A Decision Support Tool using Canonical Representations and Algorithms for Data Fusion and Information Delivery (CRA-FIND)

Members of the armed forces depend on the quality of their information for mission success. Providing high quality information requires optimizing the value of the dynamic"information economy,"where data fusion is the supply, information requirements are the demand, and information delivery is how they connect. Though data fusion, requirements capture, and information delivery are often framed as algorithm problems, lessons from industry show that information quality problems are also caused by the lack of standard mathematical models (i.e., canonical forms) for multi-level representations of information. Canonical representations link data fusion, requirements capture, and information delivery through a mathematically sound, data- and model-driven approach. We therefore propose to design and demonstrate a decision support tool using Canonical Representations and Algorithms for Data Fusion and Information Delivery (CRA-FIND) that provides a: (1) test environment for data fusion and information delivery algorithms; (2) software-instantiated method that links algorithms via canonical representations to a shareable world model, thereby improving their robustness and precision; (3) systematic method for learning the contexts under which different algorithms perform well and using this information to manage those algorithms"use; (4) general, reusable algorithm that queries the world model for information that can impact an algorithm"s outputs.