基于深度残差适配网络的通信辐射源个体识别

doi:10.12305/j.issn.1001-506X.2021.03.02

摘要/Abstract

摘要：

为解决通信辐射源识别中传统的人工特征提取方法鲁棒性不足和深度学习方法需要大量带标签目标域数据的问题, 提出一种基于深度残差适配网络的通信辐射源个体识别方法。应用深度学习技术实现从源域到目标域上的迁移识别, 只需要将带标签的源域数据和无标签的目标域数据进行训练。原始通信辐射源信号经过预处理后输入网络训练, 将源域和目标域的分布差异和网络的损失函数作为优化目标, 反复迭代得到最终模型。在实际采集的通信辐射源数据集上的实验结果证明了该方法的可行性和有效性。

关键词: 辐射源个体识别, 深度学习, 迁移学习, 特征提取

Abstract:

In order to solve the problem that the traditional artificial feature extraction method is not robust enough and the deep learning method needs a large number of labeled target domain data, a communication transmitter individual identification method based on deep residual adaptation network is proposed. Applying deep learning technology to realize the transfer recognition from the source domain to the target domain only needs to train the labeled source domain data and the unlabeled target domain data. The original communication emitter signal is input into the network training after preprocessing. The distribution difference between the source domain and the target domain and the loss function of the network are taken as the optimization objectives, and the final model is obtained by iteration. The experimental results on the actual communication emitter data set show that the method is feasible and effective.

Key words: transmitter individual identification, deep learning, transfer learning, feature extraction

中图分类号:

TN911.7

陈浩, 杨俊安, 刘辉. 基于深度残差适配网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2021, 43(3): 603-609.

Hao CHEN, Jun'an YANG, Hui LIU. Communication transmitter individual identification based on deep residual adaptation network[J]. Systems Engineering and Electronics, 2021, 43(3): 603-609.

图/表 10

图1

图2

表1

图3

图4

表2

表3

图5

图6

图7

参考文献 23

1	LANGLEY L E. Specific emitter identification (SEI) and classical parameter fusion technology[C]//Proc.of WESCON, 1993: 377-381.
2	KLEIN R W, TEMPLE M A, MENDENHALL M J, et al. Sensitivity analysis of burst detection and RF fingerprinting classification performance[C]//Proc.of the IEEE International Conference on Communications, 2009.
3	蔡忠伟. 基于双谱的通信辐射源个体识别[J]. 通信学报, 2007, 28 (2): 75- 79.
	CAI Z W . Study of transmitter individual identification based on bispectra[J]. Journal on Communications, 2007, 28 (2): 75- 79.
4	ZHANG X D , SHI Y , BAO Z . A new feature vector using selected bispectra for signal classification with application in radar target recognition[J]. IEEE Trans.on Signal Processing, 2001, 49 (9): 1875- 1885. doi: 10.1109/78.942617
5	任东方, 张涛, 韩洁, 等. 基于ITD与纹理分析的特定辐射源识别方法[J]. 通信学报, 2017, 38 (12): 160- 168. doi: 10.11959/j.issn.1000-436x.2017299
	REN D F , ZHANG T , HAN J , et al. Specific emitter identification based on ITD and texture analysis[J]. Journal on Communications, 2017, 38 (12): 160- 168. doi: 10.11959/j.issn.1000-436x.2017299
6	WONG L J. On the use of convolutional neural networks for specific emitter identification[D]. Virginia: Virginia Polytechnic Institute and State University, 2018.
7	WU Q , FERES C , KUZMENKO D , et al. Deep learning based RF fingerprinting for device identification and wireless security[J]. Electronics Letters, 2018, 54 (24): 1405- 1407. doi: 10.1049/el.2018.6404
8	PAN Y W , YANG S H , PENG H , et al. Specific emitter identification based on deep residual networks[J]. IEEE Access, 2019, 7, 54425- 54434. doi: 10.1109/ACCESS.2019.2913759
9	黄健航, 雷迎科. 基于深度学习的通信辐射源指纹特征提取算法[J]. 信号处理, 2018, 34 (1): 31- 38.
	HUANG J H , LEI Y K . An individual communication transmitter fingerprint feature extraction algorithm based on deep learning[J]. Signal Processing, 2018, 34 (1): 31- 38.
10	HU J, LU J, TAN Y P. Deep transfer metric learning[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 325-333.
11	ZHANG J, DING Z W, LI W Q, et al. Importance weighted adversarial nets for partial domain adaptation[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 8156-8164.
12	YANG P , GAO W . Information-theoretic multi-view domain adaptation: a theoretical and empirical study[J]. Journal of Artificial Intelligence Research, 2014, 49, 501- 525. doi: 10.1613/jair.4190
13	SHAFIK R A , YANG S , DAS A , et al. Learning transfer-based adaptive energy minimization in embedded systems[J]. IEEE Trans.on Computer-aided Design of Integrated Circuits and Systems, 2015, 35 (6): 877- 890.
14	LIU Z , YANG J A , LIU H , et al. Transfer learning by sample selection bias correction and its application in communication specific emitter identification[J]. Journal of Communications, 2016, 11 (4): 417- 427.
15	LONG M S, WANG J M. Learning transferable features with deep adaptation networks[C]//Proc.of the International Conference on Machine Learning, 2015: 97-105.
16	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc.of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
17	GRETTON A, SEJDINOVIC D, STRATHMANN H, et al. Optimal kernel choice for large-scale two-sample tests[C]//Proc.of the Advances in Neural Information Processing Systems, 2012: 1205-1213.
18	龙明盛.迁移学习问题与方法研究[D].北京: 清华大学, 2014.
	LONG M S. Transfer learning: problem and methods[D]. Beijing: Tsinghua University, 2014.
19	RUBNER Y , TOMASI C , GUIBAS L J . The earth mover's distance as a metric for image retrieval[J]. International Journal of Computer Vision, 2000, 40 (2): 99- 121. doi: 10.1023/A:1026543900054
20	YOSINSKI J , CLUNE J , BENGIO Y , et al. How transferable are features in deep neural networks?[J]. Advances in Neural Information Processing Systems, 2014, 27, 3320- 3328.
21	ZHANG J W , WANG F G , DOBRE O A , et al. Specific emitter identification via Hilbert-Huang transform in single-hop and relaying scenarios[J]. IEEE Trans.on Information Forensics and Security, 2016, 11 (6): 1192- 1205. doi: 10.1109/TIFS.2016.2520908
22	UDIT S , NIKITA T , GAGARIN B , et al. Specific emitter identification based on variational mode decomposition and spectral features in single hop and relaying scenarios[J]. IEEE Trans.on Information Forensics and Security, 2018, 14 (3): 581- 591.
23	PAN S J , TSANG I W , KWOK J T , et al. Domain adaptation via transfer component analysis[J]. IEEE Trans.on Neural Networks, 2011, 22 (2): 199- 210. doi: 10.1109/TNN.2010.2091281

