基于残差原型网络的辐射源个体识别

doi:10.12305/j.issn.1001-506X.2023.07.36

摘要/Abstract

摘要：

利用深度学习进行通信辐射源识别分类时, 现有算法在较低信噪比下的识别能力还不足, 且均着重关注各类辐射源个体的类间距离, 忽视了类内紧密性。针对此问题, 结合残差网络和原型学习基本思想, 提出残差原型网络, 对输入信号的差分星座轨迹图进行识别。此外, 在基于距离的交叉熵损失函数基础上加入原型损失, 通过提高类内紧密度的方式进一步扩增了类间距离。通过对5种ZigBee设备的实验, 结果表明所提算法在相同信噪比条件下相较于其他算法具有更好的识别性能, 在信噪比高于8 dB时, 可达到99%以上的准确率。

关键词: 残差原型网络, 原型学习, 辐射源个体识别, 差分星座轨迹图

Abstract:

When deep learning methods are used for specific emitter identification, the existing algorithms are insufficient under the low signal to noise ratio. Meanwhile, they all focus on the inter-class distance but ignore the intra-class compactness. To solve this problem, a residual prototype network is proposed to recognize the differential constellation trace figure of input signals by combining the residual network and prototype learning. In addition, prototype loss is combinedwith the distance-based cross entropy loss to further amplify the inter-class distanceby improving the intra-class compactness. The results show that the proposed algorithm has better recognition performance under the same signal to noise ratio condition through experiments on five ZigBee devices. And the accuracy can reach more than 99% when the signal to noise ratio is higher than 8 dB.

Key words: residual prototype network, prototype learning, specific emitter identification, differential constellation trace figure

中图分类号:

TN975

王春升, 王永民, 许华, 朱华丽. 基于残差原型网络的辐射源个体识别[J]. 系统工程与电子技术, 2023, 45(7): 2249-2258.

Chunsheng WANG, Yongmin WANG, Hua XU, Huali ZHU. Specific emitter identification based on residual prototype network[J]. Systems Engineering and Electronics, 2023, 45(7): 2249-2258.

