Acquiring Probabilistic Knowledge for Information Fusion

Acquiring probabilistic knowledge for the development of fusion models can prove to be a difficult task. In many applications, the lack of availability of historical data forces the modelers to rely extensively on expert judgment techniques which traditionally requires a large amount of manpower and is exceedingly time-consuming. Under Phase I of this effort, the DAC Team has proven the feasibility of the Semi-Automated Building and Evaluation of Relational Models (SABER) technique. SABER provides an intuitive means for the non-expert to construct probabilistic models, quantitatively evaluate them, and identify “hotspots” in the network that are highly influential. In Phase II we plan to build on our Phase I prototype and implement and test the approach in operational environments. Through our partnerships with the Air Force Special Operations Command (AFSOC) and the Army’s 9th Infantry Regiment, we have operational users that will be aligned with our design-implement-test spiral development process. The end of Phase II will result in prototype software that has been battletested in Warfighting environments and is ready for Phase III transition.