面向雷达行为识别的多尺度卷积注意力网络

熊敬伟; 潘继飞; 毕大平; 杜明洋

doi:10.19665/j.issn1001-2400.20231005

您当前的位置：

首页 >

文章列表页 >

面向雷达行为识别的多尺度卷积注意力网络

电磁空间安全专栏 | 更新时间：2024-01-22

- 面向雷达行为识别的多尺度卷积注意力网络
- 暂无标题
- 西安电子科技大学学报 2023年50卷第6期页码：62-74
- 作者机构：
  
  国防科技大学电子对抗学院,安徽合肥 230000
- 作者简介：
  
  [ "熊敬伟(1995—),男,国防科技大学硕士研究生,E-mail:[email protected];" ]
  潘继飞(1978—),男,教授,E-mail:[email protected]
  [ "毕大平(1965—),男,教授,E-mail:[email protected];" ]
  [ "杜明洋(1994—),男,讲师,E-mail:[email protected]。" ]
- 基金信息：
  
  国家自然科学基金(62071476)
- DOI：10.19665/j.issn1001-2400.20231005
  中图分类号：
扫描看全文
熊敬伟, 潘继飞, 毕大平, 等. 面向雷达行为识别的多尺度卷积注意力网络[J]. 西安电子科技大学学报, 2023,50(6):62-74.
熊敬伟, 潘继飞, 毕大平, 等. 面向雷达行为识别的多尺度卷积注意力网络[J]. 西安电子科技大学学报, 2023,50(6):62-74. DOI： 10.19665/j.issn1001-2400.20231005.

DOI：

摘要

针对低信噪比条件下雷达信号特征提取难、识别稳定性低的问题,提出了一种基于深度分组卷积、多尺度卷积和自注意力机制的雷达行为模式识别算法,在不增加训练难度的情况下提高复杂环境下的识别能力。该算法先采用深度分组卷积在浅层网络分离弱相关的通道,再通过多尺度卷积代替常规卷积实现多维特征的提取,最后利用自注意力机制调整优化不同特征图的权值,抑制低相关和负相关的通道与空间带来的影响。对比实验表明,所提MSCANet在0~50%丢失脉冲和虚假脉冲条件下平均识别率达到约92.25%,与基线网络AlexNet、ConvNet、ResNet、VGGNet相比,准确率提升了约5%~20%,不同雷达行为模式识别稳定,模型具有更好的泛化性和鲁棒性。同时,消融实验证明了深度分组卷积、多尺度卷积和自注意力机制对模式识别的有效性。

Abstract

A radar behavior mode recognition framework is proposed aiming at the problems of difficult feature extraction and low recognition stability of the radar signal under a low signal-to-noise ratio,which is based on depth-wise convolution,multi-scale convolution and the self-attention mechanism.It improves the recognition ability in complex environment without increasing the difficulty of training.This algorithm employs depth-wise convolution to segregate weakly correlated channels in the shallow network.Subsequently,it utilizes multi-scale convolution to replace conventional convolution for multi-dimensional feature extraction.Finally,it employs a self-attention mechanism to adjust and optimize the weights of different feature maps,thus suppressing the influence of low and negative correlations in both channels and the spatial domains.Comparative experiments demonstrate that the proposed MSCANet achieves an average recognition rate of 92.25% under conditions of 0~50% missing pulses and false pulses.Compared to baseline networks such as AlexNet,ConvNet,ResNet,and VGGNet,the accuracy has been improved by 5% to 20%.The model exhibits stable recognition of various radar patterns and demonstrates enhanced generalization and robustness.Simultaneously,ablation experiments confirm the effectiveness of deep grouped convolution,multi-scale convolution,and the self-attention mechanism for radar behavior recognition.

关键词

深度学习机器学习模式识别深度分组卷积多尺度卷积自注意力机制

Keywords

deep learningmachine learningmode recognitiondepth-wise convolutionmultiscale convolutionself-attention mechanism

references

刘宏伟, 水鹏朗, 孔令讲, 等. 雷达技术进展专题序言[J]. 西安电子科技大学学报, 2021, 48(2):1-6.

