Fractal-based Belief Entropy

Abstract: The total uncertainty measurement of basic probability assignment (BPA) in Dempster-Shafer evidence theory (DSET) has always been an open issue. Although some scholars put forward various measurements and entropies of BPA, due to the existence of discord and non-specificity, there is no method can measure BPA reasonably. In order to utilize BPA to practical decision-making, pignistic probability transformation of BPA is a significant method. In the paper, we simulate the pignistic probability transformation (PPT) process based on the fractal idea, which describes PPT process in detail and shows the process of information volume changes during transformation intuitively. Based on transformation process, we propose a new belief entropy called fractal-based belief (FB) entropy. After verification, FB entropy is superior to all existing belief entropies in terms of total uncertainty measurement and physical model consistency.