A reliability discounting strategy based on plausibility function of evidence

Abstract

Evidence gathered from different sources may have different reliabilities. Such reliability should be integrated into corresponding evidence model to make the evidence combination result rational. In this paper, a novel discounting strategy is developed for the integration of evidence's model and reliability. Dissimilar to the current one based on BPA, this strategy discounts the evidence's plausibility function with power rather than discounts BPA function with coefficient. It can alter the evidence's belief mass as well as its core simultaneously and hereby is more suitable for the discounting of evidence with unreliable core than the one based on BPA function. Furthermore, this new strategy is in some sense a linear discounting strategy which reduces the maximum possible support degree for each atomic proposition with an amount proportional to discount percent. Finally, two examples are presented to demonstrate the characteristics of the proposed discounting strategy.