用于雷达信号异常检测的残差神经网络自动编码器

ResNet-AE for Radar Signal Anomaly Detection.

作者信息

Cheng Donghang, Fan Youchen, Fang Shengliang, Wang Mengtao, Liu Han

机构信息

School of Space Information, Space Engineering University, Beijing 101416, China.

出版信息

Sensors (Basel). 2022 Aug 19;22(16):6249. doi: 10.3390/s22166249.

DOI:10.3390/s22166249

PMID:36016010

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9416614/

Abstract

Radar signal anomaly detection is an effective method to detect potential threat targets. Given the low of the traditional AE model and the complex network of GAN, an anomaly detection method based on ResNet-AE is proposed. In this method, CNN is used to extract features and learn the potential distribution law of data. LSTM is used to discover the time dependence of data. ResNet is used to alleviate the problem of gradient loss and improve the efficiency of the deep network. Firstly, the signal subsequence is extracted according to the pulse's rising edge and falling edge. Then, the normal radar signal data are used for model training, and the mean square error distance is used to calculate the error between the reconstructed data and the original data. Finally, the adaptive threshold is used to determine the anomaly. Experimental results show that the recognition of this method can reach more than 85%. Compared with AE, CNN-AE, LSTM-AE, LSTM-GAN, LSTM-based VAE-GAN, and other models, is increased by more than 4%, and it is improved in , , 1-score, and AUC. Moreover, the model has a simple structure, strong stability, and certain universality. It has good performance under different SNRs.

摘要

雷达信号异常检测是检测潜在威胁目标的有效方法。鉴于传统自编码器（AE）模型的局限性以及生成对抗网络（GAN）的复杂网络结构，提出了一种基于残差网络自编码器（ResNet-AE）的异常检测方法。在该方法中，卷积神经网络（CNN）用于提取特征并学习数据的潜在分布规律。长短期记忆网络（LSTM）用于发现数据的时间依赖性。残差网络（ResNet）用于缓解梯度消失问题并提高深度网络的效率。首先，根据脉冲的上升沿和下降沿提取信号子序列。然后，使用正常雷达信号数据进行模型训练，并使用均方误差距离来计算重建数据与原始数据之间的误差。最后，使用自适应阈值来确定异常。实验结果表明，该方法的识别率可达85%以上。与AE、CNN-AE、LSTM-AE、LSTM-GAN、基于LSTM的变分自编码器生成对抗网络（VAE-GAN）等模型相比，识别率提高了超过4%，并且在召回率、精确率、F1分数和曲线下面积（AUC）方面都有所提升。此外，该模型结构简单，稳定性强，具有一定的通用性。在不同信噪比下均具有良好的性能。