Big RF for homeland security applications

As homeland security network deployments evolve to rely on increasingly large amounts of data from a growing variety of data sources, the ability to synthesize actionable information will become progressively more challenging. A similar problem is seen in the Information Technology (IT) domain, which is pursuing Big Data techniques to gain new insights from the relationships among the mountains of data. We believe that by applying the Big Data lessons learned in the IT world to homeland security networking and electromagnetic spectrum (EMS) problems (an application that we call 'Big RF'), networks can be made more effective and efficient, commanders can gain new understanding of behaviors, problems can be identified and rectified more quickly, and many complex network management problems currently requiring human intervention can be automated. This paper examines the parallels between Big Data problems and emerging cognitive radio and related wireless applications, appropriate Big Data tools for Big RF, new Big RF applications for homeland security networks, and other developments needed to enable warfighters, first responders, network managers, and cognitive radios to maximize the capabilities offered by Big Data applied to RF domain problems.