Key result
A hybrid CNN/RNN-based scheme outperformed CNN-based and conventional spectrogram-based schemes for detecting frequency-hopping signals in simulations.
Why the study?
Detection of frequency-hopping signals is challenging when the hopping rate is unknown, and conventional spectrogram-based schemes are limited by the time-frequency resolution trade-off and spectral leakage.
A hybrid CNN/RNN-based scheme improves the detection of frequency-hopping signals by mitigating time-frequency resolution trade-offs and spectral leakage.
Simulation evidence supports hybrid deep learning for signal detection; leaves open real-world validation in operational networks.
Detection of the frequency-hopping (FH) signal is challenging when the hopping rate is unknown. Conventional spectrogram-based schemes can detect FH signals, but its performance is limited by the time-frequency resolution trade-off and spectral leakage. To alleviate this issue, we design convolutional neural network (CNN) and hybrid CNN/recurrent neural network (RNN)-based schemes. The CNN-based scheme alleviates spectral leakage by using feature maps. The hybrid CNN/RNN-based scheme mitigates the time-frequency resolution trade-off by using feature maps extracted from spectrograms of various window lengths. In simulations, the hybrid CNN/RNN-based scheme is shown to outperform the CNN-based and conventional detection schemes.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2020) studied Frequency-hopping signal detection. Hybrid CNN/RNN-based scheme vs. CNN-based and conventional spectrogram-based schemes was evaluated on Detection performance. A hybrid CNN/RNN-based scheme outperformed CNN-based and conventional spectrogram-based schemes for detecting frequency-hopping signals in simulations.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: