the difference and correlation between two pieces of evidence are considered,the Einstein operator is used to define a new evidence conflict measurement coefficient.The simulation results indicate that this method not only can effectively measure the degree of conflict between evidences,but also has a good convergence on the fusion of conflict evidences.

关 键 词：证据理论 冲突度量 组合规则 冲突因子 Einstein算子 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]