If human ears could hear the electromagnetic spectrum, the noise levels these days would be overwhelming. The skyrocketing use of wireless devices in military and civilian domains has created a complicated and noisy environment, filled with signals of widely varying frequency and amplitude and a menagerie of modulations. For warfighters trying to maintain critical communications links, interpret ambiguous radar returns, or defend against electronic warfare tactics, the ability to sort through that thicket of waveforms is essential - to identify where key signals are coming from, what kind of signals they are, and how best to send and receive information via the least contested spectral bands.
In light of this problem, DARPA recently hosted the Battle of the ModRecs - a low-key competitive opportunity for engineers with a penchant for antennas and algorithms to test their skills in modulation recognition. DARPA wants scientists and engineers to rethink conventional approaches and advance the technology to new heights, so it will function dynamically and with precision - not just under laboratory conditions but in real-world scenarios.
Held for a few days in conjunction with the IEEE DySPAN conference in Baltimore, where DARPA program manager Tom Rondeau and staffers created a sort of pop-up spectrum testbed, the Battle put hand-coded, expert systems against newer, experimental systems designed to take advantage of recent advances in machine learning.
In this realistic scenario with complex waveforms, the hand-coded systems performed better than the machine-learning systems. They now have a better understanding of the state of the art and which directions to explore as they pursue their goal of more effectively managing the spectrum.
The Baltimore event was one of several related exercises planned for this year. A February hackfest hosted in Brussels, for example, focused on radio interference, and an upcoming event in the San Francisco Bay Area will focus on unmanned aerial vehicles. Through these efforts and a variety of ongoing DARPA programs, including the Spectrum Collaboration Challenge that program manager Paul Tilghman is overseeing. DARPA aims to build an improved technological capacity for spectrum-related situational awareness and help U.S. forces make better use of this powerful but limited electromagnetic resource.
