A new complex correlation coefficient in complex evidence theory
Niu Wang, Niu Wang, Mengjiao Chen, Ningkui Wang, Ningkui Wang · International Journal of Parallel Emergent and Distributed Systems · 2024
Complex Evidence Theory (CET) is a generalization of D-S Evidence Theory that can represent uncertain information and express uncertainty effectively. One of the hot topics in CET is how to measure the conflict between different pieces of evidence. Recently, a complex correlation coefficient has been proposed to measure the degree of similarity between two sets of evidence, where the similarity reflects the difference between the evidence, i.e. the degree of conflict between the sets of evidence. However, there is still a need to improve the precision of conflict metrics. In this paper, a new complex correlation coefficient called CCOR is proposed to measure the similarity between two sets of evidence. Through some numerical examples, CCOR can be used to measure the conflict between the two sets of evidence well. Finally, the validity and applicability of the method proposed in this paper are further illustrated by comparative experiments on real datasets.