Network-Based Truth Maintenance System for Trustworthy Battlefield Information Processing

"The growing digitization of the battlefield gives the intelligence analyst a unique opportunity to access large amounts of information collected over time across a variety of sensors to achieve an unparalleled level of situation awareness. However, beforeusing this array of dynamically changing information, the data must be correlated and fused, and, most of all, managed in a truth maintenance system (TMS) ensuring logical data consistency. Under Phase I, we formalized a Bayesian belief network approachthat focuses truth maintenance only on the portions of the fused data relevant to the current assessment task. Each network was constructed to assess a specific high-level situation in the form of the commander's priority intelligence requirement (PIR). Wedeveloped a limited-scope prototype, which was demonstrated using a SASO (Stability and Support Operations) scenario.For Phase II, we propose a full-scope development of a Network-Based Truth Maintenance System (NTMS). The truth maintenance functionality will be enhanced to cover a broader battlefield information database based on the verification of user-definedconstraints. An enhanced network sensitivity analysis will also isolate a group of nodes associated with inconsistency. We are specifically targeting to transition our TMS technology to CECOM's Agile Commander ATD."