Expedition Technology, Inc. (EXP) announces a Phase 2 Small Business Innovative Research (SBIR) award for continued development of a neural network-based technique to mitigate the effects of saturation and clipping on data received from high-rate, direct-sampling analog to digital converters for the Office of Naval Research (ONR). The effort, named Fast Recovery of Signal Estimates using Neural Networks (FROSENN), develops machine learning (ML)-based techniques to address the recovery of corrupted signals due to saturation and digitization effects resulting from wideband signal collection.
This builds upon Phase 1 development that demonstrated a degraded signal passed through the FROSENN network can recover a significant percentage of the performance gap between the distorted and undistorted signal. This represents a significant improvement in demodulation quality and serves as proof-of-concept for a Neural Network based estimator for improving these saturated signals.
“Maritime domain situational awareness is becoming an increasingly difficult problem, largely due to the pace of technological advancement and the rapid proliferation of low-cost communications equipment and small radars,” says EXP Senior Business Lead Bob Smarrelli. “The US Navy’s surface ships, aircraft, and submarines that operate in this environment require a more robust approach in order to properly characterize and exploit the RF spectrum, and FROSENN will address this need by developing modern ML techniques to benefit our maritime forces.”
