Layered Data to Areas of Interest

According to the U.S. Navy Information Dominance Roadmap, 20132028, prevailing in the 21st Century combat environments is contingent upon addressing the intensifying challenge of Battlespace Awareness and Information Dominance, i.e., upon promptly deriving enhanced information content from advanced means to rapidly sense, collect, process, analyze, evaluate and exploit intelligence about adversaries and operational environments. Currently, the exponential growth in ISR data volume severely limits manual processing of the available regional text and imagery/video datasets, necessitating the automated exploitation tools to aid systematic extraction of mission-critical Intel.To rapidly exploit very large data streams over wide areas and autonomously highlight areas of interest for tactical decisions without a priori knowledge of the area and/or location of high value, we are developing INFLECT (Intelligent Filtering for Layered Exploration with Cognitive-aid Technologies) -- a novel data-mining, correlation, and reasoning engine equipped with scalable data association, pattern-matching, and value-based filtering algorithms that automate: (1) statistical tracking of situational dynamics to extract useful knowledge, patterns, and regularities; (2) heuristic appraisal of mission-specific relevance/value of information; (3) value-based filtering, triage, fusion, and summarization of large multi-modal datasets to prioritize and highlight relevant information; and (4) multi-layered inference and semantic exploration of large text/video datasets.