摘要
针对证据理论应用过程中,冲突证据的组合问题和基本概率赋值函数难以确定的问题,提出了一种新的冲突证据的组合方法。该方法以修改模型为基础,而不改变Dempster组合规则的结构。首先,在充分考虑焦元属性之间及证据之间的相互关联性基础上,引入证据体距离函数,然后,求出系统中各证据被其他证据所支持的程度,对支持度归一化后获得各个证据的可信度,并将可信度作为证据的权重,再将平均证据代替冲突证据,最后利用Dempster组合规则实现信息融合。通过仿真实验,将该方法与现有方法进行了分析比较,结果表明应用该方法是一种有效可行的证据组合方法。
Considering the combination of conflict evidences and the difficulty in determining the Basic Probability Assignment Function （BPAF） in the application of evidence theory, a new method for conflict evidence combination is put forward. The method is based on a modified evidence model and the structure of Dempster＇s combination rule is not modified. First, considering the correlations between focal attributes and between evidence, a distance function between the bodies of evidence is introduced. Then, the support degree and the credibility of each evidence are obtained. The conflict evidence is superseded by average evidence. Finally, the Dempster＇s combination rule is used to realize information fusion. In simulations, the proposed method is compared with the existing combination methods, and the result shows that the method is an effective and feasible method for conflict evidence combination.
出处
《电光与控制》
北大核心
2010年第4期5-8,13,共5页
Electronics Optics & Control
基金
陕西省教育厅专项基金资助项目(06JK281)
关键词
证据理论
冲突证据
组合规则
信息融合
evidence theory
conflict evidence
combination rule
information fusion
