Contextual Models of Information Fusion
Abstract
The core research objective of this project is to determine how observations with different types of associated uncertainty can be combined such that: 1. uncertainty is suitably assigned numerically to evidence 2. the level of trust in or reliance on a given data source or piece of data is adequately represented This project leveraged developments in the field of quantum information science in order to provide a principled theoretical framework and associated operational modelling language for determining if and then how combination of observations is possible. The key quantum concept being leveraged is contextuality. When decisions of trust are contextual, then a single joint probability distribution cannot be formed to model the decision making process. This impacts standard probabilistic models of information fusion which assume that the joint distribution can always be formed.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 29, 2022
- Accession Number
- AD1183675
Entities
People
- Jerome Busemeyer
- Peter David Bruza
Organizations
- Queensland University of Technology