图/表 12

图1

图2

表1

图3

图4

图5

图6

图7

图8

图9

图10

图11

参考文献 37

1	BIHL T J , BAUER K W , TEMPLE M A . Feature selection for RF fingerprinting with multiple discriminant analysis and using ZigBee device emissions[J]. IEEE Trans.on Information Forensics and Security, 2017, 11 (8): 1862- 1874.
2	PATEL H J , TEMPLE M A , BALDWIN R O . Improving ZigBee device network authentication using ensemble decision tree classifiers with radio frequency distinct native attribute fingerprinting[J]. IEEE Trans.on Reliability, 2015, 64 (1): 221- 233. doi: 10.1109/TR.2014.2372432
3	RAMSEY B W, TEMPLE M A, MULLINS B E. PHY foundation for multi-factor ZigBee node authentication[C]//Proc. of the IEEE Global Communications Conference, 2012: 795-800.
4	KENNEDY I O, SCANLON P, MULLANY F J. Radio transmitter fingerprinting: a steady state frequency domain approach[C]//Proc. of the 68th IEEE Vehicular Technology Conference, 2008.
5	HUANG N E , SHEN Z , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454 (1971): 903- 995. doi: 10.1098/rspa.1998.0193
6	XU S H, HUANG B X, XU L N, et al. Radio transmitter classification using a new method of stray features analysis combined with PCA[C]//Proc. of the IEEE Military Communications Conference, 2007.
7	刘明骞, 颜志文, 张俊林. 空中目标辐射源的个体识别方法[J]. 系统工程与电子技术, 2019, 41 (11): 2408- 2415.
	LIU M Q , YAN Z W , ZHANG J L . Specific emitter identification method for aerial target[J]. Systems Engineering and Electronics, 2019, 41 (11): 2408- 2415.
8	PENG L N, HU A Q, YU J B, et al. A differential constellation trace figure based device identification method for ZigBee nodes[C]//Proc. of the IEEE International Conference on Wireless Communications & Signal Processing, 2016.
9	彭林宁, 胡爱群, 朱长明, 等. 基于星座轨迹图的射频指纹提取方法[J]. 信息安全学报, 2016, 1 (1): 50- 58. doi: 10.19363/j.cnki.cn10-1380/tn.2016.01.007
	PENG L N , HU A Q , ZHU C M , et al. Radio frequency fingerprint extraction method based on constellation trace figure[J]. Journal of Information Security, 2016, 1 (1): 50- 58. doi: 10.19363/j.cnki.cn10-1380/tn.2016.01.007
10	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2021-10-02]. https://arxiv.org/abs/1409.1556.
11	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
12	王炳程. 通信设备指纹识别关键技术研究[D]. 成都: 电子科技大学, 2019.
	WANG B C. Research on key technology of fingerprint identification of communication equipment[D]. Chengdu: University of Electronic Science and Technology of China, 2019.
13	DING L D , WANG S L , WANG F G , et al. Specific emitter identification via convolutional neural networks[J]. IEEE Communications Letters, 2018, 22, 2591- 2594. doi: 10.1109/LCOMM.2018.2871465
14	WONG L J , HEADLEY W C , MICHAELS A J . Specific emitter identification using convolutional neural network-based IQ imbalance estimators[J]. IEEE Access, 2019, 7, 33544- 33555. doi: 10.1109/ACCESS.2019.2903444
15	MERCHANT K , REVAY S , STANTCHEV G , et al. Deep learning for RF device fingerprinting in cognitive communication networks[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12 (2): 160- 167.
16	SANKHE K , BELGIOVINE M , ZHOU F , et al. No radio left behind: radio fingerprinting through deep learning of physical-layer hardware impairments[J]. IEEE Trans.on Cognitive Communications and Networking, 2019, 6 (1): 165- 178.
17	QING G W , WANG H F , ZHANG T P . Radio frequency fingerprinting identification for Zigbee via lightweight CNN[J]. Physical Communication, 2021, 44 (1): 101250.
18	ZHOU X Y , HU A Q , LI G Y , et al. A robust radio-frequency fingerprint extraction scheme for practical device recognition[J]. IEEE Internet of Things Journal, 2021, 8 (14): 11276- 11289. doi: 10.1109/JIOT.2021.3051402
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 MILCOM IEEE Military Communications Conference, 2018: 26-33.
20	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. Communication emitter individual identification based on stacked LSTM network[J]. Systems Engineering and Electronics, 2020, 42 (12): 2915- 2923. doi: 10.3969/j.issn.1001-506X.2020.12.30
21	秦嘉. 基于深度学习的通信辐射源个体识别[D]. 北京: 北京邮电大学, 2019.
	QIN J. Individual identification of communication radiators based on deep learning[D]. Beijing: Beijing University of Posts and Telecommunications, 2019.
22	LIU Y H , XU H , QI Z S , et al. Specific emitter identification against unreliable features interference based on time-series classification network structure[J]. IEEE Access, 2020, 8, 200194- 200208. doi: 10.1109/ACCESS.2020.3035813
23	WANG Y , GUI G , GACANIN H , et al. An efficient specific emitter identification method based on complex-valued neural networks and network compression[J]. IEEE Journal on Selected Areas in Communications, 2021, 39 (8): 2305- 2317. doi: 10.1109/JSAC.2021.3087243
24	WANG S H , JIANG H L , FANG X F , et al. Radio frequency fingerprint identification based on deep complex residual network[J]. IEEE Access, 2020, 8, 204417- 204424. doi: 10.1109/ACCESS.2020.3037206
25	牛伟宇, 许华, 刘英辉, 等. 基于PACGAN与差分星座轨迹图的辐射源个体识别[J]. 信号处理, 2021, 37 (8): 1559- 1567.
	NIU W Y , XU H , LIU Y H , et al. Individual identification method based on PACGAN and differential constellation trace figure[J]. Signal Processing, 2021, 37 (8): 1559- 1567.
26	方章闻, 张金艺, 李科, 等. 小样本条件下的通信辐射源半监督特征提取[J]. 系统工程与电子技术, 2020, 42 (10): 2381- 2389. doi: 10.3969/j.issn.1001-506X.2020.10.29
	FANG Z W , ZHANG J Y , LI K , et al. Semi-supervised feature extraction of communication emitter under small sample condition[J]. Systems Engineering and Electronics, 2020, 42 (10): 2381- 2389. doi: 10.3969/j.issn.1001-506X.2020.10.29
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 . Communication transmitter individual identification based on deep residual adaptation network[J]. Systems Engineering and Electronics, 2021, 43 (3): 603- 609.
28	PAN Y W , YANG S H , PENG H . Specific emitter identification based on deep residual networks[J]. IEEE Access, 2019, 7, 54425- 54434. doi: 10.1109/ACCESS.2019.2913759
29	PENG L N , ZHANG J Q , LIU M , et al. Deep learning based RF fingerprint identification using differential constellation trace figure[J]. IEEE Trans.on Vehicular Technology, 2020, 69 (1): 1091- 1095. doi: 10.1109/TVT.2019.2950670
30	SNELL J , SWERSKY K , ZEMEL R S . Prototypical networks for few-shot learning[J]. Advances in Neural Information Processing Systems, 2017, 30, 4077- 4087.
31	STANISLAV F. Gaussian prototypical networks for few-shot learning on omniglot[EB/OL]. [2021-10-02]. https://arxiv.org/abs/1708.02735.
32	YANG H M, ZHANG X Y, YIN F, et al. Robust classification with convolutional prototype learning[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 3474-3482.
33	YANG H M , ZHANG X Y , YIN F , et al. Convolutional prototype network for open set recognition[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2020, 44 (5): 2385- 2370.
34	SHU Y , SHI Y M , WANG Y W , et al. P-ODN: prototype-based open deep network for open set recognition[J]. Scientific Reports, 2020, 10, 7146.
35	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.
36	LIU C L , NAKAGAWA M . Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition[J]. Pattern Recognition, 2001, 34 (3): 601- 615.
37	IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proc. of the 32nd International Conference on Machine Learning, 2015: 448-456.

