Towards a formal comparison of uncertainty handling

Abstract

This paper explores the use of the Uncertainty Representation and Reasoning Evaluation Framework (URREF), a framework intended to change that state of affairs, in evaluating potential uncertainty representation approaches for a maritime Decision Support System. We revisit some comparison aspects discussed along the years and map them to the URREF. We illustrate the comparison on a simple maritime use case involving basic reasoning about threat assessment, with observations from partially reliable sources. The same fusion problem is modeled with the two uncertainty theories of Bayesian probability theory and evidence theory. Within the same framework, we consider two different reasoning schemes, Causal and Evidential, complemented with a source model of partial reliability. Comparison items are mapped to URREF ontology criteria of (Representation) Expressiveness and (Reasoning) Correctness. We highlight the criteria that can be useful in supporting systems developers in their choice of how to represent and manage uncertainty in information fusion processes, and propose some refinement to the URREF to capture handling of inconsistency.