Authors: Tarik Crnovrsanin, Chris Muelder, Kwan-Liu Ma
Abstract: Analysis of radio transmissions is vital for military defense as it provides valuable information about enemy communication and infrastructure. One challenge to the data analysis task is that there are far too many signals for analysts to go through by hand. Even typical signal meta data (such as frequency band, duration,and geographic location) can be overwhelming. In this paper, we present a system for exploring and analyzing such radio signal meta-data. Our system incorporates several visual representations for signal data, designed for readability and ease of comparison, as well as novel algorithms for extracting and classifying consistent signal patterns. We demonstrate the effectiveness of our system using data collected from real missions with an airborne sensor platform.