-
摘要:
关于辐射源射频指纹识别(RFFI)研究通常被视为一个典型的闭集分类问题，但在非合作空间中，辐射源都是事先未知的，所以闭集分类算法很难适用。针对这一问题，本文提出一种面向非合作空间辐射源专家模型自扩展的开集识别方法，可自扩展识别非合作空间中的未知辐射源。首先利用开集方法对已知/未知辐射源样本进行识别，通过样本库构建形成若干独立辐射源识别专家模型；其次提出一种模型解耦式联邦策略，用于辐射源识别专家模型自扩展，使得专家模型能够在线持续学习(CL)空间中的辐射源样本，有效克服了传统辐射源识别模型设计中出现的无法自动学习识别新辐射源样本和易发生灾难性遗忘等问题；最后，采用样本均衡和交织技术提升专家模型对辐射源指纹特征的特异性，从而确保各专家模型快速收敛和保持对特定辐射源识别高泛化能力。实验表明：所提方法在5 dB信噪比(SNR)环境下对辐射源设备的分类准确率达到97.8%以上，27 dB信噪比环境下可达到100%的准确率。
Abstract:The research on radio frequency fingerprint identification (RFFI) of radiation sources is usually regarded as a typical closed-set classification problem. However, in the non-cooperative space, the radiation sources are unknown, so the closed-set classification algorithm is inapplicable. To solve this problem, this paper proposed an open set recognition (OSR) method for the expert model self-extension of non-cooperative space radiation sources, which can self-expand to identify unknown radiation sources in non-cooperative space. Firstly, the open set method was used to identify the known/unknown radiation source samples, and several independent radiation source identification expert models were formed through the sample library construction. Secondly, a model decoupling federation strategy was proposed for the expert model self-expansion of radiation source identification, which ensured the online continual learning (CL) of the expert model on the radiation source samples in space, effectively overcoming the problems in the traditional radiation source identification model design, such as the inability to automatically learn and identify new radiation source samples and the vulnerability to catastrophic forgetting. Finally, the sample balance and interleaving techniques were used to enhance the specificity of expert models for fingerprint features of radiation sources to ensure the rapid convergence of expert models and maintain the high-generalization ability for specific radiation source identification. The experimental results show that the classification accuracy of the proposed method on the radiation source equipment is more than 97.8% in the signal-to-noise (SNR) environment of 5 dB and 100% in the signal-to-noise environment of 27 dB.
-
图 2 16QAM信号经过信噪比为20 dB的高斯白噪声信道的IQ不平衡星座图
Figure 2. IQ imbalance constellation of 16QAM signal passing through Gaussian white noise channel with SNR of 20 dB
图 3 基于专家模型自扩展的开集辐射源识别架构
Figure 3. Open set radiation sources identification architecture based on expert model self-expansion
图 6
2000 个已知和未知辐射源样本输入$ {\phi _1} $对应的输出值Figure 6. Output values corresponding to 2 000 known and unknown radiation source samples with $ {\phi _1} $ input
图 7 2 000个已知和未知辐射源样本输入$ {\phi _2} $对应的输出值
Figure 7. Output values corresponding to 2 000 known and unknown radiation source samples with $ {\phi _2} $ input
图 10 4个辐射源在不同信噪比和采样率下的分类准确率
Figure 10. Classification accuracy of four radiation sources under different SNRs and sampling rates
图 11 辐射源的某一种调制信号训练及其他调制信号测试矩阵图
Figure 11. Matrix of training of a certain modulation signal of a radiation source and test of other modulation signals
表 1 5种调制信号闭集和开集测试
Table 1. Closed set and open set tests of five modulation signals
方法 16QAM 64QAM BPSK 8PSK CPFSK 闭集 1 1 1 1 1 Softmax+
Threshold0.654 0.632 0.672 0.667 0.583 Openmax 0.786 0.762 0.774 0.756 0.732 本文方法 0.992 0.984 0.991 0.982 0.979 
下载: 导出CSV
-
[1] DANEV B, ZANETTI D, CAPKUN S. On physical-layer identification of wireless devices[J]. ACM Computing Surveys, 2012, 45(1): 1-29. [2] 俞佳宝, 胡爱群, 朱长明, 等. 无线通信设备的射频指纹提取与识别方法[J]. 密码学报, 2016, 3(5): 433-446.YU J B, HU A Q, ZHU C M, et al. RF fingerprinting extraction and identification of wireless communication devices[J]. Journal of Cryptologic Research, 2016, 3(5): 433-446(in Chinese). [3] CHOE H C, POOLE C E, YU A M, et al. Novel identification of intercepted signals from unknown radio transmitters[C]//Proceedings Volume 2491, Wavelet Applications II. Orlando: SPIE, 1995: 504-517. [4] HALL J, BARBEAU M, KRANAKIS E. Detection of transient in radio frequency fingerprinting using signal phase[C]//Proceedings of the IASTED International Conference on Wireless and Optical Communications. Calgary: ACTA Press, 2003: 13-18. [5] ELLIS K J, SERINKEN N. Characteristics of radio transmitter fingerprints[J]. Radio Science, 2001, 36(4): 585-597. [6] KIM K, SPOONER C M, AKBAR I, et al. Specific emitter identification for cognitive radio with application to IEEE 802.11[C]//Proceedings of 2008 IEEE Global Telecommunications Conference. Piscataway: IEEE Press, 2008: 1-5. [7] 田金鹏, 刘燕平, 刘小娟. 