To address challenges such as the difficulty in correcting time-varying amplitude-phase errors caused by polarization multi-channel reception, the difficulty in obtaining the number of radiation sources in non-cooperative monitoring scenarios, and the poor performance of polarization feature extraction and clustering under low signal-to-noise ratio conditions, this paper proposes an efficient blind clustering algorithm for polarization features of communication radiation sources. First, a single-channel time-division dual-polarization reception system is designed to mitigate the adverse impact of amplitude-phase errors across multiple reception channels on polarization feature extraction, thereby enhancing the estimation quality of individual communication radiation source polarization characteristics. Simultaneously, leveraging the adaptive mechanism of the Affinity Propagation algorithm, the number of radiation sources is accurately estimated using minimal data. Building upon this foundation, a deep neural network capable of rapidly extracting latent correlation features between polarization amplitude and phase is designed, incorporating deep embedded learning principles. The Kullback-Leibler divergence between the initial distribution of polarization features and the target distribution is calculated, enabling adaptive clustering of individual communication radiation sources. Testing with simulation data and anechoic chamber measurements demonstrates that the proposed algorithm achieves communication radiation source clustering under conditions of unknown source count. Both clustering efficiency and average accuracy surpass existing algorithms, fully validating the novel approach's effectiveness.
[1] 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(1): 160-167.
[2] RU X H, LIU Z, JIANG W L, 等. Recognition performance analysis of instantaneous phase and its transformed features for radar emitter identification[J/OL]. IET Radar, Sonar and Navigation, 2016, 10(5): 945-952. DOI:10.1049/iet-rsn.2014.0512.
[3] ZHANG T, CHEN J, LI F, 等. Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions[J/OL]. ISA Transactions, 2022, 119: 152-171. DOI:10.1016/j.isatra.2021.02.042.
[4] 郑娜娥, 王盛, 张靖志, 等. 基于射频指纹的辐射源个体识别技术综述[J]. 信息工程大学学报, 2020, 21(3): 285-289.
ZHENG N E, WANG S, ZHANG J Z, et al. Review of Individual Identification Technology of Radiation Source Based on RF Fingerprint[J]. Journal of Information Engineering University, 2020, 21(3): 285-289 (in Chinese).
[5] 孙丽婷, 黄知涛, 王翔, 等. 辐射源指纹特征提取方法述评[J]. 雷达学报, 2020, 9(6): 1014-1031.
SUN L T, HUANG Z T, WANG X, et al. A Review of Feature Extraction Methods for Radiation Source Fingerprints[J]. Journal of Radars, 2020, 9(6): 1014-1031 (in Chinese).
[6] 韦建宇, 俞璐. 通信辐射源个体识别中的特征提取方法综述[J]. 通信技术, 2022, 55(6): 681-687.
WEI J Y, YU L. Survey of Feature Extraction Methods in Individual Identification of Communication Radiation Sources[J]. Communications Technology, 2022, 55(6): 681-687 (in Chinese).
[7] Luo Z, Cao Y, Yeo T S, et al. Few-shot radar jamming recognition network via time-frequency self-attention and global knowledge distillation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 1-12.
[8] Zhen P, Zhang B, Chen Z, et al. Spectrum sensing method based on wavelet transform and residual network[J]. IEEE Wireless Communications Letters, 2022, 11(12): 2517-2521.
[9] 陈蒙, 邢小鹏, 陈世文, 等. 基于贝塞尔曲线的雷达信号脉内无意调相特征提取及个体识别[J]. 信息工程大学学报, 2022, 23(1): 9-17 (in Chinese).
CHEN M, XING X P, CHEN S W, et al. Unintentional phase modulation on pulse feature extraction and radar specific emitter identification based on Bezier curve[J]. Journal of Information Engineering University, 2022, 23(1): 9-17 (in Chinese).
[10] 秦鑫, 黄洁, 王建涛, 等. 基于无意调相特性的雷达辐射源个体识别[J]. 通信学报, 2020, 41(5).
HUANG X, HUANG J, WANG J T, et al. Radar emitter identification based on unintentional phase modulation on pulse characteristic[J]. Journal on Communications, 2020, 41(5): 104-111 (in Chinese).
[11] Ru X, Ye H, Liu Z, et al. An experimental study on secondary radar transponder UMP characteristics[C]// 2016 European radar conference (EuRAD). IEEE, 2016: 314-317.
[12] Peng L, Zhang J, Liu M, et al. Deep learning based RF fingerprint identification using differential constellation trace figure[J]. IEEE Transactions on Vehicular Technology, 2019, 69(1): 1091-1095.
[13] 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.
[14] Gan J, Du Z, Li Q, et al. Cost-effective RF fingerprinting based on hybrid CVNN-RF classifier with automated multidimensional early-exit strategy[J]. IEEE Internet of Things Journal, 2024, 11(20): 32557-32571.
[15] Dreifuerst R M, Graff A, Kumar S, et al. End-to-End Radio Fingerprinting with Neural Networks[J]. arXiv preprint arXiv:2010.05169, 2020.
[16] Khalid U, Karim N, Rahnavard N. Rf signal transformation and classification using deep neural networks[C]//Big Data IV: Learning, Analytics, and Applications. SPIE, 2022, 12097: 51-57.
[17] Shen G, Zhang J, Marshall A, et al. Toward length-versatile and noise-robust radio frequency fingerprint identification[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 2355-2367.
[18] 陈翔, 汪连栋, 许雄, 等. 基于 Raw I/Q 和深度学习的射频指纹识别方法综述[J]. 雷达学报, 2022, 12(1): 214-234.
CHEN X, WANG L D, XU X, et al. A review of radio frequency fingerprinting methods based on Raw I/Q and deep learning[J]. Journal of Radars, 2022, 12(1): 214-234 (in Chinese).
[19] 张梓轩,齐子森,许华,等.采用极化特征的通信辐射源个体识别方法[J].西安交通大学学报,2023,57(10):207-220.
ZHANG Z X, QI Z S, XU H, et al. Individual Identification Method of Communication Radiation Source Using Polarization Features[J]. Journal of Xi'an Jiaotong University, 2023, 57(10): 207-220 (in Chinese).
[20] WANG K, ZHANG J, LI D, et al. Adaptive affinity propagation clustering[A/OL]. arXiv, 2008[2025-05-06]. DOI:10.48550/arXiv.0805.1096.
[21] Xie J, Girshick R, Farhadi A. Unsupervised deep embedding for clustering analysis[C]//International conference on machine learning. PMLR, 2016: 478-487.
[22] 齐子森, 张梓轩, 许华, 等. 利用无线电极化特征的跳频网台分选方法[J]. 电 子 与 信 息 学 报, 2024, 46: 4.
QI Z, ZHANG Z, XU H, et al. Frequency-Hopping Network Station Sorting Method Using Radio Polarization Characteristics[J]. 电子与信息学报, 2024, 46(4): 1286-1295 (in Chinese).
CJA