A novel conflict measurement method based on cosine similarity and Deng entropy in Dempster-Shafer evidence theory

As a generalization of probability theory, Dempster-Shafer evidence theory is superior in dealing with uncertain information. However, a counter-intuitive result is often obtained when combining highly conflicting evidence. In this paper, a new method based on similarity and Deng entropy of the evidence is proposed to measure the conflict and a new framework of fusing conflicting evidence is built based the proposed method. When most evidence has the same view, this evidence is given the higher weight. Moreover, the lower the entropy of the evidence, the stronger its ability to provide accurate information, and should be paid more attention. Experiments on real data show that this method can effectively solve the combination problem of conflicting evidence and it has a higher accuracy rate in the classification problem compared with other methods.