摘要
针对证据合成时出现的冲突问题,提出一种融合可信度和不确定度的D-S证据组合方法,以证据之间的曼哈顿距离来衡量其差异性,定义相似度,判断证据的准确性和可信度,然后计算证据之间的信息熵度量证据的不确定性.将证据的可信度与不确定度进行相乘得到折扣系数,以修正原始证据,最后利用D-S组合规则得到融合结果,并通过算例分析对算法的合理性和准确性进行了验证.
Aiming at the conflict problem in evidence synthesis,a D-S evidence combination method combining credibility and uncertainty was proposed.The Manhattan distance between evidences was used to measure the difference,define similarity,judge the accuracy and credibility of evidence,and then calculate the information entropy between evidences to measure the uncer⁃tainty of evidence.The discount coefficient was obtained by multiplying the credibility and uncertainty of the evidence to correct the original evidence.Finally,the fusion result was obtained by using the D-S combination rule.The rationality and accuracy of the algorithm were verified by an example.
作者
沈金羽
王玉
张琳
SHEN Jinyu;WANG Yu;ZHANG Lin(School of Electrical&Information Engineering,Jiangsu University of Technology,Changzhou,Jiangsu 213001,China)
出处
《宜宾学院学报》
2023年第6期32-38,71,共8页
Journal of Yibin University
基金
国家自然科学基金青年基金项目“混合车联网架构下基于连通性的路侧单元部署与频谱共享技术研究”(61901196)。
关键词
证据理论
曼哈顿距离
信息熵
可信度
不确定度
evidence theory
Manhattan distance
information entropy
credibility
uncertainty
