Deep Learning Based Radio-Signal Identification With Hardware Design

This paper proposes a deep learning based intelligent method for detecting and identifying radio signals considering two applications: first, cognitive radar for identifying micro unmanned aerial systems and second, an automated modulation classification scheme for cognitive radio, which can be used for aeronautical communication systems. Our proposed intelligent method is designed of a spectral correlation function based feature extractor and a low-complexity deep belief network classifier with low FPGA logic utilization.