Research Projects
Current Research Projects
-
$156,150 personal allocation of awards totaling $800,000
A Computational Theory of Intelligence Analysis
PI: Gheorghe Tecuci, Co-PI: David Schum, Mihai Boicu
Intelligence analysts face the highly complex task of drawing defensible and persuasive conclusions from masses of evidence of all kinds from a variety of different sources. Arguments, often stunningly complex, requiring both imaginative and critical reasoning, are necessary in order to establish and defend the three major credentials of evidence: its relevance, believability, and inferential force or weight. Additionally, the analysts may be required to answer questions that are of immediate interest and that do not allow often without having time for extensive research and deliberation. The objective of this multidisciplinary research project is to develop a Computational Theory of Intelligence Analysis, which will be at the basis of advanced cognitive assistants that will facilitate the highly complex intelligence analysis education and practice. The envisioned theory will be based on a general, systematic, and unifying approach to intelligence analysis which is viewed as ceaseless discovery in a non-stationary world involving three concurrent processes: evidence in search of hypotheses (through abductive reasoning); hypothesis in search of evidence (through deductive reasoning); evidential tests of hypotheses (through inductive reasoning).
PTT-Tutor: Web-based intelligent agent for training residents in pediatric telephone triage
PI: Mihai Boicu, Co-PI: D. Ascher, K. Donnelly, F. Garner, D. Goldberg
The main goal of this project is to research and develop a learning agent (software system) for training residents in performing safe and cost-effective pediatric telephone triage. This system, called the PTT-Tutor, will form the basis of a follow-on project for developing a learning agent that will provide personalized triage advice and education to parents. This will serve as a pilot study to demonstrate the usefulness of the learning agent technology in developing learning agents for personalized health-care practice and education.
Recognizing the importance of pediatric telephone triage for resident and junior doctors, the Pediatric Residency Review Committee (RRC) of Inova Fairfax Hospital for Children (IFHC), which establishes the requirements for specialty training in Pediatrics, requires Programs to train future primary care pediatricians in these skills. However, the opportunities to achieve this training within the scope of the program are currently limited by several factors, including (a) resident work hour limitations; (b) language barriers, particularly for the Medicaid population, which is predominantly Spanish-speaking; and (c) the necessity for the resident and faculty to be proximate to allow timely supervision of the resident’s delivered advice (Donnelly, 2010).
Previous Research Projects
-
$1,424,004 personal allocation from awards totaling $4,313,358
Intelligent Software Agent for Training Intelligence Analysts
Contact me for more information
Disciple Technologies for Development, Utilization, and Maintenance of Regulatory Knowledge Bases (Phase 2)
PI: Gheorghe Tecuci, Co-PI: Mihai Boicu
Agent Learning for Mixed-initiative Knowledge Acquisition
PI: Gheorghe Tecuci, Co-PI: Mihai
Boicu
C4T Support to DCGS-Marine Corps
PI: Mihai Boicu
Intelligent Assistants for Distributed Knowledge Acquisition, Integration, Validation, and Maintenance
PI: Gheorghe Tecuci, Co-PI: Mihai
Boicu
Disciple Technologies for Development, Utilization, and Maintenance of Regulatory Knowledge Bases (Phase 1)
PI: Gheorghe Tecuci, Co-PI: Mihai Boicu
Personal Cognitive Assistants for Military Intelligence Analysis: Mixed-Initiative Learning, Tutoring, and Problem Solving
Contact me for more information
Virtual Experts for Multi-Domain Collaborative Planning
Contact me for more information
Research Assistant as part of the following Grants of the Learning Agents Laboratory
2000-2003: | Collaborative Assistant
for Rapid Knowledge Formation and Reasoning, F30602-00-2-0546, as part of the Rapid Knowledge Formation program, Sponsor: Defense Advanced Research Projects Agency and Air Force Research Laboratory, Air Force Material Command, USAF |
2000-2003: | Mixed-Initiative
Knowledge Base Development, F49620-00-1-0072, Sponsor: Air Force Office of Scientific Research |
2001-2003: | Intelligent Agents for Center of
Gravity Analysis, Sponsor: US Army War College |
1997-2000: | Constructing and Refining Knowledge
Bases: A Cooperative Apprenticeship Multistrategy Learning
Approach, F49620-97-1-0188, as part of the High Performance Knowledge Bases program. Sponsor: Air Force Office of Scientific Research and Defense Advanced Research Projects Agency |
1998: | Workaround Reasoning, Sponsor: Alphatech |