基于证据源和组合规则双修正的证据合成

Evidence Synthesis Based on Double Modification of Evidence Source and Combination Rule

针对冲突证据合成时传统证据合成和单一修正改进方法存在的问题,提出了新的证据源预处理和组合规则双修正的证据合成方法。利用夹角余弦理论,计算证据向量距离后转化得到权重系数,依据权重系数对证据进行重新概率分配,完成证据源修正;之后用修正的动态合成规则,进行修正证据的合成;同时提出了算法分析模型。实例结果验证了算法在证据合成时具有最优结果、较强通用性和稳定性,可应用于信息融合、不确定信息决策等领域。

In view of the problems existing in the traditional evidence synthesis and the single correction improvement method,a new evidence combination method is proposed,which is based on the combination of evidence sources preprocessing and combination rules. According to the concept of included angle co-sine,the multi-dimensional vector distance formula is inferred. Evidence distances representing the con-flict degree are calculated using the evidence vector, which are further converted into the weight coeffi-cient. The evidences probability is redistributed by using the weight coefficient. Finally,the improved dy-namic synthesis rule is used to complete the combination of the evidence. At the same time,a new algo-rithm analysis model is proposed. The experimental results show that the algorithm has the best results, strong versatility and stability in the evidences combination,and it can be applied in information fusion,un-certain information decision-making and other fields.