嵌入注意力机制的通信辐射源个体识别方法

doi:10.12305/j.issn.1001-506X.2022.01.03

摘要/Abstract

摘要：

复杂电磁环境中, 针对低信噪比条件下现有神经网络识别算法对于通信电台识别准确率不高的问题, 提出一种结合双层注意力机制和残差网络的通信辐射源个体识别方法。首先, 以空间注意模块和通道注意模块构成注意力机制。其次, 在一维残差网络中嵌入双层注意力机制, 提高对关键特征的学习能力。最后, 在实际数据集上验证算法的有效性。实验证明, 相比于残差神经网络算法, 所提方法既能保持模型较好的稳定性又在数据集上有明显的提升效果。

关键词: 低信噪比, 辐射源识别, 注意力机制, 残差学习

Abstract:

In complex electromagnetic environment, a novel communication radiation source identification method combining double-deck attention mechanism and residual network is proposed to solve the problem that the existing neural network identification algorithm is not accurate enough in communication station identification under low signal to noise ratio condition.Firstly, spatial attention module and channel attention module are used to construct the attention mechanism. Secondly, a two-layer attention mechanism is embedded in the one-dimensional residual network to improve the learning ability of key features. Finally, the effectiveness of the algorithm is verified on the actual dataset.Experimental results show that, compared with the residual neural network algorithm, the proposed method not only maintains better stability of the model, but also has a significant improvement effect on the dataset.

Key words: low signal to noise ratio, radiation source identification, attention mechanism, residual learning

中图分类号:

TN911.7

曲凌志, 杨俊安, 刘辉, 黄科举. 嵌入注意力机制的通信辐射源个体识别方法[J]. 系统工程与电子技术, 2022, 44(1): 20-27.

Lingzhi QU, Junan YANG, Hui LIU, Keju HUANG. Method for individual identification of communication radiation source embedded in attention mechanism[J]. Systems Engineering and Electronics, 2022, 44(1): 20-27.

