URREF Self-Confidence in Information Fusion Trust

PDF

Authors
  1. Blasch, E.
  2. Josang, A.
  3. Dezert, J.
  4. Costa, P.C.G.
  5. Jousselme, A-L.
Corporate Authors
Defence Research and Development Canada, Valcartier Research Centre, Quebec QC (CAN)
Abstract
The Uncertainty Representation and Reasoning Evaluation Framework (URREF) includes an ontology that represents concepts and criteria needed to evaluate the uncertainty management aspects of a fusion system. The URREF ontology defines self-confidence as a measure of the information credibility as evaluated by the sensor itself. The concept of confidence, which is not explicitly defined in the ontology at URREF, has been extensively explored in the literature about evaluation in information fusion systems (IFS). In this paper, we provide a discussion on confidence as it relates to the evaluation of IFS, and compare it with the existing concepts in the URREF ontology. Our goal is two-fold, since we address both the distinctions between confidence and self-confidence, as well as the implications of these differences when evaluating the impact of uncertainty to the decision-making processes supported byt the IFS. We illustrate the discussion with an example of decision making that involves signal detection theory, confusion matrix fusion, subjective logic, and proportional conflict redistribution. We argue that uncertainty can be minimized through confidence (information evidence) and self-confidence (source agent) processing, The results here seek to enrich the ongoing discussion at the ISIF’s Evaluation of Techniques for Uncertainty Representation Working Group (ETURWG) on self-confidence and trust in information fusion systems design.
Keywords
Information Fusion;Self-Confidence;Confidence;Trust;Level 5 Fusion;Hard & Soft fusion;Subjective Logic
Report Number
DRDC-RDDC-2016-P123 — External Literature
Date of publication
07 Dec 2016
Number of Pages
8
DSTKIM No
CA042817
CANDIS No
804711
Format(s):
Electronic Document(PDF)

Permanent link

Document 1 of 1

Date modified: