| Summary: | The goal of radar emitter recognition (RER) is to extract the features of the received emitter signal. This has become a critical issue as new radar types are emerging, and the electromagnetic environment is becoming denser and more complex. Deep neural networks (DNNs) have recently proven effective for emitter identification; however, the recognition of phase-coded waveforms at a low signal to noise ratio (SNR) remains challenging. In this paper, a novel phase-based RER approach using short time fourier transform (STFT) and bidirectional long short term memory (BiLSTM) is proposed, while enhancing the ability to learn features from noisy signals. The phase spectrum of phase-coded signals was analyzed in contrast to the amplitude spectrum used in state-of-the-art approaches in the literature. The derived phase-based features were directly provided as inputs to the proposed BiLSTM architecture. The fully connected layer follows the BiLSTM layer. Finally, a softmax classifier was employed to accomplish the recognition task. Six distinct types of phase-coded waveforms degraded by additive white gaussian noise (AWGN) with SNRs ranging from −8 dB to 8 dB were simulated. The method proposed in this research involves simple pre-processing and exhibits an overall recognition accuracy of more than 90% at SNR of −2 dB.
|
|---|