Whereas machine processing algorithms for low-level data fusion has made significant progress in recent years, Human-in-Loop aids to help the human in the OODA (Observe, Orient, Decide & Act) Loop for situational awareness fusion process, has not made as much progress. In this project we propose a human-machine collaboration mode solution, Expozé-Aware which uses clustering technology to condense huge amounts of data to understandable pieces of information chunks which can lead to identification of actionable intelligence for space situation awareness. Clustering the data can help maintain user focus at all times for achieving situational awareness even with massive amounts of data while allowing actionable information to emerge from low-level tuning/filtering of data when necessary. The vision of this project is to utilize the output from the clustering infrastructure to feed as input for various NECC-aware planning tools, whose visualizers are currently inundated with data that has not been sufficiently differentiated with respect to their relevance and salience for the mission focus.
Benefit: The value-added benefit that Expozé-Aware will bring to the intelligence analysts will not only enable analysis for law enforcement and intelligence agencies, but also other surveillance organizations in the military such as logistics and tactical planning wings for the various military institutions. In addition, Enterprise Information Integration (EII) systems are beginning to adopt an abstract semantic mediation layer to access heterogeneous data such as enterprise resource planning (ERP) and customer relationships management (CRM) applications.Expoze-Aware will provide value in these markets.
Keywords: Clustering, Actionable Intelligence, Situational Awareness, Necc-Aware Tool, Temporal And Spatial Associations, Behavioral Patterns, Threat Trigger Rules