The paper introduces an isopignistic transformation method based on the belief evolution network (BEN) that can cover the entire isopignistic domain. This transformation allows for the adjustment of the information granule while retaining the potential decision outcome.
The isopignistic canonical decomposition decomposes a belief function into two components:
Propensity: This component is a possibility distribution that represents the least committed case within the isopignistic domain. It is derived from the consonant mass function, which has the highest non-commitment degree in the isopignistic domain.
Commitment: This component is used to adjust the commitment degree from the consonant mass function to the input belief function. It is represented by the isopignistic transformation coefficients, either τ or ζ.
The paper establishes a theoretical basis for building general models of artificial intelligence based on probability theory, Dempster-Shafer theory, and possibility theory. It explores the advantages of the isopignistic canonical decomposition in modeling and handling uncertainty within the hyper-cautious transferable belief model.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Qianli Zhou,... at arxiv.org 05-07-2024
https://arxiv.org/pdf/2405.02653.pdfDeeper Inquiries