Intelligence Analysis as Agent-Assisted Discovery of Evidence, Hypotheses and Arguments

This paper presents a computational approach to intelligence analysis which is viewed as mixed-initiative discovery of evidence, hypotheses and arguments by an intelligence analyst and a cognitive assistant. The approach is illustrated with the analysis of wide area motion imagery of fixed geographic locations where the goal is to discover threat events such as an ambush or a rocket launch. This example is used to show how the Disciple cognitive assistants developed in the Learning Agents Center can help the analysts in coping with the astonishing complexity of intelligence analysis.

[1]  Gheorghe Tecuci,et al.  Seven Aspects of Mixed-Initiative Reasoning: An Introduction to this Special Issue on Mixed-Initiative Assistants , 2007, AI Mag..

[2]  Gheorghe Tecuci,et al.  Cognitive Assistants for Evidence-Based Reasoning Tasks , 2011, AAAI Fall Symposium: Advances in Cognitive Systems.

[3]  O. Morgenthaler,et al.  Proceedings of the Conference , 1930 .

[4]  David A. Schum,et al.  Evidence and inference for the intelligence analyst , 1987 .

[5]  Gheorghe Tecuci,et al.  Substance-Blind Classification of Evidence for Intelligence Analysis , 2009 .

[6]  GHEORGHE TECUCI,et al.  Coping with the Complexity of Intelligence Analysis : Cognitive Assistants for Evidence-Based Reasoning , 2010 .

[7]  Gheorghe Tecuci,et al.  THE DISCIPLE–RKF LEARNING AND REASONING AGENT , 2005, Comput. Intell..

[8]  Disciple-LTA : Learning , Tutoring and Analytic Assistance , 2008 .

[9]  D. Schum The Evidential Foundations of Probabilistic Reasoning , 1994 .

[10]  Gheorghe Tecuci Building Intelligent Agents: An Apprenticeship, Multistrategy Learning Theory, Methodology, Tool and Case Studies , 1998 .

[11]  Gheorghe Tecuci,et al.  Agent Shell for the Development of Tutoring Systems for Expert Problem Solving Knowledge , 2008, Intelligent Tutoring Systems.

[12]  S. Toulmin The uses of argument , 1960 .

[13]  C. Weiss Communicating Uncertainty in Intelligence and Other Professions , 2008 .

[14]  Dorin Marcu,et al.  Disciple-LTA: Learning, Tutoring and Analytic Assistance 1 , 2008 .

[15]  David A. Schum,et al.  Species of Abductive Reasoning in Fact Investigation in Law , 2002 .

[16]  Nils J. Nilsson,et al.  Problem-solving methods in artificial intelligence , 1971, McGraw-Hill computer science series.

[17]  John Henry Wigmore,et al.  The Science of Judicial Proof , 1938 .

[18]  David A. Schum,et al.  Analysis of Evidence: Frontmatter , 2005 .