Defeating Emplaced Improvised Explosive Devices (IED) Using Fusion Algorithms

Period of Performance: 04/16/2008 - 01/20/2009

$100K

Phase 1 SBIR

Recipient Firm

SET Assoc. Corp.
1005 N. Glebe Rd.Suite 400
Arlington, VA 22201
Principal Investigator

Abstract

The proposed Potential IED Threat System Plus Plus (PITS++) is an adaptive software system that quantitatively predicts the timing and location of IED emplacements by fusing geographic and social/political/demographical features. It combines SET Corporation's IED emplacement prediction algorithm with Lehigh University's case-based reasoning expertise in order to fuse multiple data sources and make predictions. It is an extension of our previous PITS work under DTO funding that demonstrated statistically significant performance. The original PITS system uses reinforcement learning technique to predict IED threats from geographic features. PITS++ extends that work in three important ways: 1) explicitly addressing the timing of IED emplacement; 2) incorporating machine learning methods to deal with non-linearity in the system; and 3) incorporating case-based reasoning technology to consider non-geographic features. We believe the enhancements will make the PITS more robust and more accurate in its IED emplacement predictions.