网络结构	内部组成	输出
卷积模块1	[3×3, 64]×1	S×S维特征
卷积模块2	$ \left[\begin{array}{l}3 \times 3, 64 \\3 \times 3, 64\end{array}\right] \times 3$	S×S维特征
卷积模块3	$ \left[\begin{array}{l}3 \times 3, 128 \\ 3 \times 3, 128\end{array}\right] \times 4$	$ \frac{S}{2} \times \frac{S}{2}$维特征
卷积模块4	$ \left[\begin{array}{l}3 \times 3, 256 \\ 3 \times 3, 256\end{array}\right] \times 6 $	$ \frac{S}{4} \times \frac{S}{4}$维特征
卷积模块5	$ \left[\begin{array}{l}3 \times 3, 512 \\ 3 \times 3, 512\end{array}\right] \times 3 $	$ \frac{S}{8} \times \frac{S}{8}$维特征
卷积模块6	$ \left[\begin{array}{l}3 \times 3, 512 \\ 3 \times 3, 512\end{array}\right] \times 3 $	$ \frac{S}{16} \times \frac{S}{16}$维特征
池化层	自适应平均池化	1×1维特征
全连接层	(512, 2)	2维特征
损失函数	DCEL+PL	d, η, a_i

[1]	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.
[2]	吴子龙, 陈红, 雷迎科, 李昕, 熊颢. 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.
[3]	方章闻, 张金艺, 李科, 姜玉稀. 小样本条件下的通信辐射源半监督特征提取[J]. 系统工程与电子技术, 2020, 42(10): 2381-2389.
[4]	刘明骞, 颜志文, 张俊林. 空中目标辐射源的个体识别方法[J]. 系统工程与电子技术, 2019, 41(11): 2408-2415.
[5]	王桂良, 黄渊凌. 多普勒及多普勒变化率对辐射源个体识别性能的影响分析[J]. 系统工程与电子技术, 2017, 39(12): 2671-2676.