An Improved Weighted Evidence Combination Based on Tangent Similarity and Its Application in Decision-Making

Abstract

Dempster-Shafer theory (DST) has been widely recognized across multiple disciplines for its superior handling of uncertainty compared to traditional probability theory. Nonetheless, the application of Dempster's rule in the presence of conflicting evidence can lead to outcomes that are sometimes non-intuitive. To mitigate this issue, this paper proposes a new tangent similarity measure within DST to assess the conflict between evidences. The proposed measure adheres to several key properties, enhancing its ability to accurately reflect the similarity between evidences. Additionally, an improved weighted evidence combination framework utilizing the tangent similarity measure is developed. The effectiveness of the proposed method is demonstrated through a decision-making scenario in plant disease detection.