通信特定辐射源识别的多特征融合分类方法

doi:10.11959/j.issn.1000-436x.2021028

摘要/Abstract

摘要：

针对通信辐射源个体识别问题，提出了一种基于多通道变换投影、集成深度学习和生成对抗网络的融合分类方法。首先，通过对原始信号进行多种变换得到三维特征图像，据此构建信号的时频域投影以构建特征数据集，并使用生成对抗网络对数据集进行扩充。然后，设计了一种基于多特征融合的双阶段识别分类方法，利用神经网络初级分类器分别对3类特征数据集进行学习，得到初始分类结果。最后，通过叠加融合学习初始分类结果，得到最终的分类结果。实测数据分析结果证明，所提方法相比基于单一特征提取方法和经典多特征提取方法有更高的准确率，使用室外典型场景多径衰落信道模型对辐射源信号进行了处理，所提模型仍可进行有效识别，能够适用于复杂无线信道环境的应用。

关键词: 特定辐射源识别, 生成对抗网络, 多特征融合, 集成学习

Abstract:

A multi-feature fusion classification method based on multi-channel transform projection, integrated deep learning and generative adversarial network (GAN) was proposed for communication specific emitter identification.First, three-dimensional feature images were obtained by performing various transformations, the time and frequency domain projection of the signal was constructed to construct the feature datasets.GAN was used to expand the datasets.Then, a two-stage recognition and classification method based on multi-feature fusion was designed.Deep neural networks were used to learn the three feature datasets, and the initial classification results were obtained.Finally, through fusion and re-learning of the initial classification result, the final classification result was obtained.Based on the measurement and analysis of the actual signals, the experimental results show that the method has higher accuracy than the single feature extraction method.The multipath fading channel has been used to simulate the outdoor propagation environment, and the method has certain generalization performance to adapt to the complex wireless channel environments.

Key words: specific emitter identification, generative adversarial network, multi-feature fusion, ensemble learning

中图分类号:

TN911.7

何遵文, 侯帅, 张万成, 张焱. 通信特定辐射源识别的多特征融合分类方法[J]. 通信学报, 2021, 42(2): 103-112.

Zunwen HE, Shuai HOU, Wancheng ZHANG, Yan ZHANG. Multi-feature fusion classification method for communication specific emitter identification[J]. Journal on Communications, 2021, 42(2): 103-112.