图/表 17

图1

图2

图3

图4

图5

图6

表1

表2

图7

表3

表4

表5

图8

表6

图9

表7

表8

参考文献 32

1	TALBOT K I , DULEY P R , HYATT M H . Specific emitter identification and verification[J]. Technology Review, 2003, 113.
2	BALDINI G, STERI G, GIULIANI R. Identification of wireless devices from their physical layer radio-frequency fingerprints[M]. 4th ed. Encyclopedia of Information Science and Technology. Hershey: IGI Global, 2017.
3	HUANG G Q , YUAN Y J , WANG X , et al. Specific emitter identification based on nonlinear dynamical characteristics[J]. Canadian Journal of Electrical & Computer Engineering, 2016, 39 (1): 34- 41.
4	PAN Y W, PENG H, LI T Y, et al. High-fidelity symbol synchronization for specific emitter identification[C]//Proc. of the IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference, 2019: 393-398.
5	SHIEH C S , LIN C T . A vector neural network for emitter identification[J]. IEEE Trans.on Antennas and Propagation, 2002, 50 (8): 1120- 1127. doi: 10.1109/TAP.2002.801387
6	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.
7	URETEN O , SERINKEN N . Bayesian detection of Wi-Fi transmitter RF fingerprints[J]. Electronics Letters, 2005, 41 (6): 373- 374. doi: 10.1049/el:20057769
8	HALL J, BARBEAU M, KRANAKIS E. Radio frequency fingerprinting for intrusion detection in wireless networks[C]//Proc. of the IASTED International Conference on Communications, Internet, and Information Technology, 2005.
9	YUAN Y J , HUANG Z T , WU H , et al. Specific emitter identification based on Hilbert-Huang transform-based time-frequency-energy distribution features[J]. Communications IET, 2014, 8 (13): 2404- 2412. doi: 10.1049/iet-com.2013.0865
10	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 radiation source identification method based on ITD and texture analysis[J]. Journal of Communications, 2017, 38 (12): 160- 168. doi: 10.11959/j.issn.1000-436x.2017299
11	SATIJA U , TRIVEDI N , BISWAL G , 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.
12	LI L , JI H B , JIANG L . Quadratic time-frequency analysis and sequential recognition for specific emitter identification[J]. IET Signal Processing, 2011, 5 (6): 568- 574. doi: 10.1049/iet-spr.2010.0070
13	HUANG J H , LEI Y K . Communication radio individual recognition based on semi-supervised rectangular network[J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2019, 47 (1): 1- 8.
14	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
15	ZHUO F , HUANG Y L , CHEN J . Radio frequency fingerprint extraction of radio emitter based on I/Q imbalance[J]. Procedia Computer Science, 2017, 107, 472- 477. doi: 10.1016/j.procs.2017.03.092
16	BRIK V, BANERJEE S, GRUTESER M, et al. Wireless device identification with radiometric signatures[C]//Proc. of the 14th Annual International Conference on Mobile Computing and Networking, 2008.
17	周志文, 黄高明, 王雪宝, 等. 基于联合协作表示的特定辐射源识别[J]. 系统工程与电子技术, 2019, 41 (4): 724- 729.
	ZHOU Z W , HUANG G M , WANG X B , et al. Specific radiation source identification based on joint cooperative representation[J]. Systems Engineering and Electronics, 2019, 41 (4): 724- 729.
18	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
19	WONG L J, HEADLEY W C, ANDREWS S, et al. Clustering learned CNN features from raw I/Q data for emitter identification[C]//Proc. of the IEEE Military Communications Confe-rence, 2019.
20	ZHANG M , DIAO M , GUO L M . Convolutional neural networks for automatic cognitive radio waveform recognition[J]. IEEE Access, 2017, 5, 11074- 11082. doi: 10.1109/ACCESS.2017.2716191
21	WEST N E, O'SHEA T. Deep architectures for modulation recognition[C]//Proc. of the IEEE International Symposium on Dynamic Spectrum Access Networks, 2017.
22	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
23	DING L D , WANG S L , WANG F G , et al. Specific emitter identification via convolutional neural networks[J]. IEEE Communications Letters, 2018, 22 (12): 2591- 2594. doi: 10.1109/LCOMM.2018.2871465
24	周东青, 王玉冰, 王星, 等. 基于深度限制波尔兹曼机的辐射源信号识别[J]. 国防科技大学学报, 2016, 38 (6): 136- 141.
	ZHOU D Q , WANG Y B , WANG X , et al. Radiation source signal identification based on depth limit boltzmann machine[J]. Journal of National University of Defense Technology, 2016, 38 (6): 136- 141.
25	刘高辉, 张晓博. 一种基于深度置信网络的通信辐射源个体识别方法[J]. 电波科学学报, 2020, 35 (3): 395- 403.
	LIU G H , ZHANG X B . An individual identification method of communication radiation source based on deep confidence network[J]. Journal of Radio Science, 2020, 35 (3): 395- 403.
26	吴子龙, 陈红, 雷迎科, 等. 基于堆栈式LSTM网络的通信辐射源个体识别[J]. 系统工程与电子技术, 2020, 42 (12): 2915- 2923. doi: 10.3969/j.issn.1001-506X.2020.12.30
	WU Z L , CHEN H , LEI Y K , et al. Individual identification of communication radiation source based on stack LSTM network[J]. Systems Engineering and Electronics, 2020, 42 (12): 2915- 2923. doi: 10.3969/j.issn.1001-506X.2020.12.30
27	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.
	CHEN H , YANG J A , LIU H . Individual identification of communication radiation sources based on deep residual adaptive network[J]. Systems Engineering and Electronics, 2021, 43 (3): 603- 609.
28	BALDINI G , GENTILE C , GIULIANI R , et al. Comparison of techniques for radiometric identification based on deep convolutional neural networks[J]. Electronics Letters, 2019, 55 (2): 90- 92. doi: 10.1049/el.2018.6229
29	WOO S, PARK J, LEE J, et al. CBAM: convolutional block attention module[C]//Proc. of the European Conference on Computer Vision, 2018: 3-19.
30	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.
31	HE K M, ZHANG X Y, REN S Q, et al. Delving deep into rectifiers: surpassing human-level performance on imagenet classification[C]//Proc. of the IEEE International Conference on Computer Vision, 2015: 1026-1034.
32	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, 2017, 11 (6): 1192- 1205.

网络结构	输出维度	网络结构	输出维度
输入层	2×8 192	一维残差堆栈4	512×256
卷积层	64×4 096	注意力单元	512×256
注意力单元	64×4 096	池化层	512×1
池化层	64×2 048	平坦层	512
一维残差堆栈1	64×2 048	全连接层	8
一维残差堆栈2	128×1 024	归一化层	8
一维残差堆栈3	256×512	-	-

信号参数	参数值
epoch	200
batchsize	64
学习率	1e-3
优化器	Adam
损失函数	Cross Entropy

信号参数	参数值
信号载频/MHz	450~460
调制方式	QPSK
业务模式	数传
码速率/Kbps	256
采样率/MHz	50
电台功率/W	0.125

信号参数	参数值
信号载频/MHz	450;512
调制方式	8 PSK
码速率/Kbps	512
采样率/MHz	3.84
信噪比/dB	大于15
采样时间/s	≈2

识别算法	识别准确率/%
ITD	63.03
EMD	55.14
ResNet	80.77
CBAMResBlock	75.34
DDAM-ResNet	82.64