摘要
为提高不同类型冲突证据融合结果的可靠性,提出基于多证据同步融合的目标辨识算法。新算法先是通过分析证据之间的冲突状况,选择适用的冲突衡量参数,并相应给出基于不同参数的证据及源自于不同证据焦元的权值计算公式;进一步,依据新的焦元权值对多证据局部冲突信息实行按权指派。实例和仿真应用结果显示,与现有常用相关算法比较,新算法具有稳定性高、使用范围广泛的优点。
In order to improve the reliability of the fusion results of different types of conflict evidence, a target recognition algorithm based on synchronous fusion of multiple pieces of evidence is proposed. First, by analyzing the conflict among pieces of evidence, applicable conflict measure parameters are selected in the new algorithm. And the weight calculation formulas of evidence and those of the focal element originating from different pieces of evidence based on different parameters are given. Furthermore, according to the new weight of focal element, the local conflict information can be assigned to related focal element. The simulation results show that compared with the existing algorithms, the new algorithm has the advantages of high stability and wide range of application.
作者
周莉
郭伟震
何月明
ZHOU Li;GUO Wei-zhen;HE Yue-ming(School of Information ＆ Electrical Engineering,Ludong University,Yantai 264025,China)
出处
《运筹与管理》
CSSCI
CSCD
北大核心
2018年第10期90-96,共7页
Operations Research and Management Science
基金
国家自然科学基金重大研究计划资助项目(91538201)
国家自然科学基金青年基金资助项目(61304052)
关键词
D-S证据组合规则
目标辨识
冲突证据
焦元
D-S evidence combination rule
target recognition
conflict evidence
focal element.