基于瞬态强度的射频指纹识别方法[J]. 电子测量技术, 2016, 39(4): 58-61,65. doi: 10.3969/j.issn.1002-7300.2016.04.014TIAN J P, LIU Y P, LIU X J. RF fingerprinting method based on transient intensity[J]. Electronic Measurement Technology, 2016, 39(4): 58-61,65(in Chinese). doi: 10.3969/j.issn.1002-7300.2016.04.014 [8] 张敏, 罗正华, 黄建刚, 等. 一种基于I/Q失配的辐射源指纹提取方法[J]. 电子学报, 2020, 48(4): 717-722.ZHANG M, LUO Z H, HUANG J G, et al. A fingerprint extraction method based on I/Q imbalance[J]. Acta Electronica Sinica, 2020, 48(4): 717-722(in Chinese). [9] KENNEDY I O, SCANLON P, MULLANY F J, et al. Radio transmitter fingerprinting: A steady state frequency domain approach[C]//Proceedings of 2008 IEEE 68th Vehicular Technology Conference. Piscataway: IEEE Press, 2008: 1-5. [10] BRIK V, BANERJEE S, GRUTESER M, et al. Wireless device identification with radiometric signatures[C]// Proceedings of the 14th ACM International Conference on Mobile Computing and Networking. New York: ACM, 2008: 116-127. [11] HUANG G Q, YUAN Y J, WANG X, et al. Specific emitter identification based on nonlinear dynamical characteristics[J]. Canadian Journal of Electrical and Computer Engineering, 2016, 39(1): 34-41. doi: 10.1109/CJECE.2015.2496143 [12] 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(in Chinese). [13] 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.2017299REN 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(in Chinese). doi: 10.11959/j.issn.1000-436x.2017299 [14] TU Y, UN Y, WANG J, et al. Semi-supervised learning with generative adversarial networks on digital signal modulation classification[J]. Computers Materials & Continua, 2018, 55(2): 243-254. [15] 张思成, 林云, 涂涯, 等. 基于轻量级深度神经网络的电磁信号调制识别技术[J]. 通信学报, 2020, 41(11): 12-21. doi: 10.11959/j.issn.1000-436x.2020237ZHANG S C, LIN Y, TU Y, et al. Electromagnetic signal modulation recognition technology based on lightweight deep neural network[J]. Journal on Communications, 2020, 41(11): 12-21(in Chinese). doi: 10.11959/j.issn.1000-436x.2020237 [16] HOU C B, ZHANG X, CHEN X. Electromagnetic signal feature fusion and recognition based on multi-modal deep learning[J]. International Journal of Performability Engineering, 2020, 16(6): 941. doi: 10.23940/ijpe.20.06.p12.941949 [17] LIN Y, WANG M Y, ZHOU X L, et al. Dynamic spectrum interaction of UAV flight formation communication with priority: A deep reinforcement learning approach [J]. IEEE Transactions on Cognitive Communications and Networking, 2020, 6(3): 892-903. [18] 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 [19] ZHANG J Q, WOODS R, SANDELL M, et al. Radio frequency fingerprint identification for narrowband systems, modelling and classification[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 3974-3987. doi: 10.1109/TIFS.2021.3088008 [20] WONG L J, HEADLEY W C, ANDREWS S, et al. Clustering learned CNN features from raw I/Q data for emitter identification[C]//Proceedings of 2018 IEEE Military Communications Conference. Piscataway: IEEE Press, 2018: 26-33. [21] LI Y B. Frequency dependent IQ imbalance estimation and compensation[M]//LI Y B. In-Phase and Quadrature Imbalance: Modeling, Estimation, and Compensation. New York: Springer New York, 2013: 49-62. [22] INTI D L N S. Time-varying frequency selective IQ imbalance estimation and compensation[D]. Virginia: Virginia Polytechnic Institute and State University, 2017. [23] KARL P. On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling[M]//KOTZ S, JOHNSON N L. Breakthroughs in Statistics Volume II: Methodology and Distribution. New York: Springer New York, 1992: 11-28. -
下载:
点击查看大图
计量
- 文章访问数: 227
- HTML全文浏览量: 84
- PDF下载量: 5
- 被引次数: 0