LIU Hongwei, SHUI Penglang, KONG Lingjiang, et al. Editorial:Introduction to the Special Issue on Advances in Radar Technology[J]. Journal of Xidian University, 2021, 48(2):1-6.

张雅荔, 李文元, 李昌禄, 等. 融合注意力引导的多尺度低照度图像增强方法[J]. 西安电子科技大学学报, 2023, 50(1):129-136.

ZHANG Yali, LI Wenyuan, LI Changlu, et al. Method for Enhancement of the Multi-Scale Low-Light Image by Combining an Attention Guidance[J]. Journal of Xidian University, 2023, 50(1):129-136.

CHEN W, CHEN B, PENG X, et al. Tensor RNN with Bayesian Nonparametric Mixture for Radar HRRP Modeling and Target Recognition[J]. IEEE Transactions on Signal Processing, 2021, 69:1995-2009. DOI:10.1109/TSP.2021.3065847http://doi.org/10.1109/TSP.2021.3065847https://ieeexplore.ieee.org/document/9380220/https://ieeexplore.ieee.org/document/9380220/

DU M, ZHONG P, CAI X, et al. DNCNet:Deep Radar Signal Denoising and Recognition[J]. IEEE Transactions on Aerospace and Electronic Systems, 2022, 58(4):3549-3562. DOI:10.1109/TAES.2022.3153756http://doi.org/10.1109/TAES.2022.3153756https://ieeexplore.ieee.org/document/9721582/https://ieeexplore.ieee.org/document/9721582/

LIU L, LI X. Unknown Radar Waveform Recognition System via Triplet Convolution Network and Support Vector Machine[J]. Digital Signal Processing, 2022, 123:103439. DOI:10.1016/j.dsp.2022.103439http://doi.org/10.1016/j.dsp.2022.103439https://linkinghub.elsevier.com/retrieve/pii/S1051200422000562https://linkinghub.elsevier.com/retrieve/pii/S1051200422000562

XU T, YUAN S, LIU Z, et al. Radar Emitter Recognition Based on Parameter Set Clustering and Classification[J]. Remote Sensing, 2022, 14(18):4468. DOI:10.3390/rs14184468http://doi.org/10.3390/rs14184468https://www.mdpi.com/2072-4292/14/18/4468https://www.mdpi.com/2072-4292/14/18/4468

于浩洋, 尹良, 李书芳, 等. 生成对抗网络小样本雷达调制信号识别算法[J]. 西安电子科技大学学报, 2021, 48(6):96-104.

YU Haoyang, YIN Liang, LI Shufang, et al. Recognition Algorithm for the Little Sample Radar Modulation Signal Based on the Generative Adversarial Network[J]. Journal of Xidian University, 2021, 48(6):96-104.

DONG Y, JIANG X, ZHOU H, et al. SR2CNN:Zero-Shot Learning for Signal Recognition[J]. IEEE Transactions on Signal Processing, 2021, 69:2316-2329. DOI:10.1109/TSP.2021.3070186http://doi.org/10.1109/TSP.2021.3070186https://ieeexplore.ieee.org/document/9392373/https://ieeexplore.ieee.org/document/9392373/

利强, 张伟, 金秋园, 等. 基于知识原型网络的小样本多功能雷达工作模式识别[J]. 电子学报, 2022, 50(6):1344-1350. DOI:10.12263/DZXB.20210932http://doi.org/10.12263/DZXB.20210932

LI Qiang, ZHANG Wei, JIN Qiuyuan, et al. Multi-Function Radar Working Mode Recognition with Few Samples Based on Knowledge Embedded Prototype Network[J]. Acta Electronica Sinica, 2022, 50(6):1344-1350. DOI:10.12263/DZXB.20210932http://doi.org/10.12263/DZXB.20210932

ZHENG S, ZHOU X, ZHANG L, et al. Toward Next-Generation Signal Intelligence:A Hybrid Knowledge and Data-Driven Deep Learning Framework for Radio Signal Classification[J]. IEEE Transactions on Cognitive Communications and Networking, 2023, 9(3):564-579. DOI:10.1109/TCCN.2023.3243899http://doi.org/10.1109/TCCN.2023.3243899https://ieeexplore.ieee.org/document/10042021/https://ieeexplore.ieee.org/document/10042021/

