Title: Computational approach and cognitive assistant for evidence-based reasoning in intelligence analysis

Authors: Gheorghe Tecuci; David A. Schum; Dorin Marcu; Mihai Boicu

Addresses: Learning Agents Center, Volgenau School of Engineering, George Mason University, 4400 University Dr., Fairfax, VA, USA ' Learning Agents Center, Volgenau School of Engineering, George Mason University, 4400 University Dr., Fairfax, VA, USA ' Learning Agents Center, Volgenau School of Engineering, George Mason University, 4400 University Dr., Fairfax, VA, USA ' Learning Agents Center, Volgenau School of Engineering, George Mason University, 4400 University Dr., Fairfax, VA, USA

Abstract: This paper presents a computational approach to intelligence analysis and its current implementation into a cognitive assistant called Disciple-CD. Intelligence analysis is viewed as ceaseless discovery of evidence, hypotheses, and arguments in a non-stationary world, involving cooperative processes of evidence in search of hypotheses, hypotheses in search of evidence, and evidentiary tests of hypotheses. Disciple-CD helps intelligence analysts formulate hypotheses, develop arguments that reduce complex hypotheses to simpler and simpler ones, collect evidence to evaluate the simplest hypotheses, assess the relevance, believability, and inferential force of evidence, and finally the likeliness of the hypotheses.

Keywords: science of evidence; intelligence analysis; artificial intelligence; cognitive assistant; discovery; abduction; deduction; induction; abstraction; substance-blind classification; relevance; believability; inferential force; inferential weight; assumption; evidence-based reasoning.

DOI: 10.1504/IJIDSS.2014.059976

International Journal of Intelligent Defence Support Systems, 2014 Vol.5 No.2, pp.146 - 172

Published online: 25 Jul 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article