MIDW-Net: A multi-tasking network architecture for radar intra-pulse parameter description

The automatic modulation recognition (AMR) of radar signals has become a popular research topic in recent years. However, most algorithms focus on the type of signal modulation and lack further understanding of the signal. To address this gap, a network architecture for multi-tasking intra-pulse description words (MIDW-Net) is proposed herein. In this framework, the denoising algorithm employs a convolutional denoising autoencoder, which is an effective method for suppressing noise interference and preserving signal information. The multiscale feature-extraction capability of a feature pyramid network (FPN) is utilized to expand the perceptual domain without losing the high-frequency features of the image. Finally, AMR and modulation parameter estimation are accomplished via multitask learning. Experiments performed on simulated radar signals using four intra-pulse descriptors verified the effectiveness of the proposed algorithm.