Context Oriented Subject Matter Intelligence Capture (COSMIC)

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N00014-09-M-0202
Agency Tracking Number: N091-076-0535
Amount: $70,000.00
Phase: Phase I
Program: SBIR
Awards Year: 2009
Solicitation Year: 2009
Solicitation Topic Code: N091-076
Solicitation Number: 2009.1
Small Business Information
1235 South Clark Street, Suite 400, Arlington, VA, 22202
DUNS: 036593457
HUBZone Owned: N
Woman Owned: N
Socially and Economically Disadvantaged: N
Principal Investigator
 Jonathan Day
 Senior Engineer
 (703) 414-5015
 jonathan.day@dac.us
Business Contact
 Kelly McClelland
Title: Senior Engineer
Phone: (703) 414-5024
Email: kelly.mcclelland@dac.us
Research Institution
N/A
Abstract
In an insurgency — a type of conflict characterized as a “learning contest” due to the extreme flexibility and adaptability of insurgent tactics and operations — the force that is able to perform the most thorough and rapid exploitation of its intelligence data will gain an important advantage. This learning contest provides a sharp contrast to a static form of the same problem. Because the enemy is constantly changing their tactics, a learning contest requires tools and systems that can re-solve and readjust solutions on an ongoing basis. The DAC Team’s unique approach to the problem of winning the learning contest combines the creativity, experience and intuition of SMEs with our powerful suite of data mining, machine learning and social network modeling algorithms. The system we propose to develop under this SBIR effort will foster a partnership between the human expert and our advanced ML algorithms that amplifies the capabilities of both. To develop an innovative and multi-disciplinary social network modeling service we have assembled a team whose background matches the problem space. Under our Content-Oriented Subject Matter Intelligence Capture (COSMIC) approach to social network analysis and modeling, SME activity is divided into three broad phases: Discovery of the information present in the available data, Probabilistic Modeling of social networks and Analysis using the models to understand the current situation and predict future events. The result is an accelerated inductive reasoning and learning process that produces automatable, expressive, high-fidelity social models of the battlespace.

* Information listed above is at the time of submission. *

Agency Micro-sites

SBA logo
Department of Agriculture logo
Department of Commerce logo
Department of Defense logo
Department of Education logo
Department of Energy logo
Department of Health and Human Services logo
Department of Homeland Security logo
Department of Transportation logo
Environmental Protection Agency logo
National Aeronautics and Space Administration logo
National Science Foundation logo
US Flag An Official Website of the United States Government