图/表 8

图1

图2

图3

图4

表1

图5

图6

图7

参考文献 29

[1]	LANGLEY L E , . Specific emitter identification (SEI) and classical parameter fusion technology[C]// Proceedings of WESCON’93. Piscataway:IEEE Press, 2002: 377-381.
[2]	桂冠, 王禹, 黄浩 . 基于深度学习的物理层无线通信技术:机遇与挑战[J]. 通信学报, 2019,40(2): 19-23.
	GUI G , WANG Y , HUANG H . Deep learning based physical layer wireless communication techniques:opportunities and challenges[J]. Journal on Communications, 2019,40(2): 19-23.
[3]	曾勇虎, 陈翔, 林云 ,等. 射频指纹识别的研究现状及趋势[J]. 电波科学学报, 2020,35(3): 305-315.
	ZENG Y H , CHEN X , LIN Y ,et al. Review of radio frequency fingerprinting identification[J]. Chinese Journal of Radio Science, 2020,35(3): 305-315.
[4]	WANG W , LIU H , YANG J ,et al. Specific emitter identification using decomposed hierarchical feature extraction methods[C]// International Conference on Natural Computation. Piscataway:IEEE Press, 2017: 1639-1643.
[5]	MCGINTHY J M , WONG L J , MICHAELS A J . Groundwork for neural network-based specific emitter identification authentication for IoT[J]. IEEE Internet of Things Journal, 2019,6(4): 6429-6440.
[6]	ROBINSON J , KUZDEBA S , STANKOWICZ J ,et al. Dilated causal convolutional model for RF fingerprinting[C]// Computing and Communication Workshop and Conference. Piscataway:IEEE Press, 2020: 157-162.
[7]	WONG L J , HEADLRY W C , MICHAELS A J . Specific emitter identification using convolutional neural network-based IQ imbalance estimators[J]. IEEE Access, 2019,7: 33544-33555.
[8]	GONG J , XU X , QIN Y ,et al. A generative adversarial network based framework for specific emitter characterization and identification[C]// 2019 11th International Conference on Wireless Communications and Signal Processing. Piscataway:IEEE Press, 2019: 1-6.
[9]	DENG S , HUANG Z , WANG X . A novel specific emitter identification method based on radio frequency fingerprints[C]// 2017 2nd IEEE International Conference on Computational Intelligence and Applications. Piscataway:IEEE Press, 2017: 368-371.
[10]	CHEN P , XU K , LI G ,et al. Local frechet distance in specific emitter identification[C]// 2017 IEEE 9th International Conference on Communication Software and Networks. Piscataway:IEEE Press, 2017: 842-845.
[11]	WANG H , ZHANG T . Specific emitter identification based on fractal and wavelet theories[C]// IEEE Advanced Information Technology Electronic and Automation Control Conference. Piscataway:IEEE Press, 2017: 1613-1617.
[12]	WU L , ZHAO Y , WANG Z ,et al. Specific emitter identification using fractal features based on box-counting dimension and variance dimension[C]// IEEE International Symposium on Signal Processing ＆ Information Technology. Piscataway:IEEE Press, 2017: 226-231.
[13]	HUANG G , YUAN Y , WANG X ,et al. Specific emitter identification based on nonlinear dynamical characteristics[J]. Canadian Journal of Electrical ＆ Computer Engineering, 2016,39(1): 34-41.
[14]	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.
	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.
[15]	BERTONCINI C , RUDD K , NOUSAIN B ,et al. Wavelet fingerprinting of radio-frequency identification (RFID) tags[J]. IEEE Transactions on Industrial Electronics, 2012,59(12): 4843-4850.
[16]	KONG M , ZHANG J , LIU W ,et al. Radar emitter identification based on deep convolutional neural network[C]// International Conference on Control and Automation. Piscataway:IEEE Press, 2018: 309-314.
[17]	YE W , PENG C . Recognition algorithm of emitter signals based on PCA+CNN[C]// 2018 IEEE 3rd Advanced Information Technology,Electronic and Automation Control Conference. Piscataway:IEEE Press, 2018: 2410-2414.
[18]	韩洁, 张涛, 王欢欢 ,等. 基于3D-Hibert能量谱和多尺度分形特征的通信辐射源个体识别[J]. 通信学报, 2017,38(4): 99-109.
	HAN J , ZHANG T , WANG H H ,et al. Communication emitter individual identification based on 3D-Hibert energy spectrum and multi-scale fractal features[J]. Journal on Communications, 2017,38(4): 99-109.
[19]	PAN Y , YANG S , PENG H ,et al. Specific emitter identification based on deep residual networks[J]. IEEE Access, 2019,7: 54425-54434.
[20]	ZHANG J , WANG F , DOBRE O A ,et al. Specific emitter identification via Hilbert-Huang transform in single-hop and relaying scenarios[J]. IEEE Transactions on Information Forensics and Security, 2016,11(6): 1192-1205.
[21]	HAN J , ZHANG T , REN D ,et al. Communication emitter identification based on distribution of bispectrum amplitude and phase[J]. Measurement ＆ Technology,IET, 2017,11(8): 1104-1112.
[22]	DING L , WANG S , WANG F ,et al. Specific emitter identification via convolutional neural networks[J]. IEEE Communications Letters, 2018,22(12): 2591-2594.
[23]	ZHANG X , LUO P , HU X ,et al. A hybrid method for classification and identification of emitter signals[C]// International Conference on Systems ＆ Informatics. Piscataway:IEEE Press, 2017: 1060-1065.
[24]	SA K , LANG D , WANG C ,et al. Specific emitter identification techniques for the Internet of things[J]. IEEE Access, 2019,8: 1644-1652.
[25]	齐建文, 陈慧贤, 吴彦华 ,等. 通信辐射源信号细微特征分析与处理[M]. 北京: 国防工业出版社, 2015.
	QI J W , CHEN H X , WU Y H ,et al. Analysis and processing of the subtle features of communication emitter signal[M]. Beijing: National Defense Industry Press, 2015.
[26]	唐哲, 雷迎科 . 基于最大相关熵的通信辐射源个体识别方法[J]. 通信学报, 2016,37(12): 171-175.
	TANG Z , LEI Y K . Method of individual communication transmitter identification based on maximum correntropy[J]. Journal on Communications, 2016,37(12): 171-175.
[27]	YU J , HE Z , ZHANG Y . A modulation recognition method based on bispectrum and DNN[C]// International Conference on Communications,Signal Processing,and Systems. Piscataway:IEEE Press, 2018: 898-906.
[28]	HE K , ZHANG X , REN S ,et al. Deep residual learning for image recognition[C]// IEEE Conference on Computer Vision ＆ Pattern Recognition. Piscataway:IEEE Press, 2016: 770-778.
[29]	FADUL M , REISING D , LOVELESS D ,et al. RF-DNA fingerprint classification of OFDM signals using a rayleigh fading channel model[C]// 2019 IEEE Wireless Communications and Networking Conference. Piscataway:IEEE Press, 2019: 1-7.

方法	5 dB	10 dB	15 dB	20 dB	25 dB
本文方法	60.5%	74.4%	85.5%	94.3%	96.2%
对比方法1	56.2%	67.3%	81.5%	91.2%	92%
对比方法2	48.8%	56.4%	67.8%	78.3%	82.2%
对比方法3	38.2%	46.3%	55.4%	58.5%	61.7%