A novel method for combining conflicting evidences based on information entropy

Dempster-Shafer evidence theory is widely used to deal with uncertainty in intelligent systems. However, the application of this theory is constrained by the failure to balance multiple conflict evidence. The existing studies have primarily focused on investigating similarity of evidence. However, the similarity measurement is highly dependent on the capability of distance functions and will substantially increase the computational complexity. So, the efficient method with acceptable expense should be intensively investigated. In this paper, we propose a new method based on the variance of information entropy to handle the conflict of evidence. First, the fuzzy preference relations based on the variance of information entropy are constructed for multiple pieces of evidence. Next, credible values of alternative evidence are calculated. Finally, according to the Dempster’s rule of combination, the weighted average combination result can be obtained. Typical example and several actual data are used to demonstrate that the proposed method is more reasonable than some existing methods both in managing conflict and reducing computational complexity.