Intelligence analysts and military decision makers are faced with an onslaught of information. From the now ubiquitous presence of intelligence, surveillance, and reconnaissance (ISR) platforms providing large volumes of sensor data, to vast amounts of open source data in the form of news reports, blog postings, or social media postings, the amount of information available to a modern decision maker is staggering. Whether tasked with leading a military campaign or providing support for a humanitarian mission, being able to make sense of all the information available is a challenge. Due to the volume and velocity of this data, automated tools are required to help support reasoned, human decisions. In this paper we describe several automated techniques that are targeted at supporting decision making. Our approaches include modeling the kinematics of moving targets as motifs; developing normalcy models and detecting anomalies in kinematic data; automatically classifying the roles of users in social media; and modeling geo-spatial regions based on the behavior that takes place in them. These techniques cover a wide-range of potential decision maker needs.
Today's Warfighter requires new capabilities that reduce the kill chain timeline. The capability to maintain track on mobile Time Sensitive Targets (TSTs) throughout the entire targeting cycle is a step towards that goal. Continuous tracking provides strike assets with high confident, actionable, targeting information, which reduces the time it takes to reacquire the target prior to prosecution. The Defense Advanced Research Program Agency (DARPA) Dynamic Tactical Targeting (DTT) program is developing new sensor resource management and data fusion technologies for continuous coordination of tactical sensor resources to detect and identify mobile ground targets and maintain track on these known high-value targets. An essential concept of the DTT approach is the need for the fusion system and the resource manager to operate as part of a closed loop process that produces optimum collection plans against the designated high value TSTs. In this paper, we describe this closed loop approach used within the DTT system. The paper also describes other aspects of the DTT program, including overall program status, the DTT distributed architecture, details of the fusion and dynamic sensor management components, and concludes with current evaluation results.