Research on Radar Signal Fingerprint Identification Based on Wavelet Packet Energy Features
Yuwen Tang, Boya Li, Liu Fei, Jun Shu Han · 2024
In order to achieve radar signal fingerprint identification with lower sampling rate and computational cost, this paper proposes a radar identification method based on wavelet packet energy features. Firstly, normalize the amplitude of the collected signal to eliminate the influence of receiving distance on identification performance. Then, extract the wavelet packet transform features of the signal and normalize them. Finally, use SVM for identification. The experimental results show that when the sampling rate is 40MHz and SNR=OdB, the identification rate of simulated radar signals from four software defined radio devices of the same model and manufacturer is close to 80%. When SNR> 1 OdB, the identification rate exceeds 90%.