基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别

针对低截获概率(LPI)雷达信号识别率低且特征提取困难的问题，该文提出一种基于Choi-Williams分布(CWD)和栈式稀疏自编码器(sSAE)的自动分类识别系统。该系统从反映信号本质特征的时频图像入手，首先对LPI雷达信号进行CWD时频分析，获取2维时频图像；然后对得到的时频原始图像进行预处理，并把预处理后的图像送入多层稀疏自编码器(SAE)进行离线训练；最后把SAE自动提取的特征输入softmax分类器，实现雷达信号的在线分类识别。仿真结果表明，信噪比为时，该系统对8种LPI雷达信号(LFM, BPSK, Costas, Frank和T1~T4)的整体平均识别率达到96.4%，在低信噪比条件下明显优于人工设计提取信号特征的识别方法。

Low Probability of Intercept Radar Signal Recognition Based on Stacked Sparse Auto-encoder

In order to solve the problem that the correct recognition rate of Low Probability of Intercept (LPI) radar signal is low and the feature extraction is difficult, an automatic classification and recognition system based on Choi-Williams Distribution (CWD) and stacked Sparse Auto-Encoder (sSAE) is proposed. The system starts from the time-frequency image which reflects the essential characteristics of the signal. Firstly, the CWD is performed on the LPI radar signal to obtain the two-dimensional time-frequency image. Then, the obtained time-frequency original image is preprocessed and the preprocessed image is sent into the multilayer SAE for off-line training. Finally, the feature automatically extracted from the SAE is sent to the softmax classifier, to achieve on-line classification and identification of the radar signal. Simulation results show that the classification system achieves overall correct recognition rate of 96.4% at SNR of for the eight LPI radar signals (LFM, BPSK, Costas, Frank and T1~T4), which is better than the method of manually designing the extract signal characteristics under low SNR conditions.