A New Combination Rule Based on the Average Belief Function

Abstract

An important tool in modelling and reasoning under uncertainty is the Dempster Shafer theory (DST) of evidence. Its widespread application can be attributed to its capability to handle uncertainty due to randomness and non-specificity. The Dempster Shafer (DS) rule of combination offers opportunity to fuse pieces of evidence from different independent sources. However, the DS rule of combination is often prone to counterintuitive results when pieces of evidence are highly conflicting. To overcome this issue, several methods have been proposed. In this work, we propose a new rule of combination based on the average belief function. The performance of the proposed method was compared with some existing approaches using numerical examples.