A modified soft-likelihood function based on POWA operator

摘要

Information fusion is an important research direction. In this field, there are plenty of ways to combine evidence. Initially, Yager proposed a soft-likelihood function based on the ordered weighted average (OWA) operator to effectively fuse compatible probabilistic evidence. Recently, Song et al proposed a new soft-likelihood function based on the power ordered weighted average (POWA) operator. However, through analysis, we find Song et al's method has the following two shortcomings: (a) The weight of POWA cannot comprehensively reflect the relation between probability and OWA operator, (b) The soft-likelihood function does not reflect the preferences of decision makers. To overcome the above problem, we propose a modified soft-likelihood function. The effectiveness of the proposed method is demonstrated from the perspective of theoretical analysis and numerical examples.