基于Lance距离和信度熵的冲突证据融合方法  被引量:9

Conflict evidence fusion method based on Lance distance and credibility entropy

在线阅读下载全文

作  者:王旋 狄鹏[1] 尹东亮 WANG Xuan;DI Peng;YIN Dongliang(Department of Management Engineering and Equipment Economic, Naval University of Engineering, Wuhan 430033, China;Department of Operation Research and Planning, Naval University of Engineering, Wuhan 430033, China)

机构地区:[1]海军工程大学管理工程与装备经济系,湖北武汉430033 [2]海军工程大学作战运筹与规划系,湖北武汉430033

出  处:《系统工程与电子技术》2022年第2期592-602,共11页Systems Engineering and Electronics

基  金:海军装备技术基础项目(191HJ35003)资助课题。

摘  要:针对D-S(Dempster-Shafer)证据理论中证据融合可能存在冲突的问题,通过考虑证据之间的关系及其本身的特性,提出一种基于Lance距离和信度熵的冲突证据融合方法。首先,利用Lance距离来度量证据之间的差异和冲突程度,并通过矩阵形式表示证据的可信度,再通过计算信度熵来度量证据的信息量,并以此表示证据的不确定度。其次,综合考虑证据的可信度和不确定度来衡量证据最终融合的折扣系数,并通过折扣系数修正原始证据。最后,采用Dempster合成规则进行证据融合得到最终结果。算例分析结果表明,所提方法较其他方法而言,收敛速度更快,融合结果更准确、可靠。In view of the possible conflicts in the fusion of evidence in the D-S(Dempster-Shafer)evidence theory,a conflict evidence fusion method based on Lance distance and reliability entropy is proposed by considering the relationship between the evidence and their own characteristics.Firstly,Lance distance is used to measure the difference and conflict between evidences,and the credibility of evidence is determined by matrix form,then the information quantity of evidence is measured by calculating the credibility entropy,and the uncertainty of evidence is expressed.Secondly,the discount coefficient of the final fusion of evidence is measured by comprehensively considering the reliability and uncertainty of evidence,and the original evidence is corrected by the discount coefficient.Finally,Dempster synthesis rule is used for evidence fusion to get the final result.The results of example analysis show that the proposed method has faster convergence speed and more accurate and reliable fusion results than other methods.

关 键 词:D-S证据理论 冲突证据 Lance距离 信度熵 可信度 不确定度 

分 类 号:TP13[自动化与计算机技术—控制理论与控制工程] TJ06[自动化与计算机技术—控制科学与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象