信号参数	参数值
信号载频/MHz	450, 512
调制方式	8 PSK
信号带宽/MHz	2
采样率/MHz	3.84
信噪比/dB	大于15
信号长度	约等于8×10⁶

算法	f₀/MHz
算法	450→512	512→450
EMD	54.2	49.4
ITD	57.2	60.8
VMD	62.8	57.6
TCA_EMD	49.6	45.2
TCA_ITD	52.8	51.6
TCA_VMD	52.6	55.2
LSTM	24.4	20.8
ResNet	68.2	64.8
DRAN	97.6	91.8

算法	f₀/MHz
算法	450→512	512→450
DRAN(目标域无标签)	97.6	91.8
DRAN(目标域有标签)	99.8	99.6

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	杨立儒, 刘永祥, 杨威. 基于迁移学习的雷达杂波幅度统计模型选择[J]. 系统工程与电子技术, 2022, 44(8): 2457-2467.
[3]	马泽煊, 李进, 路艳丽, 陈晨. 融合WaveNet和BiGRU的网络入侵检测方法[J]. 系统工程与电子技术, 2022, 44(8): 2652-2660.
[4]	李郝亮, 陈思伟, 王雪松. 海面角反射器的极化旋转域特性研究[J]. 系统工程与电子技术, 2022, 44(7): 2065-2073.
[5]	张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.
[6]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[7]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[8]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[9]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[10]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[11]	周晓玲, 张朝霞, 鲁雅, 王倩, 王琨琨. 基于改进R-FCN的SAR图像识别[J]. 系统工程与电子技术, 2022, 44(4): 1202-1209.
[12]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[13]	何立, 沈亮, 李辉, 王壮, 唐文泉. 强化学习中的策略重用: 研究进展[J]. 系统工程与电子技术, 2022, 44(3): 884-899.
[14]	吴涛, 王伦文, 朱敬成. 基于迁移学习和注意力机制的伪装图像分割[J]. 系统工程与电子技术, 2022, 44(2): 376-384.
[15]	姚云翔, 陈莹. 注意力机制下双模态交互融合的目标跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 410-419.