Facility Identification via Networks with Adaptive Links - FINAL

Repetitive crimes, such as the production of improvised explosive devices (IEDs) or the supplying of illegal drugs, present a growing challenge to society. Physical structures that can support these crimes provide potentially important invariants. The crimes must be situated somewhere, and the physical structures present in any given location change slowly. Knowledge of those structures and their capabilities is a lens on their operations. To inspect and detect predictive patterns in enemy supply chains is demonstrably beyond the capability of analysts; it requires computational models. Facility Identification via Networks with Adaptive Links (FINAL), the envisioned product of this SBIR, is a unique tool that will aid analysts in finding facilities associated with adversarial actions and discovering the intent for their use. FINAL is based on previously developed technology that performs probabilistic network pattern identification based on partial knowledge about network nodes, links, and their attributes. Assisted by a knowledge base of physical structures, FINAL will create hypothesis networks by combining networks of data describing actual conditions and more abstract network models of repetitive crimes