A Method of Radar Signal Feature Extraction Based on Fractional Fourier Transform
Chen Shiwen, Wang Gongming, Xing Xiaopeng, Huang J. Jie · 2019
Aiming at the main problems in feature extraction of new radar signals, a method of feature extraction based on Fractional Fourier Transform is proposed in this paper. By using the difference of waveforms of different signals in fractional domain, four groups of improved resemblance coefficients are extracted to form joint eigenvectors to realize automatic sorting and recognition of radar signals. The simulation results show that the extracted improved resemblance coefficient features have better separation of different classes and better anti-noise performance. When the signal-to-noise ratio is 4 dB, the overall average recognition rate of six radar signals reaches 96.3%.