Deep Neural Networks for Radar Waveform Classification

2021/02/15 by Wharton, Michael, Pavy, Anne M., Schniter, Philip
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2102.07827

Abstract

We consider the problem of classifying radar pulses given raw I/Q waveforms in the presence of noise and absence of synchronization. We also consider the problem of classifying multiple superimposed radar pulses. For both, we design deep neural networks (DNNs) that are robust to synchronization, pulse width, and SNR. Our designs yield more than 100x reduction in error-rate over the previous state-of-the-art.

Related

• Classification of Common Waveforms Including a Watchdog for Unknown Signals
• Blind Source Separation of Radar Signals in Time Domain Using Deep Learning
• Radar Emitter Classification with Attribute-specific Recurrent Neural Networks
• One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification
• DNN Transfer Learning from Diversified Micro-Doppler for Motion\n Classification