HAN J W, PARK C H. A Unified Method for Deinterleaving and PRI Modulation Recognition of Radar Pulses Based on Deep Neural Networks[J]. IEEE Access, 2021, 9:89360-89375. DOI:10.1109/ACCESS.2021.3091309http://doi.org/10.1109/ACCESS.2021.3091309https://ieeexplore.ieee.org/document/9461742/https://ieeexplore.ieee.org/document/9461742/

LIU H, CHENG D, SUN X, et al. Radar Emitter Recognition Based on CNN and LSTM[C]// 2021 International Conference on Neural Networks,Information and Communication Engineering.Bellingham:SPIE, 2021:1-6.

SHI F, YUE C, HAN C. A Lightweight and Efficient Neural Network for Modulation Recognition[J]. Digital Signal Processing, 2022, 123:103444. DOI:10.1016/j.dsp.2022.103444http://doi.org/10.1016/j.dsp.2022.103444https://linkinghub.elsevier.com/retrieve/pii/S1051200422000616https://linkinghub.elsevier.com/retrieve/pii/S1051200422000616

YU H H, YAN X P, LIU S K, et al. Radar Emitter Multi-Label Recognition Based on Residual Network[J]. Defence Technology, 2022, 18(3):410-417. DOI:10.1016/j.dt.2021.02.005http://doi.org/10.1016/j.dt.2021.02.005

DADGARNIA A, SADEGHI M T. Automatic Recognition of Pulse Repetition Interval Modulation Using Temporal Convolutional Network[J]. IET Signal Processing, 2021, 15(9):633-648. DOI:10.1049/sil2.v15.9http://doi.org/10.1049/sil2.v15.9https://onlinelibrary.wiley.com/toc/17519683/15/9https://onlinelibrary.wiley.com/toc/17519683/15/9

HU J, SHEN L, SUN G. Squeeze-and-Excitation Networks[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Piscataway:IEEE, 2018:7132-7141.

WOO S, PARK J, LEE J Y, et al. CBAM:Convolutional Block Attention Module[C]// Proceedings of the European Conference on Computer Vision(ECCV).Heidelberg:Springer, 2018:3-19.

秦鑫, 黄洁, 查雄, 等. 基于扩张残差网络的雷达辐射源信号识别[J]. 电子学报, 2020, 48(3):456-462. DOI:10.3969/j.issn.0372-2112.2020.03.006http://doi.org/10.3969/j.issn.0372-2112.2020.03.006

QIN Xin, HUANG Jie, CHA Xiong, et al. Radar Emitter Signal Recognition Based on Dilated Residual Network[J]. Acta Electronica Sinica, 2020, 48(3):456-462. DOI:10.3969/j.issn.0372-2112.2020.03.006http://doi.org/10.3969/j.issn.0372-2112.2020.03.006

DU X, SUN Y, SONG Y, et al. A Comparative Study of Different CNN Models and Transfer Learning Effect for Underwater Object Classification in Side-Scan Sonar Images[J]. Remote Sensing, 2023, 15(3):593. DOI:10.3390/rs15030593http://doi.org/10.3390/rs15030593https://www.mdpi.com/2072-4292/15/3/593https://www.mdpi.com/2072-4292/15/3/593

SKOLNIK M I. Radar Handbook[M]. 3rd. New York: McGraw-Hill, 2008.

GUO L, CHEN X. Low Probability of Intercept Radar Signal Recognition Based on the Improved AlexNet Model[C]// Proceedings of the 2nd International Conference on Digital Signal Processing. New York: ACM, 2018:119-124.

张焕. 基于图像处理与深度学习的典型军事目标识别[D]. 南京: 南京理工大学, 2021.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种用于点云分类的轻量级深度神经网络

一种特征融合的工作模式识别方法

一种融合纵横时空特征的交通流预测方法

自适应差分隐私的高效深度学习方案

基于隐写噪声深度提取的JPEG图像隐写分析