A graph-based framework for fusion: From hypothesis generation to forensics

The intent of this paper is to show enhancements in Level 2 and 3 fusion capabilities through a new class of graph models and solution strategies. The problem today is not often lack of information, but instead, information overload. Graphs have demonstrated to be a useful framework to represent and analyze large amounts of information. Classical strategies such as Bayesian Networks, Semantic Networks and Graph Matching are some examples of the power of graphs. We will introduce two different but related graph-based structures that will allow us to span the temporal performance of decision-making processes. Given that most of the high level information fusion problems of interest are NP-Hard, there is a need to separate methodologies between "near real-time" tools and forensic heuristics. With this in mind we will introduce a real-time decision-making tool (INFERD) and a forensic graph matching algorithm (TruST).