A Novel Method for Conflict Data Fusion Using an Improved Belief Divergence Measure in Dempster–Shafer Evidence Theory

Dempster–Shafer (D-S) evidence theory plays an important role in multisource data fusion. Due to the nature of Dempster combination rule, there can be counterintuitive results when fusing highly conflicting data. To date, conflict management D-S is still open issue. Inspired by modification considering internal indeterminacy and external support, a novel method for fusion proposed based on improved belief divergence, distance, entropy. First, divergence measure defined characterize discrepancy between bodies (BOEs). Second, credibility generated describe support complementary advantages distance. Third, entropy utilized quantify further determine weight. Lastly, classical rule applied fuse BOEs modified their degrees weights. As numerical examples application show, overcome invalidity existing measures some special cases. Additionally, recognizes correct target with highest value 98.96%, which outperforms other related methods management. The also displays better convergence, validity, robustness.