Time and Accuracy Trade-Off of LPI Radar Classification Technology Based on Time-Frequency Analysis and Deep Learning

Technology for classifying low probability of intercept (LPI) radar signals with speed and accuracy is critical for cognitive communication research. We used time-frequency analysis (TFA) and deep learning to classify 12 typical LPI radar signals. Traditional methods use the Choi-Williams distribution (CWD), which requires more than 500 times longer TFA generation time than the spectrogram method. In this paper, we show the trade-off relationship between classification accuracy and detection time using a spectrogram, Wigner-Ville distribution (WVD), and CWD as the training datasets. As a result, the CWD model showed higher accuracy than the spectrogram model, but the prediction time was more than 200 times longer. The accuracy difference was only 1 %p for an SNR over −2 dB, but it reached 7.5%p for an SNR of −10 dB. Therefore, a lower SNR shows a distinct trade-off between prediction time and accuracy, depending on the type of TFA.