Fast Recovery Of Signal Estimates using Neural Networks (FROSENN)

Current automated RF signal acquisition and analysis systems and traditional information discovery methods struggle to keep up as the signal density continues to increase and new signals of interest (SOI) spread across the globe. In this environment, a communications link can be affected by multi-path scattering and therefore the Bit Error Rate (BER) of the link fluctuates over time with the movement of the transmitter or the receiver. Furthermore, maintaining reliable communication links in dense signal environments becomes especially challenging where strong and weak signals mingle close to each other in frequency. This condition is exacerbated as the Instantaneous Bandwidth (IBW) of the receiver becomes wider and bit-depth is reduced, making it vulnerable to saturation and clipping. To counteract these effects, Expedition Technology, Inc. (EXP) is proposing Fast Recovery Of Signal Estimates using Neural Networks (FROSENN). FROSENN will be able to reduce re-acquisition time of signals that are dropped due to deep-fading and estimate and predict the lost signal using Machine Learning Algorithms (MLAs). In addition, these MLAs will counter saturation effects by separating the interfering signals and any intermodulation products from the desired SOI(s). Figure 1 illustrates the high level architecture of FROSENN.