Identification and application of the evidence conflict based on K-L information distance

Evidence conflict is proved to be the main restricting problem of various synthesis methods in the evidences integration, this paper introduces the K-L information distance function to describe the conflict characteristics between evidences, defines the conflict degree of independent evidence in the whole system through the structure of distance matrix, realizes the systematic recognition of evidence conflict. Simulating results show that: the effective conflict identification of K-L information distance can complete the application constraint of D-S theory's synthetic rule, obtaining the optimized convergence results for synthesis of normal conflicting evidences, extracting the valuable information for the characteristics analysis of highly conflicting isolation evidence.