End‐to‐end cubic phase signal recovery method based on deep convolutional neural network

Cubic phase (CP) signal is widely used in radar and sonar signal processing and the CP signal received by the radar or sonar sensors may miss part of discrete samples and be corrupted by noise. In this study, a novel end-to-end CP signal recovery method is proposed to recover the CP signal that experiences data missing and noise corruption based on deep convolutional neural network (DCNN). Two key techniques are used in the structure design of the proposed network. The first is dilated convolution, which has a larger receptive field than the standard convolution operation and can extract information more efficiently in the CP signal recovery problem. The second is denseNet, which connects all layers directly and can alleviate the vanishing-gradient problem. Experiment results show that the proposed DCNN-based method achieves superior performance to the traditional compressed sensing-based method both from the perspective of recovery error and time consumption.