基于深度置信网络和双谱对角切片的低截获概率雷达信号识别

基于深度置信网络(DBN)对信号双谱对角切片(BDS)结构特征进行学习，实现低截获概率(LPI)雷达信号识别。该方法首先建立基于受限玻尔兹曼机(RBM)的DBN模型，对LPI雷达信号的BDS数据进行逐层无监督贪心学习，然后运用后向传播(BP)机制在有监督学习方式下根据学习误差对DBN模型参数进行微调，最后基于该BDS-DBN模型实现未知信号的分类和识别。理论分析和仿真结果表明，信噪比高于8 dB时，基于BDS和DBN的识别方法对调频连续波(FMCW), Frank, Costas, FSK/PSK 4类LPI信号的综合识别率保持在93.4%以上，高于传统的主成分分析加支持向量机法(PCA-SVM)和主成分分析加线性判别分析法(PCA-LDA)。

Research on Low Probability of Intercept Radar Signal Recognition Using Deep Belief Network and Bispectra Diagonal Slice

A novel recognition algorithm for Low Probability of Intercept (LPI) radar signal based on deep learning of radar signals Bispectra Diagonal Slice (BDS) is proposed in this paper. Firstly, a Deep Belief Network (DBN) model is established on stacked Restricted Boltzmann Machines (RBM), then the model is used for layer-by-layer unsupervised greedy learning of radar signals BDS. Secondly, a Back Propagation (BP) algorithm is applied to fine tune parameters of DBN model with a supervised way according to learning error. Finally, the BDS-DBN model is constructed to classify and recognize unknown LPI signals. The theoretical analysis and the simulation results show that, the average recognition accuracy of the proposed algorithm for Frequency Modulation Continuous Wave (FMCW), Frank, Costas and FSK/PSK signals can reach 93.4% or ever higher while the SNR is better than 8 dB, which is better than that of Principal Component Analysis-Support Vector Machine (PCA-SVM) algorithm and Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA) algorithm.